768 files changed, 41258 insertions, 25932 deletions

diff --git a/fs/9p/acl.c b/fs/9p/acl.c
index b3c2cc79c20d..082d227fa56b 100644
--- a/fs/9p/acl.c
+++ b/fs/9p/acl.c
@@ -277,6 +277,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
 	case ACL_TYPE_ACCESS:
 		if (acl) {
 			struct iattr iattr;
+			struct posix_acl *old_acl = acl;
 
 			retval = posix_acl_update_mode(inode, &iattr.ia_mode, &acl);
 			if (retval)
@@ -287,6 +288,7 @@ static int v9fs_xattr_set_acl(const struct xattr_handler *handler,
 				 * by the mode bits. So don't
 				 * update ACL.
 				 */
+				posix_acl_release(old_acl);
 				value = NULL;
 				size = 0;
 			}
diff --git a/fs/9p/fid.c b/fs/9p/fid.c
index 60fb47469c86..ed4f8519b627 100644
--- a/fs/9p/fid.c
+++ b/fs/9p/fid.c
@@ -91,10 +91,10 @@ static struct p9_fid *v9fs_fid_find(struct dentry *dentry, kuid_t uid, int any)
  * dentry names.
  */
 static int build_path_from_dentry(struct v9fs_session_info *v9ses,
-				  struct dentry *dentry, char ***names)
+				  struct dentry *dentry, const unsigned char ***names)
 {
 	int n = 0, i;
-	char **wnames;
+	const unsigned char **wnames;
 	struct dentry *ds;
 
 	for (ds = dentry; !IS_ROOT(ds); ds = ds->d_parent)
@@ -105,7 +105,7 @@ static int build_path_from_dentry(struct v9fs_session_info *v9ses,
 		goto err_out;
 
 	for (ds = dentry, i = (n-1); i >= 0; i--, ds = ds->d_parent)
-		wnames[i] = (char  *)ds->d_name.name;
+		wnames[i] = ds->d_name.name;
 
 	*names = wnames;
 	return n;
@@ -117,7 +117,7 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
 					       kuid_t uid, int any)
 {
 	struct dentry *ds;
-	char **wnames, *uname;
+	const unsigned char **wnames, *uname;
 	int i, n, l, clone, access;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid, *old_fid = NULL;
@@ -137,7 +137,7 @@ static struct p9_fid *v9fs_fid_lookup_with_uid(struct dentry *dentry,
 	fid = v9fs_fid_find(ds, uid, any);
 	if (fid) {
 		/* Found the parent fid do a lookup with that */
-		fid = p9_client_walk(fid, 1, (char **)&dentry->d_name.name, 1);
+		fid = p9_client_walk(fid, 1, &dentry->d_name.name, 1);
 		goto fid_out;
 	}
 	up_read(&v9ses->rename_sem);
diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c
index 072e7599583a..8fb89ddc6cc7 100644
--- a/fs/9p/v9fs.c
+++ b/fs/9p/v9fs.c
@@ -29,9 +29,11 @@
 #include <linux/errno.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/parser.h>
 #include <linux/idr.h>
 #include <linux/slab.h>
+#include <linux/seq_file.h>
 #include <net/9p/9p.h>
 #include <net/9p/client.h>
 #include <net/9p/transport.h>
@@ -81,6 +83,13 @@ static const match_table_t tokens = {
 	{Opt_err, NULL}
 };
 
+static const char *const v9fs_cache_modes[nr__p9_cache_modes] = {
+	[CACHE_NONE]	= "none",
+	[CACHE_MMAP]	= "mmap",
+	[CACHE_LOOSE]	= "loose",
+	[CACHE_FSCACHE]	= "fscache",
+};
+
 /* Interpret mount options for cache mode */
 static int get_cache_mode(char *s)
 {
@@ -103,6 +112,58 @@ static int get_cache_mode(char *s)
 	return version;
 }
 
+/*
+ * Display the mount options in /proc/mounts.
+ */
+int v9fs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct v9fs_session_info *v9ses = root->d_sb->s_fs_info;
+
+	if (v9ses->debug)
+		seq_printf(m, ",debug=%x", v9ses->debug);
+	if (!uid_eq(v9ses->dfltuid, V9FS_DEFUID))
+		seq_printf(m, ",dfltuid=%u",
+			   from_kuid_munged(&init_user_ns, v9ses->dfltuid));
+	if (!gid_eq(v9ses->dfltgid, V9FS_DEFGID))
+		seq_printf(m, ",dfltgid=%u",
+			   from_kgid_munged(&init_user_ns, v9ses->dfltgid));
+	if (v9ses->afid != ~0)
+		seq_printf(m, ",afid=%u", v9ses->afid);
+	if (strcmp(v9ses->uname, V9FS_DEFUSER) != 0)
+		seq_printf(m, ",uname=%s", v9ses->uname);
+	if (strcmp(v9ses->aname, V9FS_DEFANAME) != 0)
+		seq_printf(m, ",aname=%s", v9ses->aname);
+	if (v9ses->nodev)
+		seq_puts(m, ",nodevmap");
+	if (v9ses->cache)
+		seq_printf(m, ",%s", v9fs_cache_modes[v9ses->cache]);
+#ifdef CONFIG_9P_FSCACHE
+	if (v9ses->cachetag && v9ses->cache == CACHE_FSCACHE)
+		seq_printf(m, ",cachetag=%s", v9ses->cachetag);
+#endif
+
+	switch (v9ses->flags & V9FS_ACCESS_MASK) {
+	case V9FS_ACCESS_USER:
+		seq_puts(m, ",access=user");
+		break;
+	case V9FS_ACCESS_ANY:
+		seq_puts(m, ",access=any");
+		break;
+	case V9FS_ACCESS_CLIENT:
+		seq_puts(m, ",access=client");
+		break;
+	case V9FS_ACCESS_SINGLE:
+		seq_printf(m, ",access=%u",
+			   from_kuid_munged(&init_user_ns, v9ses->uid));
+		break;
+	}
+
+	if (v9ses->flags & V9FS_POSIX_ACL)
+		seq_puts(m, ",posixacl");
+
+	return p9_show_client_options(m, v9ses->clnt);
+}
+
 /**
  * v9fs_parse_options - parse mount options into session structure
  * @v9ses: existing v9fs session information
@@ -229,6 +290,7 @@ static int v9fs_parse_options(struct v9fs_session_info *v9ses, char *opts)
 			break;
 		case Opt_cachetag:
 #ifdef CONFIG_9P_FSCACHE
+			kfree(v9ses->cachetag);
 			v9ses->cachetag = match_strdup(&args[0]);
 #endif
 			break;
@@ -332,10 +394,6 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 		goto err_names;
 	init_rwsem(&v9ses->rename_sem);
 
-	rc = bdi_setup_and_register(&v9ses->bdi, "9p");
-	if (rc)
-		goto err_names;
-
 	v9ses->uid = INVALID_UID;
 	v9ses->dfltuid = V9FS_DEFUID;
 	v9ses->dfltgid = V9FS_DEFGID;
@@ -344,7 +402,7 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 	if (IS_ERR(v9ses->clnt)) {
 		rc = PTR_ERR(v9ses->clnt);
 		p9_debug(P9_DEBUG_ERROR, "problem initializing 9p client\n");
-		goto err_bdi;
+		goto err_names;
 	}
 
 	v9ses->flags = V9FS_ACCESS_USER;
@@ -414,8 +472,6 @@ struct p9_fid *v9fs_session_init(struct v9fs_session_info *v9ses,
 
 err_clnt:
 	p9_client_destroy(v9ses->clnt);
-err_bdi:
-	bdi_destroy(&v9ses->bdi);
 err_names:
 	kfree(v9ses->uname);
 	kfree(v9ses->aname);
@@ -444,8 +500,6 @@ void v9fs_session_close(struct v9fs_session_info *v9ses)
 	kfree(v9ses->uname);
 	kfree(v9ses->aname);
 
-	bdi_destroy(&v9ses->bdi);
-
 	spin_lock(&v9fs_sessionlist_lock);
 	list_del(&v9ses->slist);
 	spin_unlock(&v9fs_sessionlist_lock);
diff --git a/fs/9p/v9fs.h b/fs/9p/v9fs.h
index 443d12e02043..982e017acadb 100644
--- a/fs/9p/v9fs.h
+++ b/fs/9p/v9fs.h
@@ -67,6 +67,7 @@ enum p9_cache_modes {
 	CACHE_MMAP,
 	CACHE_LOOSE,
 	CACHE_FSCACHE,
+	nr__p9_cache_modes
 };
 
 /**
@@ -114,7 +115,6 @@ struct v9fs_session_info {
 	kuid_t uid;		/* if ACCESS_SINGLE, the uid that has access */
 	struct p9_client *clnt;	/* 9p client */
 	struct list_head slist; /* list of sessions registered with v9fs */
-	struct backing_dev_info bdi;
 	struct rw_semaphore rename_sem;
 };
 
@@ -138,6 +138,8 @@ static inline struct v9fs_inode *V9FS_I(const struct inode *inode)
 	return container_of(inode, struct v9fs_inode, vfs_inode);
 }
 
+extern int v9fs_show_options(struct seq_file *m, struct dentry *root);
+
 struct p9_fid *v9fs_session_init(struct v9fs_session_info *, const char *,
 									char *);
 extern void v9fs_session_close(struct v9fs_session_info *v9ses);
diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c
index 6a0f3fa85ef7..3de3b4a89d89 100644
--- a/fs/9p/vfs_file.c
+++ b/fs/9p/vfs_file.c
@@ -534,11 +534,11 @@ v9fs_mmap_file_mmap(struct file *filp, struct vm_area_struct *vma)
 }
 
 static int
-v9fs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+v9fs_vm_page_mkwrite(struct vm_fault *vmf)
 {
 	struct v9fs_inode *v9inode;
 	struct page *page = vmf->page;
-	struct file *filp = vma->vm_file;
+	struct file *filp = vmf->vma->vm_file;
 	struct inode *inode = file_inode(filp);
 
 
diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c
index f4f4450119e4..2a5de610dd8f 100644
--- a/fs/9p/vfs_inode.c
+++ b/fs/9p/vfs_inode.c
@@ -643,7 +643,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 		struct dentry *dentry, char *extension, u32 perm, u8 mode)
 {
 	int err;
-	char *name;
+	const unsigned char *name;
 	struct p9_fid *dfid, *ofid, *fid;
 	struct inode *inode;
 
@@ -652,7 +652,7 @@ v9fs_create(struct v9fs_session_info *v9ses, struct inode *dir,
 	err = 0;
 	ofid = NULL;
 	fid = NULL;
-	name = (char *) dentry->d_name.name;
+	name = dentry->d_name.name;
 	dfid = v9fs_parent_fid(dentry);
 	if (IS_ERR(dfid)) {
 		err = PTR_ERR(dfid);
@@ -788,7 +788,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *dfid, *fid;
 	struct inode *inode;
-	char *name;
+	const unsigned char *name;
 
 	p9_debug(P9_DEBUG_VFS, "dir: %p dentry: (%pd) %p flags: %x\n",
 		 dir, dentry, dentry, flags);
@@ -802,7 +802,7 @@ struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry,
 	if (IS_ERR(dfid))
 		return ERR_CAST(dfid);
 
-	name = (char *) dentry->d_name.name;
+	name = dentry->d_name.name;
 	fid = p9_client_walk(dfid, 1, &name, 1);
 	if (IS_ERR(fid)) {
 		if (fid == ERR_PTR(-ENOENT)) {
@@ -1012,7 +1012,7 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 	v9fs_blank_wstat(&wstat);
 	wstat.muid = v9ses->uname;
-	wstat.name = (char *) new_dentry->d_name.name;
+	wstat.name = new_dentry->d_name.name;
 	retval = p9_client_wstat(oldfid, &wstat);
 
 clunk_newdir:
@@ -1047,16 +1047,18 @@ done:
 
 /**
  * v9fs_vfs_getattr - retrieve file metadata
- * @mnt: mount information
- * @dentry: file to get attributes on
+ * @path: Object to query
  * @stat: metadata structure to populate
+ * @request_mask: Mask of STATX_xxx flags indicating the caller's interests
+ * @flags: AT_STATX_xxx setting
  *
  */
 
 static int
-v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		 struct kstat *stat)
+v9fs_vfs_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid;
 	struct p9_wstat *st;
diff --git a/fs/9p/vfs_inode_dotl.c b/fs/9p/vfs_inode_dotl.c
index 5999bd050678..70f9887c59a9 100644
--- a/fs/9p/vfs_inode_dotl.c
+++ b/fs/9p/vfs_inode_dotl.c
@@ -244,7 +244,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 	int err = 0;
 	kgid_t gid;
 	umode_t mode;
-	char *name = NULL;
+	const unsigned char *name = NULL;
 	struct p9_qid qid;
 	struct inode *inode;
 	struct p9_fid *fid = NULL;
@@ -269,7 +269,7 @@ v9fs_vfs_atomic_open_dotl(struct inode *dir, struct dentry *dentry,
 
 	v9ses = v9fs_inode2v9ses(dir);
 
-	name = (char *) dentry->d_name.name;
+	name = dentry->d_name.name;
 	p9_debug(P9_DEBUG_VFS, "name:%s flags:0x%x mode:0x%hx\n",
 		 name, flags, omode);
 
@@ -385,7 +385,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid = NULL, *dfid = NULL;
 	kgid_t gid;
-	char *name;
+	const unsigned char *name;
 	umode_t mode;
 	struct inode *inode;
 	struct p9_qid qid;
@@ -416,7 +416,7 @@ static int v9fs_vfs_mkdir_dotl(struct inode *dir,
 			 err);
 		goto error;
 	}
-	name = (char *) dentry->d_name.name;
+	name = dentry->d_name.name;
 	err = p9_client_mkdir_dotl(dfid, name, mode, gid, &qid);
 	if (err < 0)
 		goto error;
@@ -468,9 +468,10 @@ error:
 }
 
 static int
-v9fs_vfs_getattr_dotl(struct vfsmount *mnt, struct dentry *dentry,
-		 struct kstat *stat)
+v9fs_vfs_getattr_dotl(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid;
 	struct p9_stat_dotl *st;
@@ -678,14 +679,14 @@ v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry,
 {
 	int err;
 	kgid_t gid;
-	char *name;
+	const unsigned char *name;
 	struct p9_qid qid;
 	struct inode *inode;
 	struct p9_fid *dfid;
 	struct p9_fid *fid = NULL;
 	struct v9fs_session_info *v9ses;
 
-	name = (char *) dentry->d_name.name;
+	name = dentry->d_name.name;
 	p9_debug(P9_DEBUG_VFS, "%lu,%s,%s\n", dir->i_ino, name, symname);
 	v9ses = v9fs_inode2v9ses(dir);
 
@@ -699,7 +700,7 @@ v9fs_vfs_symlink_dotl(struct inode *dir, struct dentry *dentry,
 	gid = v9fs_get_fsgid_for_create(dir);
 
 	/* Server doesn't alter fid on TSYMLINK. Hence no need to clone it. */
-	err = p9_client_symlink(dfid, name, (char *)symname, gid, &qid);
+	err = p9_client_symlink(dfid, name, symname, gid, &qid);
 
 	if (err < 0) {
 		p9_debug(P9_DEBUG_VFS, "p9_client_symlink failed %d\n", err);
@@ -775,7 +776,7 @@ v9fs_vfs_link_dotl(struct dentry *old_dentry, struct inode *dir,
 	if (IS_ERR(oldfid))
 		return PTR_ERR(oldfid);
 
-	err = p9_client_link(dfid, oldfid, (char *)dentry->d_name.name);
+	err = p9_client_link(dfid, oldfid, dentry->d_name.name);
 
 	if (err < 0) {
 		p9_debug(P9_DEBUG_VFS, "p9_client_link failed %d\n", err);
@@ -812,7 +813,7 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 {
 	int err;
 	kgid_t gid;
-	char *name;
+	const unsigned char *name;
 	umode_t mode;
 	struct v9fs_session_info *v9ses;
 	struct p9_fid *fid = NULL, *dfid = NULL;
@@ -842,7 +843,7 @@ v9fs_vfs_mknod_dotl(struct inode *dir, struct dentry *dentry, umode_t omode,
 			 err);
 		goto error;
 	}
-	name = (char *) dentry->d_name.name;
+	name = dentry->d_name.name;
 
 	err = p9_client_mknod_dotl(dfid, name, mode, rdev, gid, &qid);
 	if (err < 0)
diff --git a/fs/9p/vfs_super.c b/fs/9p/vfs_super.c
index de3ed8629196..8b75463cb211 100644
--- a/fs/9p/vfs_super.c
+++ b/fs/9p/vfs_super.c
@@ -33,7 +33,6 @@
 #include <linux/string.h>
 #include <linux/inet.h>
 #include <linux/pagemap.h>
-#include <linux/seq_file.h>
 #include <linux/mount.h>
 #include <linux/idr.h>
 #include <linux/sched.h>
@@ -72,10 +71,12 @@ static int v9fs_set_super(struct super_block *s, void *data)
  *
  */
 
-static void
+static int
 v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 		int flags, void *data)
 {
+	int ret;
+
 	sb->s_maxbytes = MAX_LFS_FILESIZE;
 	sb->s_blocksize_bits = fls(v9ses->maxdata - 1);
 	sb->s_blocksize = 1 << sb->s_blocksize_bits;
@@ -85,7 +86,11 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 		sb->s_xattr = v9fs_xattr_handlers;
 	} else
 		sb->s_op = &v9fs_super_ops;
-	sb->s_bdi = &v9ses->bdi;
+
+	ret = super_setup_bdi(sb);
+	if (ret)
+		return ret;
+
 	if (v9ses->cache)
 		sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024)/PAGE_SIZE;
 
@@ -98,7 +103,7 @@ v9fs_fill_super(struct super_block *sb, struct v9fs_session_info *v9ses,
 		sb->s_flags |= MS_POSIXACL;
 #endif
 
-	save_mount_options(sb, data);
+	return 0;
 }
 
 /**
@@ -138,7 +143,9 @@ static struct dentry *v9fs_mount(struct file_system_type *fs_type, int flags,
 		retval = PTR_ERR(sb);
 		goto clunk_fid;
 	}
-	v9fs_fill_super(sb, v9ses, flags, data);
+	retval = v9fs_fill_super(sb, v9ses, flags, data);
+	if (retval)
+		goto release_sb;
 
 	if (v9ses->cache == CACHE_LOOSE || v9ses->cache == CACHE_FSCACHE)
 		sb->s_d_op = &v9fs_cached_dentry_operations;
@@ -340,7 +347,7 @@ static const struct super_operations v9fs_super_ops = {
 	.destroy_inode = v9fs_destroy_inode,
 	.statfs = simple_statfs,
 	.evict_inode = v9fs_evict_inode,
-	.show_options = generic_show_options,
+	.show_options = v9fs_show_options,
 	.umount_begin = v9fs_umount_begin,
 	.write_inode = v9fs_write_inode,
 };
@@ -351,7 +358,7 @@ static const struct super_operations v9fs_super_ops_dotl = {
 	.statfs = v9fs_statfs,
 	.drop_inode = v9fs_drop_inode,
 	.evict_inode = v9fs_evict_inode,
-	.show_options = generic_show_options,
+	.show_options = v9fs_show_options,
 	.umount_begin = v9fs_umount_begin,
 	.write_inode = v9fs_write_inode_dotl,
 };
diff --git a/fs/Kconfig b/fs/Kconfig
index 83eab52fb3f6..7aee6d699fd6 100644
--- a/fs/Kconfig
+++ b/fs/Kconfig
@@ -39,6 +39,7 @@ config FS_DAX
 	depends on MMU
 	depends on !(ARM || MIPS || SPARC)
 	select FS_IOMAP
+	select DAX
 	help
 	  Direct Access (DAX) can be used on memory-backed block devices.
 	  If the block device supports DAX and the filesystem supports DAX,
@@ -79,7 +80,6 @@ config EXPORTFS_BLOCK_OPS
 config FILE_LOCKING
 	bool "Enable POSIX file locking API" if EXPERT
 	default y
-	select PERCPU_RWSEM
 	help
 	  This option enables standard file locking support, required
           for filesystems like NFS and for the flock() system
diff --git a/fs/affs/affs.h b/fs/affs/affs.h
index 2f088773f1c0..773749be8290 100644
--- a/fs/affs/affs.h
+++ b/fs/affs/affs.h
@@ -7,7 +7,7 @@
 #include <linux/types.h>
 #include <linux/fs.h>
 #include <linux/buffer_head.h>
-#include <linux/amigaffs.h>
+#include "amigaffs.h"
 #include <linux/mutex.h>
 #include <linux/workqueue.h>
 
@@ -138,9 +138,9 @@ extern int	affs_remove_hash(struct inode *dir, struct buffer_head *rem_bh);
 extern int	affs_remove_header(struct dentry *dentry);
 extern u32	affs_checksum_block(struct super_block *sb, struct buffer_head *bh);
 extern void	affs_fix_checksum(struct super_block *sb, struct buffer_head *bh);
-extern void	secs_to_datestamp(time64_t secs, struct affs_date *ds);
-extern umode_t	prot_to_mode(u32 prot);
-extern void	mode_to_prot(struct inode *inode);
+extern void	affs_secs_to_datestamp(time64_t secs, struct affs_date *ds);
+extern umode_t	affs_prot_to_mode(u32 prot);
+extern void	affs_mode_to_prot(struct inode *inode);
 __printf(3, 4)
 extern void	affs_error(struct super_block *sb, const char *function,
 			   const char *fmt, ...);
@@ -162,6 +162,7 @@ extern void	affs_free_bitmap(struct super_block *sb);
 
 /* namei.c */
 
+extern const struct export_operations affs_export_ops;
 extern int	affs_hash_name(struct super_block *sb, const u8 *name, unsigned int len);
 extern struct dentry *affs_lookup(struct inode *dir, struct dentry *dentry, unsigned int);
 extern int	affs_unlink(struct inode *dir, struct dentry *dentry);
@@ -172,13 +173,12 @@ extern int	affs_link(struct dentry *olddentry, struct inode *dir,
 			  struct dentry *dentry);
 extern int	affs_symlink(struct inode *dir, struct dentry *dentry,
 			     const char *symname);
-extern int	affs_rename(struct inode *old_dir, struct dentry *old_dentry,
+extern int	affs_rename2(struct inode *old_dir, struct dentry *old_dentry,
 			    struct inode *new_dir, struct dentry *new_dentry,
 			    unsigned int flags);
 
 /* inode.c */
 
-extern unsigned long		 affs_parent_ino(struct inode *dir);
 extern struct inode		*affs_new_inode(struct inode *dir);
 extern int			 affs_notify_change(struct dentry *dentry, struct iattr *attr);
 extern void			 affs_evict_inode(struct inode *inode);
@@ -213,6 +213,12 @@ extern const struct address_space_operations	 affs_aops_ofs;
 extern const struct dentry_operations	 affs_dentry_operations;
 extern const struct dentry_operations	 affs_intl_dentry_operations;
 
+static inline bool affs_validblock(struct super_block *sb, int block)
+{
+	return(block >= AFFS_SB(sb)->s_reserved &&
+	       block < AFFS_SB(sb)->s_partition_size);
+}
+
 static inline void
 affs_set_blocksize(struct super_block *sb, int size)
 {
@@ -222,7 +228,7 @@ static inline struct buffer_head *
 affs_bread(struct super_block *sb, int block)
 {
 	pr_debug("%s: %d\n", __func__, block);
-	if (block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size)
+	if (affs_validblock(sb, block))
 		return sb_bread(sb, block);
 	return NULL;
 }
@@ -230,7 +236,7 @@ static inline struct buffer_head *
 affs_getblk(struct super_block *sb, int block)
 {
 	pr_debug("%s: %d\n", __func__, block);
-	if (block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size)
+	if (affs_validblock(sb, block))
 		return sb_getblk(sb, block);
 	return NULL;
 }
@@ -239,7 +245,7 @@ affs_getzeroblk(struct super_block *sb, int block)
 {
 	struct buffer_head *bh;
 	pr_debug("%s: %d\n", __func__, block);
-	if (block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size) {
+	if (affs_validblock(sb, block)) {
 		bh = sb_getblk(sb, block);
 		lock_buffer(bh);
 		memset(bh->b_data, 0 , sb->s_blocksize);
@@ -254,7 +260,7 @@ affs_getemptyblk(struct super_block *sb, int block)
 {
 	struct buffer_head *bh;
 	pr_debug("%s: %d\n", __func__, block);
-	if (block >= AFFS_SB(sb)->s_reserved && block < AFFS_SB(sb)->s_partition_size) {
+	if (affs_validblock(sb, block)) {
 		bh = sb_getblk(sb, block);
 		wait_on_buffer(bh);
 		set_buffer_uptodate(bh);
diff --git a/fs/affs/amigaffs.c b/fs/affs/amigaffs.c
index 0ec65c133b93..b573c3b9a328 100644
--- a/fs/affs/amigaffs.c
+++ b/fs/affs/amigaffs.c
@@ -367,7 +367,7 @@ affs_fix_checksum(struct super_block *sb, struct buffer_head *bh)
 }
 
 void
-secs_to_datestamp(time64_t secs, struct affs_date *ds)
+affs_secs_to_datestamp(time64_t secs, struct affs_date *ds)
 {
 	u32	 days;
 	u32	 minute;
@@ -386,55 +386,55 @@ secs_to_datestamp(time64_t secs, struct affs_date *ds)
 }
 
 umode_t
-prot_to_mode(u32 prot)
+affs_prot_to_mode(u32 prot)
 {
 	umode_t mode = 0;
 
 	if (!(prot & FIBF_NOWRITE))
-		mode |= S_IWUSR;
+		mode |= 0200;
 	if (!(prot & FIBF_NOREAD))
-		mode |= S_IRUSR;
+		mode |= 0400;
 	if (!(prot & FIBF_NOEXECUTE))
-		mode |= S_IXUSR;
+		mode |= 0100;
 	if (prot & FIBF_GRP_WRITE)
-		mode |= S_IWGRP;
+		mode |= 0020;
 	if (prot & FIBF_GRP_READ)
-		mode |= S_IRGRP;
+		mode |= 0040;
 	if (prot & FIBF_GRP_EXECUTE)
-		mode |= S_IXGRP;
+		mode |= 0010;
 	if (prot & FIBF_OTR_WRITE)
-		mode |= S_IWOTH;
+		mode |= 0002;
 	if (prot & FIBF_OTR_READ)
-		mode |= S_IROTH;
+		mode |= 0004;
 	if (prot & FIBF_OTR_EXECUTE)
-		mode |= S_IXOTH;
+		mode |= 0001;
 
 	return mode;
 }
 
 void
-mode_to_prot(struct inode *inode)
+affs_mode_to_prot(struct inode *inode)
 {
 	u32 prot = AFFS_I(inode)->i_protect;
 	umode_t mode = inode->i_mode;
 
-	if (!(mode & S_IXUSR))
+	if (!(mode & 0100))
 		prot |= FIBF_NOEXECUTE;
-	if (!(mode & S_IRUSR))
+	if (!(mode & 0400))
 		prot |= FIBF_NOREAD;
-	if (!(mode & S_IWUSR))
+	if (!(mode & 0200))
 		prot |= FIBF_NOWRITE;
-	if (mode & S_IXGRP)
+	if (mode & 0010)
 		prot |= FIBF_GRP_EXECUTE;
-	if (mode & S_IRGRP)
+	if (mode & 0040)
 		prot |= FIBF_GRP_READ;
-	if (mode & S_IWGRP)
+	if (mode & 0020)
 		prot |= FIBF_GRP_WRITE;
-	if (mode & S_IXOTH)
+	if (mode & 0001)
 		prot |= FIBF_OTR_EXECUTE;
-	if (mode & S_IROTH)
+	if (mode & 0004)
 		prot |= FIBF_OTR_READ;
-	if (mode & S_IWOTH)
+	if (mode & 0002)
 		prot |= FIBF_OTR_WRITE;
 
 	AFFS_I(inode)->i_protect = prot;
diff --git a/fs/affs/amigaffs.h b/fs/affs/amigaffs.h
new file mode 100644
index 000000000000..43b41c06aa37
--- /dev/null
+++ b/fs/affs/amigaffs.h
@@ -0,0 +1,144 @@
+#ifndef AMIGAFFS_H
+#define AMIGAFFS_H
+
+#include <linux/types.h>
+#include <asm/byteorder.h>
+
+#define FS_OFS		0x444F5300
+#define FS_FFS		0x444F5301
+#define FS_INTLOFS	0x444F5302
+#define FS_INTLFFS	0x444F5303
+#define FS_DCOFS	0x444F5304
+#define FS_DCFFS	0x444F5305
+#define MUFS_FS		0x6d754653   /* 'muFS' */
+#define MUFS_OFS	0x6d754600   /* 'muF\0' */
+#define MUFS_FFS	0x6d754601   /* 'muF\1' */
+#define MUFS_INTLOFS	0x6d754602   /* 'muF\2' */
+#define MUFS_INTLFFS	0x6d754603   /* 'muF\3' */
+#define MUFS_DCOFS	0x6d754604   /* 'muF\4' */
+#define MUFS_DCFFS	0x6d754605   /* 'muF\5' */
+
+#define T_SHORT		2
+#define T_LIST		16
+#define T_DATA		8
+
+#define ST_LINKFILE	-4
+#define ST_FILE		-3
+#define ST_ROOT		1
+#define ST_USERDIR	2
+#define ST_SOFTLINK	3
+#define ST_LINKDIR	4
+
+#define AFFS_ROOT_BMAPS		25
+
+struct affs_date {
+	__be32 days;
+	__be32 mins;
+	__be32 ticks;
+};
+
+struct affs_short_date {
+	__be16 days;
+	__be16 mins;
+	__be16 ticks;
+};
+
+struct affs_root_head {
+	__be32 ptype;
+	__be32 spare1;
+	__be32 spare2;
+	__be32 hash_size;
+	__be32 spare3;
+	__be32 checksum;
+	__be32 hashtable[1];
+};
+
+struct affs_root_tail {
+	__be32 bm_flag;
+	__be32 bm_blk[AFFS_ROOT_BMAPS];
+	__be32 bm_ext;
+	struct affs_date root_change;
+	u8 disk_name[32];
+	__be32 spare1;
+	__be32 spare2;
+	struct affs_date disk_change;
+	struct affs_date disk_create;
+	__be32 spare3;
+	__be32 spare4;
+	__be32 dcache;
+	__be32 stype;
+};
+
+struct affs_head {
+	__be32 ptype;
+	__be32 key;
+	__be32 block_count;
+	__be32 spare1;
+	__be32 first_data;
+	__be32 checksum;
+	__be32 table[1];
+};
+
+struct affs_tail {
+	__be32 spare1;
+	__be16 uid;
+	__be16 gid;
+	__be32 protect;
+	__be32 size;
+	u8 comment[92];
+	struct affs_date change;
+	u8 name[32];
+	__be32 spare2;
+	__be32 original;
+	__be32 link_chain;
+	__be32 spare[5];
+	__be32 hash_chain;
+	__be32 parent;
+	__be32 extension;
+	__be32 stype;
+};
+
+struct slink_front
+{
+	__be32 ptype;
+	__be32 key;
+	__be32 spare1[3];
+	__be32 checksum;
+	u8 symname[1];	/* depends on block size */
+};
+
+struct affs_data_head
+{
+	__be32 ptype;
+	__be32 key;
+	__be32 sequence;
+	__be32 size;
+	__be32 next;
+	__be32 checksum;
+	u8 data[1];	/* depends on block size */
+};
+
+/* Permission bits */
+
+#define FIBF_OTR_READ		0x8000
+#define FIBF_OTR_WRITE		0x4000
+#define FIBF_OTR_EXECUTE	0x2000
+#define FIBF_OTR_DELETE		0x1000
+#define FIBF_GRP_READ		0x0800
+#define FIBF_GRP_WRITE		0x0400
+#define FIBF_GRP_EXECUTE	0x0200
+#define FIBF_GRP_DELETE		0x0100
+
+#define FIBF_HIDDEN		0x0080
+#define FIBF_SCRIPT		0x0040
+#define FIBF_PURE		0x0020		/* no use under linux */
+#define FIBF_ARCHIVED		0x0010		/* never set, always cleared on write */
+#define FIBF_NOREAD		0x0008		/* 0 means allowed */
+#define FIBF_NOWRITE		0x0004		/* 0 means allowed */
+#define FIBF_NOEXECUTE		0x0002		/* 0 means allowed, ignored under linux */
+#define FIBF_NODELETE		0x0001		/* 0 means allowed */
+
+#define FIBF_OWNER		0x000F		/* Bits pertaining to owner */
+#define FIBF_MASK		0xEE0E		/* Bits modified by Linux */
+
+#endif
diff --git a/fs/affs/dir.c b/fs/affs/dir.c
index f1e7294381c5..591ecd7f3063 100644
--- a/fs/affs/dir.c
+++ b/fs/affs/dir.c
@@ -35,7 +35,7 @@ const struct inode_operations affs_dir_inode_operations = {
 	.symlink	= affs_symlink,
 	.mkdir		= affs_mkdir,
 	.rmdir		= affs_rmdir,
-	.rename		= affs_rename,
+	.rename		= affs_rename2,
 	.setattr	= affs_notify_change,
 };
 
diff --git a/fs/affs/file.c b/fs/affs/file.c
index 0deec9cc2362..196ee7f6fdc4 100644
--- a/fs/affs/file.c
+++ b/fs/affs/file.c
@@ -499,7 +499,7 @@ affs_getemptyblk_ino(struct inode *inode, int block)
 }
 
 static int
-affs_do_readpage_ofs(struct page *page, unsigned to)
+affs_do_readpage_ofs(struct page *page, unsigned to, int create)
 {
 	struct inode *inode = page->mapping->host;
 	struct super_block *sb = inode->i_sb;
@@ -518,7 +518,7 @@ affs_do_readpage_ofs(struct page *page, unsigned to)
 	boff = tmp % bsize;
 
 	while (pos < to) {
-		bh = affs_bread_ino(inode, bidx, 0);
+		bh = affs_bread_ino(inode, bidx, create);
 		if (IS_ERR(bh))
 			return PTR_ERR(bh);
 		tmp = min(bsize - boff, to - pos);
@@ -620,7 +620,7 @@ affs_readpage_ofs(struct file *file, struct page *page)
 		memset(page_address(page) + to, 0, PAGE_SIZE - to);
 	}
 
-	err = affs_do_readpage_ofs(page, to);
+	err = affs_do_readpage_ofs(page, to, 0);
 	if (!err)
 		SetPageUptodate(page);
 	unlock_page(page);
@@ -657,7 +657,7 @@ static int affs_write_begin_ofs(struct file *file, struct address_space *mapping
 		return 0;
 
 	/* XXX: inefficient but safe in the face of short writes */
-	err = affs_do_readpage_ofs(page, PAGE_SIZE);
+	err = affs_do_readpage_ofs(page, PAGE_SIZE, 1);
 	if (err) {
 		unlock_page(page);
 		put_page(page);
@@ -679,7 +679,7 @@ static int affs_write_end_ofs(struct file *file, struct address_space *mapping,
 	int written;
 
 	from = pos & (PAGE_SIZE - 1);
-	to = pos + len;
+	to = from + len;
 	/*
 	 * XXX: not sure if this can handle short copies (len < copied), but
 	 * we don't have to, because the page should always be uptodate here,
diff --git a/fs/affs/inode.c b/fs/affs/inode.c
index fe4e1290dbb5..fd4ef3c40e40 100644
--- a/fs/affs/inode.c
+++ b/fs/affs/inode.c
@@ -10,6 +10,7 @@
  *  (C) 1991  Linus Torvalds - minix filesystem
  */
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/gfp.h>
 #include "affs.h"
 
@@ -69,7 +70,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino)
 	if (affs_test_opt(sbi->s_flags, SF_SETMODE))
 		inode->i_mode = sbi->s_mode;
 	else
-		inode->i_mode = prot_to_mode(prot);
+		inode->i_mode = affs_prot_to_mode(prot);
 
 	id = be16_to_cpu(tail->uid);
 	if (id == 0 || affs_test_opt(sbi->s_flags, SF_SETUID))
@@ -139,6 +140,7 @@ struct inode *affs_iget(struct super_block *sb, unsigned long ino)
 		inode->i_fop = &affs_file_operations;
 		break;
 	case ST_SOFTLINK:
+		inode->i_size = strlen((char *)AFFS_HEAD(bh)->table);
 		inode->i_mode |= S_IFLNK;
 		inode_nohighmem(inode);
 		inode->i_op = &affs_symlink_inode_operations;
@@ -184,11 +186,12 @@ affs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	}
 	tail = AFFS_TAIL(sb, bh);
 	if (tail->stype == cpu_to_be32(ST_ROOT)) {
-		secs_to_datestamp(inode->i_mtime.tv_sec,&AFFS_ROOT_TAIL(sb, bh)->root_change);
+		affs_secs_to_datestamp(inode->i_mtime.tv_sec,
+				       &AFFS_ROOT_TAIL(sb, bh)->root_change);
 	} else {
 		tail->protect = cpu_to_be32(AFFS_I(inode)->i_protect);
 		tail->size = cpu_to_be32(inode->i_size);
-		secs_to_datestamp(inode->i_mtime.tv_sec,&tail->change);
+		affs_secs_to_datestamp(inode->i_mtime.tv_sec, &tail->change);
 		if (!(inode->i_ino == AFFS_SB(sb)->s_root_block)) {
 			uid = i_uid_read(inode);
 			gid = i_gid_read(inode);
@@ -249,7 +252,7 @@ affs_notify_change(struct dentry *dentry, struct iattr *attr)
 	mark_inode_dirty(inode);
 
 	if (attr->ia_valid & ATTR_MODE)
-		mode_to_prot(inode);
+		affs_mode_to_prot(inode);
 out:
 	return error;
 }
diff --git a/fs/affs/namei.c b/fs/affs/namei.c
index 29186d29a3b6..46d3ace6761d 100644
--- a/fs/affs/namei.c
+++ b/fs/affs/namei.c
@@ -9,29 +9,10 @@
  */
 
 #include "affs.h"
+#include <linux/exportfs.h>
 
 typedef int (*toupper_t)(int);
 
-static int	 affs_toupper(int ch);
-static int	 affs_hash_dentry(const struct dentry *, struct qstr *);
-static int       affs_compare_dentry(const struct dentry *dentry,
-		unsigned int len, const char *str, const struct qstr *name);
-static int	 affs_intl_toupper(int ch);
-static int	 affs_intl_hash_dentry(const struct dentry *, struct qstr *);
-static int       affs_intl_compare_dentry(const struct dentry *dentry,
-		unsigned int len, const char *str, const struct qstr *name);
-
-const struct dentry_operations affs_dentry_operations = {
-	.d_hash		= affs_hash_dentry,
-	.d_compare	= affs_compare_dentry,
-};
-
-const struct dentry_operations affs_intl_dentry_operations = {
-	.d_hash		= affs_intl_hash_dentry,
-	.d_compare	= affs_intl_compare_dentry,
-};
-
-
 /* Simple toupper() for DOS\1 */
 
 static int
@@ -271,7 +252,7 @@ affs_create(struct inode *dir, struct dentry *dentry, umode_t mode, bool excl)
 		return -ENOSPC;
 
 	inode->i_mode = mode;
-	mode_to_prot(inode);
+	affs_mode_to_prot(inode);
 	mark_inode_dirty(inode);
 
 	inode->i_op = &affs_file_inode_operations;
@@ -301,7 +282,7 @@ affs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 		return -ENOSPC;
 
 	inode->i_mode = S_IFDIR | mode;
-	mode_to_prot(inode);
+	affs_mode_to_prot(inode);
 
 	inode->i_op = &affs_dir_inode_operations;
 	inode->i_fop = &affs_dir_operations;
@@ -347,7 +328,7 @@ affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 	inode_nohighmem(inode);
 	inode->i_data.a_ops = &affs_symlink_aops;
 	inode->i_mode = S_IFLNK | 0777;
-	mode_to_prot(inode);
+	affs_mode_to_prot(inode);
 
 	error = -EIO;
 	bh = affs_bread(sb, inode->i_ino);
@@ -384,6 +365,7 @@ affs_symlink(struct inode *dir, struct dentry *dentry, const char *symname)
 				symname++;
 	}
 	*p = 0;
+	inode->i_size = i + 1;
 	mark_buffer_dirty_inode(bh, inode);
 	affs_brelse(bh);
 	mark_inode_dirty(inode);
@@ -412,21 +394,14 @@ affs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry)
 	return affs_add_entry(dir, inode, dentry, ST_LINKFILE);
 }
 
-int
+static int
 affs_rename(struct inode *old_dir, struct dentry *old_dentry,
-	    struct inode *new_dir, struct dentry *new_dentry,
-	    unsigned int flags)
+	    struct inode *new_dir, struct dentry *new_dentry)
 {
 	struct super_block *sb = old_dir->i_sb;
 	struct buffer_head *bh = NULL;
 	int retval;
 
-	if (flags & ~RENAME_NOREPLACE)
-		return -EINVAL;
-
-	pr_debug("%s(old=%lu,\"%pd\" to new=%lu,\"%pd\")\n", __func__,
-		 old_dir->i_ino, old_dentry, new_dir->i_ino, new_dentry);
-
 	retval = affs_check_name(new_dentry->d_name.name,
 				 new_dentry->d_name.len,
 				 affs_nofilenametruncate(old_dentry));
@@ -465,3 +440,136 @@ done:
 	affs_brelse(bh);
 	return retval;
 }
+
+static int
+affs_xrename(struct inode *old_dir, struct dentry *old_dentry,
+	     struct inode *new_dir, struct dentry *new_dentry)
+{
+
+	struct super_block *sb = old_dir->i_sb;
+	struct buffer_head *bh_old = NULL;
+	struct buffer_head *bh_new = NULL;
+	int retval;
+
+	bh_old = affs_bread(sb, d_inode(old_dentry)->i_ino);
+	if (!bh_old)
+		return -EIO;
+
+	bh_new = affs_bread(sb, d_inode(new_dentry)->i_ino);
+	if (!bh_new)
+		return -EIO;
+
+	/* Remove old header from its parent directory. */
+	affs_lock_dir(old_dir);
+	retval = affs_remove_hash(old_dir, bh_old);
+	affs_unlock_dir(old_dir);
+	if (retval)
+		goto done;
+
+	/* Remove new header from its parent directory. */
+	affs_lock_dir(new_dir);
+	retval = affs_remove_hash(new_dir, bh_new);
+	affs_unlock_dir(new_dir);
+	if (retval)
+		goto done;
+
+	/* Insert old into the new directory with the new name. */
+	affs_copy_name(AFFS_TAIL(sb, bh_old)->name, new_dentry);
+	affs_fix_checksum(sb, bh_old);
+	affs_lock_dir(new_dir);
+	retval = affs_insert_hash(new_dir, bh_old);
+	affs_unlock_dir(new_dir);
+
+	/* Insert new into the old directory with the old name. */
+	affs_copy_name(AFFS_TAIL(sb, bh_new)->name, old_dentry);
+	affs_fix_checksum(sb, bh_new);
+	affs_lock_dir(old_dir);
+	retval = affs_insert_hash(old_dir, bh_new);
+	affs_unlock_dir(old_dir);
+done:
+	mark_buffer_dirty_inode(bh_old, new_dir);
+	mark_buffer_dirty_inode(bh_new, old_dir);
+	affs_brelse(bh_old);
+	affs_brelse(bh_new);
+	return retval;
+}
+
+int affs_rename2(struct inode *old_dir, struct dentry *old_dentry,
+			struct inode *new_dir, struct dentry *new_dentry,
+			unsigned int flags)
+{
+
+	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE))
+		return -EINVAL;
+
+	pr_debug("%s(old=%lu,\"%pd\" to new=%lu,\"%pd\")\n", __func__,
+		 old_dir->i_ino, old_dentry, new_dir->i_ino, new_dentry);
+
+	if (flags & RENAME_EXCHANGE)
+		return affs_xrename(old_dir, old_dentry, new_dir, new_dentry);
+
+	return affs_rename(old_dir, old_dentry, new_dir, new_dentry);
+}
+
+static struct dentry *affs_get_parent(struct dentry *child)
+{
+	struct inode *parent;
+	struct buffer_head *bh;
+
+	bh = affs_bread(child->d_sb, d_inode(child)->i_ino);
+	if (!bh)
+		return ERR_PTR(-EIO);
+
+	parent = affs_iget(child->d_sb,
+			   be32_to_cpu(AFFS_TAIL(child->d_sb, bh)->parent));
+	brelse(bh);
+	if (IS_ERR(parent))
+		return ERR_CAST(parent);
+
+	return d_obtain_alias(parent);
+}
+
+static struct inode *affs_nfs_get_inode(struct super_block *sb, u64 ino,
+					u32 generation)
+{
+	struct inode *inode;
+
+	if (!affs_validblock(sb, ino))
+		return ERR_PTR(-ESTALE);
+
+	inode = affs_iget(sb, ino);
+	if (IS_ERR(inode))
+		return ERR_CAST(inode);
+
+	return inode;
+}
+
+static struct dentry *affs_fh_to_dentry(struct super_block *sb, struct fid *fid,
+					int fh_len, int fh_type)
+{
+	return generic_fh_to_dentry(sb, fid, fh_len, fh_type,
+				    affs_nfs_get_inode);
+}
+
+static struct dentry *affs_fh_to_parent(struct super_block *sb, struct fid *fid,
+					int fh_len, int fh_type)
+{
+	return generic_fh_to_parent(sb, fid, fh_len, fh_type,
+				    affs_nfs_get_inode);
+}
+
+const struct export_operations affs_export_ops = {
+	.fh_to_dentry = affs_fh_to_dentry,
+	.fh_to_parent = affs_fh_to_parent,
+	.get_parent = affs_get_parent,
+};
+
+const struct dentry_operations affs_dentry_operations = {
+	.d_hash		= affs_hash_dentry,
+	.d_compare	= affs_compare_dentry,
+};
+
+const struct dentry_operations affs_intl_dentry_operations = {
+	.d_hash		= affs_intl_hash_dentry,
+	.d_compare	= affs_intl_compare_dentry,
+};
diff --git a/fs/affs/super.c b/fs/affs/super.c
index d6384863192c..7bf47a41cb4f 100644
--- a/fs/affs/super.c
+++ b/fs/affs/super.c
@@ -16,12 +16,15 @@
 #include <linux/parser.h>
 #include <linux/magic.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/slab.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
+#include <linux/seq_file.h>
 #include "affs.h"
 
 static int affs_statfs(struct dentry *dentry, struct kstatfs *buf);
+static int affs_show_options(struct seq_file *m, struct dentry *root);
 static int affs_remount (struct super_block *sb, int *flags, char *data);
 
 static void
@@ -32,7 +35,7 @@ affs_commit_super(struct super_block *sb, int wait)
 	struct affs_root_tail *tail = AFFS_ROOT_TAIL(sb, bh);
 
 	lock_buffer(bh);
-	secs_to_datestamp(ktime_get_real_seconds(), &tail->disk_change);
+	affs_secs_to_datestamp(ktime_get_real_seconds(), &tail->disk_change);
 	affs_fix_checksum(sb, bh);
 	unlock_buffer(bh);
 
@@ -158,7 +161,7 @@ static const struct super_operations affs_sops = {
 	.sync_fs	= affs_sync_fs,
 	.statfs		= affs_statfs,
 	.remount_fs	= affs_remount,
-	.show_options	= generic_show_options,
+	.show_options	= affs_show_options,
 };
 
 enum {
@@ -292,6 +295,40 @@ parse_options(char *options, kuid_t *uid, kgid_t *gid, int *mode, int *reserved,
 	return 1;
 }
 
+static int affs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct super_block *sb = root->d_sb;
+	struct affs_sb_info *sbi = AFFS_SB(sb);
+
+	if (sb->s_blocksize)
+		seq_printf(m, ",bs=%lu", sb->s_blocksize);
+	if (affs_test_opt(sbi->s_flags, SF_SETMODE))
+		seq_printf(m, ",mode=%o", sbi->s_mode);
+	if (affs_test_opt(sbi->s_flags, SF_MUFS))
+		seq_puts(m, ",mufs");
+	if (affs_test_opt(sbi->s_flags, SF_NO_TRUNCATE))
+		seq_puts(m, ",nofilenametruncate");
+	if (affs_test_opt(sbi->s_flags, SF_PREFIX))
+		seq_printf(m, ",prefix=%s", sbi->s_prefix);
+	if (affs_test_opt(sbi->s_flags, SF_IMMUTABLE))
+		seq_puts(m, ",protect");
+	if (sbi->s_reserved != 2)
+		seq_printf(m, ",reserved=%u", sbi->s_reserved);
+	if (sbi->s_root_block != (sbi->s_reserved + sbi->s_partition_size - 1) / 2)
+		seq_printf(m, ",root=%u", sbi->s_root_block);
+	if (affs_test_opt(sbi->s_flags, SF_SETGID))
+		seq_printf(m, ",setgid=%u",
+			   from_kgid_munged(&init_user_ns, sbi->s_gid));
+	if (affs_test_opt(sbi->s_flags, SF_SETUID))
+		seq_printf(m, ",setuid=%u",
+			   from_kuid_munged(&init_user_ns, sbi->s_uid));
+	if (affs_test_opt(sbi->s_flags, SF_VERBOSE))
+		seq_puts(m, ",verbose");
+	if (sbi->s_volume[0])
+		seq_printf(m, ",volume=%s", sbi->s_volume);
+	return 0;
+}
+
 /* This function definitely needs to be split up. Some fine day I'll
  * hopefully have the guts to do so. Until then: sorry for the mess.
  */
@@ -315,8 +352,6 @@ static int affs_fill_super(struct super_block *sb, void *data, int silent)
 	u8			 sig[4];
 	int			 ret;
 
-	save_mount_options(sb, data);
-
 	pr_debug("read_super(%s)\n", data ? (const char *)data : "no options");
 
 	sb->s_magic             = AFFS_SUPER_MAGIC;
@@ -507,6 +542,7 @@ got_root:
 		return -ENOMEM;
 	}
 
+	sb->s_export_op = &affs_export_ops;
 	pr_debug("s_flags=%lX\n", sb->s_flags);
 	return 0;
 }
@@ -546,8 +582,6 @@ affs_remount(struct super_block *sb, int *flags, char *data)
 	}
 
 	flush_delayed_work(&sbi->sb_work);
-	if (new_opts)
-		replace_mount_options(sb, new_opts);
 
 	sbi->s_flags = mount_flags;
 	sbi->s_mode  = mode;
diff --git a/fs/afs/Makefile b/fs/afs/Makefile
index 4f64b95d57bd..095c54165dfd 100644
--- a/fs/afs/Makefile
+++ b/fs/afs/Makefile
@@ -27,6 +27,7 @@ kafs-objs := \
 	vlocation.o \
 	vnode.o \
 	volume.o \
-	write.o
+	write.o \
+	xattr.o
 
 obj-$(CONFIG_AFS_FS)  := kafs.o
diff --git a/fs/afs/callback.c b/fs/afs/callback.c
index 1e9d2f84e5b5..25d404d22cae 100644
--- a/fs/afs/callback.c
+++ b/fs/afs/callback.c
@@ -343,7 +343,7 @@ void afs_dispatch_give_up_callbacks(struct work_struct *work)
 	 *   had callbacks entirely, and the server will call us later to break
 	 *   them
 	 */
-	afs_fs_give_up_callbacks(server, &afs_async_call);
+	afs_fs_give_up_callbacks(server, true);
 }
 
 /*
@@ -362,7 +362,7 @@ static void afs_callback_updater(struct work_struct *work)
 {
 	struct afs_server *server;
 	struct afs_vnode *vnode, *xvnode;
-	time_t now;
+	time64_t now;
 	long timeout;
 	int ret;
 
@@ -370,7 +370,7 @@ static void afs_callback_updater(struct work_struct *work)
 
 	_enter("");
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 
 	/* find the first vnode to update */
 	spin_lock(&server->cb_lock);
@@ -424,7 +424,8 @@ static void afs_callback_updater(struct work_struct *work)
 
 	/* and then reschedule */
 	_debug("reschedule");
-	vnode->update_at = get_seconds() + afs_vnode_update_timeout;
+	vnode->update_at = ktime_get_real_seconds() +
+			afs_vnode_update_timeout;
 
 	spin_lock(&server->cb_lock);
 
diff --git a/fs/afs/cmservice.c b/fs/afs/cmservice.c
index d764236072b1..782d4d05a53b 100644
--- a/fs/afs/cmservice.c
+++ b/fs/afs/cmservice.c
@@ -24,65 +24,86 @@ static int afs_deliver_cb_callback(struct afs_call *);
 static int afs_deliver_cb_probe_uuid(struct afs_call *);
 static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *);
 static void afs_cm_destructor(struct afs_call *);
+static void SRXAFSCB_CallBack(struct work_struct *);
+static void SRXAFSCB_InitCallBackState(struct work_struct *);
+static void SRXAFSCB_Probe(struct work_struct *);
+static void SRXAFSCB_ProbeUuid(struct work_struct *);
+static void SRXAFSCB_TellMeAboutYourself(struct work_struct *);
+
+#define CM_NAME(name) \
+	const char afs_SRXCB##name##_name[] __tracepoint_string =	\
+		"CB." #name
 
 /*
  * CB.CallBack operation type
  */
+static CM_NAME(CallBack);
 static const struct afs_call_type afs_SRXCBCallBack = {
-	.name		= "CB.CallBack",
+	.name		= afs_SRXCBCallBack_name,
 	.deliver	= afs_deliver_cb_callback,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_CallBack,
 };
 
 /*
  * CB.InitCallBackState operation type
  */
+static CM_NAME(InitCallBackState);
 static const struct afs_call_type afs_SRXCBInitCallBackState = {
-	.name		= "CB.InitCallBackState",
+	.name		= afs_SRXCBInitCallBackState_name,
 	.deliver	= afs_deliver_cb_init_call_back_state,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_InitCallBackState,
 };
 
 /*
  * CB.InitCallBackState3 operation type
  */
+static CM_NAME(InitCallBackState3);
 static const struct afs_call_type afs_SRXCBInitCallBackState3 = {
-	.name		= "CB.InitCallBackState3",
+	.name		= afs_SRXCBInitCallBackState3_name,
 	.deliver	= afs_deliver_cb_init_call_back_state3,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_InitCallBackState,
 };
 
 /*
  * CB.Probe operation type
  */
+static CM_NAME(Probe);
 static const struct afs_call_type afs_SRXCBProbe = {
-	.name		= "CB.Probe",
+	.name		= afs_SRXCBProbe_name,
 	.deliver	= afs_deliver_cb_probe,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_Probe,
 };
 
 /*
  * CB.ProbeUuid operation type
  */
+static CM_NAME(ProbeUuid);
 static const struct afs_call_type afs_SRXCBProbeUuid = {
-	.name		= "CB.ProbeUuid",
+	.name		= afs_SRXCBProbeUuid_name,
 	.deliver	= afs_deliver_cb_probe_uuid,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_ProbeUuid,
 };
 
 /*
  * CB.TellMeAboutYourself operation type
  */
+static CM_NAME(TellMeAboutYourself);
 static const struct afs_call_type afs_SRXCBTellMeAboutYourself = {
-	.name		= "CB.TellMeAboutYourself",
+	.name		= afs_SRXCBTellMeAboutYourself_name,
 	.deliver	= afs_deliver_cb_tell_me_about_yourself,
 	.abort_to_error	= afs_abort_to_error,
 	.destructor	= afs_cm_destructor,
+	.work		= SRXAFSCB_TellMeAboutYourself,
 };
 
 /*
@@ -153,6 +174,7 @@ static void SRXAFSCB_CallBack(struct work_struct *work)
 	afs_send_empty_reply(call);
 
 	afs_break_callbacks(call->server, call->count, call->request);
+	afs_put_call(call);
 	_leave("");
 }
 
@@ -165,7 +187,6 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 	struct afs_callback *cb;
 	struct afs_server *server;
 	__be32 *bp;
-	u32 tmp;
 	int ret, loop;
 
 	_enter("{%u}", call->unmarshall);
@@ -227,9 +248,9 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 		if (ret < 0)
 			return ret;
 
-		tmp = ntohl(call->tmp);
-		_debug("CB count: %u", tmp);
-		if (tmp != call->count && tmp != 0)
+		call->count2 = ntohl(call->tmp);
+		_debug("CB count: %u", call->count2);
+		if (call->count2 != call->count && call->count2 != 0)
 			return -EBADMSG;
 		call->offset = 0;
 		call->unmarshall++;
@@ -237,14 +258,14 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 	case 4:
 		_debug("extract CB array");
 		ret = afs_extract_data(call, call->buffer,
-				       call->count * 3 * 4, false);
+				       call->count2 * 3 * 4, false);
 		if (ret < 0)
 			return ret;
 
 		_debug("unmarshall CB array");
 		cb = call->request;
 		bp = call->buffer;
-		for (loop = call->count; loop > 0; loop--, cb++) {
+		for (loop = call->count2; loop > 0; loop--, cb++) {
 			cb->version	= ntohl(*bp++);
 			cb->expiry	= ntohl(*bp++);
 			cb->type	= ntohl(*bp++);
@@ -274,9 +295,7 @@ static int afs_deliver_cb_callback(struct afs_call *call)
 		return -ENOTCONN;
 	call->server = server;
 
-	INIT_WORK(&call->work, SRXAFSCB_CallBack);
-	queue_work(afs_wq, &call->work);
-	return 0;
+	return afs_queue_call_work(call);
 }
 
 /*
@@ -290,6 +309,7 @@ static void SRXAFSCB_InitCallBackState(struct work_struct *work)
 
 	afs_init_callback_state(call->server);
 	afs_send_empty_reply(call);
+	afs_put_call(call);
 	_leave("");
 }
 
@@ -320,9 +340,7 @@ static int afs_deliver_cb_init_call_back_state(struct afs_call *call)
 		return -ENOTCONN;
 	call->server = server;
 
-	INIT_WORK(&call->work, SRXAFSCB_InitCallBackState);
-	queue_work(afs_wq, &call->work);
-	return 0;
+	return afs_queue_call_work(call);
 }
 
 /*
@@ -368,9 +386,9 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 
 		b = call->buffer;
 		r = call->request;
-		r->time_low			= ntohl(b[0]);
-		r->time_mid			= ntohl(b[1]);
-		r->time_hi_and_version		= ntohl(b[2]);
+		r->time_low			= b[0];
+		r->time_mid			= htons(ntohl(b[1]));
+		r->time_hi_and_version		= htons(ntohl(b[2]));
 		r->clock_seq_hi_and_reserved 	= ntohl(b[3]);
 		r->clock_seq_low		= ntohl(b[4]);
 
@@ -394,9 +412,7 @@ static int afs_deliver_cb_init_call_back_state3(struct afs_call *call)
 		return -ENOTCONN;
 	call->server = server;
 
-	INIT_WORK(&call->work, SRXAFSCB_InitCallBackState);
-	queue_work(afs_wq, &call->work);
-	return 0;
+	return afs_queue_call_work(call);
 }
 
 /*
@@ -408,6 +424,7 @@ static void SRXAFSCB_Probe(struct work_struct *work)
 
 	_enter("");
 	afs_send_empty_reply(call);
+	afs_put_call(call);
 	_leave("");
 }
 
@@ -427,9 +444,7 @@ static int afs_deliver_cb_probe(struct afs_call *call)
 	/* no unmarshalling required */
 	call->state = AFS_CALL_REPLYING;
 
-	INIT_WORK(&call->work, SRXAFSCB_Probe);
-	queue_work(afs_wq, &call->work);
-	return 0;
+	return afs_queue_call_work(call);
 }
 
 /*
@@ -452,6 +467,7 @@ static void SRXAFSCB_ProbeUuid(struct work_struct *work)
 		reply.match = htonl(1);
 
 	afs_send_simple_reply(call, &reply, sizeof(reply));
+	afs_put_call(call);
 	_leave("");
 }
 
@@ -510,9 +526,7 @@ static int afs_deliver_cb_probe_uuid(struct afs_call *call)
 
 	call->state = AFS_CALL_REPLYING;
 
-	INIT_WORK(&call->work, SRXAFSCB_ProbeUuid);
-	queue_work(afs_wq, &call->work);
-	return 0;
+	return afs_queue_call_work(call);
 }
 
 /*
@@ -554,9 +568,9 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work)
 	memset(&reply, 0, sizeof(reply));
 	reply.ia.nifs = htonl(nifs);
 
-	reply.ia.uuid[0] = htonl(afs_uuid.time_low);
-	reply.ia.uuid[1] = htonl(afs_uuid.time_mid);
-	reply.ia.uuid[2] = htonl(afs_uuid.time_hi_and_version);
+	reply.ia.uuid[0] = afs_uuid.time_low;
+	reply.ia.uuid[1] = htonl(ntohs(afs_uuid.time_mid));
+	reply.ia.uuid[2] = htonl(ntohs(afs_uuid.time_hi_and_version));
 	reply.ia.uuid[3] = htonl((s8) afs_uuid.clock_seq_hi_and_reserved);
 	reply.ia.uuid[4] = htonl((s8) afs_uuid.clock_seq_low);
 	for (loop = 0; loop < 6; loop++)
@@ -574,7 +588,7 @@ static void SRXAFSCB_TellMeAboutYourself(struct work_struct *work)
 	reply.cap.capcount = htonl(1);
 	reply.cap.caps[0] = htonl(AFS_CAP_ERROR_TRANSLATION);
 	afs_send_simple_reply(call, &reply, sizeof(reply));
-
+	afs_put_call(call);
 	_leave("");
 }
 
@@ -594,7 +608,5 @@ static int afs_deliver_cb_tell_me_about_yourself(struct afs_call *call)
 	/* no unmarshalling required */
 	call->state = AFS_CALL_REPLYING;
 
-	INIT_WORK(&call->work, SRXAFSCB_TellMeAboutYourself);
-	queue_work(afs_wq, &call->work);
-	return 0;
+	return afs_queue_call_work(call);
 }
diff --git a/fs/afs/dir.c b/fs/afs/dir.c
index 51a241e09fbb..613a77058263 100644
--- a/fs/afs/dir.c
+++ b/fs/afs/dir.c
@@ -61,6 +61,7 @@ const struct inode_operations afs_dir_inode_operations = {
 	.permission	= afs_permission,
 	.getattr	= afs_getattr,
 	.setattr	= afs_setattr,
+	.listxattr	= afs_listxattr,
 };
 
 const struct dentry_operations afs_fs_dentry_operations = {
@@ -252,7 +253,7 @@ static int afs_dir_iterate_block(struct dir_context *ctx,
 		/* skip entries marked unused in the bitmap */
 		if (!(block->pagehdr.bitmap[offset / 8] &
 		      (1 << (offset % 8)))) {
-			_debug("ENT[%Zu.%u]: unused",
+			_debug("ENT[%zu.%u]: unused",
 			       blkoff / sizeof(union afs_dir_block), offset);
 			if (offset >= curr)
 				ctx->pos = blkoff +
@@ -266,7 +267,7 @@ static int afs_dir_iterate_block(struct dir_context *ctx,
 			       sizeof(*block) -
 			       offset * sizeof(union afs_dirent));
 
-		_debug("ENT[%Zu.%u]: %s %Zu \"%s\"",
+		_debug("ENT[%zu.%u]: %s %zu \"%s\"",
 		       blkoff / sizeof(union afs_dir_block), offset,
 		       (offset < curr ? "skip" : "fill"),
 		       nlen, dire->u.name);
@@ -274,23 +275,23 @@ static int afs_dir_iterate_block(struct dir_context *ctx,
 		/* work out where the next possible entry is */
 		for (tmp = nlen; tmp > 15; tmp -= sizeof(union afs_dirent)) {
 			if (next >= AFS_DIRENT_PER_BLOCK) {
-				_debug("ENT[%Zu.%u]:"
+				_debug("ENT[%zu.%u]:"
 				       " %u travelled beyond end dir block"
-				       " (len %u/%Zu)",
+				       " (len %u/%zu)",
 				       blkoff / sizeof(union afs_dir_block),
 				       offset, next, tmp, nlen);
 				return -EIO;
 			}
 			if (!(block->pagehdr.bitmap[next / 8] &
 			      (1 << (next % 8)))) {
-				_debug("ENT[%Zu.%u]:"
-				       " %u unmarked extension (len %u/%Zu)",
+				_debug("ENT[%zu.%u]:"
+				       " %u unmarked extension (len %u/%zu)",
 				       blkoff / sizeof(union afs_dir_block),
 				       offset, next, tmp, nlen);
 				return -EIO;
 			}
 
-			_debug("ENT[%Zu.%u]: ext %u/%Zu",
+			_debug("ENT[%zu.%u]: ext %u/%zu",
 			       blkoff / sizeof(union afs_dir_block),
 			       next, tmp, nlen);
 			next++;
diff --git a/fs/afs/file.c b/fs/afs/file.c
index 6344aee4ac4b..510cba15fa56 100644
--- a/fs/afs/file.c
+++ b/fs/afs/file.c
@@ -16,6 +16,7 @@
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/gfp.h>
+#include <linux/task_io_accounting_ops.h>
 #include "internal.h"
 
 static int afs_readpage(struct file *file, struct page *page);
@@ -29,6 +30,7 @@ static int afs_readpages(struct file *filp, struct address_space *mapping,
 
 const struct file_operations afs_file_operations = {
 	.open		= afs_open,
+	.flush		= afs_flush,
 	.release	= afs_release,
 	.llseek		= generic_file_llseek,
 	.read_iter	= generic_file_read_iter,
@@ -44,6 +46,7 @@ const struct inode_operations afs_file_inode_operations = {
 	.getattr	= afs_getattr,
 	.setattr	= afs_setattr,
 	.permission	= afs_permission,
+	.listxattr	= afs_listxattr,
 };
 
 const struct address_space_operations afs_fs_aops = {
@@ -101,6 +104,21 @@ int afs_release(struct inode *inode, struct file *file)
 	return 0;
 }
 
+/*
+ * Dispose of a ref to a read record.
+ */
+void afs_put_read(struct afs_read *req)
+{
+	int i;
+
+	if (atomic_dec_and_test(&req->usage)) {
+		for (i = 0; i < req->nr_pages; i++)
+			if (req->pages[i])
+				put_page(req->pages[i]);
+		kfree(req);
+	}
+}
+
 #ifdef CONFIG_AFS_FSCACHE
 /*
  * deal with notification that a page was read from the cache
@@ -126,9 +144,8 @@ int afs_page_filler(void *data, struct page *page)
 {
 	struct inode *inode = page->mapping->host;
 	struct afs_vnode *vnode = AFS_FS_I(inode);
+	struct afs_read *req;
 	struct key *key = data;
-	size_t len;
-	off_t offset;
 	int ret;
 
 	_enter("{%x},{%lu},{%lu}", key_serial(key), inode->i_ino, page->index);
@@ -164,12 +181,26 @@ int afs_page_filler(void *data, struct page *page)
 		_debug("cache said ENOBUFS");
 	default:
 	go_on:
-		offset = page->index << PAGE_SHIFT;
-		len = min_t(size_t, i_size_read(inode) - offset, PAGE_SIZE);
+		req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *),
+			      GFP_KERNEL);
+		if (!req)
+			goto enomem;
+
+		/* We request a full page.  If the page is a partial one at the
+		 * end of the file, the server will return a short read and the
+		 * unmarshalling code will clear the unfilled space.
+		 */
+		atomic_set(&req->usage, 1);
+		req->pos = (loff_t)page->index << PAGE_SHIFT;
+		req->len = PAGE_SIZE;
+		req->nr_pages = 1;
+		req->pages[0] = page;
+		get_page(page);
 
 		/* read the contents of the file from the server into the
 		 * page */
-		ret = afs_vnode_fetch_data(vnode, key, offset, len, page);
+		ret = afs_vnode_fetch_data(vnode, key, req);
+		afs_put_read(req);
 		if (ret < 0) {
 			if (ret == -ENOENT) {
 				_debug("got NOENT from server"
@@ -182,7 +213,13 @@ int afs_page_filler(void *data, struct page *page)
 			fscache_uncache_page(vnode->cache, page);
 #endif
 			BUG_ON(PageFsCache(page));
-			goto error;
+
+			if (ret == -EINTR ||
+			    ret == -ENOMEM ||
+			    ret == -ERESTARTSYS ||
+			    ret == -EAGAIN)
+				goto error;
+			goto io_error;
 		}
 
 		SetPageUptodate(page);
@@ -201,8 +238,12 @@ int afs_page_filler(void *data, struct page *page)
 	_leave(" = 0");
 	return 0;
 
-error:
+io_error:
 	SetPageError(page);
+	goto error;
+enomem:
+	ret = -ENOMEM;
+error:
 	unlock_page(page);
 	_leave(" = %d", ret);
 	return ret;
@@ -235,6 +276,131 @@ static int afs_readpage(struct file *file, struct page *page)
 }
 
 /*
+ * Make pages available as they're filled.
+ */
+static void afs_readpages_page_done(struct afs_call *call, struct afs_read *req)
+{
+#ifdef CONFIG_AFS_FSCACHE
+	struct afs_vnode *vnode = call->reply;
+#endif
+	struct page *page = req->pages[req->index];
+
+	req->pages[req->index] = NULL;
+	SetPageUptodate(page);
+
+	/* send the page to the cache */
+#ifdef CONFIG_AFS_FSCACHE
+	if (PageFsCache(page) &&
+	    fscache_write_page(vnode->cache, page, GFP_KERNEL) != 0) {
+		fscache_uncache_page(vnode->cache, page);
+		BUG_ON(PageFsCache(page));
+	}
+#endif
+	unlock_page(page);
+	put_page(page);
+}
+
+/*
+ * Read a contiguous set of pages.
+ */
+static int afs_readpages_one(struct file *file, struct address_space *mapping,
+			     struct list_head *pages)
+{
+	struct afs_vnode *vnode = AFS_FS_I(mapping->host);
+	struct afs_read *req;
+	struct list_head *p;
+	struct page *first, *page;
+	struct key *key = file->private_data;
+	pgoff_t index;
+	int ret, n, i;
+
+	/* Count the number of contiguous pages at the front of the list.  Note
+	 * that the list goes prev-wards rather than next-wards.
+	 */
+	first = list_entry(pages->prev, struct page, lru);
+	index = first->index + 1;
+	n = 1;
+	for (p = first->lru.prev; p != pages; p = p->prev) {
+		page = list_entry(p, struct page, lru);
+		if (page->index != index)
+			break;
+		index++;
+		n++;
+	}
+
+	req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *) * n,
+		      GFP_NOFS);
+	if (!req)
+		return -ENOMEM;
+
+	atomic_set(&req->usage, 1);
+	req->page_done = afs_readpages_page_done;
+	req->pos = first->index;
+	req->pos <<= PAGE_SHIFT;
+
+	/* Transfer the pages to the request.  We add them in until one fails
+	 * to add to the LRU and then we stop (as that'll make a hole in the
+	 * contiguous run.
+	 *
+	 * Note that it's possible for the file size to change whilst we're
+	 * doing this, but we rely on the server returning less than we asked
+	 * for if the file shrank.  We also rely on this to deal with a partial
+	 * page at the end of the file.
+	 */
+	do {
+		page = list_entry(pages->prev, struct page, lru);
+		list_del(&page->lru);
+		index = page->index;
+		if (add_to_page_cache_lru(page, mapping, index,
+					  readahead_gfp_mask(mapping))) {
+#ifdef CONFIG_AFS_FSCACHE
+			fscache_uncache_page(vnode->cache, page);
+#endif
+			put_page(page);
+			break;
+		}
+
+		req->pages[req->nr_pages++] = page;
+		req->len += PAGE_SIZE;
+	} while (req->nr_pages < n);
+
+	if (req->nr_pages == 0) {
+		kfree(req);
+		return 0;
+	}
+
+	ret = afs_vnode_fetch_data(vnode, key, req);
+	if (ret < 0)
+		goto error;
+
+	task_io_account_read(PAGE_SIZE * req->nr_pages);
+	afs_put_read(req);
+	return 0;
+
+error:
+	if (ret == -ENOENT) {
+		_debug("got NOENT from server"
+		       " - marking file deleted and stale");
+		set_bit(AFS_VNODE_DELETED, &vnode->flags);
+		ret = -ESTALE;
+	}
+
+	for (i = 0; i < req->nr_pages; i++) {
+		page = req->pages[i];
+		if (page) {
+#ifdef CONFIG_AFS_FSCACHE
+			fscache_uncache_page(vnode->cache, page);
+#endif
+			SetPageError(page);
+			unlock_page(page);
+		}
+	}
+
+	afs_put_read(req);
+	return ret;
+}
+
+/*
  * read a set of pages
  */
 static int afs_readpages(struct file *file, struct address_space *mapping,
@@ -287,8 +453,11 @@ static int afs_readpages(struct file *file, struct address_space *mapping,
 		return ret;
 	}
 
-	/* load the missing pages from the network */
-	ret = read_cache_pages(mapping, pages, afs_page_filler, key);
+	while (!list_empty(pages)) {
+		ret = afs_readpages_one(file, mapping, pages);
+		if (ret < 0)
+			break;
+	}
 
 	_leave(" = %d [netting]", ret);
 	return ret;
diff --git a/fs/afs/fsclient.c b/fs/afs/fsclient.c
index 31c616ab9b40..19f76ae36982 100644
--- a/fs/afs/fsclient.c
+++ b/fs/afs/fsclient.c
@@ -17,6 +17,12 @@
 #include "afs_fs.h"
 
 /*
+ * We need somewhere to discard into in case the server helpfully returns more
+ * than we asked for in FS.FetchData{,64}.
+ */
+static u8 afs_discard_buffer[64];
+
+/*
  * decode an AFSFid block
  */
 static void xdr_decode_AFSFid(const __be32 **_bp, struct afs_fid *fid)
@@ -105,7 +111,7 @@ static void xdr_decode_AFSFetchStatus(const __be32 **_bp,
 			vnode->vfs_inode.i_mode = mode;
 		}
 
-		vnode->vfs_inode.i_ctime.tv_sec	= status->mtime_server;
+		vnode->vfs_inode.i_ctime.tv_sec	= status->mtime_client;
 		vnode->vfs_inode.i_mtime	= vnode->vfs_inode.i_ctime;
 		vnode->vfs_inode.i_atime	= vnode->vfs_inode.i_ctime;
 		vnode->vfs_inode.i_version	= data_version;
@@ -139,7 +145,7 @@ static void xdr_decode_AFSCallBack(const __be32 **_bp, struct afs_vnode *vnode)
 	vnode->cb_version	= ntohl(*bp++);
 	vnode->cb_expiry	= ntohl(*bp++);
 	vnode->cb_type		= ntohl(*bp++);
-	vnode->cb_expires	= vnode->cb_expiry + get_seconds();
+	vnode->cb_expires	= vnode->cb_expiry + ktime_get_real_seconds();
 	*_bp = bp;
 }
 
@@ -275,7 +281,7 @@ int afs_fs_fetch_file_status(struct afs_server *server,
 			     struct key *key,
 			     struct afs_vnode *vnode,
 			     struct afs_volsync *volsync,
-			     const struct afs_wait_mode *wait_mode)
+			     bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -300,7 +306,7 @@ int afs_fs_fetch_file_status(struct afs_server *server,
 	bp[2] = htonl(vnode->fid.vnode);
 	bp[3] = htonl(vnode->fid.unique);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -309,15 +315,19 @@ int afs_fs_fetch_file_status(struct afs_server *server,
 static int afs_deliver_fs_fetch_data(struct afs_call *call)
 {
 	struct afs_vnode *vnode = call->reply;
+	struct afs_read *req = call->reply3;
 	const __be32 *bp;
-	struct page *page;
+	unsigned int size;
 	void *buffer;
 	int ret;
 
-	_enter("{%u}", call->unmarshall);
+	_enter("{%u,%zu/%u;%llu/%llu}",
+	       call->unmarshall, call->offset, call->count,
+	       req->remain, req->actual_len);
 
 	switch (call->unmarshall) {
 	case 0:
+		req->actual_len = 0;
 		call->offset = 0;
 		call->unmarshall++;
 		if (call->operation_ID != FSFETCHDATA64) {
@@ -334,10 +344,8 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		if (ret < 0)
 			return ret;
 
-		call->count = ntohl(call->tmp);
-		_debug("DATA length MSW: %u", call->count);
-		if (call->count > 0)
-			return -EBADMSG;
+		req->actual_len = ntohl(call->tmp);
+		req->actual_len <<= 32;
 		call->offset = 0;
 		call->unmarshall++;
 
@@ -349,31 +357,73 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		if (ret < 0)
 			return ret;
 
-		call->count = ntohl(call->tmp);
-		_debug("DATA length: %u", call->count);
-		if (call->count > PAGE_SIZE)
-			return -EBADMSG;
-		call->offset = 0;
+		req->actual_len |= ntohl(call->tmp);
+		_debug("DATA length: %llu", req->actual_len);
+
+		req->remain = req->actual_len;
+		call->offset = req->pos & (PAGE_SIZE - 1);
+		req->index = 0;
+		if (req->actual_len == 0)
+			goto no_more_data;
 		call->unmarshall++;
 
+	begin_page:
+		ASSERTCMP(req->index, <, req->nr_pages);
+		if (req->remain > PAGE_SIZE - call->offset)
+			size = PAGE_SIZE - call->offset;
+		else
+			size = req->remain;
+		call->count = call->offset + size;
+		ASSERTCMP(call->count, <=, PAGE_SIZE);
+		req->remain -= size;
+
 		/* extract the returned data */
 	case 3:
-		_debug("extract data");
-		if (call->count > 0) {
-			page = call->reply3;
-			buffer = kmap(page);
-			ret = afs_extract_data(call, buffer,
-					       call->count, true);
-			kunmap(page);
-			if (ret < 0)
-				return ret;
+		_debug("extract data %llu/%llu %zu/%u",
+		       req->remain, req->actual_len, call->offset, call->count);
+
+		buffer = kmap(req->pages[req->index]);
+		ret = afs_extract_data(call, buffer, call->count, true);
+		kunmap(req->pages[req->index]);
+		if (ret < 0)
+			return ret;
+		if (call->offset == PAGE_SIZE) {
+			if (req->page_done)
+				req->page_done(call, req);
+			req->index++;
+			if (req->remain > 0) {
+				call->offset = 0;
+				if (req->index >= req->nr_pages) {
+					call->unmarshall = 4;
+					goto begin_discard;
+				}
+				goto begin_page;
+			}
 		}
+		goto no_more_data;
+
+		/* Discard any excess data the server gave us */
+	begin_discard:
+	case 4:
+		size = min_t(loff_t, sizeof(afs_discard_buffer), req->remain);
+		call->count = size;
+		_debug("extract discard %llu/%llu %zu/%u",
+		       req->remain, req->actual_len, call->offset, call->count);
 
 		call->offset = 0;
-		call->unmarshall++;
+		ret = afs_extract_data(call, afs_discard_buffer, call->count, true);
+		req->remain -= call->offset;
+		if (ret < 0)
+			return ret;
+		if (req->remain > 0)
+			goto begin_discard;
+
+	no_more_data:
+		call->offset = 0;
+		call->unmarshall = 5;
 
 		/* extract the metadata */
-	case 4:
+	case 5:
 		ret = afs_extract_data(call, call->buffer,
 				       (21 + 3 + 6) * 4, false);
 		if (ret < 0)
@@ -388,22 +438,31 @@ static int afs_deliver_fs_fetch_data(struct afs_call *call)
 		call->offset = 0;
 		call->unmarshall++;
 
-	case 5:
+	case 6:
 		break;
 	}
 
-	if (call->count < PAGE_SIZE) {
-		_debug("clear");
-		page = call->reply3;
-		buffer = kmap(page);
-		memset(buffer + call->count, 0, PAGE_SIZE - call->count);
-		kunmap(page);
+	for (; req->index < req->nr_pages; req->index++) {
+		if (call->count < PAGE_SIZE)
+			zero_user_segment(req->pages[req->index],
+					  call->count, PAGE_SIZE);
+		if (req->page_done)
+			req->page_done(call, req);
+		call->count = 0;
 	}
 
 	_leave(" = 0 [done]");
 	return 0;
 }
 
+static void afs_fetch_data_destructor(struct afs_call *call)
+{
+	struct afs_read *req = call->reply3;
+
+	afs_put_read(req);
+	afs_flat_call_destructor(call);
+}
+
 /*
  * FS.FetchData operation type
  */
@@ -411,14 +470,14 @@ static const struct afs_call_type afs_RXFSFetchData = {
 	.name		= "FS.FetchData",
 	.deliver	= afs_deliver_fs_fetch_data,
 	.abort_to_error	= afs_abort_to_error,
-	.destructor	= afs_flat_call_destructor,
+	.destructor	= afs_fetch_data_destructor,
 };
 
 static const struct afs_call_type afs_RXFSFetchData64 = {
 	.name		= "FS.FetchData64",
 	.deliver	= afs_deliver_fs_fetch_data,
 	.abort_to_error	= afs_abort_to_error,
-	.destructor	= afs_flat_call_destructor,
+	.destructor	= afs_fetch_data_destructor,
 };
 
 /*
@@ -427,17 +486,14 @@ static const struct afs_call_type afs_RXFSFetchData64 = {
 static int afs_fs_fetch_data64(struct afs_server *server,
 			       struct key *key,
 			       struct afs_vnode *vnode,
-			       off_t offset, size_t length,
-			       struct page *buffer,
-			       const struct afs_wait_mode *wait_mode)
+			       struct afs_read *req,
+			       bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
 
 	_enter("");
 
-	ASSERTCMP(length, <, ULONG_MAX);
-
 	call = afs_alloc_flat_call(&afs_RXFSFetchData64, 32, (21 + 3 + 6) * 4);
 	if (!call)
 		return -ENOMEM;
@@ -445,7 +501,7 @@ static int afs_fs_fetch_data64(struct afs_server *server,
 	call->key = key;
 	call->reply = vnode;
 	call->reply2 = NULL; /* volsync */
-	call->reply3 = buffer;
+	call->reply3 = req;
 	call->service_id = FS_SERVICE;
 	call->port = htons(AFS_FS_PORT);
 	call->operation_ID = FSFETCHDATA64;
@@ -456,12 +512,13 @@ static int afs_fs_fetch_data64(struct afs_server *server,
 	bp[1] = htonl(vnode->fid.vid);
 	bp[2] = htonl(vnode->fid.vnode);
 	bp[3] = htonl(vnode->fid.unique);
-	bp[4] = htonl(upper_32_bits(offset));
-	bp[5] = htonl((u32) offset);
+	bp[4] = htonl(upper_32_bits(req->pos));
+	bp[5] = htonl(lower_32_bits(req->pos));
 	bp[6] = 0;
-	bp[7] = htonl((u32) length);
+	bp[7] = htonl(lower_32_bits(req->len));
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	atomic_inc(&req->usage);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -470,16 +527,16 @@ static int afs_fs_fetch_data64(struct afs_server *server,
 int afs_fs_fetch_data(struct afs_server *server,
 		      struct key *key,
 		      struct afs_vnode *vnode,
-		      off_t offset, size_t length,
-		      struct page *buffer,
-		      const struct afs_wait_mode *wait_mode)
+		      struct afs_read *req,
+		      bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
 
-	if (upper_32_bits(offset) || upper_32_bits(offset + length))
-		return afs_fs_fetch_data64(server, key, vnode, offset, length,
-					   buffer, wait_mode);
+	if (upper_32_bits(req->pos) ||
+	    upper_32_bits(req->len) ||
+	    upper_32_bits(req->pos + req->len))
+		return afs_fs_fetch_data64(server, key, vnode, req, async);
 
 	_enter("");
 
@@ -490,7 +547,7 @@ int afs_fs_fetch_data(struct afs_server *server,
 	call->key = key;
 	call->reply = vnode;
 	call->reply2 = NULL; /* volsync */
-	call->reply3 = buffer;
+	call->reply3 = req;
 	call->service_id = FS_SERVICE;
 	call->port = htons(AFS_FS_PORT);
 	call->operation_ID = FSFETCHDATA;
@@ -501,10 +558,11 @@ int afs_fs_fetch_data(struct afs_server *server,
 	bp[1] = htonl(vnode->fid.vid);
 	bp[2] = htonl(vnode->fid.vnode);
 	bp[3] = htonl(vnode->fid.unique);
-	bp[4] = htonl(offset);
-	bp[5] = htonl(length);
+	bp[4] = htonl(lower_32_bits(req->pos));
+	bp[5] = htonl(lower_32_bits(req->len));
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	atomic_inc(&req->usage);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -533,7 +591,7 @@ static const struct afs_call_type afs_RXFSGiveUpCallBacks = {
  * - the callbacks are held in the server->cb_break ring
  */
 int afs_fs_give_up_callbacks(struct afs_server *server,
-			     const struct afs_wait_mode *wait_mode)
+			     bool async)
 {
 	struct afs_call *call;
 	size_t ncallbacks;
@@ -587,7 +645,7 @@ int afs_fs_give_up_callbacks(struct afs_server *server,
 	ASSERT(ncallbacks > 0);
 	wake_up_nr(&server->cb_break_waitq, ncallbacks);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -638,7 +696,7 @@ int afs_fs_create(struct afs_server *server,
 		  struct afs_fid *newfid,
 		  struct afs_file_status *newstatus,
 		  struct afs_callback *newcb,
-		  const struct afs_wait_mode *wait_mode)
+		  bool async)
 {
 	struct afs_call *call;
 	size_t namesz, reqsz, padsz;
@@ -676,14 +734,14 @@ int afs_fs_create(struct afs_server *server,
 		memset(bp, 0, padsz);
 		bp = (void *) bp + padsz;
 	}
-	*bp++ = htonl(AFS_SET_MODE);
-	*bp++ = 0; /* mtime */
+	*bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME);
+	*bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */
 	*bp++ = 0; /* owner */
 	*bp++ = 0; /* group */
 	*bp++ = htonl(mode & S_IALLUGO); /* unix mode */
 	*bp++ = 0; /* segment size */
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -728,7 +786,7 @@ int afs_fs_remove(struct afs_server *server,
 		  struct afs_vnode *vnode,
 		  const char *name,
 		  bool isdir,
-		  const struct afs_wait_mode *wait_mode)
+		  bool async)
 {
 	struct afs_call *call;
 	size_t namesz, reqsz, padsz;
@@ -763,7 +821,7 @@ int afs_fs_remove(struct afs_server *server,
 		bp = (void *) bp + padsz;
 	}
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -809,7 +867,7 @@ int afs_fs_link(struct afs_server *server,
 		struct afs_vnode *dvnode,
 		struct afs_vnode *vnode,
 		const char *name,
-		const struct afs_wait_mode *wait_mode)
+		bool async)
 {
 	struct afs_call *call;
 	size_t namesz, reqsz, padsz;
@@ -848,7 +906,7 @@ int afs_fs_link(struct afs_server *server,
 	*bp++ = htonl(vnode->fid.vnode);
 	*bp++ = htonl(vnode->fid.unique);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -897,7 +955,7 @@ int afs_fs_symlink(struct afs_server *server,
 		   const char *contents,
 		   struct afs_fid *newfid,
 		   struct afs_file_status *newstatus,
-		   const struct afs_wait_mode *wait_mode)
+		   bool async)
 {
 	struct afs_call *call;
 	size_t namesz, reqsz, padsz, c_namesz, c_padsz;
@@ -945,14 +1003,14 @@ int afs_fs_symlink(struct afs_server *server,
 		memset(bp, 0, c_padsz);
 		bp = (void *) bp + c_padsz;
 	}
-	*bp++ = htonl(AFS_SET_MODE);
-	*bp++ = 0; /* mtime */
+	*bp++ = htonl(AFS_SET_MODE | AFS_SET_MTIME);
+	*bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */
 	*bp++ = 0; /* owner */
 	*bp++ = 0; /* group */
 	*bp++ = htonl(S_IRWXUGO); /* unix mode */
 	*bp++ = 0; /* segment size */
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1001,7 +1059,7 @@ int afs_fs_rename(struct afs_server *server,
 		  const char *orig_name,
 		  struct afs_vnode *new_dvnode,
 		  const char *new_name,
-		  const struct afs_wait_mode *wait_mode)
+		  bool async)
 {
 	struct afs_call *call;
 	size_t reqsz, o_namesz, o_padsz, n_namesz, n_padsz;
@@ -1055,7 +1113,7 @@ int afs_fs_rename(struct afs_server *server,
 		bp = (void *) bp + n_padsz;
 	}
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1110,7 +1168,7 @@ static int afs_fs_store_data64(struct afs_server *server,
 			       pgoff_t first, pgoff_t last,
 			       unsigned offset, unsigned to,
 			       loff_t size, loff_t pos, loff_t i_size,
-			       const struct afs_wait_mode *wait_mode)
+			       bool async)
 {
 	struct afs_vnode *vnode = wb->vnode;
 	struct afs_call *call;
@@ -1145,8 +1203,8 @@ static int afs_fs_store_data64(struct afs_server *server,
 	*bp++ = htonl(vnode->fid.vnode);
 	*bp++ = htonl(vnode->fid.unique);
 
-	*bp++ = 0; /* mask */
-	*bp++ = 0; /* mtime */
+	*bp++ = htonl(AFS_SET_MTIME); /* mask */
+	*bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */
 	*bp++ = 0; /* owner */
 	*bp++ = 0; /* group */
 	*bp++ = 0; /* unix mode */
@@ -1159,7 +1217,7 @@ static int afs_fs_store_data64(struct afs_server *server,
 	*bp++ = htonl(i_size >> 32);
 	*bp++ = htonl((u32) i_size);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1168,7 +1226,7 @@ static int afs_fs_store_data64(struct afs_server *server,
 int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
 		      pgoff_t first, pgoff_t last,
 		      unsigned offset, unsigned to,
-		      const struct afs_wait_mode *wait_mode)
+		      bool async)
 {
 	struct afs_vnode *vnode = wb->vnode;
 	struct afs_call *call;
@@ -1178,7 +1236,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
 	_enter(",%x,{%x:%u},,",
 	       key_serial(wb->key), vnode->fid.vid, vnode->fid.vnode);
 
-	size = to - offset;
+	size = (loff_t)to - (loff_t)offset;
 	if (first != last)
 		size += (loff_t)(last - first) << PAGE_SHIFT;
 	pos = (loff_t)first << PAGE_SHIFT;
@@ -1194,7 +1252,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
 
 	if (pos >> 32 || i_size >> 32 || size >> 32 || (pos + size) >> 32)
 		return afs_fs_store_data64(server, wb, first, last, offset, to,
-					   size, pos, i_size, wait_mode);
+					   size, pos, i_size, async);
 
 	call = afs_alloc_flat_call(&afs_RXFSStoreData,
 				   (4 + 6 + 3) * 4,
@@ -1222,8 +1280,8 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
 	*bp++ = htonl(vnode->fid.vnode);
 	*bp++ = htonl(vnode->fid.unique);
 
-	*bp++ = 0; /* mask */
-	*bp++ = 0; /* mtime */
+	*bp++ = htonl(AFS_SET_MTIME); /* mask */
+	*bp++ = htonl(vnode->vfs_inode.i_mtime.tv_sec); /* mtime */
 	*bp++ = 0; /* owner */
 	*bp++ = 0; /* group */
 	*bp++ = 0; /* unix mode */
@@ -1233,7 +1291,7 @@ int afs_fs_store_data(struct afs_server *server, struct afs_writeback *wb,
 	*bp++ = htonl(size);
 	*bp++ = htonl(i_size);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1295,7 +1353,7 @@ static const struct afs_call_type afs_RXFSStoreData64_as_Status = {
  */
 static int afs_fs_setattr_size64(struct afs_server *server, struct key *key,
 				 struct afs_vnode *vnode, struct iattr *attr,
-				 const struct afs_wait_mode *wait_mode)
+				 bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -1334,7 +1392,7 @@ static int afs_fs_setattr_size64(struct afs_server *server, struct key *key,
 	*bp++ = htonl(attr->ia_size >> 32);	/* new file length */
 	*bp++ = htonl((u32) attr->ia_size);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1343,7 +1401,7 @@ static int afs_fs_setattr_size64(struct afs_server *server, struct key *key,
  */
 static int afs_fs_setattr_size(struct afs_server *server, struct key *key,
 			       struct afs_vnode *vnode, struct iattr *attr,
-			       const struct afs_wait_mode *wait_mode)
+			       bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -1354,7 +1412,7 @@ static int afs_fs_setattr_size(struct afs_server *server, struct key *key,
 	ASSERT(attr->ia_valid & ATTR_SIZE);
 	if (attr->ia_size >> 32)
 		return afs_fs_setattr_size64(server, key, vnode, attr,
-					     wait_mode);
+					     async);
 
 	call = afs_alloc_flat_call(&afs_RXFSStoreData_as_Status,
 				   (4 + 6 + 3) * 4,
@@ -1382,7 +1440,7 @@ static int afs_fs_setattr_size(struct afs_server *server, struct key *key,
 	*bp++ = 0;				/* size of write */
 	*bp++ = htonl(attr->ia_size);		/* new file length */
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1391,14 +1449,14 @@ static int afs_fs_setattr_size(struct afs_server *server, struct key *key,
  */
 int afs_fs_setattr(struct afs_server *server, struct key *key,
 		   struct afs_vnode *vnode, struct iattr *attr,
-		   const struct afs_wait_mode *wait_mode)
+		   bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
 
 	if (attr->ia_valid & ATTR_SIZE)
 		return afs_fs_setattr_size(server, key, vnode, attr,
-					   wait_mode);
+					   async);
 
 	_enter(",%x,{%x:%u},,",
 	       key_serial(key), vnode->fid.vid, vnode->fid.vnode);
@@ -1424,7 +1482,7 @@ int afs_fs_setattr(struct afs_server *server, struct key *key,
 
 	xdr_encode_AFS_StoreStatus(&bp, attr);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1626,7 +1684,7 @@ int afs_fs_get_volume_status(struct afs_server *server,
 			     struct key *key,
 			     struct afs_vnode *vnode,
 			     struct afs_volume_status *vs,
-			     const struct afs_wait_mode *wait_mode)
+			     bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -1656,7 +1714,7 @@ int afs_fs_get_volume_status(struct afs_server *server,
 	bp[0] = htonl(FSGETVOLUMESTATUS);
 	bp[1] = htonl(vnode->fid.vid);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1718,7 +1776,7 @@ int afs_fs_set_lock(struct afs_server *server,
 		    struct key *key,
 		    struct afs_vnode *vnode,
 		    afs_lock_type_t type,
-		    const struct afs_wait_mode *wait_mode)
+		    bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -1742,7 +1800,7 @@ int afs_fs_set_lock(struct afs_server *server,
 	*bp++ = htonl(vnode->fid.unique);
 	*bp++ = htonl(type);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1751,7 +1809,7 @@ int afs_fs_set_lock(struct afs_server *server,
 int afs_fs_extend_lock(struct afs_server *server,
 		       struct key *key,
 		       struct afs_vnode *vnode,
-		       const struct afs_wait_mode *wait_mode)
+		       bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -1774,7 +1832,7 @@ int afs_fs_extend_lock(struct afs_server *server,
 	*bp++ = htonl(vnode->fid.vnode);
 	*bp++ = htonl(vnode->fid.unique);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
 
 /*
@@ -1783,7 +1841,7 @@ int afs_fs_extend_lock(struct afs_server *server,
 int afs_fs_release_lock(struct afs_server *server,
 			struct key *key,
 			struct afs_vnode *vnode,
-			const struct afs_wait_mode *wait_mode)
+			bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -1806,5 +1864,5 @@ int afs_fs_release_lock(struct afs_server *server,
 	*bp++ = htonl(vnode->fid.vnode);
 	*bp++ = htonl(vnode->fid.unique);
 
-	return afs_make_call(&server->addr, call, GFP_NOFS, wait_mode);
+	return afs_make_call(&server->addr, call, GFP_NOFS, async);
 }
diff --git a/fs/afs/inode.c b/fs/afs/inode.c
index 86cc7264c21c..342316a9e3e0 100644
--- a/fs/afs/inode.c
+++ b/fs/afs/inode.c
@@ -28,6 +28,11 @@ struct afs_iget_data {
 	struct afs_volume	*volume;	/* volume on which resides */
 };
 
+static const struct inode_operations afs_symlink_inode_operations = {
+	.get_link	= page_get_link,
+	.listxattr	= afs_listxattr,
+};
+
 /*
  * map the AFS file status to the inode member variables
  */
@@ -54,8 +59,21 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
 		inode->i_fop	= &afs_dir_file_operations;
 		break;
 	case AFS_FTYPE_SYMLINK:
-		inode->i_mode	= S_IFLNK | vnode->status.mode;
-		inode->i_op	= &page_symlink_inode_operations;
+		/* Symlinks with a mode of 0644 are actually mountpoints. */
+		if ((vnode->status.mode & 0777) == 0644) {
+			inode->i_flags |= S_AUTOMOUNT;
+
+			spin_lock(&vnode->lock);
+			set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
+			spin_unlock(&vnode->lock);
+
+			inode->i_mode	= S_IFDIR | 0555;
+			inode->i_op	= &afs_mntpt_inode_operations;
+			inode->i_fop	= &afs_mntpt_file_operations;
+		} else {
+			inode->i_mode	= S_IFLNK | vnode->status.mode;
+			inode->i_op	= &afs_symlink_inode_operations;
+		}
 		inode_nohighmem(inode);
 		break;
 	default:
@@ -70,27 +88,15 @@ static int afs_inode_map_status(struct afs_vnode *vnode, struct key *key)
 
 	set_nlink(inode, vnode->status.nlink);
 	inode->i_uid		= vnode->status.owner;
-	inode->i_gid		= GLOBAL_ROOT_GID;
+	inode->i_gid            = vnode->status.group;
 	inode->i_size		= vnode->status.size;
-	inode->i_ctime.tv_sec	= vnode->status.mtime_server;
+	inode->i_ctime.tv_sec	= vnode->status.mtime_client;
 	inode->i_ctime.tv_nsec	= 0;
 	inode->i_atime		= inode->i_mtime = inode->i_ctime;
 	inode->i_blocks		= 0;
 	inode->i_generation	= vnode->fid.unique;
 	inode->i_version	= vnode->status.data_version;
 	inode->i_mapping->a_ops	= &afs_fs_aops;
-
-	/* check to see whether a symbolic link is really a mountpoint */
-	if (vnode->status.type == AFS_FTYPE_SYMLINK) {
-		afs_mntpt_check_symlink(vnode, key);
-
-		if (test_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags)) {
-			inode->i_mode	= S_IFDIR | vnode->status.mode;
-			inode->i_op	= &afs_mntpt_inode_operations;
-			inode->i_fop	= &afs_mntpt_file_operations;
-		}
-	}
-
 	return 0;
 }
 
@@ -245,12 +251,13 @@ struct inode *afs_iget(struct super_block *sb, struct key *key,
 			vnode->cb_version = 0;
 			vnode->cb_expiry = 0;
 			vnode->cb_type = 0;
-			vnode->cb_expires = get_seconds();
+			vnode->cb_expires = ktime_get_real_seconds();
 		} else {
 			vnode->cb_version = cb->version;
 			vnode->cb_expiry = cb->expiry;
 			vnode->cb_type = cb->type;
-			vnode->cb_expires = vnode->cb_expiry + get_seconds();
+			vnode->cb_expires = vnode->cb_expiry +
+				ktime_get_real_seconds();
 		}
 	}
 
@@ -323,7 +330,7 @@ int afs_validate(struct afs_vnode *vnode, struct key *key)
 	    !test_bit(AFS_VNODE_CB_BROKEN, &vnode->flags) &&
 	    !test_bit(AFS_VNODE_MODIFIED, &vnode->flags) &&
 	    !test_bit(AFS_VNODE_ZAP_DATA, &vnode->flags)) {
-		if (vnode->cb_expires < get_seconds() + 10) {
+		if (vnode->cb_expires < ktime_get_real_seconds() + 10) {
 			_debug("callback expired");
 			set_bit(AFS_VNODE_CB_BROKEN, &vnode->flags);
 		} else {
@@ -375,12 +382,10 @@ error_unlock:
 /*
  * read the attributes of an inode
  */
-int afs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		      struct kstat *stat)
+int afs_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode;
-
-	inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 
 	_enter("{ ino=%lu v=%u }", inode->i_ino, inode->i_generation);
 
@@ -446,7 +451,7 @@ void afs_evict_inode(struct inode *inode)
 
 	mutex_lock(&vnode->permits_lock);
 	permits = vnode->permits;
-	rcu_assign_pointer(vnode->permits, NULL);
+	RCU_INIT_POINTER(vnode->permits, NULL);
 	mutex_unlock(&vnode->permits_lock);
 	if (permits)
 		call_rcu(&permits->rcu, afs_zap_permits);
diff --git a/fs/afs/internal.h b/fs/afs/internal.h
index 535a38d2c1d0..82e16556afea 100644
--- a/fs/afs/internal.h
+++ b/fs/afs/internal.h
@@ -11,6 +11,7 @@
 
 #include <linux/compiler.h>
 #include <linux/kernel.h>
+#include <linux/ktime.h>
 #include <linux/fs.h>
 #include <linux/pagemap.h>
 #include <linux/rxrpc.h>
@@ -19,6 +20,7 @@
 #include <linux/sched.h>
 #include <linux/fscache.h>
 #include <linux/backing-dev.h>
+#include <linux/uuid.h>
 #include <net/af_rxrpc.h>
 
 #include "afs.h"
@@ -51,31 +53,22 @@ struct afs_mount_params {
 	struct key		*key;		/* key to use for secure mounting */
 };
 
-/*
- * definition of how to wait for the completion of an operation
- */
-struct afs_wait_mode {
-	/* RxRPC received message notification */
-	rxrpc_notify_rx_t notify_rx;
-
-	/* synchronous call waiter and call dispatched notification */
-	int (*wait)(struct afs_call *call);
-
-	/* asynchronous call completion */
-	void (*async_complete)(void *reply, int error);
+enum afs_call_state {
+	AFS_CALL_REQUESTING,	/* request is being sent for outgoing call */
+	AFS_CALL_AWAIT_REPLY,	/* awaiting reply to outgoing call */
+	AFS_CALL_AWAIT_OP_ID,	/* awaiting op ID on incoming call */
+	AFS_CALL_AWAIT_REQUEST,	/* awaiting request data on incoming call */
+	AFS_CALL_REPLYING,	/* replying to incoming call */
+	AFS_CALL_AWAIT_ACK,	/* awaiting final ACK of incoming call */
+	AFS_CALL_COMPLETE,	/* Completed or failed */
 };
-
-extern const struct afs_wait_mode afs_sync_call;
-extern const struct afs_wait_mode afs_async_call;
-
 /*
  * a record of an in-progress RxRPC call
  */
 struct afs_call {
 	const struct afs_call_type *type;	/* type of call */
-	const struct afs_wait_mode *wait_mode;	/* completion wait mode */
 	wait_queue_head_t	waitq;		/* processes awaiting completion */
-	struct work_struct	async_work;	/* asynchronous work processor */
+	struct work_struct	async_work;	/* async I/O processor */
 	struct work_struct	work;		/* actual work processor */
 	struct rxrpc_call	*rxcall;	/* RxRPC call handle */
 	struct key		*key;		/* security for this call */
@@ -91,25 +84,22 @@ struct afs_call {
 	pgoff_t			first;		/* first page in mapping to deal with */
 	pgoff_t			last;		/* last page in mapping to deal with */
 	size_t			offset;		/* offset into received data store */
-	enum {					/* call state */
-		AFS_CALL_REQUESTING,	/* request is being sent for outgoing call */
-		AFS_CALL_AWAIT_REPLY,	/* awaiting reply to outgoing call */
-		AFS_CALL_AWAIT_OP_ID,	/* awaiting op ID on incoming call */
-		AFS_CALL_AWAIT_REQUEST,	/* awaiting request data on incoming call */
-		AFS_CALL_REPLYING,	/* replying to incoming call */
-		AFS_CALL_AWAIT_ACK,	/* awaiting final ACK of incoming call */
-		AFS_CALL_COMPLETE,	/* Completed or failed */
-	}			state;
+	atomic_t		usage;
+	enum afs_call_state	state;
 	int			error;		/* error code */
 	u32			abort_code;	/* Remote abort ID or 0 */
 	unsigned		request_size;	/* size of request data */
 	unsigned		reply_max;	/* maximum size of reply */
 	unsigned		first_offset;	/* offset into mapping[first] */
-	unsigned		last_to;	/* amount of mapping[last] */
+	union {
+		unsigned	last_to;	/* amount of mapping[last] */
+		unsigned	count2;		/* count used in unmarshalling */
+	};
 	unsigned char		unmarshall;	/* unmarshalling phase */
 	bool			incoming;	/* T if incoming call */
 	bool			send_pages;	/* T if data from mapping should be sent */
 	bool			need_attention;	/* T if RxRPC poked us */
+	bool			async;		/* T if asynchronous */
 	u16			service_id;	/* RxRPC service ID to call */
 	__be16			port;		/* target UDP port */
 	u32			operation_ID;	/* operation ID for an incoming call */
@@ -131,6 +121,24 @@ struct afs_call_type {
 
 	/* clean up a call */
 	void (*destructor)(struct afs_call *call);
+
+	/* Work function */
+	void (*work)(struct work_struct *work);
+};
+
+/*
+ * Record of an outstanding read operation on a vnode.
+ */
+struct afs_read {
+	loff_t			pos;		/* Where to start reading */
+	loff_t			len;		/* How much we're asking for */
+	loff_t			actual_len;	/* How much we're actually getting */
+	loff_t			remain;		/* Amount remaining */
+	atomic_t		usage;
+	unsigned int		index;		/* Which page we're reading into */
+	unsigned int		nr_pages;
+	void (*page_done)(struct afs_call *, struct afs_read *);
+	struct page		*pages[];
 };
 
 /*
@@ -242,7 +250,7 @@ struct afs_cache_vhash {
  */
 struct afs_vlocation {
 	atomic_t		usage;
-	time_t			time_of_death;	/* time at which put reduced usage to 0 */
+	time64_t		time_of_death;	/* time at which put reduced usage to 0 */
 	struct list_head	link;		/* link in cell volume location list */
 	struct list_head	grave;		/* link in master graveyard list */
 	struct list_head	update;		/* link in master update list */
@@ -253,7 +261,7 @@ struct afs_vlocation {
 	struct afs_cache_vlocation vldb;	/* volume information DB record */
 	struct afs_volume	*vols[3];	/* volume access record pointer (index by type) */
 	wait_queue_head_t	waitq;		/* status change waitqueue */
-	time_t			update_at;	/* time at which record should be updated */
+	time64_t		update_at;	/* time at which record should be updated */
 	spinlock_t		lock;		/* access lock */
 	afs_vlocation_state_t	state;		/* volume location state */
 	unsigned short		upd_rej_cnt;	/* ENOMEDIUM count during update */
@@ -266,7 +274,7 @@ struct afs_vlocation {
  */
 struct afs_server {
 	atomic_t		usage;
-	time_t			time_of_death;	/* time at which put reduced usage to 0 */
+	time64_t		time_of_death;	/* time at which put reduced usage to 0 */
 	struct in_addr		addr;		/* server address */
 	struct afs_cell		*cell;		/* cell in which server resides */
 	struct list_head	link;		/* link in cell's server list */
@@ -310,7 +318,6 @@ struct afs_volume {
 	unsigned short		rjservers;	/* number of servers discarded due to -ENOMEDIUM */
 	struct afs_server	*servers[8];	/* servers on which volume resides (ordered) */
 	struct rw_semaphore	server_sem;	/* lock for accessing current server */
-	struct backing_dev_info	bdi;
 };
 
 /*
@@ -369,8 +376,8 @@ struct afs_vnode {
 	struct rb_node		server_rb;	/* link in server->fs_vnodes */
 	struct rb_node		cb_promise;	/* link in server->cb_promises */
 	struct work_struct	cb_broken_work;	/* work to be done on callback break */
-	time_t			cb_expires;	/* time at which callback expires */
-	time_t			cb_expires_at;	/* time used to order cb_promise */
+	time64_t		cb_expires;	/* time at which callback expires */
+	time64_t		cb_expires_at;	/* time used to order cb_promise */
 	unsigned		cb_version;	/* callback version */
 	unsigned		cb_expiry;	/* callback expiry time */
 	afs_callback_type_t	cb_type;	/* type of callback */
@@ -403,28 +410,13 @@ struct afs_interface {
 	unsigned	mtu;		/* MTU of interface */
 };
 
-/*
- * UUID definition [internet draft]
- * - the timestamp is a 60-bit value, split 32/16/12, and goes in 100ns
- *   increments since midnight 15th October 1582
- *   - add AFS_UUID_TO_UNIX_TIME to convert unix time in 100ns units to UUID
- *     time
- * - the clock sequence is a 14-bit counter to avoid duplicate times
- */
 struct afs_uuid {
-	u32		time_low;			/* low part of timestamp */
-	u16		time_mid;			/* mid part of timestamp */
-	u16		time_hi_and_version;		/* high part of timestamp and version  */
-#define AFS_UUID_TO_UNIX_TIME	0x01b21dd213814000ULL
-#define AFS_UUID_TIMEHI_MASK	0x0fff
-#define AFS_UUID_VERSION_TIME	0x1000	/* time-based UUID */
-#define AFS_UUID_VERSION_NAME	0x3000	/* name-based UUID */
-#define AFS_UUID_VERSION_RANDOM	0x4000	/* (pseudo-)random generated UUID */
-	u8		clock_seq_hi_and_reserved;	/* clock seq hi and variant */
-#define AFS_UUID_CLOCKHI_MASK	0x3f
-#define AFS_UUID_VARIANT_STD	0x80
-	u8		clock_seq_low;			/* clock seq low */
-	u8		node[6];			/* spatially unique node ID (MAC addr) */
+	__be32		time_low;			/* low part of timestamp */
+	__be16		time_mid;			/* mid part of timestamp */
+	__be16		time_hi_and_version;		/* high part of timestamp and version  */
+	__u8		clock_seq_hi_and_reserved;	/* clock seq hi and variant */
+	__u8		clock_seq_low;			/* clock seq low */
+	__u8		node[6];			/* spatially unique node ID (MAC addr) */
 };
 
 /*****************************************************************************/
@@ -494,6 +486,7 @@ extern const struct file_operations afs_file_operations;
 extern int afs_open(struct inode *, struct file *);
 extern int afs_release(struct inode *, struct file *);
 extern int afs_page_filler(void *, struct page *);
+extern void afs_put_read(struct afs_read *);
 
 /*
  * flock.c
@@ -509,50 +502,37 @@ extern int afs_flock(struct file *, int, struct file_lock *);
  */
 extern int afs_fs_fetch_file_status(struct afs_server *, struct key *,
 				    struct afs_vnode *, struct afs_volsync *,
-				    const struct afs_wait_mode *);
-extern int afs_fs_give_up_callbacks(struct afs_server *,
-				    const struct afs_wait_mode *);
+				    bool);
+extern int afs_fs_give_up_callbacks(struct afs_server *, bool);
 extern int afs_fs_fetch_data(struct afs_server *, struct key *,
-			     struct afs_vnode *, off_t, size_t, struct page *,
-			     const struct afs_wait_mode *);
+			     struct afs_vnode *, struct afs_read *, bool);
 extern int afs_fs_create(struct afs_server *, struct key *,
 			 struct afs_vnode *, const char *, umode_t,
 			 struct afs_fid *, struct afs_file_status *,
-			 struct afs_callback *,
-			 const struct afs_wait_mode *);
+			 struct afs_callback *, bool);
 extern int afs_fs_remove(struct afs_server *, struct key *,
-			 struct afs_vnode *, const char *, bool,
-			 const struct afs_wait_mode *);
+			 struct afs_vnode *, const char *, bool, bool);
 extern int afs_fs_link(struct afs_server *, struct key *, struct afs_vnode *,
-		       struct afs_vnode *, const char *,
-		       const struct afs_wait_mode *);
+		       struct afs_vnode *, const char *, bool);
 extern int afs_fs_symlink(struct afs_server *, struct key *,
 			  struct afs_vnode *, const char *, const char *,
-			  struct afs_fid *, struct afs_file_status *,
-			  const struct afs_wait_mode *);
+			  struct afs_fid *, struct afs_file_status *, bool);
 extern int afs_fs_rename(struct afs_server *, struct key *,
 			 struct afs_vnode *, const char *,
-			 struct afs_vnode *, const char *,
-			 const struct afs_wait_mode *);
+			 struct afs_vnode *, const char *, bool);
 extern int afs_fs_store_data(struct afs_server *, struct afs_writeback *,
-			     pgoff_t, pgoff_t, unsigned, unsigned,
-			     const struct afs_wait_mode *);
+			     pgoff_t, pgoff_t, unsigned, unsigned, bool);
 extern int afs_fs_setattr(struct afs_server *, struct key *,
-			  struct afs_vnode *, struct iattr *,
-			  const struct afs_wait_mode *);
+			  struct afs_vnode *, struct iattr *, bool);
 extern int afs_fs_get_volume_status(struct afs_server *, struct key *,
 				    struct afs_vnode *,
-				    struct afs_volume_status *,
-				    const struct afs_wait_mode *);
+				    struct afs_volume_status *, bool);
 extern int afs_fs_set_lock(struct afs_server *, struct key *,
-			   struct afs_vnode *, afs_lock_type_t,
-			   const struct afs_wait_mode *);
+			   struct afs_vnode *, afs_lock_type_t, bool);
 extern int afs_fs_extend_lock(struct afs_server *, struct key *,
-			      struct afs_vnode *,
-			      const struct afs_wait_mode *);
+			      struct afs_vnode *, bool);
 extern int afs_fs_release_lock(struct afs_server *, struct key *,
-			       struct afs_vnode *,
-			       const struct afs_wait_mode *);
+			       struct afs_vnode *, bool);
 
 /*
  * inode.c
@@ -564,7 +544,7 @@ extern struct inode *afs_iget(struct super_block *, struct key *,
 			      struct afs_callback *);
 extern void afs_zap_data(struct afs_vnode *);
 extern int afs_validate(struct afs_vnode *, struct key *);
-extern int afs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int afs_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int afs_setattr(struct dentry *, struct iattr *);
 extern void afs_evict_inode(struct inode *);
 extern int afs_drop_inode(struct inode *);
@@ -588,10 +568,14 @@ extern const struct inode_operations afs_autocell_inode_operations;
 extern const struct file_operations afs_mntpt_file_operations;
 
 extern struct vfsmount *afs_d_automount(struct path *);
-extern int afs_mntpt_check_symlink(struct afs_vnode *, struct key *);
 extern void afs_mntpt_kill_timer(void);
 
 /*
+ * netdevices.c
+ */
+extern int afs_get_ipv4_interfaces(struct afs_interface *, size_t, bool);
+
+/*
  * proc.c
  */
 extern int afs_proc_init(void);
@@ -603,11 +587,13 @@ extern void afs_proc_cell_remove(struct afs_cell *);
  * rxrpc.c
  */
 extern struct socket *afs_socket;
+extern atomic_t afs_outstanding_calls;
 
 extern int afs_open_socket(void);
 extern void afs_close_socket(void);
-extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t,
-			 const struct afs_wait_mode *);
+extern void afs_put_call(struct afs_call *);
+extern int afs_queue_call_work(struct afs_call *);
+extern int afs_make_call(struct in_addr *, struct afs_call *, gfp_t, bool);
 extern struct afs_call *afs_alloc_flat_call(const struct afs_call_type *,
 					    size_t, size_t);
 extern void afs_flat_call_destructor(struct afs_call *);
@@ -653,21 +639,14 @@ extern int afs_fs_init(void);
 extern void afs_fs_exit(void);
 
 /*
- * use-rtnetlink.c
- */
-extern int afs_get_ipv4_interfaces(struct afs_interface *, size_t, bool);
-extern int afs_get_MAC_address(u8 *, size_t);
-
-/*
  * vlclient.c
  */
 extern int afs_vl_get_entry_by_name(struct in_addr *, struct key *,
 				    const char *, struct afs_cache_vlocation *,
-				    const struct afs_wait_mode *);
+				    bool);
 extern int afs_vl_get_entry_by_id(struct in_addr *, struct key *,
 				  afs_volid_t, afs_voltype_t,
-				  struct afs_cache_vlocation *,
-				  const struct afs_wait_mode *);
+				  struct afs_cache_vlocation *, bool);
 
 /*
  * vlocation.c
@@ -699,7 +678,7 @@ extern void afs_vnode_finalise_status_update(struct afs_vnode *,
 extern int afs_vnode_fetch_status(struct afs_vnode *, struct afs_vnode *,
 				  struct key *);
 extern int afs_vnode_fetch_data(struct afs_vnode *, struct key *,
-				off_t, size_t, struct page *);
+				struct afs_read *);
 extern int afs_vnode_create(struct afs_vnode *, struct key *, const char *,
 			    umode_t, struct afs_fid *, struct afs_file_status *,
 			    struct afs_callback *, struct afs_server **);
@@ -749,13 +728,21 @@ extern int afs_writepages(struct address_space *, struct writeback_control *);
 extern void afs_pages_written_back(struct afs_vnode *, struct afs_call *);
 extern ssize_t afs_file_write(struct kiocb *, struct iov_iter *);
 extern int afs_writeback_all(struct afs_vnode *);
+extern int afs_flush(struct file *, fl_owner_t);
 extern int afs_fsync(struct file *, loff_t, loff_t, int);
 
+/*
+ * xattr.c
+ */
+extern const struct xattr_handler *afs_xattr_handlers[];
+extern ssize_t afs_listxattr(struct dentry *, char *, size_t);
 
 /*****************************************************************************/
 /*
  * debug tracing
  */
+#include <trace/events/afs.h>
+
 extern unsigned afs_debug;
 
 #define dbgprintk(FMT,...) \
diff --git a/fs/afs/main.c b/fs/afs/main.c
index 0b187ef3b5b7..9944770849da 100644
--- a/fs/afs/main.c
+++ b/fs/afs/main.c
@@ -15,6 +15,7 @@
 #include <linux/completion.h>
 #include <linux/sched.h>
 #include <linux/random.h>
+#define CREATE_TRACE_POINTS
 #include "internal.h"
 
 MODULE_DESCRIPTION("AFS Client File System");
@@ -34,49 +35,6 @@ struct afs_uuid afs_uuid;
 struct workqueue_struct *afs_wq;
 
 /*
- * get a client UUID
- */
-static int __init afs_get_client_UUID(void)
-{
-	struct timespec ts;
-	u64 uuidtime;
-	u16 clockseq;
-	int ret;
-
-	/* read the MAC address of one of the external interfaces and construct
-	 * a UUID from it */
-	ret = afs_get_MAC_address(afs_uuid.node, sizeof(afs_uuid.node));
-	if (ret < 0)
-		return ret;
-
-	getnstimeofday(&ts);
-	uuidtime = (u64) ts.tv_sec * 1000 * 1000 * 10;
-	uuidtime += ts.tv_nsec / 100;
-	uuidtime += AFS_UUID_TO_UNIX_TIME;
-	afs_uuid.time_low = uuidtime;
-	afs_uuid.time_mid = uuidtime >> 32;
-	afs_uuid.time_hi_and_version = (uuidtime >> 48) & AFS_UUID_TIMEHI_MASK;
-	afs_uuid.time_hi_and_version |= AFS_UUID_VERSION_TIME;
-
-	get_random_bytes(&clockseq, 2);
-	afs_uuid.clock_seq_low = clockseq;
-	afs_uuid.clock_seq_hi_and_reserved =
-		(clockseq >> 8) & AFS_UUID_CLOCKHI_MASK;
-	afs_uuid.clock_seq_hi_and_reserved |= AFS_UUID_VARIANT_STD;
-
-	_debug("AFS UUID: %08x-%04x-%04x-%02x%02x-%02x%02x%02x%02x%02x%02x",
-	       afs_uuid.time_low,
-	       afs_uuid.time_mid,
-	       afs_uuid.time_hi_and_version,
-	       afs_uuid.clock_seq_hi_and_reserved,
-	       afs_uuid.clock_seq_low,
-	       afs_uuid.node[0], afs_uuid.node[1], afs_uuid.node[2],
-	       afs_uuid.node[3], afs_uuid.node[4], afs_uuid.node[5]);
-
-	return 0;
-}
-
-/*
  * initialise the AFS client FS module
  */
 static int __init afs_init(void)
@@ -85,9 +43,7 @@ static int __init afs_init(void)
 
 	printk(KERN_INFO "kAFS: Red Hat AFS client v0.1 registering.\n");
 
-	ret = afs_get_client_UUID();
-	if (ret < 0)
-		return ret;
+	generate_random_uuid((unsigned char *)&afs_uuid);
 
 	/* create workqueue */
 	ret = -ENOMEM;
diff --git a/fs/afs/misc.c b/fs/afs/misc.c
index 91ea1aa0d8b3..100b207efc9e 100644
--- a/fs/afs/misc.c
+++ b/fs/afs/misc.c
@@ -84,6 +84,8 @@ int afs_abort_to_error(u32 abort_code)
 	case RXKADDATALEN:	return -EKEYREJECTED;
 	case RXKADILLEGALLEVEL:	return -EKEYREJECTED;
 
+	case RXGEN_OPCODE:	return -ENOTSUPP;
+
 	default:		return -EREMOTEIO;
 	}
 }
diff --git a/fs/afs/mntpt.c b/fs/afs/mntpt.c
index 81dd075356b9..690fea9d84c3 100644
--- a/fs/afs/mntpt.c
+++ b/fs/afs/mntpt.c
@@ -35,6 +35,7 @@ const struct inode_operations afs_mntpt_inode_operations = {
 	.lookup		= afs_mntpt_lookup,
 	.readlink	= page_readlink,
 	.getattr	= afs_getattr,
+	.listxattr	= afs_listxattr,
 };
 
 const struct inode_operations afs_autocell_inode_operations = {
@@ -47,59 +48,6 @@ static DECLARE_DELAYED_WORK(afs_mntpt_expiry_timer, afs_mntpt_expiry_timed_out);
 static unsigned long afs_mntpt_expiry_timeout = 10 * 60;
 
 /*
- * check a symbolic link to see whether it actually encodes a mountpoint
- * - sets the AFS_VNODE_MOUNTPOINT flag on the vnode appropriately
- */
-int afs_mntpt_check_symlink(struct afs_vnode *vnode, struct key *key)
-{
-	struct page *page;
-	size_t size;
-	char *buf;
-	int ret;
-
-	_enter("{%x:%u,%u}",
-	       vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique);
-
-	/* read the contents of the symlink into the pagecache */
-	page = read_cache_page(AFS_VNODE_TO_I(vnode)->i_mapping, 0,
-			       afs_page_filler, key);
-	if (IS_ERR(page)) {
-		ret = PTR_ERR(page);
-		goto out;
-	}
-
-	ret = -EIO;
-	if (PageError(page))
-		goto out_free;
-
-	buf = kmap(page);
-
-	/* examine the symlink's contents */
-	size = vnode->status.size;
-	_debug("symlink to %*.*s", (int) size, (int) size, buf);
-
-	if (size > 2 &&
-	    (buf[0] == '%' || buf[0] == '#') &&
-	    buf[size - 1] == '.'
-	    ) {
-		_debug("symlink is a mountpoint");
-		spin_lock(&vnode->lock);
-		set_bit(AFS_VNODE_MOUNTPOINT, &vnode->flags);
-		vnode->vfs_inode.i_flags |= S_AUTOMOUNT;
-		spin_unlock(&vnode->lock);
-	}
-
-	ret = 0;
-
-	kunmap(page);
-out_free:
-	put_page(page);
-out:
-	_leave(" = %d", ret);
-	return ret;
-}
-
-/*
  * no valid lookup procedure on this sort of dir
  */
 static struct dentry *afs_mntpt_lookup(struct inode *dir,
@@ -202,7 +150,7 @@ static struct vfsmount *afs_mntpt_do_automount(struct dentry *mntpt)
 
 	/* try and do the mount */
 	_debug("--- attempting mount %s -o %s ---", devname, options);
-	mnt = vfs_kern_mount(&afs_fs_type, 0, devname, options);
+	mnt = vfs_submount(mntpt, &afs_fs_type, devname, options);
 	_debug("--- mount result %p ---", mnt);
 
 	free_page((unsigned long) devname);
diff --git a/fs/afs/netdevices.c b/fs/afs/netdevices.c
index 7ad36506c256..40b2bab3e401 100644
--- a/fs/afs/netdevices.c
+++ b/fs/afs/netdevices.c
@@ -12,27 +12,6 @@
 #include "internal.h"
 
 /*
- * get a MAC address from a random ethernet interface that has a real one
- * - the buffer will normally be 6 bytes in size
- */
-int afs_get_MAC_address(u8 *mac, size_t maclen)
-{
-	struct net_device *dev;
-	int ret = -ENODEV;
-
-	BUG_ON(maclen != ETH_ALEN);
-
-	rtnl_lock();
-	dev = __dev_getfirstbyhwtype(&init_net, ARPHRD_ETHER);
-	if (dev) {
-		memcpy(mac, dev->dev_addr, maclen);
-		ret = 0;
-	}
-	rtnl_unlock();
-	return ret;
-}
-
-/*
  * get a list of this system's interface IPv4 addresses, netmasks and MTUs
  * - maxbufs must be at least 1
  * - returns the number of interface records in the buffer
diff --git a/fs/afs/rxrpc.c b/fs/afs/rxrpc.c
index 25f05a8d21b1..02781e78ffb6 100644
--- a/fs/afs/rxrpc.c
+++ b/fs/afs/rxrpc.c
@@ -10,6 +10,8 @@
  */
 
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
+
 #include <net/sock.h>
 #include <net/af_rxrpc.h>
 #include <rxrpc/packet.h>
@@ -19,35 +21,16 @@
 struct socket *afs_socket; /* my RxRPC socket */
 static struct workqueue_struct *afs_async_calls;
 static struct afs_call *afs_spare_incoming_call;
-static atomic_t afs_outstanding_calls;
+atomic_t afs_outstanding_calls;
 
-static void afs_free_call(struct afs_call *);
 static void afs_wake_up_call_waiter(struct sock *, struct rxrpc_call *, unsigned long);
 static int afs_wait_for_call_to_complete(struct afs_call *);
 static void afs_wake_up_async_call(struct sock *, struct rxrpc_call *, unsigned long);
-static int afs_dont_wait_for_call_to_complete(struct afs_call *);
 static void afs_process_async_call(struct work_struct *);
 static void afs_rx_new_call(struct sock *, struct rxrpc_call *, unsigned long);
 static void afs_rx_discard_new_call(struct rxrpc_call *, unsigned long);
 static int afs_deliver_cm_op_id(struct afs_call *);
 
-/* synchronous call management */
-const struct afs_wait_mode afs_sync_call = {
-	.notify_rx	= afs_wake_up_call_waiter,
-	.wait		= afs_wait_for_call_to_complete,
-};
-
-/* asynchronous call management */
-const struct afs_wait_mode afs_async_call = {
-	.notify_rx	= afs_wake_up_async_call,
-	.wait		= afs_dont_wait_for_call_to_complete,
-};
-
-/* asynchronous incoming call management */
-static const struct afs_wait_mode afs_async_incoming_call = {
-	.notify_rx	= afs_wake_up_async_call,
-};
-
 /* asynchronous incoming call initial processing */
 static const struct afs_call_type afs_RXCMxxxx = {
 	.name		= "CB.xxxx",
@@ -130,9 +113,11 @@ void afs_close_socket(void)
 {
 	_enter("");
 
+	kernel_listen(afs_socket, 0);
+	flush_workqueue(afs_async_calls);
+
 	if (afs_spare_incoming_call) {
-		atomic_inc(&afs_outstanding_calls);
-		afs_free_call(afs_spare_incoming_call);
+		afs_put_call(afs_spare_incoming_call);
 		afs_spare_incoming_call = NULL;
 	}
 
@@ -141,7 +126,6 @@ void afs_close_socket(void)
 			 TASK_UNINTERRUPTIBLE);
 	_debug("no outstanding calls");
 
-	flush_workqueue(afs_async_calls);
 	kernel_sock_shutdown(afs_socket, SHUT_RDWR);
 	flush_workqueue(afs_async_calls);
 	sock_release(afs_socket);
@@ -152,44 +136,79 @@ void afs_close_socket(void)
 }
 
 /*
- * free a call
+ * Allocate a call.
  */
-static void afs_free_call(struct afs_call *call)
+static struct afs_call *afs_alloc_call(const struct afs_call_type *type,
+				       gfp_t gfp)
 {
-	_debug("DONE %p{%s} [%d]",
-	       call, call->type->name, atomic_read(&afs_outstanding_calls));
+	struct afs_call *call;
+	int o;
 
-	ASSERTCMP(call->rxcall, ==, NULL);
-	ASSERT(!work_pending(&call->async_work));
-	ASSERT(call->type->name != NULL);
+	call = kzalloc(sizeof(*call), gfp);
+	if (!call)
+		return NULL;
 
-	kfree(call->request);
-	kfree(call);
+	call->type = type;
+	atomic_set(&call->usage, 1);
+	INIT_WORK(&call->async_work, afs_process_async_call);
+	init_waitqueue_head(&call->waitq);
 
-	if (atomic_dec_and_test(&afs_outstanding_calls))
-		wake_up_atomic_t(&afs_outstanding_calls);
+	o = atomic_inc_return(&afs_outstanding_calls);
+	trace_afs_call(call, afs_call_trace_alloc, 1, o,
+		       __builtin_return_address(0));
+	return call;
 }
 
 /*
- * End a call but do not free it
+ * Dispose of a reference on a call.
  */
-static void afs_end_call_nofree(struct afs_call *call)
+void afs_put_call(struct afs_call *call)
 {
-	if (call->rxcall) {
-		rxrpc_kernel_end_call(afs_socket, call->rxcall);
-		call->rxcall = NULL;
+	int n = atomic_dec_return(&call->usage);
+	int o = atomic_read(&afs_outstanding_calls);
+
+	trace_afs_call(call, afs_call_trace_put, n + 1, o,
+		       __builtin_return_address(0));
+
+	ASSERTCMP(n, >=, 0);
+	if (n == 0) {
+		ASSERT(!work_pending(&call->async_work));
+		ASSERT(call->type->name != NULL);
+
+		if (call->rxcall) {
+			rxrpc_kernel_end_call(afs_socket, call->rxcall);
+			call->rxcall = NULL;
+		}
+		if (call->type->destructor)
+			call->type->destructor(call);
+
+		kfree(call->request);
+		kfree(call);
+
+		o = atomic_dec_return(&afs_outstanding_calls);
+		trace_afs_call(call, afs_call_trace_free, 0, o,
+			       __builtin_return_address(0));
+		if (o == 0)
+			wake_up_atomic_t(&afs_outstanding_calls);
 	}
-	if (call->type->destructor)
-		call->type->destructor(call);
 }
 
 /*
- * End a call and free it
+ * Queue the call for actual work.  Returns 0 unconditionally for convenience.
  */
-static void afs_end_call(struct afs_call *call)
+int afs_queue_call_work(struct afs_call *call)
 {
-	afs_end_call_nofree(call);
-	afs_free_call(call);
+	int u = atomic_inc_return(&call->usage);
+
+	trace_afs_call(call, afs_call_trace_work, u,
+		       atomic_read(&afs_outstanding_calls),
+		       __builtin_return_address(0));
+
+	INIT_WORK(&call->work, call->type->work);
+
+	if (!queue_work(afs_wq, &call->work))
+		afs_put_call(call);
+	return 0;
 }
 
 /*
@@ -200,25 +219,19 @@ struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type,
 {
 	struct afs_call *call;
 
-	call = kzalloc(sizeof(*call), GFP_NOFS);
+	call = afs_alloc_call(type, GFP_NOFS);
 	if (!call)
 		goto nomem_call;
 
-	_debug("CALL %p{%s} [%d]",
-	       call, type->name, atomic_read(&afs_outstanding_calls));
-	atomic_inc(&afs_outstanding_calls);
-
-	call->type = type;
-	call->request_size = request_size;
-	call->reply_max = reply_max;
-
 	if (request_size) {
+		call->request_size = request_size;
 		call->request = kmalloc(request_size, GFP_NOFS);
 		if (!call->request)
 			goto nomem_free;
 	}
 
 	if (reply_max) {
+		call->reply_max = reply_max;
 		call->buffer = kmalloc(reply_max, GFP_NOFS);
 		if (!call->buffer)
 			goto nomem_free;
@@ -228,7 +241,7 @@ struct afs_call *afs_alloc_flat_call(const struct afs_call_type *type,
 	return call;
 
 nomem_free:
-	afs_free_call(call);
+	afs_put_call(call);
 nomem_call:
 	return NULL;
 }
@@ -246,68 +259,74 @@ void afs_flat_call_destructor(struct afs_call *call)
 	call->buffer = NULL;
 }
 
+#define AFS_BVEC_MAX 8
+
+/*
+ * Load the given bvec with the next few pages.
+ */
+static void afs_load_bvec(struct afs_call *call, struct msghdr *msg,
+			  struct bio_vec *bv, pgoff_t first, pgoff_t last,
+			  unsigned offset)
+{
+	struct page *pages[AFS_BVEC_MAX];
+	unsigned int nr, n, i, to, bytes = 0;
+
+	nr = min_t(pgoff_t, last - first + 1, AFS_BVEC_MAX);
+	n = find_get_pages_contig(call->mapping, first, nr, pages);
+	ASSERTCMP(n, ==, nr);
+
+	msg->msg_flags |= MSG_MORE;
+	for (i = 0; i < nr; i++) {
+		to = PAGE_SIZE;
+		if (first + i >= last) {
+			to = call->last_to;
+			msg->msg_flags &= ~MSG_MORE;
+		}
+		bv[i].bv_page = pages[i];
+		bv[i].bv_len = to - offset;
+		bv[i].bv_offset = offset;
+		bytes += to - offset;
+		offset = 0;
+	}
+
+	iov_iter_bvec(&msg->msg_iter, WRITE | ITER_BVEC, bv, nr, bytes);
+}
+
 /*
  * attach the data from a bunch of pages on an inode to a call
  */
-static int afs_send_pages(struct afs_call *call, struct msghdr *msg,
-			  struct kvec *iov)
+static int afs_send_pages(struct afs_call *call, struct msghdr *msg)
 {
-	struct page *pages[8];
-	unsigned count, n, loop, offset, to;
+	struct bio_vec bv[AFS_BVEC_MAX];
+	unsigned int bytes, nr, loop, offset;
 	pgoff_t first = call->first, last = call->last;
 	int ret;
 
-	_enter("");
-
 	offset = call->first_offset;
 	call->first_offset = 0;
 
 	do {
-		_debug("attach %lx-%lx", first, last);
-
-		count = last - first + 1;
-		if (count > ARRAY_SIZE(pages))
-			count = ARRAY_SIZE(pages);
-		n = find_get_pages_contig(call->mapping, first, count, pages);
-		ASSERTCMP(n, ==, count);
-
-		loop = 0;
-		do {
-			msg->msg_flags = 0;
-			to = PAGE_SIZE;
-			if (first + loop >= last)
-				to = call->last_to;
-			else
-				msg->msg_flags = MSG_MORE;
-			iov->iov_base = kmap(pages[loop]) + offset;
-			iov->iov_len = to - offset;
-			offset = 0;
-
-			_debug("- range %u-%u%s",
-			       offset, to, msg->msg_flags ? " [more]" : "");
-			iov_iter_kvec(&msg->msg_iter, WRITE | ITER_KVEC,
-				      iov, 1, to - offset);
-
-			/* have to change the state *before* sending the last
-			 * packet as RxRPC might give us the reply before it
-			 * returns from sending the request */
-			if (first + loop >= last)
-				call->state = AFS_CALL_AWAIT_REPLY;
-			ret = rxrpc_kernel_send_data(afs_socket, call->rxcall,
-						     msg, to - offset);
-			kunmap(pages[loop]);
-			if (ret < 0)
-				break;
-		} while (++loop < count);
-		first += count;
-
-		for (loop = 0; loop < count; loop++)
-			put_page(pages[loop]);
+		afs_load_bvec(call, msg, bv, first, last, offset);
+		offset = 0;
+		bytes = msg->msg_iter.count;
+		nr = msg->msg_iter.nr_segs;
+
+		/* Have to change the state *before* sending the last
+		 * packet as RxRPC might give us the reply before it
+		 * returns from sending the request.
+		 */
+		if (first + nr - 1 >= last)
+			call->state = AFS_CALL_AWAIT_REPLY;
+		ret = rxrpc_kernel_send_data(afs_socket, call->rxcall,
+					     msg, bytes);
+		for (loop = 0; loop < nr; loop++)
+			put_page(bv[loop].bv_page);
 		if (ret < 0)
 			break;
+
+		first += nr;
 	} while (first <= last);
 
-	_leave(" = %d", ret);
 	return ret;
 }
 
@@ -315,12 +334,15 @@ static int afs_send_pages(struct afs_call *call, struct msghdr *msg,
  * initiate a call
  */
 int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
-		  const struct afs_wait_mode *wait_mode)
+		  bool async)
 {
 	struct sockaddr_rxrpc srx;
 	struct rxrpc_call *rxcall;
 	struct msghdr msg;
 	struct kvec iov[1];
+	size_t offset;
+	s64 tx_total_len;
+	u32 abort_code;
 	int ret;
 
 	_enter("%x,{%d},", addr->s_addr, ntohs(call->port));
@@ -332,8 +354,7 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 	       call, call->type->name, key_serial(call->key),
 	       atomic_read(&afs_outstanding_calls));
 
-	call->wait_mode = wait_mode;
-	INIT_WORK(&call->async_work, afs_process_async_call);
+	call->async = async;
 
 	memset(&srx, 0, sizeof(srx));
 	srx.srx_family = AF_RXRPC;
@@ -344,10 +365,23 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 	srx.transport.sin.sin_port = call->port;
 	memcpy(&srx.transport.sin.sin_addr, addr, 4);
 
+	/* Work out the length we're going to transmit.  This is awkward for
+	 * calls such as FS.StoreData where there's an extra injection of data
+	 * after the initial fixed part.
+	 */
+	tx_total_len = call->request_size;
+	if (call->send_pages) {
+		tx_total_len += call->last_to - call->first_offset;
+		tx_total_len += (call->last - call->first) * PAGE_SIZE;
+	}
+
 	/* create a call */
 	rxcall = rxrpc_kernel_begin_call(afs_socket, &srx, call->key,
-					 (unsigned long) call, gfp,
-					 wait_mode->notify_rx);
+					 (unsigned long)call,
+					 tx_total_len, gfp,
+					 (async ?
+					  afs_wake_up_async_call :
+					  afs_wake_up_call_waiter));
 	call->key = NULL;
 	if (IS_ERR(rxcall)) {
 		ret = PTR_ERR(rxcall);
@@ -368,9 +402,11 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 	msg.msg_controllen	= 0;
 	msg.msg_flags		= (call->send_pages ? MSG_MORE : 0);
 
-	/* have to change the state *before* sending the last packet as RxRPC
-	 * might give us the reply before it returns from sending the
-	 * request */
+	/* We have to change the state *before* sending the last packet as
+	 * rxrpc might give us the reply before it returns from sending the
+	 * request.  Further, if the send fails, we may already have been given
+	 * a notification and may have collected it.
+	 */
 	if (!call->send_pages)
 		call->state = AFS_CALL_AWAIT_REPLY;
 	ret = rxrpc_kernel_send_data(afs_socket, rxcall,
@@ -379,19 +415,32 @@ int afs_make_call(struct in_addr *addr, struct afs_call *call, gfp_t gfp,
 		goto error_do_abort;
 
 	if (call->send_pages) {
-		ret = afs_send_pages(call, &msg, iov);
+		ret = afs_send_pages(call, &msg);
 		if (ret < 0)
 			goto error_do_abort;
 	}
 
 	/* at this point, an async call may no longer exist as it may have
 	 * already completed */
-	return wait_mode->wait(call);
+	if (call->async)
+		return -EINPROGRESS;
+
+	return afs_wait_for_call_to_complete(call);
 
 error_do_abort:
-	rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT, -ret, "KSD");
+	call->state = AFS_CALL_COMPLETE;
+	if (ret != -ECONNABORTED) {
+		rxrpc_kernel_abort_call(afs_socket, rxcall, RX_USER_ABORT,
+					ret, "KSD");
+	} else {
+		abort_code = 0;
+		offset = 0;
+		rxrpc_kernel_recv_data(afs_socket, rxcall, NULL, 0, &offset,
+				       false, &abort_code);
+		ret = call->type->abort_to_error(abort_code);
+	}
 error_kill_call:
-	afs_end_call(call);
+	afs_put_call(call);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -416,6 +465,8 @@ static void afs_deliver_to_call(struct afs_call *call)
 			ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall,
 						     NULL, 0, &offset, false,
 						     &call->abort_code);
+			trace_afs_recv_data(call, 0, offset, false, ret);
+
 			if (ret == -EINPROGRESS || ret == -EAGAIN)
 				return;
 			if (ret == 1 || ret < 0) {
@@ -434,16 +485,18 @@ static void afs_deliver_to_call(struct afs_call *call)
 		case -EINPROGRESS:
 		case -EAGAIN:
 			goto out;
+		case -ECONNABORTED:
+			goto call_complete;
 		case -ENOTCONN:
 			abort_code = RX_CALL_DEAD;
 			rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-						abort_code, -ret, "KNC");
-			goto do_abort;
+						abort_code, ret, "KNC");
+			goto save_error;
 		case -ENOTSUPP:
-			abort_code = RX_INVALID_OPERATION;
+			abort_code = RXGEN_OPCODE;
 			rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-						abort_code, -ret, "KIV");
-			goto do_abort;
+						abort_code, ret, "KIV");
+			goto save_error;
 		case -ENODATA:
 		case -EBADMSG:
 		case -EMSGSIZE:
@@ -452,20 +505,21 @@ static void afs_deliver_to_call(struct afs_call *call)
 			if (call->state != AFS_CALL_AWAIT_REPLY)
 				abort_code = RXGEN_SS_UNMARSHAL;
 			rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-						abort_code, EBADMSG, "KUM");
-			goto do_abort;
+						abort_code, -EBADMSG, "KUM");
+			goto save_error;
 		}
 	}
 
 done:
 	if (call->state == AFS_CALL_COMPLETE && call->incoming)
-		afs_end_call(call);
+		afs_put_call(call);
 out:
 	_leave("");
 	return;
 
-do_abort:
+save_error:
 	call->error = ret;
+call_complete:
 	call->state = AFS_CALL_COMPLETE;
 	goto done;
 }
@@ -475,7 +529,6 @@ do_abort:
  */
 static int afs_wait_for_call_to_complete(struct afs_call *call)
 {
-	const char *abort_why;
 	int ret;
 
 	DECLARE_WAITQUEUE(myself, current);
@@ -494,13 +547,8 @@ static int afs_wait_for_call_to_complete(struct afs_call *call)
 			continue;
 		}
 
-		abort_why = "KWC";
-		ret = call->error;
-		if (call->state == AFS_CALL_COMPLETE)
-			break;
-		abort_why = "KWI";
-		ret = -EINTR;
-		if (signal_pending(current))
+		if (call->state == AFS_CALL_COMPLETE ||
+		    signal_pending(current))
 			break;
 		schedule();
 	}
@@ -508,15 +556,16 @@ static int afs_wait_for_call_to_complete(struct afs_call *call)
 	remove_wait_queue(&call->waitq, &myself);
 	__set_current_state(TASK_RUNNING);
 
-	/* kill the call */
+	/* Kill off the call if it's still live. */
 	if (call->state < AFS_CALL_COMPLETE) {
-		_debug("call incomplete");
+		_debug("call interrupted");
 		rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-					RX_CALL_DEAD, -ret, abort_why);
+					RX_USER_ABORT, -EINTR, "KWI");
 	}
 
+	ret = call->error;
 	_debug("call complete");
-	afs_end_call(call);
+	afs_put_call(call);
 	_leave(" = %d", ret);
 	return ret;
 }
@@ -540,24 +589,25 @@ static void afs_wake_up_async_call(struct sock *sk, struct rxrpc_call *rxcall,
 				   unsigned long call_user_ID)
 {
 	struct afs_call *call = (struct afs_call *)call_user_ID;
+	int u;
 
+	trace_afs_notify_call(rxcall, call);
 	call->need_attention = true;
-	queue_work(afs_async_calls, &call->async_work);
-}
 
-/*
- * put a call into asynchronous mode
- * - mustn't touch the call descriptor as the call my have completed by the
- *   time we get here
- */
-static int afs_dont_wait_for_call_to_complete(struct afs_call *call)
-{
-	_enter("");
-	return -EINPROGRESS;
+	u = __atomic_add_unless(&call->usage, 1, 0);
+	if (u != 0) {
+		trace_afs_call(call, afs_call_trace_wake, u,
+			       atomic_read(&afs_outstanding_calls),
+			       __builtin_return_address(0));
+
+		if (!queue_work(afs_async_calls, &call->async_work))
+			afs_put_call(call);
+	}
 }
 
 /*
- * delete an asynchronous call
+ * Delete an asynchronous call.  The work item carries a ref to the call struct
+ * that we need to release.
  */
 static void afs_delete_async_call(struct work_struct *work)
 {
@@ -565,13 +615,14 @@ static void afs_delete_async_call(struct work_struct *work)
 
 	_enter("");
 
-	afs_free_call(call);
+	afs_put_call(call);
 
 	_leave("");
 }
 
 /*
- * perform processing on an asynchronous call
+ * Perform I/O processing on an asynchronous call.  The work item carries a ref
+ * to the call struct that we either need to release or to pass on.
  */
 static void afs_process_async_call(struct work_struct *work)
 {
@@ -584,21 +635,19 @@ static void afs_process_async_call(struct work_struct *work)
 		afs_deliver_to_call(call);
 	}
 
-	if (call->state == AFS_CALL_COMPLETE && call->wait_mode) {
-		if (call->wait_mode->async_complete)
-			call->wait_mode->async_complete(call->reply,
-							call->error);
+	if (call->state == AFS_CALL_COMPLETE) {
 		call->reply = NULL;
 
-		/* kill the call */
-		afs_end_call_nofree(call);
-
-		/* we can't just delete the call because the work item may be
-		 * queued */
+		/* We have two refs to release - one from the alloc and one
+		 * queued with the work item - and we can't just deallocate the
+		 * call because the work item may be queued again.
+		 */
 		call->async_work.func = afs_delete_async_call;
-		queue_work(afs_async_calls, &call->async_work);
+		if (!queue_work(afs_async_calls, &call->async_work))
+			afs_put_call(call);
 	}
 
+	afs_put_call(call);
 	_leave("");
 }
 
@@ -618,15 +667,13 @@ static void afs_charge_preallocation(struct work_struct *work)
 
 	for (;;) {
 		if (!call) {
-			call = kzalloc(sizeof(struct afs_call), GFP_KERNEL);
+			call = afs_alloc_call(&afs_RXCMxxxx, GFP_KERNEL);
 			if (!call)
 				break;
 
-			INIT_WORK(&call->async_work, afs_process_async_call);
-			call->wait_mode = &afs_async_incoming_call;
-			call->type = &afs_RXCMxxxx;
-			init_waitqueue_head(&call->waitq);
+			call->async = true;
 			call->state = AFS_CALL_AWAIT_OP_ID;
+			init_waitqueue_head(&call->waitq);
 		}
 
 		if (rxrpc_kernel_charge_accept(afs_socket,
@@ -648,9 +695,8 @@ static void afs_rx_discard_new_call(struct rxrpc_call *rxcall,
 {
 	struct afs_call *call = (struct afs_call *)user_call_ID;
 
-	atomic_inc(&afs_outstanding_calls);
 	call->rxcall = NULL;
-	afs_free_call(call);
+	afs_put_call(call);
 }
 
 /*
@@ -659,7 +705,6 @@ static void afs_rx_discard_new_call(struct rxrpc_call *rxcall,
 static void afs_rx_new_call(struct sock *sk, struct rxrpc_call *rxcall,
 			    unsigned long user_call_ID)
 {
-	atomic_inc(&afs_outstanding_calls);
 	queue_work(afs_wq, &afs_charge_preallocation_work);
 }
 
@@ -689,6 +734,8 @@ static int afs_deliver_cm_op_id(struct afs_call *call)
 	if (!afs_cm_incoming_call(call))
 		return -ENOTSUPP;
 
+	trace_afs_cb_call(call);
+
 	/* pass responsibility for the remainer of this message off to the
 	 * cache manager op */
 	return call->type->deliver(call);
@@ -703,6 +750,8 @@ void afs_send_empty_reply(struct afs_call *call)
 
 	_enter("");
 
+	rxrpc_kernel_set_tx_length(afs_socket, call->rxcall, 0);
+
 	msg.msg_name		= NULL;
 	msg.msg_namelen		= 0;
 	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, NULL, 0, 0);
@@ -719,9 +768,8 @@ void afs_send_empty_reply(struct afs_call *call)
 	case -ENOMEM:
 		_debug("oom");
 		rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-					RX_USER_ABORT, ENOMEM, "KOO");
+					RX_USER_ABORT, -ENOMEM, "KOO");
 	default:
-		afs_end_call(call);
 		_leave(" [error]");
 		return;
 	}
@@ -738,6 +786,8 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 
 	_enter("");
 
+	rxrpc_kernel_set_tx_length(afs_socket, call->rxcall, len);
+
 	iov[0].iov_base		= (void *) buf;
 	iov[0].iov_len		= len;
 	msg.msg_name		= NULL;
@@ -758,9 +808,8 @@ void afs_send_simple_reply(struct afs_call *call, const void *buf, size_t len)
 	if (n == -ENOMEM) {
 		_debug("oom");
 		rxrpc_kernel_abort_call(afs_socket, call->rxcall,
-					RX_USER_ABORT, ENOMEM, "KOO");
+					RX_USER_ABORT, -ENOMEM, "KOO");
 	}
-	afs_end_call(call);
 	_leave(" [error]");
 }
 
@@ -780,6 +829,7 @@ int afs_extract_data(struct afs_call *call, void *buf, size_t count,
 	ret = rxrpc_kernel_recv_data(afs_socket, call->rxcall,
 				     buf, count, &call->offset,
 				     want_more, &call->abort_code);
+	trace_afs_recv_data(call, count, call->offset, want_more, ret);
 	if (ret == 0 || ret == -EAGAIN)
 		return ret;
 
diff --git a/fs/afs/security.c b/fs/afs/security.c
index 8d010422dc89..faca66227ecf 100644
--- a/fs/afs/security.c
+++ b/fs/afs/security.c
@@ -114,7 +114,7 @@ void afs_clear_permits(struct afs_vnode *vnode)
 
 	mutex_lock(&vnode->permits_lock);
 	permits = vnode->permits;
-	rcu_assign_pointer(vnode->permits, NULL);
+	RCU_INIT_POINTER(vnode->permits, NULL);
 	mutex_unlock(&vnode->permits_lock);
 
 	if (permits)
@@ -327,12 +327,11 @@ int afs_permission(struct inode *inode, int mask)
 			if (!(access & AFS_ACE_LOOKUP))
 				goto permission_denied;
 		} else if (mask & MAY_READ) {
-			if (!(access & AFS_ACE_READ))
+			if (!(access & AFS_ACE_LOOKUP))
 				goto permission_denied;
 		} else if (mask & MAY_WRITE) {
 			if (!(access & (AFS_ACE_DELETE | /* rmdir, unlink, rename from */
-					AFS_ACE_INSERT | /* create, mkdir, symlink, rename to */
-					AFS_ACE_WRITE))) /* chmod */
+					AFS_ACE_INSERT))) /* create, mkdir, symlink, rename to */
 				goto permission_denied;
 		} else {
 			BUG();
@@ -340,17 +339,22 @@ int afs_permission(struct inode *inode, int mask)
 	} else {
 		if (!(access & AFS_ACE_LOOKUP))
 			goto permission_denied;
+		if ((mask & MAY_EXEC) && !(inode->i_mode & S_IXUSR))
+			goto permission_denied;
 		if (mask & (MAY_EXEC | MAY_READ)) {
 			if (!(access & AFS_ACE_READ))
 				goto permission_denied;
+			if (!(inode->i_mode & S_IRUSR))
+				goto permission_denied;
 		} else if (mask & MAY_WRITE) {
 			if (!(access & AFS_ACE_WRITE))
 				goto permission_denied;
+			if (!(inode->i_mode & S_IWUSR))
+				goto permission_denied;
 		}
 	}
 
 	key_put(key);
-	ret = generic_permission(inode, mask);
 	_leave(" = %d", ret);
 	return ret;
 
diff --git a/fs/afs/server.c b/fs/afs/server.c
index d4066ab7dd55..c001b1f2455f 100644
--- a/fs/afs/server.c
+++ b/fs/afs/server.c
@@ -242,7 +242,7 @@ void afs_put_server(struct afs_server *server)
 	spin_lock(&afs_server_graveyard_lock);
 	if (atomic_read(&server->usage) == 0) {
 		list_move_tail(&server->grave, &afs_server_graveyard);
-		server->time_of_death = get_seconds();
+		server->time_of_death = ktime_get_real_seconds();
 		queue_delayed_work(afs_wq, &afs_server_reaper,
 				   afs_server_timeout * HZ);
 	}
@@ -277,9 +277,9 @@ static void afs_reap_server(struct work_struct *work)
 	LIST_HEAD(corpses);
 	struct afs_server *server;
 	unsigned long delay, expiry;
-	time_t now;
+	time64_t now;
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 	spin_lock(&afs_server_graveyard_lock);
 
 	while (!list_empty(&afs_server_graveyard)) {
diff --git a/fs/afs/super.c b/fs/afs/super.c
index fbdb022b75a2..689173c0a682 100644
--- a/fs/afs/super.c
+++ b/fs/afs/super.c
@@ -37,6 +37,8 @@ static void afs_kill_super(struct super_block *sb);
 static struct inode *afs_alloc_inode(struct super_block *sb);
 static void afs_destroy_inode(struct inode *inode);
 static int afs_statfs(struct dentry *dentry, struct kstatfs *buf);
+static int afs_show_devname(struct seq_file *m, struct dentry *root);
+static int afs_show_options(struct seq_file *m, struct dentry *root);
 
 struct file_system_type afs_fs_type = {
 	.owner		= THIS_MODULE,
@@ -53,7 +55,8 @@ static const struct super_operations afs_super_ops = {
 	.drop_inode	= afs_drop_inode,
 	.destroy_inode	= afs_destroy_inode,
 	.evict_inode	= afs_evict_inode,
-	.show_options	= generic_show_options,
+	.show_devname	= afs_show_devname,
+	.show_options	= afs_show_options,
 };
 
 static struct kmem_cache *afs_inode_cachep;
@@ -136,6 +139,45 @@ void __exit afs_fs_exit(void)
 }
 
 /*
+ * Display the mount device name in /proc/mounts.
+ */
+static int afs_show_devname(struct seq_file *m, struct dentry *root)
+{
+	struct afs_super_info *as = root->d_sb->s_fs_info;
+	struct afs_volume *volume = as->volume;
+	struct afs_cell *cell = volume->cell;
+	const char *suf = "";
+	char pref = '%';
+
+	switch (volume->type) {
+	case AFSVL_RWVOL:
+		break;
+	case AFSVL_ROVOL:
+		pref = '#';
+		if (volume->type_force)
+			suf = ".readonly";
+		break;
+	case AFSVL_BACKVOL:
+		pref = '#';
+		suf = ".backup";
+		break;
+	}
+
+	seq_printf(m, "%c%s:%s%s", pref, cell->name, volume->vlocation->vldb.name, suf);
+	return 0;
+}
+
+/*
+ * Display the mount options in /proc/mounts.
+ */
+static int afs_show_options(struct seq_file *m, struct dentry *root)
+{
+	if (test_bit(AFS_VNODE_AUTOCELL, &AFS_FS_I(d_inode(root))->flags))
+		seq_puts(m, "autocell");
+	return 0;
+}
+
+/*
  * parse the mount options
  * - this function has been shamelessly adapted from the ext3 fs which
  *   shamelessly adapted it from the msdos fs
@@ -319,7 +361,11 @@ static int afs_fill_super(struct super_block *sb,
 	sb->s_blocksize_bits	= PAGE_SHIFT;
 	sb->s_magic		= AFS_FS_MAGIC;
 	sb->s_op		= &afs_super_ops;
-	sb->s_bdi		= &as->volume->bdi;
+	sb->s_xattr		= afs_xattr_handlers;
+	ret = super_setup_bdi(sb);
+	if (ret)
+		return ret;
+	sb->s_bdi->ra_pages	= VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
 	strlcpy(sb->s_id, as->volume->vlocation->vldb.name, sizeof(sb->s_id));
 
 	/* allocate the root inode and dentry */
@@ -423,7 +469,6 @@ static struct dentry *afs_mount(struct file_system_type *fs_type,
 			deactivate_locked_super(sb);
 			goto error;
 		}
-		save_mount_options(sb, new_opts);
 		sb->s_flags |= MS_ACTIVE;
 	} else {
 		_debug("reuse");
diff --git a/fs/afs/vlclient.c b/fs/afs/vlclient.c
index 94bcd97d22b8..a5e4cc561b6c 100644
--- a/fs/afs/vlclient.c
+++ b/fs/afs/vlclient.c
@@ -147,7 +147,7 @@ int afs_vl_get_entry_by_name(struct in_addr *addr,
 			     struct key *key,
 			     const char *volname,
 			     struct afs_cache_vlocation *entry,
-			     const struct afs_wait_mode *wait_mode)
+			     bool async)
 {
 	struct afs_call *call;
 	size_t volnamesz, reqsz, padsz;
@@ -177,7 +177,7 @@ int afs_vl_get_entry_by_name(struct in_addr *addr,
 		memset((void *) bp + volnamesz, 0, padsz);
 
 	/* initiate the call */
-	return afs_make_call(addr, call, GFP_KERNEL, wait_mode);
+	return afs_make_call(addr, call, GFP_KERNEL, async);
 }
 
 /*
@@ -188,7 +188,7 @@ int afs_vl_get_entry_by_id(struct in_addr *addr,
 			   afs_volid_t volid,
 			   afs_voltype_t voltype,
 			   struct afs_cache_vlocation *entry,
-			   const struct afs_wait_mode *wait_mode)
+			   bool async)
 {
 	struct afs_call *call;
 	__be32 *bp;
@@ -211,5 +211,5 @@ int afs_vl_get_entry_by_id(struct in_addr *addr,
 	*bp   = htonl(voltype);
 
 	/* initiate the call */
-	return afs_make_call(addr, call, GFP_KERNEL, wait_mode);
+	return afs_make_call(addr, call, GFP_KERNEL, async);
 }
diff --git a/fs/afs/vlocation.c b/fs/afs/vlocation.c
index 45a86396fd2d..37b7c3b342a6 100644
--- a/fs/afs/vlocation.c
+++ b/fs/afs/vlocation.c
@@ -53,7 +53,7 @@ static int afs_vlocation_access_vl_by_name(struct afs_vlocation *vl,
 
 		/* attempt to access the VL server */
 		ret = afs_vl_get_entry_by_name(&addr, key, vl->vldb.name, vldb,
-					       &afs_sync_call);
+					       false);
 		switch (ret) {
 		case 0:
 			goto out;
@@ -111,7 +111,7 @@ static int afs_vlocation_access_vl_by_id(struct afs_vlocation *vl,
 
 		/* attempt to access the VL server */
 		ret = afs_vl_get_entry_by_id(&addr, key, volid, voltype, vldb,
-					     &afs_sync_call);
+					     false);
 		switch (ret) {
 		case 0:
 			goto out;
@@ -340,7 +340,8 @@ static void afs_vlocation_queue_for_updates(struct afs_vlocation *vl)
 	struct afs_vlocation *xvl;
 
 	/* wait at least 10 minutes before updating... */
-	vl->update_at = get_seconds() + afs_vlocation_update_timeout;
+	vl->update_at = ktime_get_real_seconds() +
+			afs_vlocation_update_timeout;
 
 	spin_lock(&afs_vlocation_updates_lock);
 
@@ -506,7 +507,7 @@ void afs_put_vlocation(struct afs_vlocation *vl)
 	if (atomic_read(&vl->usage) == 0) {
 		_debug("buried");
 		list_move_tail(&vl->grave, &afs_vlocation_graveyard);
-		vl->time_of_death = get_seconds();
+		vl->time_of_death = ktime_get_real_seconds();
 		queue_delayed_work(afs_wq, &afs_vlocation_reap,
 				   afs_vlocation_timeout * HZ);
 
@@ -543,11 +544,11 @@ static void afs_vlocation_reaper(struct work_struct *work)
 	LIST_HEAD(corpses);
 	struct afs_vlocation *vl;
 	unsigned long delay, expiry;
-	time_t now;
+	time64_t now;
 
 	_enter("");
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 	spin_lock(&afs_vlocation_graveyard_lock);
 
 	while (!list_empty(&afs_vlocation_graveyard)) {
@@ -622,13 +623,13 @@ static void afs_vlocation_updater(struct work_struct *work)
 {
 	struct afs_cache_vlocation vldb;
 	struct afs_vlocation *vl, *xvl;
-	time_t now;
+	time64_t now;
 	long timeout;
 	int ret;
 
 	_enter("");
 
-	now = get_seconds();
+	now = ktime_get_real_seconds();
 
 	/* find a record to update */
 	spin_lock(&afs_vlocation_updates_lock);
@@ -684,7 +685,8 @@ static void afs_vlocation_updater(struct work_struct *work)
 
 	/* and then reschedule */
 	_debug("reschedule");
-	vl->update_at = get_seconds() + afs_vlocation_update_timeout;
+	vl->update_at = ktime_get_real_seconds() +
+			afs_vlocation_update_timeout;
 
 	spin_lock(&afs_vlocation_updates_lock);
 
diff --git a/fs/afs/vnode.c b/fs/afs/vnode.c
index 25cf4c3f4ff7..dcb956143c86 100644
--- a/fs/afs/vnode.c
+++ b/fs/afs/vnode.c
@@ -358,7 +358,7 @@ get_anyway:
 		       server, ntohl(server->addr.s_addr));
 
 		ret = afs_fs_fetch_file_status(server, key, vnode, NULL,
-					       &afs_sync_call);
+					       false);
 
 	} while (!afs_volume_release_fileserver(vnode, server, ret));
 
@@ -393,7 +393,7 @@ no_server:
  * - TODO implement caching
  */
 int afs_vnode_fetch_data(struct afs_vnode *vnode, struct key *key,
-			 off_t offset, size_t length, struct page *page)
+			 struct afs_read *desc)
 {
 	struct afs_server *server;
 	int ret;
@@ -420,8 +420,8 @@ int afs_vnode_fetch_data(struct afs_vnode *vnode, struct key *key,
 
 		_debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
 
-		ret = afs_fs_fetch_data(server, key, vnode, offset, length,
-					page, &afs_sync_call);
+		ret = afs_fs_fetch_data(server, key, vnode, desc,
+					false);
 
 	} while (!afs_volume_release_fileserver(vnode, server, ret));
 
@@ -477,7 +477,7 @@ int afs_vnode_create(struct afs_vnode *vnode, struct key *key,
 		_debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
 
 		ret = afs_fs_create(server, key, vnode, name, mode, newfid,
-				    newstatus, newcb, &afs_sync_call);
+				    newstatus, newcb, false);
 
 	} while (!afs_volume_release_fileserver(vnode, server, ret));
 
@@ -533,7 +533,7 @@ int afs_vnode_remove(struct afs_vnode *vnode, struct key *key, const char *name,
 		_debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
 
 		ret = afs_fs_remove(server, key, vnode, name, isdir,
-				    &afs_sync_call);
+				    false);
 
 	} while (!afs_volume_release_fileserver(vnode, server, ret));
 
@@ -595,7 +595,7 @@ int afs_vnode_link(struct afs_vnode *dvnode, struct afs_vnode *vnode,
 		_debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
 
 		ret = afs_fs_link(server, key, dvnode, vnode, name,
-				  &afs_sync_call);
+				  false);
 
 	} while (!afs_volume_release_fileserver(dvnode, server, ret));
 
@@ -659,7 +659,7 @@ int afs_vnode_symlink(struct afs_vnode *vnode, struct key *key,
 		_debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
 
 		ret = afs_fs_symlink(server, key, vnode, name, content,
-				     newfid, newstatus, &afs_sync_call);
+				     newfid, newstatus, false);
 
 	} while (!afs_volume_release_fileserver(vnode, server, ret));
 
@@ -729,7 +729,7 @@ int afs_vnode_rename(struct afs_vnode *orig_dvnode,
 		_debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
 
 		ret = afs_fs_rename(server, key, orig_dvnode, orig_name,
-				    new_dvnode, new_name, &afs_sync_call);
+				    new_dvnode, new_name, false);
 
 	} while (!afs_volume_release_fileserver(orig_dvnode, server, ret));
 
@@ -795,7 +795,7 @@ int afs_vnode_store_data(struct afs_writeback *wb, pgoff_t first, pgoff_t last,
 		_debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
 
 		ret = afs_fs_store_data(server, wb, first, last, offset, to,
-					&afs_sync_call);
+					false);
 
 	} while (!afs_volume_release_fileserver(vnode, server, ret));
 
@@ -847,7 +847,7 @@ int afs_vnode_setattr(struct afs_vnode *vnode, struct key *key,
 
 		_debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
 
-		ret = afs_fs_setattr(server, key, vnode, attr, &afs_sync_call);
+		ret = afs_fs_setattr(server, key, vnode, attr, false);
 
 	} while (!afs_volume_release_fileserver(vnode, server, ret));
 
@@ -894,7 +894,7 @@ int afs_vnode_get_volume_status(struct afs_vnode *vnode, struct key *key,
 
 		_debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
 
-		ret = afs_fs_get_volume_status(server, key, vnode, vs, &afs_sync_call);
+		ret = afs_fs_get_volume_status(server, key, vnode, vs, false);
 
 	} while (!afs_volume_release_fileserver(vnode, server, ret));
 
@@ -933,7 +933,7 @@ int afs_vnode_set_lock(struct afs_vnode *vnode, struct key *key,
 
 		_debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
 
-		ret = afs_fs_set_lock(server, key, vnode, type, &afs_sync_call);
+		ret = afs_fs_set_lock(server, key, vnode, type, false);
 
 	} while (!afs_volume_release_fileserver(vnode, server, ret));
 
@@ -971,7 +971,7 @@ int afs_vnode_extend_lock(struct afs_vnode *vnode, struct key *key)
 
 		_debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
 
-		ret = afs_fs_extend_lock(server, key, vnode, &afs_sync_call);
+		ret = afs_fs_extend_lock(server, key, vnode, false);
 
 	} while (!afs_volume_release_fileserver(vnode, server, ret));
 
@@ -1009,7 +1009,7 @@ int afs_vnode_release_lock(struct afs_vnode *vnode, struct key *key)
 
 		_debug("USING SERVER: %08x\n", ntohl(server->addr.s_addr));
 
-		ret = afs_fs_release_lock(server, key, vnode, &afs_sync_call);
+		ret = afs_fs_release_lock(server, key, vnode, false);
 
 	} while (!afs_volume_release_fileserver(vnode, server, ret));
 
diff --git a/fs/afs/volume.c b/fs/afs/volume.c
index d142a2449e65..db73d6dad02b 100644
--- a/fs/afs/volume.c
+++ b/fs/afs/volume.c
@@ -106,10 +106,6 @@ struct afs_volume *afs_volume_lookup(struct afs_mount_params *params)
 	volume->cell		= params->cell;
 	volume->vid		= vlocation->vldb.vid[params->type];
 
-	ret = bdi_setup_and_register(&volume->bdi, "afs");
-	if (ret)
-		goto error_bdi;
-
 	init_rwsem(&volume->server_sem);
 
 	/* look up all the applicable server records */
@@ -155,8 +151,6 @@ error:
 	return ERR_PTR(ret);
 
 error_discard:
-	bdi_destroy(&volume->bdi);
-error_bdi:
 	up_write(&params->cell->vl_sem);
 
 	for (loop = volume->nservers - 1; loop >= 0; loop--)
@@ -206,7 +200,6 @@ void afs_put_volume(struct afs_volume *volume)
 	for (loop = volume->nservers - 1; loop >= 0; loop--)
 		afs_put_server(volume->servers[loop]);
 
-	bdi_destroy(&volume->bdi);
 	kfree(volume);
 
 	_leave(" [destroyed]");
diff --git a/fs/afs/write.c b/fs/afs/write.c
index f865c3f05bea..2d2fccd5044b 100644
--- a/fs/afs/write.c
+++ b/fs/afs/write.c
@@ -84,21 +84,27 @@ void afs_put_writeback(struct afs_writeback *wb)
  * partly or wholly fill a page that's under preparation for writing
  */
 static int afs_fill_page(struct afs_vnode *vnode, struct key *key,
-			 loff_t pos, struct page *page)
+			 loff_t pos, unsigned int len, struct page *page)
 {
-	loff_t i_size;
+	struct afs_read *req;
 	int ret;
-	int len;
 
 	_enter(",,%llu", (unsigned long long)pos);
 
-	i_size = i_size_read(&vnode->vfs_inode);
-	if (pos + PAGE_SIZE > i_size)
-		len = i_size - pos;
-	else
-		len = PAGE_SIZE;
+	req = kzalloc(sizeof(struct afs_read) + sizeof(struct page *),
+		      GFP_KERNEL);
+	if (!req)
+		return -ENOMEM;
+
+	atomic_set(&req->usage, 1);
+	req->pos = pos;
+	req->len = len;
+	req->nr_pages = 1;
+	req->pages[0] = page;
+	get_page(page);
 
-	ret = afs_vnode_fetch_data(vnode, key, pos, len, page);
+	ret = afs_vnode_fetch_data(vnode, key, req);
+	afs_put_read(req);
 	if (ret < 0) {
 		if (ret == -ENOENT) {
 			_debug("got NOENT from server"
@@ -148,12 +154,12 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 		kfree(candidate);
 		return -ENOMEM;
 	}
-	*pagep = page;
-	/* page won't leak in error case: it eventually gets cleaned off LRU */
 
 	if (!PageUptodate(page) && len != PAGE_SIZE) {
-		ret = afs_fill_page(vnode, key, index << PAGE_SHIFT, page);
+		ret = afs_fill_page(vnode, key, pos & PAGE_MASK, PAGE_SIZE, page);
 		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
 			kfree(candidate);
 			_leave(" = %d [prep]", ret);
 			return ret;
@@ -161,6 +167,9 @@ int afs_write_begin(struct file *file, struct address_space *mapping,
 		SetPageUptodate(page);
 	}
 
+	/* page won't leak in error case: it eventually gets cleaned off LRU */
+	*pagep = page;
+
 try_again:
 	spin_lock(&vnode->writeback_lock);
 
@@ -222,7 +231,7 @@ flush_conflicting_wb:
 	if (wb->state == AFS_WBACK_PENDING)
 		wb->state = AFS_WBACK_CONFLICTING;
 	spin_unlock(&vnode->writeback_lock);
-	if (PageDirty(page)) {
+	if (clear_page_dirty_for_io(page)) {
 		ret = afs_write_back_from_locked_page(wb, page);
 		if (ret < 0) {
 			afs_put_writeback(candidate);
@@ -246,7 +255,9 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 		  struct page *page, void *fsdata)
 {
 	struct afs_vnode *vnode = AFS_FS_I(file_inode(file));
+	struct key *key = file->private_data;
 	loff_t i_size, maybe_i_size;
+	int ret;
 
 	_enter("{%x:%u},{%lx}",
 	       vnode->fid.vid, vnode->fid.vnode, page->index);
@@ -262,6 +273,20 @@ int afs_write_end(struct file *file, struct address_space *mapping,
 		spin_unlock(&vnode->writeback_lock);
 	}
 
+	if (!PageUptodate(page)) {
+		if (copied < len) {
+			/* Try and load any missing data from the server.  The
+			 * unmarshalling routine will take care of clearing any
+			 * bits that are beyond the EOF.
+			 */
+			ret = afs_fill_page(vnode, key, pos + copied,
+					    len - copied, page);
+			if (ret < 0)
+				return ret;
+		}
+		SetPageUptodate(page);
+	}
+
 	set_page_dirty(page);
 	if (PageDirty(page))
 		_debug("dirtied");
@@ -296,10 +321,14 @@ static void afs_kill_pages(struct afs_vnode *vnode, bool error,
 		ASSERTCMP(pv.nr, ==, count);
 
 		for (loop = 0; loop < count; loop++) {
-			ClearPageUptodate(pv.pages[loop]);
+			struct page *page = pv.pages[loop];
+			ClearPageUptodate(page);
 			if (error)
-				SetPageError(pv.pages[loop]);
-			end_page_writeback(pv.pages[loop]);
+				SetPageError(page);
+			if (PageWriteback(page))
+				end_page_writeback(page);
+			if (page->index >= first)
+				first = page->index + 1;
 		}
 
 		__pagevec_release(&pv);
@@ -324,8 +353,6 @@ static int afs_write_back_from_locked_page(struct afs_writeback *wb,
 	_enter(",%lx", primary_page->index);
 
 	count = 1;
-	if (!clear_page_dirty_for_io(primary_page))
-		BUG();
 	if (test_set_page_writeback(primary_page))
 		BUG();
 
@@ -491,17 +518,17 @@ static int afs_writepages_region(struct address_space *mapping,
 		 */
 		lock_page(page);
 
-		if (page->mapping != mapping) {
+		if (page->mapping != mapping || !PageDirty(page)) {
 			unlock_page(page);
 			put_page(page);
 			continue;
 		}
 
-		if (wbc->sync_mode != WB_SYNC_NONE)
-			wait_on_page_writeback(page);
-
-		if (PageWriteback(page) || !PageDirty(page)) {
+		if (PageWriteback(page)) {
 			unlock_page(page);
+			if (wbc->sync_mode != WB_SYNC_NONE)
+				wait_on_page_writeback(page);
+			put_page(page);
 			continue;
 		}
 
@@ -512,6 +539,8 @@ static int afs_writepages_region(struct address_space *mapping,
 		wb->state = AFS_WBACK_WRITING;
 		spin_unlock(&wb->vnode->writeback_lock);
 
+		if (!clear_page_dirty_for_io(page))
+			BUG();
 		ret = afs_write_back_from_locked_page(wb, page);
 		unlock_page(page);
 		put_page(page);
@@ -735,6 +764,20 @@ out:
 }
 
 /*
+ * Flush out all outstanding writes on a file opened for writing when it is
+ * closed.
+ */
+int afs_flush(struct file *file, fl_owner_t id)
+{
+	_enter("");
+
+	if ((file->f_mode & FMODE_WRITE) == 0)
+		return 0;
+
+	return vfs_fsync(file, 0);
+}
+
+/*
  * notification that a previously read-only page is about to become writable
  * - if it returns an error, the caller will deliver a bus error signal
  */
diff --git a/fs/afs/xattr.c b/fs/afs/xattr.c
new file mode 100644
index 000000000000..2830e4f48d85
--- /dev/null
+++ b/fs/afs/xattr.c
@@ -0,0 +1,121 @@
+/* Extended attribute handling for AFS.  We use xattrs to get and set metadata
+ * instead of providing pioctl().
+ *
+ * Copyright (C) 2017 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public Licence
+ * as published by the Free Software Foundation; either version
+ * 2 of the Licence, or (at your option) any later version.
+ */
+
+#include <linux/slab.h>
+#include <linux/fs.h>
+#include <linux/xattr.h>
+#include "internal.h"
+
+static const char afs_xattr_list[] =
+	"afs.cell\0"
+	"afs.fid\0"
+	"afs.volume";
+
+/*
+ * Retrieve a list of the supported xattrs.
+ */
+ssize_t afs_listxattr(struct dentry *dentry, char *buffer, size_t size)
+{
+	if (size == 0)
+		return sizeof(afs_xattr_list);
+	if (size < sizeof(afs_xattr_list))
+		return -ERANGE;
+	memcpy(buffer, afs_xattr_list, sizeof(afs_xattr_list));
+	return sizeof(afs_xattr_list);
+}
+
+/*
+ * Get the name of the cell on which a file resides.
+ */
+static int afs_xattr_get_cell(const struct xattr_handler *handler,
+			      struct dentry *dentry,
+			      struct inode *inode, const char *name,
+			      void *buffer, size_t size)
+{
+	struct afs_vnode *vnode = AFS_FS_I(inode);
+	struct afs_cell *cell = vnode->volume->cell;
+	size_t namelen;
+
+	namelen = strlen(cell->name);
+	if (size == 0)
+		return namelen;
+	if (namelen > size)
+		return -ERANGE;
+	memcpy(buffer, cell->name, size);
+	return namelen;
+}
+
+static const struct xattr_handler afs_xattr_afs_cell_handler = {
+	.name	= "afs.cell",
+	.get	= afs_xattr_get_cell,
+};
+
+/*
+ * Get the volume ID, vnode ID and vnode uniquifier of a file as a sequence of
+ * hex numbers separated by colons.
+ */
+static int afs_xattr_get_fid(const struct xattr_handler *handler,
+			     struct dentry *dentry,
+			     struct inode *inode, const char *name,
+			     void *buffer, size_t size)
+{
+	struct afs_vnode *vnode = AFS_FS_I(inode);
+	char text[8 + 1 + 8 + 1 + 8 + 1];
+	size_t len;
+
+	len = sprintf(text, "%x:%x:%x",
+		      vnode->fid.vid, vnode->fid.vnode, vnode->fid.unique);
+	if (size == 0)
+		return len;
+	if (len > size)
+		return -ERANGE;
+	memcpy(buffer, text, len);
+	return len;
+}
+
+static const struct xattr_handler afs_xattr_afs_fid_handler = {
+	.name	= "afs.fid",
+	.get	= afs_xattr_get_fid,
+};
+
+/*
+ * Get the name of the volume on which a file resides.
+ */
+static int afs_xattr_get_volume(const struct xattr_handler *handler,
+			      struct dentry *dentry,
+			      struct inode *inode, const char *name,
+			      void *buffer, size_t size)
+{
+	struct afs_vnode *vnode = AFS_FS_I(inode);
+	const char *volname = vnode->volume->vlocation->vldb.name;
+	size_t namelen;
+
+	namelen = strlen(volname);
+	if (size == 0)
+		return namelen;
+	if (namelen > size)
+		return -ERANGE;
+	memcpy(buffer, volname, size);
+	return namelen;
+}
+
+static const struct xattr_handler afs_xattr_afs_volume_handler = {
+	.name	= "afs.volume",
+	.get	= afs_xattr_get_volume,
+};
+
+const struct xattr_handler *afs_xattr_handlers[] = {
+	&afs_xattr_afs_cell_handler,
+	&afs_xattr_afs_fid_handler,
+	&afs_xattr_afs_volume_handler,
+	NULL
+};
diff --git a/fs/aio.c b/fs/aio.c
index 873b4ca82ccb..dcad3a66748c 100644
--- a/fs/aio.c
+++ b/fs/aio.c
@@ -20,7 +20,7 @@
 #include <linux/backing-dev.h>
 #include <linux/uio.h>
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/mm.h>
@@ -512,7 +512,7 @@ static int aio_setup_ring(struct kioctx *ctx)
 
 	ctx->mmap_base = do_mmap_pgoff(ctx->aio_ring_file, 0, ctx->mmap_size,
 				       PROT_READ | PROT_WRITE,
-				       MAP_SHARED, 0, &unused);
+				       MAP_SHARED, 0, &unused, NULL);
 	up_write(&mm->mmap_sem);
 	if (IS_ERR((void *)ctx->mmap_base)) {
 		ctx->mmap_size = 0;
@@ -1495,7 +1495,7 @@ static ssize_t aio_read(struct kiocb *req, struct iocb *iocb, bool vectored,
 		return ret;
 	ret = rw_verify_area(READ, file, &req->ki_pos, iov_iter_count(&iter));
 	if (!ret)
-		ret = aio_ret(req, file->f_op->read_iter(req, &iter));
+		ret = aio_ret(req, call_read_iter(file, req, &iter));
 	kfree(iovec);
 	return ret;
 }
@@ -1520,7 +1520,7 @@ static ssize_t aio_write(struct kiocb *req, struct iocb *iocb, bool vectored,
 	if (!ret) {
 		req->ki_flags |= IOCB_WRITE;
 		file_start_write(file);
-		ret = aio_ret(req, file->f_op->write_iter(req, &iter));
+		ret = aio_ret(req, call_write_iter(file, req, &iter));
 		/*
 		 * We release freeze protection in aio_complete().  Fool lockdep
 		 * by telling it the lock got released so that it doesn't
@@ -1541,7 +1541,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	ssize_t ret;
 
 	/* enforce forwards compatibility on users */
-	if (unlikely(iocb->aio_reserved1 || iocb->aio_reserved2)) {
+	if (unlikely(iocb->aio_reserved2)) {
 		pr_debug("EINVAL: reserve field set\n");
 		return -EINVAL;
 	}
@@ -1568,6 +1568,7 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 	req->common.ki_pos = iocb->aio_offset;
 	req->common.ki_complete = aio_complete;
 	req->common.ki_flags = iocb_flags(req->common.ki_filp);
+	req->common.ki_hint = file_write_hint(file);
 
 	if (iocb->aio_flags & IOCB_FLAG_RESFD) {
 		/*
@@ -1586,6 +1587,18 @@ static int io_submit_one(struct kioctx *ctx, struct iocb __user *user_iocb,
 		req->common.ki_flags |= IOCB_EVENTFD;
 	}
 
+	ret = kiocb_set_rw_flags(&req->common, iocb->aio_rw_flags);
+	if (unlikely(ret)) {
+		pr_debug("EINVAL: aio_rw_flags\n");
+		goto out_put_req;
+	}
+
+	if ((req->common.ki_flags & IOCB_NOWAIT) &&
+			!(req->common.ki_flags & IOCB_DIRECT)) {
+		ret = -EOPNOTSUPP;
+		goto out_put_req;
+	}
+
 	ret = put_user(KIOCB_KEY, &user_iocb->aio_key);
 	if (unlikely(ret)) {
 		pr_debug("EFAULT: aio_key\n");
diff --git a/fs/attr.c b/fs/attr.c
index c902b3d53508..135304146120 100644
--- a/fs/attr.c
+++ b/fs/attr.c
@@ -9,6 +9,7 @@
 #include <linux/time.h>
 #include <linux/mm.h>
 #include <linux/string.h>
+#include <linux/sched/signal.h>
 #include <linux/capability.h>
 #include <linux/fsnotify.h>
 #include <linux/fcntl.h>
diff --git a/fs/autofs4/Kconfig b/fs/autofs4/Kconfig
index 1204d6384d39..44727bf18297 100644
--- a/fs/autofs4/Kconfig
+++ b/fs/autofs4/Kconfig
@@ -7,7 +7,7 @@ config AUTOFS4_FS
 	  automounter (amd), which is a pure user space daemon.
 
 	  To use the automounter you need the user-space tools from
-	  <ftp://ftp.kernel.org/pub/linux/daemons/autofs/v4/>; you also
+	  <https://www.kernel.org/pub/linux/daemons/autofs/v4/>; you also
 	  want to answer Y to "NFS file system support", below.
 
 	  To compile this support as a module, choose M here: the module will be
diff --git a/fs/autofs4/autofs_i.h b/fs/autofs4/autofs_i.h
index c885daae68c8..beef981aa54f 100644
--- a/fs/autofs4/autofs_i.h
+++ b/fs/autofs4/autofs_i.h
@@ -14,6 +14,7 @@
 #include <linux/mutex.h>
 #include <linux/spinlock.h>
 #include <linux/list.h>
+#include <linux/completion.h>
 
 /* This is the range of ioctl() numbers we claim as ours */
 #define AUTOFS_IOC_FIRST     AUTOFS_IOC_READY
diff --git a/fs/autofs4/dev-ioctl.c b/fs/autofs4/dev-ioctl.c
index 6f48d670c941..dd9f1bebb5a3 100644
--- a/fs/autofs4/dev-ioctl.c
+++ b/fs/autofs4/dev-ioctl.c
@@ -17,6 +17,7 @@
 #include <linux/file.h>
 #include <linux/fdtable.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/compat.h>
 #include <linux/syscalls.h>
 #include <linux/magic.h>
@@ -38,8 +39,6 @@
  * which have been left busy at at service shutdown.
  */
 
-#define AUTOFS_DEV_IOCTL_SIZE	sizeof(struct autofs_dev_ioctl)
-
 typedef int (*ioctl_fn)(struct file *, struct autofs_sb_info *,
 			struct autofs_dev_ioctl *);
 
@@ -345,7 +344,7 @@ static int autofs_dev_ioctl_fail(struct file *fp,
 	int status;
 
 	token = (autofs_wqt_t) param->fail.token;
-	status = param->fail.status ? param->fail.status : -ENOENT;
+	status = param->fail.status < 0 ? param->fail.status : -ENOENT;
 	return autofs4_wait_release(sbi, token, status);
 }
 
diff --git a/fs/autofs4/root.c b/fs/autofs4/root.c
index 82e8f6edfb48..d79ced925861 100644
--- a/fs/autofs4/root.c
+++ b/fs/autofs4/root.c
@@ -281,8 +281,8 @@ static int autofs4_mount_wait(const struct path *path, bool rcu_walk)
 		pr_debug("waiting for mount name=%pd\n", path->dentry);
 		status = autofs4_wait(sbi, path, NFY_MOUNT);
 		pr_debug("mount wait done status=%d\n", status);
+		ino->last_used = jiffies;
 	}
-	ino->last_used = jiffies;
 	return status;
 }
 
@@ -321,16 +321,21 @@ static struct dentry *autofs4_mountpoint_changed(struct path *path)
 	 */
 	if (autofs_type_indirect(sbi->type) && d_unhashed(dentry)) {
 		struct dentry *parent = dentry->d_parent;
-		struct autofs_info *ino;
 		struct dentry *new;
 
 		new = d_lookup(parent, &dentry->d_name);
 		if (!new)
 			return NULL;
-		ino = autofs4_dentry_ino(new);
-		ino->last_used = jiffies;
-		dput(path->dentry);
-		path->dentry = new;
+		if (new == dentry)
+			dput(new);
+		else {
+			struct autofs_info *ino;
+
+			ino = autofs4_dentry_ino(new);
+			ino->last_used = jiffies;
+			dput(path->dentry);
+			path->dentry = new;
+		}
 	}
 	return path->dentry;
 }
diff --git a/fs/autofs4/waitq.c b/fs/autofs4/waitq.c
index 1278335ce366..24a58bf9ca72 100644
--- a/fs/autofs4/waitq.c
+++ b/fs/autofs4/waitq.c
@@ -10,6 +10,7 @@
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/signal.h>
+#include <linux/sched/signal.h>
 #include <linux/file.h>
 #include "autofs_i.h"
 
@@ -436,8 +437,8 @@ int autofs4_wait(struct autofs_sb_info *sbi,
 		memcpy(&wq->name, &qstr, sizeof(struct qstr));
 		wq->dev = autofs4_get_dev(sbi);
 		wq->ino = autofs4_get_ino(sbi);
-		wq->uid = current_real_cred()->uid;
-		wq->gid = current_real_cred()->gid;
+		wq->uid = current_cred()->uid;
+		wq->gid = current_cred()->gid;
 		wq->pid = pid;
 		wq->tgid = tgid;
 		wq->status = -EINTR; /* Status return if interrupted */
diff --git a/fs/bad_inode.c b/fs/bad_inode.c
index 5f685c819298..bb53728c7a31 100644
--- a/fs/bad_inode.c
+++ b/fs/bad_inode.c
@@ -89,8 +89,8 @@ static int bad_inode_permission(struct inode *inode, int mask)
 	return -EIO;
 }
 
-static int bad_inode_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			struct kstat *stat)
+static int bad_inode_getattr(const struct path *path, struct kstat *stat,
+			     u32 request_mask, unsigned int query_flags)
 {
 	return -EIO;
 }
diff --git a/fs/befs/btree.c b/fs/befs/btree.c
index d509887c580c..1b7e0f7128d6 100644
--- a/fs/befs/btree.c
+++ b/fs/befs/btree.c
@@ -120,18 +120,15 @@ static int befs_compare_strings(const void *key1, int keylen1,
 				const void *key2, int keylen2);
 
 /**
- * befs_bt_read_super - read in btree superblock convert to cpu byteorder
- * @sb: Filesystem superblock
- * @ds: Datastream to read from
- * @sup: Buffer in which to place the btree superblock
+ * befs_bt_read_super() - read in btree superblock convert to cpu byteorder
+ * @sb:        Filesystem superblock
+ * @ds:        Datastream to read from
+ * @sup:       Buffer in which to place the btree superblock
  *
  * Calls befs_read_datastream to read in the btree superblock and
  * makes sure it is in cpu byteorder, byteswapping if necessary.
- *
- * On success, returns BEFS_OK and *@sup contains the btree superblock,
- * in cpu byte order.
- *
- * On failure, BEFS_ERR is returned.
+ * Return: BEFS_OK on success and if *@sup contains the btree superblock in cpu
+ * byte order. Otherwise return BEFS_ERR on error.
  */
 static int
 befs_bt_read_super(struct super_block *sb, const befs_data_stream *ds,
diff --git a/fs/befs/linuxvfs.c b/fs/befs/linuxvfs.c
index 19407165f4aa..4a4a5a366158 100644
--- a/fs/befs/linuxvfs.c
+++ b/fs/befs/linuxvfs.c
@@ -18,7 +18,9 @@
 #include <linux/parser.h>
 #include <linux/namei.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/exportfs.h>
+#include <linux/seq_file.h>
 
 #include "befs.h"
 #include "btree.h"
@@ -52,11 +54,13 @@ static int befs_nls2utf(struct super_block *sb, const char *in, int in_len,
 static void befs_put_super(struct super_block *);
 static int befs_remount(struct super_block *, int *, char *);
 static int befs_statfs(struct dentry *, struct kstatfs *);
+static int befs_show_options(struct seq_file *, struct dentry *);
 static int parse_options(char *, struct befs_mount_options *);
 static struct dentry *befs_fh_to_dentry(struct super_block *sb,
 				struct fid *fid, int fh_len, int fh_type);
 static struct dentry *befs_fh_to_parent(struct super_block *sb,
 				struct fid *fid, int fh_len, int fh_type);
+static struct dentry *befs_get_parent(struct dentry *child);
 
 static const struct super_operations befs_sops = {
 	.alloc_inode	= befs_alloc_inode,	/* allocate a new inode */
@@ -64,7 +68,7 @@ static const struct super_operations befs_sops = {
 	.put_super	= befs_put_super,	/* uninit super */
 	.statfs		= befs_statfs,	/* statfs */
 	.remount_fs	= befs_remount,
-	.show_options	= generic_show_options,
+	.show_options	= befs_show_options,
 };
 
 /* slab cache for befs_inode_info objects */
@@ -92,6 +96,7 @@ static const struct address_space_operations befs_symlink_aops = {
 static const struct export_operations befs_export_operations = {
 	.fh_to_dentry	= befs_fh_to_dentry,
 	.fh_to_parent	= befs_fh_to_parent,
+	.get_parent	= befs_get_parent,
 };
 
 /*
@@ -666,6 +671,19 @@ static struct dentry *befs_fh_to_parent(struct super_block *sb,
 				    befs_nfs_get_inode);
 }
 
+static struct dentry *befs_get_parent(struct dentry *child)
+{
+	struct inode *parent;
+	struct befs_inode_info *befs_ino = BEFS_I(d_inode(child));
+
+	parent = befs_iget(child->d_sb,
+			   (unsigned long)befs_ino->i_parent.start);
+	if (IS_ERR(parent))
+		return ERR_CAST(parent);
+
+	return d_obtain_alias(parent);
+}
+
 enum {
 	Opt_uid, Opt_gid, Opt_charset, Opt_debug, Opt_err,
 };
@@ -755,6 +773,24 @@ parse_options(char *options, struct befs_mount_options *opts)
 	return 1;
 }
 
+static int befs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct befs_sb_info *befs_sb = BEFS_SB(root->d_sb);
+	struct befs_mount_options *opts = &befs_sb->mount_opts;
+
+	if (!uid_eq(opts->uid, GLOBAL_ROOT_UID))
+		seq_printf(m, ",uid=%u",
+			   from_kuid_munged(&init_user_ns, opts->uid));
+	if (!gid_eq(opts->gid, GLOBAL_ROOT_GID))
+		seq_printf(m, ",gid=%u",
+			   from_kgid_munged(&init_user_ns, opts->gid));
+	if (opts->iocharset)
+		seq_printf(m, ",charset=%s", opts->iocharset);
+	if (opts->debug)
+		seq_puts(m, ",debug");
+	return 0;
+}
+
 /* This function has the responsibiltiy of getting the
  * filesystem ready for unmounting.
  * Basically, we free everything that we allocated in
@@ -788,8 +824,6 @@ befs_fill_super(struct super_block *sb, void *data, int silent)
 	const off_t x86_sb_off = 512;
 	int blocksize;
 
-	save_mount_options(sb, data);
-
 	sb->s_fs_info = kzalloc(sizeof(*befs_sb), GFP_KERNEL);
 	if (sb->s_fs_info == NULL)
 		goto unacquire_none;
diff --git a/fs/bfs/inode.c b/fs/bfs/inode.c
index f2deec0a62f0..9a69392f1fb3 100644
--- a/fs/bfs/inode.c
+++ b/fs/bfs/inode.c
@@ -1,7 +1,7 @@
 /*
  *	fs/bfs/inode.c
  *	BFS superblock and inode operations.
- *	Copyright (C) 1999-2006 Tigran Aivazian <tigran@aivazian.fsnet.co.uk>
+ *	Copyright (C) 1999-2006 Tigran Aivazian <aivazian.tigran@gmail.com>
  *	From fs/minix, Copyright (C) 1991, 1992 Linus Torvalds.
  *
  *      Made endianness-clean by Andrew Stribblehill <ads@wompom.org>, 2005.
@@ -19,7 +19,7 @@
 #include <linux/uaccess.h>
 #include "bfs.h"
 
-MODULE_AUTHOR("Tigran Aivazian <tigran@aivazian.fsnet.co.uk>");
+MODULE_AUTHOR("Tigran Aivazian <aivazian.tigran@gmail.com>");
 MODULE_DESCRIPTION("SCO UnixWare BFS filesystem for Linux");
 MODULE_LICENSE("GPL");
 
@@ -419,7 +419,7 @@ static int bfs_fill_super(struct super_block *s, void *data, int silent)
 		if (i_sblock > info->si_blocks ||
 			i_eblock > info->si_blocks ||
 			i_sblock > i_eblock ||
-			i_eoff > s_size ||
+			(i_eoff != le32_to_cpu(-1) && i_eoff > s_size) ||
 			i_sblock * BFS_BSIZE > i_eoff) {
 
 			printf("Inode 0x%08x corrupted\n", i);
diff --git a/fs/binfmt_aout.c b/fs/binfmt_aout.c
index 2a59139f520b..9be82c4e14a4 100644
--- a/fs/binfmt_aout.c
+++ b/fs/binfmt_aout.c
@@ -25,6 +25,7 @@
 #include <linux/init.h>
 #include <linux/coredump.h>
 #include <linux/slab.h>
+#include <linux/sched/task_stack.h>
 
 #include <linux/uaccess.h>
 #include <asm/cacheflush.h>
diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c
index 422370293cfd..879ff9c7ffd0 100644
--- a/fs/binfmt_elf.c
+++ b/fs/binfmt_elf.c
@@ -35,6 +35,10 @@
 #include <linux/utsname.h>
 #include <linux/coredump.h>
 #include <linux/sched.h>
+#include <linux/sched/coredump.h>
+#include <linux/sched/task_stack.h>
+#include <linux/sched/cputime.h>
+#include <linux/cred.h>
 #include <linux/dax.h>
 #include <linux/uaccess.h>
 #include <asm/param.h>
@@ -91,12 +95,18 @@ static struct linux_binfmt elf_format = {
 
 #define BAD_ADDR(x) ((unsigned long)(x) >= TASK_SIZE)
 
-static int set_brk(unsigned long start, unsigned long end)
+static int set_brk(unsigned long start, unsigned long end, int prot)
 {
 	start = ELF_PAGEALIGN(start);
 	end = ELF_PAGEALIGN(end);
 	if (end > start) {
-		int error = vm_brk(start, end - start);
+		/*
+		 * Map the last of the bss segment.
+		 * If the header is requesting these pages to be
+		 * executable, honour that (ppc32 needs this).
+		 */
+		int error = vm_brk_flags(start, end - start,
+				prot & PROT_EXEC ? VM_EXEC : 0);
 		if (error)
 			return error;
 	}
@@ -153,8 +163,6 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	unsigned long p = bprm->p;
 	int argc = bprm->argc;
 	int envc = bprm->envc;
-	elf_addr_t __user *argv;
-	elf_addr_t __user *envp;
 	elf_addr_t __user *sp;
 	elf_addr_t __user *u_platform;
 	elf_addr_t __user *u_base_platform;
@@ -294,38 +302,38 @@ create_elf_tables(struct linux_binprm *bprm, struct elfhdr *exec,
 	/* Now, let's put argc (and argv, envp if appropriate) on the stack */
 	if (__put_user(argc, sp++))
 		return -EFAULT;
-	argv = sp;
-	envp = argv + argc + 1;
 
-	/* Populate argv and envp */
+	/* Populate list of argv pointers back to argv strings. */
 	p = current->mm->arg_end = current->mm->arg_start;
 	while (argc-- > 0) {
 		size_t len;
-		if (__put_user((elf_addr_t)p, argv++))
+		if (__put_user((elf_addr_t)p, sp++))
 			return -EFAULT;
 		len = strnlen_user((void __user *)p, MAX_ARG_STRLEN);
 		if (!len || len > MAX_ARG_STRLEN)
 			return -EINVAL;
 		p += len;
 	}
-	if (__put_user(0, argv))
+	if (__put_user(0, sp++))
 		return -EFAULT;
-	current->mm->arg_end = current->mm->env_start = p;
+	current->mm->arg_end = p;
+
+	/* Populate list of envp pointers back to envp strings. */
+	current->mm->env_end = current->mm->env_start = p;
 	while (envc-- > 0) {
 		size_t len;
-		if (__put_user((elf_addr_t)p, envp++))
+		if (__put_user((elf_addr_t)p, sp++))
 			return -EFAULT;
 		len = strnlen_user((void __user *)p, MAX_ARG_STRLEN);
 		if (!len || len > MAX_ARG_STRLEN)
 			return -EINVAL;
 		p += len;
 	}
-	if (__put_user(0, envp))
+	if (__put_user(0, sp++))
 		return -EFAULT;
 	current->mm->env_end = p;
 
 	/* Put the elf_info on the stack in the right place.  */
-	sp = (elf_addr_t __user *)envp + 1;
 	if (copy_to_user(sp, elf_info, ei_index * sizeof(elf_addr_t)))
 		return -EFAULT;
 	return 0;
@@ -524,6 +532,7 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 	unsigned long load_addr = 0;
 	int load_addr_set = 0;
 	unsigned long last_bss = 0, elf_bss = 0;
+	int bss_prot = 0;
 	unsigned long error = ~0UL;
 	unsigned long total_size;
 	int i;
@@ -606,8 +615,10 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 			 * elf_bss and last_bss is the bss section.
 			 */
 			k = load_addr + eppnt->p_vaddr + eppnt->p_memsz;
-			if (k > last_bss)
+			if (k > last_bss) {
 				last_bss = k;
+				bss_prot = elf_prot;
+			}
 		}
 	}
 
@@ -623,13 +634,14 @@ static unsigned long load_elf_interp(struct elfhdr *interp_elf_ex,
 	/*
 	 * Next, align both the file and mem bss up to the page size,
 	 * since this is where elf_bss was just zeroed up to, and where
-	 * last_bss will end after the vm_brk() below.
+	 * last_bss will end after the vm_brk_flags() below.
 	 */
 	elf_bss = ELF_PAGEALIGN(elf_bss);
 	last_bss = ELF_PAGEALIGN(last_bss);
 	/* Finally, if there is still more bss to allocate, do it. */
 	if (last_bss > elf_bss) {
-		error = vm_brk(elf_bss, last_bss - elf_bss);
+		error = vm_brk_flags(elf_bss, last_bss - elf_bss,
+				bss_prot & PROT_EXEC ? VM_EXEC : 0);
 		if (error)
 			goto out;
 	}
@@ -674,6 +686,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	unsigned long error;
 	struct elf_phdr *elf_ppnt, *elf_phdata, *interp_elf_phdata = NULL;
 	unsigned long elf_bss, elf_brk;
+	int bss_prot = 0;
 	int retval, i;
 	unsigned long elf_entry;
 	unsigned long interp_load_addr = 0;
@@ -882,7 +895,8 @@ static int load_elf_binary(struct linux_binprm *bprm)
 			   before this one. Map anonymous pages, if needed,
 			   and clear the area.  */
 			retval = set_brk(elf_bss + load_bias,
-					 elf_brk + load_bias);
+					 elf_brk + load_bias,
+					 bss_prot);
 			if (retval)
 				goto out_free_dentry;
 			nbyte = ELF_PAGEOFFSET(elf_bss);
@@ -911,17 +925,60 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		elf_flags = MAP_PRIVATE | MAP_DENYWRITE | MAP_EXECUTABLE;
 
 		vaddr = elf_ppnt->p_vaddr;
+		/*
+		 * If we are loading ET_EXEC or we have already performed
+		 * the ET_DYN load_addr calculations, proceed normally.
+		 */
 		if (loc->elf_ex.e_type == ET_EXEC || load_addr_set) {
 			elf_flags |= MAP_FIXED;
 		} else if (loc->elf_ex.e_type == ET_DYN) {
-			/* Try and get dynamic programs out of the way of the
-			 * default mmap base, as well as whatever program they
-			 * might try to exec.  This is because the brk will
-			 * follow the loader, and is not movable.  */
-			load_bias = ELF_ET_DYN_BASE - vaddr;
-			if (current->flags & PF_RANDOMIZE)
-				load_bias += arch_mmap_rnd();
-			load_bias = ELF_PAGESTART(load_bias);
+			/*
+			 * This logic is run once for the first LOAD Program
+			 * Header for ET_DYN binaries to calculate the
+			 * randomization (load_bias) for all the LOAD
+			 * Program Headers, and to calculate the entire
+			 * size of the ELF mapping (total_size). (Note that
+			 * load_addr_set is set to true later once the
+			 * initial mapping is performed.)
+			 *
+			 * There are effectively two types of ET_DYN
+			 * binaries: programs (i.e. PIE: ET_DYN with INTERP)
+			 * and loaders (ET_DYN without INTERP, since they
+			 * _are_ the ELF interpreter). The loaders must
+			 * be loaded away from programs since the program
+			 * may otherwise collide with the loader (especially
+			 * for ET_EXEC which does not have a randomized
+			 * position). For example to handle invocations of
+			 * "./ld.so someprog" to test out a new version of
+			 * the loader, the subsequent program that the
+			 * loader loads must avoid the loader itself, so
+			 * they cannot share the same load range. Sufficient
+			 * room for the brk must be allocated with the
+			 * loader as well, since brk must be available with
+			 * the loader.
+			 *
+			 * Therefore, programs are loaded offset from
+			 * ELF_ET_DYN_BASE and loaders are loaded into the
+			 * independently randomized mmap region (0 load_bias
+			 * without MAP_FIXED).
+			 */
+			if (elf_interpreter) {
+				load_bias = ELF_ET_DYN_BASE;
+				if (current->flags & PF_RANDOMIZE)
+					load_bias += arch_mmap_rnd();
+				elf_flags |= MAP_FIXED;
+			} else
+				load_bias = 0;
+
+			/*
+			 * Since load_bias is used for all subsequent loading
+			 * calculations, we must lower it by the first vaddr
+			 * so that the remaining calculations based on the
+			 * ELF vaddrs will be correctly offset. The result
+			 * is then page aligned.
+			 */
+			load_bias = ELF_PAGESTART(load_bias - vaddr);
+
 			total_size = total_mapping_size(elf_phdata,
 							loc->elf_ex.e_phnum);
 			if (!total_size) {
@@ -976,8 +1033,10 @@ static int load_elf_binary(struct linux_binprm *bprm)
 		if (end_data < k)
 			end_data = k;
 		k = elf_ppnt->p_vaddr + elf_ppnt->p_memsz;
-		if (k > elf_brk)
+		if (k > elf_brk) {
+			bss_prot = elf_prot;
 			elf_brk = k;
+		}
 	}
 
 	loc->elf_ex.e_entry += load_bias;
@@ -993,7 +1052,7 @@ static int load_elf_binary(struct linux_binprm *bprm)
 	 * mapping in the interpreter, to make sure it doesn't wind
 	 * up getting placed where the bss needs to go.
 	 */
-	retval = set_brk(elf_bss, elf_brk);
+	retval = set_brk(elf_bss, elf_brk, bss_prot);
 	if (retval)
 		goto out_free_dentry;
 	if (likely(elf_bss != elf_brk) && unlikely(padzero(elf_bss))) {
@@ -1428,17 +1487,18 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
 		 * group-wide total, not its individual thread total.
 		 */
 		thread_group_cputime(p, &cputime);
-		cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
-		cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
+		prstatus->pr_utime = ns_to_timeval(cputime.utime);
+		prstatus->pr_stime = ns_to_timeval(cputime.stime);
 	} else {
-		cputime_t utime, stime;
+		u64 utime, stime;
 
 		task_cputime(p, &utime, &stime);
-		cputime_to_timeval(utime, &prstatus->pr_utime);
-		cputime_to_timeval(stime, &prstatus->pr_stime);
+		prstatus->pr_utime = ns_to_timeval(utime);
+		prstatus->pr_stime = ns_to_timeval(stime);
 	}
-	cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
-	cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
+
+	prstatus->pr_cutime = ns_to_timeval(p->signal->cutime);
+	prstatus->pr_cstime = ns_to_timeval(p->signal->cstime);
 }
 
 static int fill_psinfo(struct elf_prpsinfo *psinfo, struct task_struct *p,
diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c
index d2e36f82c35d..cf93a4fad012 100644
--- a/fs/binfmt_elf_fdpic.c
+++ b/fs/binfmt_elf_fdpic.c
@@ -15,6 +15,9 @@
 #include <linux/fs.h>
 #include <linux/stat.h>
 #include <linux/sched.h>
+#include <linux/sched/coredump.h>
+#include <linux/sched/task_stack.h>
+#include <linux/sched/cputime.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/errno.h>
@@ -1349,17 +1352,17 @@ static void fill_prstatus(struct elf_prstatus *prstatus,
 		 * group-wide total, not its individual thread total.
 		 */
 		thread_group_cputime(p, &cputime);
-		cputime_to_timeval(cputime.utime, &prstatus->pr_utime);
-		cputime_to_timeval(cputime.stime, &prstatus->pr_stime);
+		prstatus->pr_utime = ns_to_timeval(cputime.utime);
+		prstatus->pr_stime = ns_to_timeval(cputime.stime);
 	} else {
-		cputime_t utime, stime;
+		u64 utime, stime;
 
 		task_cputime(p, &utime, &stime);
-		cputime_to_timeval(utime, &prstatus->pr_utime);
-		cputime_to_timeval(stime, &prstatus->pr_stime);
+		prstatus->pr_utime = ns_to_timeval(utime);
+		prstatus->pr_stime = ns_to_timeval(stime);
 	}
-	cputime_to_timeval(p->signal->cutime, &prstatus->pr_cutime);
-	cputime_to_timeval(p->signal->cstime, &prstatus->pr_cstime);
+	prstatus->pr_cutime = ns_to_timeval(p->signal->cutime);
+	prstatus->pr_cstime = ns_to_timeval(p->signal->cstime);
 
 	prstatus->pr_exec_fdpic_loadmap = p->mm->context.exec_fdpic_loadmap;
 	prstatus->pr_interp_fdpic_loadmap = p->mm->context.interp_fdpic_loadmap;
diff --git a/fs/binfmt_flat.c b/fs/binfmt_flat.c
index 9b2917a30294..a1e6860b6f46 100644
--- a/fs/binfmt_flat.c
+++ b/fs/binfmt_flat.c
@@ -19,6 +19,7 @@
 
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/sched/task_stack.h>
 #include <linux/mm.h>
 #include <linux/mman.h>
 #include <linux/errno.h>
@@ -421,9 +422,9 @@ static int load_flat_file(struct linux_binprm *bprm,
 {
 	struct flat_hdr *hdr;
 	unsigned long textpos, datapos, realdatastart;
-	unsigned long text_len, data_len, bss_len, stack_len, full_data, flags;
+	u32 text_len, data_len, bss_len, stack_len, full_data, flags;
 	unsigned long len, memp, memp_size, extra, rlim;
-	unsigned long __user *reloc, *rp;
+	u32 __user *reloc, *rp;
 	struct inode *inode;
 	int i, rev, relocs;
 	loff_t fpos;
@@ -573,7 +574,7 @@ static int load_flat_file(struct linux_binprm *bprm,
 				MAX_SHARED_LIBS * sizeof(unsigned long),
 				FLAT_DATA_ALIGN);
 
-		pr_debug("Allocated data+bss+stack (%ld bytes): %lx\n",
+		pr_debug("Allocated data+bss+stack (%u bytes): %lx\n",
 			 data_len + bss_len + stack_len, datapos);
 
 		fpos = ntohl(hdr->data_start);
@@ -595,13 +596,13 @@ static int load_flat_file(struct linux_binprm *bprm,
 			goto err;
 		}
 
-		reloc = (unsigned long __user *)
+		reloc = (u32 __user *)
 			(datapos + (ntohl(hdr->reloc_start) - text_len));
 		memp = realdatastart;
 		memp_size = len;
 	} else {
 
-		len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(unsigned long);
+		len = text_len + data_len + extra + MAX_SHARED_LIBS * sizeof(u32);
 		len = PAGE_ALIGN(len);
 		textpos = vm_mmap(NULL, 0, len,
 			PROT_READ | PROT_EXEC | PROT_WRITE, MAP_PRIVATE, 0);
@@ -617,10 +618,10 @@ static int load_flat_file(struct linux_binprm *bprm,
 
 		realdatastart = textpos + ntohl(hdr->data_start);
 		datapos = ALIGN(realdatastart +
-				MAX_SHARED_LIBS * sizeof(unsigned long),
+				MAX_SHARED_LIBS * sizeof(u32),
 				FLAT_DATA_ALIGN);
 
-		reloc = (unsigned long __user *)
+		reloc = (u32 __user *)
 			(datapos + (ntohl(hdr->reloc_start) - text_len));
 		memp = textpos;
 		memp_size = len;
@@ -693,7 +694,7 @@ static int load_flat_file(struct linux_binprm *bprm,
 			ret = result;
 			pr_err("Unable to read code+data+bss, errno %d\n", ret);
 			vm_munmap(textpos, text_len + data_len + extra +
-				MAX_SHARED_LIBS * sizeof(unsigned long));
+				MAX_SHARED_LIBS * sizeof(u32));
 			goto err;
 		}
 	}
@@ -753,8 +754,8 @@ static int load_flat_file(struct linux_binprm *bprm,
 	 * image.
 	 */
 	if (flags & FLAT_FLAG_GOTPIC) {
-		for (rp = (unsigned long __user *)datapos; ; rp++) {
-			unsigned long addr, rp_val;
+		for (rp = (u32 __user *)datapos; ; rp++) {
+			u32 addr, rp_val;
 			if (get_user(rp_val, rp))
 				return -EFAULT;
 			if (rp_val == 0xffffffff)
@@ -783,9 +784,9 @@ static int load_flat_file(struct linux_binprm *bprm,
 	 * __start to address 4 so that is okay).
 	 */
 	if (rev > OLD_FLAT_VERSION) {
-		unsigned long __maybe_unused persistent = 0;
+		u32 __maybe_unused persistent = 0;
 		for (i = 0; i < relocs; i++) {
-			unsigned long addr, relval;
+			u32 addr, relval;
 
 			/*
 			 * Get the address of the pointer to be
@@ -798,15 +799,18 @@ static int load_flat_file(struct linux_binprm *bprm,
 			if (flat_set_persistent(relval, &persistent))
 				continue;
 			addr = flat_get_relocate_addr(relval);
-			rp = (unsigned long __user *)calc_reloc(addr, libinfo, id, 1);
-			if (rp == (unsigned long __user *)RELOC_FAILED) {
+			rp = (u32 __user *)calc_reloc(addr, libinfo, id, 1);
+			if (rp == (u32 __user *)RELOC_FAILED) {
 				ret = -ENOEXEC;
 				goto err;
 			}
 
 			/* Get the pointer's value.  */
-			addr = flat_get_addr_from_rp(rp, relval, flags,
-							&persistent);
+			ret = flat_get_addr_from_rp(rp, relval, flags,
+							&addr, &persistent);
+			if (unlikely(ret))
+				goto err;
+
 			if (addr != 0) {
 				/*
 				 * Do the relocation.  PIC relocs in the data section are
@@ -821,12 +825,14 @@ static int load_flat_file(struct linux_binprm *bprm,
 				}
 
 				/* Write back the relocated pointer.  */
-				flat_put_addr_at_rp(rp, addr, relval);
+				ret = flat_put_addr_at_rp(rp, addr, relval);
+				if (unlikely(ret))
+					goto err;
 			}
 		}
 	} else {
 		for (i = 0; i < relocs; i++) {
-			unsigned long relval;
+			u32 relval;
 			if (get_user(relval, reloc + i))
 				return -EFAULT;
 			relval = ntohl(relval);
diff --git a/fs/binfmt_misc.c b/fs/binfmt_misc.c
index 9b4688ab1d8e..f4718098ac31 100644
--- a/fs/binfmt_misc.c
+++ b/fs/binfmt_misc.c
@@ -12,7 +12,7 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/magic.h>
 #include <linux/binfmts.h>
 #include <linux/slab.h>
@@ -818,7 +818,7 @@ static const struct super_operations s_ops = {
 static int bm_fill_super(struct super_block *sb, void *data, int silent)
 {
 	int err;
-	static struct tree_descr bm_files[] = {
+	static const struct tree_descr bm_files[] = {
 		[2] = {"status", &bm_status_operations, S_IWUSR|S_IRUGO},
 		[3] = {"register", &bm_register_operations, S_IWUSR},
 		/* last one */ {""}
diff --git a/fs/block_dev.c b/fs/block_dev.c
index 3c47614a4b32..9941dc8342df 100644
--- a/fs/block_dev.c
+++ b/fs/block_dev.c
@@ -18,6 +18,7 @@
 #include <linux/module.h>
 #include <linux/blkpg.h>
 #include <linux/magic.h>
+#include <linux/dax.h>
 #include <linux/buffer_head.h>
 #include <linux/swap.h>
 #include <linux/pagevec.h>
@@ -103,12 +104,11 @@ void invalidate_bdev(struct block_device *bdev)
 {
 	struct address_space *mapping = bdev->bd_inode->i_mapping;
 
-	if (mapping->nrpages == 0)
-		return;
-
-	invalidate_bh_lrus();
-	lru_add_drain_all();	/* make sure all lru add caches are flushed */
-	invalidate_mapping_pages(mapping, 0, -1);
+	if (mapping->nrpages) {
+		invalidate_bh_lrus();
+		lru_add_drain_all();	/* make sure all lru add caches are flushed */
+		invalidate_mapping_pages(mapping, 0, -1);
+	}
 	/* 99% of the time, we don't need to flush the cleancache on the bdev.
 	 * But, for the strange corners, lets be cautious
 	 */
@@ -225,6 +225,7 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 	bio_init(&bio, vecs, nr_pages);
 	bio.bi_bdev = bdev;
 	bio.bi_iter.bi_sector = pos >> 9;
+	bio.bi_write_hint = iocb->ki_hint;
 	bio.bi_private = current;
 	bio.bi_end_io = blkdev_bio_end_io_simple;
 
@@ -262,8 +263,11 @@ __blkdev_direct_IO_simple(struct kiocb *iocb, struct iov_iter *iter,
 	if (vecs != inline_vecs)
 		kfree(vecs);
 
-	if (unlikely(bio.bi_error))
-		return bio.bi_error;
+	if (unlikely(bio.bi_status))
+		ret = blk_status_to_errno(bio.bi_status);
+
+	bio_uninit(&bio);
+
 	return ret;
 }
 
@@ -288,16 +292,18 @@ static void blkdev_bio_end_io(struct bio *bio)
 	bool should_dirty = dio->should_dirty;
 
 	if (dio->multi_bio && !atomic_dec_and_test(&dio->ref)) {
-		if (bio->bi_error && !dio->bio.bi_error)
-			dio->bio.bi_error = bio->bi_error;
+		if (bio->bi_status && !dio->bio.bi_status)
+			dio->bio.bi_status = bio->bi_status;
 	} else {
 		if (!dio->is_sync) {
 			struct kiocb *iocb = dio->iocb;
-			ssize_t ret = dio->bio.bi_error;
+			ssize_t ret;
 
-			if (likely(!ret)) {
+			if (likely(!dio->bio.bi_status)) {
 				ret = dio->size;
 				iocb->ki_pos += ret;
+			} else {
+				ret = blk_status_to_errno(dio->bio.bi_status);
 			}
 
 			dio->iocb->ki_complete(iocb, ret, 0);
@@ -334,7 +340,7 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	bool is_read = (iov_iter_rw(iter) == READ), is_sync;
 	loff_t pos = iocb->ki_pos;
 	blk_qc_t qc = BLK_QC_T_NONE;
-	int ret;
+	int ret = 0;
 
 	if ((pos | iov_iter_alignment(iter)) &
 	    (bdev_logical_block_size(bdev) - 1))
@@ -358,12 +364,13 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	for (;;) {
 		bio->bi_bdev = bdev;
 		bio->bi_iter.bi_sector = pos >> 9;
+		bio->bi_write_hint = iocb->ki_hint;
 		bio->bi_private = dio;
 		bio->bi_end_io = blkdev_bio_end_io;
 
 		ret = bio_iov_iter_get_pages(bio, iter);
 		if (unlikely(ret)) {
-			bio->bi_error = ret;
+			bio->bi_status = BLK_STS_IOERR;
 			bio_endio(bio);
 			break;
 		}
@@ -412,7 +419,8 @@ __blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter, int nr_pages)
 	}
 	__set_current_state(TASK_RUNNING);
 
-	ret = dio->bio.bi_error;
+	if (!ret)
+		ret = blk_status_to_errno(dio->bio.bi_status);
 	if (likely(!ret))
 		ret = dio->size;
 
@@ -436,7 +444,7 @@ blkdev_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 
 static __init int blkdev_init(void)
 {
-	blkdev_dio_pool = bioset_create(4, offsetof(struct blkdev_dio, bio));
+	blkdev_dio_pool = bioset_create(4, offsetof(struct blkdev_dio, bio), BIOSET_NEED_BVECS);
 	if (!blkdev_dio_pool)
 		return -ENOMEM;
 	return 0;
@@ -624,7 +632,7 @@ int blkdev_fsync(struct file *filp, loff_t start, loff_t end, int datasync)
 	struct block_device *bdev = I_BDEV(bd_inode);
 	int error;
 	
-	error = filemap_write_and_wait_range(filp->f_mapping, start, end);
+	error = file_write_and_wait_range(filp, start, end);
 	if (error)
 		return error;
 
@@ -717,120 +725,6 @@ int bdev_write_page(struct block_device *bdev, sector_t sector,
 }
 EXPORT_SYMBOL_GPL(bdev_write_page);
 
-/**
- * bdev_direct_access() - Get the address for directly-accessibly memory
- * @bdev: The device containing the memory
- * @dax: control and output parameters for ->direct_access
- *
- * If a block device is made up of directly addressable memory, this function
- * will tell the caller the PFN and the address of the memory.  The address
- * may be directly dereferenced within the kernel without the need to call
- * ioremap(), kmap() or similar.  The PFN is suitable for inserting into
- * page tables.
- *
- * Return: negative errno if an error occurs, otherwise the number of bytes
- * accessible at this address.
- */
-long bdev_direct_access(struct block_device *bdev, struct blk_dax_ctl *dax)
-{
-	sector_t sector = dax->sector;
-	long avail, size = dax->size;
-	const struct block_device_operations *ops = bdev->bd_disk->fops;
-
-	/*
-	 * The device driver is allowed to sleep, in order to make the
-	 * memory directly accessible.
-	 */
-	might_sleep();
-
-	if (size < 0)
-		return size;
-	if (!blk_queue_dax(bdev_get_queue(bdev)) || !ops->direct_access)
-		return -EOPNOTSUPP;
-	if ((sector + DIV_ROUND_UP(size, 512)) >
-					part_nr_sects_read(bdev->bd_part))
-		return -ERANGE;
-	sector += get_start_sect(bdev);
-	if (sector % (PAGE_SIZE / 512))
-		return -EINVAL;
-	avail = ops->direct_access(bdev, sector, &dax->addr, &dax->pfn, size);
-	if (!avail)
-		return -ERANGE;
-	if (avail > 0 && avail & ~PAGE_MASK)
-		return -ENXIO;
-	return min(avail, size);
-}
-EXPORT_SYMBOL_GPL(bdev_direct_access);
-
-/**
- * bdev_dax_supported() - Check if the device supports dax for filesystem
- * @sb: The superblock of the device
- * @blocksize: The block size of the device
- *
- * This is a library function for filesystems to check if the block device
- * can be mounted with dax option.
- *
- * Return: negative errno if unsupported, 0 if supported.
- */
-int bdev_dax_supported(struct super_block *sb, int blocksize)
-{
-	struct blk_dax_ctl dax = {
-		.sector = 0,
-		.size = PAGE_SIZE,
-	};
-	int err;
-
-	if (blocksize != PAGE_SIZE) {
-		vfs_msg(sb, KERN_ERR, "error: unsupported blocksize for dax");
-		return -EINVAL;
-	}
-
-	err = bdev_direct_access(sb->s_bdev, &dax);
-	if (err < 0) {
-		switch (err) {
-		case -EOPNOTSUPP:
-			vfs_msg(sb, KERN_ERR,
-				"error: device does not support dax");
-			break;
-		case -EINVAL:
-			vfs_msg(sb, KERN_ERR,
-				"error: unaligned partition for dax");
-			break;
-		default:
-			vfs_msg(sb, KERN_ERR,
-				"error: dax access failed (%d)", err);
-		}
-		return err;
-	}
-
-	return 0;
-}
-EXPORT_SYMBOL_GPL(bdev_dax_supported);
-
-/**
- * bdev_dax_capable() - Return if the raw device is capable for dax
- * @bdev: The device for raw block device access
- */
-bool bdev_dax_capable(struct block_device *bdev)
-{
-	struct blk_dax_ctl dax = {
-		.size = PAGE_SIZE,
-	};
-
-	if (!IS_ENABLED(CONFIG_FS_DAX))
-		return false;
-
-	dax.sector = 0;
-	if (bdev_direct_access(bdev, &dax) < 0)
-		return false;
-
-	dax.sector = bdev->bd_part->nr_sects - (PAGE_SIZE / 512);
-	if (bdev_direct_access(bdev, &dax) < 0)
-		return false;
-
-	return true;
-}
-
 /*
  * pseudo-fs
  */
@@ -870,6 +764,7 @@ static void init_once(void *foo)
 #ifdef CONFIG_SYSFS
 	INIT_LIST_HEAD(&bdev->bd_holder_disks);
 #endif
+	bdev->bd_bdi = &noop_backing_dev_info;
 	inode_init_once(&ei->vfs_inode);
 	/* Initialize mutex for freeze. */
 	mutex_init(&bdev->bd_fsfreeze_mutex);
@@ -884,6 +779,12 @@ static void bdev_evict_inode(struct inode *inode)
 	spin_lock(&bdev_lock);
 	list_del_init(&bdev->bd_list);
 	spin_unlock(&bdev_lock);
+	/* Detach inode from wb early as bdi_put() may free bdi->wb */
+	inode_detach_wb(inode);
+	if (bdev->bd_bdi != &noop_backing_dev_info) {
+		bdi_put(bdev->bd_bdi);
+		bdev->bd_bdi = &noop_backing_dev_info;
+	}
 }
 
 static const struct super_operations bdev_sops = {
@@ -954,6 +855,21 @@ static int bdev_set(struct inode *inode, void *data)
 
 static LIST_HEAD(all_bdevs);
 
+/*
+ * If there is a bdev inode for this device, unhash it so that it gets evicted
+ * as soon as last inode reference is dropped.
+ */
+void bdev_unhash_inode(dev_t dev)
+{
+	struct inode *inode;
+
+	inode = ilookup5(blockdev_superblock, hash(dev), bdev_test, &dev);
+	if (inode) {
+		remove_inode_hash(inode);
+		iput(inode);
+	}
+}
+
 struct block_device *bdget(dev_t dev)
 {
 	struct block_device *bdev;
@@ -971,7 +887,7 @@ struct block_device *bdget(dev_t dev)
 		bdev->bd_contains = NULL;
 		bdev->bd_super = NULL;
 		bdev->bd_inode = inode;
-		bdev->bd_block_size = (1 << inode->i_blkbits);
+		bdev->bd_block_size = i_blocksize(inode);
 		bdev->bd_part_count = 0;
 		bdev->bd_invalidated = 0;
 		inode->i_mode = S_IFBLK;
@@ -1025,13 +941,22 @@ static struct block_device *bd_acquire(struct inode *inode)
 
 	spin_lock(&bdev_lock);
 	bdev = inode->i_bdev;
-	if (bdev) {
+	if (bdev && !inode_unhashed(bdev->bd_inode)) {
 		bdgrab(bdev);
 		spin_unlock(&bdev_lock);
 		return bdev;
 	}
 	spin_unlock(&bdev_lock);
 
+	/*
+	 * i_bdev references block device inode that was already shut down
+	 * (corresponding device got removed).  Remove the reference and look
+	 * up block device inode again just in case new device got
+	 * reestablished under the same device number.
+	 */
+	if (bdev)
+		bd_forget(inode);
+
 	bdev = bdget(inode->i_rdev);
 	if (bdev) {
 		spin_lock(&bdev_lock);
@@ -1422,7 +1347,6 @@ int revalidate_disk(struct gendisk *disk)
 
 	if (disk->fops->revalidate_disk)
 		ret = disk->fops->revalidate_disk(disk);
-	blk_integrity_revalidate(disk);
 	bdev = bdget_disk(disk, 0);
 	if (!bdev)
 		return ret;
@@ -1591,6 +1515,9 @@ static int __blkdev_get(struct block_device *bdev, fmode_t mode, int for_part)
 			}
 			bd_set_size(bdev, (loff_t)bdev->bd_part->nr_sects << 9);
 		}
+
+		if (bdev->bd_bdi == &noop_backing_dev_info)
+			bdev->bd_bdi = bdi_get(disk->queue->backing_dev_info);
 	} else {
 		if (bdev->bd_contains == bdev) {
 			ret = 0;
@@ -1824,6 +1751,7 @@ static int blkdev_open(struct inode * inode, struct file * filp)
 		return -ENOMEM;
 
 	filp->f_mapping = bdev->bd_inode->i_mapping;
+	filp->f_wb_err = filemap_sample_wb_err(filp->f_mapping);
 
 	return blkdev_get(bdev, filp->f_mode, filp);
 }
@@ -1843,12 +1771,6 @@ static void __blkdev_put(struct block_device *bdev, fmode_t mode, int for_part)
 		kill_bdev(bdev);
 
 		bdev_write_inode(bdev);
-		/*
-		 * Detaching bdev inode from its wb in __destroy_inode()
-		 * is too late: the queue which embeds its bdi (along with
-		 * root wb) can be gone as soon as we put_disk() below.
-		 */
-		inode_detach_wb(bdev->bd_inode);
 	}
 	if (bdev->bd_contains == bdev) {
 		if (disk->fops->release)
@@ -2041,7 +1963,6 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 			     loff_t len)
 {
 	struct block_device *bdev = I_BDEV(bdev_file_inode(file));
-	struct request_queue *q = bdev_get_queue(bdev);
 	struct address_space *mapping;
 	loff_t end = start + len - 1;
 	loff_t isize;
@@ -2077,18 +1998,13 @@ static long blkdev_fallocate(struct file *file, int mode, loff_t start,
 	case FALLOC_FL_ZERO_RANGE:
 	case FALLOC_FL_ZERO_RANGE | FALLOC_FL_KEEP_SIZE:
 		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
-					    GFP_KERNEL, false);
+					    GFP_KERNEL, BLKDEV_ZERO_NOUNMAP);
 		break;
 	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE:
-		/* Only punch if the device can do zeroing discard. */
-		if (!blk_queue_discard(q) || !q->limits.discard_zeroes_data)
-			return -EOPNOTSUPP;
-		error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
-					     GFP_KERNEL, 0);
+		error = blkdev_issue_zeroout(bdev, start >> 9, len >> 9,
+					     GFP_KERNEL, BLKDEV_ZERO_NOFALLBACK);
 		break;
 	case FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE | FALLOC_FL_NO_HIDE_STALE:
-		if (!blk_queue_discard(q))
-			return -EOPNOTSUPP;
 		error = blkdev_issue_discard(bdev, start >> 9, len >> 9,
 					     GFP_KERNEL, 0);
 		break;
diff --git a/fs/btrfs/acl.c b/fs/btrfs/acl.c
index 247b8dfaf6e5..8d8370ddb6b2 100644
--- a/fs/btrfs/acl.c
+++ b/fs/btrfs/acl.c
@@ -78,12 +78,6 @@ static int __btrfs_set_acl(struct btrfs_trans_handle *trans,
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name = XATTR_NAME_POSIX_ACL_ACCESS;
-		if (acl) {
-			ret = posix_acl_update_mode(inode, &inode->i_mode, &acl);
-			if (ret)
-				return ret;
-		}
-		ret = 0;
 		break;
 	case ACL_TYPE_DEFAULT:
 		if (!S_ISDIR(inode->i_mode))
@@ -119,6 +113,13 @@ out:
 
 int btrfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
+	int ret;
+
+	if (type == ACL_TYPE_ACCESS && acl) {
+		ret = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+		if (ret)
+			return ret;
+	}
 	return __btrfs_set_acl(NULL, inode, acl, type);
 }
 
diff --git a/fs/btrfs/backref.c b/fs/btrfs/backref.c
index 8299601a3549..f723c11bb763 100644
--- a/fs/btrfs/backref.c
+++ b/fs/btrfs/backref.c
@@ -16,7 +16,7 @@
  * Boston, MA 021110-1307, USA.
  */
 
-#include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include <linux/rbtree.h>
 #include "ctree.h"
 #include "disk-io.h"
@@ -26,6 +26,11 @@
 #include "delayed-ref.h"
 #include "locking.h"
 
+enum merge_mode {
+	MERGE_IDENTICAL_KEYS = 1,
+	MERGE_IDENTICAL_PARENTS,
+};
+
 /* Just an arbitrary number so we can be sure this happened */
 #define BACKREF_FOUND_SHARED 6
 
@@ -533,7 +538,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 	 * slot==nritems. In that case, go to the next leaf before we continue.
 	 */
 	if (path->slots[0] >= btrfs_header_nritems(path->nodes[0])) {
-		if (time_seq == (u64)-1)
+		if (time_seq == SEQ_LAST)
 			ret = btrfs_next_leaf(root, path);
 		else
 			ret = btrfs_next_old_leaf(root, path, time_seq);
@@ -577,7 +582,7 @@ static int add_all_parents(struct btrfs_root *root, struct btrfs_path *path,
 			eie = NULL;
 		}
 next:
-		if (time_seq == (u64)-1)
+		if (time_seq == SEQ_LAST)
 			ret = btrfs_next_item(root, path);
 		else
 			ret = btrfs_next_old_item(root, path, time_seq);
@@ -629,7 +634,7 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
 
 	if (path->search_commit_root)
 		root_level = btrfs_header_level(root->commit_root);
-	else if (time_seq == (u64)-1)
+	else if (time_seq == SEQ_LAST)
 		root_level = btrfs_header_level(root->node);
 	else
 		root_level = btrfs_old_root_level(root, time_seq);
@@ -640,7 +645,7 @@ static int __resolve_indirect_ref(struct btrfs_fs_info *fs_info,
 	}
 
 	path->lowest_level = level;
-	if (time_seq == (u64)-1)
+	if (time_seq == SEQ_LAST)
 		ret = btrfs_search_slot(NULL, root, &ref->key_for_search, path,
 					0, 0);
 	else
@@ -809,14 +814,12 @@ static int __add_missing_keys(struct btrfs_fs_info *fs_info,
 /*
  * merge backrefs and adjust counts accordingly
  *
- * mode = 1: merge identical keys, if key is set
- *    FIXME: if we add more keys in __add_prelim_ref, we can merge more here.
- *           additionally, we could even add a key range for the blocks we
- *           looked into to merge even more (-> replace unresolved refs by those
- *           having a parent).
- * mode = 2: merge identical parents
+ *    FIXME: For MERGE_IDENTICAL_KEYS, if we add more keys in __add_prelim_ref
+ *           then we can merge more here. Additionally, we could even add a key
+ *           range for the blocks we looked into to merge even more (-> replace
+ *           unresolved refs by those having a parent).
  */
-static void __merge_refs(struct list_head *head, int mode)
+static void __merge_refs(struct list_head *head, enum merge_mode mode)
 {
 	struct __prelim_ref *pos1;
 
@@ -829,7 +832,7 @@ static void __merge_refs(struct list_head *head, int mode)
 
 			if (!ref_for_same_block(ref1, ref2))
 				continue;
-			if (mode == 1) {
+			if (mode == MERGE_IDENTICAL_KEYS) {
 				if (!ref1->parent && ref2->parent)
 					swap(ref1, ref2);
 			} else {
@@ -956,8 +959,7 @@ static int __add_delayed_refs(struct btrfs_delayed_ref_head *head, u64 seq,
 /*
  * add all inline backrefs for bytenr to the list
  */
-static int __add_inline_refs(struct btrfs_fs_info *fs_info,
-			     struct btrfs_path *path, u64 bytenr,
+static int __add_inline_refs(struct btrfs_path *path, u64 bytenr,
 			     int *info_level, struct list_head *prefs,
 			     struct ref_root *ref_tree,
 			     u64 *total_refs, u64 inum)
@@ -1197,7 +1199,7 @@ static int __add_keyed_refs(struct btrfs_fs_info *fs_info,
  *
  * NOTE: This can return values > 0
  *
- * If time_seq is set to (u64)-1, it will not search delayed_refs, and behave
+ * If time_seq is set to SEQ_LAST, it will not search delayed_refs, and behave
  * much like trans == NULL case, the difference only lies in it will not
  * commit root.
  * The special case is for qgroup to search roots in commit_transaction().
@@ -1244,7 +1246,7 @@ static int find_parent_nodes(struct btrfs_trans_handle *trans,
 		path->skip_locking = 1;
 	}
 
-	if (time_seq == (u64)-1)
+	if (time_seq == SEQ_LAST)
 		path->skip_locking = 1;
 
 	/*
@@ -1274,9 +1276,9 @@ again:
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 	if (trans && likely(trans->type != __TRANS_DUMMY) &&
-	    time_seq != (u64)-1) {
+	    time_seq != SEQ_LAST) {
 #else
-	if (trans && time_seq != (u64)-1) {
+	if (trans && time_seq != SEQ_LAST) {
 #endif
 		/*
 		 * look if there are updates for this ref queued and lock the
@@ -1284,10 +1286,10 @@ again:
 		 */
 		delayed_refs = &trans->transaction->delayed_refs;
 		spin_lock(&delayed_refs->lock);
-		head = btrfs_find_delayed_ref_head(trans, bytenr);
+		head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
 		if (head) {
 			if (!mutex_trylock(&head->mutex)) {
-				atomic_inc(&head->node.refs);
+				refcount_inc(&head->node.refs);
 				spin_unlock(&delayed_refs->lock);
 
 				btrfs_release_path(path);
@@ -1354,7 +1356,7 @@ again:
 		if (key.objectid == bytenr &&
 		    (key.type == BTRFS_EXTENT_ITEM_KEY ||
 		     key.type == BTRFS_METADATA_ITEM_KEY)) {
-			ret = __add_inline_refs(fs_info, path, bytenr,
+			ret = __add_inline_refs(path, bytenr,
 						&info_level, &prefs,
 						ref_tree, &total_refs,
 						inum);
@@ -1375,7 +1377,7 @@ again:
 	if (ret)
 		goto out;
 
-	__merge_refs(&prefs, 1);
+	__merge_refs(&prefs, MERGE_IDENTICAL_KEYS);
 
 	ret = __resolve_indirect_refs(fs_info, path, time_seq, &prefs,
 				      extent_item_pos, total_refs,
@@ -1383,7 +1385,7 @@ again:
 	if (ret)
 		goto out;
 
-	__merge_refs(&prefs, 2);
+	__merge_refs(&prefs, MERGE_IDENTICAL_PARENTS);
 
 	while (!list_empty(&prefs)) {
 		ref = list_first_entry(&prefs, struct __prelim_ref, list);
@@ -2303,7 +2305,7 @@ struct btrfs_data_container *init_data_container(u32 total_bytes)
 	size_t alloc_bytes;
 
 	alloc_bytes = max_t(size_t, total_bytes, sizeof(*data));
-	data = vmalloc(alloc_bytes);
+	data = kvmalloc(alloc_bytes, GFP_KERNEL);
 	if (!data)
 		return ERR_PTR(-ENOMEM);
 
@@ -2337,9 +2339,9 @@ struct inode_fs_paths *init_ipath(s32 total_bytes, struct btrfs_root *fs_root,
 	if (IS_ERR(fspath))
 		return (void *)fspath;
 
-	ifp = kmalloc(sizeof(*ifp), GFP_NOFS);
+	ifp = kmalloc(sizeof(*ifp), GFP_KERNEL);
 	if (!ifp) {
-		vfree(fspath);
+		kvfree(fspath);
 		return ERR_PTR(-ENOMEM);
 	}
 
@@ -2354,6 +2356,6 @@ void free_ipath(struct inode_fs_paths *ipath)
 {
 	if (!ipath)
 		return;
-	vfree(ipath->fspath);
+	kvfree(ipath->fspath);
 	kfree(ipath);
 }
diff --git a/fs/btrfs/btrfs_inode.h b/fs/btrfs/btrfs_inode.h
index 1a8fa46ff87e..d87ac27a5f2b 100644
--- a/fs/btrfs/btrfs_inode.h
+++ b/fs/btrfs/btrfs_inode.h
@@ -125,6 +125,13 @@ struct btrfs_inode {
 	u64 delalloc_bytes;
 
 	/*
+	 * Total number of bytes pending delalloc that fall within a file
+	 * range that is either a hole or beyond EOF (and no prealloc extent
+	 * exists in the range). This is always <= delalloc_bytes.
+	 */
+	u64 new_delalloc_bytes;
+
+	/*
 	 * total number of bytes pending defrag, used by stat to check whether
 	 * it needs COW.
 	 */
@@ -224,47 +231,45 @@ static inline void btrfs_insert_inode_hash(struct inode *inode)
 	__insert_inode_hash(inode, h);
 }
 
-static inline u64 btrfs_ino(struct inode *inode)
+static inline u64 btrfs_ino(struct btrfs_inode *inode)
 {
-	u64 ino = BTRFS_I(inode)->location.objectid;
+	u64 ino = inode->location.objectid;
 
 	/*
 	 * !ino: btree_inode
 	 * type == BTRFS_ROOT_ITEM_KEY: subvol dir
 	 */
-	if (!ino || BTRFS_I(inode)->location.type == BTRFS_ROOT_ITEM_KEY)
-		ino = inode->i_ino;
+	if (!ino || inode->location.type == BTRFS_ROOT_ITEM_KEY)
+		ino = inode->vfs_inode.i_ino;
 	return ino;
 }
 
-static inline void btrfs_i_size_write(struct inode *inode, u64 size)
+static inline void btrfs_i_size_write(struct btrfs_inode *inode, u64 size)
 {
-	i_size_write(inode, size);
-	BTRFS_I(inode)->disk_i_size = size;
+	i_size_write(&inode->vfs_inode, size);
+	inode->disk_i_size = size;
 }
 
-static inline bool btrfs_is_free_space_inode(struct inode *inode)
+static inline bool btrfs_is_free_space_inode(struct btrfs_inode *inode)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 
 	if (root == root->fs_info->tree_root &&
 	    btrfs_ino(inode) != BTRFS_BTREE_INODE_OBJECTID)
 		return true;
-	if (BTRFS_I(inode)->location.objectid == BTRFS_FREE_INO_OBJECTID)
+	if (inode->location.objectid == BTRFS_FREE_INO_OBJECTID)
 		return true;
 	return false;
 }
 
-static inline int btrfs_inode_in_log(struct inode *inode, u64 generation)
+static inline int btrfs_inode_in_log(struct btrfs_inode *inode, u64 generation)
 {
 	int ret = 0;
 
-	spin_lock(&BTRFS_I(inode)->lock);
-	if (BTRFS_I(inode)->logged_trans == generation &&
-	    BTRFS_I(inode)->last_sub_trans <=
-	    BTRFS_I(inode)->last_log_commit &&
-	    BTRFS_I(inode)->last_sub_trans <=
-	    BTRFS_I(inode)->root->last_log_commit) {
+	spin_lock(&inode->lock);
+	if (inode->logged_trans == generation &&
+	    inode->last_sub_trans <= inode->last_log_commit &&
+	    inode->last_sub_trans <= inode->root->last_log_commit) {
 		/*
 		 * After a ranged fsync we might have left some extent maps
 		 * (that fall outside the fsync's range). So return false
@@ -272,10 +277,10 @@ static inline int btrfs_inode_in_log(struct inode *inode, u64 generation)
 		 * will be called and process those extent maps.
 		 */
 		smp_mb();
-		if (list_empty(&BTRFS_I(inode)->extent_tree.modified_extents))
+		if (list_empty(&inode->extent_tree.modified_extents))
 			ret = 1;
 	}
-	spin_unlock(&BTRFS_I(inode)->lock);
+	spin_unlock(&inode->lock);
 	return ret;
 }
 
@@ -305,7 +310,8 @@ struct btrfs_dio_private {
 	 * The original bio may be split to several sub-bios, this is
 	 * done during endio of sub-bios
 	 */
-	int (*subio_endio)(struct inode *, struct btrfs_io_bio *, int);
+	blk_status_t (*subio_endio)(struct inode *, struct btrfs_io_bio *,
+			blk_status_t);
 };
 
 /*
@@ -313,17 +319,34 @@ struct btrfs_dio_private {
  * to grab i_mutex. It is used to avoid the endless truncate due to
  * nonlocked dio read.
  */
-static inline void btrfs_inode_block_unlocked_dio(struct inode *inode)
+static inline void btrfs_inode_block_unlocked_dio(struct btrfs_inode *inode)
 {
-	set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &BTRFS_I(inode)->runtime_flags);
+	set_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags);
 	smp_mb();
 }
 
-static inline void btrfs_inode_resume_unlocked_dio(struct inode *inode)
+static inline void btrfs_inode_resume_unlocked_dio(struct btrfs_inode *inode)
 {
 	smp_mb__before_atomic();
-	clear_bit(BTRFS_INODE_READDIO_NEED_LOCK,
-		  &BTRFS_I(inode)->runtime_flags);
+	clear_bit(BTRFS_INODE_READDIO_NEED_LOCK, &inode->runtime_flags);
+}
+
+static inline void btrfs_print_data_csum_error(struct btrfs_inode *inode,
+		u64 logical_start, u32 csum, u32 csum_expected, int mirror_num)
+{
+	struct btrfs_root *root = inode->root;
+
+	/* Output minus objectid, which is more meaningful */
+	if (root->objectid >= BTRFS_LAST_FREE_OBJECTID)
+		btrfs_warn_rl(root->fs_info,
+	"csum failed root %lld ino %lld off %llu csum 0x%08x expected csum 0x%08x mirror %d",
+			root->objectid, btrfs_ino(inode),
+			logical_start, csum, csum_expected, mirror_num);
+	else
+		btrfs_warn_rl(root->fs_info,
+	"csum failed root %llu ino %llu off %llu csum 0x%08x expected csum 0x%08x mirror %d",
+			root->objectid, btrfs_ino(inode),
+			logical_start, csum, csum_expected, mirror_num);
 }
 
 bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end);
diff --git a/fs/btrfs/check-integrity.c b/fs/btrfs/check-integrity.c
index ab14c2e635ca..11d37c94ce05 100644
--- a/fs/btrfs/check-integrity.c
+++ b/fs/btrfs/check-integrity.c
@@ -94,7 +94,7 @@
 #include <linux/mutex.h>
 #include <linux/genhd.h>
 #include <linux/blkdev.h>
-#include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include <linux/string.h>
 #include "ctree.h"
 #include "disk-io.h"
@@ -1638,12 +1638,7 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 		struct bio *bio;
 		unsigned int j;
 
-		bio = btrfs_io_bio_alloc(GFP_NOFS, num_pages - i);
-		if (!bio) {
-			pr_info("btrfsic: bio_alloc() for %u pages failed!\n",
-			       num_pages - i);
-			return -1;
-		}
+		bio = btrfs_io_bio_alloc(num_pages - i);
 		bio->bi_bdev = block_ctx->dev->bdev;
 		bio->bi_iter.bi_sector = dev_bytenr >> 9;
 		bio_set_op_attrs(bio, REQ_OP_READ, 0);
@@ -1668,14 +1663,8 @@ static int btrfsic_read_block(struct btrfsic_state *state,
 		dev_bytenr += (j - i) * PAGE_SIZE;
 		i = j;
 	}
-	for (i = 0; i < num_pages; i++) {
+	for (i = 0; i < num_pages; i++)
 		block_ctx->datav[i] = kmap(block_ctx->pagev[i]);
-		if (!block_ctx->datav[i]) {
-			pr_info("btrfsic: kmap() failed (dev %s)!\n",
-			       block_ctx->dev->name);
-			return -1;
-		}
-	}
 
 	return block_ctx->len;
 }
@@ -2129,7 +2118,7 @@ static void btrfsic_bio_end_io(struct bio *bp)
 	/* mutex is not held! This is not save if IO is not yet completed
 	 * on umount */
 	iodone_w_error = 0;
-	if (bp->bi_error)
+	if (bp->bi_status)
 		iodone_w_error = 1;
 
 	BUG_ON(NULL == block);
@@ -2143,7 +2132,7 @@ static void btrfsic_bio_end_io(struct bio *bp)
 		if ((dev_state->state->print_mask &
 		     BTRFSIC_PRINT_MASK_END_IO_BIO_BH))
 			pr_info("bio_end_io(err=%d) for %c @%llu (%s/%llu/%d)\n",
-			       bp->bi_error,
+			       bp->bi_status,
 			       btrfsic_get_block_type(dev_state->state, block),
 			       block->logical_bytenr, dev_state->name,
 			       block->dev_bytenr, block->mirror_num);
@@ -2822,44 +2811,47 @@ static void __btrfsic_submit_bio(struct bio *bio)
 	dev_state = btrfsic_dev_state_lookup(bio->bi_bdev);
 	if (NULL != dev_state &&
 	    (bio_op(bio) == REQ_OP_WRITE) && bio_has_data(bio)) {
-		unsigned int i;
+		unsigned int i = 0;
 		u64 dev_bytenr;
 		u64 cur_bytenr;
-		struct bio_vec *bvec;
+		struct bio_vec bvec;
+		struct bvec_iter iter;
 		int bio_is_patched;
 		char **mapped_datav;
+		unsigned int segs = bio_segments(bio);
 
 		dev_bytenr = 512 * bio->bi_iter.bi_sector;
 		bio_is_patched = 0;
 		if (dev_state->state->print_mask &
 		    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH)
 			pr_info("submit_bio(rw=%d,0x%x, bi_vcnt=%u, bi_sector=%llu (bytenr %llu), bi_bdev=%p)\n",
-			       bio_op(bio), bio->bi_opf, bio->bi_vcnt,
+			       bio_op(bio), bio->bi_opf, segs,
 			       (unsigned long long)bio->bi_iter.bi_sector,
 			       dev_bytenr, bio->bi_bdev);
 
-		mapped_datav = kmalloc_array(bio->bi_vcnt,
+		mapped_datav = kmalloc_array(segs,
 					     sizeof(*mapped_datav), GFP_NOFS);
 		if (!mapped_datav)
 			goto leave;
 		cur_bytenr = dev_bytenr;
 
-		bio_for_each_segment_all(bvec, bio, i) {
-			BUG_ON(bvec->bv_len != PAGE_SIZE);
-			mapped_datav[i] = kmap(bvec->bv_page);
+		bio_for_each_segment(bvec, bio, iter) {
+			BUG_ON(bvec.bv_len != PAGE_SIZE);
+			mapped_datav[i] = kmap(bvec.bv_page);
+			i++;
 
 			if (dev_state->state->print_mask &
 			    BTRFSIC_PRINT_MASK_SUBMIT_BIO_BH_VERBOSE)
 				pr_info("#%u: bytenr=%llu, len=%u, offset=%u\n",
-				       i, cur_bytenr, bvec->bv_len, bvec->bv_offset);
-			cur_bytenr += bvec->bv_len;
+				       i, cur_bytenr, bvec.bv_len, bvec.bv_offset);
+			cur_bytenr += bvec.bv_len;
 		}
 		btrfsic_process_written_block(dev_state, dev_bytenr,
-					      mapped_datav, bio->bi_vcnt,
+					      mapped_datav, segs,
 					      bio, &bio_is_patched,
 					      NULL, bio->bi_opf);
-		bio_for_each_segment_all(bvec, bio, i)
-			kunmap(bvec->bv_page);
+		bio_for_each_segment(bvec, bio, iter)
+			kunmap(bvec.bv_page);
 		kfree(mapped_datav);
 	} else if (NULL != dev_state && (bio->bi_opf & REQ_PREFLUSH)) {
 		if (dev_state->state->print_mask &
@@ -2923,13 +2915,10 @@ int btrfsic_mount(struct btrfs_fs_info *fs_info,
 		       fs_info->sectorsize, PAGE_SIZE);
 		return -1;
 	}
-	state = kzalloc(sizeof(*state), GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
+	state = kvzalloc(sizeof(*state), GFP_KERNEL);
 	if (!state) {
-		state = vzalloc(sizeof(*state));
-		if (!state) {
-			pr_info("btrfs check-integrity: vzalloc() failed!\n");
-			return -1;
-		}
+		pr_info("btrfs check-integrity: allocation failed!\n");
+		return -1;
 	}
 
 	if (!btrfsic_is_initialized) {
diff --git a/fs/btrfs/compression.c b/fs/btrfs/compression.c
index 7f390849343b..d2ef9ac2a630 100644
--- a/fs/btrfs/compression.c
+++ b/fs/btrfs/compression.c
@@ -32,6 +32,7 @@
 #include <linux/writeback.h>
 #include <linux/bit_spinlock.h>
 #include <linux/slab.h>
+#include <linux/sched/mm.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -42,48 +43,7 @@
 #include "extent_io.h"
 #include "extent_map.h"
 
-struct compressed_bio {
-	/* number of bios pending for this compressed extent */
-	atomic_t pending_bios;
-
-	/* the pages with the compressed data on them */
-	struct page **compressed_pages;
-
-	/* inode that owns this data */
-	struct inode *inode;
-
-	/* starting offset in the inode for our pages */
-	u64 start;
-
-	/* number of bytes in the inode we're working on */
-	unsigned long len;
-
-	/* number of bytes on disk */
-	unsigned long compressed_len;
-
-	/* the compression algorithm for this bio */
-	int compress_type;
-
-	/* number of compressed pages in the array */
-	unsigned long nr_pages;
-
-	/* IO errors */
-	int errors;
-	int mirror_num;
-
-	/* for reads, this is the bio we are copying the data into */
-	struct bio *orig_bio;
-
-	/*
-	 * the start of a variable length array of checksums only
-	 * used by reads
-	 */
-	u32 sums;
-};
-
-static int btrfs_decompress_bio(int type, struct page **pages_in,
-				   u64 disk_start, struct bio *orig_bio,
-				   size_t srclen);
+static int btrfs_decompress_bio(struct compressed_bio *cb);
 
 static inline int compressed_bio_size(struct btrfs_fs_info *fs_info,
 				      unsigned long disk_size)
@@ -94,13 +54,7 @@ static inline int compressed_bio_size(struct btrfs_fs_info *fs_info,
 		(DIV_ROUND_UP(disk_size, fs_info->sectorsize)) * csum_size;
 }
 
-static struct bio *compressed_bio_alloc(struct block_device *bdev,
-					u64 first_byte, gfp_t gfp_flags)
-{
-	return btrfs_bio_alloc(bdev, first_byte >> 9, BIO_MAX_PAGES, gfp_flags);
-}
-
-static int check_compressed_csum(struct inode *inode,
+static int check_compressed_csum(struct btrfs_inode *inode,
 				 struct compressed_bio *cb,
 				 u64 disk_start)
 {
@@ -111,7 +65,7 @@ static int check_compressed_csum(struct inode *inode,
 	u32 csum;
 	u32 *cb_sum = &cb->sums;
 
-	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)
+	if (inode->flags & BTRFS_INODE_NODATASUM)
 		return 0;
 
 	for (i = 0; i < cb->nr_pages; i++) {
@@ -124,10 +78,8 @@ static int check_compressed_csum(struct inode *inode,
 		kunmap_atomic(kaddr);
 
 		if (csum != *cb_sum) {
-			btrfs_info(BTRFS_I(inode)->root->fs_info,
-			   "csum failed ino %llu extent %llu csum %u wanted %u mirror %d",
-			   btrfs_ino(inode), disk_start, csum, *cb_sum,
-			   cb->mirror_num);
+			btrfs_print_data_csum_error(inode, disk_start, csum,
+					*cb_sum, cb->mirror_num);
 			ret = -EIO;
 			goto fail;
 		}
@@ -157,17 +109,17 @@ static void end_compressed_bio_read(struct bio *bio)
 	unsigned long index;
 	int ret;
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		cb->errors = 1;
 
 	/* if there are more bios still pending for this compressed
 	 * extent, just exit
 	 */
-	if (!atomic_dec_and_test(&cb->pending_bios))
+	if (!refcount_dec_and_test(&cb->pending_bios))
 		goto out;
 
 	inode = cb->inode;
-	ret = check_compressed_csum(inode, cb,
+	ret = check_compressed_csum(BTRFS_I(inode), cb,
 				    (u64)bio->bi_iter.bi_sector << 9);
 	if (ret)
 		goto csum_failed;
@@ -175,11 +127,8 @@ static void end_compressed_bio_read(struct bio *bio)
 	/* ok, we're the last bio for this extent, lets start
 	 * the decompression.
 	 */
-	ret = btrfs_decompress_bio(cb->compress_type,
-				      cb->compressed_pages,
-				      cb->start,
-				      cb->orig_bio,
-				      cb->compressed_len);
+	ret = btrfs_decompress_bio(cb);
+
 csum_failed:
 	if (ret)
 		cb->errors = 1;
@@ -203,6 +152,7 @@ csum_failed:
 		 * we have verified the checksum already, set page
 		 * checked so the end_io handlers know about it
 		 */
+		ASSERT(!bio_flagged(bio, BIO_CLONED));
 		bio_for_each_segment_all(bvec, cb->orig_bio, i)
 			SetPageChecked(bvec->bv_page);
 
@@ -270,13 +220,13 @@ static void end_compressed_bio_write(struct bio *bio)
 	struct page *page;
 	unsigned long index;
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		cb->errors = 1;
 
 	/* if there are more bios still pending for this compressed
 	 * extent, just exit
 	 */
-	if (!atomic_dec_and_test(&cb->pending_bios))
+	if (!refcount_dec_and_test(&cb->pending_bios))
 		goto out;
 
 	/* ok, we're the last bio for this extent, step one is to
@@ -289,7 +239,7 @@ static void end_compressed_bio_write(struct bio *bio)
 					 cb->start,
 					 cb->start + cb->len - 1,
 					 NULL,
-					 bio->bi_error ? 0 : 1);
+					 bio->bi_status ? 0 : 1);
 	cb->compressed_pages[0]->mapping = NULL;
 
 	end_compressed_writeback(inode, cb);
@@ -322,7 +272,7 @@ out:
  * This also checksums the file bytes and gets things ready for
  * the end io hooks.
  */
-int btrfs_submit_compressed_write(struct inode *inode, u64 start,
+blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				 unsigned long len, u64 disk_start,
 				 unsigned long compressed_len,
 				 struct page **compressed_pages,
@@ -337,14 +287,14 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 	struct page *page;
 	u64 first_byte = disk_start;
 	struct block_device *bdev;
-	int ret;
+	blk_status_t ret;
 	int skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
 	WARN_ON(start & ((u64)PAGE_SIZE - 1));
 	cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS);
 	if (!cb)
-		return -ENOMEM;
-	atomic_set(&cb->pending_bios, 0);
+		return BLK_STS_RESOURCE;
+	refcount_set(&cb->pending_bios, 0);
 	cb->errors = 0;
 	cb->inode = inode;
 	cb->start = start;
@@ -357,30 +307,26 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 
 	bdev = fs_info->fs_devices->latest_bdev;
 
-	bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS);
-	if (!bio) {
-		kfree(cb);
-		return -ENOMEM;
-	}
+	bio = btrfs_bio_alloc(bdev, first_byte);
 	bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 	bio->bi_private = cb;
 	bio->bi_end_io = end_compressed_bio_write;
-	atomic_inc(&cb->pending_bios);
+	refcount_set(&cb->pending_bios, 1);
 
 	/* create and submit bios for the compressed pages */
 	bytes_left = compressed_len;
 	for (pg_index = 0; pg_index < cb->nr_pages; pg_index++) {
+		int submit = 0;
+
 		page = compressed_pages[pg_index];
 		page->mapping = inode->i_mapping;
 		if (bio->bi_iter.bi_size)
-			ret = io_tree->ops->merge_bio_hook(page, 0,
+			submit = io_tree->ops->merge_bio_hook(page, 0,
 							   PAGE_SIZE,
 							   bio, 0);
-		else
-			ret = 0;
 
 		page->mapping = NULL;
-		if (ret || bio_add_page(bio, page, PAGE_SIZE, 0) <
+		if (submit || bio_add_page(bio, page, PAGE_SIZE, 0) <
 		    PAGE_SIZE) {
 			bio_get(bio);
 
@@ -390,7 +336,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 			 * we inc the count.  Otherwise, the cb might get
 			 * freed before we're done setting it up
 			 */
-			atomic_inc(&cb->pending_bios);
+			refcount_inc(&cb->pending_bios);
 			ret = btrfs_bio_wq_end_io(fs_info, bio,
 						  BTRFS_WQ_ENDIO_DATA);
 			BUG_ON(ret); /* -ENOMEM */
@@ -402,14 +348,13 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 
 			ret = btrfs_map_bio(fs_info, bio, 0, 1);
 			if (ret) {
-				bio->bi_error = ret;
+				bio->bi_status = ret;
 				bio_endio(bio);
 			}
 
 			bio_put(bio);
 
-			bio = compressed_bio_alloc(bdev, first_byte, GFP_NOFS);
-			BUG_ON(!bio);
+			bio = btrfs_bio_alloc(bdev, first_byte);
 			bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
 			bio->bi_private = cb;
 			bio->bi_end_io = end_compressed_bio_write;
@@ -436,7 +381,7 @@ int btrfs_submit_compressed_write(struct inode *inode, u64 start,
 
 	ret = btrfs_map_bio(fs_info, bio, 0, 1);
 	if (ret) {
-		bio->bi_error = ret;
+		bio->bi_status = ret;
 		bio_endio(bio);
 	}
 
@@ -571,7 +516,7 @@ next:
  * After the compressed pages are read, we copy the bytes into the
  * bio we were passed and then call the bio end_io calls
  */
-int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
+blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -588,7 +533,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	u64 em_len;
 	u64 em_start;
 	struct extent_map *em;
-	int ret = -ENOMEM;
+	blk_status_t ret = BLK_STS_RESOURCE;
 	int faili = 0;
 	u32 *sums;
 
@@ -602,14 +547,14 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				   PAGE_SIZE);
 	read_unlock(&em_tree->lock);
 	if (!em)
-		return -EIO;
+		return BLK_STS_IOERR;
 
 	compressed_len = em->block_len;
 	cb = kmalloc(compressed_bio_size(fs_info, compressed_len), GFP_NOFS);
 	if (!cb)
 		goto out;
 
-	atomic_set(&cb->pending_bios, 0);
+	refcount_set(&cb->pending_bios, 0);
 	cb->errors = 0;
 	cb->inode = inode;
 	cb->mirror_num = mirror_num;
@@ -640,7 +585,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 							      __GFP_HIGHMEM);
 		if (!cb->compressed_pages[pg_index]) {
 			faili = pg_index - 1;
-			ret = -ENOMEM;
+			ret = BLK_STS_RESOURCE;
 			goto fail2;
 		}
 	}
@@ -652,28 +597,26 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 	/* include any pages we added in add_ra-bio_pages */
 	cb->len = bio->bi_iter.bi_size;
 
-	comp_bio = compressed_bio_alloc(bdev, cur_disk_byte, GFP_NOFS);
-	if (!comp_bio)
-		goto fail2;
+	comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte);
 	bio_set_op_attrs (comp_bio, REQ_OP_READ, 0);
 	comp_bio->bi_private = cb;
 	comp_bio->bi_end_io = end_compressed_bio_read;
-	atomic_inc(&cb->pending_bios);
+	refcount_set(&cb->pending_bios, 1);
 
 	for (pg_index = 0; pg_index < nr_pages; pg_index++) {
+		int submit = 0;
+
 		page = cb->compressed_pages[pg_index];
 		page->mapping = inode->i_mapping;
 		page->index = em_start >> PAGE_SHIFT;
 
 		if (comp_bio->bi_iter.bi_size)
-			ret = tree->ops->merge_bio_hook(page, 0,
+			submit = tree->ops->merge_bio_hook(page, 0,
 							PAGE_SIZE,
 							comp_bio, 0);
-		else
-			ret = 0;
 
 		page->mapping = NULL;
-		if (ret || bio_add_page(comp_bio, page, PAGE_SIZE, 0) <
+		if (submit || bio_add_page(comp_bio, page, PAGE_SIZE, 0) <
 		    PAGE_SIZE) {
 			bio_get(comp_bio);
 
@@ -687,7 +630,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 			 * we inc the count.  Otherwise, the cb might get
 			 * freed before we're done setting it up
 			 */
-			atomic_inc(&cb->pending_bios);
+			refcount_inc(&cb->pending_bios);
 
 			if (!(BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM)) {
 				ret = btrfs_lookup_bio_sums(inode, comp_bio,
@@ -699,15 +642,13 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
 			ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0);
 			if (ret) {
-				comp_bio->bi_error = ret;
+				comp_bio->bi_status = ret;
 				bio_endio(comp_bio);
 			}
 
 			bio_put(comp_bio);
 
-			comp_bio = compressed_bio_alloc(bdev, cur_disk_byte,
-							GFP_NOFS);
-			BUG_ON(!comp_bio);
+			comp_bio = btrfs_bio_alloc(bdev, cur_disk_byte);
 			bio_set_op_attrs(comp_bio, REQ_OP_READ, 0);
 			comp_bio->bi_private = cb;
 			comp_bio->bi_end_io = end_compressed_bio_read;
@@ -728,7 +669,7 @@ int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 
 	ret = btrfs_map_bio(fs_info, comp_bio, mirror_num, 0);
 	if (ret) {
-		comp_bio->bi_error = ret;
+		comp_bio->bi_status = ret;
 		bio_endio(comp_bio);
 	}
 
@@ -803,6 +744,7 @@ static struct list_head *find_workspace(int type)
 	struct list_head *workspace;
 	int cpus = num_online_cpus();
 	int idx = type - 1;
+	unsigned nofs_flag;
 
 	struct list_head *idle_ws	= &btrfs_comp_ws[idx].idle_ws;
 	spinlock_t *ws_lock		= &btrfs_comp_ws[idx].ws_lock;
@@ -832,7 +774,15 @@ again:
 	atomic_inc(total_ws);
 	spin_unlock(ws_lock);
 
+	/*
+	 * Allocation helpers call vmalloc that can't use GFP_NOFS, so we have
+	 * to turn it off here because we might get called from the restricted
+	 * context of btrfs_compress_bio/btrfs_compress_pages
+	 */
+	nofs_flag = memalloc_nofs_save();
 	workspace = btrfs_compress_op[idx]->alloc_workspace();
+	memalloc_nofs_restore(nofs_flag);
+
 	if (IS_ERR(workspace)) {
 		atomic_dec(total_ws);
 		wake_up(ws_wait);
@@ -913,32 +863,28 @@ static void free_workspaces(void)
 }
 
 /*
- * given an address space and start/len, compress the bytes.
+ * Given an address space and start and length, compress the bytes into @pages
+ * that are allocated on demand.
  *
- * pages are allocated to hold the compressed result and stored
- * in 'pages'
+ * @out_pages is an in/out parameter, holds maximum number of pages to allocate
+ * and returns number of actually allocated pages
  *
- * out_pages is used to return the number of pages allocated.  There
- * may be pages allocated even if we return an error
- *
- * total_in is used to return the number of bytes actually read.  It
- * may be smaller then len if we had to exit early because we
+ * @total_in is used to return the number of bytes actually read.  It
+ * may be smaller than the input length if we had to exit early because we
  * ran out of room in the pages array or because we cross the
  * max_out threshold.
  *
- * total_out is used to return the total number of compressed bytes
+ * @total_out is an in/out parameter, must be set to the input length and will
+ * be also used to return the total number of compressed bytes
  *
- * max_out tells us the max number of bytes that we're allowed to
+ * @max_out tells us the max number of bytes that we're allowed to
  * stuff into pages
  */
 int btrfs_compress_pages(int type, struct address_space *mapping,
-			 u64 start, unsigned long len,
-			 struct page **pages,
-			 unsigned long nr_dest_pages,
+			 u64 start, struct page **pages,
 			 unsigned long *out_pages,
 			 unsigned long *total_in,
-			 unsigned long *total_out,
-			 unsigned long max_out)
+			 unsigned long *total_out)
 {
 	struct list_head *workspace;
 	int ret;
@@ -946,10 +892,9 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
 	workspace = find_workspace(type);
 
 	ret = btrfs_compress_op[type-1]->compress_pages(workspace, mapping,
-						      start, len, pages,
-						      nr_dest_pages, out_pages,
-						      total_in, total_out,
-						      max_out);
+						      start, pages,
+						      out_pages,
+						      total_in, total_out);
 	free_workspace(type, workspace);
 	return ret;
 }
@@ -968,19 +913,16 @@ int btrfs_compress_pages(int type, struct address_space *mapping,
  * be contiguous.  They all correspond to the range of bytes covered by
  * the compressed extent.
  */
-static int btrfs_decompress_bio(int type, struct page **pages_in,
-				   u64 disk_start, struct bio *orig_bio,
-				   size_t srclen)
+static int btrfs_decompress_bio(struct compressed_bio *cb)
 {
 	struct list_head *workspace;
 	int ret;
+	int type = cb->compress_type;
 
 	workspace = find_workspace(type);
-
-	ret = btrfs_compress_op[type-1]->decompress_bio(workspace, pages_in,
-							 disk_start, orig_bio,
-							 srclen);
+	ret = btrfs_compress_op[type - 1]->decompress_bio(workspace, cb);
 	free_workspace(type, workspace);
+
 	return ret;
 }
 
@@ -1017,13 +959,14 @@ void btrfs_exit_compress(void)
  *
  * total_out is the last byte of the buffer
  */
-int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
+int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
 			      unsigned long total_out, u64 disk_start,
 			      struct bio *bio)
 {
 	unsigned long buf_offset;
 	unsigned long current_buf_start;
 	unsigned long start_byte;
+	unsigned long prev_start_byte;
 	unsigned long working_bytes = total_out - buf_start;
 	unsigned long bytes;
 	char *kaddr;
@@ -1071,26 +1014,34 @@ int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
 		if (!bio->bi_iter.bi_size)
 			return 0;
 		bvec = bio_iter_iovec(bio, bio->bi_iter);
-
+		prev_start_byte = start_byte;
 		start_byte = page_offset(bvec.bv_page) - disk_start;
 
 		/*
-		 * make sure our new page is covered by this
-		 * working buffer
+		 * We need to make sure we're only adjusting
+		 * our offset into compression working buffer when
+		 * we're switching pages.  Otherwise we can incorrectly
+		 * keep copying when we were actually done.
 		 */
-		if (total_out <= start_byte)
-			return 1;
+		if (start_byte != prev_start_byte) {
+			/*
+			 * make sure our new page is covered by this
+			 * working buffer
+			 */
+			if (total_out <= start_byte)
+				return 1;
 
-		/*
-		 * the next page in the biovec might not be adjacent
-		 * to the last page, but it might still be found
-		 * inside this working buffer. bump our offset pointer
-		 */
-		if (total_out > start_byte &&
-		    current_buf_start < start_byte) {
-			buf_offset = start_byte - buf_start;
-			working_bytes = total_out - start_byte;
-			current_buf_start = buf_start + buf_offset;
+			/*
+			 * the next page in the biovec might not be adjacent
+			 * to the last page, but it might still be found
+			 * inside this working buffer. bump our offset pointer
+			 */
+			if (total_out > start_byte &&
+			    current_buf_start < start_byte) {
+				buf_offset = start_byte - buf_start;
+				working_bytes = total_out - start_byte;
+				current_buf_start = buf_start + buf_offset;
+			}
 		}
 	}
 
diff --git a/fs/btrfs/compression.h b/fs/btrfs/compression.h
index 09879579fbc8..87f6d3332163 100644
--- a/fs/btrfs/compression.h
+++ b/fs/btrfs/compression.h
@@ -19,29 +19,80 @@
 #ifndef __BTRFS_COMPRESSION_
 #define __BTRFS_COMPRESSION_
 
+/*
+ * We want to make sure that amount of RAM required to uncompress an extent is
+ * reasonable, so we limit the total size in ram of a compressed extent to
+ * 128k.  This is a crucial number because it also controls how easily we can
+ * spread reads across cpus for decompression.
+ *
+ * We also want to make sure the amount of IO required to do a random read is
+ * reasonably small, so we limit the size of a compressed extent to 128k.
+ */
+
+/* Maximum length of compressed data stored on disk */
+#define BTRFS_MAX_COMPRESSED		(SZ_128K)
+/* Maximum size of data before compression */
+#define BTRFS_MAX_UNCOMPRESSED		(SZ_128K)
+
+struct compressed_bio {
+	/* number of bios pending for this compressed extent */
+	refcount_t pending_bios;
+
+	/* the pages with the compressed data on them */
+	struct page **compressed_pages;
+
+	/* inode that owns this data */
+	struct inode *inode;
+
+	/* starting offset in the inode for our pages */
+	u64 start;
+
+	/* number of bytes in the inode we're working on */
+	unsigned long len;
+
+	/* number of bytes on disk */
+	unsigned long compressed_len;
+
+	/* the compression algorithm for this bio */
+	int compress_type;
+
+	/* number of compressed pages in the array */
+	unsigned long nr_pages;
+
+	/* IO errors */
+	int errors;
+	int mirror_num;
+
+	/* for reads, this is the bio we are copying the data into */
+	struct bio *orig_bio;
+
+	/*
+	 * the start of a variable length array of checksums only
+	 * used by reads
+	 */
+	u32 sums;
+};
+
 void btrfs_init_compress(void);
 void btrfs_exit_compress(void);
 
 int btrfs_compress_pages(int type, struct address_space *mapping,
-			 u64 start, unsigned long len,
-			 struct page **pages,
-			 unsigned long nr_dest_pages,
+			 u64 start, struct page **pages,
 			 unsigned long *out_pages,
 			 unsigned long *total_in,
-			 unsigned long *total_out,
-			 unsigned long max_out);
+			 unsigned long *total_out);
 int btrfs_decompress(int type, unsigned char *data_in, struct page *dest_page,
 		     unsigned long start_byte, size_t srclen, size_t destlen);
-int btrfs_decompress_buf2page(char *buf, unsigned long buf_start,
+int btrfs_decompress_buf2page(const char *buf, unsigned long buf_start,
 			      unsigned long total_out, u64 disk_start,
 			      struct bio *bio);
 
-int btrfs_submit_compressed_write(struct inode *inode, u64 start,
+blk_status_t btrfs_submit_compressed_write(struct inode *inode, u64 start,
 				  unsigned long len, u64 disk_start,
 				  unsigned long compressed_len,
 				  struct page **compressed_pages,
 				  unsigned long nr_pages);
-int btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
+blk_status_t btrfs_submit_compressed_read(struct inode *inode, struct bio *bio,
 				 int mirror_num, unsigned long bio_flags);
 
 enum btrfs_compression_type {
@@ -59,19 +110,14 @@ struct btrfs_compress_op {
 
 	int (*compress_pages)(struct list_head *workspace,
 			      struct address_space *mapping,
-			      u64 start, unsigned long len,
+			      u64 start,
 			      struct page **pages,
-			      unsigned long nr_dest_pages,
 			      unsigned long *out_pages,
 			      unsigned long *total_in,
-			      unsigned long *total_out,
-			      unsigned long max_out);
+			      unsigned long *total_out);
 
 	int (*decompress_bio)(struct list_head *workspace,
-				 struct page **pages_in,
-				 u64 disk_start,
-				 struct bio *orig_bio,
-				 size_t srclen);
+				struct compressed_bio *cb);
 
 	int (*decompress)(struct list_head *workspace,
 			  unsigned char *data_in,
diff --git a/fs/btrfs/ctree.c b/fs/btrfs/ctree.c
index a426dc822d4d..3f4daa9d6e2c 100644
--- a/fs/btrfs/ctree.c
+++ b/fs/btrfs/ctree.c
@@ -19,7 +19,7 @@
 #include <linux/sched.h>
 #include <linux/slab.h>
 #include <linux/rbtree.h>
-#include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "transaction.h"
@@ -28,9 +28,9 @@
 
 static int split_node(struct btrfs_trans_handle *trans, struct btrfs_root
 		      *root, struct btrfs_path *path, int level);
-static int split_leaf(struct btrfs_trans_handle *trans, struct btrfs_root
-		      *root, struct btrfs_key *ins_key,
-		      struct btrfs_path *path, int data_size, int extend);
+static int split_leaf(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		      const struct btrfs_key *ins_key, struct btrfs_path *path,
+		      int data_size, int extend);
 static int push_node_left(struct btrfs_trans_handle *trans,
 			  struct btrfs_fs_info *fs_info,
 			  struct extent_buffer *dst,
@@ -426,7 +426,7 @@ void btrfs_put_tree_mod_seq(struct btrfs_fs_info *fs_info,
 	tm_root = &fs_info->tree_mod_log;
 	for (node = rb_first(tm_root); node; node = next) {
 		next = rb_next(node);
-		tm = container_of(node, struct tree_mod_elem, node);
+		tm = rb_entry(node, struct tree_mod_elem, node);
 		if (tm->seq > min_seq)
 			continue;
 		rb_erase(node, tm_root);
@@ -453,14 +453,12 @@ __tree_mod_log_insert(struct btrfs_fs_info *fs_info, struct tree_mod_elem *tm)
 	struct rb_node *parent = NULL;
 	struct tree_mod_elem *cur;
 
-	BUG_ON(!tm);
-
 	tm->seq = btrfs_inc_tree_mod_seq(fs_info);
 
 	tm_root = &fs_info->tree_mod_log;
 	new = &tm_root->rb_node;
 	while (*new) {
-		cur = container_of(*new, struct tree_mod_elem, node);
+		cur = rb_entry(*new, struct tree_mod_elem, node);
 		parent = *new;
 		if (cur->logical < tm->logical)
 			new = &((*new)->rb_left);
@@ -569,7 +567,7 @@ tree_mod_log_insert_key(struct btrfs_fs_info *fs_info,
 static noinline int
 tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
 			 struct extent_buffer *eb, int dst_slot, int src_slot,
-			 int nr_items, gfp_t flags)
+			 int nr_items)
 {
 	struct tree_mod_elem *tm = NULL;
 	struct tree_mod_elem **tm_list = NULL;
@@ -580,11 +578,11 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
 	if (!tree_mod_need_log(fs_info, eb))
 		return 0;
 
-	tm_list = kcalloc(nr_items, sizeof(struct tree_mod_elem *), flags);
+	tm_list = kcalloc(nr_items, sizeof(struct tree_mod_elem *), GFP_NOFS);
 	if (!tm_list)
 		return -ENOMEM;
 
-	tm = kzalloc(sizeof(*tm), flags);
+	tm = kzalloc(sizeof(*tm), GFP_NOFS);
 	if (!tm) {
 		ret = -ENOMEM;
 		goto free_tms;
@@ -598,7 +596,7 @@ tree_mod_log_insert_move(struct btrfs_fs_info *fs_info,
 
 	for (i = 0; i + dst_slot < src_slot && i < nr_items; i++) {
 		tm_list[i] = alloc_tree_mod_elem(eb, i + dst_slot,
-		    MOD_LOG_KEY_REMOVE_WHILE_MOVING, flags);
+		    MOD_LOG_KEY_REMOVE_WHILE_MOVING, GFP_NOFS);
 		if (!tm_list[i]) {
 			ret = -ENOMEM;
 			goto free_tms;
@@ -665,7 +663,7 @@ __tree_mod_log_free_eb(struct btrfs_fs_info *fs_info,
 static noinline int
 tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
 			 struct extent_buffer *old_root,
-			 struct extent_buffer *new_root, gfp_t flags,
+			 struct extent_buffer *new_root,
 			 int log_removal)
 {
 	struct tree_mod_elem *tm = NULL;
@@ -680,14 +678,14 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
 	if (log_removal && btrfs_header_level(old_root) > 0) {
 		nritems = btrfs_header_nritems(old_root);
 		tm_list = kcalloc(nritems, sizeof(struct tree_mod_elem *),
-				  flags);
+				  GFP_NOFS);
 		if (!tm_list) {
 			ret = -ENOMEM;
 			goto free_tms;
 		}
 		for (i = 0; i < nritems; i++) {
 			tm_list[i] = alloc_tree_mod_elem(old_root, i,
-			    MOD_LOG_KEY_REMOVE_WHILE_FREEING, flags);
+			    MOD_LOG_KEY_REMOVE_WHILE_FREEING, GFP_NOFS);
 			if (!tm_list[i]) {
 				ret = -ENOMEM;
 				goto free_tms;
@@ -695,7 +693,7 @@ tree_mod_log_insert_root(struct btrfs_fs_info *fs_info,
 		}
 	}
 
-	tm = kzalloc(sizeof(*tm), flags);
+	tm = kzalloc(sizeof(*tm), GFP_NOFS);
 	if (!tm) {
 		ret = -ENOMEM;
 		goto free_tms;
@@ -746,7 +744,7 @@ __tree_mod_log_search(struct btrfs_fs_info *fs_info, u64 start, u64 min_seq,
 	tm_root = &fs_info->tree_mod_log;
 	node = tm_root->rb_node;
 	while (node) {
-		cur = container_of(node, struct tree_mod_elem, node);
+		cur = rb_entry(node, struct tree_mod_elem, node);
 		if (cur->logical < start) {
 			node = node->rb_left;
 		} else if (cur->logical > start) {
@@ -875,7 +873,7 @@ tree_mod_log_eb_move(struct btrfs_fs_info *fs_info, struct extent_buffer *dst,
 {
 	int ret;
 	ret = tree_mod_log_insert_move(fs_info, dst, dst_offset, src_offset,
-				       nr_items, GFP_NOFS);
+				       nr_items);
 	BUG_ON(ret < 0);
 }
 
@@ -945,7 +943,7 @@ tree_mod_log_set_root_pointer(struct btrfs_root *root,
 {
 	int ret;
 	ret = tree_mod_log_insert_root(root->fs_info, root->node,
-				       new_root_node, GFP_NOFS, log_removal);
+				       new_root_node, log_removal);
 	BUG_ON(ret < 0);
 }
 
@@ -1074,7 +1072,7 @@ static noinline int update_ref_for_cow(struct btrfs_trans_handle *trans,
 			ret = btrfs_dec_ref(trans, root, buf, 1);
 			BUG_ON(ret); /* -ENOMEM */
 		}
-		clean_tree_block(trans, fs_info, buf);
+		clean_tree_block(fs_info, buf);
 		*last_ref = 1;
 	}
 	return 0;
@@ -1326,7 +1324,7 @@ __tree_mod_log_rewind(struct btrfs_fs_info *fs_info, struct extent_buffer *eb,
 		next = rb_next(&tm->node);
 		if (!next)
 			break;
-		tm = container_of(next, struct tree_mod_elem, node);
+		tm = rb_entry(next, struct tree_mod_elem, node);
 		if (tm->logical != first_tm->logical)
 			break;
 	}
@@ -1580,7 +1578,8 @@ static int close_blocks(u64 blocknr, u64 other, u32 blocksize)
 /*
  * compare two keys in a memcmp fashion
  */
-static int comp_keys(struct btrfs_disk_key *disk, struct btrfs_key *k2)
+static int comp_keys(const struct btrfs_disk_key *disk,
+		     const struct btrfs_key *k2)
 {
 	struct btrfs_key k1;
 
@@ -1592,7 +1591,7 @@ static int comp_keys(struct btrfs_disk_key *disk, struct btrfs_key *k2)
 /*
  * same as comp_keys only with two btrfs_key's
  */
-int btrfs_comp_cpu_keys(struct btrfs_key *k1, struct btrfs_key *k2)
+int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2)
 {
 	if (k1->objectid > k2->objectid)
 		return 1;
@@ -1732,8 +1731,8 @@ int btrfs_realloc_node(struct btrfs_trans_handle *trans,
  * slot may point to max if the key is bigger than all of the keys
  */
 static noinline int generic_bin_search(struct extent_buffer *eb,
-				       unsigned long p,
-				       int item_size, struct btrfs_key *key,
+				       unsigned long p, int item_size,
+				       const struct btrfs_key *key,
 				       int max, int *slot)
 {
 	int low = 0;
@@ -1802,7 +1801,7 @@ static noinline int generic_bin_search(struct extent_buffer *eb,
  * simple bin_search frontend that does the right thing for
  * leaves vs nodes
  */
-static int bin_search(struct extent_buffer *eb, struct btrfs_key *key,
+static int bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
 		      int level, int *slot)
 {
 	if (level == 0)
@@ -1819,7 +1818,7 @@ static int bin_search(struct extent_buffer *eb, struct btrfs_key *key,
 					  slot);
 }
 
-int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
+int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
 		     int level, int *slot)
 {
 	return bin_search(eb, key, level, slot);
@@ -1937,7 +1936,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 
 		path->locks[level] = 0;
 		path->nodes[level] = NULL;
-		clean_tree_block(trans, fs_info, mid);
+		clean_tree_block(fs_info, mid);
 		btrfs_tree_unlock(mid);
 		/* once for the path */
 		free_extent_buffer(mid);
@@ -1998,7 +1997,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		if (wret < 0 && wret != -ENOSPC)
 			ret = wret;
 		if (btrfs_header_nritems(right) == 0) {
-			clean_tree_block(trans, fs_info, right);
+			clean_tree_block(fs_info, right);
 			btrfs_tree_unlock(right);
 			del_ptr(root, path, level + 1, pslot + 1);
 			root_sub_used(root, right->len);
@@ -2042,7 +2041,7 @@ static noinline int balance_level(struct btrfs_trans_handle *trans,
 		BUG_ON(wret == 1);
 	}
 	if (btrfs_header_nritems(mid) == 0) {
-		clean_tree_block(trans, fs_info, mid);
+		clean_tree_block(fs_info, mid);
 		btrfs_tree_unlock(mid);
 		del_ptr(root, path, level + 1, pslot);
 		root_sub_used(root, mid->len);
@@ -2437,10 +2436,9 @@ noinline void btrfs_unlock_up_safe(struct btrfs_path *path, int level)
  * reada.  -EAGAIN is returned and the search must be repeated.
  */
 static int
-read_block_for_search(struct btrfs_trans_handle *trans,
-		       struct btrfs_root *root, struct btrfs_path *p,
-		       struct extent_buffer **eb_ret, int level, int slot,
-		       struct btrfs_key *key, u64 time_seq)
+read_block_for_search(struct btrfs_root *root, struct btrfs_path *p,
+		      struct extent_buffer **eb_ret, int level, int slot,
+		      const struct btrfs_key *key)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 blocknr;
@@ -2587,7 +2585,7 @@ done:
 }
 
 static void key_search_validate(struct extent_buffer *b,
-				struct btrfs_key *key,
+				const struct btrfs_key *key,
 				int level)
 {
 #ifdef CONFIG_BTRFS_ASSERT
@@ -2606,7 +2604,7 @@ static void key_search_validate(struct extent_buffer *b,
 #endif
 }
 
-static int key_search(struct extent_buffer *b, struct btrfs_key *key,
+static int key_search(struct extent_buffer *b, const struct btrfs_key *key,
 		      int level, int *prev_cmp, int *slot)
 {
 	if (*prev_cmp != 0) {
@@ -2668,9 +2666,9 @@ int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
  * tree.  if ins_len < 0, nodes will be merged as we walk down the tree (if
  * possible)
  */
-int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
-		      *root, struct btrfs_key *key, struct btrfs_path *p, int
-		      ins_len, int cow)
+int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		      const struct btrfs_key *key, struct btrfs_path *p,
+		      int ins_len, int cow)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_buffer *b;
@@ -2870,8 +2868,8 @@ cow_done:
 				goto done;
 			}
 
-			err = read_block_for_search(trans, root, p,
-						    &b, level, slot, key, 0);
+			err = read_block_for_search(root, p, &b, level,
+						    slot, key);
 			if (err == -EAGAIN)
 				goto again;
 			if (err) {
@@ -2953,7 +2951,7 @@ done:
  * The resulting path and return value will be set up as if we called
  * btrfs_search_slot at that point in time with ins_len and cow both set to 0.
  */
-int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key,
+int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key,
 			  struct btrfs_path *p, u64 time_seq)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -3014,8 +3012,8 @@ again:
 				goto done;
 			}
 
-			err = read_block_for_search(NULL, root, p, &b, level,
-						    slot, key, time_seq);
+			err = read_block_for_search(root, p, &b, level,
+						    slot, key);
 			if (err == -EAGAIN)
 				goto again;
 			if (err) {
@@ -3067,8 +3065,9 @@ done:
  * < 0 on error
  */
 int btrfs_search_slot_for_read(struct btrfs_root *root,
-			       struct btrfs_key *key, struct btrfs_path *p,
-			       int find_higher, int return_any)
+			       const struct btrfs_key *key,
+			       struct btrfs_path *p, int find_higher,
+			       int return_any)
 {
 	int ret;
 	struct extent_buffer *leaf;
@@ -3166,7 +3165,7 @@ static void fixup_low_keys(struct btrfs_fs_info *fs_info,
  */
 void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
 			     struct btrfs_path *path,
-			     struct btrfs_key *new_key)
+			     const struct btrfs_key *new_key)
 {
 	struct btrfs_disk_key disk_key;
 	struct extent_buffer *eb;
@@ -3594,8 +3593,7 @@ noinline int btrfs_leaf_free_space(struct btrfs_fs_info *fs_info,
  * min slot controls the lowest index we're willing to push to the
  * right.  We'll push up to and including min_slot, but no lower
  */
-static noinline int __push_leaf_right(struct btrfs_trans_handle *trans,
-				      struct btrfs_fs_info *fs_info,
+static noinline int __push_leaf_right(struct btrfs_fs_info *fs_info,
 				      struct btrfs_path *path,
 				      int data_size, int empty,
 				      struct extent_buffer *right,
@@ -3669,14 +3667,14 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans,
 	/* make room in the right data area */
 	data_end = leaf_data_end(fs_info, right);
 	memmove_extent_buffer(right,
-			      btrfs_leaf_data(right) + data_end - push_space,
-			      btrfs_leaf_data(right) + data_end,
+			      BTRFS_LEAF_DATA_OFFSET + data_end - push_space,
+			      BTRFS_LEAF_DATA_OFFSET + data_end,
 			      BTRFS_LEAF_DATA_SIZE(fs_info) - data_end);
 
 	/* copy from the left data area */
-	copy_extent_buffer(right, left, btrfs_leaf_data(right) +
+	copy_extent_buffer(right, left, BTRFS_LEAF_DATA_OFFSET +
 		     BTRFS_LEAF_DATA_SIZE(fs_info) - push_space,
-		     btrfs_leaf_data(left) + leaf_data_end(fs_info, left),
+		     BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, left),
 		     push_space);
 
 	memmove_extent_buffer(right, btrfs_item_nr_offset(push_items),
@@ -3704,7 +3702,7 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans,
 	if (left_nritems)
 		btrfs_mark_buffer_dirty(left);
 	else
-		clean_tree_block(trans, fs_info, left);
+		clean_tree_block(fs_info, left);
 
 	btrfs_mark_buffer_dirty(right);
 
@@ -3716,7 +3714,7 @@ static noinline int __push_leaf_right(struct btrfs_trans_handle *trans,
 	if (path->slots[0] >= left_nritems) {
 		path->slots[0] -= left_nritems;
 		if (btrfs_header_nritems(path->nodes[0]) == 0)
-			clean_tree_block(trans, fs_info, path->nodes[0]);
+			clean_tree_block(fs_info, path->nodes[0]);
 		btrfs_tree_unlock(path->nodes[0]);
 		free_extent_buffer(path->nodes[0]);
 		path->nodes[0] = right;
@@ -3809,7 +3807,7 @@ static int push_leaf_right(struct btrfs_trans_handle *trans, struct btrfs_root
 		return 0;
 	}
 
-	return __push_leaf_right(trans, fs_info, path, min_data_size, empty,
+	return __push_leaf_right(fs_info, path, min_data_size, empty,
 				right, free_space, left_nritems, min_slot);
 out_unlock:
 	btrfs_tree_unlock(right);
@@ -3825,8 +3823,7 @@ out_unlock:
  * item at 'max_slot' won't be touched.  Use (u32)-1 to make us do all the
  * items
  */
-static noinline int __push_leaf_left(struct btrfs_trans_handle *trans,
-				     struct btrfs_fs_info *fs_info,
+static noinline int __push_leaf_left(struct btrfs_fs_info *fs_info,
 				     struct btrfs_path *path, int data_size,
 				     int empty, struct extent_buffer *left,
 				     int free_space, u32 right_nritems,
@@ -3891,9 +3888,9 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans,
 	push_space = BTRFS_LEAF_DATA_SIZE(fs_info) -
 		     btrfs_item_offset_nr(right, push_items - 1);
 
-	copy_extent_buffer(left, right, btrfs_leaf_data(left) +
+	copy_extent_buffer(left, right, BTRFS_LEAF_DATA_OFFSET +
 		     leaf_data_end(fs_info, left) - push_space,
-		     btrfs_leaf_data(right) +
+		     BTRFS_LEAF_DATA_OFFSET +
 		     btrfs_item_offset_nr(right, push_items - 1),
 		     push_space);
 	old_left_nritems = btrfs_header_nritems(left);
@@ -3920,9 +3917,9 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans,
 	if (push_items < right_nritems) {
 		push_space = btrfs_item_offset_nr(right, push_items - 1) -
 						  leaf_data_end(fs_info, right);
-		memmove_extent_buffer(right, btrfs_leaf_data(right) +
+		memmove_extent_buffer(right, BTRFS_LEAF_DATA_OFFSET +
 				      BTRFS_LEAF_DATA_SIZE(fs_info) - push_space,
-				      btrfs_leaf_data(right) +
+				      BTRFS_LEAF_DATA_OFFSET +
 				      leaf_data_end(fs_info, right), push_space);
 
 		memmove_extent_buffer(right, btrfs_item_nr_offset(0),
@@ -3945,7 +3942,7 @@ static noinline int __push_leaf_left(struct btrfs_trans_handle *trans,
 	if (right_nritems)
 		btrfs_mark_buffer_dirty(right);
 	else
-		clean_tree_block(trans, fs_info, right);
+		clean_tree_block(fs_info, right);
 
 	btrfs_item_key(right, &disk_key, 0);
 	fixup_low_keys(fs_info, path, &disk_key, 1);
@@ -4035,7 +4032,7 @@ static int push_leaf_left(struct btrfs_trans_handle *trans, struct btrfs_root
 		goto out;
 	}
 
-	return __push_leaf_left(trans, fs_info, path, min_data_size,
+	return __push_leaf_left(fs_info, path, min_data_size,
 			       empty, left, free_space, right_nritems,
 			       max_slot);
 out:
@@ -4072,8 +4069,8 @@ static noinline void copy_for_split(struct btrfs_trans_handle *trans,
 			   nritems * sizeof(struct btrfs_item));
 
 	copy_extent_buffer(right, l,
-		     btrfs_leaf_data(right) + BTRFS_LEAF_DATA_SIZE(fs_info) -
-		     data_copy_size, btrfs_leaf_data(l) +
+		     BTRFS_LEAF_DATA_OFFSET + BTRFS_LEAF_DATA_SIZE(fs_info) -
+		     data_copy_size, BTRFS_LEAF_DATA_OFFSET +
 		     leaf_data_end(fs_info, l), data_copy_size);
 
 	rt_data_off = BTRFS_LEAF_DATA_SIZE(fs_info) - btrfs_item_end_nr(l, mid);
@@ -4160,6 +4157,9 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans,
 
 	/* try to push all the items before our slot into the next leaf */
 	slot = path->slots[0];
+	space_needed = data_size;
+	if (slot > 0)
+		space_needed -= btrfs_leaf_free_space(fs_info, path->nodes[0]);
 	ret = push_leaf_left(trans, root, path, 1, space_needed, 0, slot);
 	if (ret < 0)
 		return ret;
@@ -4180,7 +4180,7 @@ static noinline int push_for_double_split(struct btrfs_trans_handle *trans,
  */
 static noinline int split_leaf(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root,
-			       struct btrfs_key *ins_key,
+			       const struct btrfs_key *ins_key,
 			       struct btrfs_path *path, int data_size,
 			       int extend)
 {
@@ -4215,6 +4215,10 @@ static noinline int split_leaf(struct btrfs_trans_handle *trans,
 		if (wret < 0)
 			return wret;
 		if (wret) {
+			space_needed = data_size;
+			if (slot > 0)
+				space_needed -= btrfs_leaf_free_space(fs_info,
+								      l);
 			wret = push_leaf_left(trans, root, path, space_needed,
 					      space_needed, 0, (u32)-1);
 			if (wret < 0)
@@ -4412,10 +4416,9 @@ err:
 	return ret;
 }
 
-static noinline int split_item(struct btrfs_trans_handle *trans,
-			       struct btrfs_fs_info *fs_info,
+static noinline int split_item(struct btrfs_fs_info *fs_info,
 			       struct btrfs_path *path,
-			       struct btrfs_key *new_key,
+			       const struct btrfs_key *new_key,
 			       unsigned long split_offset)
 {
 	struct extent_buffer *leaf;
@@ -4501,7 +4504,7 @@ static noinline int split_item(struct btrfs_trans_handle *trans,
 int btrfs_split_item(struct btrfs_trans_handle *trans,
 		     struct btrfs_root *root,
 		     struct btrfs_path *path,
-		     struct btrfs_key *new_key,
+		     const struct btrfs_key *new_key,
 		     unsigned long split_offset)
 {
 	int ret;
@@ -4510,7 +4513,7 @@ int btrfs_split_item(struct btrfs_trans_handle *trans,
 	if (ret)
 		return ret;
 
-	ret = split_item(trans, root->fs_info, path, new_key, split_offset);
+	ret = split_item(root->fs_info, path, new_key, split_offset);
 	return ret;
 }
 
@@ -4525,7 +4528,7 @@ int btrfs_split_item(struct btrfs_trans_handle *trans,
 int btrfs_duplicate_item(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root,
 			 struct btrfs_path *path,
-			 struct btrfs_key *new_key)
+			 const struct btrfs_key *new_key)
 {
 	struct extent_buffer *leaf;
 	int ret;
@@ -4604,8 +4607,8 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info,
 
 	/* shift the data */
 	if (from_end) {
-		memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) +
-			      data_end + size_diff, btrfs_leaf_data(leaf) +
+		memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET +
+			      data_end + size_diff, BTRFS_LEAF_DATA_OFFSET +
 			      data_end, old_data_start + new_size - data_end);
 	} else {
 		struct btrfs_disk_key disk_key;
@@ -4631,8 +4634,8 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info,
 			}
 		}
 
-		memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) +
-			      data_end + size_diff, btrfs_leaf_data(leaf) +
+		memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET +
+			      data_end + size_diff, BTRFS_LEAF_DATA_OFFSET +
 			      data_end, old_data_start - data_end);
 
 		offset = btrfs_disk_key_offset(&disk_key);
@@ -4704,8 +4707,8 @@ void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
 	}
 
 	/* shift the data */
-	memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) +
-		      data_end - data_size, btrfs_leaf_data(leaf) +
+	memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET +
+		      data_end - data_size, BTRFS_LEAF_DATA_OFFSET +
 		      data_end, old_data - data_end);
 
 	data_end = old_data;
@@ -4726,7 +4729,7 @@ void btrfs_extend_item(struct btrfs_fs_info *fs_info, struct btrfs_path *path,
  * that doesn't call btrfs_search_slot
  */
 void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
-			    struct btrfs_key *cpu_key, u32 *data_size,
+			    const struct btrfs_key *cpu_key, u32 *data_size,
 			    u32 total_data, u32 total_size, int nr)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -4787,8 +4790,8 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
 			      (nritems - slot) * sizeof(struct btrfs_item));
 
 		/* shift the data */
-		memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) +
-			      data_end - total_data, btrfs_leaf_data(leaf) +
+		memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET +
+			      data_end - total_data, BTRFS_LEAF_DATA_OFFSET +
 			      data_end, old_data - data_end);
 		data_end = old_data;
 	}
@@ -4820,7 +4823,7 @@ void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
 int btrfs_insert_empty_items(struct btrfs_trans_handle *trans,
 			    struct btrfs_root *root,
 			    struct btrfs_path *path,
-			    struct btrfs_key *cpu_key, u32 *data_size,
+			    const struct btrfs_key *cpu_key, u32 *data_size,
 			    int nr)
 {
 	int ret = 0;
@@ -4851,9 +4854,9 @@ int btrfs_insert_empty_items(struct btrfs_trans_handle *trans,
  * Given a key and some data, insert an item into the tree.
  * This does all the path init required, making room in the tree if needed.
  */
-int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root
-		      *root, struct btrfs_key *cpu_key, void *data, u32
-		      data_size)
+int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		      const struct btrfs_key *cpu_key, void *data,
+		      u32 data_size)
 {
 	int ret = 0;
 	struct btrfs_path *path;
@@ -4980,9 +4983,9 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	if (slot + nr != nritems) {
 		int data_end = leaf_data_end(fs_info, leaf);
 
-		memmove_extent_buffer(leaf, btrfs_leaf_data(leaf) +
+		memmove_extent_buffer(leaf, BTRFS_LEAF_DATA_OFFSET +
 			      data_end + dsize,
-			      btrfs_leaf_data(leaf) + data_end,
+			      BTRFS_LEAF_DATA_OFFSET + data_end,
 			      last_off - data_end);
 
 		for (i = slot + nr; i < nritems; i++) {
@@ -5008,7 +5011,7 @@ int btrfs_del_items(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 			btrfs_set_header_level(leaf, 0);
 		} else {
 			btrfs_set_path_blocking(path);
-			clean_tree_block(trans, fs_info, leaf);
+			clean_tree_block(fs_info, leaf);
 			btrfs_del_leaf(trans, root, path, leaf);
 		}
 	} else {
@@ -5243,7 +5246,7 @@ out:
 
 static int tree_move_down(struct btrfs_fs_info *fs_info,
 			   struct btrfs_path *path,
-			   int *level, int root_level)
+			   int *level)
 {
 	struct extent_buffer *eb;
 
@@ -5258,8 +5261,7 @@ static int tree_move_down(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-static int tree_move_next_or_upnext(struct btrfs_fs_info *fs_info,
-				    struct btrfs_path *path,
+static int tree_move_next_or_upnext(struct btrfs_path *path,
 				    int *level, int root_level)
 {
 	int ret = 0;
@@ -5298,10 +5300,9 @@ static int tree_advance(struct btrfs_fs_info *fs_info,
 	int ret;
 
 	if (*level == 0 || !allow_down) {
-		ret = tree_move_next_or_upnext(fs_info, path, level,
-					       root_level);
+		ret = tree_move_next_or_upnext(path, level, root_level);
 	} else {
-		ret = tree_move_down(fs_info, path, level, root_level);
+		ret = tree_move_down(fs_info, path, level);
 	}
 	if (ret >= 0) {
 		if (*level == 0)
@@ -5391,13 +5392,10 @@ int btrfs_compare_trees(struct btrfs_root *left_root,
 		goto out;
 	}
 
-	tmp_buf = kmalloc(fs_info->nodesize, GFP_KERNEL | __GFP_NOWARN);
+	tmp_buf = kvmalloc(fs_info->nodesize, GFP_KERNEL);
 	if (!tmp_buf) {
-		tmp_buf = vmalloc(fs_info->nodesize);
-		if (!tmp_buf) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		ret = -ENOMEM;
+		goto out;
 	}
 
 	left_path->search_commit_root = 1;
@@ -5784,8 +5782,8 @@ again:
 
 		next = c;
 		next_rw_lock = path->locks[level];
-		ret = read_block_for_search(NULL, root, path, &next, level,
-					    slot, &key, 0);
+		ret = read_block_for_search(root, path, &next, level,
+					    slot, &key);
 		if (ret == -EAGAIN)
 			goto again;
 
@@ -5834,8 +5832,8 @@ again:
 		if (!level)
 			break;
 
-		ret = read_block_for_search(NULL, root, path, &next, level,
-					    0, &key, 0);
+		ret = read_block_for_search(root, path, &next, level,
+					    0, &key);
 		if (ret == -EAGAIN)
 			goto again;
 
diff --git a/fs/btrfs/ctree.h b/fs/btrfs/ctree.h
index 6a823719b6c5..3f3eb7b17cac 100644
--- a/fs/btrfs/ctree.h
+++ b/fs/btrfs/ctree.h
@@ -20,6 +20,7 @@
 #define __BTRFS_CTREE__
 
 #include <linux/mm.h>
+#include <linux/sched/signal.h>
 #include <linux/highmem.h>
 #include <linux/fs.h>
 #include <linux/rwsem.h>
@@ -38,6 +39,7 @@
 #include <linux/security.h>
 #include <linux/sizes.h>
 #include <linux/dynamic_debug.h>
+#include <linux/refcount.h>
 #include "extent_io.h"
 #include "extent_map.h"
 #include "async-thread.h"
@@ -46,7 +48,6 @@ struct btrfs_trans_handle;
 struct btrfs_transaction;
 struct btrfs_pending_snapshot;
 extern struct kmem_cache *btrfs_trans_handle_cachep;
-extern struct kmem_cache *btrfs_transaction_cachep;
 extern struct kmem_cache *btrfs_bit_radix_cachep;
 extern struct kmem_cache *btrfs_path_cachep;
 extern struct kmem_cache *btrfs_free_space_cachep;
@@ -97,6 +98,14 @@ static const int btrfs_csum_sizes[] = { 4 };
 
 #define BTRFS_MAX_EXTENT_SIZE SZ_128M
 
+/*
+ * Count how many BTRFS_MAX_EXTENT_SIZE cover the @size
+ */
+static inline u32 count_max_extents(u64 size)
+{
+	return div_u64(size + BTRFS_MAX_EXTENT_SIZE - 1, BTRFS_MAX_EXTENT_SIZE);
+}
+
 struct btrfs_mapping_tree {
 	struct extent_map_tree map_tree;
 };
@@ -509,7 +518,7 @@ struct btrfs_caching_control {
 	struct btrfs_work work;
 	struct btrfs_block_group_cache *block_group;
 	u64 progress;
-	atomic_t count;
+	refcount_t count;
 };
 
 /* Once caching_thread() finds this much free space, it will wake up waiters. */
@@ -529,6 +538,14 @@ struct btrfs_io_ctl {
 	unsigned check_crcs:1;
 };
 
+/*
+ * Tree to record all locked full stripes of a RAID5/6 block group
+ */
+struct btrfs_full_stripe_locks_tree {
+	struct rb_root root;
+	struct mutex lock;
+};
+
 struct btrfs_block_group_cache {
 	struct btrfs_key key;
 	struct btrfs_block_group_item item;
@@ -639,6 +656,9 @@ struct btrfs_block_group_cache {
 	 * Protected by free_space_lock.
 	 */
 	int needs_free_space;
+
+	/* Record locked full stripes for RAID5/6 block group */
+	struct btrfs_full_stripe_locks_tree full_stripe_locks_root;
 };
 
 /* delayed seq elem */
@@ -649,6 +669,8 @@ struct seq_list {
 
 #define SEQ_LIST_INIT(name)	{ .list = LIST_HEAD_INIT((name).list), .seq = 0 }
 
+#define SEQ_LAST	((u64)-1)
+
 enum btrfs_orphan_cleanup_state {
 	ORPHAN_CLEANUP_STARTED	= 1,
 	ORPHAN_CLEANUP_DONE	= 2,
@@ -693,6 +715,15 @@ struct btrfs_delayed_root;
 #define BTRFS_FS_BTREE_ERR			11
 #define BTRFS_FS_LOG1_ERR			12
 #define BTRFS_FS_LOG2_ERR			13
+#define BTRFS_FS_QUOTA_OVERRIDE			14
+/* Used to record internally whether fs has been frozen */
+#define BTRFS_FS_FROZEN				15
+
+/*
+ * Indicate that a whole-filesystem exclusive operation is running
+ * (device replace, resize, device add/delete, balance)
+ */
+#define BTRFS_FS_EXCL_OP			14
 
 struct btrfs_fs_info {
 	u8 fsid[BTRFS_FSID_SIZE];
@@ -720,8 +751,7 @@ struct btrfs_fs_info {
 	struct rb_root block_group_cache_tree;
 
 	/* keep track of unallocated space */
-	spinlock_t free_chunk_lock;
-	u64 free_chunk_space;
+	atomic64_t free_chunk_space;
 
 	struct extent_io_tree freed_extents[2];
 	struct extent_io_tree *pinned_extents;
@@ -769,17 +799,7 @@ struct btrfs_fs_info {
 	 * so it is also safe.
 	 */
 	u64 max_inline;
-	/*
-	 * Protected by ->chunk_mutex and sb->s_umount.
-	 *
-	 * The reason that we use two lock to protect it is because only
-	 * remount and mount operations can change it and these two operations
-	 * are under sb->s_umount, but the read side (chunk allocation) can not
-	 * acquire sb->s_umount or the deadlock would happen. So we use two
-	 * locks to protect it. On the write side, we must acquire two locks,
-	 * and on the read side, we just need acquire one of them.
-	 */
-	u64 alloc_start;
+
 	struct btrfs_transaction *running_transaction;
 	wait_queue_head_t transaction_throttle;
 	wait_queue_head_t transaction_wait;
@@ -801,7 +821,6 @@ struct btrfs_fs_info {
 	struct btrfs_super_block *super_for_commit;
 	struct super_block *sb;
 	struct inode *btree_inode;
-	struct backing_dev_info bdi;
 	struct mutex tree_log_mutex;
 	struct mutex transaction_kthread_mutex;
 	struct mutex cleaner_mutex;
@@ -1058,8 +1077,6 @@ struct btrfs_fs_info {
 	/* device replace state */
 	struct btrfs_dev_replace dev_replace;
 
-	atomic_t mutually_exclusive_operation_running;
-
 	struct percpu_counter bio_counter;
 	wait_queue_head_t replace_wait;
 
@@ -1082,9 +1099,6 @@ struct btrfs_fs_info {
 	 */
 	struct list_head pinned_chunks;
 
-	/* Used to record internally whether fs has been frozen */
-	int fs_frozen;
-
 	/* Cached block sizes */
 	u32 nodesize;
 	u32 sectorsize;
@@ -1212,7 +1226,7 @@ struct btrfs_root {
 	dev_t anon_dev;
 
 	spinlock_t root_item_lock;
-	atomic_t refs;
+	refcount_t refs;
 
 	struct mutex delalloc_mutex;
 	spinlock_t delalloc_lock;
@@ -1250,23 +1264,22 @@ struct btrfs_root {
 	atomic_t will_be_snapshoted;
 
 	/* For qgroup metadata space reserve */
-	atomic_t qgroup_meta_rsv;
+	atomic64_t qgroup_meta_rsv;
 };
+
 static inline u32 btrfs_inode_sectorsize(const struct inode *inode)
 {
 	return btrfs_sb(inode->i_sb)->sectorsize;
 }
 
-static inline u32 __BTRFS_LEAF_DATA_SIZE(u32 blocksize)
-{
-	return blocksize - sizeof(struct btrfs_header);
-}
-
 static inline u32 BTRFS_LEAF_DATA_SIZE(const struct btrfs_fs_info *info)
 {
-	return __BTRFS_LEAF_DATA_SIZE(info->nodesize);
+
+	return info->nodesize - sizeof(struct btrfs_header);
 }
 
+#define BTRFS_LEAF_DATA_OFFSET		offsetof(struct btrfs_leaf, items)
+
 static inline u32 BTRFS_MAX_ITEM_SIZE(const struct btrfs_fs_info *info)
 {
 	return BTRFS_LEAF_DATA_SIZE(info) - sizeof(struct btrfs_item);
@@ -1528,8 +1541,27 @@ static inline void btrfs_set_##name(type *s, u##bits val)		\
 	s->member = cpu_to_le##bits(val);				\
 }
 
+
+static inline u64 btrfs_device_total_bytes(struct extent_buffer *eb,
+					   struct btrfs_dev_item *s)
+{
+	BUILD_BUG_ON(sizeof(u64) !=
+		     sizeof(((struct btrfs_dev_item *)0))->total_bytes);
+	return btrfs_get_64(eb, s, offsetof(struct btrfs_dev_item,
+					    total_bytes));
+}
+static inline void btrfs_set_device_total_bytes(struct extent_buffer *eb,
+						struct btrfs_dev_item *s,
+						u64 val)
+{
+	BUILD_BUG_ON(sizeof(u64) !=
+		     sizeof(((struct btrfs_dev_item *)0))->total_bytes);
+	WARN_ON(!IS_ALIGNED(val, eb->fs_info->sectorsize));
+	btrfs_set_64(eb, s, offsetof(struct btrfs_dev_item, total_bytes), val);
+}
+
+
 BTRFS_SETGET_FUNCS(device_type, struct btrfs_dev_item, type, 64);
-BTRFS_SETGET_FUNCS(device_total_bytes, struct btrfs_dev_item, total_bytes, 64);
 BTRFS_SETGET_FUNCS(device_bytes_used, struct btrfs_dev_item, bytes_used, 64);
 BTRFS_SETGET_FUNCS(device_io_align, struct btrfs_dev_item, io_align, 32);
 BTRFS_SETGET_FUNCS(device_io_width, struct btrfs_dev_item, io_width, 32);
@@ -1953,7 +1985,7 @@ BTRFS_SETGET_STACK_FUNCS(disk_key_offset, struct btrfs_disk_key, offset, 64);
 BTRFS_SETGET_STACK_FUNCS(disk_key_type, struct btrfs_disk_key, type, 8);
 
 static inline void btrfs_disk_key_to_cpu(struct btrfs_key *cpu,
-					 struct btrfs_disk_key *disk)
+					 const struct btrfs_disk_key *disk)
 {
 	cpu->offset = le64_to_cpu(disk->offset);
 	cpu->type = disk->type;
@@ -1961,7 +1993,7 @@ static inline void btrfs_disk_key_to_cpu(struct btrfs_key *cpu,
 }
 
 static inline void btrfs_cpu_key_to_disk(struct btrfs_disk_key *disk,
-					 struct btrfs_key *cpu)
+					 const struct btrfs_key *cpu)
 {
 	disk->offset = cpu_to_le64(cpu->offset);
 	disk->type = cpu->type;
@@ -1993,8 +2025,7 @@ static inline void btrfs_dir_item_key_to_cpu(struct extent_buffer *eb,
 	btrfs_disk_key_to_cpu(key, &disk_key);
 }
 
-
-static inline u8 btrfs_key_type(struct btrfs_key *key)
+static inline u8 btrfs_key_type(const struct btrfs_key *key)
 {
 	return key->type;
 }
@@ -2300,10 +2331,6 @@ static inline int btrfs_super_csum_size(struct btrfs_super_block *s)
 	return btrfs_csum_sizes[t];
 }
 
-static inline unsigned long btrfs_leaf_data(struct extent_buffer *l)
-{
-	return offsetof(struct btrfs_leaf, items);
-}
 
 /*
  * The leaf data grows from end-to-front in the node.
@@ -2514,11 +2541,11 @@ BTRFS_SETGET_STACK_FUNCS(stack_dev_replace_cursor_right,
 
 /* helper function to cast into the data area of the leaf. */
 #define btrfs_item_ptr(leaf, slot, type) \
-	((type *)(btrfs_leaf_data(leaf) + \
+	((type *)(BTRFS_LEAF_DATA_OFFSET + \
 	btrfs_item_offset_nr(leaf, slot)))
 
 #define btrfs_item_ptr_offset(leaf, slot) \
-	((unsigned long)(btrfs_leaf_data(leaf) + \
+	((unsigned long)(BTRFS_LEAF_DATA_OFFSET + \
 	btrfs_item_offset_nr(leaf, slot)))
 
 static inline bool btrfs_mixed_space_info(struct btrfs_space_info *space_info)
@@ -2539,7 +2566,7 @@ u64 btrfs_csum_bytes_to_leaves(struct btrfs_fs_info *fs_info, u64 csum_bytes);
 static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info,
 						 unsigned num_items)
 {
-	return fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
+	return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * 2 * num_items;
 }
 
 /*
@@ -2549,7 +2576,7 @@ static inline u64 btrfs_calc_trans_metadata_size(struct btrfs_fs_info *fs_info,
 static inline u64 btrfs_calc_trunc_metadata_size(struct btrfs_fs_info *fs_info,
 						 unsigned num_items)
 {
-	return fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
+	return (u64)fs_info->nodesize * BTRFS_MAX_LEVEL * num_items;
 }
 
 int btrfs_should_throttle_delayed_refs(struct btrfs_trans_handle *trans,
@@ -2577,8 +2604,7 @@ int btrfs_pin_extent_for_log_replay(struct btrfs_fs_info *fs_info,
 				    u64 bytenr, u64 num_bytes);
 int btrfs_exclude_logged_extents(struct btrfs_fs_info *fs_info,
 				 struct extent_buffer *eb);
-int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
-			  struct btrfs_root *root,
+int btrfs_cross_ref_exist(struct btrfs_root *root,
 			  u64 objectid, u64 offset, u64 bytenr);
 struct btrfs_block_group_cache *btrfs_lookup_block_group(
 						 struct btrfs_fs_info *info,
@@ -2587,10 +2613,11 @@ void btrfs_get_block_group(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group(struct btrfs_block_group_cache *cache);
 int get_block_group_index(struct btrfs_block_group_cache *cache);
 struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
-					struct btrfs_root *root, u64 parent,
-					u64 root_objectid,
-					struct btrfs_disk_key *key, int level,
-					u64 hint, u64 empty_size);
+					     struct btrfs_root *root,
+					     u64 parent, u64 root_objectid,
+					     const struct btrfs_disk_key *key,
+					     int level, u64 hint,
+					     u64 empty_size);
 void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct extent_buffer *buf,
@@ -2623,8 +2650,7 @@ int btrfs_free_reserved_extent(struct btrfs_fs_info *fs_info,
 			       u64 start, u64 len, int delalloc);
 int btrfs_free_and_pin_reserved_extent(struct btrfs_fs_info *fs_info,
 				       u64 start, u64 len);
-void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
-				 struct btrfs_fs_info *fs_info);
+void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info);
 int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 			       struct btrfs_fs_info *fs_info);
 int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
@@ -2657,7 +2683,9 @@ void btrfs_get_block_group_trimming(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_trimming(struct btrfs_block_group_cache *cache);
 void btrfs_create_pending_block_groups(struct btrfs_trans_handle *trans,
 				       struct btrfs_fs_info *fs_info);
-u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data);
+u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info);
+u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info);
+u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info);
 void btrfs_clear_space_info_full(struct btrfs_fs_info *info);
 
 enum btrfs_reserve_flush_enum {
@@ -2680,28 +2708,31 @@ enum btrfs_flush_state {
 	COMMIT_TRANS		=	6,
 };
 
-int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len);
-int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes);
-void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len);
+int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes);
+int btrfs_check_data_free_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len);
+void btrfs_free_reserved_data_space(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len);
+void btrfs_delalloc_release_space(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len);
 void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
 					    u64 len);
 void btrfs_trans_release_metadata(struct btrfs_trans_handle *trans,
 				  struct btrfs_fs_info *fs_info);
 void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans);
 int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
-				  struct inode *inode);
-void btrfs_orphan_release_metadata(struct inode *inode);
+				  struct btrfs_inode *inode);
+void btrfs_orphan_release_metadata(struct btrfs_inode *inode);
 int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 				     struct btrfs_block_rsv *rsv,
 				     int nitems,
 				     u64 *qgroup_reserved, bool use_global_rsv);
 void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
-				      struct btrfs_block_rsv *rsv,
-				      u64 qgroup_reserved);
-int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes);
-void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes);
-int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len);
-void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len);
+				      struct btrfs_block_rsv *rsv);
+int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes);
+void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes);
+int btrfs_delalloc_reserve_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len);
 void btrfs_init_block_rsv(struct btrfs_block_rsv *rsv, unsigned short type);
 struct btrfs_block_rsv *btrfs_alloc_block_rsv(struct btrfs_fs_info *fs_info,
 					      unsigned short type);
@@ -2724,7 +2755,7 @@ int btrfs_cond_migrate_bytes(struct btrfs_fs_info *fs_info,
 void btrfs_block_rsv_release(struct btrfs_fs_info *fs_info,
 			     struct btrfs_block_rsv *block_rsv,
 			     u64 num_bytes);
-int btrfs_inc_block_group_ro(struct btrfs_root *root,
+int btrfs_inc_block_group_ro(struct btrfs_fs_info *fs_info,
 			     struct btrfs_block_group_cache *cache);
 void btrfs_dec_block_group_ro(struct btrfs_block_group_cache *cache);
 void btrfs_put_block_group_cache(struct btrfs_fs_info *info);
@@ -2750,9 +2781,9 @@ u64 add_new_free_space(struct btrfs_block_group_cache *block_group,
 		       struct btrfs_fs_info *info, u64 start, u64 end);
 
 /* ctree.c */
-int btrfs_bin_search(struct extent_buffer *eb, struct btrfs_key *key,
+int btrfs_bin_search(struct extent_buffer *eb, const struct btrfs_key *key,
 		     int level, int *slot);
-int btrfs_comp_cpu_keys(struct btrfs_key *k1, struct btrfs_key *k2);
+int btrfs_comp_cpu_keys(const struct btrfs_key *k1, const struct btrfs_key *k2);
 int btrfs_previous_item(struct btrfs_root *root,
 			struct btrfs_path *path, u64 min_objectid,
 			int type);
@@ -2760,7 +2791,7 @@ int btrfs_previous_extent_item(struct btrfs_root *root,
 			struct btrfs_path *path, u64 min_objectid);
 void btrfs_set_item_key_safe(struct btrfs_fs_info *fs_info,
 			     struct btrfs_path *path,
-			     struct btrfs_key *new_key);
+			     const struct btrfs_key *new_key);
 struct extent_buffer *btrfs_root_node(struct btrfs_root *root);
 struct extent_buffer *btrfs_lock_root_node(struct btrfs_root *root);
 int btrfs_find_next_key(struct btrfs_root *root, struct btrfs_path *path,
@@ -2802,22 +2833,23 @@ void btrfs_truncate_item(struct btrfs_fs_info *fs_info,
 int btrfs_split_item(struct btrfs_trans_handle *trans,
 		     struct btrfs_root *root,
 		     struct btrfs_path *path,
-		     struct btrfs_key *new_key,
+		     const struct btrfs_key *new_key,
 		     unsigned long split_offset);
 int btrfs_duplicate_item(struct btrfs_trans_handle *trans,
 			 struct btrfs_root *root,
 			 struct btrfs_path *path,
-			 struct btrfs_key *new_key);
+			 const struct btrfs_key *new_key);
 int btrfs_find_item(struct btrfs_root *fs_root, struct btrfs_path *path,
 		u64 inum, u64 ioff, u8 key_type, struct btrfs_key *found_key);
-int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root
-		      *root, struct btrfs_key *key, struct btrfs_path *p, int
-		      ins_len, int cow);
-int btrfs_search_old_slot(struct btrfs_root *root, struct btrfs_key *key,
+int btrfs_search_slot(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		      const struct btrfs_key *key, struct btrfs_path *p,
+		      int ins_len, int cow);
+int btrfs_search_old_slot(struct btrfs_root *root, const struct btrfs_key *key,
 			  struct btrfs_path *p, u64 time_seq);
 int btrfs_search_slot_for_read(struct btrfs_root *root,
-			       struct btrfs_key *key, struct btrfs_path *p,
-			       int find_higher, int return_any);
+			       const struct btrfs_key *key,
+			       struct btrfs_path *p, int find_higher,
+			       int return_any);
 int btrfs_realloc_node(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root, struct extent_buffer *parent,
 		       int start_slot, u64 *last_ret,
@@ -2840,19 +2872,20 @@ static inline int btrfs_del_item(struct btrfs_trans_handle *trans,
 }
 
 void setup_items_for_insert(struct btrfs_root *root, struct btrfs_path *path,
-			    struct btrfs_key *cpu_key, u32 *data_size,
+			    const struct btrfs_key *cpu_key, u32 *data_size,
 			    u32 total_data, u32 total_size, int nr);
-int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root
-		      *root, struct btrfs_key *key, void *data, u32 data_size);
+int btrfs_insert_item(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		      const struct btrfs_key *key, void *data, u32 data_size);
 int btrfs_insert_empty_items(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root,
 			     struct btrfs_path *path,
-			     struct btrfs_key *cpu_key, u32 *data_size, int nr);
+			     const struct btrfs_key *cpu_key, u32 *data_size,
+			     int nr);
 
 static inline int btrfs_insert_empty_item(struct btrfs_trans_handle *trans,
 					  struct btrfs_root *root,
 					  struct btrfs_path *path,
-					  struct btrfs_key *key,
+					  const struct btrfs_key *key,
 					  u32 data_size)
 {
 	return btrfs_insert_empty_items(trans, root, path, key, &data_size, 1);
@@ -2941,15 +2974,15 @@ int btrfs_del_root_ref(struct btrfs_trans_handle *trans,
 		       u64 root_id, u64 ref_id, u64 dirid, u64 *sequence,
 		       const char *name, int name_len);
 int btrfs_del_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		   struct btrfs_key *key);
-int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root
-		      *root, struct btrfs_key *key, struct btrfs_root_item
-		      *item);
+		   const struct btrfs_key *key);
+int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
+		      const struct btrfs_key *key,
+		      struct btrfs_root_item *item);
 int __must_check btrfs_update_root(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root,
 				   struct btrfs_key *key,
 				   struct btrfs_root_item *item);
-int btrfs_find_root(struct btrfs_root *root, struct btrfs_key *search_key,
+int btrfs_find_root(struct btrfs_root *root, const struct btrfs_key *search_key,
 		    struct btrfs_path *path, struct btrfs_root_item *root_item,
 		    struct btrfs_key *root_key);
 int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info);
@@ -2975,7 +3008,7 @@ int btrfs_check_dir_item_collision(struct btrfs_root *root, u64 dir,
 			  const char *name, int name_len);
 int btrfs_insert_dir_item(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *root, const char *name,
-			  int name_len, struct inode *dir,
+			  int name_len, struct btrfs_inode *dir,
 			  struct btrfs_key *location, u8 type, u64 index);
 struct btrfs_dir_item *btrfs_lookup_dir_item(struct btrfs_trans_handle *trans,
 					     struct btrfs_root *root,
@@ -3007,12 +3040,14 @@ struct btrfs_dir_item *btrfs_lookup_xattr(struct btrfs_trans_handle *trans,
 					  const char *name, u16 name_len,
 					  int mod);
 int verify_dir_item(struct btrfs_fs_info *fs_info,
-		    struct extent_buffer *leaf,
+		    struct extent_buffer *leaf, int slot,
 		    struct btrfs_dir_item *dir_item);
 struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info,
 						 struct btrfs_path *path,
 						 const char *name,
 						 int name_len);
+bool btrfs_is_name_len_valid(struct extent_buffer *leaf, int slot,
+			     unsigned long start, u16 name_len);
 
 /* orphan.c */
 int btrfs_insert_orphan_item(struct btrfs_trans_handle *trans,
@@ -3054,8 +3089,8 @@ int btrfs_find_name_in_ext_backref(struct btrfs_path *path,
 struct btrfs_dio_private;
 int btrfs_del_csums(struct btrfs_trans_handle *trans,
 		    struct btrfs_fs_info *fs_info, u64 bytenr, u64 len);
-int btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst);
-int btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio,
+blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst);
+blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio,
 			      u64 logical_offset);
 int btrfs_insert_file_extent(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root,
@@ -3070,11 +3105,11 @@ int btrfs_lookup_file_extent(struct btrfs_trans_handle *trans,
 int btrfs_csum_file_blocks(struct btrfs_trans_handle *trans,
 			   struct btrfs_root *root,
 			   struct btrfs_ordered_sum *sums);
-int btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
+blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 		       u64 file_start, int contig);
 int btrfs_lookup_csums_range(struct btrfs_root *root, u64 start, u64 end,
 			     struct list_head *list, int search_commit);
-void btrfs_extent_item_to_extent_map(struct inode *inode,
+void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 				     const struct btrfs_path *path,
 				     struct btrfs_file_extent_item *fi,
 				     const bool new_inline,
@@ -3093,9 +3128,9 @@ struct btrfs_delalloc_work *btrfs_alloc_delalloc_work(struct inode *inode,
 						    int delay_iput);
 void btrfs_wait_and_free_delalloc_work(struct btrfs_delalloc_work *work);
 
-struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page,
-					   size_t pg_offset, u64 start, u64 len,
-					   int create);
+struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
+		struct page *page, size_t pg_offset, u64 start,
+		u64 len, int create);
 noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *orig_start, u64 *orig_block_len,
 			      u64 *ram_bytes);
@@ -3116,13 +3151,13 @@ static inline void btrfs_force_ra(struct address_space *mapping,
 }
 
 struct inode *btrfs_lookup_dentry(struct inode *dir, struct dentry *dentry);
-int btrfs_set_inode_index(struct inode *dir, u64 *index);
+int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index);
 int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root,
-		       struct inode *dir, struct inode *inode,
+		       struct btrfs_inode *dir, struct btrfs_inode *inode,
 		       const char *name, int name_len);
 int btrfs_add_link(struct btrfs_trans_handle *trans,
-		   struct inode *parent_inode, struct inode *inode,
+		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
 		   const char *name, int name_len, int add_backref, u64 index);
 int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 			struct btrfs_root *root,
@@ -3147,7 +3182,8 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
 			 size_t size, struct bio *bio,
 			 unsigned long bio_flags);
-int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
+void btrfs_set_range_writeback(void *private_data, u64 start, u64 end);
+int btrfs_page_mkwrite(struct vm_fault *vmf);
 int btrfs_readpage(struct file *file, struct page *page);
 void btrfs_evict_inode(struct inode *inode);
 int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc);
@@ -3159,15 +3195,16 @@ void btrfs_destroy_cachep(void);
 long btrfs_ioctl_trans_end(struct file *file);
 struct inode *btrfs_iget(struct super_block *s, struct btrfs_key *location,
 			 struct btrfs_root *root, int *was_new);
-struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
-				    size_t pg_offset, u64 start, u64 end,
-				    int create);
+struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
+		struct page *page, size_t pg_offset,
+		u64 start, u64 end, int create);
 int btrfs_update_inode(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root,
 			      struct inode *inode);
 int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root, struct inode *inode);
-int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode);
+int btrfs_orphan_add(struct btrfs_trans_handle *trans,
+		struct btrfs_inode *inode);
 int btrfs_orphan_cleanup(struct btrfs_root *root);
 void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
 			      struct btrfs_root *root);
@@ -3208,11 +3245,11 @@ ssize_t btrfs_dedupe_file_range(struct file *src_file, u64 loff, u64 olen,
 int btrfs_auto_defrag_init(void);
 void btrfs_auto_defrag_exit(void);
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
-			   struct inode *inode);
+			   struct btrfs_inode *inode);
 int btrfs_run_defrag_inodes(struct btrfs_fs_info *fs_info);
 void btrfs_cleanup_defrag_inodes(struct btrfs_fs_info *fs_info);
 int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
-void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
+void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
 			     int skip_pinned);
 extern const struct file_operations btrfs_file_operations;
 int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
@@ -3226,7 +3263,7 @@ int btrfs_drop_extents(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root, struct inode *inode, u64 start,
 		       u64 end, int drop_cache);
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
-			      struct inode *inode, u64 start, u64 end);
+			      struct btrfs_inode *inode, u64 start, u64 end);
 int btrfs_release_file(struct inode *inode, struct file *file);
 int btrfs_dirty_pages(struct inode *inode, struct page **pages,
 		      size_t num_pages, loff_t pos, size_t write_bytes,
@@ -3447,7 +3484,8 @@ do {								\
 			"BTRFS: Transaction aborted (error %d)\n",	\
 			(errno));					\
 		} else {						\
-			pr_debug("BTRFS: Transaction aborted (error %d)\n", \
+			btrfs_debug((trans)->fs_info,			\
+				    "Transaction aborted (error %d)", \
 				  (errno));			\
 		}						\
 	}							\
@@ -3637,6 +3675,12 @@ int btrfs_scrub_cancel_dev(struct btrfs_fs_info *info,
 			   struct btrfs_device *dev);
 int btrfs_scrub_progress(struct btrfs_fs_info *fs_info, u64 devid,
 			 struct btrfs_scrub_progress *progress);
+static inline void btrfs_init_full_stripe_locks_tree(
+			struct btrfs_full_stripe_locks_tree *locks_root)
+{
+	locks_root->root = RB_ROOT;
+	mutex_init(&locks_root->lock);
+}
 
 /* dev-replace.c */
 void btrfs_bio_counter_inc_blocked(struct btrfs_fs_info *fs_info);
@@ -3661,8 +3705,7 @@ struct reada_control *btrfs_reada_add(struct btrfs_root *root,
 			      struct btrfs_key *start, struct btrfs_key *end);
 int btrfs_reada_wait(void *handle);
 void btrfs_reada_detach(void *handle);
-int btree_readahead_hook(struct btrfs_fs_info *fs_info,
-			 struct extent_buffer *eb, int err);
+int btree_readahead_hook(struct extent_buffer *eb, int err);
 
 static inline int is_fstree(u64 rootid)
 {
diff --git a/fs/btrfs/delayed-inode.c b/fs/btrfs/delayed-inode.c
index 80982a83c9fd..8ae409b5a61d 100644
--- a/fs/btrfs/delayed-inode.c
+++ b/fs/btrfs/delayed-inode.c
@@ -52,7 +52,7 @@ static inline void btrfs_init_delayed_node(
 {
 	delayed_node->root = root;
 	delayed_node->inode_id = inode_id;
-	atomic_set(&delayed_node->refs, 0);
+	refcount_set(&delayed_node->refs, 0);
 	delayed_node->ins_root = RB_ROOT;
 	delayed_node->del_root = RB_ROOT;
 	mutex_init(&delayed_node->mutex);
@@ -72,16 +72,16 @@ static inline int btrfs_is_continuous_delayed_item(
 	return 0;
 }
 
-static struct btrfs_delayed_node *btrfs_get_delayed_node(struct inode *inode)
+static struct btrfs_delayed_node *btrfs_get_delayed_node(
+		struct btrfs_inode *btrfs_inode)
 {
-	struct btrfs_inode *btrfs_inode = BTRFS_I(inode);
 	struct btrfs_root *root = btrfs_inode->root;
-	u64 ino = btrfs_ino(inode);
+	u64 ino = btrfs_ino(btrfs_inode);
 	struct btrfs_delayed_node *node;
 
-	node = ACCESS_ONCE(btrfs_inode->delayed_node);
+	node = READ_ONCE(btrfs_inode->delayed_node);
 	if (node) {
-		atomic_inc(&node->refs);
+		refcount_inc(&node->refs);
 		return node;
 	}
 
@@ -89,14 +89,14 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(struct inode *inode)
 	node = radix_tree_lookup(&root->delayed_nodes_tree, ino);
 	if (node) {
 		if (btrfs_inode->delayed_node) {
-			atomic_inc(&node->refs);	/* can be accessed */
+			refcount_inc(&node->refs);	/* can be accessed */
 			BUG_ON(btrfs_inode->delayed_node != node);
 			spin_unlock(&root->inode_lock);
 			return node;
 		}
 		btrfs_inode->delayed_node = node;
 		/* can be accessed and cached in the inode */
-		atomic_add(2, &node->refs);
+		refcount_add(2, &node->refs);
 		spin_unlock(&root->inode_lock);
 		return node;
 	}
@@ -107,16 +107,15 @@ static struct btrfs_delayed_node *btrfs_get_delayed_node(struct inode *inode)
 
 /* Will return either the node or PTR_ERR(-ENOMEM) */
 static struct btrfs_delayed_node *btrfs_get_or_create_delayed_node(
-							struct inode *inode)
+		struct btrfs_inode *btrfs_inode)
 {
 	struct btrfs_delayed_node *node;
-	struct btrfs_inode *btrfs_inode = BTRFS_I(inode);
 	struct btrfs_root *root = btrfs_inode->root;
-	u64 ino = btrfs_ino(inode);
+	u64 ino = btrfs_ino(btrfs_inode);
 	int ret;
 
 again:
-	node = btrfs_get_delayed_node(inode);
+	node = btrfs_get_delayed_node(btrfs_inode);
 	if (node)
 		return node;
 
@@ -126,7 +125,7 @@ again:
 	btrfs_init_delayed_node(node, root, ino);
 
 	/* cached in the btrfs inode and can be accessed */
-	atomic_add(2, &node->refs);
+	refcount_set(&node->refs, 2);
 
 	ret = radix_tree_preload(GFP_NOFS);
 	if (ret) {
@@ -167,7 +166,7 @@ static void btrfs_queue_delayed_node(struct btrfs_delayed_root *root,
 	} else {
 		list_add_tail(&node->n_list, &root->node_list);
 		list_add_tail(&node->p_list, &root->prepare_list);
-		atomic_inc(&node->refs);	/* inserted into list */
+		refcount_inc(&node->refs);	/* inserted into list */
 		root->nodes++;
 		set_bit(BTRFS_DELAYED_NODE_IN_LIST, &node->flags);
 	}
@@ -181,7 +180,7 @@ static void btrfs_dequeue_delayed_node(struct btrfs_delayed_root *root,
 	spin_lock(&root->lock);
 	if (test_bit(BTRFS_DELAYED_NODE_IN_LIST, &node->flags)) {
 		root->nodes--;
-		atomic_dec(&node->refs);	/* not in the list */
+		refcount_dec(&node->refs);	/* not in the list */
 		list_del_init(&node->n_list);
 		if (!list_empty(&node->p_list))
 			list_del_init(&node->p_list);
@@ -202,7 +201,7 @@ static struct btrfs_delayed_node *btrfs_first_delayed_node(
 
 	p = delayed_root->node_list.next;
 	node = list_entry(p, struct btrfs_delayed_node, n_list);
-	atomic_inc(&node->refs);
+	refcount_inc(&node->refs);
 out:
 	spin_unlock(&delayed_root->lock);
 
@@ -229,7 +228,7 @@ static struct btrfs_delayed_node *btrfs_next_delayed_node(
 		p = node->n_list.next;
 
 	next = list_entry(p, struct btrfs_delayed_node, n_list);
-	atomic_inc(&next->refs);
+	refcount_inc(&next->refs);
 out:
 	spin_unlock(&delayed_root->lock);
 
@@ -254,11 +253,11 @@ static void __btrfs_release_delayed_node(
 		btrfs_dequeue_delayed_node(delayed_root, delayed_node);
 	mutex_unlock(&delayed_node->mutex);
 
-	if (atomic_dec_and_test(&delayed_node->refs)) {
+	if (refcount_dec_and_test(&delayed_node->refs)) {
 		bool free = false;
 		struct btrfs_root *root = delayed_node->root;
 		spin_lock(&root->inode_lock);
-		if (atomic_read(&delayed_node->refs) == 0) {
+		if (refcount_read(&delayed_node->refs) == 0) {
 			radix_tree_delete(&root->delayed_nodes_tree,
 					  delayed_node->inode_id);
 			free = true;
@@ -287,7 +286,7 @@ static struct btrfs_delayed_node *btrfs_first_prepared_delayed_node(
 	p = delayed_root->prepare_list.next;
 	list_del_init(p);
 	node = list_entry(p, struct btrfs_delayed_node, p_list);
-	atomic_inc(&node->refs);
+	refcount_inc(&node->refs);
 out:
 	spin_unlock(&delayed_root->lock);
 
@@ -309,7 +308,7 @@ static struct btrfs_delayed_item *btrfs_alloc_delayed_item(u32 data_len)
 		item->ins_or_del = 0;
 		item->bytes_reserved = 0;
 		item->delayed_node = NULL;
-		atomic_set(&item->refs, 1);
+		refcount_set(&item->refs, 1);
 	}
 	return item;
 }
@@ -484,7 +483,7 @@ static void btrfs_release_delayed_item(struct btrfs_delayed_item *item)
 {
 	if (item) {
 		__btrfs_remove_delayed_item(item);
-		if (atomic_dec_and_test(&item->refs))
+		if (refcount_dec_and_test(&item->refs))
 			kfree(item);
 	}
 }
@@ -574,7 +573,7 @@ static void btrfs_delayed_item_release_metadata(struct btrfs_fs_info *fs_info,
 static int btrfs_delayed_inode_reserve_metadata(
 					struct btrfs_trans_handle *trans,
 					struct btrfs_root *root,
-					struct inode *inode,
+					struct btrfs_inode *inode,
 					struct btrfs_delayed_node *node)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -603,13 +602,13 @@ static int btrfs_delayed_inode_reserve_metadata(
 	 * worth which is less likely to hurt us.
 	 */
 	if (src_rsv && src_rsv->type == BTRFS_BLOCK_RSV_DELALLOC) {
-		spin_lock(&BTRFS_I(inode)->lock);
+		spin_lock(&inode->lock);
 		if (test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
-				       &BTRFS_I(inode)->runtime_flags))
+				       &inode->runtime_flags))
 			release = true;
 		else
 			src_rsv = NULL;
-		spin_unlock(&BTRFS_I(inode)->lock);
+		spin_unlock(&inode->lock);
 	}
 
 	/*
@@ -1196,7 +1195,7 @@ int btrfs_run_delayed_items_nr(struct btrfs_trans_handle *trans,
 }
 
 int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
-				     struct inode *inode)
+				     struct btrfs_inode *inode)
 {
 	struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode);
 	struct btrfs_path *path;
@@ -1233,9 +1232,9 @@ int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-int btrfs_commit_inode_delayed_inode(struct inode *inode)
+int btrfs_commit_inode_delayed_inode(struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	struct btrfs_trans_handle *trans;
 	struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode);
 	struct btrfs_path *path;
@@ -1288,15 +1287,15 @@ out:
 	return ret;
 }
 
-void btrfs_remove_delayed_node(struct inode *inode)
+void btrfs_remove_delayed_node(struct btrfs_inode *inode)
 {
 	struct btrfs_delayed_node *delayed_node;
 
-	delayed_node = ACCESS_ONCE(BTRFS_I(inode)->delayed_node);
+	delayed_node = READ_ONCE(inode->delayed_node);
 	if (!delayed_node)
 		return;
 
-	BTRFS_I(inode)->delayed_node = NULL;
+	inode->delayed_node = NULL;
 	btrfs_release_delayed_node(delayed_node);
 }
 
@@ -1434,7 +1433,7 @@ void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info)
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 				   struct btrfs_fs_info *fs_info,
 				   const char *name, int name_len,
-				   struct inode *dir,
+				   struct btrfs_inode *dir,
 				   struct btrfs_disk_key *disk_key, u8 type,
 				   u64 index)
 {
@@ -1510,7 +1509,7 @@ static int btrfs_delete_delayed_insertion_item(struct btrfs_fs_info *fs_info,
 
 int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 				   struct btrfs_fs_info *fs_info,
-				   struct inode *dir, u64 index)
+				   struct btrfs_inode *dir, u64 index)
 {
 	struct btrfs_delayed_node *node;
 	struct btrfs_delayed_item *item;
@@ -1558,7 +1557,7 @@ end:
 	return ret;
 }
 
-int btrfs_inode_delayed_dir_index_count(struct inode *inode)
+int btrfs_inode_delayed_dir_index_count(struct btrfs_inode *inode)
 {
 	struct btrfs_delayed_node *delayed_node = btrfs_get_delayed_node(inode);
 
@@ -1575,7 +1574,7 @@ int btrfs_inode_delayed_dir_index_count(struct inode *inode)
 		return -EINVAL;
 	}
 
-	BTRFS_I(inode)->index_cnt = delayed_node->index_cnt;
+	inode->index_cnt = delayed_node->index_cnt;
 	btrfs_release_delayed_node(delayed_node);
 	return 0;
 }
@@ -1587,7 +1586,7 @@ bool btrfs_readdir_get_delayed_items(struct inode *inode,
 	struct btrfs_delayed_node *delayed_node;
 	struct btrfs_delayed_item *item;
 
-	delayed_node = btrfs_get_delayed_node(inode);
+	delayed_node = btrfs_get_delayed_node(BTRFS_I(inode));
 	if (!delayed_node)
 		return false;
 
@@ -1601,14 +1600,14 @@ bool btrfs_readdir_get_delayed_items(struct inode *inode,
 	mutex_lock(&delayed_node->mutex);
 	item = __btrfs_first_delayed_insertion_item(delayed_node);
 	while (item) {
-		atomic_inc(&item->refs);
+		refcount_inc(&item->refs);
 		list_add_tail(&item->readdir_list, ins_list);
 		item = __btrfs_next_delayed_item(item);
 	}
 
 	item = __btrfs_first_delayed_deletion_item(delayed_node);
 	while (item) {
-		atomic_inc(&item->refs);
+		refcount_inc(&item->refs);
 		list_add_tail(&item->readdir_list, del_list);
 		item = __btrfs_next_delayed_item(item);
 	}
@@ -1622,7 +1621,7 @@ bool btrfs_readdir_get_delayed_items(struct inode *inode,
 	 * insert/delete delayed items in this period. So we also needn't
 	 * requeue or dequeue this delayed node.
 	 */
-	atomic_dec(&delayed_node->refs);
+	refcount_dec(&delayed_node->refs);
 
 	return true;
 }
@@ -1635,13 +1634,13 @@ void btrfs_readdir_put_delayed_items(struct inode *inode,
 
 	list_for_each_entry_safe(curr, next, ins_list, readdir_list) {
 		list_del(&curr->readdir_list);
-		if (atomic_dec_and_test(&curr->refs))
+		if (refcount_dec_and_test(&curr->refs))
 			kfree(curr);
 	}
 
 	list_for_each_entry_safe(curr, next, del_list, readdir_list) {
 		list_del(&curr->readdir_list);
-		if (atomic_dec_and_test(&curr->refs))
+		if (refcount_dec_and_test(&curr->refs))
 			kfree(curr);
 	}
 
@@ -1668,7 +1667,7 @@ int btrfs_should_delete_dir_index(struct list_head *del_list,
 		list_del(&curr->readdir_list);
 		ret = (curr->key.offset == index);
 
-		if (atomic_dec_and_test(&curr->refs))
+		if (refcount_dec_and_test(&curr->refs))
 			kfree(curr);
 
 		if (ret)
@@ -1706,7 +1705,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
 		list_del(&curr->readdir_list);
 
 		if (curr->key.offset < ctx->pos) {
-			if (atomic_dec_and_test(&curr->refs))
+			if (refcount_dec_and_test(&curr->refs))
 				kfree(curr);
 			continue;
 		}
@@ -1723,7 +1722,7 @@ int btrfs_readdir_delayed_dir_index(struct dir_context *ctx,
 		over = !dir_emit(ctx, name, name_len,
 			       location.objectid, d_type);
 
-		if (atomic_dec_and_test(&curr->refs))
+		if (refcount_dec_and_test(&curr->refs))
 			kfree(curr);
 
 		if (over)
@@ -1776,7 +1775,7 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev)
 	struct btrfs_delayed_node *delayed_node;
 	struct btrfs_inode_item *inode_item;
 
-	delayed_node = btrfs_get_delayed_node(inode);
+	delayed_node = btrfs_get_delayed_node(BTRFS_I(inode));
 	if (!delayed_node)
 		return -ENOENT;
 
@@ -1791,7 +1790,7 @@ int btrfs_fill_inode(struct inode *inode, u32 *rdev)
 
 	i_uid_write(inode, btrfs_stack_inode_uid(inode_item));
 	i_gid_write(inode, btrfs_stack_inode_gid(inode_item));
-	btrfs_i_size_write(inode, btrfs_stack_inode_size(inode_item));
+	btrfs_i_size_write(BTRFS_I(inode), btrfs_stack_inode_size(inode_item));
 	inode->i_mode = btrfs_stack_inode_mode(inode_item);
 	set_nlink(inode, btrfs_stack_inode_nlink(inode_item));
 	inode_set_bytes(inode, btrfs_stack_inode_nbytes(inode_item));
@@ -1831,7 +1830,7 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_node *delayed_node;
 	int ret = 0;
 
-	delayed_node = btrfs_get_or_create_delayed_node(inode);
+	delayed_node = btrfs_get_or_create_delayed_node(BTRFS_I(inode));
 	if (IS_ERR(delayed_node))
 		return PTR_ERR(delayed_node);
 
@@ -1841,7 +1840,7 @@ int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
 		goto release_node;
 	}
 
-	ret = btrfs_delayed_inode_reserve_metadata(trans, root, inode,
+	ret = btrfs_delayed_inode_reserve_metadata(trans, root, BTRFS_I(inode),
 						   delayed_node);
 	if (ret)
 		goto release_node;
@@ -1856,9 +1855,9 @@ release_node:
 	return ret;
 }
 
-int btrfs_delayed_delete_inode_ref(struct inode *inode)
+int btrfs_delayed_delete_inode_ref(struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	struct btrfs_delayed_node *delayed_node;
 
 	/*
@@ -1933,7 +1932,7 @@ static void __btrfs_kill_delayed_node(struct btrfs_delayed_node *delayed_node)
 	mutex_unlock(&delayed_node->mutex);
 }
 
-void btrfs_kill_delayed_inode_items(struct inode *inode)
+void btrfs_kill_delayed_inode_items(struct btrfs_inode *inode)
 {
 	struct btrfs_delayed_node *delayed_node;
 
@@ -1964,7 +1963,7 @@ void btrfs_kill_all_delayed_nodes(struct btrfs_root *root)
 		inode_id = delayed_nodes[n - 1]->inode_id + 1;
 
 		for (i = 0; i < n; i++)
-			atomic_inc(&delayed_nodes[i]->refs);
+			refcount_inc(&delayed_nodes[i]->refs);
 		spin_unlock(&root->inode_lock);
 
 		for (i = 0; i < n; i++) {
diff --git a/fs/btrfs/delayed-inode.h b/fs/btrfs/delayed-inode.h
index 8a2bf5e3e4cf..c4189d495934 100644
--- a/fs/btrfs/delayed-inode.h
+++ b/fs/btrfs/delayed-inode.h
@@ -26,7 +26,7 @@
 #include <linux/list.h>
 #include <linux/wait.h>
 #include <linux/atomic.h>
-
+#include <linux/refcount.h>
 #include "ctree.h"
 
 /* types of the delayed item */
@@ -67,7 +67,7 @@ struct btrfs_delayed_node {
 	struct rb_root del_root;
 	struct mutex mutex;
 	struct btrfs_inode_item inode_item;
-	atomic_t refs;
+	refcount_t refs;
 	u64 index_cnt;
 	unsigned long flags;
 	int count;
@@ -80,7 +80,7 @@ struct btrfs_delayed_item {
 	struct list_head readdir_list;	/* used for readdir items */
 	u64 bytes_reserved;
 	struct btrfs_delayed_node *delayed_node;
-	atomic_t refs;
+	refcount_t refs;
 	int ins_or_del;
 	u32 data_len;
 	char data[0];
@@ -101,15 +101,15 @@ static inline void btrfs_init_delayed_root(
 int btrfs_insert_delayed_dir_index(struct btrfs_trans_handle *trans,
 				   struct btrfs_fs_info *fs_info,
 				   const char *name, int name_len,
-				   struct inode *dir,
+				   struct btrfs_inode *dir,
 				   struct btrfs_disk_key *disk_key, u8 type,
 				   u64 index);
 
 int btrfs_delete_delayed_dir_index(struct btrfs_trans_handle *trans,
 				   struct btrfs_fs_info *fs_info,
-				   struct inode *dir, u64 index);
+				   struct btrfs_inode *dir, u64 index);
 
-int btrfs_inode_delayed_dir_index_count(struct inode *inode);
+int btrfs_inode_delayed_dir_index_count(struct btrfs_inode *inode);
 
 int btrfs_run_delayed_items(struct btrfs_trans_handle *trans,
 			    struct btrfs_fs_info *fs_info);
@@ -119,17 +119,17 @@ int btrfs_run_delayed_items_nr(struct btrfs_trans_handle *trans,
 void btrfs_balance_delayed_items(struct btrfs_fs_info *fs_info);
 
 int btrfs_commit_inode_delayed_items(struct btrfs_trans_handle *trans,
-				     struct inode *inode);
+				     struct btrfs_inode *inode);
 /* Used for evicting the inode. */
-void btrfs_remove_delayed_node(struct inode *inode);
-void btrfs_kill_delayed_inode_items(struct inode *inode);
-int btrfs_commit_inode_delayed_inode(struct inode *inode);
+void btrfs_remove_delayed_node(struct btrfs_inode *inode);
+void btrfs_kill_delayed_inode_items(struct btrfs_inode *inode);
+int btrfs_commit_inode_delayed_inode(struct btrfs_inode *inode);
 
 
 int btrfs_delayed_update_inode(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root, struct inode *inode);
 int btrfs_fill_inode(struct inode *inode, u32 *rdev);
-int btrfs_delayed_delete_inode_ref(struct inode *inode);
+int btrfs_delayed_delete_inode_ref(struct btrfs_inode *inode);
 
 /* Used for drop dead root */
 void btrfs_kill_all_delayed_nodes(struct btrfs_root *root);
diff --git a/fs/btrfs/delayed-ref.c b/fs/btrfs/delayed-ref.c
index ef724a5fc30e..93ffa898df6d 100644
--- a/fs/btrfs/delayed-ref.c
+++ b/fs/btrfs/delayed-ref.c
@@ -164,7 +164,7 @@ int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
 	if (mutex_trylock(&head->mutex))
 		return 0;
 
-	atomic_inc(&head->node.refs);
+	refcount_inc(&head->node.refs);
 	spin_unlock(&delayed_refs->lock);
 
 	mutex_lock(&head->mutex);
@@ -470,7 +470,8 @@ add_tail:
 static noinline void
 update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
 			 struct btrfs_delayed_ref_node *existing,
-			 struct btrfs_delayed_ref_node *update)
+			 struct btrfs_delayed_ref_node *update,
+			 int *old_ref_mod_ret)
 {
 	struct btrfs_delayed_ref_head *existing_ref;
 	struct btrfs_delayed_ref_head *ref;
@@ -523,6 +524,8 @@ update_existing_head_ref(struct btrfs_delayed_ref_root *delayed_refs,
 	 * currently, for refs we just added we know we're a-ok.
 	 */
 	old_ref_mod = existing_ref->total_ref_mod;
+	if (old_ref_mod_ret)
+		*old_ref_mod_ret = old_ref_mod;
 	existing->ref_mod += update->ref_mod;
 	existing_ref->total_ref_mod += update->ref_mod;
 
@@ -550,13 +553,15 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		     struct btrfs_delayed_ref_node *ref,
 		     struct btrfs_qgroup_extent_record *qrecord,
 		     u64 bytenr, u64 num_bytes, u64 ref_root, u64 reserved,
-		     int action, int is_data)
+		     int action, int is_data, int *qrecord_inserted_ret,
+		     int *old_ref_mod, int *new_ref_mod)
 {
 	struct btrfs_delayed_ref_head *existing;
 	struct btrfs_delayed_ref_head *head_ref = NULL;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	int count_mod = 1;
 	int must_insert_reserved = 0;
+	int qrecord_inserted = 0;
 
 	/* If reserved is provided, it must be a data extent. */
 	BUG_ON(!is_data && reserved);
@@ -589,7 +594,7 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 	delayed_refs = &trans->transaction->delayed_refs;
 
 	/* first set the basic ref node struct up */
-	atomic_set(&ref->refs, 1);
+	refcount_set(&ref->refs, 1);
 	ref->bytenr = bytenr;
 	ref->num_bytes = num_bytes;
 	ref->ref_mod = count_mod;
@@ -623,6 +628,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		if(btrfs_qgroup_trace_extent_nolock(fs_info,
 					delayed_refs, qrecord))
 			kfree(qrecord);
+		else
+			qrecord_inserted = 1;
 	}
 
 	spin_lock_init(&head_ref->lock);
@@ -635,7 +642,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 	if (existing) {
 		WARN_ON(ref_root && reserved && existing->qgroup_ref_root
 			&& existing->qgroup_reserved);
-		update_existing_head_ref(delayed_refs, &existing->node, ref);
+		update_existing_head_ref(delayed_refs, &existing->node, ref,
+					 old_ref_mod);
 		/*
 		 * we've updated the existing ref, free the newly
 		 * allocated ref
@@ -643,6 +651,8 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		kmem_cache_free(btrfs_delayed_ref_head_cachep, head_ref);
 		head_ref = existing;
 	} else {
+		if (old_ref_mod)
+			*old_ref_mod = 0;
 		if (is_data && count_mod < 0)
 			delayed_refs->pending_csums += num_bytes;
 		delayed_refs->num_heads++;
@@ -650,6 +660,10 @@ add_delayed_ref_head(struct btrfs_fs_info *fs_info,
 		atomic_inc(&delayed_refs->num_entries);
 		trans->delayed_ref_updates++;
 	}
+	if (qrecord_inserted_ret)
+		*qrecord_inserted_ret = qrecord_inserted;
+	if (new_ref_mod)
+		*new_ref_mod = head_ref->total_ref_mod;
 	return head_ref;
 }
 
@@ -677,7 +691,7 @@ add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	delayed_refs = &trans->transaction->delayed_refs;
 
 	/* first set the basic ref node struct up */
-	atomic_set(&ref->refs, 1);
+	refcount_set(&ref->refs, 1);
 	ref->bytenr = bytenr;
 	ref->num_bytes = num_bytes;
 	ref->ref_mod = 1;
@@ -734,7 +748,7 @@ add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 		seq = atomic64_read(&fs_info->tree_mod_seq);
 
 	/* first set the basic ref node struct up */
-	atomic_set(&ref->refs, 1);
+	refcount_set(&ref->refs, 1);
 	ref->bytenr = bytenr;
 	ref->num_bytes = num_bytes;
 	ref->ref_mod = 1;
@@ -773,12 +787,14 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 			       struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes, u64 parent,
 			       u64 ref_root,  int level, int action,
-			       struct btrfs_delayed_extent_op *extent_op)
+			       struct btrfs_delayed_extent_op *extent_op,
+			       int *old_ref_mod, int *new_ref_mod)
 {
 	struct btrfs_delayed_tree_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_qgroup_extent_record *record = NULL;
+	int qrecord_inserted;
 
 	BUG_ON(extent_op && extent_op->is_data);
 	ref = kmem_cache_alloc(btrfs_delayed_tree_ref_cachep, GFP_NOFS);
@@ -806,12 +822,16 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 	 * the spin lock
 	 */
 	head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record,
-					bytenr, num_bytes, 0, 0, action, 0);
+					bytenr, num_bytes, 0, 0, action, 0,
+					&qrecord_inserted, old_ref_mod,
+					new_ref_mod);
 
 	add_delayed_tree_ref(fs_info, trans, head_ref, &ref->node, bytenr,
 			     num_bytes, parent, ref_root, level, action);
 	spin_unlock(&delayed_refs->lock);
 
+	if (qrecord_inserted)
+		return btrfs_qgroup_trace_extent_post(fs_info, record);
 	return 0;
 
 free_head_ref:
@@ -830,14 +850,14 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 			       u64 bytenr, u64 num_bytes,
 			       u64 parent, u64 ref_root,
 			       u64 owner, u64 offset, u64 reserved, int action,
-			       struct btrfs_delayed_extent_op *extent_op)
+			       int *old_ref_mod, int *new_ref_mod)
 {
 	struct btrfs_delayed_data_ref *ref;
 	struct btrfs_delayed_ref_head *head_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
 	struct btrfs_qgroup_extent_record *record = NULL;
+	int qrecord_inserted;
 
-	BUG_ON(extent_op && !extent_op->is_data);
 	ref = kmem_cache_alloc(btrfs_delayed_data_ref_cachep, GFP_NOFS);
 	if (!ref)
 		return -ENOMEM;
@@ -859,7 +879,7 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 		}
 	}
 
-	head_ref->extent_op = extent_op;
+	head_ref->extent_op = NULL;
 
 	delayed_refs = &trans->transaction->delayed_refs;
 	spin_lock(&delayed_refs->lock);
@@ -870,13 +890,16 @@ int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 	 */
 	head_ref = add_delayed_ref_head(fs_info, trans, &head_ref->node, record,
 					bytenr, num_bytes, ref_root, reserved,
-					action, 1);
+					action, 1, &qrecord_inserted,
+					old_ref_mod, new_ref_mod);
 
 	add_delayed_data_ref(fs_info, trans, head_ref, &ref->node, bytenr,
 				   num_bytes, parent, ref_root, owner, offset,
 				   action);
 	spin_unlock(&delayed_refs->lock);
 
+	if (qrecord_inserted)
+		return btrfs_qgroup_trace_extent_post(fs_info, record);
 	return 0;
 }
 
@@ -899,7 +922,7 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
 
 	add_delayed_ref_head(fs_info, trans, &head_ref->node, NULL, bytenr,
 			     num_bytes, 0, 0, BTRFS_UPDATE_DELAYED_HEAD,
-			     extent_op->is_data);
+			     extent_op->is_data, NULL, NULL, NULL);
 
 	spin_unlock(&delayed_refs->lock);
 	return 0;
@@ -911,11 +934,8 @@ int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
  * the head node if any where found, or NULL if not.
  */
 struct btrfs_delayed_ref_head *
-btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr)
+btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs, u64 bytenr)
 {
-	struct btrfs_delayed_ref_root *delayed_refs;
-
-	delayed_refs = &trans->transaction->delayed_refs;
 	return find_ref_head(&delayed_refs->href_root, bytenr, 0);
 }
 
diff --git a/fs/btrfs/delayed-ref.h b/fs/btrfs/delayed-ref.h
index 50947b5a9152..ce88e4ac5276 100644
--- a/fs/btrfs/delayed-ref.h
+++ b/fs/btrfs/delayed-ref.h
@@ -18,6 +18,8 @@
 #ifndef __DELAYED_REF__
 #define __DELAYED_REF__
 
+#include <linux/refcount.h>
+
 /* these are the possible values of struct btrfs_delayed_ref_node->action */
 #define BTRFS_ADD_DELAYED_REF    1 /* add one backref to the tree */
 #define BTRFS_DROP_DELAYED_REF   2 /* delete one backref from the tree */
@@ -53,7 +55,7 @@ struct btrfs_delayed_ref_node {
 	u64 seq;
 
 	/* ref count on this data structure */
-	atomic_t refs;
+	refcount_t refs;
 
 	/*
 	 * how many refs is this entry adding or deleting.  For
@@ -220,8 +222,8 @@ btrfs_free_delayed_extent_op(struct btrfs_delayed_extent_op *op)
 
 static inline void btrfs_put_delayed_ref(struct btrfs_delayed_ref_node *ref)
 {
-	WARN_ON(atomic_read(&ref->refs) == 0);
-	if (atomic_dec_and_test(&ref->refs)) {
+	WARN_ON(refcount_read(&ref->refs) == 0);
+	if (refcount_dec_and_test(&ref->refs)) {
 		WARN_ON(ref->in_tree);
 		switch (ref->type) {
 		case BTRFS_TREE_BLOCK_REF_KEY:
@@ -245,13 +247,14 @@ int btrfs_add_delayed_tree_ref(struct btrfs_fs_info *fs_info,
 			       struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes, u64 parent,
 			       u64 ref_root, int level, int action,
-			       struct btrfs_delayed_extent_op *extent_op);
+			       struct btrfs_delayed_extent_op *extent_op,
+			       int *old_ref_mod, int *new_ref_mod);
 int btrfs_add_delayed_data_ref(struct btrfs_fs_info *fs_info,
 			       struct btrfs_trans_handle *trans,
 			       u64 bytenr, u64 num_bytes,
 			       u64 parent, u64 ref_root,
 			       u64 owner, u64 offset, u64 reserved, int action,
-			       struct btrfs_delayed_extent_op *extent_op);
+			       int *old_ref_mod, int *new_ref_mod);
 int btrfs_add_delayed_extent_op(struct btrfs_fs_info *fs_info,
 				struct btrfs_trans_handle *trans,
 				u64 bytenr, u64 num_bytes,
@@ -262,7 +265,8 @@ void btrfs_merge_delayed_refs(struct btrfs_trans_handle *trans,
 			      struct btrfs_delayed_ref_head *head);
 
 struct btrfs_delayed_ref_head *
-btrfs_find_delayed_ref_head(struct btrfs_trans_handle *trans, u64 bytenr);
+btrfs_find_delayed_ref_head(struct btrfs_delayed_ref_root *delayed_refs,
+			    u64 bytenr);
 int btrfs_delayed_ref_lock(struct btrfs_trans_handle *trans,
 			   struct btrfs_delayed_ref_head *head);
 static inline void btrfs_delayed_ref_unlock(struct btrfs_delayed_ref_head *head)
diff --git a/fs/btrfs/dev-replace.c b/fs/btrfs/dev-replace.c
index 5de280b9ad73..bee3edeea7a3 100644
--- a/fs/btrfs/dev-replace.c
+++ b/fs/btrfs/dev-replace.c
@@ -304,8 +304,9 @@ void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info)
 		dev_replace->cursor_left_last_write_of_item;
 }
 
-int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, char *tgtdev_name,
-				u64 srcdevid, char *srcdev_name, int read_src)
+int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
+		const char *tgtdev_name, u64 srcdevid, const char *srcdev_name,
+		int read_src)
 {
 	struct btrfs_root *root = fs_info->dev_root;
 	struct btrfs_trans_handle *trans;
@@ -387,7 +388,7 @@ int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, char *tgtdev_name,
 	if (ret)
 		btrfs_err(fs_info, "kobj add dev failed %d", ret);
 
-	btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
+	btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
 
 	/* force writing the updated state information to disk */
 	trans = btrfs_start_transaction(root, 0);
@@ -506,7 +507,7 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 		return ret;
 	}
-	btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
+	btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
 
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
@@ -545,8 +546,10 @@ static int btrfs_dev_replace_finishing(struct btrfs_fs_info *fs_info,
 		mutex_unlock(&fs_info->chunk_mutex);
 		mutex_unlock(&fs_info->fs_devices->device_list_mutex);
 		mutex_unlock(&uuid_mutex);
+		btrfs_rm_dev_replace_blocked(fs_info);
 		if (tgt_device)
 			btrfs_destroy_dev_replace_tgtdev(fs_info, tgt_device);
+		btrfs_rm_dev_replace_unblocked(fs_info);
 		mutex_unlock(&dev_replace->lock_finishing_cancel_unmount);
 
 		return scrub_ret;
@@ -664,7 +667,7 @@ void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_STARTED:
 	case BTRFS_IOCTL_DEV_REPLACE_STATE_SUSPENDED:
 		srcdev = dev_replace->srcdev;
-		args->status.progress_1000 = div_u64(dev_replace->cursor_left,
+		args->status.progress_1000 = div64_u64(dev_replace->cursor_left,
 			div_u64(btrfs_device_get_total_bytes(srcdev), 1000));
 		break;
 	}
@@ -783,8 +786,7 @@ int btrfs_resume_dev_replace_async(struct btrfs_fs_info *fs_info)
 	}
 	btrfs_dev_replace_unlock(dev_replace, 1);
 
-	WARN_ON(atomic_xchg(
-		&fs_info->mutually_exclusive_operation_running, 1));
+	WARN_ON(test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags));
 	task = kthread_run(btrfs_dev_replace_kthread, fs_info, "btrfs-devrepl");
 	return PTR_ERR_OR_ZERO(task);
 }
@@ -813,7 +815,7 @@ static int btrfs_dev_replace_kthread(void *data)
 			(unsigned int)progress);
 	}
 	btrfs_dev_replace_continue_on_mount(fs_info);
-	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 
 	return 0;
 }
diff --git a/fs/btrfs/dev-replace.h b/fs/btrfs/dev-replace.h
index 54ea12bda15b..f94a76844ae7 100644
--- a/fs/btrfs/dev-replace.h
+++ b/fs/btrfs/dev-replace.h
@@ -27,8 +27,9 @@ int btrfs_run_dev_replace(struct btrfs_trans_handle *trans,
 void btrfs_after_dev_replace_commit(struct btrfs_fs_info *fs_info);
 int btrfs_dev_replace_by_ioctl(struct btrfs_fs_info *fs_info,
 			    struct btrfs_ioctl_dev_replace_args *args);
-int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info, char *tgtdev_name,
-				u64 srcdevid, char *srcdev_name, int read_src);
+int btrfs_dev_replace_start(struct btrfs_fs_info *fs_info,
+		const char *tgtdev_name, u64 srcdevid, const char *srcdev_name,
+		int read_src);
 void btrfs_dev_replace_status(struct btrfs_fs_info *fs_info,
 			      struct btrfs_ioctl_dev_replace_args *args);
 int btrfs_dev_replace_cancel(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/dir-item.c b/fs/btrfs/dir-item.c
index b039fe0c751a..41cb9196eaa8 100644
--- a/fs/btrfs/dir-item.c
+++ b/fs/btrfs/dir-item.c
@@ -80,7 +80,8 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 	u32 data_size;
 
-	BUG_ON(name_len + data_len > BTRFS_MAX_XATTR_SIZE(root->fs_info));
+	if (name_len + data_len > BTRFS_MAX_XATTR_SIZE(root->fs_info))
+		return -ENOSPC;
 
 	key.objectid = objectid;
 	key.type = BTRFS_XATTR_ITEM_KEY;
@@ -120,7 +121,7 @@ int btrfs_insert_xattr_item(struct btrfs_trans_handle *trans,
  */
 int btrfs_insert_dir_item(struct btrfs_trans_handle *trans, struct btrfs_root
 			  *root, const char *name, int name_len,
-			  struct inode *dir, struct btrfs_key *location,
+			  struct btrfs_inode *dir, struct btrfs_key *location,
 			  u8 type, u64 index)
 {
 	int ret = 0;
@@ -174,8 +175,7 @@ second_insert:
 	btrfs_release_path(path);
 
 	ret2 = btrfs_insert_delayed_dir_index(trans, root->fs_info, name,
-					      name_len, dir, &disk_key, type,
-					      index);
+			name_len, dir, &disk_key, type, index);
 out_free:
 	btrfs_free_path(path);
 	if (ret)
@@ -395,8 +395,6 @@ struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info,
 
 	leaf = path->nodes[0];
 	dir_item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_dir_item);
-	if (verify_dir_item(fs_info, leaf, dir_item))
-		return NULL;
 
 	total_len = btrfs_item_size_nr(leaf, path->slots[0]);
 	while (cur < total_len) {
@@ -405,6 +403,8 @@ struct btrfs_dir_item *btrfs_match_dir_item_name(struct btrfs_fs_info *fs_info,
 			btrfs_dir_data_len(leaf, dir_item);
 		name_ptr = (unsigned long)(dir_item + 1);
 
+		if (verify_dir_item(fs_info, leaf, path->slots[0], dir_item))
+			return NULL;
 		if (btrfs_dir_name_len(leaf, dir_item) == name_len &&
 		    memcmp_extent_buffer(leaf, name, name_ptr, name_len) == 0)
 			return dir_item;
@@ -453,9 +453,11 @@ int btrfs_delete_one_dir_name(struct btrfs_trans_handle *trans,
 
 int verify_dir_item(struct btrfs_fs_info *fs_info,
 		    struct extent_buffer *leaf,
+		    int slot,
 		    struct btrfs_dir_item *dir_item)
 {
 	u16 namelen = BTRFS_NAME_LEN;
+	int ret;
 	u8 type = btrfs_dir_type(leaf, dir_item);
 
 	if (type >= BTRFS_FT_MAX) {
@@ -468,10 +470,16 @@ int verify_dir_item(struct btrfs_fs_info *fs_info,
 
 	if (btrfs_dir_name_len(leaf, dir_item) > namelen) {
 		btrfs_crit(fs_info, "invalid dir item name len: %u",
-		       (unsigned)btrfs_dir_data_len(leaf, dir_item));
+		       (unsigned)btrfs_dir_name_len(leaf, dir_item));
 		return 1;
 	}
 
+	namelen = btrfs_dir_name_len(leaf, dir_item);
+	ret = btrfs_is_name_len_valid(leaf, slot,
+				      (unsigned long)(dir_item + 1), namelen);
+	if (!ret)
+		return 1;
+
 	/* BTRFS_MAX_XATTR_SIZE is the same for all dir items */
 	if ((btrfs_dir_data_len(leaf, dir_item) +
 	     btrfs_dir_name_len(leaf, dir_item)) >
@@ -484,3 +492,67 @@ int verify_dir_item(struct btrfs_fs_info *fs_info,
 
 	return 0;
 }
+
+bool btrfs_is_name_len_valid(struct extent_buffer *leaf, int slot,
+			     unsigned long start, u16 name_len)
+{
+	struct btrfs_fs_info *fs_info = leaf->fs_info;
+	struct btrfs_key key;
+	u32 read_start;
+	u32 read_end;
+	u32 item_start;
+	u32 item_end;
+	u32 size;
+	bool ret = true;
+
+	ASSERT(start > BTRFS_LEAF_DATA_OFFSET);
+
+	read_start = start - BTRFS_LEAF_DATA_OFFSET;
+	read_end = read_start + name_len;
+	item_start = btrfs_item_offset_nr(leaf, slot);
+	item_end = btrfs_item_end_nr(leaf, slot);
+
+	btrfs_item_key_to_cpu(leaf, &key, slot);
+
+	switch (key.type) {
+	case BTRFS_DIR_ITEM_KEY:
+	case BTRFS_XATTR_ITEM_KEY:
+	case BTRFS_DIR_INDEX_KEY:
+		size = sizeof(struct btrfs_dir_item);
+		break;
+	case BTRFS_INODE_REF_KEY:
+		size = sizeof(struct btrfs_inode_ref);
+		break;
+	case BTRFS_INODE_EXTREF_KEY:
+		size = sizeof(struct btrfs_inode_extref);
+		break;
+	case BTRFS_ROOT_REF_KEY:
+	case BTRFS_ROOT_BACKREF_KEY:
+		size = sizeof(struct btrfs_root_ref);
+		break;
+	default:
+		ret = false;
+		goto out;
+	}
+
+	if (read_start < item_start) {
+		ret = false;
+		goto out;
+	}
+	if (read_end > item_end) {
+		ret = false;
+		goto out;
+	}
+
+	/* there shall be item(s) before name */
+	if (read_start - item_start < size) {
+		ret = false;
+		goto out;
+	}
+
+out:
+	if (!ret)
+		btrfs_crit(fs_info, "invalid dir item name len: %u",
+			   (unsigned int)name_len);
+	return ret;
+}
diff --git a/fs/btrfs/disk-io.c b/fs/btrfs/disk-io.c
index 18004169552c..080e2ebb8aa0 100644
--- a/fs/btrfs/disk-io.c
+++ b/fs/btrfs/disk-io.c
@@ -64,8 +64,7 @@
 static const struct extent_io_ops btree_extent_io_ops;
 static void end_workqueue_fn(struct btrfs_work *work);
 static void free_fs_root(struct btrfs_root *root);
-static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
-				    int read_only);
+static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info);
 static void btrfs_destroy_ordered_extents(struct btrfs_root *root);
 static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 				      struct btrfs_fs_info *fs_info);
@@ -88,9 +87,8 @@ struct btrfs_end_io_wq {
 	bio_end_io_t *end_io;
 	void *private;
 	struct btrfs_fs_info *info;
-	int error;
+	blk_status_t status;
 	enum btrfs_wq_endio_type metadata;
-	struct list_head list;
 	struct btrfs_work work;
 };
 
@@ -119,9 +117,9 @@ void btrfs_end_io_wq_exit(void)
  * just before they are sent down the IO stack.
  */
 struct async_submit_bio {
-	struct inode *inode;
+	void *private_data;
+	struct btrfs_fs_info *fs_info;
 	struct bio *bio;
-	struct list_head list;
 	extent_submit_bio_hook_t *submit_bio_start;
 	extent_submit_bio_hook_t *submit_bio_done;
 	int mirror_num;
@@ -132,7 +130,7 @@ struct async_submit_bio {
 	 */
 	u64 bio_offset;
 	struct btrfs_work work;
-	int error;
+	blk_status_t status;
 };
 
 /*
@@ -220,12 +218,12 @@ void btrfs_set_buffer_lockdep_class(u64 objectid, struct extent_buffer *eb,
  * extents on the btree inode are pretty simple, there's one extent
  * that covers the entire device
  */
-static struct extent_map *btree_get_extent(struct inode *inode,
+static struct extent_map *btree_get_extent(struct btrfs_inode *inode,
 		struct page *page, size_t pg_offset, u64 start, u64 len,
 		int create)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	int ret;
 
@@ -266,7 +264,7 @@ out:
 	return em;
 }
 
-u32 btrfs_csum_data(char *data, u32 seed, size_t len)
+u32 btrfs_csum_data(const char *data, u32 seed, size_t len)
 {
 	return btrfs_crc32c(seed, data, len);
 }
@@ -763,7 +761,7 @@ static int btree_readpage_end_io_hook(struct btrfs_io_bio *io_bio,
 err:
 	if (reads_done &&
 	    test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
-		btree_readahead_hook(fs_info, eb, ret);
+		btree_readahead_hook(eb, ret);
 
 	if (ret) {
 		/*
@@ -788,7 +786,7 @@ static int btree_io_failed_hook(struct page *page, int failed_mirror)
 	eb->read_mirror = failed_mirror;
 	atomic_dec(&eb->io_pages);
 	if (test_and_clear_bit(EXTENT_BUFFER_READAHEAD, &eb->bflags))
-		btree_readahead_hook(eb->fs_info, eb, -EIO);
+		btree_readahead_hook(eb, -EIO);
 	return -EIO;	/* we fixed nothing */
 }
 
@@ -800,7 +798,7 @@ static void end_workqueue_bio(struct bio *bio)
 	btrfs_work_func_t func;
 
 	fs_info = end_io_wq->info;
-	end_io_wq->error = bio->bi_error;
+	end_io_wq->status = bio->bi_status;
 
 	if (bio_op(bio) == REQ_OP_WRITE) {
 		if (end_io_wq->metadata == BTRFS_WQ_ENDIO_METADATA) {
@@ -837,19 +835,19 @@ static void end_workqueue_bio(struct bio *bio)
 	btrfs_queue_work(wq, &end_io_wq->work);
 }
 
-int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
+blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
 			enum btrfs_wq_endio_type metadata)
 {
 	struct btrfs_end_io_wq *end_io_wq;
 
 	end_io_wq = kmem_cache_alloc(btrfs_end_io_wq_cache, GFP_NOFS);
 	if (!end_io_wq)
-		return -ENOMEM;
+		return BLK_STS_RESOURCE;
 
 	end_io_wq->private = bio->bi_private;
 	end_io_wq->end_io = bio->bi_end_io;
 	end_io_wq->info = info;
-	end_io_wq->error = 0;
+	end_io_wq->status = 0;
 	end_io_wq->bio = bio;
 	end_io_wq->metadata = metadata;
 
@@ -869,14 +867,14 @@ unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info)
 static void run_one_async_start(struct btrfs_work *work)
 {
 	struct async_submit_bio *async;
-	int ret;
+	blk_status_t ret;
 
 	async = container_of(work, struct  async_submit_bio, work);
-	ret = async->submit_bio_start(async->inode, async->bio,
+	ret = async->submit_bio_start(async->private_data, async->bio,
 				      async->mirror_num, async->bio_flags,
 				      async->bio_offset);
 	if (ret)
-		async->error = ret;
+		async->status = ret;
 }
 
 static void run_one_async_done(struct btrfs_work *work)
@@ -886,7 +884,7 @@ static void run_one_async_done(struct btrfs_work *work)
 	int limit;
 
 	async = container_of(work, struct  async_submit_bio, work);
-	fs_info = BTRFS_I(async->inode)->root->fs_info;
+	fs_info = async->fs_info;
 
 	limit = btrfs_async_submit_limit(fs_info);
 	limit = limit * 2 / 3;
@@ -899,13 +897,13 @@ static void run_one_async_done(struct btrfs_work *work)
 		wake_up(&fs_info->async_submit_wait);
 
 	/* If an error occurred we just want to clean up the bio and move on */
-	if (async->error) {
-		async->bio->bi_error = async->error;
+	if (async->status) {
+		async->bio->bi_status = async->status;
 		bio_endio(async->bio);
 		return;
 	}
 
-	async->submit_bio_done(async->inode, async->bio, async->mirror_num,
+	async->submit_bio_done(async->private_data, async->bio, async->mirror_num,
 			       async->bio_flags, async->bio_offset);
 }
 
@@ -917,20 +915,20 @@ static void run_one_async_free(struct btrfs_work *work)
 	kfree(async);
 }
 
-int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
-			struct bio *bio, int mirror_num,
-			unsigned long bio_flags,
-			u64 bio_offset,
-			extent_submit_bio_hook_t *submit_bio_start,
-			extent_submit_bio_hook_t *submit_bio_done)
+blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
+				 int mirror_num, unsigned long bio_flags,
+				 u64 bio_offset, void *private_data,
+				 extent_submit_bio_hook_t *submit_bio_start,
+				 extent_submit_bio_hook_t *submit_bio_done)
 {
 	struct async_submit_bio *async;
 
 	async = kmalloc(sizeof(*async), GFP_NOFS);
 	if (!async)
-		return -ENOMEM;
+		return BLK_STS_RESOURCE;
 
-	async->inode = inode;
+	async->private_data = private_data;
+	async->fs_info = fs_info;
 	async->bio = bio;
 	async->mirror_num = mirror_num;
 	async->submit_bio_start = submit_bio_start;
@@ -942,7 +940,7 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
 	async->bio_flags = bio_flags;
 	async->bio_offset = bio_offset;
 
-	async->error = 0;
+	async->status = 0;
 
 	atomic_inc(&fs_info->nr_async_submits);
 
@@ -960,12 +958,13 @@ int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
 	return 0;
 }
 
-static int btree_csum_one_bio(struct bio *bio)
+static blk_status_t btree_csum_one_bio(struct bio *bio)
 {
 	struct bio_vec *bvec;
 	struct btrfs_root *root;
 	int i, ret = 0;
 
+	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, i) {
 		root = BTRFS_I(bvec->bv_page->mapping->host)->root;
 		ret = csum_dirty_buffer(root->fs_info, bvec->bv_page);
@@ -973,12 +972,12 @@ static int btree_csum_one_bio(struct bio *bio)
 			break;
 	}
 
-	return ret;
+	return errno_to_blk_status(ret);
 }
 
-static int __btree_submit_bio_start(struct inode *inode, struct bio *bio,
-				    int mirror_num, unsigned long bio_flags,
-				    u64 bio_offset)
+static blk_status_t __btree_submit_bio_start(void *private_data, struct bio *bio,
+					     int mirror_num, unsigned long bio_flags,
+					     u64 bio_offset)
 {
 	/*
 	 * when we're called for a write, we're already in the async
@@ -987,11 +986,12 @@ static int __btree_submit_bio_start(struct inode *inode, struct bio *bio,
 	return btree_csum_one_bio(bio);
 }
 
-static int __btree_submit_bio_done(struct inode *inode, struct bio *bio,
-				 int mirror_num, unsigned long bio_flags,
-				 u64 bio_offset)
+static blk_status_t __btree_submit_bio_done(void *private_data, struct bio *bio,
+					    int mirror_num, unsigned long bio_flags,
+					    u64 bio_offset)
 {
-	int ret;
+	struct inode *inode = private_data;
+	blk_status_t ret;
 
 	/*
 	 * when we're called for a write, we're already in the async
@@ -999,13 +999,13 @@ static int __btree_submit_bio_done(struct inode *inode, struct bio *bio,
 	 */
 	ret = btrfs_map_bio(btrfs_sb(inode->i_sb), bio, mirror_num, 1);
 	if (ret) {
-		bio->bi_error = ret;
+		bio->bi_status = ret;
 		bio_endio(bio);
 	}
 	return ret;
 }
 
-static int check_async_write(struct inode *inode, unsigned long bio_flags)
+static int check_async_write(unsigned long bio_flags)
 {
 	if (bio_flags & EXTENT_BIO_TREE_LOG)
 		return 0;
@@ -1016,13 +1016,14 @@ static int check_async_write(struct inode *inode, unsigned long bio_flags)
 	return 1;
 }
 
-static int btree_submit_bio_hook(struct inode *inode, struct bio *bio,
-				 int mirror_num, unsigned long bio_flags,
-				 u64 bio_offset)
+static blk_status_t btree_submit_bio_hook(void *private_data, struct bio *bio,
+					  int mirror_num, unsigned long bio_flags,
+					  u64 bio_offset)
 {
+	struct inode *inode = private_data;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	int async = check_async_write(inode, bio_flags);
-	int ret;
+	int async = check_async_write(bio_flags);
+	blk_status_t ret;
 
 	if (bio_op(bio) != REQ_OP_WRITE) {
 		/*
@@ -1044,8 +1045,8 @@ static int btree_submit_bio_hook(struct inode *inode, struct bio *bio,
 		 * kthread helpers are used to submit writes so that
 		 * checksumming can happen in parallel across all CPUs
 		 */
-		ret = btrfs_wq_submit_bio(fs_info, inode, bio, mirror_num, 0,
-					  bio_offset,
+		ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, 0,
+					  bio_offset, private_data,
 					  __btree_submit_bio_start,
 					  __btree_submit_bio_done);
 	}
@@ -1055,7 +1056,7 @@ static int btree_submit_bio_hook(struct inode *inode, struct bio *bio,
 	return 0;
 
 out_w_error:
-	bio->bi_error = ret;
+	bio->bi_status = ret;
 	bio_endio(bio);
 	return ret;
 }
@@ -1223,10 +1224,10 @@ int btrfs_write_tree_block(struct extent_buffer *buf)
 					buf->start + buf->len - 1);
 }
 
-int btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
+void btrfs_wait_tree_block_writeback(struct extent_buffer *buf)
 {
-	return filemap_fdatawait_range(buf->pages[0]->mapping,
-				       buf->start, buf->start + buf->len - 1);
+	filemap_fdatawait_range(buf->pages[0]->mapping,
+			        buf->start, buf->start + buf->len - 1);
 }
 
 struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
@@ -1248,8 +1249,7 @@ struct extent_buffer *read_tree_block(struct btrfs_fs_info *fs_info, u64 bytenr,
 
 }
 
-void clean_tree_block(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info,
+void clean_tree_block(struct btrfs_fs_info *fs_info,
 		      struct extent_buffer *buf)
 {
 	if (btrfs_header_generation(buf) ==
@@ -1257,9 +1257,9 @@ void clean_tree_block(struct btrfs_trans_handle *trans,
 		btrfs_assert_tree_locked(buf);
 
 		if (test_and_clear_bit(EXTENT_BUFFER_DIRTY, &buf->bflags)) {
-			__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-					     -buf->len,
-					     fs_info->dirty_metadata_batch);
+			percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
+						 -buf->len,
+						 fs_info->dirty_metadata_batch);
 			/* ugh, clear_extent_buffer_dirty needs to lock the page */
 			btrfs_set_lock_blocking(buf);
 			clear_extent_buffer_dirty(buf);
@@ -1342,15 +1342,14 @@ static void __setup_root(struct btrfs_root *root, struct btrfs_fs_info *fs_info,
 	atomic_set(&root->log_writers, 0);
 	atomic_set(&root->log_batch, 0);
 	atomic_set(&root->orphan_inodes, 0);
-	atomic_set(&root->refs, 1);
+	refcount_set(&root->refs, 1);
 	atomic_set(&root->will_be_snapshoted, 0);
-	atomic_set(&root->qgroup_meta_rsv, 0);
+	atomic64_set(&root->qgroup_meta_rsv, 0);
 	root->log_transid = 0;
 	root->log_transid_committed = -1;
 	root->last_log_commit = 0;
 	if (!dummy)
-		extent_io_tree_init(&root->dirty_log_pages,
-				     fs_info->btree_inode->i_mapping);
+		extent_io_tree_init(&root->dirty_log_pages, NULL);
 
 	memset(&root->root_key, 0, sizeof(root->root_key));
 	memset(&root->root_item, 0, sizeof(root->root_item));
@@ -1800,7 +1799,7 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 	list_for_each_entry_rcu(device, &info->fs_devices->devices, dev_list) {
 		if (!device->bdev)
 			continue;
-		bdi = blk_get_backing_dev_info(device->bdev);
+		bdi = device->bdev->bd_bdi;
 		if (bdi_congested(bdi, bdi_bits)) {
 			ret = 1;
 			break;
@@ -1810,21 +1809,6 @@ static int btrfs_congested_fn(void *congested_data, int bdi_bits)
 	return ret;
 }
 
-static int setup_bdi(struct btrfs_fs_info *info, struct backing_dev_info *bdi)
-{
-	int err;
-
-	err = bdi_setup_and_register(bdi, "btrfs");
-	if (err)
-		return err;
-
-	bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
-	bdi->congested_fn	= btrfs_congested_fn;
-	bdi->congested_data	= info;
-	bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
-	return 0;
-}
-
 /*
  * called by the kthread helper functions to finally call the bio end_io
  * functions.  This is where read checksum verification actually happens
@@ -1837,7 +1821,7 @@ static void end_workqueue_fn(struct btrfs_work *work)
 	end_io_wq = container_of(work, struct btrfs_end_io_wq, work);
 	bio = end_io_wq->bio;
 
-	bio->bi_error = end_io_wq->error;
+	bio->bi_status = end_io_wq->status;
 	bio->bi_private = end_io_wq->private;
 	bio->bi_end_io = end_io_wq->end_io;
 	kmem_cache_free(btrfs_end_io_wq_cache, end_io_wq);
@@ -2207,11 +2191,9 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->delalloc_workers);
 	btrfs_destroy_workqueue(fs_info->workers);
 	btrfs_destroy_workqueue(fs_info->endio_workers);
-	btrfs_destroy_workqueue(fs_info->endio_meta_workers);
 	btrfs_destroy_workqueue(fs_info->endio_raid56_workers);
 	btrfs_destroy_workqueue(fs_info->endio_repair_workers);
 	btrfs_destroy_workqueue(fs_info->rmw_workers);
-	btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
 	btrfs_destroy_workqueue(fs_info->endio_write_workers);
 	btrfs_destroy_workqueue(fs_info->endio_freespace_worker);
 	btrfs_destroy_workqueue(fs_info->submit_workers);
@@ -2221,6 +2203,13 @@ static void btrfs_stop_all_workers(struct btrfs_fs_info *fs_info)
 	btrfs_destroy_workqueue(fs_info->flush_workers);
 	btrfs_destroy_workqueue(fs_info->qgroup_rescan_workers);
 	btrfs_destroy_workqueue(fs_info->extent_workers);
+	/*
+	 * Now that all other work queues are destroyed, we can safely destroy
+	 * the queues used for metadata I/O, since tasks from those other work
+	 * queues can do metadata I/O operations.
+	 */
+	btrfs_destroy_workqueue(fs_info->endio_meta_workers);
+	btrfs_destroy_workqueue(fs_info->endio_meta_write_workers);
 }
 
 static void free_root_extent_buffers(struct btrfs_root *root)
@@ -2321,7 +2310,7 @@ static void btrfs_init_btree_inode(struct btrfs_fs_info *fs_info)
 	inode->i_mapping->a_ops = &btree_aops;
 
 	RB_CLEAR_NODE(&BTRFS_I(inode)->rb_node);
-	extent_io_tree_init(&BTRFS_I(inode)->io_tree, inode->i_mapping);
+	extent_io_tree_init(&BTRFS_I(inode)->io_tree, inode);
 	BTRFS_I(inode)->io_tree.track_uptodate = 0;
 	extent_map_tree_init(&BTRFS_I(inode)->extent_tree);
 
@@ -2598,16 +2587,10 @@ int open_ctree(struct super_block *sb,
 		goto fail;
 	}
 
-	ret = setup_bdi(fs_info, &fs_info->bdi);
-	if (ret) {
-		err = ret;
-		goto fail_srcu;
-	}
-
 	ret = percpu_counter_init(&fs_info->dirty_metadata_bytes, 0, GFP_KERNEL);
 	if (ret) {
 		err = ret;
-		goto fail_bdi;
+		goto fail_srcu;
 	}
 	fs_info->dirty_metadata_batch = PAGE_SIZE *
 					(1 + ilog2(nr_cpu_ids));
@@ -2644,7 +2627,6 @@ int open_ctree(struct super_block *sb,
 	spin_lock_init(&fs_info->fs_roots_radix_lock);
 	spin_lock_init(&fs_info->delayed_iput_lock);
 	spin_lock_init(&fs_info->defrag_inodes_lock);
-	spin_lock_init(&fs_info->free_chunk_lock);
 	spin_lock_init(&fs_info->tree_mod_seq_lock);
 	spin_lock_init(&fs_info->super_lock);
 	spin_lock_init(&fs_info->qgroup_op_lock);
@@ -2680,12 +2662,11 @@ int open_ctree(struct super_block *sb,
 	atomic_set(&fs_info->qgroup_op_seq, 0);
 	atomic_set(&fs_info->reada_works_cnt, 0);
 	atomic64_set(&fs_info->tree_mod_seq, 0);
-	fs_info->fs_frozen = 0;
 	fs_info->sb = sb;
 	fs_info->max_inline = BTRFS_DEFAULT_MAX_INLINE;
 	fs_info->metadata_ratio = 0;
 	fs_info->defrag_inodes = RB_ROOT;
-	fs_info->free_chunk_space = 0;
+	atomic64_set(&fs_info->free_chunk_space, 0);
 	fs_info->tree_mod_log = RB_ROOT;
 	fs_info->commit_interval = BTRFS_DEFAULT_COMMIT_INTERVAL;
 	fs_info->avg_delayed_ref_runtime = NSEC_PER_SEC >> 6; /* div by 64 */
@@ -2715,7 +2696,6 @@ int open_ctree(struct super_block *sb,
 
 	sb->s_blocksize = 4096;
 	sb->s_blocksize_bits = blksize_bits(4096);
-	sb->s_bdi = &fs_info->bdi;
 
 	btrfs_init_btree_inode(fs_info);
 
@@ -2723,10 +2703,8 @@ int open_ctree(struct super_block *sb,
 	fs_info->block_group_cache_tree = RB_ROOT;
 	fs_info->first_logical_byte = (u64)-1;
 
-	extent_io_tree_init(&fs_info->freed_extents[0],
-			     fs_info->btree_inode->i_mapping);
-	extent_io_tree_init(&fs_info->freed_extents[1],
-			     fs_info->btree_inode->i_mapping);
+	extent_io_tree_init(&fs_info->freed_extents[0], NULL);
+	extent_io_tree_init(&fs_info->freed_extents[1], NULL);
 	fs_info->pinned_extents = &fs_info->freed_extents[0];
 	set_bit(BTRFS_FS_BARRIER, &fs_info->flags);
 
@@ -2802,7 +2780,7 @@ int open_ctree(struct super_block *sb,
 
 	memcpy(fs_info->fsid, fs_info->super_copy->fsid, BTRFS_FSID_SIZE);
 
-	ret = btrfs_check_super_valid(fs_info, sb->s_flags & MS_RDONLY);
+	ret = btrfs_check_super_valid(fs_info);
 	if (ret) {
 		btrfs_err(fs_info, "superblock contains fatal errors");
 		err = -EINVAL;
@@ -2912,9 +2890,12 @@ int open_ctree(struct super_block *sb,
 		goto fail_sb_buffer;
 	}
 
-	fs_info->bdi.ra_pages *= btrfs_super_num_devices(disk_super);
-	fs_info->bdi.ra_pages = max(fs_info->bdi.ra_pages,
-				    SZ_4M / PAGE_SIZE);
+	sb->s_bdi->congested_fn = btrfs_congested_fn;
+	sb->s_bdi->congested_data = fs_info;
+	sb->s_bdi->capabilities |= BDI_CAP_CGROUP_WRITEBACK;
+	sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
+	sb->s_bdi->ra_pages *= btrfs_super_num_devices(disk_super);
+	sb->s_bdi->ra_pages = max(sb->s_bdi->ra_pages, SZ_4M / PAGE_SIZE);
 
 	sb->s_blocksize = sectorsize;
 	sb->s_blocksize_bits = blksize_bits(sectorsize);
@@ -3263,7 +3244,6 @@ fail_fsdev_sysfs:
 
 fail_block_groups:
 	btrfs_put_block_group_cache(fs_info);
-	btrfs_free_block_groups(fs_info);
 
 fail_tree_roots:
 	free_root_pointers(fs_info, 1);
@@ -3271,6 +3251,7 @@ fail_tree_roots:
 
 fail_sb_buffer:
 	btrfs_stop_all_workers(fs_info);
+	btrfs_free_block_groups(fs_info);
 fail_alloc:
 fail_iput:
 	btrfs_mapping_tree_free(&fs_info->mapping_tree);
@@ -3282,8 +3263,6 @@ fail_delalloc_bytes:
 	percpu_counter_destroy(&fs_info->delalloc_bytes);
 fail_dirty_metadata_bytes:
 	percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
-fail_bdi:
-	bdi_destroy(&fs_info->bdi);
 fail_srcu:
 	cleanup_srcu_struct(&fs_info->subvol_srcu);
 fail:
@@ -3411,7 +3390,7 @@ struct buffer_head *btrfs_read_dev_super(struct block_device *bdev)
  */
 static int write_dev_supers(struct btrfs_device *device,
 			    struct btrfs_super_block *sb,
-			    int do_barriers, int wait, int max_mirrors)
+			    int wait, int max_mirrors)
 {
 	struct buffer_head *bh;
 	int i;
@@ -3450,7 +3429,7 @@ static int write_dev_supers(struct btrfs_device *device,
 			btrfs_set_super_bytenr(sb, bytenr);
 
 			crc = ~(u32)0;
-			crc = btrfs_csum_data((char *)sb +
+			crc = btrfs_csum_data((const char *)sb +
 					      BTRFS_CSUM_SIZE, crc,
 					      BTRFS_SUPER_INFO_SIZE -
 					      BTRFS_CSUM_SIZE);
@@ -3485,10 +3464,12 @@ static int write_dev_supers(struct btrfs_device *device,
 		 * we fua the first super.  The others we allow
 		 * to go down lazy.
 		 */
-		if (i == 0)
-			ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_FUA, bh);
-		else
+		if (i == 0) {
+			ret = btrfsic_submit_bh(REQ_OP_WRITE,
+						REQ_SYNC | REQ_FUA, bh);
+		} else {
 			ret = btrfsic_submit_bh(REQ_OP_WRITE, REQ_SYNC, bh);
+		}
 		if (ret)
 			errors++;
 	}
@@ -3501,64 +3482,61 @@ static int write_dev_supers(struct btrfs_device *device,
  */
 static void btrfs_end_empty_barrier(struct bio *bio)
 {
-	if (bio->bi_private)
-		complete(bio->bi_private);
-	bio_put(bio);
+	complete(bio->bi_private);
 }
 
 /*
- * trigger flushes for one the devices.  If you pass wait == 0, the flushes are
- * sent down.  With wait == 1, it waits for the previous flush.
- *
- * any device where the flush fails with eopnotsupp are flagged as not-barrier
- * capable
+ * Submit a flush request to the device if it supports it. Error handling is
+ * done in the waiting counterpart.
  */
-static int write_dev_flush(struct btrfs_device *device, int wait)
+static void write_dev_flush(struct btrfs_device *device)
 {
-	struct bio *bio;
-	int ret = 0;
+	struct request_queue *q = bdev_get_queue(device->bdev);
+	struct bio *bio = device->flush_bio;
 
-	if (device->nobarriers)
-		return 0;
+	if (!test_bit(QUEUE_FLAG_WC, &q->queue_flags))
+		return;
 
-	if (wait) {
-		bio = device->flush_bio;
-		if (!bio)
-			return 0;
+	bio_reset(bio);
+	bio->bi_end_io = btrfs_end_empty_barrier;
+	bio->bi_bdev = device->bdev;
+	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
+	init_completion(&device->flush_wait);
+	bio->bi_private = &device->flush_wait;
 
-		wait_for_completion(&device->flush_wait);
+	submit_bio(bio);
+	device->flush_bio_sent = 1;
+}
 
-		if (bio->bi_error) {
-			ret = bio->bi_error;
-			btrfs_dev_stat_inc_and_print(device,
-				BTRFS_DEV_STAT_FLUSH_ERRS);
-		}
+/*
+ * If the flush bio has been submitted by write_dev_flush, wait for it.
+ */
+static blk_status_t wait_dev_flush(struct btrfs_device *device)
+{
+	struct bio *bio = device->flush_bio;
 
-		/* drop the reference from the wait == 0 run */
-		bio_put(bio);
-		device->flush_bio = NULL;
+	if (!device->flush_bio_sent)
+		return 0;
 
-		return ret;
-	}
+	device->flush_bio_sent = 0;
+	wait_for_completion_io(&device->flush_wait);
 
-	/*
-	 * one reference for us, and we leave it for the
-	 * caller
-	 */
-	device->flush_bio = NULL;
-	bio = btrfs_io_bio_alloc(GFP_NOFS, 0);
-	if (!bio)
-		return -ENOMEM;
+	return bio->bi_status;
+}
 
-	bio->bi_end_io = btrfs_end_empty_barrier;
-	bio->bi_bdev = device->bdev;
-	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
-	init_completion(&device->flush_wait);
-	bio->bi_private = &device->flush_wait;
-	device->flush_bio = bio;
+static int check_barrier_error(struct btrfs_fs_devices *fsdevs)
+{
+	int dev_flush_error = 0;
+	struct btrfs_device *dev;
 
-	bio_get(bio);
-	btrfsic_submit_bio(bio);
+	list_for_each_entry_rcu(dev, &fsdevs->devices, dev_list) {
+		if (!dev->bdev || dev->last_flush_error)
+			dev_flush_error++;
+	}
+
+	if (dev_flush_error >
+	    fsdevs->fs_info->num_tolerated_disk_barrier_failures)
+		return -EIO;
 
 	return 0;
 }
@@ -3571,25 +3549,21 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 {
 	struct list_head *head;
 	struct btrfs_device *dev;
-	int errors_send = 0;
 	int errors_wait = 0;
-	int ret;
+	blk_status_t ret;
 
 	/* send down all the barriers */
 	head = &info->fs_devices->devices;
 	list_for_each_entry_rcu(dev, head, dev_list) {
 		if (dev->missing)
 			continue;
-		if (!dev->bdev) {
-			errors_send++;
+		if (!dev->bdev)
 			continue;
-		}
 		if (!dev->in_fs_metadata || !dev->writeable)
 			continue;
 
-		ret = write_dev_flush(dev, 0);
-		if (ret)
-			errors_send++;
+		write_dev_flush(dev);
+		dev->last_flush_error = 0;
 	}
 
 	/* wait for all the barriers */
@@ -3603,13 +3577,23 @@ static int barrier_all_devices(struct btrfs_fs_info *info)
 		if (!dev->in_fs_metadata || !dev->writeable)
 			continue;
 
-		ret = write_dev_flush(dev, 1);
-		if (ret)
+		ret = wait_dev_flush(dev);
+		if (ret) {
+			dev->last_flush_error = ret;
+			btrfs_dev_stat_inc_and_print(dev,
+					BTRFS_DEV_STAT_FLUSH_ERRS);
 			errors_wait++;
+		}
+	}
+
+	if (errors_wait) {
+		/*
+		 * At some point we need the status of all disks
+		 * to arrive at the volume status. So error checking
+		 * is being pushed to a separate loop.
+		 */
+		return check_barrier_error(info->fs_devices);
 	}
-	if (errors_send > info->num_tolerated_disk_barrier_failures ||
-	    errors_wait > info->num_tolerated_disk_barrier_failures)
-		return -EIO;
 	return 0;
 }
 
@@ -3696,7 +3680,7 @@ int btrfs_calc_num_tolerated_disk_barrier_failures(
 	return num_tolerated_disk_barrier_failures;
 }
 
-static int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
+int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 {
 	struct list_head *head;
 	struct btrfs_device *dev;
@@ -3753,7 +3737,7 @@ static int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 		flags = btrfs_super_flags(sb);
 		btrfs_set_super_flags(sb, flags | BTRFS_HEADER_FLAG_WRITTEN);
 
-		ret = write_dev_supers(dev, sb, do_barriers, 0, max_mirrors);
+		ret = write_dev_supers(dev, sb, 0, max_mirrors);
 		if (ret)
 			total_errors++;
 	}
@@ -3776,7 +3760,7 @@ static int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 		if (!dev->in_fs_metadata || !dev->writeable)
 			continue;
 
-		ret = write_dev_supers(dev, sb, do_barriers, 1, max_mirrors);
+		ret = write_dev_supers(dev, sb, 1, max_mirrors);
 		if (ret)
 			total_errors++;
 	}
@@ -3790,12 +3774,6 @@ static int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors)
 	return 0;
 }
 
-int write_ctree_super(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info, int max_mirrors)
-{
-	return write_all_supers(fs_info, max_mirrors);
-}
-
 /* Drop a fs root from the radix tree and free it. */
 void btrfs_drop_and_free_fs_root(struct btrfs_fs_info *fs_info,
 				  struct btrfs_root *root)
@@ -3985,8 +3963,6 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 
 	btrfs_put_block_group_cache(fs_info);
 
-	btrfs_free_block_groups(fs_info);
-
 	/*
 	 * we must make sure there is not any read request to
 	 * submit after we stopping all workers.
@@ -3994,6 +3970,8 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	invalidate_inode_pages2(fs_info->btree_inode->i_mapping);
 	btrfs_stop_all_workers(fs_info);
 
+	btrfs_free_block_groups(fs_info);
+
 	clear_bit(BTRFS_FS_OPEN, &fs_info->flags);
 	free_root_pointers(fs_info, 1);
 
@@ -4010,7 +3988,6 @@ void close_ctree(struct btrfs_fs_info *fs_info)
 	percpu_counter_destroy(&fs_info->dirty_metadata_bytes);
 	percpu_counter_destroy(&fs_info->delalloc_bytes);
 	percpu_counter_destroy(&fs_info->bio_counter);
-	bdi_destroy(&fs_info->bdi);
 	cleanup_srcu_struct(&fs_info->subvol_srcu);
 
 	btrfs_free_stripe_hash_table(fs_info);
@@ -4071,9 +4048,9 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf)
 			buf->start, transid, fs_info->generation);
 	was_dirty = set_extent_buffer_dirty(buf);
 	if (!was_dirty)
-		__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-				     buf->len,
-				     fs_info->dirty_metadata_batch);
+		percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
+					 buf->len,
+					 fs_info->dirty_metadata_batch);
 #ifdef CONFIG_BTRFS_FS_CHECK_INTEGRITY
 	if (btrfs_header_level(buf) == 0 && check_leaf(root, buf)) {
 		btrfs_print_leaf(fs_info, buf);
@@ -4122,8 +4099,7 @@ int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid)
 	return btree_read_extent_buffer_pages(fs_info, buf, parent_transid);
 }
 
-static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info,
-			      int read_only)
+static int btrfs_check_super_valid(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_super_block *sb = fs_info->super_copy;
 	u64 nodesize = btrfs_super_nodesize(sb);
@@ -4347,7 +4323,7 @@ static int btrfs_destroy_delayed_refs(struct btrfs_transaction *trans,
 		head = rb_entry(node, struct btrfs_delayed_ref_head,
 				href_node);
 		if (!mutex_trylock(&head->mutex)) {
-			atomic_inc(&head->node.refs);
+			refcount_inc(&head->node.refs);
 			spin_unlock(&delayed_refs->lock);
 
 			mutex_lock(&head->mutex);
@@ -4601,11 +4577,6 @@ void btrfs_cleanup_one_transaction(struct btrfs_transaction *cur_trans,
 
 	cur_trans->state =TRANS_STATE_COMPLETED;
 	wake_up(&cur_trans->commit_wait);
-
-	/*
-	memset(cur_trans, 0, sizeof(*cur_trans));
-	kmem_cache_free(btrfs_transaction_cachep, cur_trans);
-	*/
 }
 
 static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
@@ -4619,7 +4590,7 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 		t = list_first_entry(&fs_info->trans_list,
 				     struct btrfs_transaction, list);
 		if (t->state >= TRANS_STATE_COMMIT_START) {
-			atomic_inc(&t->use_count);
+			refcount_inc(&t->use_count);
 			spin_unlock(&fs_info->trans_lock);
 			btrfs_wait_for_commit(fs_info, t->transid);
 			btrfs_put_transaction(t);
@@ -4661,10 +4632,21 @@ static int btrfs_cleanup_transaction(struct btrfs_fs_info *fs_info)
 	return 0;
 }
 
+static struct btrfs_fs_info *btree_fs_info(void *private_data)
+{
+	struct inode *inode = private_data;
+	return btrfs_sb(inode->i_sb);
+}
+
 static const struct extent_io_ops btree_extent_io_ops = {
-	.readpage_end_io_hook = btree_readpage_end_io_hook,
-	.readpage_io_failed_hook = btree_io_failed_hook,
+	/* mandatory callbacks */
 	.submit_bio_hook = btree_submit_bio_hook,
+	.readpage_end_io_hook = btree_readpage_end_io_hook,
 	/* note we're sharing with inode.c for the merge bio hook */
 	.merge_bio_hook = btrfs_merge_bio_hook,
+	.readpage_io_failed_hook = btree_io_failed_hook,
+	.set_range_writeback = btrfs_set_range_writeback,
+	.tree_fs_info = btree_fs_info,
+
+	/* optional callbacks */
 };
diff --git a/fs/btrfs/disk-io.h b/fs/btrfs/disk-io.h
index 44dcd9af6b7c..0a634d3ffc16 100644
--- a/fs/btrfs/disk-io.h
+++ b/fs/btrfs/disk-io.h
@@ -52,14 +52,12 @@ int reada_tree_block_flagged(struct btrfs_fs_info *fs_info, u64 bytenr,
 struct extent_buffer *btrfs_find_create_tree_block(
 						struct btrfs_fs_info *fs_info,
 						u64 bytenr);
-void clean_tree_block(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info, struct extent_buffer *buf);
+void clean_tree_block(struct btrfs_fs_info *fs_info, struct extent_buffer *buf);
 int open_ctree(struct super_block *sb,
 	       struct btrfs_fs_devices *fs_devices,
 	       char *options);
 void close_ctree(struct btrfs_fs_info *fs_info);
-int write_ctree_super(struct btrfs_trans_handle *trans,
-		      struct btrfs_fs_info *fs_info, int max_mirrors);
+int write_all_supers(struct btrfs_fs_info *fs_info, int max_mirrors);
 struct buffer_head *btrfs_read_dev_super(struct block_device *bdev);
 int btrfs_read_dev_one_super(struct block_device *bdev, int copy_num,
 			struct buffer_head **bh_ret);
@@ -103,14 +101,14 @@ struct btrfs_root *btrfs_alloc_dummy_root(struct btrfs_fs_info *fs_info);
  */
 static inline struct btrfs_root *btrfs_grab_fs_root(struct btrfs_root *root)
 {
-	if (atomic_inc_not_zero(&root->refs))
+	if (refcount_inc_not_zero(&root->refs))
 		return root;
 	return NULL;
 }
 
 static inline void btrfs_put_fs_root(struct btrfs_root *root)
 {
-	if (atomic_dec_and_test(&root->refs))
+	if (refcount_dec_and_test(&root->refs))
 		kfree(root);
 }
 
@@ -118,18 +116,18 @@ void btrfs_mark_buffer_dirty(struct extent_buffer *buf);
 int btrfs_buffer_uptodate(struct extent_buffer *buf, u64 parent_transid,
 			  int atomic);
 int btrfs_read_buffer(struct extent_buffer *buf, u64 parent_transid);
-u32 btrfs_csum_data(char *data, u32 seed, size_t len);
+u32 btrfs_csum_data(const char *data, u32 seed, size_t len);
 void btrfs_csum_final(u32 crc, u8 *result);
-int btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
+blk_status_t btrfs_bio_wq_end_io(struct btrfs_fs_info *info, struct bio *bio,
 			enum btrfs_wq_endio_type metadata);
-int btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct inode *inode,
-			struct bio *bio, int mirror_num,
-			unsigned long bio_flags, u64 bio_offset,
+blk_status_t btrfs_wq_submit_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
+			int mirror_num, unsigned long bio_flags,
+			u64 bio_offset, void *private_data,
 			extent_submit_bio_hook_t *submit_bio_start,
 			extent_submit_bio_hook_t *submit_bio_done);
 unsigned long btrfs_async_submit_limit(struct btrfs_fs_info *info);
 int btrfs_write_tree_block(struct extent_buffer *buf);
-int btrfs_wait_tree_block_writeback(struct extent_buffer *buf);
+void btrfs_wait_tree_block_writeback(struct extent_buffer *buf);
 int btrfs_init_log_root_tree(struct btrfs_trans_handle *trans,
 			     struct btrfs_fs_info *fs_info);
 int btrfs_add_log_tree(struct btrfs_trans_handle *trans,
diff --git a/fs/btrfs/export.c b/fs/btrfs/export.c
index 340d90751263..fa66980726c9 100644
--- a/fs/btrfs/export.c
+++ b/fs/btrfs/export.c
@@ -30,7 +30,7 @@ static int btrfs_encode_fh(struct inode *inode, u32 *fh, int *max_len,
 	len  = BTRFS_FID_SIZE_NON_CONNECTABLE;
 	type = FILEID_BTRFS_WITHOUT_PARENT;
 
-	fid->objectid = btrfs_ino(inode);
+	fid->objectid = btrfs_ino(BTRFS_I(inode));
 	fid->root_objectid = BTRFS_I(inode)->root->objectid;
 	fid->gen = inode->i_generation;
 
@@ -166,13 +166,13 @@ static struct dentry *btrfs_get_parent(struct dentry *child)
 	if (!path)
 		return ERR_PTR(-ENOMEM);
 
-	if (btrfs_ino(dir) == BTRFS_FIRST_FREE_OBJECTID) {
+	if (btrfs_ino(BTRFS_I(dir)) == BTRFS_FIRST_FREE_OBJECTID) {
 		key.objectid = root->root_key.objectid;
 		key.type = BTRFS_ROOT_BACKREF_KEY;
 		key.offset = (u64)-1;
 		root = fs_info->tree_root;
 	} else {
-		key.objectid = btrfs_ino(dir);
+		key.objectid = btrfs_ino(BTRFS_I(dir));
 		key.type = BTRFS_INODE_REF_KEY;
 		key.offset = (u64)-1;
 	}
@@ -235,13 +235,10 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 	int ret;
 	u64 ino;
 
-	if (!dir || !inode)
-		return -EINVAL;
-
 	if (!S_ISDIR(dir->i_mode))
 		return -EINVAL;
 
-	ino = btrfs_ino(inode);
+	ino = btrfs_ino(BTRFS_I(inode));
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -255,7 +252,7 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 		root = fs_info->tree_root;
 	} else {
 		key.objectid = ino;
-		key.offset = btrfs_ino(dir);
+		key.offset = btrfs_ino(BTRFS_I(dir));
 		key.type = BTRFS_INODE_REF_KEY;
 	}
 
@@ -285,6 +282,11 @@ static int btrfs_get_name(struct dentry *parent, char *name,
 		name_len = btrfs_inode_ref_name_len(leaf, iref);
 	}
 
+	ret = btrfs_is_name_len_valid(leaf, path->slots[0], name_ptr, name_len);
+	if (!ret) {
+		btrfs_free_path(path);
+		return -EIO;
+	}
 	read_extent_buffer(leaf, name, name_ptr, name_len);
 	btrfs_free_path(path);
 
diff --git a/fs/btrfs/extent-tree.c b/fs/btrfs/extent-tree.c
index dcd2e798767e..375f8c728d91 100644
--- a/fs/btrfs/extent-tree.c
+++ b/fs/btrfs/extent-tree.c
@@ -16,6 +16,7 @@
  * Boston, MA 021110-1307, USA.
  */
 #include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/pagemap.h>
 #include <linux/writeback.h>
 #include <linux/blkdev.h>
@@ -96,10 +97,11 @@ static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
 				     u64 num_bytes, int delalloc);
 static int block_rsv_use_bytes(struct btrfs_block_rsv *block_rsv,
 			       u64 num_bytes);
-static int __reserve_metadata_bytes(struct btrfs_root *root,
+static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 				    struct btrfs_space_info *space_info,
 				    u64 orig_bytes,
-				    enum btrfs_reserve_flush_enum flush);
+				    enum btrfs_reserve_flush_enum flush,
+				    bool system_chunk);
 static void space_info_add_new_bytes(struct btrfs_fs_info *fs_info,
 				     struct btrfs_space_info *space_info,
 				     u64 num_bytes);
@@ -130,6 +132,16 @@ void btrfs_put_block_group(struct btrfs_block_group_cache *cache)
 	if (atomic_dec_and_test(&cache->count)) {
 		WARN_ON(cache->pinned > 0);
 		WARN_ON(cache->reserved > 0);
+
+		/*
+		 * If not empty, someone is still holding mutex of
+		 * full_stripe_lock, which can only be released by caller.
+		 * And it will definitely cause use-after-free when caller
+		 * tries to release full stripe lock.
+		 *
+		 * No better way to resolve, but only to warn.
+		 */
+		WARN_ON(!RB_EMPTY_ROOT(&cache->full_stripe_locks_root.root));
 		kfree(cache->free_space_ctl);
 		kfree(cache);
 	}
@@ -315,14 +327,14 @@ get_caching_control(struct btrfs_block_group_cache *cache)
 	}
 
 	ctl = cache->caching_ctl;
-	atomic_inc(&ctl->count);
+	refcount_inc(&ctl->count);
 	spin_unlock(&cache->lock);
 	return ctl;
 }
 
 static void put_caching_control(struct btrfs_caching_control *ctl)
 {
-	if (atomic_dec_and_test(&ctl->count))
+	if (refcount_dec_and_test(&ctl->count))
 		kfree(ctl);
 }
 
@@ -598,7 +610,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 	init_waitqueue_head(&caching_ctl->wait);
 	caching_ctl->block_group = cache;
 	caching_ctl->progress = cache->key.objectid;
-	atomic_set(&caching_ctl->count, 1);
+	refcount_set(&caching_ctl->count, 1);
 	btrfs_init_work(&caching_ctl->work, btrfs_cache_helper,
 			caching_thread, NULL, NULL);
 
@@ -619,7 +631,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 		struct btrfs_caching_control *ctl;
 
 		ctl = cache->caching_ctl;
-		atomic_inc(&ctl->count);
+		refcount_inc(&ctl->count);
 		prepare_to_wait(&ctl->wait, &wait, TASK_UNINTERRUPTIBLE);
 		spin_unlock(&cache->lock);
 
@@ -706,7 +718,7 @@ static int cache_block_group(struct btrfs_block_group_cache *cache,
 	}
 
 	down_write(&fs_info->commit_root_sem);
-	atomic_inc(&caching_ctl->count);
+	refcount_inc(&caching_ctl->count);
 	list_add_tail(&caching_ctl->list, &fs_info->caching_block_groups);
 	up_write(&fs_info->commit_root_sem);
 
@@ -755,6 +767,26 @@ static struct btrfs_space_info *__find_space_info(struct btrfs_fs_info *info,
 	return NULL;
 }
 
+static void add_pinned_bytes(struct btrfs_fs_info *fs_info, s64 num_bytes,
+			     u64 owner, u64 root_objectid)
+{
+	struct btrfs_space_info *space_info;
+	u64 flags;
+
+	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
+		if (root_objectid == BTRFS_CHUNK_TREE_OBJECTID)
+			flags = BTRFS_BLOCK_GROUP_SYSTEM;
+		else
+			flags = BTRFS_BLOCK_GROUP_METADATA;
+	} else {
+		flags = BTRFS_BLOCK_GROUP_DATA;
+	}
+
+	space_info = __find_space_info(fs_info, flags);
+	ASSERT(space_info);
+	percpu_counter_add(&space_info->total_bytes_pinned, num_bytes);
+}
+
 /*
  * after adding space to the filesystem, we need to clear the full flags
  * on all the space infos.
@@ -888,10 +920,10 @@ search_again:
 
 	delayed_refs = &trans->transaction->delayed_refs;
 	spin_lock(&delayed_refs->lock);
-	head = btrfs_find_delayed_ref_head(trans, bytenr);
+	head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
 	if (head) {
 		if (!mutex_trylock(&head->mutex)) {
-			atomic_inc(&head->node.refs);
+			refcount_inc(&head->node.refs);
 			spin_unlock(&delayed_refs->lock);
 
 			btrfs_release_path(path);
@@ -1035,10 +1067,11 @@ out_free:
 
 #ifdef BTRFS_COMPAT_EXTENT_TREE_V0
 static int convert_extent_item_v0(struct btrfs_trans_handle *trans,
-				  struct btrfs_root *root,
+				  struct btrfs_fs_info *fs_info,
 				  struct btrfs_path *path,
 				  u64 owner, u32 extra_size)
 {
+	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_extent_item *item;
 	struct btrfs_extent_item_v0 *ei0;
 	struct btrfs_extent_ref_v0 *ref0;
@@ -1092,7 +1125,7 @@ static int convert_extent_item_v0(struct btrfs_trans_handle *trans,
 		return ret;
 	BUG_ON(ret); /* Corruption */
 
-	btrfs_extend_item(root->fs_info, path, new_size);
+	btrfs_extend_item(fs_info, path, new_size);
 
 	leaf = path->nodes[0];
 	item = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
@@ -1151,12 +1184,13 @@ static int match_extent_data_ref(struct extent_buffer *leaf,
 }
 
 static noinline int lookup_extent_data_ref(struct btrfs_trans_handle *trans,
-					   struct btrfs_root *root,
+					   struct btrfs_fs_info *fs_info,
 					   struct btrfs_path *path,
 					   u64 bytenr, u64 parent,
 					   u64 root_objectid,
 					   u64 owner, u64 offset)
 {
+	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_key key;
 	struct btrfs_extent_data_ref *ref;
 	struct extent_buffer *leaf;
@@ -1238,12 +1272,13 @@ fail:
 }
 
 static noinline int insert_extent_data_ref(struct btrfs_trans_handle *trans,
-					   struct btrfs_root *root,
+					   struct btrfs_fs_info *fs_info,
 					   struct btrfs_path *path,
 					   u64 bytenr, u64 parent,
 					   u64 root_objectid, u64 owner,
 					   u64 offset, int refs_to_add)
 {
+	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_key key;
 	struct extent_buffer *leaf;
 	u32 size;
@@ -1317,7 +1352,7 @@ fail:
 }
 
 static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
-					   struct btrfs_root *root,
+					   struct btrfs_fs_info *fs_info,
 					   struct btrfs_path *path,
 					   int refs_to_drop, int *last_ref)
 {
@@ -1354,7 +1389,7 @@ static noinline int remove_extent_data_ref(struct btrfs_trans_handle *trans,
 	num_refs -= refs_to_drop;
 
 	if (num_refs == 0) {
-		ret = btrfs_del_item(trans, root, path);
+		ret = btrfs_del_item(trans, fs_info->extent_root, path);
 		*last_ref = 1;
 	} else {
 		if (key.type == BTRFS_EXTENT_DATA_REF_KEY)
@@ -1416,11 +1451,12 @@ static noinline u32 extent_data_ref_count(struct btrfs_path *path,
 }
 
 static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
-					  struct btrfs_root *root,
+					  struct btrfs_fs_info *fs_info,
 					  struct btrfs_path *path,
 					  u64 bytenr, u64 parent,
 					  u64 root_objectid)
 {
+	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_key key;
 	int ret;
 
@@ -1449,7 +1485,7 @@ static noinline int lookup_tree_block_ref(struct btrfs_trans_handle *trans,
 }
 
 static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
-					  struct btrfs_root *root,
+					  struct btrfs_fs_info *fs_info,
 					  struct btrfs_path *path,
 					  u64 bytenr, u64 parent,
 					  u64 root_objectid)
@@ -1466,7 +1502,8 @@ static noinline int insert_tree_block_ref(struct btrfs_trans_handle *trans,
 		key.offset = root_objectid;
 	}
 
-	ret = btrfs_insert_empty_item(trans, root, path, &key, 0);
+	ret = btrfs_insert_empty_item(trans, fs_info->extent_root,
+				      path, &key, 0);
 	btrfs_release_path(path);
 	return ret;
 }
@@ -1524,14 +1561,14 @@ static int find_next_key(struct btrfs_path *path, int level,
  */
 static noinline_for_stack
 int lookup_inline_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_root *root,
+				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref **ref_ret,
 				 u64 bytenr, u64 num_bytes,
 				 u64 parent, u64 root_objectid,
 				 u64 owner, u64 offset, int insert)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_key key;
 	struct extent_buffer *leaf;
 	struct btrfs_extent_item *ei;
@@ -1614,7 +1651,7 @@ again:
 			err = -ENOENT;
 			goto out;
 		}
-		ret = convert_extent_item_v0(trans, root, path, owner,
+		ret = convert_extent_item_v0(trans, fs_info, path, owner,
 					     extra_size);
 		if (ret < 0) {
 			err = ret;
@@ -1716,7 +1753,7 @@ out:
  * helper to add new inline back ref
  */
 static noinline_for_stack
-void setup_inline_extent_backref(struct btrfs_root *root,
+void setup_inline_extent_backref(struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref *iref,
 				 u64 parent, u64 root_objectid,
@@ -1739,7 +1776,7 @@ void setup_inline_extent_backref(struct btrfs_root *root,
 	type = extent_ref_type(parent, owner);
 	size = btrfs_extent_inline_ref_size(type);
 
-	btrfs_extend_item(root->fs_info, path, size);
+	btrfs_extend_item(fs_info, path, size);
 
 	ei = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_extent_item);
 	refs = btrfs_extent_refs(leaf, ei);
@@ -1777,7 +1814,7 @@ void setup_inline_extent_backref(struct btrfs_root *root,
 }
 
 static int lookup_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_root *root,
+				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref **ref_ret,
 				 u64 bytenr, u64 num_bytes, u64 parent,
@@ -1785,7 +1822,7 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
 {
 	int ret;
 
-	ret = lookup_inline_extent_backref(trans, root, path, ref_ret,
+	ret = lookup_inline_extent_backref(trans, fs_info, path, ref_ret,
 					   bytenr, num_bytes, parent,
 					   root_objectid, owner, offset, 0);
 	if (ret != -ENOENT)
@@ -1795,11 +1832,12 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
 	*ref_ret = NULL;
 
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		ret = lookup_tree_block_ref(trans, root, path, bytenr, parent,
-					    root_objectid);
+		ret = lookup_tree_block_ref(trans, fs_info, path, bytenr,
+					    parent, root_objectid);
 	} else {
-		ret = lookup_extent_data_ref(trans, root, path, bytenr, parent,
-					     root_objectid, owner, offset);
+		ret = lookup_extent_data_ref(trans, fs_info, path, bytenr,
+					     parent, root_objectid, owner,
+					     offset);
 	}
 	return ret;
 }
@@ -1808,7 +1846,7 @@ static int lookup_extent_backref(struct btrfs_trans_handle *trans,
  * helper to update/remove inline back ref
  */
 static noinline_for_stack
-void update_inline_extent_backref(struct btrfs_root *root,
+void update_inline_extent_backref(struct btrfs_fs_info *fs_info,
 				  struct btrfs_path *path,
 				  struct btrfs_extent_inline_ref *iref,
 				  int refs_to_mod,
@@ -1866,14 +1904,14 @@ void update_inline_extent_backref(struct btrfs_root *root,
 			memmove_extent_buffer(leaf, ptr, ptr + size,
 					      end - ptr - size);
 		item_size -= size;
-		btrfs_truncate_item(root->fs_info, path, item_size, 1);
+		btrfs_truncate_item(fs_info, path, item_size, 1);
 	}
 	btrfs_mark_buffer_dirty(leaf);
 }
 
 static noinline_for_stack
 int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_root *root,
+				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 u64 bytenr, u64 num_bytes, u64 parent,
 				 u64 root_objectid, u64 owner,
@@ -1883,15 +1921,15 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
 	struct btrfs_extent_inline_ref *iref;
 	int ret;
 
-	ret = lookup_inline_extent_backref(trans, root, path, &iref,
+	ret = lookup_inline_extent_backref(trans, fs_info, path, &iref,
 					   bytenr, num_bytes, parent,
 					   root_objectid, owner, offset, 1);
 	if (ret == 0) {
 		BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID);
-		update_inline_extent_backref(root, path, iref,
+		update_inline_extent_backref(fs_info, path, iref,
 					     refs_to_add, extent_op, NULL);
 	} else if (ret == -ENOENT) {
-		setup_inline_extent_backref(root, path, iref, parent,
+		setup_inline_extent_backref(fs_info, path, iref, parent,
 					    root_objectid, owner, offset,
 					    refs_to_add, extent_op);
 		ret = 0;
@@ -1900,7 +1938,7 @@ int insert_inline_extent_backref(struct btrfs_trans_handle *trans,
 }
 
 static int insert_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_root *root,
+				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 u64 bytenr, u64 parent, u64 root_objectid,
 				 u64 owner, u64 offset, int refs_to_add)
@@ -1908,10 +1946,10 @@ static int insert_extent_backref(struct btrfs_trans_handle *trans,
 	int ret;
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
 		BUG_ON(refs_to_add != 1);
-		ret = insert_tree_block_ref(trans, root, path, bytenr,
+		ret = insert_tree_block_ref(trans, fs_info, path, bytenr,
 					    parent, root_objectid);
 	} else {
-		ret = insert_extent_data_ref(trans, root, path, bytenr,
+		ret = insert_extent_data_ref(trans, fs_info, path, bytenr,
 					     parent, root_objectid,
 					     owner, offset, refs_to_add);
 	}
@@ -1919,7 +1957,7 @@ static int insert_extent_backref(struct btrfs_trans_handle *trans,
 }
 
 static int remove_extent_backref(struct btrfs_trans_handle *trans,
-				 struct btrfs_root *root,
+				 struct btrfs_fs_info *fs_info,
 				 struct btrfs_path *path,
 				 struct btrfs_extent_inline_ref *iref,
 				 int refs_to_drop, int is_data, int *last_ref)
@@ -1928,14 +1966,14 @@ static int remove_extent_backref(struct btrfs_trans_handle *trans,
 
 	BUG_ON(!is_data && refs_to_drop != 1);
 	if (iref) {
-		update_inline_extent_backref(root, path, iref,
+		update_inline_extent_backref(fs_info, path, iref,
 					     -refs_to_drop, NULL, last_ref);
 	} else if (is_data) {
-		ret = remove_extent_data_ref(trans, root, path, refs_to_drop,
+		ret = remove_extent_data_ref(trans, fs_info, path, refs_to_drop,
 					     last_ref);
 	} else {
 		*last_ref = 1;
-		ret = btrfs_del_item(trans, root, path);
+		ret = btrfs_del_item(trans, fs_info->extent_root, path);
 	}
 	return ret;
 }
@@ -2075,6 +2113,7 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 			 u64 bytenr, u64 num_bytes, u64 parent,
 			 u64 root_objectid, u64 owner, u64 offset)
 {
+	int old_ref_mod, new_ref_mod;
 	int ret;
 
 	BUG_ON(owner < BTRFS_FIRST_FREE_OBJECTID &&
@@ -2082,15 +2121,21 @@ int btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 
 	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
 		ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr,
-					num_bytes,
-					parent, root_objectid, (int)owner,
-					BTRFS_ADD_DELAYED_REF, NULL);
+						 num_bytes, parent,
+						 root_objectid, (int)owner,
+						 BTRFS_ADD_DELAYED_REF, NULL,
+						 &old_ref_mod, &new_ref_mod);
 	} else {
 		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
-					num_bytes, parent, root_objectid,
-					owner, offset, 0,
-					BTRFS_ADD_DELAYED_REF, NULL);
+						 num_bytes, parent,
+						 root_objectid, owner, offset,
+						 0, BTRFS_ADD_DELAYED_REF,
+						 &old_ref_mod, &new_ref_mod);
 	}
+
+	if (ret == 0 && old_ref_mod < 0 && new_ref_mod >= 0)
+		add_pinned_bytes(fs_info, -num_bytes, owner, root_objectid);
+
 	return ret;
 }
 
@@ -2117,9 +2162,9 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	/* this will setup the path even if it fails to insert the back ref */
-	ret = insert_inline_extent_backref(trans, fs_info->extent_root, path,
-					   bytenr, num_bytes, parent,
-					   root_objectid, owner, offset,
+	ret = insert_inline_extent_backref(trans, fs_info, path, bytenr,
+					   num_bytes, parent, root_objectid,
+					   owner, offset,
 					   refs_to_add, extent_op);
 	if ((ret < 0 && ret != -EAGAIN) || !ret)
 		goto out;
@@ -2143,9 +2188,8 @@ static int __btrfs_inc_extent_ref(struct btrfs_trans_handle *trans,
 	path->reada = READA_FORWARD;
 	path->leave_spinning = 1;
 	/* now insert the actual backref */
-	ret = insert_extent_backref(trans, fs_info->extent_root,
-				    path, bytenr, parent, root_objectid,
-				    owner, offset, refs_to_add);
+	ret = insert_extent_backref(trans, fs_info, path, bytenr, parent,
+				    root_objectid, owner, offset, refs_to_add);
 	if (ret)
 		btrfs_abort_transaction(trans, ret);
 out:
@@ -2290,8 +2334,7 @@ again:
 	item_size = btrfs_item_size_nr(leaf, path->slots[0]);
 #ifdef BTRFS_COMPAT_EXTENT_TREE_V0
 	if (item_size < sizeof(*ei)) {
-		ret = convert_extent_item_v0(trans, fs_info->extent_root,
-					     path, (u64)-1, 0);
+		ret = convert_extent_item_v0(trans, fs_info, path, (u64)-1, 0);
 		if (ret < 0) {
 			err = ret;
 			goto out;
@@ -2396,6 +2439,16 @@ static int run_one_delayed_ref(struct btrfs_trans_handle *trans,
 		head = btrfs_delayed_node_to_head(node);
 		trace_run_delayed_ref_head(fs_info, node, head, node->action);
 
+		if (head->total_ref_mod < 0) {
+			struct btrfs_block_group_cache *cache;
+
+			cache = btrfs_lookup_block_group(fs_info, node->bytenr);
+			ASSERT(cache);
+			percpu_counter_add(&cache->space_info->total_bytes_pinned,
+					   -node->num_bytes);
+			btrfs_put_block_group(cache);
+		}
+
 		if (insert_reserved) {
 			btrfs_pin_extent(fs_info, node->bytenr,
 					 node->num_bytes, 1);
@@ -2975,7 +3028,7 @@ again:
 				struct btrfs_delayed_ref_node *ref;
 
 				ref = &head->node;
-				atomic_inc(&ref->refs);
+				refcount_inc(&ref->refs);
 
 				spin_unlock(&delayed_refs->lock);
 				/*
@@ -2998,7 +3051,6 @@ again:
 		goto again;
 	}
 out:
-	assert_qgroups_uptodate(trans);
 	trans->can_flush_pending_bgs = can_flush_pending_bgs;
 	return 0;
 }
@@ -3028,8 +3080,7 @@ int btrfs_set_disk_extent_flags(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-static noinline int check_delayed_ref(struct btrfs_trans_handle *trans,
-				      struct btrfs_root *root,
+static noinline int check_delayed_ref(struct btrfs_root *root,
 				      struct btrfs_path *path,
 				      u64 objectid, u64 offset, u64 bytenr)
 {
@@ -3037,18 +3088,23 @@ static noinline int check_delayed_ref(struct btrfs_trans_handle *trans,
 	struct btrfs_delayed_ref_node *ref;
 	struct btrfs_delayed_data_ref *data_ref;
 	struct btrfs_delayed_ref_root *delayed_refs;
+	struct btrfs_transaction *cur_trans;
 	int ret = 0;
 
-	delayed_refs = &trans->transaction->delayed_refs;
+	cur_trans = root->fs_info->running_transaction;
+	if (!cur_trans)
+		return 0;
+
+	delayed_refs = &cur_trans->delayed_refs;
 	spin_lock(&delayed_refs->lock);
-	head = btrfs_find_delayed_ref_head(trans, bytenr);
+	head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
 	if (!head) {
 		spin_unlock(&delayed_refs->lock);
 		return 0;
 	}
 
 	if (!mutex_trylock(&head->mutex)) {
-		atomic_inc(&head->node.refs);
+		refcount_inc(&head->node.refs);
 		spin_unlock(&delayed_refs->lock);
 
 		btrfs_release_path(path);
@@ -3090,8 +3146,7 @@ static noinline int check_delayed_ref(struct btrfs_trans_handle *trans,
 	return ret;
 }
 
-static noinline int check_committed_ref(struct btrfs_trans_handle *trans,
-					struct btrfs_root *root,
+static noinline int check_committed_ref(struct btrfs_root *root,
 					struct btrfs_path *path,
 					u64 objectid, u64 offset, u64 bytenr)
 {
@@ -3162,9 +3217,8 @@ out:
 	return ret;
 }
 
-int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
-			  struct btrfs_root *root,
-			  u64 objectid, u64 offset, u64 bytenr)
+int btrfs_cross_ref_exist(struct btrfs_root *root, u64 objectid, u64 offset,
+			  u64 bytenr)
 {
 	struct btrfs_path *path;
 	int ret;
@@ -3175,12 +3229,12 @@ int btrfs_cross_ref_exist(struct btrfs_trans_handle *trans,
 		return -ENOENT;
 
 	do {
-		ret = check_committed_ref(trans, root, path, objectid,
+		ret = check_committed_ref(root, path, objectid,
 					  offset, bytenr);
 		if (ret && ret != -ENOENT)
 			goto out;
 
-		ret2 = check_delayed_ref(trans, root, path, objectid,
+		ret2 = check_delayed_ref(root, path, objectid,
 					 offset, bytenr);
 	} while (ret2 == -EAGAIN);
 
@@ -3348,6 +3402,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 	struct btrfs_fs_info *fs_info = block_group->fs_info;
 	struct btrfs_root *root = fs_info->tree_root;
 	struct inode *inode = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	u64 alloc_hint = 0;
 	int dcs = BTRFS_DC_ERROR;
 	u64 num_pages = 0;
@@ -3368,7 +3423,7 @@ static int cache_save_setup(struct btrfs_block_group_cache *block_group,
 	if (trans->aborted)
 		return 0;
 again:
-	inode = lookup_free_space_inode(root, block_group, path);
+	inode = lookup_free_space_inode(fs_info, block_group, path);
 	if (IS_ERR(inode) && PTR_ERR(inode) != -ENOENT) {
 		ret = PTR_ERR(inode);
 		btrfs_release_path(path);
@@ -3382,7 +3437,8 @@ again:
 		if (block_group->ro)
 			goto out_free;
 
-		ret = create_free_space_inode(root, trans, block_group, path);
+		ret = create_free_space_inode(fs_info, trans, block_group,
+					      path);
 		if (ret)
 			goto out_free;
 		goto again;
@@ -3424,7 +3480,7 @@ again:
 		if (ret)
 			goto out_put;
 
-		ret = btrfs_truncate_free_space_cache(root, trans, NULL, inode);
+		ret = btrfs_truncate_free_space_cache(trans, NULL, inode);
 		if (ret)
 			goto out_put;
 	}
@@ -3435,7 +3491,8 @@ again:
 		/*
 		 * don't bother trying to write stuff out _if_
 		 * a) we're not cached,
-		 * b) we're with nospace_cache mount option.
+		 * b) we're with nospace_cache mount option,
+		 * c) we're with v2 space_cache (FREE_SPACE_TREE).
 		 */
 		dcs = BTRFS_DC_WRITTEN;
 		spin_unlock(&block_group->lock);
@@ -3465,7 +3522,7 @@ again:
 	num_pages *= 16;
 	num_pages *= PAGE_SIZE;
 
-	ret = btrfs_check_data_free_space(inode, 0, num_pages);
+	ret = btrfs_check_data_free_space(inode, &data_reserved, 0, num_pages);
 	if (ret)
 		goto out_put;
 
@@ -3496,6 +3553,7 @@ out:
 	block_group->disk_cache_state = dcs;
 	spin_unlock(&block_group->lock);
 
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -3906,87 +3964,83 @@ static const char *alloc_name(u64 flags)
 	};
 }
 
-static int update_space_info(struct btrfs_fs_info *info, u64 flags,
-			     u64 total_bytes, u64 bytes_used,
-			     u64 bytes_readonly,
-			     struct btrfs_space_info **space_info)
+static int create_space_info(struct btrfs_fs_info *info, u64 flags,
+			     struct btrfs_space_info **new)
 {
-	struct btrfs_space_info *found;
+
+	struct btrfs_space_info *space_info;
 	int i;
-	int factor;
 	int ret;
 
-	if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
-		     BTRFS_BLOCK_GROUP_RAID10))
-		factor = 2;
-	else
-		factor = 1;
-
-	found = __find_space_info(info, flags);
-	if (found) {
-		spin_lock(&found->lock);
-		found->total_bytes += total_bytes;
-		found->disk_total += total_bytes * factor;
-		found->bytes_used += bytes_used;
-		found->disk_used += bytes_used * factor;
-		found->bytes_readonly += bytes_readonly;
-		if (total_bytes > 0)
-			found->full = 0;
-		space_info_add_new_bytes(info, found, total_bytes -
-					 bytes_used - bytes_readonly);
-		spin_unlock(&found->lock);
-		*space_info = found;
-		return 0;
-	}
-	found = kzalloc(sizeof(*found), GFP_NOFS);
-	if (!found)
+	space_info = kzalloc(sizeof(*space_info), GFP_NOFS);
+	if (!space_info)
 		return -ENOMEM;
 
-	ret = percpu_counter_init(&found->total_bytes_pinned, 0, GFP_KERNEL);
+	ret = percpu_counter_init(&space_info->total_bytes_pinned, 0,
+				 GFP_KERNEL);
 	if (ret) {
-		kfree(found);
+		kfree(space_info);
 		return ret;
 	}
 
 	for (i = 0; i < BTRFS_NR_RAID_TYPES; i++)
-		INIT_LIST_HEAD(&found->block_groups[i]);
-	init_rwsem(&found->groups_sem);
-	spin_lock_init(&found->lock);
-	found->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
-	found->total_bytes = total_bytes;
-	found->disk_total = total_bytes * factor;
-	found->bytes_used = bytes_used;
-	found->disk_used = bytes_used * factor;
-	found->bytes_pinned = 0;
-	found->bytes_reserved = 0;
-	found->bytes_readonly = bytes_readonly;
-	found->bytes_may_use = 0;
-	found->full = 0;
-	found->max_extent_size = 0;
-	found->force_alloc = CHUNK_ALLOC_NO_FORCE;
-	found->chunk_alloc = 0;
-	found->flush = 0;
-	init_waitqueue_head(&found->wait);
-	INIT_LIST_HEAD(&found->ro_bgs);
-	INIT_LIST_HEAD(&found->tickets);
-	INIT_LIST_HEAD(&found->priority_tickets);
-
-	ret = kobject_init_and_add(&found->kobj, &space_info_ktype,
+		INIT_LIST_HEAD(&space_info->block_groups[i]);
+	init_rwsem(&space_info->groups_sem);
+	spin_lock_init(&space_info->lock);
+	space_info->flags = flags & BTRFS_BLOCK_GROUP_TYPE_MASK;
+	space_info->force_alloc = CHUNK_ALLOC_NO_FORCE;
+	init_waitqueue_head(&space_info->wait);
+	INIT_LIST_HEAD(&space_info->ro_bgs);
+	INIT_LIST_HEAD(&space_info->tickets);
+	INIT_LIST_HEAD(&space_info->priority_tickets);
+
+	ret = kobject_init_and_add(&space_info->kobj, &space_info_ktype,
 				    info->space_info_kobj, "%s",
-				    alloc_name(found->flags));
+				    alloc_name(space_info->flags));
 	if (ret) {
-		kfree(found);
+		percpu_counter_destroy(&space_info->total_bytes_pinned);
+		kfree(space_info);
 		return ret;
 	}
 
-	*space_info = found;
-	list_add_rcu(&found->list, &info->space_info);
+	*new = space_info;
+	list_add_rcu(&space_info->list, &info->space_info);
 	if (flags & BTRFS_BLOCK_GROUP_DATA)
-		info->data_sinfo = found;
+		info->data_sinfo = space_info;
 
 	return ret;
 }
 
+static void update_space_info(struct btrfs_fs_info *info, u64 flags,
+			     u64 total_bytes, u64 bytes_used,
+			     u64 bytes_readonly,
+			     struct btrfs_space_info **space_info)
+{
+	struct btrfs_space_info *found;
+	int factor;
+
+	if (flags & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1 |
+		     BTRFS_BLOCK_GROUP_RAID10))
+		factor = 2;
+	else
+		factor = 1;
+
+	found = __find_space_info(info, flags);
+	ASSERT(found);
+	spin_lock(&found->lock);
+	found->total_bytes += total_bytes;
+	found->disk_total += total_bytes * factor;
+	found->bytes_used += bytes_used;
+	found->disk_used += bytes_used * factor;
+	found->bytes_readonly += bytes_readonly;
+	if (total_bytes > 0)
+		found->full = 0;
+	space_info_add_new_bytes(info, found, total_bytes -
+				 bytes_used - bytes_readonly);
+	spin_unlock(&found->lock);
+	*space_info = found;
+}
+
 static void set_avail_alloc_bits(struct btrfs_fs_info *fs_info, u64 flags)
 {
 	u64 extra_flags = chunk_to_extended(flags) &
@@ -4102,7 +4156,7 @@ static u64 get_alloc_profile(struct btrfs_fs_info *fs_info, u64 orig_flags)
 	return btrfs_reduce_alloc_profile(fs_info, flags);
 }
 
-u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
+static u64 get_alloc_profile_by_root(struct btrfs_root *root, int data)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 flags;
@@ -4119,10 +4173,34 @@ u64 btrfs_get_alloc_profile(struct btrfs_root *root, int data)
 	return ret;
 }
 
-int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes)
+u64 btrfs_data_alloc_profile(struct btrfs_fs_info *fs_info)
+{
+	return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_DATA);
+}
+
+u64 btrfs_metadata_alloc_profile(struct btrfs_fs_info *fs_info)
+{
+	return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_METADATA);
+}
+
+u64 btrfs_system_alloc_profile(struct btrfs_fs_info *fs_info)
+{
+	return get_alloc_profile(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
+}
+
+static u64 btrfs_space_info_used(struct btrfs_space_info *s_info,
+				 bool may_use_included)
+{
+	ASSERT(s_info);
+	return s_info->bytes_used + s_info->bytes_reserved +
+		s_info->bytes_pinned + s_info->bytes_readonly +
+		(may_use_included ? s_info->bytes_may_use : 0);
+}
+
+int btrfs_alloc_data_chunk_ondemand(struct btrfs_inode *inode, u64 bytes)
 {
 	struct btrfs_space_info *data_sinfo;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 used;
 	int ret = 0;
@@ -4144,9 +4222,7 @@ int btrfs_alloc_data_chunk_ondemand(struct inode *inode, u64 bytes)
 again:
 	/* make sure we have enough space to handle the data first */
 	spin_lock(&data_sinfo->lock);
-	used = data_sinfo->bytes_used + data_sinfo->bytes_reserved +
-		data_sinfo->bytes_pinned + data_sinfo->bytes_readonly +
-		data_sinfo->bytes_may_use;
+	used = btrfs_space_info_used(data_sinfo, true);
 
 	if (used + bytes > data_sinfo->total_bytes) {
 		struct btrfs_trans_handle *trans;
@@ -4161,7 +4237,7 @@ again:
 			data_sinfo->force_alloc = CHUNK_ALLOC_FORCE;
 			spin_unlock(&data_sinfo->lock);
 alloc:
-			alloc_target = btrfs_get_alloc_profile(root, 1);
+			alloc_target = btrfs_data_alloc_profile(fs_info);
 			/*
 			 * It is ugly that we don't call nolock join
 			 * transaction for the free space inode case here.
@@ -4212,7 +4288,7 @@ commit_trans:
 
 			if (need_commit > 0) {
 				btrfs_start_delalloc_roots(fs_info, 0, -1);
-				btrfs_wait_ordered_roots(fs_info, -1, 0,
+				btrfs_wait_ordered_roots(fs_info, U64_MAX, 0,
 							 (u64)-1);
 			}
 
@@ -4252,12 +4328,8 @@ commit_trans:
 	return ret;
 }
 
-/*
- * New check_data_free_space() with ability for precious data reservation
- * Will replace old btrfs_check_data_free_space(), but for patch split,
- * add a new function first and then replace it.
- */
-int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len)
+int btrfs_check_data_free_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	int ret;
@@ -4267,14 +4339,16 @@ int btrfs_check_data_free_space(struct inode *inode, u64 start, u64 len)
 	      round_down(start, fs_info->sectorsize);
 	start = round_down(start, fs_info->sectorsize);
 
-	ret = btrfs_alloc_data_chunk_ondemand(inode, len);
+	ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode), len);
 	if (ret < 0)
 		return ret;
 
 	/* Use new btrfs_qgroup_reserve_data to reserve precious data space. */
-	ret = btrfs_qgroup_reserve_data(inode, start, len);
-	if (ret)
+	ret = btrfs_qgroup_reserve_data(inode, reserved, start, len);
+	if (ret < 0)
 		btrfs_free_reserved_data_space_noquota(inode, start, len);
+	else
+		ret = 0;
 	return ret;
 }
 
@@ -4315,7 +4389,8 @@ void btrfs_free_reserved_data_space_noquota(struct inode *inode, u64 start,
  * This one will handle the per-inode data rsv map for accurate reserved
  * space framework.
  */
-void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len)
+void btrfs_free_reserved_data_space(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 
@@ -4325,7 +4400,7 @@ void btrfs_free_reserved_data_space(struct inode *inode, u64 start, u64 len)
 	start = round_down(start, root->fs_info->sectorsize);
 
 	btrfs_free_reserved_data_space_noquota(inode, start, len);
-	btrfs_qgroup_free_data(inode, start, len);
+	btrfs_qgroup_free_data(inode, reserved, start, len);
 }
 
 static void force_metadata_allocation(struct btrfs_fs_info *info)
@@ -4421,9 +4496,7 @@ void check_system_chunk(struct btrfs_trans_handle *trans,
 
 	info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_SYSTEM);
 	spin_lock(&info->lock);
-	left = info->total_bytes - info->bytes_used - info->bytes_pinned -
-		info->bytes_reserved - info->bytes_readonly -
-		info->bytes_may_use;
+	left = info->total_bytes - btrfs_space_info_used(info, true);
 	spin_unlock(&info->lock);
 
 	num_devs = get_profile_num_devs(fs_info, type);
@@ -4439,9 +4512,8 @@ void check_system_chunk(struct btrfs_trans_handle *trans,
 	}
 
 	if (left < thresh) {
-		u64 flags;
+		u64 flags = btrfs_system_alloc_profile(fs_info);
 
-		flags = btrfs_get_alloc_profile(fs_info->chunk_root, 0);
 		/*
 		 * Ignore failure to create system chunk. We might end up not
 		 * needing it, as we might not need to COW all nodes/leafs from
@@ -4482,10 +4554,10 @@ static int do_chunk_alloc(struct btrfs_trans_handle *trans,
 
 	space_info = __find_space_info(fs_info, flags);
 	if (!space_info) {
-		ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
-		BUG_ON(ret); /* -ENOMEM */
+		ret = create_space_info(fs_info, flags, &space_info);
+		if (ret)
+			return ret;
 	}
-	BUG_ON(!space_info); /* Logic error */
 
 again:
 	spin_lock(&space_info->lock);
@@ -4590,11 +4662,11 @@ out:
 	return ret;
 }
 
-static int can_overcommit(struct btrfs_root *root,
+static int can_overcommit(struct btrfs_fs_info *fs_info,
 			  struct btrfs_space_info *space_info, u64 bytes,
-			  enum btrfs_reserve_flush_enum flush)
+			  enum btrfs_reserve_flush_enum flush,
+			  bool system_chunk)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
 	u64 profile;
 	u64 space_size;
@@ -4605,9 +4677,12 @@ static int can_overcommit(struct btrfs_root *root,
 	if (space_info->flags & BTRFS_BLOCK_GROUP_DATA)
 		return 0;
 
-	profile = btrfs_get_alloc_profile(root, 0);
-	used = space_info->bytes_used + space_info->bytes_reserved +
-		space_info->bytes_pinned + space_info->bytes_readonly;
+	if (system_chunk)
+		profile = btrfs_system_alloc_profile(fs_info);
+	else
+		profile = btrfs_metadata_alloc_profile(fs_info);
+
+	used = btrfs_space_info_used(space_info, false);
 
 	/*
 	 * We only want to allow over committing if we have lots of actual space
@@ -4623,9 +4698,7 @@ static int can_overcommit(struct btrfs_root *root,
 
 	used += space_info->bytes_may_use;
 
-	spin_lock(&fs_info->free_chunk_lock);
-	avail = fs_info->free_chunk_space;
-	spin_unlock(&fs_info->free_chunk_lock);
+	avail = atomic64_read(&fs_info->free_chunk_space);
 
 	/*
 	 * If we have dup, raid1 or raid10 then only half of the free
@@ -4675,14 +4748,14 @@ static void btrfs_writeback_inodes_sb_nr(struct btrfs_fs_info *fs_info,
 	}
 }
 
-static inline int calc_reclaim_items_nr(struct btrfs_fs_info *fs_info,
+static inline u64 calc_reclaim_items_nr(struct btrfs_fs_info *fs_info,
 					u64 to_reclaim)
 {
 	u64 bytes;
-	int nr;
+	u64 nr;
 
 	bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
-	nr = (int)div64_u64(to_reclaim, bytes);
+	nr = div64_u64(to_reclaim, bytes);
 	if (!nr)
 		nr = 1;
 	return nr;
@@ -4693,24 +4766,23 @@ static inline int calc_reclaim_items_nr(struct btrfs_fs_info *fs_info,
 /*
  * shrink metadata reservation for delalloc
  */
-static void shrink_delalloc(struct btrfs_root *root, u64 to_reclaim, u64 orig,
-			    bool wait_ordered)
+static void shrink_delalloc(struct btrfs_fs_info *fs_info, u64 to_reclaim,
+			    u64 orig, bool wait_ordered)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_block_rsv *block_rsv;
 	struct btrfs_space_info *space_info;
 	struct btrfs_trans_handle *trans;
 	u64 delalloc_bytes;
 	u64 max_reclaim;
+	u64 items;
 	long time_left;
 	unsigned long nr_pages;
 	int loops;
-	int items;
 	enum btrfs_reserve_flush_enum flush;
 
 	/* Calc the number of the pages we need flush for space reservation */
 	items = calc_reclaim_items_nr(fs_info, to_reclaim);
-	to_reclaim = (u64)items * EXTENT_SIZE_PER_ITEM;
+	to_reclaim = items * EXTENT_SIZE_PER_ITEM;
 
 	trans = (struct btrfs_trans_handle *)current->journal_info;
 	block_rsv = &fs_info->delalloc_block_rsv;
@@ -4753,7 +4825,7 @@ skip_async:
 		else
 			flush = BTRFS_RESERVE_NO_FLUSH;
 		spin_lock(&space_info->lock);
-		if (can_overcommit(root, space_info, orig, flush)) {
+		if (can_overcommit(fs_info, space_info, orig, flush, false)) {
 			spin_unlock(&space_info->lock);
 			break;
 		}
@@ -4787,11 +4859,10 @@ skip_async:
  * get us somewhere and then commit the transaction if it does.  Otherwise it
  * will return -ENOSPC.
  */
-static int may_commit_transaction(struct btrfs_root *root,
+static int may_commit_transaction(struct btrfs_fs_info *fs_info,
 				  struct btrfs_space_info *space_info,
 				  u64 bytes, int force)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_block_rsv *delayed_rsv = &fs_info->delayed_block_rsv;
 	struct btrfs_trans_handle *trans;
 
@@ -4816,14 +4887,14 @@ static int may_commit_transaction(struct btrfs_root *root,
 
 	spin_lock(&delayed_rsv->lock);
 	if (percpu_counter_compare(&space_info->total_bytes_pinned,
-				   bytes - delayed_rsv->size) >= 0) {
+				   bytes - delayed_rsv->size) < 0) {
 		spin_unlock(&delayed_rsv->lock);
 		return -ENOSPC;
 	}
 	spin_unlock(&delayed_rsv->lock);
 
 commit:
-	trans = btrfs_join_transaction(root);
+	trans = btrfs_join_transaction(fs_info->extent_root);
 	if (IS_ERR(trans))
 		return -ENOSPC;
 
@@ -4837,11 +4908,11 @@ struct reserve_ticket {
 	wait_queue_head_t wait;
 };
 
-static int flush_space(struct btrfs_root *root,
+static int flush_space(struct btrfs_fs_info *fs_info,
 		       struct btrfs_space_info *space_info, u64 num_bytes,
 		       u64 orig_bytes, int state)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
+	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_trans_handle *trans;
 	int nr;
 	int ret = 0;
@@ -4864,7 +4935,7 @@ static int flush_space(struct btrfs_root *root,
 		break;
 	case FLUSH_DELALLOC:
 	case FLUSH_DELALLOC_WAIT:
-		shrink_delalloc(root, num_bytes * 2, orig_bytes,
+		shrink_delalloc(fs_info, num_bytes * 2, orig_bytes,
 				state == FLUSH_DELALLOC_WAIT);
 		break;
 	case ALLOC_CHUNK:
@@ -4874,14 +4945,15 @@ static int flush_space(struct btrfs_root *root,
 			break;
 		}
 		ret = do_chunk_alloc(trans, fs_info,
-				     btrfs_get_alloc_profile(root, 0),
+				     btrfs_metadata_alloc_profile(fs_info),
 				     CHUNK_ALLOC_NO_FORCE);
 		btrfs_end_transaction(trans);
 		if (ret > 0 || ret == -ENOSPC)
 			ret = 0;
 		break;
 	case COMMIT_TRANS:
-		ret = may_commit_transaction(root, space_info, orig_bytes, 0);
+		ret = may_commit_transaction(fs_info, space_info,
+					     orig_bytes, 0);
 		break;
 	default:
 		ret = -ENOSPC;
@@ -4894,8 +4966,9 @@ static int flush_space(struct btrfs_root *root,
 }
 
 static inline u64
-btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
-				 struct btrfs_space_info *space_info)
+btrfs_calc_reclaim_metadata_size(struct btrfs_fs_info *fs_info,
+				 struct btrfs_space_info *space_info,
+				 bool system_chunk)
 {
 	struct reserve_ticket *ticket;
 	u64 used;
@@ -4910,14 +4983,14 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
 		return to_reclaim;
 
 	to_reclaim = min_t(u64, num_online_cpus() * SZ_1M, SZ_16M);
-	if (can_overcommit(root, space_info, to_reclaim,
-			   BTRFS_RESERVE_FLUSH_ALL))
+	if (can_overcommit(fs_info, space_info, to_reclaim,
+			   BTRFS_RESERVE_FLUSH_ALL, system_chunk))
 		return 0;
 
-	used = space_info->bytes_used + space_info->bytes_reserved +
-	       space_info->bytes_pinned + space_info->bytes_readonly +
-	       space_info->bytes_may_use;
-	if (can_overcommit(root, space_info, SZ_1M, BTRFS_RESERVE_FLUSH_ALL))
+	used = btrfs_space_info_used(space_info, true);
+
+	if (can_overcommit(fs_info, space_info, SZ_1M,
+			   BTRFS_RESERVE_FLUSH_ALL, system_chunk))
 		expected = div_factor_fine(space_info->total_bytes, 95);
 	else
 		expected = div_factor_fine(space_info->total_bytes, 90);
@@ -4931,17 +5004,18 @@ btrfs_calc_reclaim_metadata_size(struct btrfs_root *root,
 	return to_reclaim;
 }
 
-static inline int need_do_async_reclaim(struct btrfs_space_info *space_info,
-					struct btrfs_root *root, u64 used)
+static inline int need_do_async_reclaim(struct btrfs_fs_info *fs_info,
+					struct btrfs_space_info *space_info,
+					u64 used, bool system_chunk)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 thresh = div_factor_fine(space_info->total_bytes, 98);
 
 	/* If we're just plain full then async reclaim just slows us down. */
 	if ((space_info->bytes_used + space_info->bytes_reserved) >= thresh)
 		return 0;
 
-	if (!btrfs_calc_reclaim_metadata_size(root, space_info))
+	if (!btrfs_calc_reclaim_metadata_size(fs_info, space_info,
+					      system_chunk))
 		return 0;
 
 	return (used >= thresh && !btrfs_fs_closing(fs_info) &&
@@ -4978,8 +5052,8 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
 	space_info = __find_space_info(fs_info, BTRFS_BLOCK_GROUP_METADATA);
 
 	spin_lock(&space_info->lock);
-	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
-						      space_info);
+	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
+						      false);
 	if (!to_reclaim) {
 		space_info->flush = 0;
 		spin_unlock(&space_info->lock);
@@ -4993,16 +5067,17 @@ static void btrfs_async_reclaim_metadata_space(struct work_struct *work)
 		struct reserve_ticket *ticket;
 		int ret;
 
-		ret = flush_space(fs_info->fs_root, space_info, to_reclaim,
-			    to_reclaim, flush_state);
+		ret = flush_space(fs_info, space_info, to_reclaim, to_reclaim,
+				  flush_state);
 		spin_lock(&space_info->lock);
 		if (list_empty(&space_info->tickets)) {
 			space_info->flush = 0;
 			spin_unlock(&space_info->lock);
 			return;
 		}
-		to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
-							      space_info);
+		to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info,
+							      space_info,
+							      false);
 		ticket = list_first_entry(&space_info->tickets,
 					  struct reserve_ticket, list);
 		if (last_tickets_id == space_info->tickets_id) {
@@ -5040,8 +5115,8 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 	int flush_state = FLUSH_DELAYED_ITEMS_NR;
 
 	spin_lock(&space_info->lock);
-	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info->fs_root,
-						      space_info);
+	to_reclaim = btrfs_calc_reclaim_metadata_size(fs_info, space_info,
+						      false);
 	if (!to_reclaim) {
 		spin_unlock(&space_info->lock);
 		return;
@@ -5049,8 +5124,8 @@ static void priority_reclaim_metadata_space(struct btrfs_fs_info *fs_info,
 	spin_unlock(&space_info->lock);
 
 	do {
-		flush_space(fs_info->fs_root, space_info, to_reclaim,
-			    to_reclaim, flush_state);
+		flush_space(fs_info, space_info, to_reclaim, to_reclaim,
+			    flush_state);
 		flush_state++;
 		spin_lock(&space_info->lock);
 		if (ticket->bytes == 0) {
@@ -5120,12 +5195,12 @@ static int wait_reserve_ticket(struct btrfs_fs_info *fs_info,
  * regain reservations will be made and this will fail if there is not enough
  * space already.
  */
-static int __reserve_metadata_bytes(struct btrfs_root *root,
+static int __reserve_metadata_bytes(struct btrfs_fs_info *fs_info,
 				    struct btrfs_space_info *space_info,
 				    u64 orig_bytes,
-				    enum btrfs_reserve_flush_enum flush)
+				    enum btrfs_reserve_flush_enum flush,
+				    bool system_chunk)
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct reserve_ticket ticket;
 	u64 used;
 	int ret = 0;
@@ -5135,9 +5210,7 @@ static int __reserve_metadata_bytes(struct btrfs_root *root,
 
 	spin_lock(&space_info->lock);
 	ret = -ENOSPC;
-	used = space_info->bytes_used + space_info->bytes_reserved +
-		space_info->bytes_pinned + space_info->bytes_readonly +
-		space_info->bytes_may_use;
+	used = btrfs_space_info_used(space_info, true);
 
 	/*
 	 * If we have enough space then hooray, make our reservation and carry
@@ -5149,7 +5222,8 @@ static int __reserve_metadata_bytes(struct btrfs_root *root,
 		trace_btrfs_space_reservation(fs_info, "space_info",
 					      space_info->flags, orig_bytes, 1);
 		ret = 0;
-	} else if (can_overcommit(root, space_info, orig_bytes, flush)) {
+	} else if (can_overcommit(fs_info, space_info, orig_bytes, flush,
+				  system_chunk)) {
 		space_info->bytes_may_use += orig_bytes;
 		trace_btrfs_space_reservation(fs_info, "space_info",
 					      space_info->flags, orig_bytes, 1);
@@ -5176,7 +5250,7 @@ static int __reserve_metadata_bytes(struct btrfs_root *root,
 							  orig_bytes, flush,
 							  "enospc");
 				queue_work(system_unbound_wq,
-					   &root->fs_info->async_reclaim_work);
+					   &fs_info->async_reclaim_work);
 			}
 		} else {
 			list_add_tail(&ticket.list,
@@ -5190,7 +5264,8 @@ static int __reserve_metadata_bytes(struct btrfs_root *root,
 		 * the async reclaim as we will panic.
 		 */
 		if (!test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags) &&
-		    need_do_async_reclaim(space_info, root, used) &&
+		    need_do_async_reclaim(fs_info, space_info,
+					  used, system_chunk) &&
 		    !work_busy(&fs_info->async_reclaim_work)) {
 			trace_btrfs_trigger_flush(fs_info, space_info->flags,
 						  orig_bytes, flush, "preempt");
@@ -5248,9 +5323,10 @@ static int reserve_metadata_bytes(struct btrfs_root *root,
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_block_rsv *global_rsv = &fs_info->global_block_rsv;
 	int ret;
+	bool system_chunk = (root == fs_info->chunk_root);
 
-	ret = __reserve_metadata_bytes(root, block_rsv->space_info, orig_bytes,
-				       flush);
+	ret = __reserve_metadata_bytes(fs_info, block_rsv->space_info,
+				       orig_bytes, flush, system_chunk);
 	if (ret == -ENOSPC &&
 	    unlikely(root->orphan_cleanup_state == ORPHAN_CLEANUP_STARTED)) {
 		if (block_rsv != global_rsv &&
@@ -5359,9 +5435,7 @@ static void space_info_add_old_bytes(struct btrfs_fs_info *fs_info,
 	 * overcommit, and if we can't then we just need to free up our space
 	 * and not satisfy any requests.
 	 */
-	used = space_info->bytes_used + space_info->bytes_reserved +
-		space_info->bytes_pinned + space_info->bytes_readonly +
-		space_info->bytes_may_use;
+	used = btrfs_space_info_used(space_info, true);
 	if (used - num_bytes >= space_info->total_bytes)
 		check_overcommit = true;
 again:
@@ -5373,8 +5447,7 @@ again:
 		 * adding the ticket space would be a double count.
 		 */
 		if (check_overcommit &&
-		    !can_overcommit(fs_info->extent_root, space_info, 0,
-				    flush))
+		    !can_overcommit(fs_info, space_info, 0, flush, false))
 			break;
 		if (num_bytes >= ticket->bytes) {
 			list_del_init(&ticket->list);
@@ -5630,9 +5703,7 @@ static void update_global_block_rsv(struct btrfs_fs_info *fs_info)
 	block_rsv->size = min_t(u64, num_bytes, SZ_512M);
 
 	if (block_rsv->reserved < block_rsv->size) {
-		num_bytes = sinfo->bytes_used + sinfo->bytes_pinned +
-			sinfo->bytes_reserved + sinfo->bytes_readonly +
-			sinfo->bytes_may_use;
+		num_bytes = btrfs_space_info_used(sinfo, true);
 		if (sinfo->total_bytes > num_bytes) {
 			num_bytes = sinfo->total_bytes - num_bytes;
 			num_bytes = min(num_bytes,
@@ -5735,10 +5806,10 @@ void btrfs_trans_release_chunk_metadata(struct btrfs_trans_handle *trans)
 
 /* Can only return 0 or -ENOSPC */
 int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
-				  struct inode *inode)
+				  struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	/*
 	 * We always use trans->block_rsv here as we will have reserved space
 	 * for our orphan when starting the transaction, using get_block_rsv()
@@ -5755,19 +5826,19 @@ int btrfs_orphan_reserve_metadata(struct btrfs_trans_handle *trans,
 	 */
 	u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
 
-	trace_btrfs_space_reservation(fs_info, "orphan",
-				      btrfs_ino(inode), num_bytes, 1);
+	trace_btrfs_space_reservation(fs_info, "orphan", btrfs_ino(inode), 
+			num_bytes, 1);
 	return btrfs_block_rsv_migrate(src_rsv, dst_rsv, num_bytes, 1);
 }
 
-void btrfs_orphan_release_metadata(struct inode *inode)
+void btrfs_orphan_release_metadata(struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	u64 num_bytes = btrfs_calc_trans_metadata_size(fs_info, 1);
 
-	trace_btrfs_space_reservation(fs_info, "orphan",
-				      btrfs_ino(inode), num_bytes, 0);
+	trace_btrfs_space_reservation(fs_info, "orphan", btrfs_ino(inode),
+			num_bytes, 0);
 	btrfs_block_rsv_release(fs_info, root->orphan_block_rsv, num_bytes);
 }
 
@@ -5799,7 +5870,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
 		/* One for parent inode, two for dir entries */
 		num_bytes = 3 * fs_info->nodesize;
-		ret = btrfs_qgroup_reserve_meta(root, num_bytes);
+		ret = btrfs_qgroup_reserve_meta(root, num_bytes, true);
 		if (ret)
 			return ret;
 	} else {
@@ -5824,8 +5895,7 @@ int btrfs_subvolume_reserve_metadata(struct btrfs_root *root,
 }
 
 void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
-				      struct btrfs_block_rsv *rsv,
-				      u64 qgroup_reserved)
+				      struct btrfs_block_rsv *rsv)
 {
 	btrfs_block_rsv_release(fs_info, rsv, (u64)-1);
 }
@@ -5840,35 +5910,32 @@ void btrfs_subvolume_release_metadata(struct btrfs_fs_info *fs_info,
  * reserved extents that need to be freed.  This must be called with
  * BTRFS_I(inode)->lock held.
  */
-static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes)
+static unsigned drop_outstanding_extent(struct btrfs_inode *inode,
+		u64 num_bytes)
 {
 	unsigned drop_inode_space = 0;
 	unsigned dropped_extents = 0;
-	unsigned num_extents = 0;
+	unsigned num_extents;
 
-	num_extents = (unsigned)div64_u64(num_bytes +
-					  BTRFS_MAX_EXTENT_SIZE - 1,
-					  BTRFS_MAX_EXTENT_SIZE);
+	num_extents = count_max_extents(num_bytes);
 	ASSERT(num_extents);
-	ASSERT(BTRFS_I(inode)->outstanding_extents >= num_extents);
-	BTRFS_I(inode)->outstanding_extents -= num_extents;
+	ASSERT(inode->outstanding_extents >= num_extents);
+	inode->outstanding_extents -= num_extents;
 
-	if (BTRFS_I(inode)->outstanding_extents == 0 &&
+	if (inode->outstanding_extents == 0 &&
 	    test_and_clear_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
-			       &BTRFS_I(inode)->runtime_flags))
+			       &inode->runtime_flags))
 		drop_inode_space = 1;
 
 	/*
 	 * If we have more or the same amount of outstanding extents than we have
 	 * reserved then we need to leave the reserved extents count alone.
 	 */
-	if (BTRFS_I(inode)->outstanding_extents >=
-	    BTRFS_I(inode)->reserved_extents)
+	if (inode->outstanding_extents >= inode->reserved_extents)
 		return drop_inode_space;
 
-	dropped_extents = BTRFS_I(inode)->reserved_extents -
-		BTRFS_I(inode)->outstanding_extents;
-	BTRFS_I(inode)->reserved_extents -= dropped_extents;
+	dropped_extents = inode->reserved_extents - inode->outstanding_extents;
+	inode->reserved_extents -= dropped_extents;
 	return dropped_extents + drop_inode_space;
 }
 
@@ -5890,24 +5957,21 @@ static unsigned drop_outstanding_extent(struct inode *inode, u64 num_bytes)
  *
  * This must be called with BTRFS_I(inode)->lock held.
  */
-static u64 calc_csum_metadata_size(struct inode *inode, u64 num_bytes,
+static u64 calc_csum_metadata_size(struct btrfs_inode *inode, u64 num_bytes,
 				   int reserve)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	u64 old_csums, num_csums;
 
-	if (BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM &&
-	    BTRFS_I(inode)->csum_bytes == 0)
+	if (inode->flags & BTRFS_INODE_NODATASUM && inode->csum_bytes == 0)
 		return 0;
 
-	old_csums = btrfs_csum_bytes_to_leaves(fs_info,
-					       BTRFS_I(inode)->csum_bytes);
+	old_csums = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes);
 	if (reserve)
-		BTRFS_I(inode)->csum_bytes += num_bytes;
+		inode->csum_bytes += num_bytes;
 	else
-		BTRFS_I(inode)->csum_bytes -= num_bytes;
-	num_csums = btrfs_csum_bytes_to_leaves(fs_info,
-					       BTRFS_I(inode)->csum_bytes);
+		inode->csum_bytes -= num_bytes;
+	num_csums = btrfs_csum_bytes_to_leaves(fs_info, inode->csum_bytes);
 
 	/* No change, no need to reserve more */
 	if (old_csums == num_csums)
@@ -5920,14 +5984,14 @@ static u64 calc_csum_metadata_size(struct inode *inode, u64 num_bytes,
 	return btrfs_calc_trans_metadata_size(fs_info, old_csums - num_csums);
 }
 
-int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
+int btrfs_delalloc_reserve_metadata(struct btrfs_inode *inode, u64 num_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct btrfs_block_rsv *block_rsv = &fs_info->delalloc_block_rsv;
 	u64 to_reserve = 0;
 	u64 csum_bytes;
-	unsigned nr_extents = 0;
+	unsigned nr_extents;
 	enum btrfs_reserve_flush_enum flush = BTRFS_RESERVE_FLUSH_ALL;
 	int ret = 0;
 	bool delalloc_lock = true;
@@ -5955,31 +6019,28 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 		schedule_timeout(1);
 
 	if (delalloc_lock)
-		mutex_lock(&BTRFS_I(inode)->delalloc_mutex);
+		mutex_lock(&inode->delalloc_mutex);
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
 
-	spin_lock(&BTRFS_I(inode)->lock);
-	nr_extents = (unsigned)div64_u64(num_bytes +
-					 BTRFS_MAX_EXTENT_SIZE - 1,
-					 BTRFS_MAX_EXTENT_SIZE);
-	BTRFS_I(inode)->outstanding_extents += nr_extents;
+	spin_lock(&inode->lock);
+	nr_extents = count_max_extents(num_bytes);
+	inode->outstanding_extents += nr_extents;
 
 	nr_extents = 0;
-	if (BTRFS_I(inode)->outstanding_extents >
-	    BTRFS_I(inode)->reserved_extents)
-		nr_extents += BTRFS_I(inode)->outstanding_extents -
-			BTRFS_I(inode)->reserved_extents;
+	if (inode->outstanding_extents > inode->reserved_extents)
+		nr_extents += inode->outstanding_extents -
+			inode->reserved_extents;
 
 	/* We always want to reserve a slot for updating the inode. */
 	to_reserve = btrfs_calc_trans_metadata_size(fs_info, nr_extents + 1);
 	to_reserve += calc_csum_metadata_size(inode, num_bytes, 1);
-	csum_bytes = BTRFS_I(inode)->csum_bytes;
-	spin_unlock(&BTRFS_I(inode)->lock);
+	csum_bytes = inode->csum_bytes;
+	spin_unlock(&inode->lock);
 
 	if (test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
 		ret = btrfs_qgroup_reserve_meta(root,
-				nr_extents * fs_info->nodesize);
+				nr_extents * fs_info->nodesize, true);
 		if (ret)
 			goto out_fail;
 	}
@@ -5991,17 +6052,17 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 		goto out_fail;
 	}
 
-	spin_lock(&BTRFS_I(inode)->lock);
+	spin_lock(&inode->lock);
 	if (test_and_set_bit(BTRFS_INODE_DELALLOC_META_RESERVED,
-			     &BTRFS_I(inode)->runtime_flags)) {
+			     &inode->runtime_flags)) {
 		to_reserve -= btrfs_calc_trans_metadata_size(fs_info, 1);
 		release_extra = true;
 	}
-	BTRFS_I(inode)->reserved_extents += nr_extents;
-	spin_unlock(&BTRFS_I(inode)->lock);
+	inode->reserved_extents += nr_extents;
+	spin_unlock(&inode->lock);
 
 	if (delalloc_lock)
-		mutex_unlock(&BTRFS_I(inode)->delalloc_mutex);
+		mutex_unlock(&inode->delalloc_mutex);
 
 	if (to_reserve)
 		trace_btrfs_space_reservation(fs_info, "delalloc",
@@ -6012,17 +6073,17 @@ int btrfs_delalloc_reserve_metadata(struct inode *inode, u64 num_bytes)
 	return 0;
 
 out_fail:
-	spin_lock(&BTRFS_I(inode)->lock);
+	spin_lock(&inode->lock);
 	dropped = drop_outstanding_extent(inode, num_bytes);
 	/*
 	 * If the inodes csum_bytes is the same as the original
 	 * csum_bytes then we know we haven't raced with any free()ers
 	 * so we can just reduce our inodes csum bytes and carry on.
 	 */
-	if (BTRFS_I(inode)->csum_bytes == csum_bytes) {
+	if (inode->csum_bytes == csum_bytes) {
 		calc_csum_metadata_size(inode, num_bytes, 0);
 	} else {
-		u64 orig_csum_bytes = BTRFS_I(inode)->csum_bytes;
+		u64 orig_csum_bytes = inode->csum_bytes;
 		u64 bytes;
 
 		/*
@@ -6033,8 +6094,8 @@ out_fail:
 		 * number of bytes that were freed while we were trying our
 		 * reservation.
 		 */
-		bytes = csum_bytes - BTRFS_I(inode)->csum_bytes;
-		BTRFS_I(inode)->csum_bytes = csum_bytes;
+		bytes = csum_bytes - inode->csum_bytes;
+		inode->csum_bytes = csum_bytes;
 		to_free = calc_csum_metadata_size(inode, bytes, 0);
 
 
@@ -6043,7 +6104,7 @@ out_fail:
 		 * been making this reservation and our ->csum_bytes were not
 		 * artificially inflated.
 		 */
-		BTRFS_I(inode)->csum_bytes = csum_bytes - num_bytes;
+		inode->csum_bytes = csum_bytes - num_bytes;
 		bytes = csum_bytes - orig_csum_bytes;
 		bytes = calc_csum_metadata_size(inode, bytes, 0);
 
@@ -6055,13 +6116,13 @@ out_fail:
 		 * need to do anything, the other free-ers did the correct
 		 * thing.
 		 */
-		BTRFS_I(inode)->csum_bytes = orig_csum_bytes - num_bytes;
+		inode->csum_bytes = orig_csum_bytes - num_bytes;
 		if (bytes > to_free)
 			to_free = bytes - to_free;
 		else
 			to_free = 0;
 	}
-	spin_unlock(&BTRFS_I(inode)->lock);
+	spin_unlock(&inode->lock);
 	if (dropped)
 		to_free += btrfs_calc_trans_metadata_size(fs_info, dropped);
 
@@ -6071,7 +6132,7 @@ out_fail:
 					      btrfs_ino(inode), to_free, 0);
 	}
 	if (delalloc_lock)
-		mutex_unlock(&BTRFS_I(inode)->delalloc_mutex);
+		mutex_unlock(&inode->delalloc_mutex);
 	return ret;
 }
 
@@ -6084,27 +6145,27 @@ out_fail:
  * once we complete IO for a given set of bytes to release their metadata
  * reservations.
  */
-void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
+void btrfs_delalloc_release_metadata(struct btrfs_inode *inode, u64 num_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	u64 to_free = 0;
 	unsigned dropped;
 
 	num_bytes = ALIGN(num_bytes, fs_info->sectorsize);
-	spin_lock(&BTRFS_I(inode)->lock);
+	spin_lock(&inode->lock);
 	dropped = drop_outstanding_extent(inode, num_bytes);
 
 	if (num_bytes)
 		to_free = calc_csum_metadata_size(inode, num_bytes, 0);
-	spin_unlock(&BTRFS_I(inode)->lock);
+	spin_unlock(&inode->lock);
 	if (dropped > 0)
 		to_free += btrfs_calc_trans_metadata_size(fs_info, dropped);
 
 	if (btrfs_is_testing(fs_info))
 		return;
 
-	trace_btrfs_space_reservation(fs_info, "delalloc",
-				      btrfs_ino(inode), to_free, 0);
+	trace_btrfs_space_reservation(fs_info, "delalloc", btrfs_ino(inode),
+				      to_free, 0);
 
 	btrfs_block_rsv_release(fs_info, &fs_info->delalloc_block_rsv, to_free);
 }
@@ -6115,6 +6176,8 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
  * @inode: inode we're writing to
  * @start: start range we are writing to
  * @len: how long the range we are writing to
+ * @reserved: mandatory parameter, record actually reserved qgroup ranges of
+ * 	      current reservation.
  *
  * This will do the following things
  *
@@ -6132,16 +6195,17 @@ void btrfs_delalloc_release_metadata(struct inode *inode, u64 num_bytes)
  * Return 0 for success
  * Return <0 for error(-ENOSPC or -EQUOT)
  */
-int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len)
+int btrfs_delalloc_reserve_space(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len)
 {
 	int ret;
 
-	ret = btrfs_check_data_free_space(inode, start, len);
+	ret = btrfs_check_data_free_space(inode, reserved, start, len);
 	if (ret < 0)
 		return ret;
-	ret = btrfs_delalloc_reserve_metadata(inode, len);
+	ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode), len);
 	if (ret < 0)
-		btrfs_free_reserved_data_space(inode, start, len);
+		btrfs_free_reserved_data_space(inode, *reserved, start, len);
 	return ret;
 }
 
@@ -6160,10 +6224,11 @@ int btrfs_delalloc_reserve_space(struct inode *inode, u64 start, u64 len)
  * list if there are no delalloc bytes left.
  * Also it will handle the qgroup reserved space.
  */
-void btrfs_delalloc_release_space(struct inode *inode, u64 start, u64 len)
+void btrfs_delalloc_release_space(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len)
 {
-	btrfs_delalloc_release_metadata(inode, len);
-	btrfs_free_reserved_data_space(inode, start, len);
+	btrfs_delalloc_release_metadata(BTRFS_I(inode), len);
+	btrfs_free_reserved_data_space(inode, reserved, start, len);
 }
 
 static int update_block_group(struct btrfs_trans_handle *trans,
@@ -6239,6 +6304,8 @@ static int update_block_group(struct btrfs_trans_handle *trans,
 			trace_btrfs_space_reservation(info, "pinned",
 						      cache->space_info->flags,
 						      num_bytes, 1);
+			percpu_counter_add(&cache->space_info->total_bytes_pinned,
+					   num_bytes);
 			set_extent_dirty(info->pinned_extents,
 					 bytenr, bytenr + num_bytes - 1,
 					 GFP_NOFS | __GFP_NOFAIL);
@@ -6315,6 +6382,7 @@ static int pin_down_extent(struct btrfs_fs_info *fs_info,
 
 	trace_btrfs_space_reservation(fs_info, "pinned",
 				      cache->space_info->flags, num_bytes, 1);
+	percpu_counter_add(&cache->space_info->total_bytes_pinned, num_bytes);
 	set_extent_dirty(fs_info->pinned_extents, bytenr,
 			 bytenr + num_bytes - 1, GFP_NOFS | __GFP_NOFAIL);
 	return 0;
@@ -6561,8 +6629,7 @@ static int btrfs_free_reserved_bytes(struct btrfs_block_group_cache *cache,
 	spin_unlock(&space_info->lock);
 	return ret;
 }
-void btrfs_prepare_extent_commit(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info)
+void btrfs_prepare_extent_commit(struct btrfs_fs_info *fs_info)
 {
 	struct btrfs_caching_control *next;
 	struct btrfs_caching_control *caching_ctl;
@@ -6786,27 +6853,6 @@ int btrfs_finish_extent_commit(struct btrfs_trans_handle *trans,
 	return 0;
 }
 
-static void add_pinned_bytes(struct btrfs_fs_info *fs_info, u64 num_bytes,
-			     u64 owner, u64 root_objectid)
-{
-	struct btrfs_space_info *space_info;
-	u64 flags;
-
-	if (owner < BTRFS_FIRST_FREE_OBJECTID) {
-		if (root_objectid == BTRFS_CHUNK_TREE_OBJECTID)
-			flags = BTRFS_BLOCK_GROUP_SYSTEM;
-		else
-			flags = BTRFS_BLOCK_GROUP_METADATA;
-	} else {
-		flags = BTRFS_BLOCK_GROUP_DATA;
-	}
-
-	space_info = __find_space_info(fs_info, flags);
-	BUG_ON(!space_info); /* Logic bug */
-	percpu_counter_add(&space_info->total_bytes_pinned, num_bytes);
-}
-
-
 static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 				struct btrfs_fs_info *info,
 				struct btrfs_delayed_ref_node *node, u64 parent,
@@ -6845,7 +6891,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 	if (is_data)
 		skinny_metadata = 0;
 
-	ret = lookup_extent_backref(trans, extent_root, path, &iref,
+	ret = lookup_extent_backref(trans, info, path, &iref,
 				    bytenr, num_bytes, parent,
 				    root_objectid, owner_objectid,
 				    owner_offset);
@@ -6877,8 +6923,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 #endif
 		if (!found_extent) {
 			BUG_ON(iref);
-			ret = remove_extent_backref(trans, extent_root, path,
-						    NULL, refs_to_drop,
+			ret = remove_extent_backref(trans, info, path, NULL,
+						    refs_to_drop,
 						    is_data, &last_ref);
 			if (ret) {
 				btrfs_abort_transaction(trans, ret);
@@ -6953,8 +6999,8 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 #ifdef BTRFS_COMPAT_EXTENT_TREE_V0
 	if (item_size < sizeof(*ei)) {
 		BUG_ON(found_extent || extent_slot != path->slots[0]);
-		ret = convert_extent_item_v0(trans, extent_root, path,
-					     owner_objectid, 0);
+		ret = convert_extent_item_v0(trans, info, path, owner_objectid,
+					     0);
 		if (ret < 0) {
 			btrfs_abort_transaction(trans, ret);
 			goto out;
@@ -7021,7 +7067,7 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 			btrfs_mark_buffer_dirty(leaf);
 		}
 		if (found_extent) {
-			ret = remove_extent_backref(trans, extent_root, path,
+			ret = remove_extent_backref(trans, info, path,
 						    iref, refs_to_drop,
 						    is_data, &last_ref);
 			if (ret) {
@@ -7029,8 +7075,6 @@ static int __btrfs_free_extent(struct btrfs_trans_handle *trans,
 				goto out;
 			}
 		}
-		add_pinned_bytes(info, -num_bytes, owner_objectid,
-				 root_objectid);
 	} else {
 		if (found_extent) {
 			BUG_ON(is_data && refs_to_drop !=
@@ -7095,7 +7139,7 @@ static noinline int check_ref_cleanup(struct btrfs_trans_handle *trans,
 
 	delayed_refs = &trans->transaction->delayed_refs;
 	spin_lock(&delayed_refs->lock);
-	head = btrfs_find_delayed_ref_head(trans, bytenr);
+	head = btrfs_find_delayed_ref_head(delayed_refs, bytenr);
 	if (!head)
 		goto out_delayed_unlock;
 
@@ -7162,19 +7206,19 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 	int ret;
 
 	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans,
-						 buf->start, buf->len,
-						 parent,
+		int old_ref_mod, new_ref_mod;
+
+		ret = btrfs_add_delayed_tree_ref(fs_info, trans, buf->start,
+						 buf->len, parent,
 						 root->root_key.objectid,
 						 btrfs_header_level(buf),
-						 BTRFS_DROP_DELAYED_REF, NULL);
+						 BTRFS_DROP_DELAYED_REF, NULL,
+						 &old_ref_mod, &new_ref_mod);
 		BUG_ON(ret); /* -ENOMEM */
+		pin = old_ref_mod >= 0 && new_ref_mod < 0;
 	}
 
-	if (!last_ref)
-		return;
-
-	if (btrfs_header_generation(buf) == trans->transid) {
+	if (last_ref && btrfs_header_generation(buf) == trans->transid) {
 		struct btrfs_block_group_cache *cache;
 
 		if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
@@ -7183,6 +7227,7 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 				goto out;
 		}
 
+		pin = 0;
 		cache = btrfs_lookup_block_group(fs_info, buf->start);
 
 		if (btrfs_header_flag(buf, BTRFS_HEADER_FLAG_WRITTEN)) {
@@ -7198,18 +7243,19 @@ void btrfs_free_tree_block(struct btrfs_trans_handle *trans,
 		btrfs_free_reserved_bytes(cache, buf->len, 0);
 		btrfs_put_block_group(cache);
 		trace_btrfs_reserved_extent_free(fs_info, buf->start, buf->len);
-		pin = 0;
 	}
 out:
 	if (pin)
 		add_pinned_bytes(fs_info, buf->len, btrfs_header_level(buf),
 				 root->root_key.objectid);
 
-	/*
-	 * Deleting the buffer, clear the corrupt flag since it doesn't matter
-	 * anymore.
-	 */
-	clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags);
+	if (last_ref) {
+		/*
+		 * Deleting the buffer, clear the corrupt flag since it doesn't
+		 * matter anymore.
+		 */
+		clear_bit(EXTENT_BUFFER_CORRUPT, &buf->bflags);
+	}
 }
 
 /* Can return -ENOMEM */
@@ -7218,12 +7264,12 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
 		      u64 bytenr, u64 num_bytes, u64 parent, u64 root_objectid,
 		      u64 owner, u64 offset)
 {
+	int old_ref_mod, new_ref_mod;
 	int ret;
 
 	if (btrfs_is_testing(fs_info))
 		return 0;
 
-	add_pinned_bytes(fs_info, num_bytes, owner, root_objectid);
 
 	/*
 	 * tree log blocks never actually go into the extent allocation
@@ -7233,19 +7279,25 @@ int btrfs_free_extent(struct btrfs_trans_handle *trans,
 		WARN_ON(owner >= BTRFS_FIRST_FREE_OBJECTID);
 		/* unlocks the pinned mutex */
 		btrfs_pin_extent(fs_info, bytenr, num_bytes, 1);
+		old_ref_mod = new_ref_mod = 0;
 		ret = 0;
 	} else if (owner < BTRFS_FIRST_FREE_OBJECTID) {
 		ret = btrfs_add_delayed_tree_ref(fs_info, trans, bytenr,
-					num_bytes,
-					parent, root_objectid, (int)owner,
-					BTRFS_DROP_DELAYED_REF, NULL);
+						 num_bytes, parent,
+						 root_objectid, (int)owner,
+						 BTRFS_DROP_DELAYED_REF, NULL,
+						 &old_ref_mod, &new_ref_mod);
 	} else {
 		ret = btrfs_add_delayed_data_ref(fs_info, trans, bytenr,
-						num_bytes,
-						parent, root_objectid, owner,
-						offset, 0,
-						BTRFS_DROP_DELAYED_REF, NULL);
+						 num_bytes, parent,
+						 root_objectid, owner, offset,
+						 0, BTRFS_DROP_DELAYED_REF,
+						 &old_ref_mod, &new_ref_mod);
 	}
+
+	if (ret == 0 && old_ref_mod >= 0 && new_ref_mod < 0)
+		add_pinned_bytes(fs_info, num_bytes, owner, root_objectid);
+
 	return ret;
 }
 
@@ -7419,12 +7471,11 @@ btrfs_release_block_group(struct btrfs_block_group_cache *cache,
  * If there is no suitable free space, we will record the max size of
  * the free space extent currently.
  */
-static noinline int find_free_extent(struct btrfs_root *orig_root,
+static noinline int find_free_extent(struct btrfs_fs_info *fs_info,
 				u64 ram_bytes, u64 num_bytes, u64 empty_size,
 				u64 hint_byte, struct btrfs_key *ins,
 				u64 flags, int delalloc)
 {
-	struct btrfs_fs_info *fs_info = orig_root->fs_info;
 	int ret = 0;
 	struct btrfs_root *root = fs_info->extent_root;
 	struct btrfs_free_cluster *last_ptr = NULL;
@@ -7716,18 +7767,20 @@ unclustered_alloc:
 			last_ptr->fragmented = 1;
 			spin_unlock(&last_ptr->lock);
 		}
-		spin_lock(&block_group->free_space_ctl->tree_lock);
-		if (cached &&
-		    block_group->free_space_ctl->free_space <
-		    num_bytes + empty_cluster + empty_size) {
-			if (block_group->free_space_ctl->free_space >
-			    max_extent_size)
-				max_extent_size =
-					block_group->free_space_ctl->free_space;
-			spin_unlock(&block_group->free_space_ctl->tree_lock);
-			goto loop;
+		if (cached) {
+			struct btrfs_free_space_ctl *ctl =
+				block_group->free_space_ctl;
+
+			spin_lock(&ctl->tree_lock);
+			if (ctl->free_space <
+			    num_bytes + empty_cluster + empty_size) {
+				if (ctl->free_space > max_extent_size)
+					max_extent_size = ctl->free_space;
+				spin_unlock(&ctl->tree_lock);
+				goto loop;
+			}
+			spin_unlock(&ctl->tree_lock);
 		}
-		spin_unlock(&block_group->free_space_ctl->tree_lock);
 
 		offset = btrfs_find_space_for_alloc(block_group, search_start,
 						    num_bytes, empty_size,
@@ -7908,9 +7961,8 @@ static void dump_space_info(struct btrfs_fs_info *fs_info,
 	spin_lock(&info->lock);
 	btrfs_info(fs_info, "space_info %llu has %llu free, is %sfull",
 		   info->flags,
-		   info->total_bytes - info->bytes_used - info->bytes_pinned -
-		   info->bytes_reserved - info->bytes_readonly -
-		   info->bytes_may_use, (info->full) ? "" : "not ");
+		   info->total_bytes - btrfs_space_info_used(info, true),
+		   info->full ? "" : "not ");
 	btrfs_info(fs_info,
 		"space_info total=%llu, used=%llu, pinned=%llu, reserved=%llu, may_use=%llu, readonly=%llu",
 		info->total_bytes, info->bytes_used, info->bytes_pinned,
@@ -7948,10 +8000,10 @@ int btrfs_reserve_extent(struct btrfs_root *root, u64 ram_bytes,
 	u64 flags;
 	int ret;
 
-	flags = btrfs_get_alloc_profile(root, is_data);
+	flags = get_alloc_profile_by_root(root, is_data);
 again:
 	WARN_ON(num_bytes < fs_info->sectorsize);
-	ret = find_free_extent(root, ram_bytes, num_bytes, empty_size,
+	ret = find_free_extent(fs_info, ram_bytes, num_bytes, empty_size,
 			       hint_byte, ins, flags, delalloc);
 	if (!ret && !is_data) {
 		btrfs_dec_block_group_reservations(fs_info, ins->objectid);
@@ -8192,10 +8244,9 @@ int btrfs_alloc_reserved_file_extent(struct btrfs_trans_handle *trans,
 	BUG_ON(root_objectid == BTRFS_TREE_LOG_OBJECTID);
 
 	ret = btrfs_add_delayed_data_ref(fs_info, trans, ins->objectid,
-					 ins->offset, 0,
-					 root_objectid, owner, offset,
-					 ram_bytes, BTRFS_ADD_DELAYED_EXTENT,
-					 NULL);
+					 ins->offset, 0, root_objectid, owner,
+					 offset, ram_bytes,
+					 BTRFS_ADD_DELAYED_EXTENT, NULL, NULL);
 	return ret;
 }
 
@@ -8256,7 +8307,7 @@ btrfs_init_new_buffer(struct btrfs_trans_handle *trans, struct btrfs_root *root,
 	btrfs_set_header_generation(buf, trans->transid);
 	btrfs_set_buffer_lockdep_class(root->root_key.objectid, buf, level);
 	btrfs_tree_lock(buf);
-	clean_tree_block(trans, fs_info, buf);
+	clean_tree_block(fs_info, buf);
 	clear_bit(EXTENT_BUFFER_STALE, &buf->bflags);
 
 	btrfs_set_lock_blocking(buf);
@@ -8351,10 +8402,11 @@ static void unuse_block_rsv(struct btrfs_fs_info *fs_info,
  * returns the tree buffer or an ERR_PTR on error.
  */
 struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
-					struct btrfs_root *root,
-					u64 parent, u64 root_objectid,
-					struct btrfs_disk_key *key, int level,
-					u64 hint, u64 empty_size)
+					     struct btrfs_root *root,
+					     u64 parent, u64 root_objectid,
+					     const struct btrfs_disk_key *key,
+					     int level, u64 hint,
+					     u64 empty_size)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_key ins;
@@ -8414,11 +8466,11 @@ struct extent_buffer *btrfs_alloc_tree_block(struct btrfs_trans_handle *trans,
 		extent_op->is_data = false;
 		extent_op->level = level;
 
-		ret = btrfs_add_delayed_tree_ref(fs_info, trans,
-						 ins.objectid, ins.offset,
-						 parent, root_objectid, level,
+		ret = btrfs_add_delayed_tree_ref(fs_info, trans, ins.objectid,
+						 ins.offset, parent,
+						 root_objectid, level,
 						 BTRFS_ADD_DELAYED_EXTENT,
-						 extent_op);
+						 extent_op, NULL, NULL);
 		if (ret)
 			goto out_free_delayed;
 	}
@@ -8876,7 +8928,7 @@ static noinline int walk_up_proc(struct btrfs_trans_handle *trans,
 			btrfs_set_lock_blocking(eb);
 			path->locks[level] = BTRFS_WRITE_LOCK_BLOCKING;
 		}
-		clean_tree_block(trans, fs_info, eb);
+		clean_tree_block(fs_info, eb);
 	}
 
 	if (eb == root->node) {
@@ -9346,8 +9398,7 @@ static int inc_block_group_ro(struct btrfs_block_group_cache *cache, int force)
 	num_bytes = cache->key.offset - cache->reserved - cache->pinned -
 		    cache->bytes_super - btrfs_block_group_used(&cache->item);
 
-	if (sinfo->bytes_used + sinfo->bytes_reserved + sinfo->bytes_pinned +
-	    sinfo->bytes_may_use + sinfo->bytes_readonly + num_bytes +
+	if (btrfs_space_info_used(sinfo, true) + num_bytes +
 	    min_allocable_bytes <= sinfo->total_bytes) {
 		sinfo->bytes_readonly += num_bytes;
 		cache->ro++;
@@ -9360,17 +9411,16 @@ out:
 	return ret;
 }
 
-int btrfs_inc_block_group_ro(struct btrfs_root *root,
+int btrfs_inc_block_group_ro(struct btrfs_fs_info *fs_info,
 			     struct btrfs_block_group_cache *cache)
 
 {
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_trans_handle *trans;
 	u64 alloc_flags;
 	int ret;
 
 again:
-	trans = btrfs_join_transaction(root);
+	trans = btrfs_join_transaction(fs_info->extent_root);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
@@ -9557,9 +9607,8 @@ int btrfs_can_relocate(struct btrfs_fs_info *fs_info, u64 bytenr)
 	 * all of the extents from this block group.  If we can, we're good
 	 */
 	if ((space_info->total_bytes != block_group->key.offset) &&
-	    (space_info->bytes_used + space_info->bytes_reserved +
-	     space_info->bytes_pinned + space_info->bytes_readonly +
-	     min_free < space_info->total_bytes)) {
+	    (btrfs_space_info_used(space_info, false) + min_free <
+	     space_info->total_bytes)) {
 		spin_unlock(&space_info->lock);
 		goto out;
 	}
@@ -9742,6 +9791,11 @@ void btrfs_put_block_group_cache(struct btrfs_fs_info *info)
 	}
 }
 
+/*
+ * Must be called only after stopping all workers, since we could have block
+ * group caching kthreads running, and therefore they could race with us if we
+ * freed the block groups before stopping them.
+ */
 int btrfs_free_block_groups(struct btrfs_fs_info *info)
 {
 	struct btrfs_block_group_cache *block_group;
@@ -9781,9 +9835,6 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 		list_del(&block_group->list);
 		up_write(&block_group->space_info->groups_sem);
 
-		if (block_group->cached == BTRFS_CACHE_STARTED)
-			wait_block_group_cache_done(block_group);
-
 		/*
 		 * We haven't cached this block group, which means we could
 		 * possibly have excluded extents on this block group.
@@ -9793,6 +9844,7 @@ int btrfs_free_block_groups(struct btrfs_fs_info *info)
 			free_excluded_extents(info, block_group);
 
 		btrfs_remove_free_space_cache(block_group);
+		ASSERT(block_group->cached != BTRFS_CACHE_STARTED);
 		ASSERT(list_empty(&block_group->dirty_list));
 		ASSERT(list_empty(&block_group->io_list));
 		ASSERT(list_empty(&block_group->bg_list));
@@ -9920,6 +9972,7 @@ btrfs_create_block_group_cache(struct btrfs_fs_info *fs_info,
 	btrfs_init_free_space_ctl(cache);
 	atomic_set(&cache->trimming, 0);
 	mutex_init(&cache->free_space_lock);
+	btrfs_init_full_stripe_locks_tree(&cache->full_stripe_locks_root);
 
 	return cache;
 }
@@ -10050,19 +10103,9 @@ int btrfs_read_block_groups(struct btrfs_fs_info *info)
 		}
 
 		trace_btrfs_add_block_group(info, cache, 0);
-		ret = update_space_info(info, cache->flags, found_key.offset,
-					btrfs_block_group_used(&cache->item),
-					cache->bytes_super, &space_info);
-		if (ret) {
-			btrfs_remove_free_space_cache(cache);
-			spin_lock(&info->block_group_cache_lock);
-			rb_erase(&cache->cache_node,
-				 &info->block_group_cache_tree);
-			RB_CLEAR_NODE(&cache->cache_node);
-			spin_unlock(&info->block_group_cache_lock);
-			btrfs_put_block_group(cache);
-			goto error;
-		}
+		update_space_info(info, cache->flags, found_key.offset,
+				  btrfs_block_group_used(&cache->item),
+				  cache->bytes_super, &space_info);
 
 		cache->space_info = space_info;
 
@@ -10194,16 +10237,19 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	}
 #endif
 	/*
-	 * Call to ensure the corresponding space_info object is created and
-	 * assigned to our block group, but don't update its counters just yet.
-	 * We want our bg to be added to the rbtree with its ->space_info set.
+	 * Ensure the corresponding space_info object is created and
+	 * assigned to our block group. We want our bg to be added to the rbtree
+	 * with its ->space_info set.
 	 */
-	ret = update_space_info(fs_info, cache->flags, 0, 0, 0,
-				&cache->space_info);
-	if (ret) {
-		btrfs_remove_free_space_cache(cache);
-		btrfs_put_block_group(cache);
-		return ret;
+	cache->space_info = __find_space_info(fs_info, cache->flags);
+	if (!cache->space_info) {
+		ret = create_space_info(fs_info, cache->flags,
+				       &cache->space_info);
+		if (ret) {
+			btrfs_remove_free_space_cache(cache);
+			btrfs_put_block_group(cache);
+			return ret;
+		}
 	}
 
 	ret = btrfs_add_block_group_cache(fs_info, cache);
@@ -10218,18 +10264,8 @@ int btrfs_make_block_group(struct btrfs_trans_handle *trans,
 	 * the rbtree, update the space info's counters.
 	 */
 	trace_btrfs_add_block_group(fs_info, cache, 1);
-	ret = update_space_info(fs_info, cache->flags, size, bytes_used,
+	update_space_info(fs_info, cache->flags, size, bytes_used,
 				cache->bytes_super, &cache->space_info);
-	if (ret) {
-		btrfs_remove_free_space_cache(cache);
-		spin_lock(&fs_info->block_group_cache_lock);
-		rb_erase(&cache->cache_node,
-			 &fs_info->block_group_cache_tree);
-		RB_CLEAR_NODE(&cache->cache_node);
-		spin_unlock(&fs_info->block_group_cache_lock);
-		btrfs_put_block_group(cache);
-		return ret;
-	}
 	update_global_block_rsv(fs_info);
 
 	__link_block_group(cache->space_info, cache);
@@ -10317,7 +10353,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	 * get the inode first so any iput calls done for the io_list
 	 * aren't the final iput (no unlinks allowed now)
 	 */
-	inode = lookup_free_space_inode(tree_root, block_group, path);
+	inode = lookup_free_space_inode(fs_info, block_group, path);
 
 	mutex_lock(&trans->transaction->cache_write_mutex);
 	/*
@@ -10344,7 +10380,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 	mutex_unlock(&trans->transaction->cache_write_mutex);
 
 	if (!IS_ERR(inode)) {
-		ret = btrfs_orphan_add(trans, inode);
+		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 		if (ret) {
 			btrfs_add_delayed_iput(inode);
 			goto out;
@@ -10419,7 +10455,7 @@ int btrfs_remove_block_group(struct btrfs_trans_handle *trans,
 				    &fs_info->caching_block_groups, list)
 				if (ctl->block_group == block_group) {
 					caching_ctl = ctl;
-					atomic_inc(&caching_ctl->count);
+					refcount_inc(&caching_ctl->count);
 					break;
 				}
 		}
@@ -10777,21 +10813,21 @@ int btrfs_init_space_info(struct btrfs_fs_info *fs_info)
 		mixed = 1;
 
 	flags = BTRFS_BLOCK_GROUP_SYSTEM;
-	ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
+	ret = create_space_info(fs_info, flags, &space_info);
 	if (ret)
 		goto out;
 
 	if (mixed) {
 		flags = BTRFS_BLOCK_GROUP_METADATA | BTRFS_BLOCK_GROUP_DATA;
-		ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
+		ret = create_space_info(fs_info, flags, &space_info);
 	} else {
 		flags = BTRFS_BLOCK_GROUP_METADATA;
-		ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
+		ret = create_space_info(fs_info, flags, &space_info);
 		if (ret)
 			goto out;
 
 		flags = BTRFS_BLOCK_GROUP_DATA;
-		ret = update_space_info(fs_info, flags, 0, 0, 0, &space_info);
+		ret = create_space_info(fs_info, flags, &space_info);
 	}
 out:
 	return ret;
@@ -10853,7 +10889,7 @@ static int btrfs_trim_free_extents(struct btrfs_device *device,
 		spin_lock(&fs_info->trans_lock);
 		trans = fs_info->running_transaction;
 		if (trans)
-			atomic_inc(&trans->use_count);
+			refcount_inc(&trans->use_count);
 		spin_unlock(&fs_info->trans_lock);
 
 		ret = find_free_dev_extent_start(trans, device, minlen, start,
diff --git a/fs/btrfs/extent_io.c b/fs/btrfs/extent_io.c
index 4ac383a3a649..0aff9b278c19 100644
--- a/fs/btrfs/extent_io.c
+++ b/fs/btrfs/extent_io.c
@@ -68,7 +68,7 @@ void btrfs_leak_debug_check(void)
 		pr_err("BTRFS: state leak: start %llu end %llu state %u in tree %d refs %d\n",
 		       state->start, state->end, state->state,
 		       extent_state_in_tree(state),
-		       atomic_read(&state->refs));
+		       refcount_read(&state->refs));
 		list_del(&state->leak_list);
 		kmem_cache_free(extent_state_cache, state);
 	}
@@ -87,19 +87,9 @@ void btrfs_leak_debug_check(void)
 static inline void __btrfs_debug_check_extent_io_range(const char *caller,
 		struct extent_io_tree *tree, u64 start, u64 end)
 {
-	struct inode *inode;
-	u64 isize;
-
-	if (!tree->mapping)
-		return;
-
-	inode = tree->mapping->host;
-	isize = i_size_read(inode);
-	if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) {
-		btrfs_debug_rl(BTRFS_I(inode)->root->fs_info,
-		    "%s: ino %llu isize %llu odd range [%llu,%llu]",
-				caller, btrfs_ino(inode), isize, start, end);
-	}
+	if (tree->ops && tree->ops->check_extent_io_range)
+		tree->ops->check_extent_io_range(tree->private_data, caller,
+						 start, end);
 }
 #else
 #define btrfs_leak_debug_add(new, head)	do {} while (0)
@@ -144,7 +134,7 @@ static void add_extent_changeset(struct extent_state *state, unsigned bits,
 	if (!set && (state->state & bits) == 0)
 		return;
 	changeset->bytes_changed += state->end - state->start + 1;
-	ret = ulist_add(changeset->range_changed, state->start, state->end,
+	ret = ulist_add(&changeset->range_changed, state->start, state->end,
 			GFP_ATOMIC);
 	/* ENOMEM */
 	BUG_ON(ret < 0);
@@ -154,9 +144,9 @@ static noinline void flush_write_bio(void *data);
 static inline struct btrfs_fs_info *
 tree_fs_info(struct extent_io_tree *tree)
 {
-	if (!tree->mapping)
-		return NULL;
-	return btrfs_sb(tree->mapping->host->i_sb);
+	if (tree->ops)
+		return tree->ops->tree_fs_info(tree->private_data);
+	return NULL;
 }
 
 int __init extent_io_init(void)
@@ -174,7 +164,8 @@ int __init extent_io_init(void)
 		goto free_state_cache;
 
 	btrfs_bioset = bioset_create(BIO_POOL_SIZE,
-				     offsetof(struct btrfs_io_bio, bio));
+				     offsetof(struct btrfs_io_bio, bio),
+				     BIOSET_NEED_BVECS);
 	if (!btrfs_bioset)
 		goto free_buffer_cache;
 
@@ -213,19 +204,24 @@ void extent_io_exit(void)
 }
 
 void extent_io_tree_init(struct extent_io_tree *tree,
-			 struct address_space *mapping)
+			 void *private_data)
 {
 	tree->state = RB_ROOT;
 	tree->ops = NULL;
 	tree->dirty_bytes = 0;
 	spin_lock_init(&tree->lock);
-	tree->mapping = mapping;
+	tree->private_data = private_data;
 }
 
 static struct extent_state *alloc_extent_state(gfp_t mask)
 {
 	struct extent_state *state;
 
+	/*
+	 * The given mask might be not appropriate for the slab allocator,
+	 * drop the unsupported bits
+	 */
+	mask &= ~(__GFP_DMA32|__GFP_HIGHMEM);
 	state = kmem_cache_alloc(extent_state_cache, mask);
 	if (!state)
 		return state;
@@ -233,7 +229,7 @@ static struct extent_state *alloc_extent_state(gfp_t mask)
 	state->failrec = NULL;
 	RB_CLEAR_NODE(&state->rb_node);
 	btrfs_leak_debug_add(&state->leak_list, &states);
-	atomic_set(&state->refs, 1);
+	refcount_set(&state->refs, 1);
 	init_waitqueue_head(&state->wq);
 	trace_alloc_extent_state(state, mask, _RET_IP_);
 	return state;
@@ -243,7 +239,7 @@ void free_extent_state(struct extent_state *state)
 {
 	if (!state)
 		return;
-	if (atomic_dec_and_test(&state->refs)) {
+	if (refcount_dec_and_test(&state->refs)) {
 		WARN_ON(extent_state_in_tree(state));
 		btrfs_leak_debug_del(&state->leak_list);
 		trace_free_extent_state(state, _RET_IP_);
@@ -364,8 +360,7 @@ static void merge_cb(struct extent_io_tree *tree, struct extent_state *new,
 		     struct extent_state *other)
 {
 	if (tree->ops && tree->ops->merge_extent_hook)
-		tree->ops->merge_extent_hook(tree->mapping->host, new,
-					     other);
+		tree->ops->merge_extent_hook(tree->private_data, new, other);
 }
 
 /*
@@ -416,14 +411,14 @@ static void set_state_cb(struct extent_io_tree *tree,
 			 struct extent_state *state, unsigned *bits)
 {
 	if (tree->ops && tree->ops->set_bit_hook)
-		tree->ops->set_bit_hook(tree->mapping->host, state, bits);
+		tree->ops->set_bit_hook(tree->private_data, state, bits);
 }
 
 static void clear_state_cb(struct extent_io_tree *tree,
 			   struct extent_state *state, unsigned *bits)
 {
 	if (tree->ops && tree->ops->clear_bit_hook)
-		tree->ops->clear_bit_hook(tree->mapping->host, state, bits);
+		tree->ops->clear_bit_hook(tree->private_data, state, bits);
 }
 
 static void set_state_bits(struct extent_io_tree *tree,
@@ -472,7 +467,7 @@ static void split_cb(struct extent_io_tree *tree, struct extent_state *orig,
 		     u64 split)
 {
 	if (tree->ops && tree->ops->split_extent_hook)
-		tree->ops->split_extent_hook(tree->mapping->host, orig, split);
+		tree->ops->split_extent_hook(tree->private_data, orig, split);
 }
 
 /*
@@ -635,7 +630,7 @@ again:
 		if (cached && extent_state_in_tree(cached) &&
 		    cached->start <= start && cached->end > start) {
 			if (clear)
-				atomic_dec(&cached->refs);
+				refcount_dec(&cached->refs);
 			state = cached;
 			goto hit_next;
 		}
@@ -787,7 +782,7 @@ process_node:
 
 		if (state->state & bits) {
 			start = state->start;
-			atomic_inc(&state->refs);
+			refcount_inc(&state->refs);
 			wait_on_state(tree, state);
 			free_extent_state(state);
 			goto again;
@@ -828,7 +823,7 @@ static void cache_state_if_flags(struct extent_state *state,
 	if (cached_ptr && !(*cached_ptr)) {
 		if (!flags || (state->state & flags)) {
 			*cached_ptr = state;
-			atomic_inc(&state->refs);
+			refcount_inc(&state->refs);
 		}
 	}
 }
@@ -1396,17 +1391,7 @@ void extent_range_redirty_for_io(struct inode *inode, u64 start, u64 end)
  */
 static void set_range_writeback(struct extent_io_tree *tree, u64 start, u64 end)
 {
-	unsigned long index = start >> PAGE_SHIFT;
-	unsigned long end_index = end >> PAGE_SHIFT;
-	struct page *page;
-
-	while (index <= end_index) {
-		page = find_get_page(tree->mapping, index);
-		BUG_ON(!page); /* Pages should be in the extent_io_tree */
-		set_page_writeback(page);
-		put_page(page);
-		index++;
-	}
+	tree->ops->set_range_writeback(tree->private_data, start, end);
 }
 
 /* find the first state struct with 'bits' set after 'start', and
@@ -1532,7 +1517,7 @@ static noinline u64 find_delalloc_range(struct extent_io_tree *tree,
 		if (!found) {
 			*start = state->start;
 			*cached_state = state;
-			atomic_inc(&state->refs);
+			refcount_inc(&state->refs);
 		}
 		found++;
 		*end = state->end;
@@ -1549,33 +1534,24 @@ out:
 	return found;
 }
 
+static int __process_pages_contig(struct address_space *mapping,
+				  struct page *locked_page,
+				  pgoff_t start_index, pgoff_t end_index,
+				  unsigned long page_ops, pgoff_t *index_ret);
+
 static noinline void __unlock_for_delalloc(struct inode *inode,
 					   struct page *locked_page,
 					   u64 start, u64 end)
 {
-	int ret;
-	struct page *pages[16];
 	unsigned long index = start >> PAGE_SHIFT;
 	unsigned long end_index = end >> PAGE_SHIFT;
-	unsigned long nr_pages = end_index - index + 1;
-	int i;
 
+	ASSERT(locked_page);
 	if (index == locked_page->index && end_index == index)
 		return;
 
-	while (nr_pages > 0) {
-		ret = find_get_pages_contig(inode->i_mapping, index,
-				     min_t(unsigned long, nr_pages,
-				     ARRAY_SIZE(pages)), pages);
-		for (i = 0; i < ret; i++) {
-			if (pages[i] != locked_page)
-				unlock_page(pages[i]);
-			put_page(pages[i]);
-		}
-		nr_pages -= ret;
-		index += ret;
-		cond_resched();
-	}
+	__process_pages_contig(inode->i_mapping, locked_page, index, end_index,
+			       PAGE_UNLOCK, NULL);
 }
 
 static noinline int lock_delalloc_pages(struct inode *inode,
@@ -1584,59 +1560,19 @@ static noinline int lock_delalloc_pages(struct inode *inode,
 					u64 delalloc_end)
 {
 	unsigned long index = delalloc_start >> PAGE_SHIFT;
-	unsigned long start_index = index;
+	unsigned long index_ret = index;
 	unsigned long end_index = delalloc_end >> PAGE_SHIFT;
-	unsigned long pages_locked = 0;
-	struct page *pages[16];
-	unsigned long nrpages;
 	int ret;
-	int i;
 
-	/* the caller is responsible for locking the start index */
+	ASSERT(locked_page);
 	if (index == locked_page->index && index == end_index)
 		return 0;
 
-	/* skip the page at the start index */
-	nrpages = end_index - index + 1;
-	while (nrpages > 0) {
-		ret = find_get_pages_contig(inode->i_mapping, index,
-				     min_t(unsigned long,
-				     nrpages, ARRAY_SIZE(pages)), pages);
-		if (ret == 0) {
-			ret = -EAGAIN;
-			goto done;
-		}
-		/* now we have an array of pages, lock them all */
-		for (i = 0; i < ret; i++) {
-			/*
-			 * the caller is taking responsibility for
-			 * locked_page
-			 */
-			if (pages[i] != locked_page) {
-				lock_page(pages[i]);
-				if (!PageDirty(pages[i]) ||
-				    pages[i]->mapping != inode->i_mapping) {
-					ret = -EAGAIN;
-					unlock_page(pages[i]);
-					put_page(pages[i]);
-					goto done;
-				}
-			}
-			put_page(pages[i]);
-			pages_locked++;
-		}
-		nrpages -= ret;
-		index += ret;
-		cond_resched();
-	}
-	ret = 0;
-done:
-	if (ret && pages_locked) {
-		__unlock_for_delalloc(inode, locked_page,
-			      delalloc_start,
-			      ((u64)(start_index + pages_locked - 1)) <<
-			      PAGE_SHIFT);
-	}
+	ret = __process_pages_contig(inode->i_mapping, locked_page, index,
+				     end_index, PAGE_LOCK, &index_ret);
+	if (ret == -EAGAIN)
+		__unlock_for_delalloc(inode, locked_page, delalloc_start,
+				      (u64)index_ret << PAGE_SHIFT);
 	return ret;
 }
 
@@ -1726,37 +1662,48 @@ out_failed:
 	return found;
 }
 
-void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
-				 u64 delalloc_end, struct page *locked_page,
-				 unsigned clear_bits,
-				 unsigned long page_ops)
+static int __process_pages_contig(struct address_space *mapping,
+				  struct page *locked_page,
+				  pgoff_t start_index, pgoff_t end_index,
+				  unsigned long page_ops, pgoff_t *index_ret)
 {
-	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
-	int ret;
+	unsigned long nr_pages = end_index - start_index + 1;
+	unsigned long pages_locked = 0;
+	pgoff_t index = start_index;
 	struct page *pages[16];
-	unsigned long index = start >> PAGE_SHIFT;
-	unsigned long end_index = end >> PAGE_SHIFT;
-	unsigned long nr_pages = end_index - index + 1;
+	unsigned ret;
+	int err = 0;
 	int i;
 
-	clear_extent_bit(tree, start, end, clear_bits, 1, 0, NULL, GFP_NOFS);
-	if (page_ops == 0)
-		return;
+	if (page_ops & PAGE_LOCK) {
+		ASSERT(page_ops == PAGE_LOCK);
+		ASSERT(index_ret && *index_ret == start_index);
+	}
 
 	if ((page_ops & PAGE_SET_ERROR) && nr_pages > 0)
-		mapping_set_error(inode->i_mapping, -EIO);
+		mapping_set_error(mapping, -EIO);
 
 	while (nr_pages > 0) {
-		ret = find_get_pages_contig(inode->i_mapping, index,
+		ret = find_get_pages_contig(mapping, index,
 				     min_t(unsigned long,
 				     nr_pages, ARRAY_SIZE(pages)), pages);
-		for (i = 0; i < ret; i++) {
+		if (ret == 0) {
+			/*
+			 * Only if we're going to lock these pages,
+			 * can we find nothing at @index.
+			 */
+			ASSERT(page_ops & PAGE_LOCK);
+			err = -EAGAIN;
+			goto out;
+		}
 
+		for (i = 0; i < ret; i++) {
 			if (page_ops & PAGE_SET_PRIVATE2)
 				SetPagePrivate2(pages[i]);
 
 			if (pages[i] == locked_page) {
 				put_page(pages[i]);
+				pages_locked++;
 				continue;
 			}
 			if (page_ops & PAGE_CLEAR_DIRTY)
@@ -1769,12 +1716,40 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 				end_page_writeback(pages[i]);
 			if (page_ops & PAGE_UNLOCK)
 				unlock_page(pages[i]);
+			if (page_ops & PAGE_LOCK) {
+				lock_page(pages[i]);
+				if (!PageDirty(pages[i]) ||
+				    pages[i]->mapping != mapping) {
+					unlock_page(pages[i]);
+					put_page(pages[i]);
+					err = -EAGAIN;
+					goto out;
+				}
+			}
 			put_page(pages[i]);
+			pages_locked++;
 		}
 		nr_pages -= ret;
 		index += ret;
 		cond_resched();
 	}
+out:
+	if (err && index_ret)
+		*index_ret = start_index + pages_locked - 1;
+	return err;
+}
+
+void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
+				 u64 delalloc_end, struct page *locked_page,
+				 unsigned clear_bits,
+				 unsigned long page_ops)
+{
+	clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, clear_bits, 1, 0,
+			 NULL, GFP_NOFS);
+
+	__process_pages_contig(inode->i_mapping, locked_page,
+			       start >> PAGE_SHIFT, end >> PAGE_SHIFT,
+			       page_ops, NULL);
 }
 
 /*
@@ -1965,11 +1940,12 @@ static void check_page_uptodate(struct extent_io_tree *tree, struct page *page)
 		SetPageUptodate(page);
 }
 
-int free_io_failure(struct inode *inode, struct io_failure_record *rec)
+int free_io_failure(struct extent_io_tree *failure_tree,
+		    struct extent_io_tree *io_tree,
+		    struct io_failure_record *rec)
 {
 	int ret;
 	int err = 0;
-	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
 
 	set_state_failrec(failure_tree, rec->start, NULL);
 	ret = clear_extent_bits(failure_tree, rec->start,
@@ -1978,7 +1954,7 @@ int free_io_failure(struct inode *inode, struct io_failure_record *rec)
 	if (ret)
 		err = ret;
 
-	ret = clear_extent_bits(&BTRFS_I(inode)->io_tree, rec->start,
+	ret = clear_extent_bits(io_tree, rec->start,
 				rec->start + rec->len - 1,
 				EXTENT_DAMAGED);
 	if (ret && !err)
@@ -1998,28 +1974,21 @@ int free_io_failure(struct inode *inode, struct io_failure_record *rec)
  * currently, there can be no more than two copies of every data bit. thus,
  * exactly one rewrite is required.
  */
-int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
-		      struct page *page, unsigned int pg_offset, int mirror_num)
+int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
+		      u64 length, u64 logical, struct page *page,
+		      unsigned int pg_offset, int mirror_num)
 {
-	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	struct bio *bio;
 	struct btrfs_device *dev;
 	u64 map_length = 0;
 	u64 sector;
 	struct btrfs_bio *bbio = NULL;
-	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
 	int ret;
 
 	ASSERT(!(fs_info->sb->s_flags & MS_RDONLY));
 	BUG_ON(!mirror_num);
 
-	/* we can't repair anything in raid56 yet */
-	if (btrfs_is_parity_mirror(map_tree, logical, length, mirror_num))
-		return 0;
-
-	bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
-	if (!bio)
-		return -EIO;
+	bio = btrfs_io_bio_alloc(1);
 	bio->bi_iter.bi_size = 0;
 	map_length = length;
 
@@ -2029,17 +1998,35 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 	 * read repair operation.
 	 */
 	btrfs_bio_counter_inc_blocked(fs_info);
-	ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical,
-			      &map_length, &bbio, mirror_num);
-	if (ret) {
-		btrfs_bio_counter_dec(fs_info);
-		bio_put(bio);
-		return -EIO;
+	if (btrfs_is_parity_mirror(fs_info, logical, length, mirror_num)) {
+		/*
+		 * Note that we don't use BTRFS_MAP_WRITE because it's supposed
+		 * to update all raid stripes, but here we just want to correct
+		 * bad stripe, thus BTRFS_MAP_READ is abused to only get the bad
+		 * stripe's dev and sector.
+		 */
+		ret = btrfs_map_block(fs_info, BTRFS_MAP_READ, logical,
+				      &map_length, &bbio, 0);
+		if (ret) {
+			btrfs_bio_counter_dec(fs_info);
+			bio_put(bio);
+			return -EIO;
+		}
+		ASSERT(bbio->mirror_num == 1);
+	} else {
+		ret = btrfs_map_block(fs_info, BTRFS_MAP_WRITE, logical,
+				      &map_length, &bbio, mirror_num);
+		if (ret) {
+			btrfs_bio_counter_dec(fs_info);
+			bio_put(bio);
+			return -EIO;
+		}
+		BUG_ON(mirror_num != bbio->mirror_num);
 	}
-	BUG_ON(mirror_num != bbio->mirror_num);
-	sector = bbio->stripes[mirror_num-1].physical >> 9;
+
+	sector = bbio->stripes[bbio->mirror_num - 1].physical >> 9;
 	bio->bi_iter.bi_sector = sector;
-	dev = bbio->stripes[mirror_num-1].dev;
+	dev = bbio->stripes[bbio->mirror_num - 1].dev;
 	btrfs_put_bbio(bbio);
 	if (!dev || !dev->bdev || !dev->writeable) {
 		btrfs_bio_counter_dec(fs_info);
@@ -2060,7 +2047,7 @@ int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
 
 	btrfs_info_rl_in_rcu(fs_info,
 		"read error corrected: ino %llu off %llu (dev %s sector %llu)",
-				  btrfs_ino(inode), start,
+				  ino, start,
 				  rcu_str_deref(dev->name), sector);
 	btrfs_bio_counter_dec(fs_info);
 	bio_put(bio);
@@ -2080,8 +2067,7 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info,
 	for (i = 0; i < num_pages; i++) {
 		struct page *p = eb->pages[i];
 
-		ret = repair_io_failure(fs_info->btree_inode, start,
-					PAGE_SIZE, start, p,
+		ret = repair_io_failure(fs_info, 0, start, PAGE_SIZE, start, p,
 					start - page_offset(p), mirror_num);
 		if (ret)
 			break;
@@ -2095,24 +2081,24 @@ int repair_eb_io_failure(struct btrfs_fs_info *fs_info,
  * each time an IO finishes, we do a fast check in the IO failure tree
  * to see if we need to process or clean up an io_failure_record
  */
-int clean_io_failure(struct inode *inode, u64 start, struct page *page,
-		     unsigned int pg_offset)
+int clean_io_failure(struct btrfs_fs_info *fs_info,
+		     struct extent_io_tree *failure_tree,
+		     struct extent_io_tree *io_tree, u64 start,
+		     struct page *page, u64 ino, unsigned int pg_offset)
 {
 	u64 private;
 	struct io_failure_record *failrec;
-	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
 	struct extent_state *state;
 	int num_copies;
 	int ret;
 
 	private = 0;
-	ret = count_range_bits(&BTRFS_I(inode)->io_failure_tree, &private,
-				(u64)-1, 1, EXTENT_DIRTY, 0);
+	ret = count_range_bits(failure_tree, &private, (u64)-1, 1,
+			       EXTENT_DIRTY, 0);
 	if (!ret)
 		return 0;
 
-	ret = get_state_failrec(&BTRFS_I(inode)->io_failure_tree, start,
-			&failrec);
+	ret = get_state_failrec(failure_tree, start, &failrec);
 	if (ret)
 		return 0;
 
@@ -2128,25 +2114,25 @@ int clean_io_failure(struct inode *inode, u64 start, struct page *page,
 	if (fs_info->sb->s_flags & MS_RDONLY)
 		goto out;
 
-	spin_lock(&BTRFS_I(inode)->io_tree.lock);
-	state = find_first_extent_bit_state(&BTRFS_I(inode)->io_tree,
+	spin_lock(&io_tree->lock);
+	state = find_first_extent_bit_state(io_tree,
 					    failrec->start,
 					    EXTENT_LOCKED);
-	spin_unlock(&BTRFS_I(inode)->io_tree.lock);
+	spin_unlock(&io_tree->lock);
 
 	if (state && state->start <= failrec->start &&
 	    state->end >= failrec->start + failrec->len - 1) {
 		num_copies = btrfs_num_copies(fs_info, failrec->logical,
 					      failrec->len);
 		if (num_copies > 1)  {
-			repair_io_failure(inode, start, failrec->len,
-					  failrec->logical, page,
-					  pg_offset, failrec->failed_mirror);
+			repair_io_failure(fs_info, ino, start, failrec->len,
+					  failrec->logical, page, pg_offset,
+					  failrec->failed_mirror);
 		}
 	}
 
 out:
-	free_io_failure(inode, failrec);
+	free_io_failure(failure_tree, io_tree, failrec);
 
 	return 0;
 }
@@ -2157,9 +2143,9 @@ out:
  * - under ordered extent
  * - the inode is freeing
  */
-void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end)
+void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start, u64 end)
 {
-	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
+	struct extent_io_tree *failure_tree = &inode->io_failure_tree;
 	struct io_failure_record *failrec;
 	struct extent_state *state, *next;
 
@@ -2272,7 +2258,7 @@ int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 	return 0;
 }
 
-int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
+bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
 			   struct io_failure_record *failrec, int failed_mirror)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
@@ -2288,7 +2274,7 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
 		btrfs_debug(fs_info,
 			"Check Repairable: cannot repair, num_copies=%d, next_mirror %d, failed_mirror %d",
 			num_copies, failrec->this_mirror, failed_mirror);
-		return 0;
+		return false;
 	}
 
 	/*
@@ -2329,10 +2315,10 @@ int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
 		btrfs_debug(fs_info,
 			"Check Repairable: (fail) num_copies=%d, next_mirror %d, failed_mirror %d",
 			num_copies, failrec->this_mirror, failed_mirror);
-		return 0;
+		return false;
 	}
 
-	return 1;
+	return true;
 }
 
 
@@ -2346,10 +2332,7 @@ struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
 	struct btrfs_io_bio *btrfs_failed_bio;
 	struct btrfs_io_bio *btrfs_bio;
 
-	bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
-	if (!bio)
-		return NULL;
-
+	bio = btrfs_io_bio_alloc(1);
 	bio->bi_end_io = endio_func;
 	bio->bi_iter.bi_sector = failrec->logical >> 9;
 	bio->bi_bdev = fs_info->fs_devices->latest_bdev;
@@ -2387,8 +2370,10 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	struct io_failure_record *failrec;
 	struct inode *inode = page->mapping->host;
 	struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
+	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
 	struct bio *bio;
 	int read_mode = 0;
+	blk_status_t status;
 	int ret;
 
 	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
@@ -2397,9 +2382,9 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 	if (ret)
 		return ret;
 
-	ret = btrfs_check_repairable(inode, failed_bio, failrec, failed_mirror);
-	if (!ret) {
-		free_io_failure(inode, failrec);
+	if (!btrfs_check_repairable(inode, failed_bio, failrec,
+				    failed_mirror)) {
+		free_io_failure(failure_tree, tree, failrec);
 		return -EIO;
 	}
 
@@ -2411,21 +2396,18 @@ static int bio_readpage_error(struct bio *failed_bio, u64 phy_offset,
 				      start - page_offset(page),
 				      (int)phy_offset, failed_bio->bi_end_io,
 				      NULL);
-	if (!bio) {
-		free_io_failure(inode, failrec);
-		return -EIO;
-	}
 	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
 
 	btrfs_debug(btrfs_sb(inode->i_sb),
 		"Repair Read Error: submitting new read[%#x] to this_mirror=%d, in_validation=%d",
 		read_mode, failrec->this_mirror, failrec->in_validation);
 
-	ret = tree->ops->submit_bio_hook(inode, bio, failrec->this_mirror,
+	status = tree->ops->submit_bio_hook(tree->private_data, bio, failrec->this_mirror,
 					 failrec->bio_flags, 0);
-	if (ret) {
-		free_io_failure(inode, failrec);
+	if (status) {
+		free_io_failure(failure_tree, tree, failrec);
 		bio_put(bio);
+		ret = blk_status_to_errno(status);
 	}
 
 	return ret;
@@ -2441,17 +2423,14 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
 
 	tree = &BTRFS_I(page->mapping->host)->io_tree;
 
-	if (tree->ops && tree->ops->writepage_end_io_hook) {
-		ret = tree->ops->writepage_end_io_hook(page, start,
-					       end, NULL, uptodate);
-		if (ret)
-			uptodate = 0;
-	}
+	if (tree->ops && tree->ops->writepage_end_io_hook)
+		tree->ops->writepage_end_io_hook(page, start, end, NULL,
+				uptodate);
 
 	if (!uptodate) {
 		ClearPageUptodate(page);
 		SetPageError(page);
-		ret = ret < 0 ? ret : -EIO;
+		ret = err < 0 ? err : -EIO;
 		mapping_set_error(page->mapping, ret);
 	}
 }
@@ -2467,11 +2446,13 @@ void end_extent_writepage(struct page *page, int err, u64 start, u64 end)
  */
 static void end_bio_extent_writepage(struct bio *bio)
 {
+	int error = blk_status_to_errno(bio->bi_status);
 	struct bio_vec *bvec;
 	u64 start;
 	u64 end;
 	int i;
 
+	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 		struct inode *inode = page->mapping->host;
@@ -2496,7 +2477,7 @@ static void end_bio_extent_writepage(struct bio *bio)
 		start = page_offset(page);
 		end = start + bvec->bv_offset + bvec->bv_len - 1;
 
-		end_extent_writepage(page, bio->bi_error, start, end);
+		end_extent_writepage(page, error, start, end);
 		end_page_writeback(page);
 	}
 
@@ -2529,9 +2510,9 @@ endio_readpage_release_extent(struct extent_io_tree *tree, u64 start, u64 len,
 static void end_bio_extent_readpage(struct bio *bio)
 {
 	struct bio_vec *bvec;
-	int uptodate = !bio->bi_error;
+	int uptodate = !bio->bi_status;
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
-	struct extent_io_tree *tree;
+	struct extent_io_tree *tree, *failure_tree;
 	u64 offset = 0;
 	u64 start;
 	u64 end;
@@ -2542,6 +2523,7 @@ static void end_bio_extent_readpage(struct bio *bio)
 	int ret;
 	int i;
 
+	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 		struct inode *inode = page->mapping->host;
@@ -2549,9 +2531,10 @@ static void end_bio_extent_readpage(struct bio *bio)
 
 		btrfs_debug(fs_info,
 			"end_bio_extent_readpage: bi_sector=%llu, err=%d, mirror=%u",
-			(u64)bio->bi_iter.bi_sector, bio->bi_error,
+			(u64)bio->bi_iter.bi_sector, bio->bi_status,
 			io_bio->mirror_num);
 		tree = &BTRFS_I(inode)->io_tree;
+		failure_tree = &BTRFS_I(inode)->io_failure_tree;
 
 		/* We always issue full-page reads, but if some block
 		 * in a page fails to read, blk_update_request() will
@@ -2574,42 +2557,54 @@ static void end_bio_extent_readpage(struct bio *bio)
 		len = bvec->bv_len;
 
 		mirror = io_bio->mirror_num;
-		if (likely(uptodate && tree->ops &&
-			   tree->ops->readpage_end_io_hook)) {
+		if (likely(uptodate && tree->ops)) {
 			ret = tree->ops->readpage_end_io_hook(io_bio, offset,
 							      page, start, end,
 							      mirror);
 			if (ret)
 				uptodate = 0;
 			else
-				clean_io_failure(inode, start, page, 0);
+				clean_io_failure(BTRFS_I(inode)->root->fs_info,
+						 failure_tree, tree, start,
+						 page,
+						 btrfs_ino(BTRFS_I(inode)), 0);
 		}
 
 		if (likely(uptodate))
 			goto readpage_ok;
 
-		if (tree->ops && tree->ops->readpage_io_failed_hook) {
+		if (tree->ops) {
 			ret = tree->ops->readpage_io_failed_hook(page, mirror);
-			if (!ret && !bio->bi_error)
-				uptodate = 1;
-		} else {
+			if (ret == -EAGAIN) {
+				/*
+				 * Data inode's readpage_io_failed_hook() always
+				 * returns -EAGAIN.
+				 *
+				 * The generic bio_readpage_error handles errors
+				 * the following way: If possible, new read
+				 * requests are created and submitted and will
+				 * end up in end_bio_extent_readpage as well (if
+				 * we're lucky, not in the !uptodate case). In
+				 * that case it returns 0 and we just go on with
+				 * the next page in our bio. If it can't handle
+				 * the error it will return -EIO and we remain
+				 * responsible for that page.
+				 */
+				ret = bio_readpage_error(bio, offset, page,
+							 start, end, mirror);
+				if (ret == 0) {
+					uptodate = !bio->bi_status;
+					offset += len;
+					continue;
+				}
+			}
+
 			/*
-			 * The generic bio_readpage_error handles errors the
-			 * following way: If possible, new read requests are
-			 * created and submitted and will end up in
-			 * end_bio_extent_readpage as well (if we're lucky, not
-			 * in the !uptodate case). In that case it returns 0 and
-			 * we just go on with the next page in our bio. If it
-			 * can't handle the error it will return -EIO and we
-			 * remain responsible for that page.
+			 * metadata's readpage_io_failed_hook() always returns
+			 * -EIO and fixes nothing.  -EIO is also returned if
+			 * data inode error could not be fixed.
 			 */
-			ret = bio_readpage_error(bio, offset, page, start, end,
-						 mirror);
-			if (ret == 0) {
-				uptodate = !bio->bi_error;
-				offset += len;
-				continue;
-			}
+			ASSERT(ret == -EIO);
 		}
 readpage_ok:
 		if (likely(uptodate)) {
@@ -2656,77 +2651,80 @@ readpage_ok:
 		endio_readpage_release_extent(tree, extent_start, extent_len,
 					      uptodate);
 	if (io_bio->end_io)
-		io_bio->end_io(io_bio, bio->bi_error);
+		io_bio->end_io(io_bio, blk_status_to_errno(bio->bi_status));
 	bio_put(bio);
 }
 
 /*
- * this allocates from the btrfs_bioset.  We're returning a bio right now
- * but you can call btrfs_io_bio for the appropriate container_of magic
+ * Initialize the members up to but not including 'bio'. Use after allocating a
+ * new bio by bio_alloc_bioset as it does not initialize the bytes outside of
+ * 'bio' because use of __GFP_ZERO is not supported.
  */
-struct bio *
-btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs,
-		gfp_t gfp_flags)
+static inline void btrfs_io_bio_init(struct btrfs_io_bio *btrfs_bio)
 {
-	struct btrfs_io_bio *btrfs_bio;
-	struct bio *bio;
-
-	bio = bio_alloc_bioset(gfp_flags, nr_vecs, btrfs_bioset);
+	memset(btrfs_bio, 0, offsetof(struct btrfs_io_bio, bio));
+}
 
-	if (bio == NULL && (current->flags & PF_MEMALLOC)) {
-		while (!bio && (nr_vecs /= 2)) {
-			bio = bio_alloc_bioset(gfp_flags,
-					       nr_vecs, btrfs_bioset);
-		}
-	}
+/*
+ * The following helpers allocate a bio. As it's backed by a bioset, it'll
+ * never fail.  We're returning a bio right now but you can call btrfs_io_bio
+ * for the appropriate container_of magic
+ */
+struct bio *btrfs_bio_alloc(struct block_device *bdev, u64 first_byte)
+{
+	struct bio *bio;
 
-	if (bio) {
-		bio->bi_bdev = bdev;
-		bio->bi_iter.bi_sector = first_sector;
-		btrfs_bio = btrfs_io_bio(bio);
-		btrfs_bio->csum = NULL;
-		btrfs_bio->csum_allocated = NULL;
-		btrfs_bio->end_io = NULL;
-	}
+	bio = bio_alloc_bioset(GFP_NOFS, BIO_MAX_PAGES, btrfs_bioset);
+	bio->bi_bdev = bdev;
+	bio->bi_iter.bi_sector = first_byte >> 9;
+	btrfs_io_bio_init(btrfs_io_bio(bio));
 	return bio;
 }
 
-struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask)
+struct bio *btrfs_bio_clone(struct bio *bio)
 {
 	struct btrfs_io_bio *btrfs_bio;
 	struct bio *new;
 
-	new = bio_clone_bioset(bio, gfp_mask, btrfs_bioset);
-	if (new) {
-		btrfs_bio = btrfs_io_bio(new);
-		btrfs_bio->csum = NULL;
-		btrfs_bio->csum_allocated = NULL;
-		btrfs_bio->end_io = NULL;
-	}
+	/* Bio allocation backed by a bioset does not fail */
+	new = bio_clone_fast(bio, GFP_NOFS, btrfs_bioset);
+	btrfs_bio = btrfs_io_bio(new);
+	btrfs_io_bio_init(btrfs_bio);
+	btrfs_bio->iter = bio->bi_iter;
 	return new;
 }
 
-/* this also allocates from the btrfs_bioset */
-struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs)
+struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs)
 {
-	struct btrfs_io_bio *btrfs_bio;
 	struct bio *bio;
 
-	bio = bio_alloc_bioset(gfp_mask, nr_iovecs, btrfs_bioset);
-	if (bio) {
-		btrfs_bio = btrfs_io_bio(bio);
-		btrfs_bio->csum = NULL;
-		btrfs_bio->csum_allocated = NULL;
-		btrfs_bio->end_io = NULL;
-	}
+	/* Bio allocation backed by a bioset does not fail */
+	bio = bio_alloc_bioset(GFP_NOFS, nr_iovecs, btrfs_bioset);
+	btrfs_io_bio_init(btrfs_io_bio(bio));
 	return bio;
 }
 
+struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size)
+{
+	struct bio *bio;
+	struct btrfs_io_bio *btrfs_bio;
+
+	/* this will never fail when it's backed by a bioset */
+	bio = bio_clone_fast(orig, GFP_NOFS, btrfs_bioset);
+	ASSERT(bio);
+
+	btrfs_bio = btrfs_io_bio(bio);
+	btrfs_io_bio_init(btrfs_bio);
+
+	bio_trim(bio, offset >> 9, size >> 9);
+	btrfs_bio->iter = bio->bi_iter;
+	return bio;
+}
 
 static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
 				       unsigned long bio_flags)
 {
-	int ret = 0;
+	blk_status_t ret = 0;
 	struct bio_vec *bvec = bio->bi_io_vec + bio->bi_vcnt - 1;
 	struct page *page = bvec->bv_page;
 	struct extent_io_tree *tree = bio->bi_private;
@@ -2737,14 +2735,14 @@ static int __must_check submit_one_bio(struct bio *bio, int mirror_num,
 	bio->bi_private = NULL;
 	bio_get(bio);
 
-	if (tree->ops && tree->ops->submit_bio_hook)
-		ret = tree->ops->submit_bio_hook(page->mapping->host, bio,
+	if (tree->ops)
+		ret = tree->ops->submit_bio_hook(tree->private_data, bio,
 					   mirror_num, bio_flags, start);
 	else
 		btrfsic_submit_bio(bio);
 
 	bio_put(bio);
-	return ret;
+	return blk_status_to_errno(ret);
 }
 
 static int merge_bio(struct extent_io_tree *tree, struct page *page,
@@ -2752,7 +2750,7 @@ static int merge_bio(struct extent_io_tree *tree, struct page *page,
 		     unsigned long bio_flags)
 {
 	int ret = 0;
-	if (tree->ops && tree->ops->merge_bio_hook)
+	if (tree->ops)
 		ret = tree->ops->merge_bio_hook(page, offset, size, bio,
 						bio_flags);
 	return ret;
@@ -2765,7 +2763,6 @@ static int submit_extent_page(int op, int op_flags, struct extent_io_tree *tree,
 			      size_t size, unsigned long offset,
 			      struct block_device *bdev,
 			      struct bio **bio_ret,
-			      unsigned long max_pages,
 			      bio_end_io_t end_io_func,
 			      int mirror_num,
 			      unsigned long prev_bio_flags,
@@ -2802,14 +2799,11 @@ static int submit_extent_page(int op, int op_flags, struct extent_io_tree *tree,
 		}
 	}
 
-	bio = btrfs_bio_alloc(bdev, sector, BIO_MAX_PAGES,
-			GFP_NOFS | __GFP_HIGH);
-	if (!bio)
-		return -ENOMEM;
-
+	bio = btrfs_bio_alloc(bdev, sector << 9);
 	bio_add_page(bio, page, page_size, offset);
 	bio->bi_end_io = end_io_func;
 	bio->bi_private = tree;
+	bio->bi_write_hint = page->mapping->host->i_write_hint;
 	bio_set_op_attrs(bio, op, op_flags);
 	if (wbc) {
 		wbc_init_bio(wbc, bio);
@@ -2856,7 +2850,7 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
 		em = *em_cached;
 		if (extent_map_in_tree(em) && start >= em->start &&
 		    start < extent_map_end(em)) {
-			atomic_inc(&em->refs);
+			refcount_inc(&em->refs);
 			return em;
 		}
 
@@ -2864,10 +2858,10 @@ __get_extent_map(struct inode *inode, struct page *page, size_t pg_offset,
 		*em_cached = NULL;
 	}
 
-	em = get_extent(inode, page, pg_offset, start, len, 0);
+	em = get_extent(BTRFS_I(inode), page, pg_offset, start, len, 0);
 	if (em_cached && !IS_ERR_OR_NULL(em)) {
 		BUG_ON(*em_cached);
-		atomic_inc(&em->refs);
+		refcount_inc(&em->refs);
 		*em_cached = em;
 	}
 	return em;
@@ -2931,7 +2925,6 @@ static int __do_readpage(struct extent_io_tree *tree,
 		}
 	}
 	while (cur <= end) {
-		unsigned long pnr = (last_byte >> PAGE_SHIFT) + 1;
 		bool force_bio_submit = false;
 
 		if (cur >= last_byte) {
@@ -3066,10 +3059,9 @@ static int __do_readpage(struct extent_io_tree *tree,
 			continue;
 		}
 
-		pnr -= page->index;
 		ret = submit_extent_page(REQ_OP_READ, read_flags, tree, NULL,
 					 page, sector, disk_io_size, pg_offset,
-					 bdev, bio, pnr,
+					 bdev, bio,
 					 end_bio_extent_readpage, mirror_num,
 					 *bio_flags,
 					 this_bio_flag,
@@ -3110,7 +3102,7 @@ static inline void __do_contiguous_readpages(struct extent_io_tree *tree,
 	inode = pages[0]->mapping->host;
 	while (1) {
 		lock_extent(tree, start, end);
-		ordered = btrfs_lookup_ordered_range(inode, start,
+		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start,
 						     end - start + 1);
 		if (!ordered)
 			break;
@@ -3182,7 +3174,7 @@ static int __extent_read_full_page(struct extent_io_tree *tree,
 
 	while (1) {
 		lock_extent(tree, start, end);
-		ordered = btrfs_lookup_ordered_range(inode, start,
+		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start,
 						PAGE_SIZE);
 		if (!ordered)
 			break;
@@ -3210,7 +3202,7 @@ int extent_read_full_page(struct extent_io_tree *tree, struct page *page,
 	return ret;
 }
 
-static void update_nr_written(struct page *page, struct writeback_control *wbc,
+static void update_nr_written(struct writeback_control *wbc,
 			      unsigned long nr_written)
 {
 	wbc->nr_to_write -= nr_written;
@@ -3330,7 +3322,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 	u64 block_start;
 	u64 iosize;
 	sector_t sector;
-	struct extent_state *cached_state = NULL;
 	struct extent_map *em;
 	struct block_device *bdev;
 	size_t pg_offset = 0;
@@ -3349,10 +3340,9 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 			else
 				redirty_page_for_writepage(wbc, page);
 
-			update_nr_written(page, wbc, nr_written);
+			update_nr_written(wbc, nr_written);
 			unlock_page(page);
-			ret = 1;
-			goto done_unlocked;
+			return 1;
 		}
 	}
 
@@ -3360,7 +3350,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 	 * we don't want to touch the inode after unlocking the page,
 	 * so we update the mapping writeback index now
 	 */
-	update_nr_written(page, wbc, nr_written + 1);
+	update_nr_written(wbc, nr_written + 1);
 
 	end = page_end;
 	if (i_size <= start) {
@@ -3374,7 +3364,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 
 	while (cur <= end) {
 		u64 em_end;
-		unsigned long max_nr;
 
 		if (cur >= i_size) {
 			if (tree->ops && tree->ops->writepage_end_io_hook)
@@ -3382,7 +3371,7 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 							 page_end, NULL, 1);
 			break;
 		}
-		em = epd->get_extent(inode, page, pg_offset, cur,
+		em = epd->get_extent(BTRFS_I(inode), page, pg_offset, cur,
 				     end - cur + 1, 1);
 		if (IS_ERR_OR_NULL(em)) {
 			SetPageError(page);
@@ -3431,8 +3420,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 			continue;
 		}
 
-		max_nr = (i_size >> PAGE_SHIFT) + 1;
-
 		set_range_writeback(tree, cur, cur + iosize - 1);
 		if (!PageWriteback(page)) {
 			btrfs_err(BTRFS_I(inode)->root->fs_info,
@@ -3442,11 +3429,14 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 
 		ret = submit_extent_page(REQ_OP_WRITE, write_flags, tree, wbc,
 					 page, sector, iosize, pg_offset,
-					 bdev, &epd->bio, max_nr,
+					 bdev, &epd->bio,
 					 end_bio_extent_writepage,
 					 0, 0, 0, false);
-		if (ret)
+		if (ret) {
 			SetPageError(page);
+			if (PageWriteback(page))
+				end_page_writeback(page);
+		}
 
 		cur = cur + iosize;
 		pg_offset += iosize;
@@ -3454,11 +3444,6 @@ static noinline_for_stack int __extent_writepage_io(struct inode *inode,
 	}
 done:
 	*nr_ret = nr;
-
-done_unlocked:
-
-	/* drop our reference on any cached states */
-	free_extent_state(cached_state);
 	return ret;
 }
 
@@ -3590,9 +3575,9 @@ lock_extent_buffer_for_io(struct extent_buffer *eb,
 		set_bit(EXTENT_BUFFER_WRITEBACK, &eb->bflags);
 		spin_unlock(&eb->refs_lock);
 		btrfs_set_header_flag(eb, BTRFS_HEADER_FLAG_WRITTEN);
-		__percpu_counter_add(&fs_info->dirty_metadata_bytes,
-				     -eb->len,
-				     fs_info->dirty_metadata_batch);
+		percpu_counter_add_batch(&fs_info->dirty_metadata_bytes,
+					 -eb->len,
+					 fs_info->dirty_metadata_batch);
 		ret = 1;
 	} else {
 		spin_unlock(&eb->refs_lock);
@@ -3693,6 +3678,7 @@ static void end_bio_extent_buffer_writepage(struct bio *bio)
 	struct extent_buffer *eb;
 	int i, done;
 
+	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 
@@ -3700,7 +3686,7 @@ static void end_bio_extent_buffer_writepage(struct bio *bio)
 		BUG_ON(!eb);
 		done = atomic_dec_and_test(&eb->io_pages);
 
-		if (bio->bi_error ||
+		if (bio->bi_status ||
 		    test_bit(EXTENT_BUFFER_WRITE_ERR, &eb->bflags)) {
 			ClearPageUptodate(page);
 			set_btree_ioerr(page);
@@ -3750,7 +3736,7 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 		 * header 0 1 2 .. N ... data_N .. data_2 data_1 data_0
 		 */
 		start = btrfs_item_nr_offset(nritems);
-		end = btrfs_leaf_data(eb) + leaf_data_end(fs_info, eb);
+		end = BTRFS_LEAF_DATA_OFFSET + leaf_data_end(fs_info, eb);
 		memzero_extent_buffer(eb, start, end - start);
 	}
 
@@ -3761,20 +3747,21 @@ static noinline_for_stack int write_one_eb(struct extent_buffer *eb,
 		set_page_writeback(p);
 		ret = submit_extent_page(REQ_OP_WRITE, write_flags, tree, wbc,
 					 p, offset >> 9, PAGE_SIZE, 0, bdev,
-					 &epd->bio, -1,
+					 &epd->bio,
 					 end_bio_extent_buffer_writepage,
 					 0, epd->bio_flags, bio_flags, false);
 		epd->bio_flags = bio_flags;
 		if (ret) {
 			set_btree_ioerr(p);
-			end_page_writeback(p);
+			if (PageWriteback(p))
+				end_page_writeback(p);
 			if (atomic_sub_and_test(num_pages - i, &eb->io_pages))
 				end_extent_buffer_writeback(eb);
 			ret = -EIO;
 			break;
 		}
 		offset += PAGE_SIZE;
-		update_nr_written(p, wbc, 1);
+		update_nr_written(wbc, 1);
 		unlock_page(p);
 	}
 
@@ -3926,8 +3913,7 @@ retry:
  * WB_SYNC_ALL then we were called for data integrity and we must wait for
  * existing IO to complete.
  */
-static int extent_write_cache_pages(struct extent_io_tree *tree,
-			     struct address_space *mapping,
+static int extent_write_cache_pages(struct address_space *mapping,
 			     struct writeback_control *wbc,
 			     writepage_t writepage, void *data,
 			     void (*flush_fn)(void *))
@@ -4168,8 +4154,7 @@ int extent_writepages(struct extent_io_tree *tree,
 		.bio_flags = 0,
 	};
 
-	ret = extent_write_cache_pages(tree, mapping, wbc,
-				       __extent_writepage, &epd,
+	ret = extent_write_cache_pages(mapping, wbc, __extent_writepage, &epd,
 				       flush_write_bio);
 	flush_epd_write_bio(&epd);
 	return ret;
@@ -4264,8 +4249,6 @@ static int try_release_extent_state(struct extent_map_tree *map,
 			   EXTENT_IOBITS, 0, NULL))
 		ret = 0;
 	else {
-		if ((mask & GFP_NOFS) == GFP_NOFS)
-			mask = GFP_NOFS;
 		/*
 		 * at this point we can safely clear everything except the
 		 * locked bit and the nodatasum bit
@@ -4354,7 +4337,7 @@ static struct extent_map *get_extent_skip_holes(struct inode *inode,
 		if (len == 0)
 			break;
 		len = ALIGN(len, sectorsize);
-		em = get_extent(inode, NULL, 0, offset, len, 0);
+		em = get_extent(BTRFS_I(inode), NULL, 0, offset, len, 0);
 		if (IS_ERR_OR_NULL(em))
 			return em;
 
@@ -4373,6 +4356,119 @@ static struct extent_map *get_extent_skip_holes(struct inode *inode,
 	return NULL;
 }
 
+/*
+ * To cache previous fiemap extent
+ *
+ * Will be used for merging fiemap extent
+ */
+struct fiemap_cache {
+	u64 offset;
+	u64 phys;
+	u64 len;
+	u32 flags;
+	bool cached;
+};
+
+/*
+ * Helper to submit fiemap extent.
+ *
+ * Will try to merge current fiemap extent specified by @offset, @phys,
+ * @len and @flags with cached one.
+ * And only when we fails to merge, cached one will be submitted as
+ * fiemap extent.
+ *
+ * Return value is the same as fiemap_fill_next_extent().
+ */
+static int emit_fiemap_extent(struct fiemap_extent_info *fieinfo,
+				struct fiemap_cache *cache,
+				u64 offset, u64 phys, u64 len, u32 flags)
+{
+	int ret = 0;
+
+	if (!cache->cached)
+		goto assign;
+
+	/*
+	 * Sanity check, extent_fiemap() should have ensured that new
+	 * fiemap extent won't overlap with cahced one.
+	 * Not recoverable.
+	 *
+	 * NOTE: Physical address can overlap, due to compression
+	 */
+	if (cache->offset + cache->len > offset) {
+		WARN_ON(1);
+		return -EINVAL;
+	}
+
+	/*
+	 * Only merges fiemap extents if
+	 * 1) Their logical addresses are continuous
+	 *
+	 * 2) Their physical addresses are continuous
+	 *    So truly compressed (physical size smaller than logical size)
+	 *    extents won't get merged with each other
+	 *
+	 * 3) Share same flags except FIEMAP_EXTENT_LAST
+	 *    So regular extent won't get merged with prealloc extent
+	 */
+	if (cache->offset + cache->len  == offset &&
+	    cache->phys + cache->len == phys  &&
+	    (cache->flags & ~FIEMAP_EXTENT_LAST) ==
+			(flags & ~FIEMAP_EXTENT_LAST)) {
+		cache->len += len;
+		cache->flags |= flags;
+		goto try_submit_last;
+	}
+
+	/* Not mergeable, need to submit cached one */
+	ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
+				      cache->len, cache->flags);
+	cache->cached = false;
+	if (ret)
+		return ret;
+assign:
+	cache->cached = true;
+	cache->offset = offset;
+	cache->phys = phys;
+	cache->len = len;
+	cache->flags = flags;
+try_submit_last:
+	if (cache->flags & FIEMAP_EXTENT_LAST) {
+		ret = fiemap_fill_next_extent(fieinfo, cache->offset,
+				cache->phys, cache->len, cache->flags);
+		cache->cached = false;
+	}
+	return ret;
+}
+
+/*
+ * Emit last fiemap cache
+ *
+ * The last fiemap cache may still be cached in the following case:
+ * 0		      4k		    8k
+ * |<- Fiemap range ->|
+ * |<------------  First extent ----------->|
+ *
+ * In this case, the first extent range will be cached but not emitted.
+ * So we must emit it before ending extent_fiemap().
+ */
+static int emit_last_fiemap_cache(struct btrfs_fs_info *fs_info,
+				  struct fiemap_extent_info *fieinfo,
+				  struct fiemap_cache *cache)
+{
+	int ret;
+
+	if (!cache->cached)
+		return 0;
+
+	ret = fiemap_fill_next_extent(fieinfo, cache->offset, cache->phys,
+				      cache->len, cache->flags);
+	cache->cached = false;
+	if (ret > 0)
+		ret = 0;
+	return ret;
+}
+
 int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		__u64 start, __u64 len, get_extent_t *get_extent)
 {
@@ -4390,6 +4486,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	struct extent_state *cached_state = NULL;
 	struct btrfs_path *path;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct fiemap_cache cache = { 0 };
 	int end = 0;
 	u64 em_start = 0;
 	u64 em_len = 0;
@@ -4410,8 +4507,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	 * lookup the last file extent.  We're not using i_size here
 	 * because there might be preallocation past i_size
 	 */
-	ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(inode), -1,
-				       0);
+	ret = btrfs_lookup_file_extent(NULL, root, path,
+			btrfs_ino(BTRFS_I(inode)), -1, 0);
 	if (ret < 0) {
 		btrfs_free_path(path);
 		return ret;
@@ -4426,7 +4523,7 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 	found_type = found_key.type;
 
 	/* No extents, but there might be delalloc bits */
-	if (found_key.objectid != btrfs_ino(inode) ||
+	if (found_key.objectid != btrfs_ino(BTRFS_I(inode)) ||
 	    found_type != BTRFS_EXTENT_DATA_KEY) {
 		/* have to trust i_size as the end */
 		last = (u64)-1;
@@ -4535,8 +4632,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			 * lookup stuff.
 			 */
 			ret = btrfs_check_shared(trans, root->fs_info,
-						 root->objectid,
-						 btrfs_ino(inode), bytenr);
+					root->objectid,
+					btrfs_ino(BTRFS_I(inode)), bytenr);
 			if (trans)
 				btrfs_end_transaction(trans);
 			if (ret < 0)
@@ -4569,8 +4666,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 			flags |= FIEMAP_EXTENT_LAST;
 			end = 1;
 		}
-		ret = fiemap_fill_next_extent(fieinfo, em_start, disko,
-					      em_len, flags);
+		ret = emit_fiemap_extent(fieinfo, &cache, em_start, disko,
+					   em_len, flags);
 		if (ret) {
 			if (ret == 1)
 				ret = 0;
@@ -4578,6 +4675,8 @@ int extent_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		}
 	}
 out_free:
+	if (!ret)
+		ret = emit_last_fiemap_cache(root->fs_info, fieinfo, &cache);
 	free_extent_map(em);
 out:
 	btrfs_free_path(path);
diff --git a/fs/btrfs/extent_io.h b/fs/btrfs/extent_io.h
index 17f9ce479ed7..4f030912f3ef 100644
--- a/fs/btrfs/extent_io.h
+++ b/fs/btrfs/extent_io.h
@@ -2,6 +2,7 @@
 #define __EXTENTIO__
 
 #include <linux/rbtree.h>
+#include <linux/refcount.h>
 #include "ulist.h"
 
 /* bits for the extent state */
@@ -14,14 +15,17 @@
 #define EXTENT_DEFRAG		(1U << 6)
 #define EXTENT_BOUNDARY		(1U << 9)
 #define EXTENT_NODATASUM	(1U << 10)
-#define EXTENT_DO_ACCOUNTING	(1U << 11)
+#define EXTENT_CLEAR_META_RESV	(1U << 11)
 #define EXTENT_FIRST_DELALLOC	(1U << 12)
 #define EXTENT_NEED_WAIT	(1U << 13)
 #define EXTENT_DAMAGED		(1U << 14)
 #define EXTENT_NORESERVE	(1U << 15)
 #define EXTENT_QGROUP_RESERVED	(1U << 16)
 #define EXTENT_CLEAR_DATA_RESV	(1U << 17)
+#define EXTENT_DELALLOC_NEW	(1U << 18)
 #define EXTENT_IOBITS		(EXTENT_LOCKED | EXTENT_WRITEBACK)
+#define EXTENT_DO_ACCOUNTING    (EXTENT_CLEAR_META_RESV | \
+				 EXTENT_CLEAR_DATA_RESV)
 #define EXTENT_CTLBITS		(EXTENT_DO_ACCOUNTING | EXTENT_FIRST_DELALLOC)
 
 /*
@@ -45,13 +49,14 @@
 #define EXTENT_BUFFER_IN_TREE 10
 #define EXTENT_BUFFER_WRITE_ERR 11    /* write IO error */
 
-/* these are flags for extent_clear_unlock_delalloc */
+/* these are flags for __process_pages_contig */
 #define PAGE_UNLOCK		(1 << 0)
 #define PAGE_CLEAR_DIRTY	(1 << 1)
 #define PAGE_SET_WRITEBACK	(1 << 2)
 #define PAGE_END_WRITEBACK	(1 << 3)
 #define PAGE_SET_PRIVATE2	(1 << 4)
 #define PAGE_SET_ERROR		(1 << 5)
+#define PAGE_LOCK		(1 << 6)
 
 /*
  * page->private values.  Every page that is controlled by the extent
@@ -83,41 +88,56 @@ extern void le_bitmap_clear(u8 *map, unsigned int start, int len);
 
 struct extent_state;
 struct btrfs_root;
+struct btrfs_inode;
 struct btrfs_io_bio;
 struct io_failure_record;
 
-typedef	int (extent_submit_bio_hook_t)(struct inode *inode, struct bio *bio,
+typedef	blk_status_t (extent_submit_bio_hook_t)(void *private_data, struct bio *bio,
 				       int mirror_num, unsigned long bio_flags,
 				       u64 bio_offset);
 struct extent_io_ops {
-	int (*fill_delalloc)(struct inode *inode, struct page *locked_page,
-			     u64 start, u64 end, int *page_started,
-			     unsigned long *nr_written);
-	int (*writepage_start_hook)(struct page *page, u64 start, u64 end);
+	/*
+	 * The following callbacks must be allways defined, the function
+	 * pointer will be called unconditionally.
+	 */
 	extent_submit_bio_hook_t *submit_bio_hook;
+	int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset,
+				    struct page *page, u64 start, u64 end,
+				    int mirror);
 	int (*merge_bio_hook)(struct page *page, unsigned long offset,
 			      size_t size, struct bio *bio,
 			      unsigned long bio_flags);
 	int (*readpage_io_failed_hook)(struct page *page, int failed_mirror);
-	int (*readpage_end_io_hook)(struct btrfs_io_bio *io_bio, u64 phy_offset,
-				    struct page *page, u64 start, u64 end,
-				    int mirror);
-	int (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
+	struct btrfs_fs_info *(*tree_fs_info)(void *private_data);
+	void (*set_range_writeback)(void *private_data, u64 start, u64 end);
+
+	/*
+	 * Optional hooks, called if the pointer is not NULL
+	 */
+	int (*fill_delalloc)(void *private_data, struct page *locked_page,
+			     u64 start, u64 end, int *page_started,
+			     unsigned long *nr_written);
+
+	int (*writepage_start_hook)(struct page *page, u64 start, u64 end);
+	void (*writepage_end_io_hook)(struct page *page, u64 start, u64 end,
 				      struct extent_state *state, int uptodate);
-	void (*set_bit_hook)(struct inode *inode, struct extent_state *state,
+	void (*set_bit_hook)(void *private_data, struct extent_state *state,
 			     unsigned *bits);
-	void (*clear_bit_hook)(struct inode *inode, struct extent_state *state,
-			       unsigned *bits);
-	void (*merge_extent_hook)(struct inode *inode,
+	void (*clear_bit_hook)(void *private_data,
+			struct extent_state *state,
+			unsigned *bits);
+	void (*merge_extent_hook)(void *private_data,
 				  struct extent_state *new,
 				  struct extent_state *other);
-	void (*split_extent_hook)(struct inode *inode,
+	void (*split_extent_hook)(void *private_data,
 				  struct extent_state *orig, u64 split);
+	void (*check_extent_io_range)(void *private_data, const char *caller,
+				      u64 start, u64 end);
 };
 
 struct extent_io_tree {
 	struct rb_root state;
-	struct address_space *mapping;
+	void *private_data;
 	u64 dirty_bytes;
 	int track_uptodate;
 	spinlock_t lock;
@@ -131,7 +151,7 @@ struct extent_state {
 
 	/* ADD NEW ELEMENTS AFTER THIS */
 	wait_queue_head_t wq;
-	atomic_t refs;
+	refcount_t refs;
 	unsigned state;
 
 	struct io_failure_record *failrec;
@@ -189,12 +209,46 @@ struct extent_buffer {
  */
 struct extent_changeset {
 	/* How many bytes are set/cleared in this operation */
-	u64 bytes_changed;
+	unsigned int bytes_changed;
 
 	/* Changed ranges */
-	struct ulist *range_changed;
+	struct ulist range_changed;
 };
 
+static inline void extent_changeset_init(struct extent_changeset *changeset)
+{
+	changeset->bytes_changed = 0;
+	ulist_init(&changeset->range_changed);
+}
+
+static inline struct extent_changeset *extent_changeset_alloc(void)
+{
+	struct extent_changeset *ret;
+
+	ret = kmalloc(sizeof(*ret), GFP_KERNEL);
+	if (!ret)
+		return NULL;
+
+	extent_changeset_init(ret);
+	return ret;
+}
+
+static inline void extent_changeset_release(struct extent_changeset *changeset)
+{
+	if (!changeset)
+		return;
+	changeset->bytes_changed = 0;
+	ulist_release(&changeset->range_changed);
+}
+
+static inline void extent_changeset_free(struct extent_changeset *changeset)
+{
+	if (!changeset)
+		return;
+	extent_changeset_release(changeset);
+	kfree(changeset);
+}
+
 static inline void extent_set_compress_type(unsigned long *bio_flags,
 					    int compress_type)
 {
@@ -208,14 +262,13 @@ static inline int extent_compress_type(unsigned long bio_flags)
 
 struct extent_map_tree;
 
-typedef struct extent_map *(get_extent_t)(struct inode *inode,
+typedef struct extent_map *(get_extent_t)(struct btrfs_inode *inode,
 					  struct page *page,
 					  size_t pg_offset,
 					  u64 start, u64 len,
 					  int create);
 
-void extent_io_tree_init(struct extent_io_tree *tree,
-			 struct address_space *mapping);
+void extent_io_tree_init(struct extent_io_tree *tree, void *private_data);
 int try_release_extent_mapping(struct extent_map_tree *map,
 			       struct extent_io_tree *tree, struct page *page,
 			       gfp_t mask);
@@ -443,19 +496,21 @@ void extent_clear_unlock_delalloc(struct inode *inode, u64 start, u64 end,
 				 u64 delalloc_end, struct page *locked_page,
 				 unsigned bits_to_clear,
 				 unsigned long page_ops);
-struct bio *
-btrfs_bio_alloc(struct block_device *bdev, u64 first_sector, int nr_vecs,
-		gfp_t gfp_flags);
-struct bio *btrfs_io_bio_alloc(gfp_t gfp_mask, unsigned int nr_iovecs);
-struct bio *btrfs_bio_clone(struct bio *bio, gfp_t gfp_mask);
+struct bio *btrfs_bio_alloc(struct block_device *bdev, u64 first_byte);
+struct bio *btrfs_io_bio_alloc(unsigned int nr_iovecs);
+struct bio *btrfs_bio_clone(struct bio *bio);
+struct bio *btrfs_bio_clone_partial(struct bio *orig, int offset, int size);
 
 struct btrfs_fs_info;
-
-int repair_io_failure(struct inode *inode, u64 start, u64 length, u64 logical,
-		      struct page *page, unsigned int pg_offset,
-		      int mirror_num);
-int clean_io_failure(struct inode *inode, u64 start, struct page *page,
-		     unsigned int pg_offset);
+struct btrfs_inode;
+
+int repair_io_failure(struct btrfs_fs_info *fs_info, u64 ino, u64 start,
+		      u64 length, u64 logical, struct page *page,
+		      unsigned int pg_offset, int mirror_num);
+int clean_io_failure(struct btrfs_fs_info *fs_info,
+		     struct extent_io_tree *failure_tree,
+		     struct extent_io_tree *io_tree, u64 start,
+		     struct page *page, u64 ino, unsigned int pg_offset);
 void end_extent_writepage(struct page *page, int err, u64 start, u64 end);
 int repair_eb_io_failure(struct btrfs_fs_info *fs_info,
 			 struct extent_buffer *eb, int mirror_num);
@@ -479,16 +534,20 @@ struct io_failure_record {
 	int in_validation;
 };
 
-void btrfs_free_io_failure_record(struct inode *inode, u64 start, u64 end);
+
+void btrfs_free_io_failure_record(struct btrfs_inode *inode, u64 start,
+		u64 end);
 int btrfs_get_io_failure_record(struct inode *inode, u64 start, u64 end,
 				struct io_failure_record **failrec_ret);
-int btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
-			   struct io_failure_record *failrec, int fail_mirror);
+bool btrfs_check_repairable(struct inode *inode, struct bio *failed_bio,
+			    struct io_failure_record *failrec, int fail_mirror);
 struct bio *btrfs_create_repair_bio(struct inode *inode, struct bio *failed_bio,
 				    struct io_failure_record *failrec,
 				    struct page *page, int pg_offset, int icsum,
 				    bio_end_io_t *endio_func, void *data);
-int free_io_failure(struct inode *inode, struct io_failure_record *rec);
+int free_io_failure(struct extent_io_tree *failure_tree,
+		    struct extent_io_tree *io_tree,
+		    struct io_failure_record *rec);
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 noinline u64 find_lock_delalloc_range(struct inode *inode,
 				      struct extent_io_tree *tree,
diff --git a/fs/btrfs/extent_map.c b/fs/btrfs/extent_map.c
index 26f9ac719d20..69850155870c 100644
--- a/fs/btrfs/extent_map.c
+++ b/fs/btrfs/extent_map.c
@@ -55,7 +55,7 @@ struct extent_map *alloc_extent_map(void)
 	em->flags = 0;
 	em->compress_type = BTRFS_COMPRESS_NONE;
 	em->generation = 0;
-	atomic_set(&em->refs, 1);
+	refcount_set(&em->refs, 1);
 	INIT_LIST_HEAD(&em->list);
 	return em;
 }
@@ -71,8 +71,8 @@ void free_extent_map(struct extent_map *em)
 {
 	if (!em)
 		return;
-	WARN_ON(atomic_read(&em->refs) == 0);
-	if (atomic_dec_and_test(&em->refs)) {
+	WARN_ON(refcount_read(&em->refs) == 0);
+	if (refcount_dec_and_test(&em->refs)) {
 		WARN_ON(extent_map_in_tree(em));
 		WARN_ON(!list_empty(&em->list));
 		if (test_bit(EXTENT_FLAG_FS_MAPPING, &em->flags))
@@ -322,7 +322,7 @@ static inline void setup_extent_mapping(struct extent_map_tree *tree,
 					struct extent_map *em,
 					int modified)
 {
-	atomic_inc(&em->refs);
+	refcount_inc(&em->refs);
 	em->mod_start = em->start;
 	em->mod_len = em->len;
 
@@ -381,7 +381,7 @@ __lookup_extent_mapping(struct extent_map_tree *tree,
 	if (strict && !(end > em->start && start < extent_map_end(em)))
 		return NULL;
 
-	atomic_inc(&em->refs);
+	refcount_inc(&em->refs);
 	return em;
 }
 
diff --git a/fs/btrfs/extent_map.h b/fs/btrfs/extent_map.h
index eb8b8fae036b..a67b2def5413 100644
--- a/fs/btrfs/extent_map.h
+++ b/fs/btrfs/extent_map.h
@@ -2,6 +2,7 @@
 #define __EXTENTMAP__
 
 #include <linux/rbtree.h>
+#include <linux/refcount.h>
 
 #define EXTENT_MAP_LAST_BYTE ((u64)-4)
 #define EXTENT_MAP_HOLE ((u64)-3)
@@ -41,7 +42,7 @@ struct extent_map {
 		 */
 		struct map_lookup *map_lookup;
 	};
-	atomic_t refs;
+	refcount_t refs;
 	unsigned int compress_type;
 	struct list_head list;
 };
diff --git a/fs/btrfs/file-item.c b/fs/btrfs/file-item.c
index e97e322c28f0..fdcb41002623 100644
--- a/fs/btrfs/file-item.c
+++ b/fs/btrfs/file-item.c
@@ -160,11 +160,12 @@ static void btrfs_io_bio_endio_readpage(struct btrfs_io_bio *bio, int err)
 	kfree(bio->csum_allocated);
 }
 
-static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
+static blk_status_t __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 				   u64 logical_offset, u32 *dst, int dio)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	struct btrfs_io_bio *btrfs_bio = btrfs_io_bio(bio);
 	struct btrfs_csum_item *item = NULL;
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
@@ -177,12 +178,12 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 	u64 page_bytes_left;
 	u32 diff;
 	int nblocks;
-	int count = 0, i;
+	int count = 0;
 	u16 csum_size = btrfs_super_csum_size(fs_info->super_copy);
 
 	path = btrfs_alloc_path();
 	if (!path)
-		return -ENOMEM;
+		return BLK_STS_RESOURCE;
 
 	nblocks = bio->bi_iter.bi_size >> inode->i_sb->s_blocksize_bits;
 	if (!dst) {
@@ -191,7 +192,7 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 					csum_size, GFP_NOFS);
 			if (!btrfs_bio->csum_allocated) {
 				btrfs_free_path(path);
-				return -ENOMEM;
+				return BLK_STS_RESOURCE;
 			}
 			btrfs_bio->csum = btrfs_bio->csum_allocated;
 			btrfs_bio->end_io = btrfs_io_bio_endio_readpage;
@@ -206,15 +207,13 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 	if (bio->bi_iter.bi_size > PAGE_SIZE * 8)
 		path->reada = READA_FORWARD;
 
-	WARN_ON(bio->bi_vcnt <= 0);
-
 	/*
 	 * the free space stuff is only read when it hasn't been
 	 * updated in the current transaction.  So, we can safely
 	 * read from the commit root and sidestep a nasty deadlock
 	 * between reading the free space cache and updating the csum tree.
 	 */
-	if (btrfs_is_free_space_inode(inode)) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
 		path->search_commit_root = 1;
 		path->skip_locking = 1;
 	}
@@ -223,13 +222,13 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 	if (dio)
 		offset = logical_offset;
 
-	bio_for_each_segment_all(bvec, bio, i) {
-		page_bytes_left = bvec->bv_len;
+	bio_for_each_segment(bvec, bio, iter) {
+		page_bytes_left = bvec.bv_len;
 		if (count)
 			goto next;
 
 		if (!dio)
-			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
+			offset = page_offset(bvec.bv_page) + bvec.bv_offset;
 		count = btrfs_find_ordered_sum(inode, offset, disk_bytenr,
 					       (u32 *)csum, nblocks);
 		if (count)
@@ -255,7 +254,7 @@ static int __btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio,
 				} else {
 					btrfs_info_rl(fs_info,
 						   "no csum found for inode %llu start %llu",
-					       btrfs_ino(inode), offset);
+					       btrfs_ino(BTRFS_I(inode)), offset);
 				}
 				item = NULL;
 				btrfs_release_path(path);
@@ -303,12 +302,12 @@ next:
 	return 0;
 }
 
-int btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst)
+blk_status_t btrfs_lookup_bio_sums(struct inode *inode, struct bio *bio, u32 *dst)
 {
 	return __btrfs_lookup_bio_sums(inode, bio, 0, dst, 0);
 }
 
-int btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, u64 offset)
+blk_status_t btrfs_lookup_bio_sums_dio(struct inode *inode, struct bio *bio, u64 offset)
 {
 	return __btrfs_lookup_bio_sums(inode, bio, offset, NULL, 1);
 }
@@ -433,26 +432,26 @@ fail:
 	return ret;
 }
 
-int btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
+blk_status_t btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 		       u64 file_start, int contig)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ordered_sum *sums;
 	struct btrfs_ordered_extent *ordered = NULL;
 	char *data;
-	struct bio_vec *bvec;
+	struct bvec_iter iter;
+	struct bio_vec bvec;
 	int index;
 	int nr_sectors;
-	int i, j;
 	unsigned long total_bytes = 0;
 	unsigned long this_sum_bytes = 0;
+	int i;
 	u64 offset;
 
-	WARN_ON(bio->bi_vcnt <= 0);
 	sums = kzalloc(btrfs_ordered_sum_size(fs_info, bio->bi_iter.bi_size),
 		       GFP_NOFS);
 	if (!sums)
-		return -ENOMEM;
+		return BLK_STS_RESOURCE;
 
 	sums->len = bio->bi_iter.bi_size;
 	INIT_LIST_HEAD(&sums->list);
@@ -465,19 +464,19 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 	sums->bytenr = (u64)bio->bi_iter.bi_sector << 9;
 	index = 0;
 
-	bio_for_each_segment_all(bvec, bio, j) {
+	bio_for_each_segment(bvec, bio, iter) {
 		if (!contig)
-			offset = page_offset(bvec->bv_page) + bvec->bv_offset;
+			offset = page_offset(bvec.bv_page) + bvec.bv_offset;
 
 		if (!ordered) {
 			ordered = btrfs_lookup_ordered_extent(inode, offset);
 			BUG_ON(!ordered); /* Logic error */
 		}
 
-		data = kmap_atomic(bvec->bv_page);
+		data = kmap_atomic(bvec.bv_page);
 
 		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info,
-						 bvec->bv_len + fs_info->sectorsize
+						 bvec.bv_len + fs_info->sectorsize
 						 - 1);
 
 		for (i = 0; i < nr_sectors; i++) {
@@ -504,12 +503,12 @@ int btrfs_csum_one_bio(struct inode *inode, struct bio *bio,
 					+ total_bytes;
 				index = 0;
 
-				data = kmap_atomic(bvec->bv_page);
+				data = kmap_atomic(bvec.bv_page);
 			}
 
 			sums->sums[index] = ~(u32)0;
 			sums->sums[index]
-				= btrfs_csum_data(data + bvec->bv_offset
+				= btrfs_csum_data(data + bvec.bv_offset
 						+ (i * fs_info->sectorsize),
 						sums->sums[index],
 						fs_info->sectorsize);
@@ -643,7 +642,33 @@ int btrfs_del_csums(struct btrfs_trans_handle *trans,
 
 		/* delete the entire item, it is inside our range */
 		if (key.offset >= bytenr && csum_end <= end_byte) {
-			ret = btrfs_del_item(trans, root, path);
+			int del_nr = 1;
+
+			/*
+			 * Check how many csum items preceding this one in this
+			 * leaf correspond to our range and then delete them all
+			 * at once.
+			 */
+			if (key.offset > bytenr && path->slots[0] > 0) {
+				int slot = path->slots[0] - 1;
+
+				while (slot >= 0) {
+					struct btrfs_key pk;
+
+					btrfs_item_key_to_cpu(leaf, &pk, slot);
+					if (pk.offset < bytenr ||
+					    pk.type != BTRFS_EXTENT_CSUM_KEY ||
+					    pk.objectid !=
+					    BTRFS_EXTENT_CSUM_OBJECTID)
+						break;
+					path->slots[0] = slot;
+					del_nr++;
+					key.offset = pk.offset;
+					slot--;
+				}
+			}
+			ret = btrfs_del_items(trans, root, path,
+					      path->slots[0], del_nr);
 			if (ret)
 				goto out;
 			if (key.offset == bytenr)
@@ -856,8 +881,8 @@ insert:
 		tmp = min(tmp, (next_offset - file_key.offset) >>
 					 fs_info->sb->s_blocksize_bits);
 
-		tmp = max((u64)1, tmp);
-		tmp = min(tmp, (u64)MAX_CSUM_ITEMS(fs_info, csum_size));
+		tmp = max_t(u64, 1, tmp);
+		tmp = min_t(u64, tmp, MAX_CSUM_ITEMS(fs_info, csum_size));
 		ins_size = csum_size * tmp;
 	} else {
 		ins_size = csum_size;
@@ -904,14 +929,14 @@ fail_unlock:
 	goto out;
 }
 
-void btrfs_extent_item_to_extent_map(struct inode *inode,
+void btrfs_extent_item_to_extent_map(struct btrfs_inode *inode,
 				     const struct btrfs_path *path,
 				     struct btrfs_file_extent_item *fi,
 				     const bool new_inline,
 				     struct extent_map *em)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf = path->nodes[0];
 	const int slot = path->slots[0];
 	struct btrfs_key key;
@@ -976,8 +1001,8 @@ void btrfs_extent_item_to_extent_map(struct inode *inode,
 		}
 	} else {
 		btrfs_err(fs_info,
-			  "unknown file extent item type %d, inode %llu, offset %llu, root %llu",
-			  type, btrfs_ino(inode), extent_start,
+			  "unknown file extent item type %d, inode %llu, offset %llu, "
+			  "root %llu", type, btrfs_ino(inode), extent_start,
 			  root->root_key.objectid);
 	}
 }
diff --git a/fs/btrfs/file.c b/fs/btrfs/file.c
index b5c5da215d05..9e75d8a39aac 100644
--- a/fs/btrfs/file.c
+++ b/fs/btrfs/file.c
@@ -92,10 +92,10 @@ static int __compare_inode_defrag(struct inode_defrag *defrag1,
  * If an existing record is found the defrag item you
  * pass in is freed
  */
-static int __btrfs_add_inode_defrag(struct inode *inode,
+static int __btrfs_add_inode_defrag(struct btrfs_inode *inode,
 				    struct inode_defrag *defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	struct inode_defrag *entry;
 	struct rb_node **p;
 	struct rb_node *parent = NULL;
@@ -123,7 +123,7 @@ static int __btrfs_add_inode_defrag(struct inode *inode,
 			return -EEXIST;
 		}
 	}
-	set_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags);
+	set_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags);
 	rb_link_node(&defrag->rb_node, parent, p);
 	rb_insert_color(&defrag->rb_node, &fs_info->defrag_inodes);
 	return 0;
@@ -145,10 +145,10 @@ static inline int __need_auto_defrag(struct btrfs_fs_info *fs_info)
  * enabled
  */
 int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
-			   struct inode *inode)
+			   struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct inode_defrag *defrag;
 	u64 transid;
 	int ret;
@@ -156,13 +156,13 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 	if (!__need_auto_defrag(fs_info))
 		return 0;
 
-	if (test_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags))
+	if (test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags))
 		return 0;
 
 	if (trans)
 		transid = trans->transid;
 	else
-		transid = BTRFS_I(inode)->root->last_trans;
+		transid = inode->root->last_trans;
 
 	defrag = kmem_cache_zalloc(btrfs_inode_defrag_cachep, GFP_NOFS);
 	if (!defrag)
@@ -173,7 +173,7 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
 	defrag->root = root->root_key.objectid;
 
 	spin_lock(&fs_info->defrag_inodes_lock);
-	if (!test_bit(BTRFS_INODE_IN_DEFRAG, &BTRFS_I(inode)->runtime_flags)) {
+	if (!test_bit(BTRFS_INODE_IN_DEFRAG, &inode->runtime_flags)) {
 		/*
 		 * If we set IN_DEFRAG flag and evict the inode from memory,
 		 * and then re-read this inode, this new inode doesn't have
@@ -194,10 +194,10 @@ int btrfs_add_inode_defrag(struct btrfs_trans_handle *trans,
  * the same inode in the tree, we will merge them together (by
  * __btrfs_add_inode_defrag()) and free the one that we want to requeue.
  */
-static void btrfs_requeue_inode_defrag(struct inode *inode,
+static void btrfs_requeue_inode_defrag(struct btrfs_inode *inode,
 				       struct inode_defrag *defrag)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	int ret;
 
 	if (!__need_auto_defrag(fs_info))
@@ -334,7 +334,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 	 */
 	if (num_defrag == BTRFS_DEFRAG_BATCH) {
 		defrag->last_offset = range.start;
-		btrfs_requeue_inode_defrag(inode, defrag);
+		btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag);
 	} else if (defrag->last_offset && !defrag->cycled) {
 		/*
 		 * we didn't fill our defrag batch, but
@@ -343,7 +343,7 @@ static int __btrfs_run_defrag_inode(struct btrfs_fs_info *fs_info,
 		 */
 		defrag->last_offset = 0;
 		defrag->cycled = 1;
-		btrfs_requeue_inode_defrag(inode, defrag);
+		btrfs_requeue_inode_defrag(BTRFS_I(inode), defrag);
 	} else {
 		kmem_cache_free(btrfs_inode_defrag_cachep, defrag);
 	}
@@ -529,13 +529,13 @@ int btrfs_dirty_pages(struct inode *inode, struct page **pages,
  * this drops all the extents in the cache that intersect the range
  * [start, end].  Existing extents are split as required.
  */
-void btrfs_drop_extent_cache(struct inode *inode, u64 start, u64 end,
+void btrfs_drop_extent_cache(struct btrfs_inode *inode, u64 start, u64 end,
 			     int skip_pinned)
 {
 	struct extent_map *em;
 	struct extent_map *split = NULL;
 	struct extent_map *split2 = NULL;
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	u64 len = end - start + 1;
 	u64 gen;
 	int ret;
@@ -702,7 +702,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 	struct btrfs_file_extent_item *fi;
 	struct btrfs_key key;
 	struct btrfs_key new_key;
-	u64 ino = btrfs_ino(inode);
+	u64 ino = btrfs_ino(BTRFS_I(inode));
 	u64 search_start = start;
 	u64 disk_bytenr = 0;
 	u64 num_bytes = 0;
@@ -720,7 +720,7 @@ int __btrfs_drop_extents(struct btrfs_trans_handle *trans,
 	int leafs_visited = 0;
 
 	if (drop_cache)
-		btrfs_drop_extent_cache(inode, start, end - 1, 0);
+		btrfs_drop_extent_cache(BTRFS_I(inode), start, end - 1, 0);
 
 	if (start >= BTRFS_I(inode)->disk_i_size && !replace_extent)
 		modify_tree = 0;
@@ -1082,10 +1082,10 @@ static int extent_mergeable(struct extent_buffer *leaf, int slot,
  * two or three.
  */
 int btrfs_mark_extent_written(struct btrfs_trans_handle *trans,
-			      struct inode *inode, u64 start, u64 end)
+			      struct btrfs_inode *inode, u64 start, u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_path *path;
 	struct btrfs_file_extent_item *fi;
@@ -1404,6 +1404,47 @@ fail:
 
 }
 
+static int btrfs_find_new_delalloc_bytes(struct btrfs_inode *inode,
+					 const u64 start,
+					 const u64 len,
+					 struct extent_state **cached_state)
+{
+	u64 search_start = start;
+	const u64 end = start + len - 1;
+
+	while (search_start < end) {
+		const u64 search_len = end - search_start + 1;
+		struct extent_map *em;
+		u64 em_len;
+		int ret = 0;
+
+		em = btrfs_get_extent(inode, NULL, 0, search_start,
+				      search_len, 0);
+		if (IS_ERR(em))
+			return PTR_ERR(em);
+
+		if (em->block_start != EXTENT_MAP_HOLE)
+			goto next;
+
+		em_len = em->len;
+		if (em->start < search_start)
+			em_len -= search_start - em->start;
+		if (em_len > search_len)
+			em_len = search_len;
+
+		ret = set_extent_bit(&inode->io_tree, search_start,
+				     search_start + em_len - 1,
+				     EXTENT_DELALLOC_NEW,
+				     NULL, cached_state, GFP_NOFS);
+next:
+		search_start = extent_map_end(em);
+		free_extent_map(em);
+		if (ret)
+			return ret;
+	}
+	return 0;
+}
+
 /*
  * This function locks the extent and properly waits for data=ordered extents
  * to finish before allowing the pages to be modified if need.
@@ -1415,13 +1456,13 @@ fail:
  * the other < 0 number - Something wrong happens
  */
 static noinline int
-lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
+lock_and_cleanup_extent_if_need(struct btrfs_inode *inode, struct page **pages,
 				size_t num_pages, loff_t pos,
 				size_t write_bytes,
 				u64 *lockstart, u64 *lockend,
 				struct extent_state **cached_state)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	u64 start_pos;
 	u64 last_pos;
 	int i;
@@ -1432,33 +1473,44 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
 		+ round_up(pos + write_bytes - start_pos,
 			   fs_info->sectorsize) - 1;
 
-	if (start_pos < inode->i_size) {
+	if (start_pos < inode->vfs_inode.i_size ||
+	    (inode->flags & BTRFS_INODE_PREALLOC)) {
 		struct btrfs_ordered_extent *ordered;
-		lock_extent_bits(&BTRFS_I(inode)->io_tree,
-				 start_pos, last_pos, cached_state);
+		unsigned int clear_bits;
+
+		lock_extent_bits(&inode->io_tree, start_pos, last_pos,
+				cached_state);
 		ordered = btrfs_lookup_ordered_range(inode, start_pos,
 						     last_pos - start_pos + 1);
 		if (ordered &&
 		    ordered->file_offset + ordered->len > start_pos &&
 		    ordered->file_offset <= last_pos) {
-			unlock_extent_cached(&BTRFS_I(inode)->io_tree,
-					     start_pos, last_pos,
-					     cached_state, GFP_NOFS);
+			unlock_extent_cached(&inode->io_tree, start_pos,
+					last_pos, cached_state, GFP_NOFS);
 			for (i = 0; i < num_pages; i++) {
 				unlock_page(pages[i]);
 				put_page(pages[i]);
 			}
-			btrfs_start_ordered_extent(inode, ordered, 1);
+			btrfs_start_ordered_extent(&inode->vfs_inode,
+					ordered, 1);
 			btrfs_put_ordered_extent(ordered);
 			return -EAGAIN;
 		}
 		if (ordered)
 			btrfs_put_ordered_extent(ordered);
-
-		clear_extent_bit(&BTRFS_I(inode)->io_tree, start_pos,
-				  last_pos, EXTENT_DIRTY | EXTENT_DELALLOC |
-				  EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG,
-				  0, 0, cached_state, GFP_NOFS);
+		ret = btrfs_find_new_delalloc_bytes(inode, start_pos,
+						    last_pos - start_pos + 1,
+						    cached_state);
+		clear_bits = EXTENT_DIRTY | EXTENT_DELALLOC |
+			EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG;
+		if (ret)
+			clear_bits |= EXTENT_DELALLOC_NEW | EXTENT_LOCKED;
+		clear_extent_bit(&inode->io_tree, start_pos,
+				 last_pos, clear_bits,
+				 (clear_bits & EXTENT_LOCKED) ? 1 : 0,
+				 0, cached_state, GFP_NOFS);
+		if (ret)
+			return ret;
 		*lockstart = start_pos;
 		*lockend = last_pos;
 		ret = 1;
@@ -1474,11 +1526,11 @@ lock_and_cleanup_extent_if_need(struct inode *inode, struct page **pages,
 	return ret;
 }
 
-static noinline int check_can_nocow(struct inode *inode, loff_t pos,
+static noinline int check_can_nocow(struct btrfs_inode *inode, loff_t pos,
 				    size_t *write_bytes)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct btrfs_ordered_extent *ordered;
 	u64 lockstart, lockend;
 	u64 num_bytes;
@@ -1493,19 +1545,20 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos,
 			   fs_info->sectorsize) - 1;
 
 	while (1) {
-		lock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
+		lock_extent(&inode->io_tree, lockstart, lockend);
 		ordered = btrfs_lookup_ordered_range(inode, lockstart,
 						     lockend - lockstart + 1);
 		if (!ordered) {
 			break;
 		}
-		unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
-		btrfs_start_ordered_extent(inode, ordered, 1);
+		unlock_extent(&inode->io_tree, lockstart, lockend);
+		btrfs_start_ordered_extent(&inode->vfs_inode, ordered, 1);
 		btrfs_put_ordered_extent(ordered);
 	}
 
 	num_bytes = lockend - lockstart + 1;
-	ret = can_nocow_extent(inode, lockstart, &num_bytes, NULL, NULL, NULL);
+	ret = can_nocow_extent(&inode->vfs_inode, lockstart, &num_bytes,
+			NULL, NULL, NULL);
 	if (ret <= 0) {
 		ret = 0;
 		btrfs_end_write_no_snapshoting(root);
@@ -1514,7 +1567,7 @@ static noinline int check_can_nocow(struct inode *inode, loff_t pos,
 				     num_bytes - pos + lockstart);
 	}
 
-	unlock_extent(&BTRFS_I(inode)->io_tree, lockstart, lockend);
+	unlock_extent(&inode->io_tree, lockstart, lockend);
 
 	return ret;
 }
@@ -1528,6 +1581,7 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct page **pages = NULL;
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	u64 release_bytes = 0;
 	u64 lockstart;
 	u64 lockend;
@@ -1575,11 +1629,14 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 		reserve_bytes = round_up(write_bytes + sector_offset,
 				fs_info->sectorsize);
 
-		ret = btrfs_check_data_free_space(inode, pos, write_bytes);
+		extent_changeset_release(data_reserved);
+		ret = btrfs_check_data_free_space(inode, &data_reserved, pos,
+						  write_bytes);
 		if (ret < 0) {
 			if ((BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
 						      BTRFS_INODE_PREALLOC)) &&
-			    check_can_nocow(inode, pos, &write_bytes) > 0) {
+			    check_can_nocow(BTRFS_I(inode), pos,
+					&write_bytes) > 0) {
 				/*
 				 * For nodata cow case, no need to reserve
 				 * data space.
@@ -1599,11 +1656,13 @@ static noinline ssize_t __btrfs_buffered_write(struct file *file,
 			}
 		}
 
-		ret = btrfs_delalloc_reserve_metadata(inode, reserve_bytes);
+		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
+				reserve_bytes);
 		if (ret) {
 			if (!only_release_metadata)
-				btrfs_free_reserved_data_space(inode, pos,
-							       write_bytes);
+				btrfs_free_reserved_data_space(inode,
+						data_reserved, pos,
+						write_bytes);
 			else
 				btrfs_end_write_no_snapshoting(root);
 			break;
@@ -1623,9 +1682,9 @@ again:
 		if (ret)
 			break;
 
-		ret = lock_and_cleanup_extent_if_need(inode, pages, num_pages,
-						pos, write_bytes, &lockstart,
-						&lockend, &cached_state);
+		ret = lock_and_cleanup_extent_if_need(BTRFS_I(inode), pages,
+				num_pages, pos, write_bytes, &lockstart,
+				&lockend, &cached_state);
 		if (ret < 0) {
 			if (ret == -EAGAIN)
 				goto again;
@@ -1677,7 +1736,7 @@ again:
 				spin_unlock(&BTRFS_I(inode)->lock);
 			}
 			if (only_release_metadata) {
-				btrfs_delalloc_release_metadata(inode,
+				btrfs_delalloc_release_metadata(BTRFS_I(inode),
 								release_bytes);
 			} else {
 				u64 __pos;
@@ -1685,8 +1744,9 @@ again:
 				__pos = round_down(pos,
 						   fs_info->sectorsize) +
 					(dirty_pages << PAGE_SHIFT);
-				btrfs_delalloc_release_space(inode, __pos,
-							     release_bytes);
+				btrfs_delalloc_release_space(inode,
+						data_reserved, __pos,
+						release_bytes);
 			}
 		}
 
@@ -1738,14 +1798,16 @@ again:
 	if (release_bytes) {
 		if (only_release_metadata) {
 			btrfs_end_write_no_snapshoting(root);
-			btrfs_delalloc_release_metadata(inode, release_bytes);
+			btrfs_delalloc_release_metadata(BTRFS_I(inode),
+					release_bytes);
 		} else {
-			btrfs_delalloc_release_space(inode,
-						round_down(pos, fs_info->sectorsize),
-						release_bytes);
+			btrfs_delalloc_release_space(inode, data_reserved,
+					round_down(pos, fs_info->sectorsize),
+					release_bytes);
 		}
 	}
 
+	extent_changeset_free(data_reserved);
 	return num_written ? num_written : ret;
 }
 
@@ -1820,17 +1882,36 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	bool sync = (file->f_flags & O_DSYNC) || IS_SYNC(file->f_mapping->host);
 	ssize_t err;
 	loff_t pos;
-	size_t count;
+	size_t count = iov_iter_count(from);
 	loff_t oldsize;
 	int clean_page = 0;
 
-	inode_lock(inode);
+	if (!inode_trylock(inode)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_lock(inode);
+	}
+
 	err = generic_write_checks(iocb, from);
 	if (err <= 0) {
 		inode_unlock(inode);
 		return err;
 	}
 
+	pos = iocb->ki_pos;
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		/*
+		 * We will allocate space in case nodatacow is not set,
+		 * so bail
+		 */
+		if (!(BTRFS_I(inode)->flags & (BTRFS_INODE_NODATACOW |
+					      BTRFS_INODE_PREALLOC)) ||
+		    check_can_nocow(BTRFS_I(inode), pos, &count) <= 0) {
+			inode_unlock(inode);
+			return -EAGAIN;
+		}
+	}
+
 	current->backing_dev_info = inode_to_bdi(inode);
 	err = file_remove_privs(file);
 	if (err) {
@@ -1858,8 +1939,6 @@ static ssize_t btrfs_file_write_iter(struct kiocb *iocb,
 	 */
 	update_time_for_write(inode);
 
-	pos = iocb->ki_pos;
-	count = iov_iter_count(from);
 	start_pos = round_down(pos, fs_info->sectorsize);
 	oldsize = i_size_read(inode);
 	if (start_pos > oldsize) {
@@ -1955,7 +2034,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct btrfs_trans_handle *trans;
 	struct btrfs_log_ctx ctx;
-	int ret = 0;
+	int ret = 0, err;
 	bool full_sync = 0;
 	u64 len;
 
@@ -1974,7 +2053,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 */
 	ret = start_ordered_ops(inode, start, end);
 	if (ret)
-		return ret;
+		goto out;
 
 	inode_lock(inode);
 	atomic_inc(&root->log_batch);
@@ -2062,7 +2141,7 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	 * commit does not start nor waits for ordered extents to complete.
 	 */
 	smp_mb();
-	if (btrfs_inode_in_log(inode, fs_info->generation) ||
+	if (btrfs_inode_in_log(BTRFS_I(inode), fs_info->generation) ||
 	    (full_sync && BTRFS_I(inode)->last_trans <=
 	     fs_info->last_trans_committed) ||
 	    (!btrfs_have_ordered_extents_in_range(inode, start, len) &&
@@ -2079,10 +2158,10 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		 * An ordered extent might have started before and completed
 		 * already with io errors, in which case the inode was not
 		 * updated and we end up here. So check the inode's mapping
-		 * flags for any errors that might have happened while doing
-		 * writeback of file data.
+		 * for any errors that might have happened since we last
+		 * checked called fsync.
 		 */
-		ret = filemap_check_errors(inode->i_mapping);
+		ret = filemap_check_wb_err(inode->i_mapping, file->f_wb_err);
 		inode_unlock(inode);
 		goto out;
 	}
@@ -2171,6 +2250,9 @@ int btrfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		ret = btrfs_end_transaction(trans);
 	}
 out:
+	err = file_check_and_advance_wb_err(file);
+	if (!ret)
+		ret = err;
 	return ret > 0 ? -EIO : ret;
 }
 
@@ -2193,7 +2275,7 @@ static int btrfs_file_mmap(struct file	*filp, struct vm_area_struct *vma)
 	return 0;
 }
 
-static int hole_mergeable(struct inode *inode, struct extent_buffer *leaf,
+static int hole_mergeable(struct btrfs_inode *inode, struct extent_buffer *leaf,
 			  int slot, u64 start, u64 end)
 {
 	struct btrfs_file_extent_item *fi;
@@ -2222,15 +2304,16 @@ static int hole_mergeable(struct inode *inode, struct extent_buffer *leaf,
 	return 0;
 }
 
-static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
-		      struct btrfs_path *path, u64 offset, u64 end)
+static int fill_holes(struct btrfs_trans_handle *trans,
+		struct btrfs_inode *inode,
+		struct btrfs_path *path, u64 offset, u64 end)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct extent_buffer *leaf;
 	struct btrfs_file_extent_item *fi;
 	struct extent_map *hole_em;
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct btrfs_key key;
 	int ret;
 
@@ -2253,7 +2336,7 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 	}
 
 	leaf = path->nodes[0];
-	if (hole_mergeable(inode, leaf, path->slots[0]-1, offset, end)) {
+	if (hole_mergeable(inode, leaf, path->slots[0] - 1, offset, end)) {
 		u64 num_bytes;
 
 		path->slots[0]--;
@@ -2285,9 +2368,8 @@ static int fill_holes(struct btrfs_trans_handle *trans, struct inode *inode,
 	}
 	btrfs_release_path(path);
 
-	ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode), offset,
-				       0, 0, end - offset, 0, end - offset,
-				       0, 0, 0);
+	ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode),
+			offset, 0, 0, end - offset, 0, end - offset, 0, 0, 0);
 	if (ret)
 		return ret;
 
@@ -2297,8 +2379,7 @@ out:
 	hole_em = alloc_extent_map();
 	if (!hole_em) {
 		btrfs_drop_extent_cache(inode, offset, end - 1, 0);
-		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-			&BTRFS_I(inode)->runtime_flags);
+		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags);
 	} else {
 		hole_em->start = offset;
 		hole_em->len = end - offset;
@@ -2321,7 +2402,7 @@ out:
 		free_extent_map(hole_em);
 		if (ret)
 			set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-				&BTRFS_I(inode)->runtime_flags);
+					&inode->runtime_flags);
 	}
 
 	return 0;
@@ -2335,17 +2416,15 @@ out:
  */
 static int find_first_non_hole(struct inode *inode, u64 *start, u64 *len)
 {
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct extent_map *em;
 	int ret = 0;
 
-	em = btrfs_get_extent(inode, NULL, 0, *start, *len, 0);
-	if (IS_ERR_OR_NULL(em)) {
-		if (!em)
-			ret = -ENOMEM;
-		else
-			ret = PTR_ERR(em);
-		return ret;
-	}
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0,
+			      round_down(*start, fs_info->sectorsize),
+			      round_up(*len, fs_info->sectorsize), 0);
+	if (IS_ERR(em))
+		return PTR_ERR(em);
 
 	/* Hole or vacuum extent(only exists in no-hole mode) */
 	if (em->block_start == EXTENT_MAP_HOLE) {
@@ -2551,8 +2630,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 		trans->block_rsv = &fs_info->trans_block_rsv;
 
 		if (cur_offset < drop_end && cur_offset < ino_size) {
-			ret = fill_holes(trans, inode, path, cur_offset,
-					 drop_end);
+			ret = fill_holes(trans, BTRFS_I(inode), path,
+					cur_offset, drop_end);
 			if (ret) {
 				/*
 				 * If we failed then we didn't insert our hole
@@ -2623,7 +2702,8 @@ static int btrfs_punch_hole(struct inode *inode, loff_t offset, loff_t len)
 	 * cur_offset == drop_end).
 	 */
 	if (cur_offset < ino_size && cur_offset < drop_end) {
-		ret = fill_holes(trans, inode, path, cur_offset, drop_end);
+		ret = fill_holes(trans, BTRFS_I(inode), path,
+				cur_offset, drop_end);
 		if (ret) {
 			/* Same comment as above. */
 			btrfs_abort_transaction(trans, ret);
@@ -2718,6 +2798,7 @@ static long btrfs_fallocate(struct file *file, int mode,
 {
 	struct inode *inode = file_inode(file);
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	struct falloc_range *range;
 	struct falloc_range *tmp;
 	struct list_head reserve_list;
@@ -2748,7 +2829,8 @@ static long btrfs_fallocate(struct file *file, int mode,
 	 *
 	 * For qgroup space, it will be checked later.
 	 */
-	ret = btrfs_alloc_data_chunk_ondemand(inode, alloc_end - alloc_start);
+	ret = btrfs_alloc_data_chunk_ondemand(BTRFS_I(inode),
+			alloc_end - alloc_start);
 	if (ret < 0)
 		return ret;
 
@@ -2828,13 +2910,10 @@ static long btrfs_fallocate(struct file *file, int mode,
 	/* First, check if we exceed the qgroup limit */
 	INIT_LIST_HEAD(&reserve_list);
 	while (1) {
-		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
 				      alloc_end - cur_offset, 0);
-		if (IS_ERR_OR_NULL(em)) {
-			if (!em)
-				ret = -ENOMEM;
-			else
-				ret = PTR_ERR(em);
+		if (IS_ERR(em)) {
+			ret = PTR_ERR(em);
 			break;
 		}
 		last_byte = min(extent_map_end(em), alloc_end);
@@ -2849,18 +2928,20 @@ static long btrfs_fallocate(struct file *file, int mode,
 				free_extent_map(em);
 				break;
 			}
-			ret = btrfs_qgroup_reserve_data(inode, cur_offset,
-					last_byte - cur_offset);
-			if (ret < 0)
+			ret = btrfs_qgroup_reserve_data(inode, &data_reserved,
+					cur_offset, last_byte - cur_offset);
+			if (ret < 0) {
+				free_extent_map(em);
 				break;
+			}
 		} else {
 			/*
 			 * Do not need to reserve unwritten extent for this
 			 * range, free reserved data space first, otherwise
 			 * it'll result in false ENOSPC error.
 			 */
-			btrfs_free_reserved_data_space(inode, cur_offset,
-				last_byte - cur_offset);
+			btrfs_free_reserved_data_space(inode, data_reserved,
+					cur_offset, last_byte - cur_offset);
 		}
 		free_extent_map(em);
 		cur_offset = last_byte;
@@ -2876,11 +2957,12 @@ static long btrfs_fallocate(struct file *file, int mode,
 		if (!ret)
 			ret = btrfs_prealloc_file_range(inode, mode,
 					range->start,
-					range->len, 1 << inode->i_blkbits,
+					range->len, i_blocksize(inode),
 					offset + len, &alloc_hint);
 		else
-			btrfs_free_reserved_data_space(inode, range->start,
-						       range->len);
+			btrfs_free_reserved_data_space(inode,
+					data_reserved, range->start,
+					range->len);
 		list_del(&range->list);
 		kfree(range);
 	}
@@ -2918,8 +3000,9 @@ out:
 	inode_unlock(inode);
 	/* Let go of our reservation. */
 	if (ret != 0)
-		btrfs_free_reserved_data_space(inode, alloc_start,
-				       alloc_end - cur_offset);
+		btrfs_free_reserved_data_space(inode, data_reserved,
+				alloc_start, alloc_end - cur_offset);
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -2955,7 +3038,8 @@ static int find_desired_extent(struct inode *inode, loff_t *offset, int whence)
 			 &cached_state);
 
 	while (start < inode->i_size) {
-		em = btrfs_get_extent_fiemap(inode, NULL, 0, start, len, 0);
+		em = btrfs_get_extent_fiemap(BTRFS_I(inode), NULL, 0,
+				start, len, 0);
 		if (IS_ERR(em)) {
 			ret = PTR_ERR(em);
 			em = NULL;
@@ -3019,13 +3103,19 @@ out:
 	return offset;
 }
 
+static int btrfs_file_open(struct inode *inode, struct file *filp)
+{
+	filp->f_mode |= FMODE_AIO_NOWAIT;
+	return generic_file_open(inode, filp);
+}
+
 const struct file_operations btrfs_file_operations = {
 	.llseek		= btrfs_file_llseek,
 	.read_iter      = generic_file_read_iter,
 	.splice_read	= generic_file_splice_read,
 	.write_iter	= btrfs_file_write_iter,
 	.mmap		= btrfs_file_mmap,
-	.open		= generic_file_open,
+	.open		= btrfs_file_open,
 	.release	= btrfs_release_file,
 	.fsync		= btrfs_sync_file,
 	.fallocate	= btrfs_fallocate,
diff --git a/fs/btrfs/free-space-cache.c b/fs/btrfs/free-space-cache.c
index 7015892c9ee8..c5e6180cdb8c 100644
--- a/fs/btrfs/free-space-cache.c
+++ b/fs/btrfs/free-space-cache.c
@@ -18,6 +18,7 @@
 
 #include <linux/pagemap.h>
 #include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/math64.h>
 #include <linux/ratelimit.h>
@@ -94,12 +95,11 @@ static struct inode *__lookup_free_space_inode(struct btrfs_root *root,
 	return inode;
 }
 
-struct inode *lookup_free_space_inode(struct btrfs_root *root,
+struct inode *lookup_free_space_inode(struct btrfs_fs_info *fs_info,
 				      struct btrfs_block_group_cache
 				      *block_group, struct btrfs_path *path)
 {
 	struct inode *inode = NULL;
-	struct btrfs_fs_info *fs_info = root->fs_info;
 	u32 flags = BTRFS_INODE_NODATASUM | BTRFS_INODE_NODATACOW;
 
 	spin_lock(&block_group->lock);
@@ -109,7 +109,7 @@ struct inode *lookup_free_space_inode(struct btrfs_root *root,
 	if (inode)
 		return inode;
 
-	inode = __lookup_free_space_inode(root, path,
+	inode = __lookup_free_space_inode(fs_info->tree_root, path,
 					  block_group->key.objectid);
 	if (IS_ERR(inode))
 		return inode;
@@ -192,7 +192,7 @@ static int __create_free_space_inode(struct btrfs_root *root,
 	return 0;
 }
 
-int create_free_space_inode(struct btrfs_root *root,
+int create_free_space_inode(struct btrfs_fs_info *fs_info,
 			    struct btrfs_trans_handle *trans,
 			    struct btrfs_block_group_cache *block_group,
 			    struct btrfs_path *path)
@@ -200,11 +200,11 @@ int create_free_space_inode(struct btrfs_root *root,
 	int ret;
 	u64 ino;
 
-	ret = btrfs_find_free_objectid(root, &ino);
+	ret = btrfs_find_free_objectid(fs_info->tree_root, &ino);
 	if (ret < 0)
 		return ret;
 
-	return __create_free_space_inode(root, trans, path, ino,
+	return __create_free_space_inode(fs_info->tree_root, trans, path, ino,
 					 block_group->key.objectid);
 }
 
@@ -227,21 +227,21 @@ int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
 	return ret;
 }
 
-int btrfs_truncate_free_space_cache(struct btrfs_root *root,
-				    struct btrfs_trans_handle *trans,
+int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
 				    struct btrfs_block_group_cache *block_group,
 				    struct inode *inode)
 {
+	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret = 0;
-	struct btrfs_path *path = btrfs_alloc_path();
 	bool locked = false;
 
-	if (!path) {
-		ret = -ENOMEM;
-		goto fail;
-	}
-
 	if (block_group) {
+		struct btrfs_path *path = btrfs_alloc_path();
+
+		if (!path) {
+			ret = -ENOMEM;
+			goto fail;
+		}
 		locked = true;
 		mutex_lock(&trans->transaction->cache_write_mutex);
 		if (!list_empty(&block_group->io_list)) {
@@ -258,10 +258,10 @@ int btrfs_truncate_free_space_cache(struct btrfs_root *root,
 		spin_lock(&block_group->lock);
 		block_group->disk_cache_state = BTRFS_DC_CLEAR;
 		spin_unlock(&block_group->lock);
+		btrfs_free_path(path);
 	}
-	btrfs_free_path(path);
 
-	btrfs_i_size_write(inode, 0);
+	btrfs_i_size_write(BTRFS_I(inode), 0);
 	truncate_pagecache(inode, 0);
 
 	/*
@@ -286,14 +286,14 @@ fail:
 	return ret;
 }
 
-static int readahead_cache(struct inode *inode)
+static void readahead_cache(struct inode *inode)
 {
 	struct file_ra_state *ra;
 	unsigned long last_index;
 
 	ra = kzalloc(sizeof(*ra), GFP_NOFS);
 	if (!ra)
-		return -ENOMEM;
+		return;
 
 	file_ra_state_init(ra, inode->i_mapping);
 	last_index = (i_size_read(inode) - 1) >> PAGE_SHIFT;
@@ -301,8 +301,6 @@ static int readahead_cache(struct inode *inode)
 	page_cache_sync_readahead(inode->i_mapping, ra, NULL, 0, last_index);
 
 	kfree(ra);
-
-	return 0;
 }
 
 static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode,
@@ -313,7 +311,7 @@ static int io_ctl_init(struct btrfs_io_ctl *io_ctl, struct inode *inode,
 
 	num_pages = DIV_ROUND_UP(i_size_read(inode), PAGE_SIZE);
 
-	if (btrfs_ino(inode) != BTRFS_FREE_INO_OBJECTID)
+	if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FREE_INO_OBJECTID)
 		check_crcs = 1;
 
 	/* Make sure we can fit our crcs into the first page */
@@ -357,7 +355,7 @@ static void io_ctl_map_page(struct btrfs_io_ctl *io_ctl, int clear)
 	io_ctl->orig = io_ctl->cur;
 	io_ctl->size = PAGE_SIZE;
 	if (clear)
-		memset(io_ctl->cur, 0, PAGE_SIZE);
+		clear_page(io_ctl->cur);
 }
 
 static void io_ctl_drop_pages(struct btrfs_io_ctl *io_ctl)
@@ -730,9 +728,7 @@ static int __load_free_space_cache(struct btrfs_root *root, struct inode *inode,
 	if (ret)
 		return ret;
 
-	ret = readahead_cache(inode);
-	if (ret)
-		goto out;
+	readahead_cache(inode);
 
 	ret = io_ctl_prepare_pages(&io_ctl, inode, 1);
 	if (ret)
@@ -828,7 +824,6 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 			  struct btrfs_block_group_cache *block_group)
 {
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
-	struct btrfs_root *root = fs_info->tree_root;
 	struct inode *inode;
 	struct btrfs_path *path;
 	int ret = 0;
@@ -852,7 +847,7 @@ int load_free_space_cache(struct btrfs_fs_info *fs_info,
 	path->search_commit_root = 1;
 	path->skip_locking = 1;
 
-	inode = lookup_free_space_inode(root, block_group, path);
+	inode = lookup_free_space_inode(fs_info, block_group, path);
 	if (IS_ERR(inode)) {
 		btrfs_free_path(path);
 		return 0;
@@ -1128,8 +1123,7 @@ cleanup_bitmap_list(struct list_head *bitmap_list)
 static void noinline_for_stack
 cleanup_write_cache_enospc(struct inode *inode,
 			   struct btrfs_io_ctl *io_ctl,
-			   struct extent_state **cached_state,
-			   struct list_head *bitmap_list)
+			   struct extent_state **cached_state)
 {
 	io_ctl_drop_pages(io_ctl);
 	unlock_extent_cached(&BTRFS_I(inode)->io_tree, 0,
@@ -1225,8 +1219,6 @@ int btrfs_wait_cache_io(struct btrfs_trans_handle *trans,
  * @ctl - the free space cache we are going to write out
  * @block_group - the block_group for this cache if it belongs to a block_group
  * @trans - the trans handle
- * @path - the path to use
- * @offset - the offset for the key we'll insert
  *
  * This function writes out a free space cache struct to disk for quick recovery
  * on mount.  This will return 0 if it was successful in writing the cache out,
@@ -1236,8 +1228,7 @@ static int __btrfs_write_out_cache(struct btrfs_root *root, struct inode *inode,
 				   struct btrfs_free_space_ctl *ctl,
 				   struct btrfs_block_group_cache *block_group,
 				   struct btrfs_io_ctl *io_ctl,
-				   struct btrfs_trans_handle *trans,
-				   struct btrfs_path *path, u64 offset)
+				   struct btrfs_trans_handle *trans)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct extent_state *cached_state = NULL;
@@ -1365,7 +1356,7 @@ out_nospc_locked:
 	mutex_unlock(&ctl->cache_writeout_mutex);
 
 out_nospc:
-	cleanup_write_cache_enospc(inode, io_ctl, &cached_state, &bitmap_list);
+	cleanup_write_cache_enospc(inode, io_ctl, &cached_state);
 
 	if (block_group && (block_group->flags & BTRFS_BLOCK_GROUP_DATA))
 		up_write(&block_group->data_rwsem);
@@ -1378,7 +1369,6 @@ int btrfs_write_out_cache(struct btrfs_fs_info *fs_info,
 			  struct btrfs_block_group_cache *block_group,
 			  struct btrfs_path *path)
 {
-	struct btrfs_root *root = fs_info->tree_root;
 	struct btrfs_free_space_ctl *ctl = block_group->free_space_ctl;
 	struct inode *inode;
 	int ret = 0;
@@ -1390,13 +1380,12 @@ int btrfs_write_out_cache(struct btrfs_fs_info *fs_info,
 	}
 	spin_unlock(&block_group->lock);
 
-	inode = lookup_free_space_inode(root, block_group, path);
+	inode = lookup_free_space_inode(fs_info, block_group, path);
 	if (IS_ERR(inode))
 		return 0;
 
-	ret = __btrfs_write_out_cache(root, inode, ctl, block_group,
-				      &block_group->io_ctl, trans,
-				      path, block_group->key.objectid);
+	ret = __btrfs_write_out_cache(fs_info->tree_root, inode, ctl,
+				block_group, &block_group->io_ctl, trans);
 	if (ret) {
 #ifdef DEBUG
 		btrfs_err(fs_info,
@@ -3543,8 +3532,7 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root,
 		return 0;
 
 	memset(&io_ctl, 0, sizeof(io_ctl));
-	ret = __btrfs_write_out_cache(root, inode, ctl, NULL, &io_ctl,
-				      trans, path, 0);
+	ret = __btrfs_write_out_cache(root, inode, ctl, NULL, &io_ctl, trans);
 	if (!ret) {
 		/*
 		 * At this point writepages() didn't error out, so our metadata
@@ -3558,7 +3546,8 @@ int btrfs_write_out_ino_cache(struct btrfs_root *root,
 
 	if (ret) {
 		if (release_metadata)
-			btrfs_delalloc_release_metadata(inode, inode->i_size);
+			btrfs_delalloc_release_metadata(BTRFS_I(inode),
+					inode->i_size);
 #ifdef DEBUG
 		btrfs_err(fs_info,
 			  "failed to write free ino cache for root %llu",
diff --git a/fs/btrfs/free-space-cache.h b/fs/btrfs/free-space-cache.h
index 6f3c025a2c6c..79eca4cabb1c 100644
--- a/fs/btrfs/free-space-cache.h
+++ b/fs/btrfs/free-space-cache.h
@@ -51,18 +51,17 @@ struct btrfs_free_space_op {
 
 struct btrfs_io_ctl;
 
-struct inode *lookup_free_space_inode(struct btrfs_root *root,
+struct inode *lookup_free_space_inode(struct btrfs_fs_info *fs_info,
 				      struct btrfs_block_group_cache
 				      *block_group, struct btrfs_path *path);
-int create_free_space_inode(struct btrfs_root *root,
+int create_free_space_inode(struct btrfs_fs_info *fs_info,
 			    struct btrfs_trans_handle *trans,
 			    struct btrfs_block_group_cache *block_group,
 			    struct btrfs_path *path);
 
 int btrfs_check_trunc_cache_free_space(struct btrfs_fs_info *fs_info,
 				       struct btrfs_block_rsv *rsv);
-int btrfs_truncate_free_space_cache(struct btrfs_root *root,
-				    struct btrfs_trans_handle *trans,
+int btrfs_truncate_free_space_cache(struct btrfs_trans_handle *trans,
 				    struct btrfs_block_group_cache *block_group,
 				    struct inode *inode);
 int load_free_space_cache(struct btrfs_fs_info *fs_info,
diff --git a/fs/btrfs/free-space-tree.c b/fs/btrfs/free-space-tree.c
index ff0c55337c2e..a5e34de06c2f 100644
--- a/fs/btrfs/free-space-tree.c
+++ b/fs/btrfs/free-space-tree.c
@@ -17,7 +17,7 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/vmalloc.h>
+#include <linux/sched/mm.h>
 #include "ctree.h"
 #include "disk-io.h"
 #include "locking.h"
@@ -153,22 +153,21 @@ static inline u32 free_space_bitmap_size(u64 size, u32 sectorsize)
 
 static u8 *alloc_bitmap(u32 bitmap_size)
 {
-	void *mem;
+	u8 *ret;
+	unsigned int nofs_flag;
 
 	/*
-	 * The allocation size varies, observed numbers were < 4K up to 16K.
-	 * Using vmalloc unconditionally would be too heavy, we'll try
-	 * contiguous allocations first.
+	 * GFP_NOFS doesn't work with kvmalloc(), but we really can't recurse
+	 * into the filesystem as the free space bitmap can be modified in the
+	 * critical section of a transaction commit.
+	 *
+	 * TODO: push the memalloc_nofs_{save,restore}() to the caller where we
+	 * know that recursion is unsafe.
 	 */
-	if  (bitmap_size <= PAGE_SIZE)
-		return kzalloc(bitmap_size, GFP_NOFS);
-
-	mem = kzalloc(bitmap_size, GFP_NOFS | __GFP_NOWARN);
-	if (mem)
-		return mem;
-
-	return __vmalloc(bitmap_size, GFP_NOFS | __GFP_HIGHMEM | __GFP_ZERO,
-			 PAGE_KERNEL);
+	nofs_flag = memalloc_nofs_save();
+	ret = kvzalloc(bitmap_size, GFP_KERNEL);
+	memalloc_nofs_restore(nofs_flag);
+	return ret;
 }
 
 int convert_free_space_to_bitmaps(struct btrfs_trans_handle *trans,
@@ -1189,11 +1188,7 @@ int btrfs_create_free_space_tree(struct btrfs_fs_info *fs_info)
 	btrfs_set_fs_compat_ro(fs_info, FREE_SPACE_TREE_VALID);
 	clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
 
-	ret = btrfs_commit_transaction(trans);
-	if (ret)
-		return ret;
-
-	return 0;
+	return btrfs_commit_transaction(trans);
 
 abort:
 	clear_bit(BTRFS_FS_CREATING_FREE_SPACE_TREE, &fs_info->flags);
@@ -1269,7 +1264,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
 	list_del(&free_space_root->dirty_list);
 
 	btrfs_tree_lock(free_space_root->node);
-	clean_tree_block(trans, fs_info, free_space_root->node);
+	clean_tree_block(fs_info, free_space_root->node);
 	btrfs_tree_unlock(free_space_root->node);
 	btrfs_free_tree_block(trans, free_space_root, free_space_root->node,
 			      0, 1);
@@ -1278,11 +1273,7 @@ int btrfs_clear_free_space_tree(struct btrfs_fs_info *fs_info)
 	free_extent_buffer(free_space_root->commit_root);
 	kfree(free_space_root);
 
-	ret = btrfs_commit_transaction(trans);
-	if (ret)
-		return ret;
-
-	return 0;
+	return btrfs_commit_transaction(trans);
 
 abort:
 	btrfs_abort_transaction(trans, ret);
diff --git a/fs/btrfs/hash.c b/fs/btrfs/hash.c
index a97fdc156a03..baacc1866861 100644
--- a/fs/btrfs/hash.c
+++ b/fs/btrfs/hash.c
@@ -38,6 +38,7 @@ u32 btrfs_crc32c(u32 crc, const void *address, unsigned int length)
 {
 	SHASH_DESC_ON_STACK(shash, tfm);
 	u32 *ctx = (u32 *)shash_desc_ctx(shash);
+	u32 retval;
 	int err;
 
 	shash->tfm = tfm;
@@ -47,5 +48,7 @@ u32 btrfs_crc32c(u32 crc, const void *address, unsigned int length)
 	err = crypto_shash_update(shash, address, length);
 	BUG_ON(err);
 
-	return *ctx;
+	retval = *ctx;
+	barrier_data(ctx);
+	return retval;
 }
diff --git a/fs/btrfs/inode-map.c b/fs/btrfs/inode-map.c
index 144b119ff43f..d02019747d00 100644
--- a/fs/btrfs/inode-map.c
+++ b/fs/btrfs/inode-map.c
@@ -400,6 +400,7 @@ int btrfs_save_ino_cache(struct btrfs_root *root,
 	struct btrfs_path *path;
 	struct inode *inode;
 	struct btrfs_block_rsv *rsv;
+	struct extent_changeset *data_reserved = NULL;
 	u64 num_bytes;
 	u64 alloc_hint = 0;
 	int ret;
@@ -467,7 +468,7 @@ again:
 	}
 
 	if (i_size_read(inode) > 0) {
-		ret = btrfs_truncate_free_space_cache(root, trans, NULL, inode);
+		ret = btrfs_truncate_free_space_cache(trans, NULL, inode);
 		if (ret) {
 			if (ret != -ENOSPC)
 				btrfs_abort_transaction(trans, ret);
@@ -492,14 +493,14 @@ again:
 	/* Just to make sure we have enough space */
 	prealloc += 8 * PAGE_SIZE;
 
-	ret = btrfs_delalloc_reserve_space(inode, 0, prealloc);
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, 0, prealloc);
 	if (ret)
 		goto out_put;
 
 	ret = btrfs_prealloc_file_range_trans(inode, trans, 0, 0, prealloc,
 					      prealloc, prealloc, &alloc_hint);
 	if (ret) {
-		btrfs_delalloc_release_metadata(inode, prealloc);
+		btrfs_delalloc_release_metadata(BTRFS_I(inode), prealloc);
 		goto out_put;
 	}
 
@@ -516,6 +517,7 @@ out:
 	trans->bytes_reserved = num_bytes;
 
 	btrfs_free_path(path);
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
diff --git a/fs/btrfs/inode.c b/fs/btrfs/inode.c
index 1e861a063721..95c212037095 100644
--- a/fs/btrfs/inode.c
+++ b/fs/btrfs/inode.c
@@ -71,6 +71,7 @@ struct btrfs_dio_data {
 	u64 reserve;
 	u64 unsubmitted_oe_range_start;
 	u64 unsubmitted_oe_range_end;
+	int overwrite;
 };
 
 static const struct inode_operations btrfs_dir_inode_operations;
@@ -85,7 +86,6 @@ static const struct extent_io_ops btrfs_extent_io_ops;
 
 static struct kmem_cache *btrfs_inode_cachep;
 struct kmem_cache *btrfs_trans_handle_cachep;
-struct kmem_cache *btrfs_transaction_cachep;
 struct kmem_cache *btrfs_path_cachep;
 struct kmem_cache *btrfs_free_space_cachep;
 
@@ -108,11 +108,36 @@ static noinline int cow_file_range(struct inode *inode,
 				   u64 start, u64 end, u64 delalloc_end,
 				   int *page_started, unsigned long *nr_written,
 				   int unlock, struct btrfs_dedupe_hash *hash);
-static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
-					   u64 len, u64 orig_start,
-					   u64 block_start, u64 block_len,
-					   u64 orig_block_len, u64 ram_bytes,
-					   int type);
+static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
+				       u64 orig_start, u64 block_start,
+				       u64 block_len, u64 orig_block_len,
+				       u64 ram_bytes, int compress_type,
+				       int type);
+
+static void __endio_write_update_ordered(struct inode *inode,
+					 const u64 offset, const u64 bytes,
+					 const bool uptodate);
+
+/*
+ * Cleanup all submitted ordered extents in specified range to handle errors
+ * from the fill_dellaloc() callback.
+ *
+ * NOTE: caller must ensure that when an error happens, it can not call
+ * extent_clear_unlock_delalloc() to clear both the bits EXTENT_DO_ACCOUNTING
+ * and EXTENT_DELALLOC simultaneously, because that causes the reserved metadata
+ * to be released, which we want to happen only when finishing the ordered
+ * extent (btrfs_finish_ordered_io()). Also note that the caller of the
+ * fill_delalloc() callback already does proper cleanup for the first page of
+ * the range, that is, it invokes the callback writepage_end_io_hook() for the
+ * range of the first page.
+ */
+static inline void btrfs_cleanup_ordered_extents(struct inode *inode,
+						 const u64 offset,
+						 const u64 bytes)
+{
+	return __endio_write_update_ordered(inode, offset + PAGE_SIZE,
+					    bytes - PAGE_SIZE, false);
+}
 
 static int btrfs_dirty_inode(struct inode *inode);
 
@@ -152,7 +177,6 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 	char *kaddr;
 	unsigned long ptr;
 	struct btrfs_file_extent_item *ei;
-	int err = 0;
 	int ret;
 	size_t cur_size = size;
 	unsigned long offset;
@@ -166,7 +190,7 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 		struct btrfs_key key;
 		size_t datasize;
 
-		key.objectid = btrfs_ino(inode);
+		key.objectid = btrfs_ino(BTRFS_I(inode));
 		key.offset = start;
 		key.type = BTRFS_EXTENT_DATA_KEY;
 
@@ -174,10 +198,8 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 		path->leave_spinning = 1;
 		ret = btrfs_insert_empty_item(trans, root, path, &key,
 					      datasize);
-		if (ret) {
-			err = ret;
+		if (ret)
 			goto fail;
-		}
 	}
 	leaf = path->nodes[0];
 	ei = btrfs_item_ptr(leaf, path->slots[0],
@@ -232,9 +254,8 @@ static int insert_inline_extent(struct btrfs_trans_handle *trans,
 	BTRFS_I(inode)->disk_i_size = inode->i_size;
 	ret = btrfs_update_inode(trans, root, inode);
 
-	return ret;
 fail:
-	return err;
+	return ret;
 }
 
 
@@ -315,8 +336,8 @@ static noinline int cow_file_range_inline(struct btrfs_root *root,
 	}
 
 	set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &BTRFS_I(inode)->runtime_flags);
-	btrfs_delalloc_release_metadata(inode, end + 1 - start);
-	btrfs_drop_extent_cache(inode, start, aligned_end - 1, 0);
+	btrfs_delalloc_release_metadata(BTRFS_I(inode), end + 1 - start);
+	btrfs_drop_extent_cache(BTRFS_I(inode), start, aligned_end - 1, 0);
 out:
 	/*
 	 * Don't forget to free the reserved space, as for inlined extent
@@ -324,7 +345,7 @@ out:
 	 * And at reserve time, it's always aligned to page size, so
 	 * just free one page here.
 	 */
-	btrfs_qgroup_free_data(inode, 0, PAGE_SIZE);
+	btrfs_qgroup_free_data(inode, NULL, 0, PAGE_SIZE);
 	btrfs_free_path(path);
 	btrfs_end_transaction(trans);
 	return ret;
@@ -388,6 +409,15 @@ static inline int inode_need_compress(struct inode *inode)
 	return 0;
 }
 
+static inline void inode_should_defrag(struct btrfs_inode *inode,
+		u64 start, u64 end, u64 num_bytes, u64 small_write)
+{
+	/* If this is a small write inside eof, kick off a defrag */
+	if (num_bytes < small_write &&
+	    (start > 0 || end + 1 < inode->disk_i_size))
+		btrfs_add_inode_defrag(NULL, inode);
+}
+
 /*
  * we create compressed extents in two phases.  The first
  * phase compresses a range of pages that have already been
@@ -420,26 +450,23 @@ static noinline void compress_file_range(struct inode *inode,
 	int ret = 0;
 	struct page **pages = NULL;
 	unsigned long nr_pages;
-	unsigned long nr_pages_ret = 0;
 	unsigned long total_compressed = 0;
 	unsigned long total_in = 0;
-	unsigned long max_compressed = SZ_128K;
-	unsigned long max_uncompressed = SZ_128K;
 	int i;
 	int will_compress;
 	int compress_type = fs_info->compress_type;
 	int redirty = 0;
 
-	/* if this is a small write inside eof, kick off a defrag */
-	if ((end - start + 1) < SZ_16K &&
-	    (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
-		btrfs_add_inode_defrag(NULL, inode);
+	inode_should_defrag(BTRFS_I(inode), start, end, end - start + 1,
+			SZ_16K);
 
 	actual_end = min_t(u64, isize, end + 1);
 again:
 	will_compress = 0;
 	nr_pages = (end >> PAGE_SHIFT) - (start >> PAGE_SHIFT) + 1;
-	nr_pages = min_t(unsigned long, nr_pages, SZ_128K / PAGE_SIZE);
+	BUILD_BUG_ON((BTRFS_MAX_COMPRESSED % PAGE_SIZE) != 0);
+	nr_pages = min_t(unsigned long, nr_pages,
+			BTRFS_MAX_COMPRESSED / PAGE_SIZE);
 
 	/*
 	 * we don't want to send crud past the end of i_size through
@@ -464,17 +491,8 @@ again:
 	   (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
 		goto cleanup_and_bail_uncompressed;
 
-	/* we want to make sure that amount of ram required to uncompress
-	 * an extent is reasonable, so we limit the total size in ram
-	 * of a compressed extent to 128k.  This is a crucial number
-	 * because it also controls how easily we can spread reads across
-	 * cpus for decompression.
-	 *
-	 * We also want to make sure the amount of IO required to do
-	 * a random read is reasonably small, so we limit the size of
-	 * a compressed extent to 128k.
-	 */
-	total_compressed = min(total_compressed, max_uncompressed);
+	total_compressed = min_t(unsigned long, total_compressed,
+			BTRFS_MAX_UNCOMPRESSED);
 	num_bytes = ALIGN(end - start + 1, blocksize);
 	num_bytes = max(blocksize,  num_bytes);
 	total_in = 0;
@@ -509,16 +527,15 @@ again:
 		redirty = 1;
 		ret = btrfs_compress_pages(compress_type,
 					   inode->i_mapping, start,
-					   total_compressed, pages,
-					   nr_pages, &nr_pages_ret,
+					   pages,
+					   &nr_pages,
 					   &total_in,
-					   &total_compressed,
-					   max_compressed);
+					   &total_compressed);
 
 		if (!ret) {
 			unsigned long offset = total_compressed &
 				(PAGE_SIZE - 1);
-			struct page *page = pages[nr_pages_ret - 1];
+			struct page *page = pages[nr_pages - 1];
 			char *kaddr;
 
 			/* zero the tail end of the last page, we might be
@@ -541,7 +558,7 @@ cont:
 			 * to make an uncompressed inline extent.
 			 */
 			ret = cow_file_range_inline(root, inode, start, end,
-						    0, 0, NULL);
+					    0, BTRFS_COMPRESS_NONE, NULL);
 		} else {
 			/* try making a compressed inline extent */
 			ret = cow_file_range_inline(root, inode, start, end,
@@ -550,7 +567,7 @@ cont:
 		}
 		if (ret <= 0) {
 			unsigned long clear_flags = EXTENT_DELALLOC |
-				EXTENT_DEFRAG;
+				EXTENT_DELALLOC_NEW | EXTENT_DEFRAG;
 			unsigned long page_error_op;
 
 			clear_flags |= (ret < 0) ? EXTENT_DO_ACCOUNTING : 0;
@@ -568,8 +585,10 @@ cont:
 						     PAGE_SET_WRITEBACK |
 						     page_error_op |
 						     PAGE_END_WRITEBACK);
-			btrfs_free_reserved_data_space_noquota(inode, start,
-						end - start + 1);
+			if (ret == 0)
+				btrfs_free_reserved_data_space_noquota(inode,
+							       start,
+							       end - start + 1);
 			goto free_pages_out;
 		}
 	}
@@ -584,12 +603,11 @@ cont:
 
 		/*
 		 * one last check to make sure the compression is really a
-		 * win, compare the page count read with the blocks on disk
+		 * win, compare the page count read with the blocks on disk,
+		 * compression must free at least one sector size
 		 */
 		total_in = ALIGN(total_in, PAGE_SIZE);
-		if (total_compressed >= total_in) {
-			will_compress = 0;
-		} else {
+		if (total_compressed + blocksize <= total_in) {
 			num_bytes = total_in;
 			*num_added += 1;
 
@@ -599,7 +617,7 @@ cont:
 			 * will submit them to the elevator.
 			 */
 			add_async_extent(async_cow, start, num_bytes,
-					total_compressed, pages, nr_pages_ret,
+					total_compressed, pages, nr_pages,
 					compress_type);
 
 			if (start + num_bytes < end) {
@@ -616,14 +634,14 @@ cont:
 		 * the compression code ran but failed to make things smaller,
 		 * free any pages it allocated and our page pointer array
 		 */
-		for (i = 0; i < nr_pages_ret; i++) {
+		for (i = 0; i < nr_pages; i++) {
 			WARN_ON(pages[i]->mapping);
 			put_page(pages[i]);
 		}
 		kfree(pages);
 		pages = NULL;
 		total_compressed = 0;
-		nr_pages_ret = 0;
+		nr_pages = 0;
 
 		/* flag the file so we don't compress in the future */
 		if (!btrfs_test_opt(fs_info, FORCE_COMPRESS) &&
@@ -652,7 +670,7 @@ cleanup_and_bail_uncompressed:
 	return;
 
 free_pages_out:
-	for (i = 0; i < nr_pages_ret; i++) {
+	for (i = 0; i < nr_pages; i++) {
 		WARN_ON(pages[i]->mapping);
 		put_page(pages[i]);
 	}
@@ -690,7 +708,6 @@ static noinline void submit_compressed_extents(struct inode *inode,
 	struct btrfs_key ins;
 	struct extent_map *em;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
 	struct extent_io_tree *io_tree;
 	int ret = 0;
 
@@ -778,46 +795,19 @@ retry:
 		 * here we're doing allocation and writeback of the
 		 * compressed pages
 		 */
-		btrfs_drop_extent_cache(inode, async_extent->start,
-					async_extent->start +
-					async_extent->ram_size - 1, 0);
-
-		em = alloc_extent_map();
-		if (!em) {
-			ret = -ENOMEM;
-			goto out_free_reserve;
-		}
-		em->start = async_extent->start;
-		em->len = async_extent->ram_size;
-		em->orig_start = em->start;
-		em->mod_start = em->start;
-		em->mod_len = em->len;
-
-		em->block_start = ins.objectid;
-		em->block_len = ins.offset;
-		em->orig_block_len = ins.offset;
-		em->ram_bytes = async_extent->ram_size;
-		em->bdev = fs_info->fs_devices->latest_bdev;
-		em->compress_type = async_extent->compress_type;
-		set_bit(EXTENT_FLAG_PINNED, &em->flags);
-		set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
-		em->generation = -1;
-
-		while (1) {
-			write_lock(&em_tree->lock);
-			ret = add_extent_mapping(em_tree, em, 1);
-			write_unlock(&em_tree->lock);
-			if (ret != -EEXIST) {
-				free_extent_map(em);
-				break;
-			}
-			btrfs_drop_extent_cache(inode, async_extent->start,
-						async_extent->start +
-						async_extent->ram_size - 1, 0);
-		}
-
-		if (ret)
+		em = create_io_em(inode, async_extent->start,
+				  async_extent->ram_size, /* len */
+				  async_extent->start, /* orig_start */
+				  ins.objectid, /* block_start */
+				  ins.offset, /* block_len */
+				  ins.offset, /* orig_block_len */
+				  async_extent->ram_size, /* ram_bytes */
+				  async_extent->compress_type,
+				  BTRFS_ORDERED_COMPRESSED);
+		if (IS_ERR(em))
+			/* ret value is not necessary due to void function */
 			goto out_free_reserve;
+		free_extent_map(em);
 
 		ret = btrfs_add_ordered_extent_compress(inode,
 						async_extent->start,
@@ -827,7 +817,8 @@ retry:
 						BTRFS_ORDERED_COMPRESSED,
 						async_extent->compress_type);
 		if (ret) {
-			btrfs_drop_extent_cache(inode, async_extent->start,
+			btrfs_drop_extent_cache(BTRFS_I(inode),
+						async_extent->start,
 						async_extent->start +
 						async_extent->ram_size - 1, 0);
 			goto out_free_reserve;
@@ -845,13 +836,12 @@ retry:
 				NULL, EXTENT_LOCKED | EXTENT_DELALLOC,
 				PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
 				PAGE_SET_WRITEBACK);
-		ret = btrfs_submit_compressed_write(inode,
+		if (btrfs_submit_compressed_write(inode,
 				    async_extent->start,
 				    async_extent->ram_size,
 				    ins.objectid,
 				    ins.offset, async_extent->pages,
-				    async_extent->nr_pages);
-		if (ret) {
+				    async_extent->nr_pages)) {
 			struct extent_io_tree *tree = &BTRFS_I(inode)->io_tree;
 			struct page *p = async_extent->pages[0];
 			const u64 start = async_extent->start;
@@ -882,6 +872,7 @@ out_free:
 				     async_extent->start +
 				     async_extent->ram_size - 1,
 				     NULL, EXTENT_LOCKED | EXTENT_DELALLOC |
+				     EXTENT_DELALLOC_NEW |
 				     EXTENT_DEFRAG | EXTENT_DO_ACCOUNTING,
 				     PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
 				     PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK |
@@ -948,14 +939,16 @@ static noinline int cow_file_range(struct inode *inode,
 	u64 num_bytes;
 	unsigned long ram_size;
 	u64 disk_num_bytes;
-	u64 cur_alloc_size;
+	u64 cur_alloc_size = 0;
 	u64 blocksize = fs_info->sectorsize;
 	struct btrfs_key ins;
 	struct extent_map *em;
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	unsigned clear_bits;
+	unsigned long page_ops;
+	bool extent_reserved = false;
 	int ret = 0;
 
-	if (btrfs_is_free_space_inode(inode)) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
 		WARN_ON_ONCE(1);
 		ret = -EINVAL;
 		goto out_unlock;
@@ -965,19 +958,17 @@ static noinline int cow_file_range(struct inode *inode,
 	num_bytes = max(blocksize,  num_bytes);
 	disk_num_bytes = num_bytes;
 
-	/* if this is a small write inside eof, kick off defrag */
-	if (num_bytes < SZ_64K &&
-	    (start > 0 || end + 1 < BTRFS_I(inode)->disk_i_size))
-		btrfs_add_inode_defrag(NULL, inode);
+	inode_should_defrag(BTRFS_I(inode), start, end, num_bytes, SZ_64K);
 
 	if (start == 0) {
 		/* lets try to make an inline extent */
-		ret = cow_file_range_inline(root, inode, start, end, 0, 0,
-					    NULL);
+		ret = cow_file_range_inline(root, inode, start, end, 0,
+					BTRFS_COMPRESS_NONE, NULL);
 		if (ret == 0) {
 			extent_clear_unlock_delalloc(inode, start, end,
 				     delalloc_end, NULL,
 				     EXTENT_LOCKED | EXTENT_DELALLOC |
+				     EXTENT_DELALLOC_NEW |
 				     EXTENT_DEFRAG, PAGE_UNLOCK |
 				     PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
 				     PAGE_END_WRITEBACK);
@@ -996,53 +987,32 @@ static noinline int cow_file_range(struct inode *inode,
 	       btrfs_super_total_bytes(fs_info->super_copy));
 
 	alloc_hint = get_extent_allocation_hint(inode, start, num_bytes);
-	btrfs_drop_extent_cache(inode, start, start + num_bytes - 1, 0);
+	btrfs_drop_extent_cache(BTRFS_I(inode), start,
+			start + num_bytes - 1, 0);
 
 	while (disk_num_bytes > 0) {
-		unsigned long op;
-
 		cur_alloc_size = disk_num_bytes;
 		ret = btrfs_reserve_extent(root, cur_alloc_size, cur_alloc_size,
 					   fs_info->sectorsize, 0, alloc_hint,
 					   &ins, 1, 1);
 		if (ret < 0)
 			goto out_unlock;
+		cur_alloc_size = ins.offset;
+		extent_reserved = true;
 
-		em = alloc_extent_map();
-		if (!em) {
-			ret = -ENOMEM;
-			goto out_reserve;
-		}
-		em->start = start;
-		em->orig_start = em->start;
 		ram_size = ins.offset;
-		em->len = ins.offset;
-		em->mod_start = em->start;
-		em->mod_len = em->len;
-
-		em->block_start = ins.objectid;
-		em->block_len = ins.offset;
-		em->orig_block_len = ins.offset;
-		em->ram_bytes = ram_size;
-		em->bdev = fs_info->fs_devices->latest_bdev;
-		set_bit(EXTENT_FLAG_PINNED, &em->flags);
-		em->generation = -1;
-
-		while (1) {
-			write_lock(&em_tree->lock);
-			ret = add_extent_mapping(em_tree, em, 1);
-			write_unlock(&em_tree->lock);
-			if (ret != -EEXIST) {
-				free_extent_map(em);
-				break;
-			}
-			btrfs_drop_extent_cache(inode, start,
-						start + ram_size - 1, 0);
-		}
-		if (ret)
+		em = create_io_em(inode, start, ins.offset, /* len */
+				  start, /* orig_start */
+				  ins.objectid, /* block_start */
+				  ins.offset, /* block_len */
+				  ins.offset, /* orig_block_len */
+				  ram_size, /* ram_bytes */
+				  BTRFS_COMPRESS_NONE, /* compress_type */
+				  BTRFS_ORDERED_REGULAR /* type */);
+		if (IS_ERR(em))
 			goto out_reserve;
+		free_extent_map(em);
 
-		cur_alloc_size = ins.offset;
 		ret = btrfs_add_ordered_extent(inode, start, ins.objectid,
 					       ram_size, cur_alloc_size, 0);
 		if (ret)
@@ -1052,15 +1022,24 @@ static noinline int cow_file_range(struct inode *inode,
 		    BTRFS_DATA_RELOC_TREE_OBJECTID) {
 			ret = btrfs_reloc_clone_csums(inode, start,
 						      cur_alloc_size);
+			/*
+			 * Only drop cache here, and process as normal.
+			 *
+			 * We must not allow extent_clear_unlock_delalloc()
+			 * at out_unlock label to free meta of this ordered
+			 * extent, as its meta should be freed by
+			 * btrfs_finish_ordered_io().
+			 *
+			 * So we must continue until @start is increased to
+			 * skip current ordered extent.
+			 */
 			if (ret)
-				goto out_drop_extent_cache;
+				btrfs_drop_extent_cache(BTRFS_I(inode), start,
+						start + ram_size - 1, 0);
 		}
 
 		btrfs_dec_block_group_reservations(fs_info, ins.objectid);
 
-		if (disk_num_bytes < cur_alloc_size)
-			break;
-
 		/* we're not doing compressed IO, don't unlock the first
 		 * page (which the caller expects to stay locked), don't
 		 * clear any dirty bits and don't set any writeback bits
@@ -1068,34 +1047,69 @@ static noinline int cow_file_range(struct inode *inode,
 		 * Do set the Private2 bit so we know this page was properly
 		 * setup for writepage
 		 */
-		op = unlock ? PAGE_UNLOCK : 0;
-		op |= PAGE_SET_PRIVATE2;
+		page_ops = unlock ? PAGE_UNLOCK : 0;
+		page_ops |= PAGE_SET_PRIVATE2;
 
 		extent_clear_unlock_delalloc(inode, start,
 					     start + ram_size - 1,
 					     delalloc_end, locked_page,
 					     EXTENT_LOCKED | EXTENT_DELALLOC,
-					     op);
-		disk_num_bytes -= cur_alloc_size;
+					     page_ops);
+		if (disk_num_bytes < cur_alloc_size)
+			disk_num_bytes = 0;
+		else
+			disk_num_bytes -= cur_alloc_size;
 		num_bytes -= cur_alloc_size;
 		alloc_hint = ins.objectid + ins.offset;
 		start += cur_alloc_size;
+		extent_reserved = false;
+
+		/*
+		 * btrfs_reloc_clone_csums() error, since start is increased
+		 * extent_clear_unlock_delalloc() at out_unlock label won't
+		 * free metadata of current ordered extent, we're OK to exit.
+		 */
+		if (ret)
+			goto out_unlock;
 	}
 out:
 	return ret;
 
 out_drop_extent_cache:
-	btrfs_drop_extent_cache(inode, start, start + ram_size - 1, 0);
+	btrfs_drop_extent_cache(BTRFS_I(inode), start, start + ram_size - 1, 0);
 out_reserve:
 	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
 	btrfs_free_reserved_extent(fs_info, ins.objectid, ins.offset, 1);
 out_unlock:
+	clear_bits = EXTENT_LOCKED | EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
+		EXTENT_DEFRAG | EXTENT_CLEAR_META_RESV;
+	page_ops = PAGE_UNLOCK | PAGE_CLEAR_DIRTY | PAGE_SET_WRITEBACK |
+		PAGE_END_WRITEBACK;
+	/*
+	 * If we reserved an extent for our delalloc range (or a subrange) and
+	 * failed to create the respective ordered extent, then it means that
+	 * when we reserved the extent we decremented the extent's size from
+	 * the data space_info's bytes_may_use counter and incremented the
+	 * space_info's bytes_reserved counter by the same amount. We must make
+	 * sure extent_clear_unlock_delalloc() does not try to decrement again
+	 * the data space_info's bytes_may_use counter, therefore we do not pass
+	 * it the flag EXTENT_CLEAR_DATA_RESV.
+	 */
+	if (extent_reserved) {
+		extent_clear_unlock_delalloc(inode, start,
+					     start + cur_alloc_size,
+					     start + cur_alloc_size,
+					     locked_page,
+					     clear_bits,
+					     page_ops);
+		start += cur_alloc_size;
+		if (start >= end)
+			goto out;
+	}
 	extent_clear_unlock_delalloc(inode, start, end, delalloc_end,
 				     locked_page,
-				     EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
-				     EXTENT_DELALLOC | EXTENT_DEFRAG,
-				     PAGE_UNLOCK | PAGE_CLEAR_DIRTY |
-				     PAGE_SET_WRITEBACK | PAGE_END_WRITEBACK);
+				     clear_bits | EXTENT_CLEAR_DATA_RESV,
+				     page_ops);
 	goto out;
 }
 
@@ -1164,7 +1178,6 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	unsigned long nr_pages;
 	u64 cur_end;
-	int limit = 10 * SZ_1M;
 
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, start, end, EXTENT_LOCKED,
 			 1, 0, NULL, GFP_NOFS);
@@ -1196,12 +1209,6 @@ static int cow_file_range_async(struct inode *inode, struct page *locked_page,
 
 		btrfs_queue_work(fs_info->delalloc_workers, &async_cow->work);
 
-		if (atomic_read(&fs_info->async_delalloc_pages) > limit) {
-			wait_event(fs_info->async_submit_wait,
-				   (atomic_read(&fs_info->async_delalloc_pages) <
-				    limit));
-		}
-
 		while (atomic_read(&fs_info->async_submit_draining) &&
 		       atomic_read(&fs_info->async_delalloc_pages)) {
 			wait_event(fs_info->async_submit_wait,
@@ -1250,11 +1257,11 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct btrfs_trans_handle *trans;
 	struct extent_buffer *leaf;
 	struct btrfs_path *path;
 	struct btrfs_file_extent_item *fi;
 	struct btrfs_key found_key;
+	struct extent_map *em;
 	u64 cow_start;
 	u64 cur_offset;
 	u64 extent_end;
@@ -1269,7 +1276,7 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 	int nocow;
 	int check_prev = 1;
 	bool nolock;
-	u64 ino = btrfs_ino(inode);
+	u64 ino = btrfs_ino(BTRFS_I(inode));
 
 	path = btrfs_alloc_path();
 	if (!path) {
@@ -1284,32 +1291,12 @@ static noinline int run_delalloc_nocow(struct inode *inode,
 		return -ENOMEM;
 	}
 
-	nolock = btrfs_is_free_space_inode(inode);
-
-	if (nolock)
-		trans = btrfs_join_transaction_nolock(root);
-	else
-		trans = btrfs_join_transaction(root);
-
-	if (IS_ERR(trans)) {
-		extent_clear_unlock_delalloc(inode, start, end, end,
-					     locked_page,
-					     EXTENT_LOCKED | EXTENT_DELALLOC |
-					     EXTENT_DO_ACCOUNTING |
-					     EXTENT_DEFRAG, PAGE_UNLOCK |
-					     PAGE_CLEAR_DIRTY |
-					     PAGE_SET_WRITEBACK |
-					     PAGE_END_WRITEBACK);
-		btrfs_free_path(path);
-		return PTR_ERR(trans);
-	}
-
-	trans->block_rsv = &fs_info->delalloc_block_rsv;
+	nolock = btrfs_is_free_space_inode(BTRFS_I(inode));
 
 	cow_start = (u64)-1;
 	cur_offset = start;
 	while (1) {
-		ret = btrfs_lookup_file_extent(trans, root, path, ino,
+		ret = btrfs_lookup_file_extent(NULL, root, path, ino,
 					       cur_offset, 0);
 		if (ret < 0)
 			goto error;
@@ -1382,7 +1369,7 @@ next_slot:
 				goto out_check;
 			if (btrfs_extent_readonly(fs_info, disk_bytenr))
 				goto out_check;
-			if (btrfs_cross_ref_exist(trans, root, ino,
+			if (btrfs_cross_ref_exist(root, ino,
 						  found_key.offset -
 						  extent_offset, disk_bytenr))
 				goto out_check;
@@ -1404,10 +1391,16 @@ next_slot:
 			 * either valid or do not exist.
 			 */
 			if (csum_exist_in_range(fs_info, disk_bytenr,
-						num_bytes))
+						num_bytes)) {
+				if (!nolock)
+					btrfs_end_write_no_snapshoting(root);
 				goto out_check;
-			if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr))
+			}
+			if (!btrfs_inc_nocow_writers(fs_info, disk_bytenr)) {
+				if (!nolock)
+					btrfs_end_write_no_snapshoting(root);
 				goto out_check;
+			}
 			nocow = 1;
 		} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 			extent_end = found_key.offset +
@@ -1455,35 +1448,28 @@ out_check:
 		}
 
 		if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
-			struct extent_map *em;
-			struct extent_map_tree *em_tree;
-			em_tree = &BTRFS_I(inode)->extent_tree;
-			em = alloc_extent_map();
-			BUG_ON(!em); /* -ENOMEM */
-			em->start = cur_offset;
-			em->orig_start = found_key.offset - extent_offset;
-			em->len = num_bytes;
-			em->block_len = num_bytes;
-			em->block_start = disk_bytenr;
-			em->orig_block_len = disk_num_bytes;
-			em->ram_bytes = ram_bytes;
-			em->bdev = fs_info->fs_devices->latest_bdev;
-			em->mod_start = em->start;
-			em->mod_len = em->len;
-			set_bit(EXTENT_FLAG_PINNED, &em->flags);
-			set_bit(EXTENT_FLAG_FILLING, &em->flags);
-			em->generation = -1;
-			while (1) {
-				write_lock(&em_tree->lock);
-				ret = add_extent_mapping(em_tree, em, 1);
-				write_unlock(&em_tree->lock);
-				if (ret != -EEXIST) {
-					free_extent_map(em);
-					break;
-				}
-				btrfs_drop_extent_cache(inode, em->start,
-						em->start + em->len - 1, 0);
+			u64 orig_start = found_key.offset - extent_offset;
+
+			em = create_io_em(inode, cur_offset, num_bytes,
+					  orig_start,
+					  disk_bytenr, /* block_start */
+					  num_bytes, /* block_len */
+					  disk_num_bytes, /* orig_block_len */
+					  ram_bytes, BTRFS_COMPRESS_NONE,
+					  BTRFS_ORDERED_PREALLOC);
+			if (IS_ERR(em)) {
+				if (!nolock && nocow)
+					btrfs_end_write_no_snapshoting(root);
+				if (nocow)
+					btrfs_dec_nocow_writers(fs_info,
+								disk_bytenr);
+				ret = PTR_ERR(em);
+				goto error;
 			}
+			free_extent_map(em);
+		}
+
+		if (extent_type == BTRFS_FILE_EXTENT_PREALLOC) {
 			type = BTRFS_ORDERED_PREALLOC;
 		} else {
 			type = BTRFS_ORDERED_NOCOW;
@@ -1496,15 +1482,14 @@ out_check:
 		BUG_ON(ret); /* -ENOMEM */
 
 		if (root->root_key.objectid ==
-		    BTRFS_DATA_RELOC_TREE_OBJECTID) {
+		    BTRFS_DATA_RELOC_TREE_OBJECTID)
+			/*
+			 * Error handled later, as we must prevent
+			 * extent_clear_unlock_delalloc() in error handler
+			 * from freeing metadata of created ordered extent.
+			 */
 			ret = btrfs_reloc_clone_csums(inode, cur_offset,
 						      num_bytes);
-			if (ret) {
-				if (!nolock && nocow)
-					btrfs_end_write_no_snapshoting(root);
-				goto error;
-			}
-		}
 
 		extent_clear_unlock_delalloc(inode, cur_offset,
 					     cur_offset + num_bytes - 1, end,
@@ -1516,6 +1501,14 @@ out_check:
 		if (!nolock && nocow)
 			btrfs_end_write_no_snapshoting(root);
 		cur_offset = extent_end;
+
+		/*
+		 * btrfs_reloc_clone_csums() error, now we're OK to call error
+		 * handler, as metadata for created ordered extent will only
+		 * be freed by btrfs_finish_ordered_io().
+		 */
+		if (ret)
+			goto error;
 		if (cur_offset > end)
 			break;
 	}
@@ -1534,10 +1527,6 @@ out_check:
 	}
 
 error:
-	err = btrfs_end_transaction(trans);
-	if (!ret)
-		ret = err;
-
 	if (ret && cur_offset < end)
 		extent_clear_unlock_delalloc(inode, cur_offset, end, end,
 					     locked_page, EXTENT_LOCKED |
@@ -1573,10 +1562,11 @@ static inline int need_force_cow(struct inode *inode, u64 start, u64 end)
 /*
  * extent_io.c call back to do delayed allocation processing
  */
-static int run_delalloc_range(struct inode *inode, struct page *locked_page,
+static int run_delalloc_range(void *private_data, struct page *locked_page,
 			      u64 start, u64 end, int *page_started,
 			      unsigned long *nr_written)
 {
+	struct inode *inode = private_data;
 	int ret;
 	int force_cow = need_force_cow(inode, start, end);
 
@@ -1595,12 +1585,15 @@ static int run_delalloc_range(struct inode *inode, struct page *locked_page,
 		ret = cow_file_range_async(inode, locked_page, start, end,
 					   page_started, nr_written);
 	}
+	if (ret)
+		btrfs_cleanup_ordered_extents(inode, start, end - start + 1);
 	return ret;
 }
 
-static void btrfs_split_extent_hook(struct inode *inode,
+static void btrfs_split_extent_hook(void *private_data,
 				    struct extent_state *orig, u64 split)
 {
+	struct inode *inode = private_data;
 	u64 size;
 
 	/* not delalloc, ignore it */
@@ -1609,7 +1602,7 @@ static void btrfs_split_extent_hook(struct inode *inode,
 
 	size = orig->end - orig->start + 1;
 	if (size > BTRFS_MAX_EXTENT_SIZE) {
-		u64 num_extents;
+		u32 num_extents;
 		u64 new_size;
 
 		/*
@@ -1617,13 +1610,10 @@ static void btrfs_split_extent_hook(struct inode *inode,
 		 * applies here, just in reverse.
 		 */
 		new_size = orig->end - split + 1;
-		num_extents = div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
-					BTRFS_MAX_EXTENT_SIZE);
+		num_extents = count_max_extents(new_size);
 		new_size = split - orig->start;
-		num_extents += div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
-					BTRFS_MAX_EXTENT_SIZE);
-		if (div64_u64(size + BTRFS_MAX_EXTENT_SIZE - 1,
-			      BTRFS_MAX_EXTENT_SIZE) >= num_extents)
+		num_extents += count_max_extents(new_size);
+		if (count_max_extents(size) >= num_extents)
 			return;
 	}
 
@@ -1638,12 +1628,13 @@ static void btrfs_split_extent_hook(struct inode *inode,
  * extents, such as when we are doing sequential writes, so we can properly
  * account for the metadata space we'll need.
  */
-static void btrfs_merge_extent_hook(struct inode *inode,
+static void btrfs_merge_extent_hook(void *private_data,
 				    struct extent_state *new,
 				    struct extent_state *other)
 {
+	struct inode *inode = private_data;
 	u64 new_size, old_size;
-	u64 num_extents;
+	u32 num_extents;
 
 	/* not delalloc, ignore it */
 	if (!(other->state & EXTENT_DELALLOC))
@@ -1681,14 +1672,10 @@ static void btrfs_merge_extent_hook(struct inode *inode,
 	 * this case.
 	 */
 	old_size = other->end - other->start + 1;
-	num_extents = div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
-				BTRFS_MAX_EXTENT_SIZE);
+	num_extents = count_max_extents(old_size);
 	old_size = new->end - new->start + 1;
-	num_extents += div64_u64(old_size + BTRFS_MAX_EXTENT_SIZE - 1,
-				 BTRFS_MAX_EXTENT_SIZE);
-
-	if (div64_u64(new_size + BTRFS_MAX_EXTENT_SIZE - 1,
-		      BTRFS_MAX_EXTENT_SIZE) >= num_extents)
+	num_extents += count_max_extents(old_size);
+	if (count_max_extents(new_size) >= num_extents)
 		return;
 
 	spin_lock(&BTRFS_I(inode)->lock);
@@ -1720,15 +1707,15 @@ static void btrfs_add_delalloc_inodes(struct btrfs_root *root,
 }
 
 static void btrfs_del_delalloc_inode(struct btrfs_root *root,
-				     struct inode *inode)
+				     struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 
 	spin_lock(&root->delalloc_lock);
-	if (!list_empty(&BTRFS_I(inode)->delalloc_inodes)) {
-		list_del_init(&BTRFS_I(inode)->delalloc_inodes);
+	if (!list_empty(&inode->delalloc_inodes)) {
+		list_del_init(&inode->delalloc_inodes);
 		clear_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-			  &BTRFS_I(inode)->runtime_flags);
+			  &inode->runtime_flags);
 		root->nr_delalloc_inodes--;
 		if (!root->nr_delalloc_inodes) {
 			spin_lock(&fs_info->delalloc_root_lock);
@@ -1745,9 +1732,10 @@ static void btrfs_del_delalloc_inode(struct btrfs_root *root,
  * bytes in this file, and to maintain the list of inodes that
  * have pending delalloc work to be done.
  */
-static void btrfs_set_bit_hook(struct inode *inode,
+static void btrfs_set_bit_hook(void *private_data,
 			       struct extent_state *state, unsigned *bits)
 {
+	struct inode *inode = private_data;
 
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 
@@ -1761,7 +1749,7 @@ static void btrfs_set_bit_hook(struct inode *inode,
 	if (!(state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
 		struct btrfs_root *root = BTRFS_I(inode)->root;
 		u64 len = state->end + 1 - state->start;
-		bool do_list = !btrfs_is_free_space_inode(inode);
+		bool do_list = !btrfs_is_free_space_inode(BTRFS_I(inode));
 
 		if (*bits & EXTENT_FIRST_DELALLOC) {
 			*bits &= ~EXTENT_FIRST_DELALLOC;
@@ -1775,8 +1763,8 @@ static void btrfs_set_bit_hook(struct inode *inode,
 		if (btrfs_is_testing(fs_info))
 			return;
 
-		__percpu_counter_add(&fs_info->delalloc_bytes, len,
-				     fs_info->delalloc_batch);
+		percpu_counter_add_batch(&fs_info->delalloc_bytes, len,
+					 fs_info->delalloc_batch);
 		spin_lock(&BTRFS_I(inode)->lock);
 		BTRFS_I(inode)->delalloc_bytes += len;
 		if (*bits & EXTENT_DEFRAG)
@@ -1786,24 +1774,32 @@ static void btrfs_set_bit_hook(struct inode *inode,
 			btrfs_add_delalloc_inodes(root, inode);
 		spin_unlock(&BTRFS_I(inode)->lock);
 	}
+
+	if (!(state->state & EXTENT_DELALLOC_NEW) &&
+	    (*bits & EXTENT_DELALLOC_NEW)) {
+		spin_lock(&BTRFS_I(inode)->lock);
+		BTRFS_I(inode)->new_delalloc_bytes += state->end + 1 -
+			state->start;
+		spin_unlock(&BTRFS_I(inode)->lock);
+	}
 }
 
 /*
  * extent_io.c clear_bit_hook, see set_bit_hook for why
  */
-static void btrfs_clear_bit_hook(struct inode *inode,
+static void btrfs_clear_bit_hook(void *private_data,
 				 struct extent_state *state,
 				 unsigned *bits)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_inode *inode = BTRFS_I((struct inode *)private_data);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	u64 len = state->end + 1 - state->start;
-	u64 num_extents = div64_u64(len + BTRFS_MAX_EXTENT_SIZE -1,
-				    BTRFS_MAX_EXTENT_SIZE);
+	u32 num_extents = count_max_extents(len);
 
-	spin_lock(&BTRFS_I(inode)->lock);
+	spin_lock(&inode->lock);
 	if ((state->state & EXTENT_DEFRAG) && (*bits & EXTENT_DEFRAG))
-		BTRFS_I(inode)->defrag_bytes -= len;
-	spin_unlock(&BTRFS_I(inode)->lock);
+		inode->defrag_bytes -= len;
+	spin_unlock(&inode->lock);
 
 	/*
 	 * set_bit and clear bit hooks normally require _irqsave/restore
@@ -1811,15 +1807,15 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 	 * bit, which is only set or cleared with irqs on
 	 */
 	if ((state->state & EXTENT_DELALLOC) && (*bits & EXTENT_DELALLOC)) {
-		struct btrfs_root *root = BTRFS_I(inode)->root;
+		struct btrfs_root *root = inode->root;
 		bool do_list = !btrfs_is_free_space_inode(inode);
 
 		if (*bits & EXTENT_FIRST_DELALLOC) {
 			*bits &= ~EXTENT_FIRST_DELALLOC;
-		} else if (!(*bits & EXTENT_DO_ACCOUNTING)) {
-			spin_lock(&BTRFS_I(inode)->lock);
-			BTRFS_I(inode)->outstanding_extents -= num_extents;
-			spin_unlock(&BTRFS_I(inode)->lock);
+		} else if (!(*bits & EXTENT_CLEAR_META_RESV)) {
+			spin_lock(&inode->lock);
+			inode->outstanding_extents -= num_extents;
+			spin_unlock(&inode->lock);
 		}
 
 		/*
@@ -1827,7 +1823,7 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 		 * don't need to call dellalloc_release_metadata if there is an
 		 * error.
 		 */
-		if (*bits & EXTENT_DO_ACCOUNTING &&
+		if (*bits & EXTENT_CLEAR_META_RESV &&
 		    root != fs_info->tree_root)
 			btrfs_delalloc_release_metadata(inode, len);
 
@@ -1835,22 +1831,30 @@ static void btrfs_clear_bit_hook(struct inode *inode,
 		if (btrfs_is_testing(fs_info))
 			return;
 
-		if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
-		    && do_list && !(state->state & EXTENT_NORESERVE)
-		    && (*bits & (EXTENT_DO_ACCOUNTING |
-		    EXTENT_CLEAR_DATA_RESV)))
-			btrfs_free_reserved_data_space_noquota(inode,
+		if (root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID &&
+		    do_list && !(state->state & EXTENT_NORESERVE) &&
+		    (*bits & EXTENT_CLEAR_DATA_RESV))
+			btrfs_free_reserved_data_space_noquota(
+					&inode->vfs_inode,
 					state->start, len);
 
-		__percpu_counter_add(&fs_info->delalloc_bytes, -len,
-				     fs_info->delalloc_batch);
-		spin_lock(&BTRFS_I(inode)->lock);
-		BTRFS_I(inode)->delalloc_bytes -= len;
-		if (do_list && BTRFS_I(inode)->delalloc_bytes == 0 &&
+		percpu_counter_add_batch(&fs_info->delalloc_bytes, -len,
+					 fs_info->delalloc_batch);
+		spin_lock(&inode->lock);
+		inode->delalloc_bytes -= len;
+		if (do_list && inode->delalloc_bytes == 0 &&
 		    test_bit(BTRFS_INODE_IN_DELALLOC_LIST,
-			     &BTRFS_I(inode)->runtime_flags))
+					&inode->runtime_flags))
 			btrfs_del_delalloc_inode(root, inode);
-		spin_unlock(&BTRFS_I(inode)->lock);
+		spin_unlock(&inode->lock);
+	}
+
+	if ((state->state & EXTENT_DELALLOC_NEW) &&
+	    (*bits & EXTENT_DELALLOC_NEW)) {
+		spin_lock(&inode->lock);
+		ASSERT(inode->new_delalloc_bytes >= len);
+		inode->new_delalloc_bytes -= len;
+		spin_unlock(&inode->lock);
 	}
 }
 
@@ -1895,11 +1899,12 @@ int btrfs_merge_bio_hook(struct page *page, unsigned long offset,
  * At IO completion time the cums attached on the ordered extent record
  * are inserted into the btree
  */
-static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio,
+static blk_status_t __btrfs_submit_bio_start(void *private_data, struct bio *bio,
 				    int mirror_num, unsigned long bio_flags,
 				    u64 bio_offset)
 {
-	int ret = 0;
+	struct inode *inode = private_data;
+	blk_status_t ret = 0;
 
 	ret = btrfs_csum_one_bio(inode, bio, 0, 0);
 	BUG_ON(ret); /* -ENOMEM */
@@ -1914,16 +1919,17 @@ static int __btrfs_submit_bio_start(struct inode *inode, struct bio *bio,
  * At IO completion time the cums attached on the ordered extent record
  * are inserted into the btree
  */
-static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio,
+static blk_status_t __btrfs_submit_bio_done(void *private_data, struct bio *bio,
 			  int mirror_num, unsigned long bio_flags,
 			  u64 bio_offset)
 {
+	struct inode *inode = private_data;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	int ret;
+	blk_status_t ret;
 
 	ret = btrfs_map_bio(fs_info, bio, mirror_num, 1);
 	if (ret) {
-		bio->bi_error = ret;
+		bio->bi_status = ret;
 		bio_endio(bio);
 	}
 	return ret;
@@ -1933,20 +1939,21 @@ static int __btrfs_submit_bio_done(struct inode *inode, struct bio *bio,
  * extent_io.c submission hook. This does the right thing for csum calculation
  * on write, or reading the csums from the tree before a read
  */
-static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
-			  int mirror_num, unsigned long bio_flags,
-			  u64 bio_offset)
+static blk_status_t btrfs_submit_bio_hook(void *private_data, struct bio *bio,
+				 int mirror_num, unsigned long bio_flags,
+				 u64 bio_offset)
 {
+	struct inode *inode = private_data;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	enum btrfs_wq_endio_type metadata = BTRFS_WQ_ENDIO_DATA;
-	int ret = 0;
+	blk_status_t ret = 0;
 	int skip_sum;
 	int async = !atomic_read(&BTRFS_I(inode)->sync_writers);
 
 	skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
-	if (btrfs_is_free_space_inode(inode))
+	if (btrfs_is_free_space_inode(BTRFS_I(inode)))
 		metadata = BTRFS_WQ_ENDIO_FREE_SPACE;
 
 	if (bio_op(bio) != REQ_OP_WRITE) {
@@ -1970,8 +1977,8 @@ static int btrfs_submit_bio_hook(struct inode *inode, struct bio *bio,
 		if (root->root_key.objectid == BTRFS_DATA_RELOC_TREE_OBJECTID)
 			goto mapit;
 		/* we're doing a write, do the async checksumming */
-		ret = btrfs_wq_submit_bio(fs_info, inode, bio, mirror_num,
-					  bio_flags, bio_offset,
+		ret = btrfs_wq_submit_bio(fs_info, bio, mirror_num, bio_flags,
+					  bio_offset, inode,
 					  __btrfs_submit_bio_start,
 					  __btrfs_submit_bio_done);
 		goto out;
@@ -1985,8 +1992,8 @@ mapit:
 	ret = btrfs_map_bio(fs_info, bio, mirror_num, 0);
 
 out:
-	if (ret < 0) {
-		bio->bi_error = ret;
+	if (ret) {
+		bio->bi_status = ret;
 		bio_endio(bio);
 	}
 	return ret;
@@ -1997,8 +2004,7 @@ out:
  * at IO completion time based on sums calculated at bio submission time.
  */
 static noinline int add_pending_csums(struct btrfs_trans_handle *trans,
-			     struct inode *inode, u64 file_offset,
-			     struct list_head *list)
+			     struct inode *inode, struct list_head *list)
 {
 	struct btrfs_ordered_sum *sum;
 
@@ -2030,6 +2036,7 @@ static void btrfs_writepage_fixup_worker(struct btrfs_work *work)
 	struct btrfs_writepage_fixup *fixup;
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	struct page *page;
 	struct inode *inode;
 	u64 page_start;
@@ -2056,7 +2063,7 @@ again:
 	if (PagePrivate2(page))
 		goto out;
 
-	ordered = btrfs_lookup_ordered_range(inode, page_start,
+	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start,
 					PAGE_SIZE);
 	if (ordered) {
 		unlock_extent_cached(&BTRFS_I(inode)->io_tree, page_start,
@@ -2067,7 +2074,7 @@ again:
 		goto again;
 	}
 
-	ret = btrfs_delalloc_reserve_space(inode, page_start,
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
 					   PAGE_SIZE);
 	if (ret) {
 		mapping_set_error(page->mapping, ret);
@@ -2087,6 +2094,7 @@ out_page:
 	unlock_page(page);
 	put_page(page);
 	kfree(fixup);
+	extent_changeset_free(data_reserved);
 }
 
 /*
@@ -2138,6 +2146,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
 	struct btrfs_key ins;
+	u64 qg_released;
 	int extent_inserted = 0;
 	int ret;
 
@@ -2161,7 +2170,7 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
 		goto out;
 
 	if (!extent_inserted) {
-		ins.objectid = btrfs_ino(inode);
+		ins.objectid = btrfs_ino(BTRFS_I(inode));
 		ins.offset = file_pos;
 		ins.type = BTRFS_EXTENT_DATA_KEY;
 
@@ -2193,14 +2202,17 @@ static int insert_reserved_file_extent(struct btrfs_trans_handle *trans,
 	ins.objectid = disk_bytenr;
 	ins.offset = disk_num_bytes;
 	ins.type = BTRFS_EXTENT_ITEM_KEY;
-	ret = btrfs_alloc_reserved_file_extent(trans, root->root_key.objectid,
-					       btrfs_ino(inode), file_pos,
-					       ram_bytes, &ins);
+
 	/*
 	 * Release the reserved range from inode dirty range map, as it is
 	 * already moved into delayed_ref_head
 	 */
-	btrfs_qgroup_release_data(inode, file_pos, ram_bytes);
+	ret = btrfs_qgroup_release_data(inode, file_pos, ram_bytes);
+	if (ret < 0)
+		goto out;
+	qg_released = ret;
+	ret = btrfs_alloc_reserved_file_extent(trans, root->root_key.objectid,
+			btrfs_ino(BTRFS_I(inode)), file_pos, qg_released, &ins);
 out:
 	btrfs_free_path(path);
 
@@ -2320,7 +2332,7 @@ static noinline int record_one_backref(u64 inum, u64 offset, u64 root_id,
 	u64 num_bytes;
 
 	if (BTRFS_I(inode)->root->root_key.objectid == root_id &&
-	    inum == btrfs_ino(inode))
+	    inum == btrfs_ino(BTRFS_I(inode)))
 		return 0;
 
 	key.objectid = root_id;
@@ -2589,7 +2601,7 @@ static noinline int relink_extent_backref(struct btrfs_path *path,
 	if (ret)
 		goto out_free_path;
 again:
-	key.objectid = btrfs_ino(inode);
+	key.objectid = btrfs_ino(BTRFS_I(inode));
 	key.type = BTRFS_EXTENT_DATA_KEY;
 	key.offset = start;
 
@@ -2768,7 +2780,7 @@ record_old_file_extents(struct inode *inode,
 	if (!path)
 		goto out_kfree;
 
-	key.objectid = btrfs_ino(inode);
+	key.objectid = btrfs_ino(BTRFS_I(inode));
 	key.type = BTRFS_EXTENT_DATA_KEY;
 	key.offset = new->file_pos;
 
@@ -2803,7 +2815,7 @@ record_old_file_extents(struct inode *inode,
 
 		btrfs_item_key_to_cpu(l, &key, slot);
 
-		if (key.objectid != btrfs_ino(inode))
+		if (key.objectid != btrfs_ino(BTRFS_I(inode)))
 			break;
 		if (key.type != BTRFS_EXTENT_DATA_KEY)
 			break;
@@ -2886,17 +2898,25 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 	u64 logical_len = ordered_extent->len;
 	bool nolock;
 	bool truncated = false;
+	bool range_locked = false;
+	bool clear_new_delalloc_bytes = false;
+
+	if (!test_bit(BTRFS_ORDERED_NOCOW, &ordered_extent->flags) &&
+	    !test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags) &&
+	    !test_bit(BTRFS_ORDERED_DIRECT, &ordered_extent->flags))
+		clear_new_delalloc_bytes = true;
 
-	nolock = btrfs_is_free_space_inode(inode);
+	nolock = btrfs_is_free_space_inode(BTRFS_I(inode));
 
 	if (test_bit(BTRFS_ORDERED_IOERR, &ordered_extent->flags)) {
 		ret = -EIO;
 		goto out;
 	}
 
-	btrfs_free_io_failure_record(inode, ordered_extent->file_offset,
-				     ordered_extent->file_offset +
-				     ordered_extent->len - 1);
+	btrfs_free_io_failure_record(BTRFS_I(inode),
+			ordered_extent->file_offset,
+			ordered_extent->file_offset +
+			ordered_extent->len - 1);
 
 	if (test_bit(BTRFS_ORDERED_TRUNCATED, &ordered_extent->flags)) {
 		truncated = true;
@@ -2914,7 +2934,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		 * space for NOCOW range.
 		 * As NOCOW won't cause a new delayed ref, just free the space
 		 */
-		btrfs_qgroup_free_data(inode, ordered_extent->file_offset,
+		btrfs_qgroup_free_data(inode, NULL, ordered_extent->file_offset,
 				       ordered_extent->len);
 		btrfs_ordered_update_i_size(inode, 0, ordered_extent);
 		if (nolock)
@@ -2933,13 +2953,14 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		goto out;
 	}
 
+	range_locked = true;
 	lock_extent_bits(io_tree, ordered_extent->file_offset,
 			 ordered_extent->file_offset + ordered_extent->len - 1,
 			 &cached_state);
 
 	ret = test_range_bit(io_tree, ordered_extent->file_offset,
 			ordered_extent->file_offset + ordered_extent->len - 1,
-			EXTENT_DEFRAG, 1, cached_state);
+			EXTENT_DEFRAG, 0, cached_state);
 	if (ret) {
 		u64 last_snapshot = btrfs_root_last_snapshot(&root->root_item);
 		if (0 && last_snapshot >= BTRFS_I(inode)->generation)
@@ -2958,7 +2979,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
 		trans = NULL;
-		goto out_unlock;
+		goto out;
 	}
 
 	trans->block_rsv = &fs_info->delalloc_block_rsv;
@@ -2967,7 +2988,7 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 		compress_type = ordered_extent->compress_type;
 	if (test_bit(BTRFS_ORDERED_PREALLOC, &ordered_extent->flags)) {
 		BUG_ON(compress_type);
-		ret = btrfs_mark_extent_written(trans, inode,
+		ret = btrfs_mark_extent_written(trans, BTRFS_I(inode),
 						ordered_extent->file_offset,
 						ordered_extent->file_offset +
 						logical_len);
@@ -2990,26 +3011,38 @@ static int btrfs_finish_ordered_io(struct btrfs_ordered_extent *ordered_extent)
 			   trans->transid);
 	if (ret < 0) {
 		btrfs_abort_transaction(trans, ret);
-		goto out_unlock;
+		goto out;
 	}
 
-	add_pending_csums(trans, inode, ordered_extent->file_offset,
-			  &ordered_extent->list);
+	add_pending_csums(trans, inode, &ordered_extent->list);
 
 	btrfs_ordered_update_i_size(inode, 0, ordered_extent);
 	ret = btrfs_update_inode_fallback(trans, root, inode);
 	if (ret) { /* -ENOMEM or corruption */
 		btrfs_abort_transaction(trans, ret);
-		goto out_unlock;
+		goto out;
 	}
 	ret = 0;
-out_unlock:
-	unlock_extent_cached(io_tree, ordered_extent->file_offset,
-			     ordered_extent->file_offset +
-			     ordered_extent->len - 1, &cached_state, GFP_NOFS);
 out:
+	if (range_locked || clear_new_delalloc_bytes) {
+		unsigned int clear_bits = 0;
+
+		if (range_locked)
+			clear_bits |= EXTENT_LOCKED;
+		if (clear_new_delalloc_bytes)
+			clear_bits |= EXTENT_DELALLOC_NEW;
+		clear_extent_bit(&BTRFS_I(inode)->io_tree,
+				 ordered_extent->file_offset,
+				 ordered_extent->file_offset +
+				 ordered_extent->len - 1,
+				 clear_bits,
+				 (clear_bits & EXTENT_LOCKED) ? 1 : 0,
+				 0, &cached_state, GFP_NOFS);
+	}
+
 	if (root != fs_info->tree_root)
-		btrfs_delalloc_release_metadata(inode, ordered_extent->len);
+		btrfs_delalloc_release_metadata(BTRFS_I(inode),
+				ordered_extent->len);
 	if (trans)
 		btrfs_end_transaction(trans);
 
@@ -3024,7 +3057,7 @@ out:
 		clear_extent_uptodate(io_tree, start, end, NULL, GFP_NOFS);
 
 		/* Drop the cache for the part of the extent we didn't write. */
-		btrfs_drop_extent_cache(inode, start, end, 0);
+		btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 0);
 
 		/*
 		 * If the ordered extent had an IOERR or something else went
@@ -3072,7 +3105,7 @@ static void finish_ordered_fn(struct btrfs_work *work)
 	btrfs_finish_ordered_io(ordered_extent);
 }
 
-static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
+static void btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 				struct extent_state *state, int uptodate)
 {
 	struct inode *inode = page->mapping->host;
@@ -3086,9 +3119,9 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 	ClearPagePrivate2(page);
 	if (!btrfs_dec_test_ordered_pending(inode, &ordered_extent, start,
 					    end - start + 1, uptodate))
-		return 0;
+		return;
 
-	if (btrfs_is_free_space_inode(inode)) {
+	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
 		wq = fs_info->endio_freespace_worker;
 		func = btrfs_freespace_write_helper;
 	} else {
@@ -3099,8 +3132,6 @@ static int btrfs_writepage_end_io_hook(struct page *page, u64 start, u64 end,
 	btrfs_init_work(&ordered_extent->work, func, finish_ordered_fn, NULL,
 			NULL);
 	btrfs_queue_work(wq, &ordered_extent->work);
-
-	return 0;
 }
 
 static int __readpage_endio_check(struct inode *inode,
@@ -3123,9 +3154,8 @@ static int __readpage_endio_check(struct inode *inode,
 	kunmap_atomic(kaddr);
 	return 0;
 zeroit:
-	btrfs_warn_rl(BTRFS_I(inode)->root->fs_info,
-		"csum failed ino %llu off %llu csum %u expected csum %u",
-			   btrfs_ino(inode), start, csum, csum_expected);
+	btrfs_print_data_csum_error(BTRFS_I(inode), start, csum, csum_expected,
+				    io_bio->mirror_num);
 	memset(kaddr + pgoff, 1, len);
 	flush_dcache_page(page);
 	kunmap_atomic(kaddr);
@@ -3263,10 +3293,11 @@ void btrfs_orphan_commit_root(struct btrfs_trans_handle *trans,
  * NOTE: caller of this function should reserve 5 units of metadata for
  *	 this function.
  */
-int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
+int btrfs_orphan_add(struct btrfs_trans_handle *trans,
+		struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 	struct btrfs_block_rsv *block_rsv = NULL;
 	int reserve = 0;
 	int insert = 0;
@@ -3288,7 +3319,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 	}
 
 	if (!test_and_set_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-			      &BTRFS_I(inode)->runtime_flags)) {
+			      &inode->runtime_flags)) {
 #if 0
 		/*
 		 * For proper ENOSPC handling, we should do orphan
@@ -3305,7 +3336,7 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 	}
 
 	if (!test_and_set_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
-			      &BTRFS_I(inode)->runtime_flags))
+			      &inode->runtime_flags))
 		reserve = 1;
 	spin_unlock(&root->orphan_lock);
 
@@ -3316,10 +3347,10 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 		if (ret) {
 			atomic_dec(&root->orphan_inodes);
 			clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
-				  &BTRFS_I(inode)->runtime_flags);
+				  &inode->runtime_flags);
 			if (insert)
 				clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-					  &BTRFS_I(inode)->runtime_flags);
+					  &inode->runtime_flags);
 			return ret;
 		}
 	}
@@ -3331,12 +3362,12 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
 			atomic_dec(&root->orphan_inodes);
 			if (reserve) {
 				clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
-					  &BTRFS_I(inode)->runtime_flags);
+					  &inode->runtime_flags);
 				btrfs_orphan_release_metadata(inode);
 			}
 			if (ret != -EEXIST) {
 				clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-					  &BTRFS_I(inode)->runtime_flags);
+					  &inode->runtime_flags);
 				btrfs_abort_transaction(trans, ret);
 				return ret;
 			}
@@ -3361,20 +3392,20 @@ int btrfs_orphan_add(struct btrfs_trans_handle *trans, struct inode *inode)
  * item for this particular inode.
  */
 static int btrfs_orphan_del(struct btrfs_trans_handle *trans,
-			    struct inode *inode)
+			    struct btrfs_inode *inode)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 	int delete_item = 0;
 	int release_rsv = 0;
 	int ret = 0;
 
 	spin_lock(&root->orphan_lock);
 	if (test_and_clear_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
-			       &BTRFS_I(inode)->runtime_flags))
+			       &inode->runtime_flags))
 		delete_item = 1;
 
 	if (test_and_clear_bit(BTRFS_INODE_ORPHAN_META_RESERVED,
-			       &BTRFS_I(inode)->runtime_flags))
+			       &inode->runtime_flags))
 		release_rsv = 1;
 	spin_unlock(&root->orphan_lock);
 
@@ -3548,7 +3579,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 				ret = PTR_ERR(trans);
 				goto out;
 			}
-			ret = btrfs_orphan_add(trans, inode);
+			ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 			btrfs_end_transaction(trans);
 			if (ret) {
 				iput(inode);
@@ -3557,7 +3588,7 @@ int btrfs_orphan_cleanup(struct btrfs_root *root)
 
 			ret = btrfs_truncate(inode);
 			if (ret)
-				btrfs_orphan_del(NULL, inode);
+				btrfs_orphan_del(NULL, BTRFS_I(inode));
 		} else {
 			nr_unlink++;
 		}
@@ -3712,7 +3743,7 @@ static int btrfs_read_locked_inode(struct inode *inode)
 	set_nlink(inode, btrfs_inode_nlink(leaf, inode_item));
 	i_uid_write(inode, btrfs_inode_uid(leaf, inode_item));
 	i_gid_write(inode, btrfs_inode_gid(leaf, inode_item));
-	btrfs_i_size_write(inode, btrfs_inode_size(leaf, inode_item));
+	btrfs_i_size_write(BTRFS_I(inode), btrfs_inode_size(leaf, inode_item));
 
 	inode->i_atime.tv_sec = btrfs_timespec_sec(leaf, &inode_item->atime);
 	inode->i_atime.tv_nsec = btrfs_timespec_nsec(leaf, &inode_item->atime);
@@ -3789,7 +3820,7 @@ cache_index:
 		goto cache_acl;
 
 	btrfs_item_key_to_cpu(leaf, &location, path->slots[0]);
-	if (location.objectid != btrfs_ino(inode))
+	if (location.objectid != btrfs_ino(BTRFS_I(inode)))
 		goto cache_acl;
 
 	ptr = btrfs_item_ptr_offset(leaf, path->slots[0]);
@@ -3811,14 +3842,14 @@ cache_acl:
 	 * any xattrs or acls
 	 */
 	maybe_acls = acls_after_inode_item(leaf, path->slots[0],
-					   btrfs_ino(inode), &first_xattr_slot);
+			btrfs_ino(BTRFS_I(inode)), &first_xattr_slot);
 	if (first_xattr_slot != -1) {
 		path->slots[0] = first_xattr_slot;
 		ret = btrfs_load_inode_props(inode, path);
 		if (ret)
 			btrfs_err(fs_info,
 				  "error loading props for ino %llu (root %llu): %d",
-				  btrfs_ino(inode),
+				  btrfs_ino(BTRFS_I(inode)),
 				  root->root_key.objectid, ret);
 	}
 	btrfs_free_path(path);
@@ -3960,7 +3991,7 @@ noinline int btrfs_update_inode(struct btrfs_trans_handle *trans,
 	 * The data relocation inode should also be directly updated
 	 * without delay
 	 */
-	if (!btrfs_is_free_space_inode(inode)
+	if (!btrfs_is_free_space_inode(BTRFS_I(inode))
 	    && root->root_key.objectid != BTRFS_DATA_RELOC_TREE_OBJECTID
 	    && !test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) {
 		btrfs_update_root_times(trans, root);
@@ -3993,7 +4024,8 @@ noinline int btrfs_update_inode_fallback(struct btrfs_trans_handle *trans,
  */
 static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
-				struct inode *dir, struct inode *inode,
+				struct btrfs_inode *dir,
+				struct btrfs_inode *inode,
 				const char *name, int name_len)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -4040,10 +4072,10 @@ static int __btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 	 * that we delay to delete it, and just do this deletion when
 	 * we update the inode item.
 	 */
-	if (BTRFS_I(inode)->dir_index) {
+	if (inode->dir_index) {
 		ret = btrfs_delayed_delete_inode_ref(inode);
 		if (!ret) {
-			index = BTRFS_I(inode)->dir_index;
+			index = inode->dir_index;
 			goto skip_backref;
 		}
 	}
@@ -4064,15 +4096,15 @@ skip_backref:
 		goto err;
 	}
 
-	ret = btrfs_del_inode_ref_in_log(trans, root, name, name_len,
-					 inode, dir_ino);
+	ret = btrfs_del_inode_ref_in_log(trans, root, name, name_len, inode,
+			dir_ino);
 	if (ret != 0 && ret != -ENOENT) {
 		btrfs_abort_transaction(trans, ret);
 		goto err;
 	}
 
-	ret = btrfs_del_dir_entries_in_log(trans, root, name, name_len,
-					   dir, index);
+	ret = btrfs_del_dir_entries_in_log(trans, root, name, name_len, dir,
+			index);
 	if (ret == -ENOENT)
 		ret = 0;
 	else if (ret)
@@ -4082,26 +4114,26 @@ err:
 	if (ret)
 		goto out;
 
-	btrfs_i_size_write(dir, dir->i_size - name_len * 2);
-	inode_inc_iversion(inode);
-	inode_inc_iversion(dir);
-	inode->i_ctime = dir->i_mtime =
-		dir->i_ctime = current_time(inode);
-	ret = btrfs_update_inode(trans, root, dir);
+	btrfs_i_size_write(dir, dir->vfs_inode.i_size - name_len * 2);
+	inode_inc_iversion(&inode->vfs_inode);
+	inode_inc_iversion(&dir->vfs_inode);
+	inode->vfs_inode.i_ctime = dir->vfs_inode.i_mtime =
+		dir->vfs_inode.i_ctime = current_time(&inode->vfs_inode);
+	ret = btrfs_update_inode(trans, root, &dir->vfs_inode);
 out:
 	return ret;
 }
 
 int btrfs_unlink_inode(struct btrfs_trans_handle *trans,
 		       struct btrfs_root *root,
-		       struct inode *dir, struct inode *inode,
+		       struct btrfs_inode *dir, struct btrfs_inode *inode,
 		       const char *name, int name_len)
 {
 	int ret;
 	ret = __btrfs_unlink_inode(trans, root, dir, inode, name, name_len);
 	if (!ret) {
-		drop_nlink(inode);
-		ret = btrfs_update_inode(trans, root, inode);
+		drop_nlink(&inode->vfs_inode);
+		ret = btrfs_update_inode(trans, root, &inode->vfs_inode);
 	}
 	return ret;
 }
@@ -4139,15 +4171,17 @@ static int btrfs_unlink(struct inode *dir, struct dentry *dentry)
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	btrfs_record_unlink_dir(trans, dir, d_inode(dentry), 0);
+	btrfs_record_unlink_dir(trans, BTRFS_I(dir), BTRFS_I(d_inode(dentry)),
+			0);
 
-	ret = btrfs_unlink_inode(trans, root, dir, d_inode(dentry),
-				 dentry->d_name.name, dentry->d_name.len);
+	ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
+			BTRFS_I(d_inode(dentry)), dentry->d_name.name,
+			dentry->d_name.len);
 	if (ret)
 		goto out;
 
 	if (inode->i_nlink == 0) {
-		ret = btrfs_orphan_add(trans, inode);
+		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 		if (ret)
 			goto out;
 	}
@@ -4170,7 +4204,7 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 	struct btrfs_key key;
 	u64 index;
 	int ret;
-	u64 dir_ino = btrfs_ino(dir);
+	u64 dir_ino = btrfs_ino(BTRFS_I(dir));
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -4222,13 +4256,13 @@ int btrfs_unlink_subvol(struct btrfs_trans_handle *trans,
 	}
 	btrfs_release_path(path);
 
-	ret = btrfs_delete_delayed_dir_index(trans, fs_info, dir, index);
+	ret = btrfs_delete_delayed_dir_index(trans, fs_info, BTRFS_I(dir), index);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto out;
 	}
 
-	btrfs_i_size_write(dir, dir->i_size - name_len * 2);
+	btrfs_i_size_write(BTRFS_I(dir), dir->i_size - name_len * 2);
 	inode_inc_iversion(dir);
 	dir->i_mtime = dir->i_ctime = current_time(dir);
 	ret = btrfs_update_inode_fallback(trans, root, dir);
@@ -4249,14 +4283,14 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 
 	if (inode->i_size > BTRFS_EMPTY_DIR_SIZE)
 		return -ENOTEMPTY;
-	if (btrfs_ino(inode) == BTRFS_FIRST_FREE_OBJECTID)
+	if (btrfs_ino(BTRFS_I(inode)) == BTRFS_FIRST_FREE_OBJECTID)
 		return -EPERM;
 
 	trans = __unlink_start_trans(dir);
 	if (IS_ERR(trans))
 		return PTR_ERR(trans);
 
-	if (unlikely(btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
+	if (unlikely(btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 		err = btrfs_unlink_subvol(trans, root, dir,
 					  BTRFS_I(inode)->location.objectid,
 					  dentry->d_name.name,
@@ -4264,17 +4298,18 @@ static int btrfs_rmdir(struct inode *dir, struct dentry *dentry)
 		goto out;
 	}
 
-	err = btrfs_orphan_add(trans, inode);
+	err = btrfs_orphan_add(trans, BTRFS_I(inode));
 	if (err)
 		goto out;
 
 	last_unlink_trans = BTRFS_I(inode)->last_unlink_trans;
 
 	/* now the directory is empty */
-	err = btrfs_unlink_inode(trans, root, dir, d_inode(dentry),
-				 dentry->d_name.name, dentry->d_name.len);
+	err = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
+			BTRFS_I(d_inode(dentry)), dentry->d_name.name,
+			dentry->d_name.len);
 	if (!err) {
-		btrfs_i_size_write(inode, 0);
+		btrfs_i_size_write(BTRFS_I(inode), 0);
 		/*
 		 * Propagate the last_unlink_trans value of the deleted dir to
 		 * its parent directory. This is to prevent an unrecoverable
@@ -4398,7 +4433,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	int extent_type = -1;
 	int ret;
 	int err = 0;
-	u64 ino = btrfs_ino(inode);
+	u64 ino = btrfs_ino(BTRFS_I(inode));
 	u64 bytes_deleted = 0;
 	bool be_nice = 0;
 	bool should_throttle = 0;
@@ -4410,7 +4445,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	 * for non-free space inodes and ref cows, we want to back off from
 	 * time to time
 	 */
-	if (!btrfs_is_free_space_inode(inode) &&
+	if (!btrfs_is_free_space_inode(BTRFS_I(inode)) &&
 	    test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 		be_nice = 1;
 
@@ -4426,7 +4461,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	 */
 	if (test_bit(BTRFS_ROOT_REF_COWS, &root->state) ||
 	    root == fs_info->tree_root)
-		btrfs_drop_extent_cache(inode, ALIGN(new_size,
+		btrfs_drop_extent_cache(BTRFS_I(inode), ALIGN(new_size,
 					fs_info->sectorsize),
 					(u64)-1, 0);
 
@@ -4437,7 +4472,7 @@ int btrfs_truncate_inode_items(struct btrfs_trans_handle *trans,
 	 * items.
 	 */
 	if (min_type == 0 && root == BTRFS_I(inode)->root)
-		btrfs_kill_delayed_inode_items(inode);
+		btrfs_kill_delayed_inode_items(BTRFS_I(inode));
 
 	key.objectid = ino;
 	key.offset = (u64)-1;
@@ -4493,28 +4528,25 @@ search_again:
 			if (extent_type != BTRFS_FILE_EXTENT_INLINE) {
 				item_end +=
 				    btrfs_file_extent_num_bytes(leaf, fi);
+
+				trace_btrfs_truncate_show_fi_regular(
+					BTRFS_I(inode), leaf, fi,
+					found_key.offset);
 			} else if (extent_type == BTRFS_FILE_EXTENT_INLINE) {
 				item_end += btrfs_file_extent_inline_len(leaf,
 							 path->slots[0], fi);
+
+				trace_btrfs_truncate_show_fi_inline(
+					BTRFS_I(inode), leaf, fi, path->slots[0],
+					found_key.offset);
 			}
 			item_end--;
 		}
 		if (found_type > min_type) {
 			del_item = 1;
 		} else {
-			if (item_end < new_size) {
-				/*
-				 * With NO_HOLES mode, for the following mapping
-				 *
-				 * [0-4k][hole][8k-12k]
-				 *
-				 * if truncating isize down to 6k, it ends up
-				 * isize being 8k.
-				 */
-				if (btrfs_fs_incompat(root->fs_info, NO_HOLES))
-					last_size = new_size;
+			if (item_end < new_size)
 				break;
-			}
 			if (found_key.offset >= new_size)
 				del_item = 1;
 			else
@@ -4697,8 +4729,12 @@ out:
 			btrfs_abort_transaction(trans, ret);
 	}
 error:
-	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID)
+	if (root->root_key.objectid != BTRFS_TREE_LOG_OBJECTID) {
+		ASSERT(last_size >= new_size);
+		if (!err && last_size > new_size)
+			last_size = new_size;
 		btrfs_ordered_update_i_size(inode, last_size, NULL);
+	}
 
 	btrfs_free_path(path);
 
@@ -4734,6 +4770,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	char *kaddr;
 	u32 blocksize = fs_info->sectorsize;
 	pgoff_t index = from >> PAGE_SHIFT;
@@ -4748,7 +4785,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 	    (!len || ((len & (blocksize - 1)) == 0)))
 		goto out;
 
-	ret = btrfs_delalloc_reserve_space(inode,
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
 			round_down(from, blocksize), blocksize);
 	if (ret)
 		goto out;
@@ -4756,7 +4793,7 @@ int btrfs_truncate_block(struct inode *inode, loff_t from, loff_t len,
 again:
 	page = find_or_create_page(mapping, index, mask);
 	if (!page) {
-		btrfs_delalloc_release_space(inode,
+		btrfs_delalloc_release_space(inode, data_reserved,
 				round_down(from, blocksize),
 				blocksize);
 		ret = -ENOMEM;
@@ -4828,11 +4865,12 @@ again:
 
 out_unlock:
 	if (ret)
-		btrfs_delalloc_release_space(inode, block_start,
+		btrfs_delalloc_release_space(inode, data_reserved, block_start,
 					     blocksize);
 	unlock_page(page);
 	put_page(page);
 out:
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -4870,8 +4908,8 @@ static int maybe_insert_hole(struct btrfs_root *root, struct inode *inode,
 		return ret;
 	}
 
-	ret = btrfs_insert_file_extent(trans, root, btrfs_ino(inode), offset,
-				       0, 0, len, 0, len, 0, 0, 0);
+	ret = btrfs_insert_file_extent(trans, root, btrfs_ino(BTRFS_I(inode)),
+			offset, 0, 0, len, 0, len, 0, 0, 0);
 	if (ret)
 		btrfs_abort_transaction(trans, ret);
 	else
@@ -4918,7 +4956,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 
 		lock_extent_bits(io_tree, hole_start, block_end - 1,
 				 &cached_state);
-		ordered = btrfs_lookup_ordered_range(inode, hole_start,
+		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), hole_start,
 						     block_end - hole_start);
 		if (!ordered)
 			break;
@@ -4930,7 +4968,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 
 	cur_offset = hole_start;
 	while (1) {
-		em = btrfs_get_extent(inode, NULL, 0, cur_offset,
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, cur_offset,
 				block_end - cur_offset, 0);
 		if (IS_ERR(em)) {
 			err = PTR_ERR(em);
@@ -4947,7 +4985,7 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 						hole_size);
 			if (err)
 				break;
-			btrfs_drop_extent_cache(inode, cur_offset,
+			btrfs_drop_extent_cache(BTRFS_I(inode), cur_offset,
 						cur_offset + hole_size - 1, 0);
 			hole_em = alloc_extent_map();
 			if (!hole_em) {
@@ -4973,7 +5011,8 @@ int btrfs_cont_expand(struct inode *inode, loff_t oldsize, loff_t size)
 				write_unlock(&em_tree->lock);
 				if (err != -EEXIST)
 					break;
-				btrfs_drop_extent_cache(inode, cur_offset,
+				btrfs_drop_extent_cache(BTRFS_I(inode),
+							cur_offset,
 							cur_offset +
 							hole_size - 1, 0);
 			}
@@ -5070,7 +5109,7 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		 * so we need to guarantee from this point on that everything
 		 * will be consistent.
 		 */
-		ret = btrfs_orphan_add(trans, inode);
+		ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 		btrfs_end_transaction(trans);
 		if (ret)
 			return ret;
@@ -5079,14 +5118,21 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 		truncate_setsize(inode, newsize);
 
 		/* Disable nonlocked read DIO to avoid the end less truncate */
-		btrfs_inode_block_unlocked_dio(inode);
+		btrfs_inode_block_unlocked_dio(BTRFS_I(inode));
 		inode_dio_wait(inode);
-		btrfs_inode_resume_unlocked_dio(inode);
+		btrfs_inode_resume_unlocked_dio(BTRFS_I(inode));
 
 		ret = btrfs_truncate(inode);
 		if (ret && inode->i_nlink) {
 			int err;
 
+			/* To get a stable disk_i_size */
+			err = btrfs_wait_ordered_range(inode, 0, (u64)-1);
+			if (err) {
+				btrfs_orphan_del(NULL, BTRFS_I(inode));
+				return err;
+			}
+
 			/*
 			 * failed to truncate, disk_i_size is only adjusted down
 			 * as we remove extents, so it should represent the true
@@ -5095,11 +5141,11 @@ static int btrfs_setsize(struct inode *inode, struct iattr *attr)
 			 */
 			trans = btrfs_join_transaction(root);
 			if (IS_ERR(trans)) {
-				btrfs_orphan_del(NULL, inode);
+				btrfs_orphan_del(NULL, BTRFS_I(inode));
 				return ret;
 			}
 			i_size_write(inode, BTRFS_I(inode)->disk_i_size);
-			err = btrfs_orphan_del(trans, inode);
+			err = btrfs_orphan_del(trans, BTRFS_I(inode));
 			if (err)
 				btrfs_abort_transaction(trans, err);
 			btrfs_end_transaction(trans);
@@ -5219,7 +5265,7 @@ static void evict_inode_truncate_pages(struct inode *inode)
 		 * Note, end is the bytenr of last byte, so we need + 1 here.
 		 */
 		if (state->state & EXTENT_DELALLOC)
-			btrfs_qgroup_free_data(inode, start, end - start + 1);
+			btrfs_qgroup_free_data(inode, NULL, start, end - start + 1);
 
 		clear_extent_bit(io_tree, start, end,
 				 EXTENT_LOCKED | EXTENT_DIRTY |
@@ -5257,18 +5303,18 @@ void btrfs_evict_inode(struct inode *inode)
 	if (inode->i_nlink &&
 	    ((btrfs_root_refs(&root->root_item) != 0 &&
 	      root->root_key.objectid != BTRFS_ROOT_TREE_OBJECTID) ||
-	     btrfs_is_free_space_inode(inode)))
+	     btrfs_is_free_space_inode(BTRFS_I(inode))))
 		goto no_delete;
 
 	if (is_bad_inode(inode)) {
-		btrfs_orphan_del(NULL, inode);
+		btrfs_orphan_del(NULL, BTRFS_I(inode));
 		goto no_delete;
 	}
 	/* do we really want it for ->i_nlink > 0 and zero btrfs_root_refs? */
 	if (!special_file(inode->i_mode))
 		btrfs_wait_ordered_range(inode, 0, (u64)-1);
 
-	btrfs_free_io_failure_record(inode, 0, (u64)-1);
+	btrfs_free_io_failure_record(BTRFS_I(inode), 0, (u64)-1);
 
 	if (test_bit(BTRFS_FS_LOG_RECOVERING, &fs_info->flags)) {
 		BUG_ON(test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
@@ -5282,22 +5328,22 @@ void btrfs_evict_inode(struct inode *inode)
 		goto no_delete;
 	}
 
-	ret = btrfs_commit_inode_delayed_inode(inode);
+	ret = btrfs_commit_inode_delayed_inode(BTRFS_I(inode));
 	if (ret) {
-		btrfs_orphan_del(NULL, inode);
+		btrfs_orphan_del(NULL, BTRFS_I(inode));
 		goto no_delete;
 	}
 
 	rsv = btrfs_alloc_block_rsv(fs_info, BTRFS_BLOCK_RSV_TEMP);
 	if (!rsv) {
-		btrfs_orphan_del(NULL, inode);
+		btrfs_orphan_del(NULL, BTRFS_I(inode));
 		goto no_delete;
 	}
 	rsv->size = min_size;
 	rsv->failfast = 1;
 	global_rsv = &fs_info->global_block_rsv;
 
-	btrfs_i_size_write(inode, 0);
+	btrfs_i_size_write(BTRFS_I(inode), 0);
 
 	/*
 	 * This is a bit simpler than btrfs_truncate since we've already
@@ -5332,14 +5378,14 @@ void btrfs_evict_inode(struct inode *inode)
 			btrfs_warn(fs_info,
 				   "Could not get space for a delete, will truncate on mount %d",
 				   ret);
-			btrfs_orphan_del(NULL, inode);
+			btrfs_orphan_del(NULL, BTRFS_I(inode));
 			btrfs_free_block_rsv(fs_info, rsv);
 			goto no_delete;
 		}
 
 		trans = btrfs_join_transaction(root);
 		if (IS_ERR(trans)) {
-			btrfs_orphan_del(NULL, inode);
+			btrfs_orphan_del(NULL, BTRFS_I(inode));
 			btrfs_free_block_rsv(fs_info, rsv);
 			goto no_delete;
 		}
@@ -5365,7 +5411,7 @@ void btrfs_evict_inode(struct inode *inode)
 		if (ret) {
 			ret = btrfs_commit_transaction(trans);
 			if (ret) {
-				btrfs_orphan_del(NULL, inode);
+				btrfs_orphan_del(NULL, BTRFS_I(inode));
 				btrfs_free_block_rsv(fs_info, rsv);
 				goto no_delete;
 			}
@@ -5394,20 +5440,20 @@ void btrfs_evict_inode(struct inode *inode)
 	 */
 	if (ret == 0) {
 		trans->block_rsv = root->orphan_block_rsv;
-		btrfs_orphan_del(trans, inode);
+		btrfs_orphan_del(trans, BTRFS_I(inode));
 	} else {
-		btrfs_orphan_del(NULL, inode);
+		btrfs_orphan_del(NULL, BTRFS_I(inode));
 	}
 
 	trans->block_rsv = &fs_info->trans_block_rsv;
 	if (!(root == fs_info->tree_root ||
 	      root->root_key.objectid == BTRFS_TREE_RELOC_OBJECTID))
-		btrfs_return_ino(root, btrfs_ino(inode));
+		btrfs_return_ino(root, btrfs_ino(BTRFS_I(inode)));
 
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
 no_delete:
-	btrfs_remove_delayed_node(inode);
+	btrfs_remove_delayed_node(BTRFS_I(inode));
 	clear_inode(inode);
 }
 
@@ -5429,8 +5475,8 @@ static int btrfs_inode_by_name(struct inode *dir, struct dentry *dentry,
 	if (!path)
 		return -ENOMEM;
 
-	di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(dir), name,
-				    namelen, 0);
+	di = btrfs_lookup_dir_item(NULL, root, path, btrfs_ino(BTRFS_I(dir)),
+			name, namelen, 0);
 	if (IS_ERR(di))
 		ret = PTR_ERR(di);
 
@@ -5485,7 +5531,7 @@ static int fixup_tree_root_location(struct btrfs_fs_info *fs_info,
 
 	leaf = path->nodes[0];
 	ref = btrfs_item_ptr(leaf, path->slots[0], struct btrfs_root_ref);
-	if (btrfs_root_ref_dirid(leaf, ref) != btrfs_ino(dir) ||
+	if (btrfs_root_ref_dirid(leaf, ref) != btrfs_ino(BTRFS_I(dir)) ||
 	    btrfs_root_ref_name_len(leaf, ref) != dentry->d_name.len)
 		goto out;
 
@@ -5520,7 +5566,7 @@ static void inode_tree_add(struct inode *inode)
 	struct rb_node **p;
 	struct rb_node *parent;
 	struct rb_node *new = &BTRFS_I(inode)->rb_node;
-	u64 ino = btrfs_ino(inode);
+	u64 ino = btrfs_ino(BTRFS_I(inode));
 
 	if (inode_unhashed(inode))
 		return;
@@ -5531,9 +5577,9 @@ static void inode_tree_add(struct inode *inode)
 		parent = *p;
 		entry = rb_entry(parent, struct btrfs_inode, rb_node);
 
-		if (ino < btrfs_ino(&entry->vfs_inode))
+		if (ino < btrfs_ino(BTRFS_I(&entry->vfs_inode)))
 			p = &parent->rb_left;
-		else if (ino > btrfs_ino(&entry->vfs_inode))
+		else if (ino > btrfs_ino(BTRFS_I(&entry->vfs_inode)))
 			p = &parent->rb_right;
 		else {
 			WARN_ON(!(entry->vfs_inode.i_state &
@@ -5593,9 +5639,9 @@ again:
 		prev = node;
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
 
-		if (objectid < btrfs_ino(&entry->vfs_inode))
+		if (objectid < btrfs_ino(BTRFS_I(&entry->vfs_inode)))
 			node = node->rb_left;
-		else if (objectid > btrfs_ino(&entry->vfs_inode))
+		else if (objectid > btrfs_ino(BTRFS_I(&entry->vfs_inode)))
 			node = node->rb_right;
 		else
 			break;
@@ -5603,7 +5649,7 @@ again:
 	if (!node) {
 		while (prev) {
 			entry = rb_entry(prev, struct btrfs_inode, rb_node);
-			if (objectid <= btrfs_ino(&entry->vfs_inode)) {
+			if (objectid <= btrfs_ino(BTRFS_I(&entry->vfs_inode))) {
 				node = prev;
 				break;
 			}
@@ -5612,7 +5658,7 @@ again:
 	}
 	while (node) {
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
-		objectid = btrfs_ino(&entry->vfs_inode) + 1;
+		objectid = btrfs_ino(BTRFS_I(&entry->vfs_inode)) + 1;
 		inode = igrab(&entry->vfs_inode);
 		if (inode) {
 			spin_unlock(&root->inode_lock);
@@ -5796,7 +5842,7 @@ static int btrfs_dentry_delete(const struct dentry *dentry)
 		if (btrfs_root_refs(&root->root_item) == 0)
 			return 1;
 
-		if (btrfs_ino(inode) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
+		if (btrfs_ino(BTRFS_I(inode)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
 			return 1;
 	}
 	return 0;
@@ -5832,7 +5878,6 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 	struct inode *inode = file_inode(file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct btrfs_item *item;
 	struct btrfs_dir_item *di;
 	struct btrfs_key key;
 	struct btrfs_key found_key;
@@ -5865,7 +5910,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 
 	key.type = BTRFS_DIR_INDEX_KEY;
 	key.offset = ctx->pos;
-	key.objectid = btrfs_ino(inode);
+	key.objectid = btrfs_ino(BTRFS_I(inode));
 
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
 	if (ret < 0)
@@ -5883,7 +5928,6 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 			continue;
 		}
 
-		item = btrfs_item_nr(slot);
 		btrfs_item_key_to_cpu(leaf, &found_key, slot);
 
 		if (found_key.objectid != key.objectid)
@@ -5898,7 +5942,7 @@ static int btrfs_real_readdir(struct file *file, struct dir_context *ctx)
 		ctx->pos = found_key.offset;
 
 		di = btrfs_item_ptr(leaf, slot, struct btrfs_dir_item);
-		if (verify_dir_item(fs_info, leaf, di))
+		if (verify_dir_item(fs_info, leaf, slot, di))
 			goto next;
 
 		name_len = btrfs_dir_name_len(leaf, di);
@@ -5974,7 +6018,8 @@ int btrfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	if (test_bit(BTRFS_INODE_DUMMY, &BTRFS_I(inode)->runtime_flags))
 		return 0;
 
-	if (btrfs_fs_closing(root->fs_info) && btrfs_is_free_space_inode(inode))
+	if (btrfs_fs_closing(root->fs_info) &&
+			btrfs_is_free_space_inode(BTRFS_I(inode)))
 		nolock = true;
 
 	if (wbc->sync_mode == WB_SYNC_ALL) {
@@ -6054,9 +6099,9 @@ static int btrfs_update_time(struct inode *inode, struct timespec *now,
  * and then set the in-memory index_cnt variable to reflect
  * free sequence numbers
  */
-static int btrfs_set_inode_index_count(struct inode *inode)
+static int btrfs_set_inode_index_count(struct btrfs_inode *inode)
 {
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 	struct btrfs_key key, found_key;
 	struct btrfs_path *path;
 	struct extent_buffer *leaf;
@@ -6085,7 +6130,7 @@ static int btrfs_set_inode_index_count(struct inode *inode)
 	 * else has to start at 2
 	 */
 	if (path->slots[0] == 0) {
-		BTRFS_I(inode)->index_cnt = 2;
+		inode->index_cnt = 2;
 		goto out;
 	}
 
@@ -6096,11 +6141,11 @@ static int btrfs_set_inode_index_count(struct inode *inode)
 
 	if (found_key.objectid != btrfs_ino(inode) ||
 	    found_key.type != BTRFS_DIR_INDEX_KEY) {
-		BTRFS_I(inode)->index_cnt = 2;
+		inode->index_cnt = 2;
 		goto out;
 	}
 
-	BTRFS_I(inode)->index_cnt = found_key.offset + 1;
+	inode->index_cnt = found_key.offset + 1;
 out:
 	btrfs_free_path(path);
 	return ret;
@@ -6110,11 +6155,11 @@ out:
  * helper to find a free sequence number in a given directory.  This current
  * code is very simple, later versions will do smarter things in the btree
  */
-int btrfs_set_inode_index(struct inode *dir, u64 *index)
+int btrfs_set_inode_index(struct btrfs_inode *dir, u64 *index)
 {
 	int ret = 0;
 
-	if (BTRFS_I(dir)->index_cnt == (u64)-1) {
+	if (dir->index_cnt == (u64)-1) {
 		ret = btrfs_inode_delayed_dir_index_count(dir);
 		if (ret) {
 			ret = btrfs_set_inode_index_count(dir);
@@ -6123,8 +6168,8 @@ int btrfs_set_inode_index(struct inode *dir, u64 *index)
 		}
 	}
 
-	*index = BTRFS_I(dir)->index_cnt;
-	BTRFS_I(dir)->index_cnt++;
+	*index = dir->index_cnt;
+	dir->index_cnt++;
 
 	return ret;
 }
@@ -6185,7 +6230,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	if (dir && name) {
 		trace_btrfs_inode_request(dir);
 
-		ret = btrfs_set_inode_index(dir, index);
+		ret = btrfs_set_inode_index(BTRFS_I(dir), index);
 		if (ret) {
 			btrfs_free_path(path);
 			iput(inode);
@@ -6294,7 +6339,7 @@ static struct inode *btrfs_new_inode(struct btrfs_trans_handle *trans,
 	if (ret)
 		btrfs_err(fs_info,
 			  "error inheriting props for ino %llu (root %llu): %d",
-			  btrfs_ino(inode), root->root_key.objectid, ret);
+			btrfs_ino(BTRFS_I(inode)), root->root_key.objectid, ret);
 
 	return inode;
 
@@ -6320,18 +6365,18 @@ static inline u8 btrfs_inode_type(struct inode *inode)
  * inode to the parent directory.
  */
 int btrfs_add_link(struct btrfs_trans_handle *trans,
-		   struct inode *parent_inode, struct inode *inode,
+		   struct btrfs_inode *parent_inode, struct btrfs_inode *inode,
 		   const char *name, int name_len, int add_backref, u64 index)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	int ret = 0;
 	struct btrfs_key key;
-	struct btrfs_root *root = BTRFS_I(parent_inode)->root;
+	struct btrfs_root *root = parent_inode->root;
 	u64 ino = btrfs_ino(inode);
 	u64 parent_ino = btrfs_ino(parent_inode);
 
 	if (unlikely(ino == BTRFS_FIRST_FREE_OBJECTID)) {
-		memcpy(&key, &BTRFS_I(inode)->root->root_key, sizeof(key));
+		memcpy(&key, &inode->root->root_key, sizeof(key));
 	} else {
 		key.objectid = ino;
 		key.type = BTRFS_INODE_ITEM_KEY;
@@ -6353,7 +6398,7 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_insert_dir_item(trans, root, name, name_len,
 				    parent_inode, &key,
-				    btrfs_inode_type(inode), index);
+				    btrfs_inode_type(&inode->vfs_inode), index);
 	if (ret == -EEXIST || ret == -EOVERFLOW)
 		goto fail_dir_item;
 	else if (ret) {
@@ -6361,12 +6406,12 @@ int btrfs_add_link(struct btrfs_trans_handle *trans,
 		return ret;
 	}
 
-	btrfs_i_size_write(parent_inode, parent_inode->i_size +
+	btrfs_i_size_write(parent_inode, parent_inode->vfs_inode.i_size +
 			   name_len * 2);
-	inode_inc_iversion(parent_inode);
-	parent_inode->i_mtime = parent_inode->i_ctime =
-		current_time(parent_inode);
-	ret = btrfs_update_inode(trans, root, parent_inode);
+	inode_inc_iversion(&parent_inode->vfs_inode);
+	parent_inode->vfs_inode.i_mtime = parent_inode->vfs_inode.i_ctime =
+		current_time(&parent_inode->vfs_inode);
+	ret = btrfs_update_inode(trans, root, &parent_inode->vfs_inode);
 	if (ret)
 		btrfs_abort_transaction(trans, ret);
 	return ret;
@@ -6390,8 +6435,8 @@ fail_dir_item:
 }
 
 static int btrfs_add_nondir(struct btrfs_trans_handle *trans,
-			    struct inode *dir, struct dentry *dentry,
-			    struct inode *inode, int backref, u64 index)
+			    struct btrfs_inode *dir, struct dentry *dentry,
+			    struct btrfs_inode *inode, int backref, u64 index)
 {
 	int err = btrfs_add_link(trans, dir, inode,
 				 dentry->d_name.name, dentry->d_name.len,
@@ -6427,8 +6472,8 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 		goto out_unlock;
 
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
-				dentry->d_name.len, btrfs_ino(dir), objectid,
-				mode, &index);
+			dentry->d_name.len, btrfs_ino(BTRFS_I(dir)), objectid,
+			mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_unlock;
@@ -6447,7 +6492,8 @@ static int btrfs_mknod(struct inode *dir, struct dentry *dentry,
 	if (err)
 		goto out_unlock_inode;
 
-	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
+	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
+			0, index);
 	if (err) {
 		goto out_unlock_inode;
 	} else {
@@ -6499,8 +6545,8 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 		goto out_unlock;
 
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
-				dentry->d_name.len, btrfs_ino(dir), objectid,
-				mode, &index);
+			dentry->d_name.len, btrfs_ino(BTRFS_I(dir)), objectid,
+			mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_unlock;
@@ -6524,7 +6570,8 @@ static int btrfs_create(struct inode *dir, struct dentry *dentry,
 	if (err)
 		goto out_unlock_inode;
 
-	err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
+	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
+			0, index);
 	if (err)
 		goto out_unlock_inode;
 
@@ -6566,7 +6613,7 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	if (inode->i_nlink >= BTRFS_LINK_MAX)
 		return -EMLINK;
 
-	err = btrfs_set_inode_index(dir, &index);
+	err = btrfs_set_inode_index(BTRFS_I(dir), &index);
 	if (err)
 		goto fail;
 
@@ -6590,7 +6637,8 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 	ihold(inode);
 	set_bit(BTRFS_INODE_COPY_EVERYTHING, &BTRFS_I(inode)->runtime_flags);
 
-	err = btrfs_add_nondir(trans, dir, dentry, inode, 1, index);
+	err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry, BTRFS_I(inode),
+			1, index);
 
 	if (err) {
 		drop_inode = 1;
@@ -6604,12 +6652,12 @@ static int btrfs_link(struct dentry *old_dentry, struct inode *dir,
 			 * If new hard link count is 1, it's a file created
 			 * with open(2) O_TMPFILE flag.
 			 */
-			err = btrfs_orphan_del(trans, inode);
+			err = btrfs_orphan_del(trans, BTRFS_I(inode));
 			if (err)
 				goto fail;
 		}
 		d_instantiate(dentry, inode);
-		btrfs_log_new_name(trans, inode, NULL, parent);
+		btrfs_log_new_name(trans, BTRFS_I(inode), NULL, parent);
 	}
 
 	btrfs_balance_delayed_items(fs_info);
@@ -6649,8 +6697,8 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 		goto out_fail;
 
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
-				dentry->d_name.len, btrfs_ino(dir), objectid,
-				S_IFDIR | mode, &index);
+			dentry->d_name.len, btrfs_ino(BTRFS_I(dir)), objectid,
+			S_IFDIR | mode, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_fail;
@@ -6665,13 +6713,14 @@ static int btrfs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	if (err)
 		goto out_fail_inode;
 
-	btrfs_i_size_write(inode, 0);
+	btrfs_i_size_write(BTRFS_I(inode), 0);
 	err = btrfs_update_inode(trans, root, inode);
 	if (err)
 		goto out_fail_inode;
 
-	err = btrfs_add_link(trans, dir, inode, dentry->d_name.name,
-			     dentry->d_name.len, 0, index);
+	err = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode),
+			dentry->d_name.name,
+			dentry->d_name.len, 0, index);
 	if (err)
 		goto out_fail_inode;
 
@@ -6788,6 +6837,20 @@ static noinline int uncompress_inline(struct btrfs_path *path,
 	max_size = min_t(unsigned long, PAGE_SIZE, max_size);
 	ret = btrfs_decompress(compress_type, tmp, page,
 			       extent_offset, inline_size, max_size);
+
+	/*
+	 * decompression code contains a memset to fill in any space between the end
+	 * of the uncompressed data and the end of max_size in case the decompressed
+	 * data ends up shorter than ram_bytes.  That doesn't cover the hole between
+	 * the end of an inline extent and the beginning of the next block, so we
+	 * cover that region here.
+	 */
+
+	if (max_size + pg_offset < PAGE_SIZE) {
+		char *map = kmap(page);
+		memset(map + pg_offset + max_size, 0, PAGE_SIZE - max_size - pg_offset);
+		kunmap(page);
+	}
 	kfree(tmp);
 	return ret;
 }
@@ -6800,12 +6863,12 @@ static noinline int uncompress_inline(struct btrfs_path *path,
  *
  * This also copies inline extents directly into the page.
  */
-
-struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
-				    size_t pg_offset, u64 start, u64 len,
-				    int create)
+struct extent_map *btrfs_get_extent(struct btrfs_inode *inode,
+		struct page *page,
+	    size_t pg_offset, u64 start, u64 len,
+		int create)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	int ret;
 	int err = 0;
 	u64 extent_start = 0;
@@ -6813,13 +6876,13 @@ struct extent_map *btrfs_get_extent(struct inode *inode, struct page *page,
 	u64 objectid = btrfs_ino(inode);
 	u32 found_type;
 	struct btrfs_path *path = NULL;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 	struct btrfs_file_extent_item *item;
 	struct extent_buffer *leaf;
 	struct btrfs_key found_key;
 	struct extent_map *em = NULL;
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
-	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+	struct extent_map_tree *em_tree = &inode->extent_tree;
+	struct extent_io_tree *io_tree = &inode->io_tree;
 	struct btrfs_trans_handle *trans = NULL;
 	const bool new_inline = !page || create;
 
@@ -6899,11 +6962,18 @@ again:
 	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
 		extent_end = extent_start +
 		       btrfs_file_extent_num_bytes(leaf, item);
+
+		trace_btrfs_get_extent_show_fi_regular(inode, leaf, item,
+						       extent_start);
 	} else if (found_type == BTRFS_FILE_EXTENT_INLINE) {
 		size_t size;
 		size = btrfs_file_extent_inline_len(leaf, path->slots[0], item);
 		extent_end = ALIGN(extent_start + size,
 				   fs_info->sectorsize);
+
+		trace_btrfs_get_extent_show_fi_inline(inode, leaf, item,
+						      path->slots[0],
+						      extent_start);
 	}
 next:
 	if (start >= extent_end) {
@@ -6932,7 +7002,8 @@ next:
 		goto not_found_em;
 	}
 
-	btrfs_extent_item_to_extent_map(inode, path, item, new_inline, em);
+	btrfs_extent_item_to_extent_map(inode, path, item,
+			new_inline, em);
 
 	if (found_type == BTRFS_FILE_EXTENT_REG ||
 	    found_type == BTRFS_FILE_EXTENT_PREALLOC) {
@@ -7084,9 +7155,10 @@ out:
 	return em;
 }
 
-struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *page,
-					   size_t pg_offset, u64 start, u64 len,
-					   int create)
+struct extent_map *btrfs_get_extent_fiemap(struct btrfs_inode *inode,
+		struct page *page,
+		size_t pg_offset, u64 start, u64 len,
+		int create)
 {
 	struct extent_map *em;
 	struct extent_map *hole_em = NULL;
@@ -7099,19 +7171,17 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
 	em = btrfs_get_extent(inode, page, pg_offset, start, len, create);
 	if (IS_ERR(em))
 		return em;
-	if (em) {
-		/*
-		 * if our em maps to
-		 * -  a hole or
-		 * -  a pre-alloc extent,
-		 * there might actually be delalloc bytes behind it.
-		 */
-		if (em->block_start != EXTENT_MAP_HOLE &&
-		    !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
-			return em;
-		else
-			hole_em = em;
-	}
+	/*
+	 * If our em maps to:
+	 * - a hole or
+	 * - a pre-alloc extent,
+	 * there might actually be delalloc bytes behind it.
+	 */
+	if (em->block_start != EXTENT_MAP_HOLE &&
+	    !test_bit(EXTENT_FLAG_PREALLOC, &em->flags))
+		return em;
+	else
+		hole_em = em;
 
 	/* check to see if we've wrapped (len == -1 or similar) */
 	end = start + len;
@@ -7123,7 +7193,7 @@ struct extent_map *btrfs_get_extent_fiemap(struct inode *inode, struct page *pag
 	em = NULL;
 
 	/* ok, we didn't find anything, lets look for delalloc */
-	found = count_range_bits(&BTRFS_I(inode)->io_tree, &range_start,
+	found = count_range_bits(&inode->io_tree, &range_start,
 				 end, len, EXTENT_DELALLOC, 1);
 	found_end = range_start + found;
 	if (found_end < range_start)
@@ -7225,9 +7295,11 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
 	int ret;
 
 	if (type != BTRFS_ORDERED_NOCOW) {
-		em = create_pinned_em(inode, start, len, orig_start,
-				      block_start, block_len, orig_block_len,
-				      ram_bytes, type);
+		em = create_io_em(inode, start, len, orig_start,
+				  block_start, block_len, orig_block_len,
+				  ram_bytes,
+				  BTRFS_COMPRESS_NONE, /* compress_type */
+				  type);
 		if (IS_ERR(em))
 			goto out;
 	}
@@ -7236,7 +7308,7 @@ static struct extent_map *btrfs_create_dio_extent(struct inode *inode,
 	if (ret) {
 		if (em) {
 			free_extent_map(em);
-			btrfs_drop_extent_cache(inode, start,
+			btrfs_drop_extent_cache(BTRFS_I(inode), start,
 						start + len - 1, 0);
 		}
 		em = ERR_PTR(ret);
@@ -7264,7 +7336,7 @@ static struct extent_map *btrfs_new_extent_direct(struct inode *inode,
 
 	em = btrfs_create_dio_extent(inode, start, ins.offset, start,
 				     ins.objectid, ins.offset, ins.offset,
-				     ins.offset, 0);
+				     ins.offset, BTRFS_ORDERED_REGULAR);
 	btrfs_dec_block_group_reservations(fs_info, ins.objectid);
 	if (IS_ERR(em))
 		btrfs_free_reserved_extent(fs_info, ins.objectid,
@@ -7282,7 +7354,6 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 			      u64 *ram_bytes)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_trans_handle *trans;
 	struct btrfs_path *path;
 	int ret;
 	struct extent_buffer *leaf;
@@ -7302,8 +7373,8 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	if (!path)
 		return -ENOMEM;
 
-	ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(inode),
-				       offset, 0);
+	ret = btrfs_lookup_file_extent(NULL, root, path,
+			btrfs_ino(BTRFS_I(inode)), offset, 0);
 	if (ret < 0)
 		goto out;
 
@@ -7319,7 +7390,7 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	ret = 0;
 	leaf = path->nodes[0];
 	btrfs_item_key_to_cpu(leaf, &key, slot);
-	if (key.objectid != btrfs_ino(inode) ||
+	if (key.objectid != btrfs_ino(BTRFS_I(inode)) ||
 	    key.type != BTRFS_EXTENT_DATA_KEY) {
 		/* not our file or wrong item type, must cow */
 		goto out;
@@ -7385,15 +7456,9 @@ noinline int can_nocow_extent(struct inode *inode, u64 offset, u64 *len,
 	 * look for other files referencing this extent, if we
 	 * find any we must cow
 	 */
-	trans = btrfs_join_transaction(root);
-	if (IS_ERR(trans)) {
-		ret = 0;
-		goto out;
-	}
 
-	ret = btrfs_cross_ref_exist(trans, root, btrfs_ino(inode),
+	ret = btrfs_cross_ref_exist(root, btrfs_ino(BTRFS_I(inode)),
 				    key.offset - backref_offset, disk_bytenr);
-	btrfs_end_transaction(trans);
 	if (ret) {
 		ret = 0;
 		goto out;
@@ -7423,11 +7488,11 @@ out:
 bool btrfs_page_exists_in_range(struct inode *inode, loff_t start, loff_t end)
 {
 	struct radix_tree_root *root = &inode->i_mapping->page_tree;
-	int found = false;
+	bool found = false;
 	void **pagep = NULL;
 	struct page *page = NULL;
-	int start_idx;
-	int end_idx;
+	unsigned long start_idx;
+	unsigned long end_idx;
 
 	start_idx = start >> PAGE_SHIFT;
 
@@ -7504,7 +7569,7 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 		 * doing DIO to, so we need to make sure there's no ordered
 		 * extents in this range.
 		 */
-		ordered = btrfs_lookup_ordered_range(inode, lockstart,
+		ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), lockstart,
 						     lockend - lockstart + 1);
 
 		/*
@@ -7570,17 +7635,23 @@ static int lock_extent_direct(struct inode *inode, u64 lockstart, u64 lockend,
 	return ret;
 }
 
-static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
-					   u64 len, u64 orig_start,
-					   u64 block_start, u64 block_len,
-					   u64 orig_block_len, u64 ram_bytes,
-					   int type)
+/* The callers of this must take lock_extent() */
+static struct extent_map *create_io_em(struct inode *inode, u64 start, u64 len,
+				       u64 orig_start, u64 block_start,
+				       u64 block_len, u64 orig_block_len,
+				       u64 ram_bytes, int compress_type,
+				       int type)
 {
 	struct extent_map_tree *em_tree;
 	struct extent_map *em;
 	struct btrfs_root *root = BTRFS_I(inode)->root;
 	int ret;
 
+	ASSERT(type == BTRFS_ORDERED_PREALLOC ||
+	       type == BTRFS_ORDERED_COMPRESSED ||
+	       type == BTRFS_ORDERED_NOCOW ||
+	       type == BTRFS_ORDERED_REGULAR);
+
 	em_tree = &BTRFS_I(inode)->extent_tree;
 	em = alloc_extent_map();
 	if (!em)
@@ -7588,8 +7659,6 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
 
 	em->start = start;
 	em->orig_start = orig_start;
-	em->mod_start = start;
-	em->mod_len = len;
 	em->len = len;
 	em->block_len = block_len;
 	em->block_start = block_start;
@@ -7598,15 +7667,23 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
 	em->ram_bytes = ram_bytes;
 	em->generation = -1;
 	set_bit(EXTENT_FLAG_PINNED, &em->flags);
-	if (type == BTRFS_ORDERED_PREALLOC)
+	if (type == BTRFS_ORDERED_PREALLOC) {
 		set_bit(EXTENT_FLAG_FILLING, &em->flags);
+	} else if (type == BTRFS_ORDERED_COMPRESSED) {
+		set_bit(EXTENT_FLAG_COMPRESSED, &em->flags);
+		em->compress_type = compress_type;
+	}
 
 	do {
-		btrfs_drop_extent_cache(inode, em->start,
+		btrfs_drop_extent_cache(BTRFS_I(inode), em->start,
 				em->start + em->len - 1, 0);
 		write_lock(&em_tree->lock);
 		ret = add_extent_mapping(em_tree, em, 1);
 		write_unlock(&em_tree->lock);
+		/*
+		 * The caller has taken lock_extent(), who could race with us
+		 * to add em?
+		 */
 	} while (ret == -EEXIST);
 
 	if (ret) {
@@ -7614,6 +7691,7 @@ static struct extent_map *create_pinned_em(struct inode *inode, u64 start,
 		return ERR_PTR(ret);
 	}
 
+	/* em got 2 refs now, callers needs to do free_extent_map once. */
 	return em;
 }
 
@@ -7621,10 +7699,8 @@ static void adjust_dio_outstanding_extents(struct inode *inode,
 					   struct btrfs_dio_data *dio_data,
 					   const u64 len)
 {
-	unsigned num_extents;
+	unsigned num_extents = count_max_extents(len);
 
-	num_extents = (unsigned) div64_u64(len + BTRFS_MAX_EXTENT_SIZE - 1,
-					   BTRFS_MAX_EXTENT_SIZE);
 	/*
 	 * If we have an outstanding_extents count still set then we're
 	 * within our reservation, otherwise we need to adjust our inode
@@ -7687,7 +7763,7 @@ static int btrfs_get_blocks_direct(struct inode *inode, sector_t iblock,
 		goto err;
 	}
 
-	em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0);
 	if (IS_ERR(em)) {
 		ret = PTR_ERR(em);
 		goto unlock_err;
@@ -7804,7 +7880,7 @@ unlock:
 		 * Need to update the i_size under the extent lock so buffered
 		 * readers will get the updated i_size when we unlock.
 		 */
-		if (start + len > i_size_read(inode))
+		if (!dio_data->overwrite && start + len > i_size_read(inode))
 			i_size_write(inode, start + len);
 
 		adjust_dio_outstanding_extents(inode, dio_data, len);
@@ -7910,9 +7986,12 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 			bio_end_io_t *repair_endio, void *repair_arg)
 {
 	struct io_failure_record *failrec;
+	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
+	struct extent_io_tree *failure_tree = &BTRFS_I(inode)->io_failure_tree;
 	struct bio *bio;
 	int isector;
 	int read_mode = 0;
+	int segs;
 	int ret;
 
 	BUG_ON(bio_op(failed_bio) == REQ_OP_WRITE);
@@ -7924,23 +8003,19 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 	ret = btrfs_check_dio_repairable(inode, failed_bio, failrec,
 					 failed_mirror);
 	if (!ret) {
-		free_io_failure(inode, failrec);
+		free_io_failure(failure_tree, io_tree, failrec);
 		return -EIO;
 	}
 
-	if ((failed_bio->bi_vcnt > 1)
-		|| (failed_bio->bi_io_vec->bv_len
-			> btrfs_inode_sectorsize(inode)))
+	segs = bio_segments(failed_bio);
+	if (segs > 1 ||
+	    (failed_bio->bi_io_vec->bv_len > btrfs_inode_sectorsize(inode)))
 		read_mode |= REQ_FAILFAST_DEV;
 
 	isector = start - btrfs_io_bio(failed_bio)->logical;
 	isector >>= inode->i_sb->s_blocksize_bits;
 	bio = btrfs_create_repair_bio(inode, failed_bio, failrec, page,
 				pgoff, isector, repair_endio, repair_arg);
-	if (!bio) {
-		free_io_failure(inode, failrec);
-		return -EIO;
-	}
 	bio_set_op_attrs(bio, REQ_OP_READ, read_mode);
 
 	btrfs_debug(BTRFS_I(inode)->root->fs_info,
@@ -7949,7 +8024,7 @@ static int dio_read_error(struct inode *inode, struct bio *failed_bio,
 
 	ret = submit_dio_repair_bio(inode, bio, failrec->this_mirror);
 	if (ret) {
-		free_io_failure(inode, failrec);
+		free_io_failure(failure_tree, io_tree, failrec);
 		bio_put(bio);
 	}
 
@@ -7966,20 +8041,25 @@ struct btrfs_retry_complete {
 static void btrfs_retry_endio_nocsum(struct bio *bio)
 {
 	struct btrfs_retry_complete *done = bio->bi_private;
-	struct inode *inode;
+	struct inode *inode = done->inode;
 	struct bio_vec *bvec;
+	struct extent_io_tree *io_tree, *failure_tree;
 	int i;
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		goto end;
 
 	ASSERT(bio->bi_vcnt == 1);
-	inode = bio->bi_io_vec->bv_page->mapping->host;
+	io_tree = &BTRFS_I(inode)->io_tree;
+	failure_tree = &BTRFS_I(inode)->io_failure_tree;
 	ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode));
 
 	done->uptodate = 1;
+	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, i)
-		clean_io_failure(done->inode, done->start, bvec->bv_page, 0);
+		clean_io_failure(BTRFS_I(inode)->root->fs_info, failure_tree,
+				 io_tree, done->start, bvec->bv_page,
+				 btrfs_ino(BTRFS_I(inode)), 0);
 end:
 	complete(&done->done);
 	bio_put(bio);
@@ -7989,36 +8069,40 @@ static int __btrfs_correct_data_nocsum(struct inode *inode,
 				       struct btrfs_io_bio *io_bio)
 {
 	struct btrfs_fs_info *fs_info;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	struct btrfs_retry_complete done;
 	u64 start;
 	unsigned int pgoff;
 	u32 sectorsize;
 	int nr_sectors;
-	int i;
 	int ret;
+	int err = 0;
 
 	fs_info = BTRFS_I(inode)->root->fs_info;
 	sectorsize = fs_info->sectorsize;
 
 	start = io_bio->logical;
 	done.inode = inode;
+	io_bio->bio.bi_iter = io_bio->iter;
 
-	bio_for_each_segment_all(bvec, &io_bio->bio, i) {
-		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
-		pgoff = bvec->bv_offset;
+	bio_for_each_segment(bvec, &io_bio->bio, iter) {
+		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
+		pgoff = bvec.bv_offset;
 
 next_block_or_try_again:
 		done.uptodate = 0;
 		done.start = start;
 		init_completion(&done.done);
 
-		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+		ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page,
 				pgoff, start, start + sectorsize - 1,
 				io_bio->mirror_num,
 				btrfs_retry_endio_nocsum, &done);
-		if (ret)
-			return ret;
+		if (ret) {
+			err = ret;
+			goto next;
+		}
 
 		wait_for_completion(&done.done);
 
@@ -8027,46 +8111,53 @@ next_block_or_try_again:
 			goto next_block_or_try_again;
 		}
 
+next:
 		start += sectorsize;
 
-		if (nr_sectors--) {
+		nr_sectors--;
+		if (nr_sectors) {
 			pgoff += sectorsize;
+			ASSERT(pgoff < PAGE_SIZE);
 			goto next_block_or_try_again;
 		}
 	}
 
-	return 0;
+	return err;
 }
 
 static void btrfs_retry_endio(struct bio *bio)
 {
 	struct btrfs_retry_complete *done = bio->bi_private;
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
-	struct inode *inode;
+	struct extent_io_tree *io_tree, *failure_tree;
+	struct inode *inode = done->inode;
 	struct bio_vec *bvec;
-	u64 start;
 	int uptodate;
 	int ret;
 	int i;
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		goto end;
 
 	uptodate = 1;
 
-	start = done->start;
-
 	ASSERT(bio->bi_vcnt == 1);
-	inode = bio->bi_io_vec->bv_page->mapping->host;
-	ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(inode));
+	ASSERT(bio->bi_io_vec->bv_len == btrfs_inode_sectorsize(done->inode));
 
+	io_tree = &BTRFS_I(inode)->io_tree;
+	failure_tree = &BTRFS_I(inode)->io_failure_tree;
+
+	ASSERT(!bio_flagged(bio, BIO_CLONED));
 	bio_for_each_segment_all(bvec, bio, i) {
-		ret = __readpage_endio_check(done->inode, io_bio, i,
-					bvec->bv_page, bvec->bv_offset,
-					done->start, bvec->bv_len);
+		ret = __readpage_endio_check(inode, io_bio, i, bvec->bv_page,
+					     bvec->bv_offset, done->start,
+					     bvec->bv_len);
 		if (!ret)
-			clean_io_failure(done->inode, done->start,
-					bvec->bv_page, bvec->bv_offset);
+			clean_io_failure(BTRFS_I(inode)->root->fs_info,
+					 failure_tree, io_tree, done->start,
+					 bvec->bv_page,
+					 btrfs_ino(BTRFS_I(inode)),
+					 bvec->bv_offset);
 		else
 			uptodate = 0;
 	}
@@ -8077,11 +8168,12 @@ end:
 	bio_put(bio);
 }
 
-static int __btrfs_subio_endio_read(struct inode *inode,
-				    struct btrfs_io_bio *io_bio, int err)
+static blk_status_t __btrfs_subio_endio_read(struct inode *inode,
+		struct btrfs_io_bio *io_bio, blk_status_t err)
 {
 	struct btrfs_fs_info *fs_info;
-	struct bio_vec *bvec;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
 	struct btrfs_retry_complete done;
 	u64 start;
 	u64 offset = 0;
@@ -8089,7 +8181,7 @@ static int __btrfs_subio_endio_read(struct inode *inode,
 	int nr_sectors;
 	unsigned int pgoff;
 	int csum_pos;
-	int i;
+	bool uptodate = (err == 0);
 	int ret;
 
 	fs_info = BTRFS_I(inode)->root->fs_info;
@@ -8098,29 +8190,31 @@ static int __btrfs_subio_endio_read(struct inode *inode,
 	err = 0;
 	start = io_bio->logical;
 	done.inode = inode;
+	io_bio->bio.bi_iter = io_bio->iter;
 
-	bio_for_each_segment_all(bvec, &io_bio->bio, i) {
-		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
+	bio_for_each_segment(bvec, &io_bio->bio, iter) {
+		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec.bv_len);
 
-		pgoff = bvec->bv_offset;
+		pgoff = bvec.bv_offset;
 next_block:
-		csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset);
-		ret = __readpage_endio_check(inode, io_bio, csum_pos,
-					bvec->bv_page, pgoff, start,
-					sectorsize);
-		if (likely(!ret))
-			goto next;
+		if (uptodate) {
+			csum_pos = BTRFS_BYTES_TO_BLKS(fs_info, offset);
+			ret = __readpage_endio_check(inode, io_bio, csum_pos,
+					bvec.bv_page, pgoff, start, sectorsize);
+			if (likely(!ret))
+				goto next;
+		}
 try_again:
 		done.uptodate = 0;
 		done.start = start;
 		init_completion(&done.done);
 
-		ret = dio_read_error(inode, &io_bio->bio, bvec->bv_page,
+		ret = dio_read_error(inode, &io_bio->bio, bvec.bv_page,
 				pgoff, start, start + sectorsize - 1,
 				io_bio->mirror_num,
 				btrfs_retry_endio, &done);
 		if (ret) {
-			err = ret;
+			err = errno_to_blk_status(ret);
 			goto next;
 		}
 
@@ -8136,8 +8230,10 @@ next:
 
 		ASSERT(nr_sectors);
 
-		if (--nr_sectors) {
+		nr_sectors--;
+		if (nr_sectors) {
 			pgoff += sectorsize;
+			ASSERT(pgoff < PAGE_SIZE);
 			goto next_block;
 		}
 	}
@@ -8145,8 +8241,8 @@ next:
 	return err;
 }
 
-static int btrfs_subio_endio_read(struct inode *inode,
-				  struct btrfs_io_bio *io_bio, int err)
+static blk_status_t btrfs_subio_endio_read(struct inode *inode,
+		struct btrfs_io_bio *io_bio, blk_status_t err)
 {
 	bool skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
@@ -8166,10 +8262,13 @@ static void btrfs_endio_direct_read(struct bio *bio)
 	struct inode *inode = dip->inode;
 	struct bio *dio_bio;
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
-	int err = bio->bi_error;
+	blk_status_t err = bio->bi_status;
 
-	if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED)
+	if (dip->flags & BTRFS_DIO_ORIG_BIO_SUBMITTED) {
 		err = btrfs_subio_endio_read(inode, io_bio, err);
+		if (!err)
+			bio->bi_status = 0;
+	}
 
 	unlock_extent(&BTRFS_I(inode)->io_tree, dip->logical_offset,
 		      dip->logical_offset + dip->bytes - 1);
@@ -8177,25 +8276,34 @@ static void btrfs_endio_direct_read(struct bio *bio)
 
 	kfree(dip);
 
-	dio_bio->bi_error = bio->bi_error;
-	dio_end_io(dio_bio, bio->bi_error);
+	dio_bio->bi_status = bio->bi_status;
+	dio_end_io(dio_bio);
 
 	if (io_bio->end_io)
-		io_bio->end_io(io_bio, err);
+		io_bio->end_io(io_bio, blk_status_to_errno(err));
 	bio_put(bio);
 }
 
-static void btrfs_endio_direct_write_update_ordered(struct inode *inode,
-						    const u64 offset,
-						    const u64 bytes,
-						    const int uptodate)
+static void __endio_write_update_ordered(struct inode *inode,
+					 const u64 offset, const u64 bytes,
+					 const bool uptodate)
 {
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_ordered_extent *ordered = NULL;
+	struct btrfs_workqueue *wq;
+	btrfs_work_func_t func;
 	u64 ordered_offset = offset;
 	u64 ordered_bytes = bytes;
 	int ret;
 
+	if (btrfs_is_free_space_inode(BTRFS_I(inode))) {
+		wq = fs_info->endio_freespace_worker;
+		func = btrfs_freespace_write_helper;
+	} else {
+		wq = fs_info->endio_write_workers;
+		func = btrfs_endio_write_helper;
+	}
+
 again:
 	ret = btrfs_dec_test_first_ordered_pending(inode, &ordered,
 						   &ordered_offset,
@@ -8204,9 +8312,8 @@ again:
 	if (!ret)
 		goto out_test;
 
-	btrfs_init_work(&ordered->work, btrfs_endio_write_helper,
-			finish_ordered_fn, NULL, NULL);
-	btrfs_queue_work(fs_info->endio_write_workers, &ordered->work);
+	btrfs_init_work(&ordered->work, func, finish_ordered_fn, NULL, NULL);
+	btrfs_queue_work(wq, &ordered->work);
 out_test:
 	/*
 	 * our bio might span multiple ordered extents.  If we haven't
@@ -8224,23 +8331,22 @@ static void btrfs_endio_direct_write(struct bio *bio)
 	struct btrfs_dio_private *dip = bio->bi_private;
 	struct bio *dio_bio = dip->dio_bio;
 
-	btrfs_endio_direct_write_update_ordered(dip->inode,
-						dip->logical_offset,
-						dip->bytes,
-						!bio->bi_error);
+	__endio_write_update_ordered(dip->inode, dip->logical_offset,
+				     dip->bytes, !bio->bi_status);
 
 	kfree(dip);
 
-	dio_bio->bi_error = bio->bi_error;
-	dio_end_io(dio_bio, bio->bi_error);
+	dio_bio->bi_status = bio->bi_status;
+	dio_end_io(dio_bio);
 	bio_put(bio);
 }
 
-static int __btrfs_submit_bio_start_direct_io(struct inode *inode,
+static blk_status_t __btrfs_submit_bio_start_direct_io(void *private_data,
 				    struct bio *bio, int mirror_num,
 				    unsigned long bio_flags, u64 offset)
 {
-	int ret;
+	struct inode *inode = private_data;
+	blk_status_t ret;
 	ret = btrfs_csum_one_bio(inode, bio, offset, 1);
 	BUG_ON(ret); /* -ENOMEM */
 	return 0;
@@ -8249,12 +8355,13 @@ static int __btrfs_submit_bio_start_direct_io(struct inode *inode,
 static void btrfs_end_dio_bio(struct bio *bio)
 {
 	struct btrfs_dio_private *dip = bio->bi_private;
-	int err = bio->bi_error;
+	blk_status_t err = bio->bi_status;
 
 	if (err)
 		btrfs_warn(BTRFS_I(dip->inode)->root->fs_info,
 			   "direct IO failed ino %llu rw %d,%u sector %#Lx len %u err no %d",
-			   btrfs_ino(dip->inode), bio_op(bio), bio->bi_opf,
+			   btrfs_ino(BTRFS_I(dip->inode)), bio_op(bio),
+			   bio->bi_opf,
 			   (unsigned long long)bio->bi_iter.bi_sector,
 			   bio->bi_iter.bi_size, err);
 
@@ -8278,31 +8385,21 @@ static void btrfs_end_dio_bio(struct bio *bio)
 	if (dip->errors) {
 		bio_io_error(dip->orig_bio);
 	} else {
-		dip->dio_bio->bi_error = 0;
+		dip->dio_bio->bi_status = 0;
 		bio_endio(dip->orig_bio);
 	}
 out:
 	bio_put(bio);
 }
 
-static struct bio *btrfs_dio_bio_alloc(struct block_device *bdev,
-				       u64 first_sector, gfp_t gfp_flags)
-{
-	struct bio *bio;
-	bio = btrfs_bio_alloc(bdev, first_sector, BIO_MAX_PAGES, gfp_flags);
-	if (bio)
-		bio_associate_current(bio);
-	return bio;
-}
-
-static inline int btrfs_lookup_and_bind_dio_csum(struct inode *inode,
+static inline blk_status_t btrfs_lookup_and_bind_dio_csum(struct inode *inode,
 						 struct btrfs_dio_private *dip,
 						 struct bio *bio,
 						 u64 file_offset)
 {
 	struct btrfs_io_bio *io_bio = btrfs_io_bio(bio);
 	struct btrfs_io_bio *orig_io_bio = btrfs_io_bio(dip->orig_bio);
-	int ret;
+	blk_status_t ret;
 
 	/*
 	 * We load all the csum data we need when we submit
@@ -8333,7 +8430,7 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_dio_private *dip = bio->bi_private;
 	bool write = bio_op(bio) == REQ_OP_WRITE;
-	int ret;
+	blk_status_t ret;
 
 	if (async_submit)
 		async_submit = !atomic_read(&BTRFS_I(inode)->sync_writers);
@@ -8350,8 +8447,8 @@ static inline int __btrfs_submit_dio_bio(struct bio *bio, struct inode *inode,
 		goto map;
 
 	if (write && async_submit) {
-		ret = btrfs_wq_submit_bio(fs_info, inode, bio, 0, 0,
-					  file_offset,
+		ret = btrfs_wq_submit_bio(fs_info, bio, 0, 0,
+					  file_offset, inode,
 					  __btrfs_submit_bio_start_direct_io,
 					  __btrfs_submit_bio_done);
 		goto err;
@@ -8381,103 +8478,83 @@ static int btrfs_submit_direct_hook(struct btrfs_dio_private *dip,
 {
 	struct inode *inode = dip->inode;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root *root = BTRFS_I(inode)->root;
 	struct bio *bio;
 	struct bio *orig_bio = dip->orig_bio;
-	struct bio_vec *bvec;
 	u64 start_sector = orig_bio->bi_iter.bi_sector;
 	u64 file_offset = dip->logical_offset;
-	u64 submit_len = 0;
 	u64 map_length;
-	u32 blocksize = fs_info->sectorsize;
 	int async_submit = 0;
-	int nr_sectors;
+	u64 submit_len;
+	int clone_offset = 0;
+	int clone_len;
 	int ret;
-	int i, j;
 
 	map_length = orig_bio->bi_iter.bi_size;
+	submit_len = map_length;
 	ret = btrfs_map_block(fs_info, btrfs_op(orig_bio), start_sector << 9,
 			      &map_length, NULL, 0);
 	if (ret)
 		return -EIO;
 
-	if (map_length >= orig_bio->bi_iter.bi_size) {
+	if (map_length >= submit_len) {
 		bio = orig_bio;
 		dip->flags |= BTRFS_DIO_ORIG_BIO_SUBMITTED;
 		goto submit;
 	}
 
 	/* async crcs make it difficult to collect full stripe writes. */
-	if (btrfs_get_alloc_profile(root, 1) & BTRFS_BLOCK_GROUP_RAID56_MASK)
+	if (btrfs_data_alloc_profile(fs_info) & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		async_submit = 0;
 	else
 		async_submit = 1;
 
-	bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev, start_sector, GFP_NOFS);
-	if (!bio)
-		return -ENOMEM;
-
-	bio->bi_opf = orig_bio->bi_opf;
-	bio->bi_private = dip;
-	bio->bi_end_io = btrfs_end_dio_bio;
-	btrfs_io_bio(bio)->logical = file_offset;
+	/* bio split */
+	ASSERT(map_length <= INT_MAX);
 	atomic_inc(&dip->pending_bios);
+	do {
+		clone_len = min_t(int, submit_len, map_length);
 
-	bio_for_each_segment_all(bvec, orig_bio, j) {
-		nr_sectors = BTRFS_BYTES_TO_BLKS(fs_info, bvec->bv_len);
-		i = 0;
-next_block:
-		if (unlikely(map_length < submit_len + blocksize ||
-		    bio_add_page(bio, bvec->bv_page, blocksize,
-			    bvec->bv_offset + (i * blocksize)) < blocksize)) {
-			/*
-			 * inc the count before we submit the bio so
-			 * we know the end IO handler won't happen before
-			 * we inc the count. Otherwise, the dip might get freed
-			 * before we're done setting it up
-			 */
-			atomic_inc(&dip->pending_bios);
-			ret = __btrfs_submit_dio_bio(bio, inode,
-						     file_offset, skip_sum,
-						     async_submit);
-			if (ret) {
-				bio_put(bio);
-				atomic_dec(&dip->pending_bios);
-				goto out_err;
-			}
-
-			start_sector += submit_len >> 9;
-			file_offset += submit_len;
+		/*
+		 * This will never fail as it's passing GPF_NOFS and
+		 * the allocation is backed by btrfs_bioset.
+		 */
+		bio = btrfs_bio_clone_partial(orig_bio, clone_offset,
+					      clone_len);
+		bio->bi_private = dip;
+		bio->bi_end_io = btrfs_end_dio_bio;
+		btrfs_io_bio(bio)->logical = file_offset;
+
+		ASSERT(submit_len >= clone_len);
+		submit_len -= clone_len;
+		if (submit_len == 0)
+			break;
 
-			submit_len = 0;
+		/*
+		 * Increase the count before we submit the bio so we know
+		 * the end IO handler won't happen before we increase the
+		 * count. Otherwise, the dip might get freed before we're
+		 * done setting it up.
+		 */
+		atomic_inc(&dip->pending_bios);
 
-			bio = btrfs_dio_bio_alloc(orig_bio->bi_bdev,
-						  start_sector, GFP_NOFS);
-			if (!bio)
-				goto out_err;
-			bio->bi_opf = orig_bio->bi_opf;
-			bio->bi_private = dip;
-			bio->bi_end_io = btrfs_end_dio_bio;
-			btrfs_io_bio(bio)->logical = file_offset;
+		ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
+					     async_submit);
+		if (ret) {
+			bio_put(bio);
+			atomic_dec(&dip->pending_bios);
+			goto out_err;
+		}
 
-			map_length = orig_bio->bi_iter.bi_size;
-			ret = btrfs_map_block(fs_info, btrfs_op(orig_bio),
-					      start_sector << 9,
-					      &map_length, NULL, 0);
-			if (ret) {
-				bio_put(bio);
-				goto out_err;
-			}
+		clone_offset += clone_len;
+		start_sector += clone_len >> 9;
+		file_offset += clone_len;
 
-			goto next_block;
-		} else {
-			submit_len += blocksize;
-			if (--nr_sectors) {
-				i++;
-				goto next_block;
-			}
-		}
-	}
+		map_length = submit_len;
+		ret = btrfs_map_block(fs_info, btrfs_op(orig_bio),
+				      start_sector << 9, &map_length, NULL, 0);
+		if (ret)
+			goto out_err;
+	} while (submit_len > 0);
 
 submit:
 	ret = __btrfs_submit_dio_bio(bio, inode, file_offset, skip_sum,
@@ -8504,19 +8581,15 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
 				loff_t file_offset)
 {
 	struct btrfs_dio_private *dip = NULL;
-	struct bio *io_bio = NULL;
-	struct btrfs_io_bio *btrfs_bio;
+	struct bio *bio = NULL;
+	struct btrfs_io_bio *io_bio;
 	int skip_sum;
 	bool write = (bio_op(dio_bio) == REQ_OP_WRITE);
 	int ret = 0;
 
 	skip_sum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
 
-	io_bio = btrfs_bio_clone(dio_bio, GFP_NOFS);
-	if (!io_bio) {
-		ret = -ENOMEM;
-		goto free_ordered;
-	}
+	bio = btrfs_bio_clone(dio_bio);
 
 	dip = kzalloc(sizeof(*dip), GFP_NOFS);
 	if (!dip) {
@@ -8529,17 +8602,17 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
 	dip->logical_offset = file_offset;
 	dip->bytes = dio_bio->bi_iter.bi_size;
 	dip->disk_bytenr = (u64)dio_bio->bi_iter.bi_sector << 9;
-	io_bio->bi_private = dip;
-	dip->orig_bio = io_bio;
+	bio->bi_private = dip;
+	dip->orig_bio = bio;
 	dip->dio_bio = dio_bio;
 	atomic_set(&dip->pending_bios, 0);
-	btrfs_bio = btrfs_io_bio(io_bio);
-	btrfs_bio->logical = file_offset;
+	io_bio = btrfs_io_bio(bio);
+	io_bio->logical = file_offset;
 
 	if (write) {
-		io_bio->bi_end_io = btrfs_endio_direct_write;
+		bio->bi_end_io = btrfs_endio_direct_write;
 	} else {
-		io_bio->bi_end_io = btrfs_endio_direct_read;
+		bio->bi_end_io = btrfs_endio_direct_read;
 		dip->subio_endio = btrfs_subio_endio_read;
 	}
 
@@ -8562,8 +8635,8 @@ static void btrfs_submit_direct(struct bio *dio_bio, struct inode *inode,
 	if (!ret)
 		return;
 
-	if (btrfs_bio->end_io)
-		btrfs_bio->end_io(btrfs_bio, ret);
+	if (io_bio->end_io)
+		io_bio->end_io(io_bio, ret);
 
 free_ordered:
 	/*
@@ -8575,35 +8648,34 @@ free_ordered:
 	 * same as btrfs_endio_direct_[write|read] because we can't call these
 	 * callbacks - they require an allocated dip and a clone of dio_bio.
 	 */
-	if (io_bio && dip) {
-		io_bio->bi_error = -EIO;
-		bio_endio(io_bio);
+	if (bio && dip) {
+		bio_io_error(bio);
 		/*
-		 * The end io callbacks free our dip, do the final put on io_bio
+		 * The end io callbacks free our dip, do the final put on bio
 		 * and all the cleanup and final put for dio_bio (through
 		 * dio_end_io()).
 		 */
 		dip = NULL;
-		io_bio = NULL;
+		bio = NULL;
 	} else {
 		if (write)
-			btrfs_endio_direct_write_update_ordered(inode,
+			__endio_write_update_ordered(inode,
 						file_offset,
 						dio_bio->bi_iter.bi_size,
-						0);
+						false);
 		else
 			unlock_extent(&BTRFS_I(inode)->io_tree, file_offset,
 			      file_offset + dio_bio->bi_iter.bi_size - 1);
 
-		dio_bio->bi_error = -EIO;
+		dio_bio->bi_status = BLK_STS_IOERR;
 		/*
 		 * Releases and cleans up our dio_bio, no need to bio_put()
 		 * nor bio_endio()/bio_io_error() against dio_bio.
 		 */
-		dio_end_io(dio_bio, ret);
+		dio_end_io(dio_bio);
 	}
-	if (io_bio)
-		bio_put(io_bio);
+	if (bio)
+		bio_put(bio);
 	kfree(dip);
 }
 
@@ -8647,6 +8719,7 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = file->f_mapping->host;
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct btrfs_dio_data dio_data = { 0 };
+	struct extent_changeset *data_reserved = NULL;
 	loff_t offset = iocb->ki_pos;
 	size_t count = 0;
 	int flags = 0;
@@ -8679,15 +8752,18 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		 * not unlock the i_mutex at this case.
 		 */
 		if (offset + count <= inode->i_size) {
+			dio_data.overwrite = 1;
 			inode_unlock(inode);
 			relock = true;
+		} else if (iocb->ki_flags & IOCB_NOWAIT) {
+			ret = -EAGAIN;
+			goto out;
 		}
-		ret = btrfs_delalloc_reserve_space(inode, offset, count);
+		ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
+						   offset, count);
 		if (ret)
 			goto out;
-		dio_data.outstanding_extents = div64_u64(count +
-						BTRFS_MAX_EXTENT_SIZE - 1,
-						BTRFS_MAX_EXTENT_SIZE);
+		dio_data.outstanding_extents = count_max_extents(count);
 
 		/*
 		 * We need to know how many extents we reserved so that we can
@@ -8716,8 +8792,8 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 		current->journal_info = NULL;
 		if (ret < 0 && ret != -EIOCBQUEUED) {
 			if (dio_data.reserve)
-				btrfs_delalloc_release_space(inode, offset,
-							     dio_data.reserve);
+				btrfs_delalloc_release_space(inode, data_reserved,
+					offset, dio_data.reserve);
 			/*
 			 * On error we might have left some ordered extents
 			 * without submitting corresponding bios for them, so
@@ -8726,14 +8802,14 @@ static ssize_t btrfs_direct_IO(struct kiocb *iocb, struct iov_iter *iter)
 			 */
 			if (dio_data.unsubmitted_oe_range_start <
 			    dio_data.unsubmitted_oe_range_end)
-				btrfs_endio_direct_write_update_ordered(inode,
+				__endio_write_update_ordered(inode,
 					dio_data.unsubmitted_oe_range_start,
 					dio_data.unsubmitted_oe_range_end -
 					dio_data.unsubmitted_oe_range_start,
-					0);
+					false);
 		} else if (ret >= 0 && (size_t)ret < count)
-			btrfs_delalloc_release_space(inode, offset,
-						     count - (size_t)ret);
+			btrfs_delalloc_release_space(inode, data_reserved,
+					offset, count - (size_t)ret);
 	}
 out:
 	if (wakeup)
@@ -8741,6 +8817,7 @@ out:
 	if (relock)
 		inode_lock(inode);
 
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -8831,7 +8908,7 @@ static int btrfs_releasepage(struct page *page, gfp_t gfp_flags)
 {
 	if (PageWriteback(page) || PageDirty(page))
 		return 0;
-	return __btrfs_releasepage(page, gfp_flags & GFP_NOFS);
+	return __btrfs_releasepage(page, gfp_flags);
 }
 
 static void btrfs_invalidatepage(struct page *page, unsigned int offset,
@@ -8866,7 +8943,7 @@ static void btrfs_invalidatepage(struct page *page, unsigned int offset,
 		lock_extent_bits(tree, page_start, page_end, &cached_state);
 again:
 	start = page_start;
-	ordered = btrfs_lookup_ordered_range(inode, start,
+	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), start,
 					page_end - start + 1);
 	if (ordered) {
 		end = min(page_end, ordered->file_offset + ordered->len - 1);
@@ -8877,6 +8954,7 @@ again:
 		if (!inode_evicting)
 			clear_extent_bit(tree, start, end,
 					 EXTENT_DIRTY | EXTENT_DELALLOC |
+					 EXTENT_DELALLOC_NEW |
 					 EXTENT_LOCKED | EXTENT_DO_ACCOUNTING |
 					 EXTENT_DEFRAG, 1, 0, &cached_state,
 					 GFP_NOFS);
@@ -8930,12 +9008,12 @@ again:
 	 *    free the entire extent.
 	 */
 	if (PageDirty(page))
-		btrfs_qgroup_free_data(inode, page_start, PAGE_SIZE);
+		btrfs_qgroup_free_data(inode, NULL, page_start, PAGE_SIZE);
 	if (!inode_evicting) {
 		clear_extent_bit(tree, page_start, page_end,
 				 EXTENT_LOCKED | EXTENT_DIRTY |
-				 EXTENT_DELALLOC | EXTENT_DO_ACCOUNTING |
-				 EXTENT_DEFRAG, 1, 1,
+				 EXTENT_DELALLOC | EXTENT_DELALLOC_NEW |
+				 EXTENT_DO_ACCOUNTING | EXTENT_DEFRAG, 1, 1,
 				 &cached_state, GFP_NOFS);
 
 		__btrfs_releasepage(page, GFP_NOFS);
@@ -8964,14 +9042,15 @@ again:
  * beyond EOF, then the page is guaranteed safe against truncation until we
  * unlock the page.
  */
-int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+int btrfs_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
 	struct extent_io_tree *io_tree = &BTRFS_I(inode)->io_tree;
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
+	struct extent_changeset *data_reserved = NULL;
 	char *kaddr;
 	unsigned long zero_start;
 	loff_t size;
@@ -8997,10 +9076,10 @@ int btrfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	 * end up waiting indefinitely to get a lock on the page currently
 	 * being processed by btrfs_page_mkwrite() function.
 	 */
-	ret = btrfs_delalloc_reserve_space(inode, page_start,
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved, page_start,
 					   reserved_space);
 	if (!ret) {
-		ret = file_update_time(vma->vm_file);
+		ret = file_update_time(vmf->vma->vm_file);
 		reserved = 1;
 	}
 	if (ret) {
@@ -9032,7 +9111,8 @@ again:
 	 * we can't set the delalloc bits if there are pending ordered
 	 * extents.  Drop our locks and wait for them to finish
 	 */
-	ordered = btrfs_lookup_ordered_range(inode, page_start, page_end);
+	ordered = btrfs_lookup_ordered_range(BTRFS_I(inode), page_start,
+			PAGE_SIZE);
 	if (ordered) {
 		unlock_extent_cached(io_tree, page_start, page_end,
 				     &cached_state, GFP_NOFS);
@@ -9050,17 +9130,17 @@ again:
 			spin_lock(&BTRFS_I(inode)->lock);
 			BTRFS_I(inode)->outstanding_extents++;
 			spin_unlock(&BTRFS_I(inode)->lock);
-			btrfs_delalloc_release_space(inode, page_start,
-						PAGE_SIZE - reserved_space);
+			btrfs_delalloc_release_space(inode, data_reserved,
+					page_start, PAGE_SIZE - reserved_space);
 		}
 	}
 
 	/*
-	 * XXX - page_mkwrite gets called every time the page is dirtied, even
-	 * if it was already dirty, so for space accounting reasons we need to
-	 * clear any delalloc bits for the range we are fixing to save.  There
-	 * is probably a better way to do this, but for now keep consistent with
-	 * prepare_pages in the normal write path.
+	 * page_mkwrite gets called when the page is firstly dirtied after it's
+	 * faulted in, but write(2) could also dirty a page and set delalloc
+	 * bits, thus in this case for space account reason, we still need to
+	 * clear any delalloc bits within this page range since we have to
+	 * reserve data&meta space before lock_page() (see above comments).
 	 */
 	clear_extent_bit(&BTRFS_I(inode)->io_tree, page_start, end,
 			  EXTENT_DIRTY | EXTENT_DELALLOC |
@@ -9102,13 +9182,16 @@ again:
 out_unlock:
 	if (!ret) {
 		sb_end_pagefault(inode->i_sb);
+		extent_changeset_free(data_reserved);
 		return VM_FAULT_LOCKED;
 	}
 	unlock_page(page);
 out:
-	btrfs_delalloc_release_space(inode, page_start, reserved_space);
+	btrfs_delalloc_release_space(inode, data_reserved, page_start,
+				     reserved_space);
 out_noreserve:
 	sb_end_pagefault(inode->i_sb);
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -9230,7 +9313,7 @@ static int btrfs_truncate(struct inode *inode)
 
 	if (ret == 0 && inode->i_nlink > 0) {
 		trans->block_rsv = root->orphan_block_rsv;
-		ret = btrfs_orphan_del(trans, inode);
+		ret = btrfs_orphan_del(trans, BTRFS_I(inode));
 		if (ret)
 			err = ret;
 	}
@@ -9275,7 +9358,7 @@ int btrfs_create_subvol_root(struct btrfs_trans_handle *trans,
 	inode->i_fop = &btrfs_dir_file_operations;
 
 	set_nlink(inode, 1);
-	btrfs_i_size_write(inode, 0);
+	btrfs_i_size_write(BTRFS_I(inode), 0);
 	unlock_new_inode(inode);
 
 	err = btrfs_subvol_inherit_props(trans, new_root, parent_root);
@@ -9305,6 +9388,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 	ei->last_sub_trans = 0;
 	ei->logged_trans = 0;
 	ei->delalloc_bytes = 0;
+	ei->new_delalloc_bytes = 0;
 	ei->defrag_bytes = 0;
 	ei->disk_i_size = 0;
 	ei->flags = 0;
@@ -9329,8 +9413,8 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 
 	inode = &ei->vfs_inode;
 	extent_map_tree_init(&ei->extent_tree);
-	extent_io_tree_init(&ei->io_tree, &inode->i_data);
-	extent_io_tree_init(&ei->io_failure_tree, &inode->i_data);
+	extent_io_tree_init(&ei->io_tree, inode);
+	extent_io_tree_init(&ei->io_failure_tree, inode);
 	ei->io_tree.track_uptodate = 1;
 	ei->io_failure_tree.track_uptodate = 1;
 	atomic_set(&ei->sync_writers, 0);
@@ -9348,7 +9432,7 @@ struct inode *btrfs_alloc_inode(struct super_block *sb)
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 void btrfs_test_destroy_inode(struct inode *inode)
 {
-	btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
+	btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0);
 	kmem_cache_free(btrfs_inode_cachep, BTRFS_I(inode));
 }
 #endif
@@ -9370,6 +9454,7 @@ void btrfs_destroy_inode(struct inode *inode)
 	WARN_ON(BTRFS_I(inode)->outstanding_extents);
 	WARN_ON(BTRFS_I(inode)->reserved_extents);
 	WARN_ON(BTRFS_I(inode)->delalloc_bytes);
+	WARN_ON(BTRFS_I(inode)->new_delalloc_bytes);
 	WARN_ON(BTRFS_I(inode)->csum_bytes);
 	WARN_ON(BTRFS_I(inode)->defrag_bytes);
 
@@ -9384,7 +9469,7 @@ void btrfs_destroy_inode(struct inode *inode)
 	if (test_bit(BTRFS_INODE_HAS_ORPHAN_ITEM,
 		     &BTRFS_I(inode)->runtime_flags)) {
 		btrfs_info(fs_info, "inode %llu still on the orphan list",
-			   btrfs_ino(inode));
+			   btrfs_ino(BTRFS_I(inode)));
 		atomic_dec(&root->orphan_inodes);
 	}
 
@@ -9403,7 +9488,7 @@ void btrfs_destroy_inode(struct inode *inode)
 	}
 	btrfs_qgroup_check_reserved_leak(inode);
 	inode_tree_del(inode);
-	btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
+	btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0);
 free:
 	call_rcu(&inode->i_rcu, btrfs_i_callback);
 }
@@ -9438,7 +9523,6 @@ void btrfs_destroy_cachep(void)
 	rcu_barrier();
 	kmem_cache_destroy(btrfs_inode_cachep);
 	kmem_cache_destroy(btrfs_trans_handle_cachep);
-	kmem_cache_destroy(btrfs_transaction_cachep);
 	kmem_cache_destroy(btrfs_path_cachep);
 	kmem_cache_destroy(btrfs_free_space_cachep);
 }
@@ -9458,12 +9542,6 @@ int btrfs_init_cachep(void)
 	if (!btrfs_trans_handle_cachep)
 		goto fail;
 
-	btrfs_transaction_cachep = kmem_cache_create("btrfs_transaction",
-			sizeof(struct btrfs_transaction), 0,
-			SLAB_TEMPORARY | SLAB_MEM_SPREAD, NULL);
-	if (!btrfs_transaction_cachep)
-		goto fail;
-
 	btrfs_path_cachep = kmem_cache_create("btrfs_path",
 			sizeof(struct btrfs_path), 0,
 			SLAB_MEM_SPREAD, NULL);
@@ -9482,18 +9560,36 @@ fail:
 	return -ENOMEM;
 }
 
-static int btrfs_getattr(struct vfsmount *mnt,
-			 struct dentry *dentry, struct kstat *stat)
+static int btrfs_getattr(const struct path *path, struct kstat *stat,
+			 u32 request_mask, unsigned int flags)
 {
 	u64 delalloc_bytes;
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	u32 blocksize = inode->i_sb->s_blocksize;
+	u32 bi_flags = BTRFS_I(inode)->flags;
+
+	stat->result_mask |= STATX_BTIME;
+	stat->btime.tv_sec = BTRFS_I(inode)->i_otime.tv_sec;
+	stat->btime.tv_nsec = BTRFS_I(inode)->i_otime.tv_nsec;
+	if (bi_flags & BTRFS_INODE_APPEND)
+		stat->attributes |= STATX_ATTR_APPEND;
+	if (bi_flags & BTRFS_INODE_COMPRESS)
+		stat->attributes |= STATX_ATTR_COMPRESSED;
+	if (bi_flags & BTRFS_INODE_IMMUTABLE)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+	if (bi_flags & BTRFS_INODE_NODUMP)
+		stat->attributes |= STATX_ATTR_NODUMP;
+
+	stat->attributes_mask |= (STATX_ATTR_APPEND |
+				  STATX_ATTR_COMPRESSED |
+				  STATX_ATTR_IMMUTABLE |
+				  STATX_ATTR_NODUMP);
 
 	generic_fillattr(inode, stat);
 	stat->dev = BTRFS_I(inode)->root->anon_dev;
 
 	spin_lock(&BTRFS_I(inode)->lock);
-	delalloc_bytes = BTRFS_I(inode)->delalloc_bytes;
+	delalloc_bytes = BTRFS_I(inode)->new_delalloc_bytes;
 	spin_unlock(&BTRFS_I(inode)->lock);
 	stat->blocks = (ALIGN(inode_get_bytes(inode), blocksize) +
 			ALIGN(delalloc_bytes, blocksize)) >> 9;
@@ -9513,8 +9609,8 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	struct inode *old_inode = old_dentry->d_inode;
 	struct timespec ctime = current_time(old_inode);
 	struct dentry *parent;
-	u64 old_ino = btrfs_ino(old_inode);
-	u64 new_ino = btrfs_ino(new_inode);
+	u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
+	u64 new_ino = btrfs_ino(BTRFS_I(new_inode));
 	u64 old_idx = 0;
 	u64 new_idx = 0;
 	u64 root_objectid;
@@ -9550,10 +9646,10 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	 * We need to find a free sequence number both in the source and
 	 * in the destination directory for the exchange.
 	 */
-	ret = btrfs_set_inode_index(new_dir, &old_idx);
+	ret = btrfs_set_inode_index(BTRFS_I(new_dir), &old_idx);
 	if (ret)
 		goto out_fail;
-	ret = btrfs_set_inode_index(old_dir, &new_idx);
+	ret = btrfs_set_inode_index(BTRFS_I(old_dir), &new_idx);
 	if (ret)
 		goto out_fail;
 
@@ -9571,7 +9667,8 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 					     new_dentry->d_name.name,
 					     new_dentry->d_name.len,
 					     old_ino,
-					     btrfs_ino(new_dir), old_idx);
+					     btrfs_ino(BTRFS_I(new_dir)),
+					     old_idx);
 		if (ret)
 			goto out_fail;
 	}
@@ -9587,7 +9684,8 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 					     old_dentry->d_name.name,
 					     old_dentry->d_name.len,
 					     new_ino,
-					     btrfs_ino(old_dir), new_idx);
+					     btrfs_ino(BTRFS_I(old_dir)),
+					     new_idx);
 		if (ret)
 			goto out_fail;
 	}
@@ -9603,8 +9701,10 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 	new_inode->i_ctime = ctime;
 
 	if (old_dentry->d_parent != new_dentry->d_parent) {
-		btrfs_record_unlink_dir(trans, old_dir, old_inode, 1);
-		btrfs_record_unlink_dir(trans, new_dir, new_inode, 1);
+		btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
+				BTRFS_I(old_inode), 1);
+		btrfs_record_unlink_dir(trans, BTRFS_I(new_dir),
+				BTRFS_I(new_inode), 1);
 	}
 
 	/* src is a subvolume */
@@ -9615,8 +9715,8 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 					  old_dentry->d_name.name,
 					  old_dentry->d_name.len);
 	} else { /* src is an inode */
-		ret = __btrfs_unlink_inode(trans, root, old_dir,
-					   old_dentry->d_inode,
+		ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir),
+					   BTRFS_I(old_dentry->d_inode),
 					   old_dentry->d_name.name,
 					   old_dentry->d_name.len);
 		if (!ret)
@@ -9635,8 +9735,8 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 					  new_dentry->d_name.name,
 					  new_dentry->d_name.len);
 	} else { /* dest is an inode */
-		ret = __btrfs_unlink_inode(trans, dest, new_dir,
-					   new_dentry->d_inode,
+		ret = __btrfs_unlink_inode(trans, dest, BTRFS_I(new_dir),
+					   BTRFS_I(new_dentry->d_inode),
 					   new_dentry->d_name.name,
 					   new_dentry->d_name.len);
 		if (!ret)
@@ -9647,7 +9747,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		goto out_fail;
 	}
 
-	ret = btrfs_add_link(trans, new_dir, old_inode,
+	ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode),
 			     new_dentry->d_name.name,
 			     new_dentry->d_name.len, 0, old_idx);
 	if (ret) {
@@ -9655,7 +9755,7 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 		goto out_fail;
 	}
 
-	ret = btrfs_add_link(trans, old_dir, new_inode,
+	ret = btrfs_add_link(trans, BTRFS_I(old_dir), BTRFS_I(new_inode),
 			     old_dentry->d_name.name,
 			     old_dentry->d_name.len, 0, new_idx);
 	if (ret) {
@@ -9670,13 +9770,15 @@ static int btrfs_rename_exchange(struct inode *old_dir,
 
 	if (root_log_pinned) {
 		parent = new_dentry->d_parent;
-		btrfs_log_new_name(trans, old_inode, old_dir, parent);
+		btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir),
+				parent);
 		btrfs_end_log_trans(root);
 		root_log_pinned = false;
 	}
 	if (dest_log_pinned) {
 		parent = old_dentry->d_parent;
-		btrfs_log_new_name(trans, new_inode, new_dir, parent);
+		btrfs_log_new_name(trans, BTRFS_I(new_inode), BTRFS_I(new_dir),
+				parent);
 		btrfs_end_log_trans(dest);
 		dest_log_pinned = false;
 	}
@@ -9693,11 +9795,11 @@ out_fail:
 	 * allow the tasks to sync it.
 	 */
 	if (ret && (root_log_pinned || dest_log_pinned)) {
-		if (btrfs_inode_in_log(old_dir, fs_info->generation) ||
-		    btrfs_inode_in_log(new_dir, fs_info->generation) ||
-		    btrfs_inode_in_log(old_inode, fs_info->generation) ||
+		if (btrfs_inode_in_log(BTRFS_I(old_dir), fs_info->generation) ||
+		    btrfs_inode_in_log(BTRFS_I(new_dir), fs_info->generation) ||
+		    btrfs_inode_in_log(BTRFS_I(old_inode), fs_info->generation) ||
 		    (new_inode &&
-		     btrfs_inode_in_log(new_inode, fs_info->generation)))
+		     btrfs_inode_in_log(BTRFS_I(new_inode), fs_info->generation)))
 			btrfs_set_log_full_commit(fs_info, trans);
 
 		if (root_log_pinned) {
@@ -9736,7 +9838,7 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans,
 	inode = btrfs_new_inode(trans, root, dir,
 				dentry->d_name.name,
 				dentry->d_name.len,
-				btrfs_ino(dir),
+				btrfs_ino(BTRFS_I(dir)),
 				objectid,
 				S_IFCHR | WHITEOUT_MODE,
 				&index);
@@ -9755,8 +9857,8 @@ static int btrfs_whiteout_for_rename(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out;
 
-	ret = btrfs_add_nondir(trans, dir, dentry,
-				inode, 0, index);
+	ret = btrfs_add_nondir(trans, BTRFS_I(dir), dentry,
+				BTRFS_I(inode), 0, index);
 	if (ret)
 		goto out;
 
@@ -9784,10 +9886,10 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	u64 index = 0;
 	u64 root_objectid;
 	int ret;
-	u64 old_ino = btrfs_ino(old_inode);
+	u64 old_ino = btrfs_ino(BTRFS_I(old_inode));
 	bool log_pinned = false;
 
-	if (btrfs_ino(new_dir) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
+	if (btrfs_ino(BTRFS_I(new_dir)) == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)
 		return -EPERM;
 
 	/* we only allow rename subvolume link between subvolumes */
@@ -9795,7 +9897,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		return -EXDEV;
 
 	if (old_ino == BTRFS_EMPTY_SUBVOL_DIR_OBJECTID ||
-	    (new_inode && btrfs_ino(new_inode) == BTRFS_FIRST_FREE_OBJECTID))
+	    (new_inode && btrfs_ino(BTRFS_I(new_inode)) == BTRFS_FIRST_FREE_OBJECTID))
 		return -ENOTEMPTY;
 
 	if (S_ISDIR(old_inode->i_mode) && new_inode &&
@@ -9855,7 +9957,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (dest != root)
 		btrfs_record_root_in_trans(trans, dest);
 
-	ret = btrfs_set_inode_index(new_dir, &index);
+	ret = btrfs_set_inode_index(BTRFS_I(new_dir), &index);
 	if (ret)
 		goto out_fail;
 
@@ -9870,7 +9972,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 					     new_dentry->d_name.name,
 					     new_dentry->d_name.len,
 					     old_ino,
-					     btrfs_ino(new_dir), index);
+					     btrfs_ino(BTRFS_I(new_dir)), index);
 		if (ret)
 			goto out_fail;
 	}
@@ -9883,7 +9985,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	old_inode->i_ctime = current_time(old_dir);
 
 	if (old_dentry->d_parent != new_dentry->d_parent)
-		btrfs_record_unlink_dir(trans, old_dir, old_inode, 1);
+		btrfs_record_unlink_dir(trans, BTRFS_I(old_dir),
+				BTRFS_I(old_inode), 1);
 
 	if (unlikely(old_ino == BTRFS_FIRST_FREE_OBJECTID)) {
 		root_objectid = BTRFS_I(old_inode)->root->root_key.objectid;
@@ -9891,8 +9994,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 					old_dentry->d_name.name,
 					old_dentry->d_name.len);
 	} else {
-		ret = __btrfs_unlink_inode(trans, root, old_dir,
-					d_inode(old_dentry),
+		ret = __btrfs_unlink_inode(trans, root, BTRFS_I(old_dir),
+					BTRFS_I(d_inode(old_dentry)),
 					old_dentry->d_name.name,
 					old_dentry->d_name.len);
 		if (!ret)
@@ -9906,7 +10009,7 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (new_inode) {
 		inode_inc_iversion(new_inode);
 		new_inode->i_ctime = current_time(new_inode);
-		if (unlikely(btrfs_ino(new_inode) ==
+		if (unlikely(btrfs_ino(BTRFS_I(new_inode)) ==
 			     BTRFS_EMPTY_SUBVOL_DIR_OBJECTID)) {
 			root_objectid = BTRFS_I(new_inode)->location.objectid;
 			ret = btrfs_unlink_subvol(trans, dest, new_dir,
@@ -9915,20 +10018,21 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 						new_dentry->d_name.len);
 			BUG_ON(new_inode->i_nlink == 0);
 		} else {
-			ret = btrfs_unlink_inode(trans, dest, new_dir,
-						 d_inode(new_dentry),
+			ret = btrfs_unlink_inode(trans, dest, BTRFS_I(new_dir),
+						 BTRFS_I(d_inode(new_dentry)),
 						 new_dentry->d_name.name,
 						 new_dentry->d_name.len);
 		}
 		if (!ret && new_inode->i_nlink == 0)
-			ret = btrfs_orphan_add(trans, d_inode(new_dentry));
+			ret = btrfs_orphan_add(trans,
+					BTRFS_I(d_inode(new_dentry)));
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
 			goto out_fail;
 		}
 	}
 
-	ret = btrfs_add_link(trans, new_dir, old_inode,
+	ret = btrfs_add_link(trans, BTRFS_I(new_dir), BTRFS_I(old_inode),
 			     new_dentry->d_name.name,
 			     new_dentry->d_name.len, 0, index);
 	if (ret) {
@@ -9942,7 +10046,8 @@ static int btrfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (log_pinned) {
 		struct dentry *parent = new_dentry->d_parent;
 
-		btrfs_log_new_name(trans, old_inode, old_dir, parent);
+		btrfs_log_new_name(trans, BTRFS_I(old_inode), BTRFS_I(old_dir),
+				parent);
 		btrfs_end_log_trans(root);
 		log_pinned = false;
 	}
@@ -9969,11 +10074,11 @@ out_fail:
 	 * allow the tasks to sync it.
 	 */
 	if (ret && log_pinned) {
-		if (btrfs_inode_in_log(old_dir, fs_info->generation) ||
-		    btrfs_inode_in_log(new_dir, fs_info->generation) ||
-		    btrfs_inode_in_log(old_inode, fs_info->generation) ||
+		if (btrfs_inode_in_log(BTRFS_I(old_dir), fs_info->generation) ||
+		    btrfs_inode_in_log(BTRFS_I(new_dir), fs_info->generation) ||
+		    btrfs_inode_in_log(BTRFS_I(old_inode), fs_info->generation) ||
 		    (new_inode &&
-		     btrfs_inode_in_log(new_inode, fs_info->generation)))
+		     btrfs_inode_in_log(BTRFS_I(new_inode), fs_info->generation)))
 			btrfs_set_log_full_commit(fs_info, trans);
 
 		btrfs_end_log_trans(root);
@@ -10237,8 +10342,8 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 		goto out_unlock;
 
 	inode = btrfs_new_inode(trans, root, dir, dentry->d_name.name,
-				dentry->d_name.len, btrfs_ino(dir), objectid,
-				S_IFLNK|S_IRWXUGO, &index);
+				dentry->d_name.len, btrfs_ino(BTRFS_I(dir)),
+				objectid, S_IFLNK|S_IRWXUGO, &index);
 	if (IS_ERR(inode)) {
 		err = PTR_ERR(inode);
 		goto out_unlock;
@@ -10264,7 +10369,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 		err = -ENOMEM;
 		goto out_unlock_inode;
 	}
-	key.objectid = btrfs_ino(inode);
+	key.objectid = btrfs_ino(BTRFS_I(inode));
 	key.offset = 0;
 	key.type = BTRFS_EXTENT_DATA_KEY;
 	datasize = btrfs_file_extent_calc_inline_size(name_len);
@@ -10294,7 +10399,7 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &btrfs_symlink_aops;
 	inode_set_bytes(inode, name_len);
-	btrfs_i_size_write(inode, name_len);
+	btrfs_i_size_write(BTRFS_I(inode), name_len);
 	err = btrfs_update_inode(trans, root, inode);
 	/*
 	 * Last step, add directory indexes for our symlink inode. This is the
@@ -10302,7 +10407,8 @@ static int btrfs_symlink(struct inode *dir, struct dentry *dentry,
 	 * elsewhere above.
 	 */
 	if (!err)
-		err = btrfs_add_nondir(trans, dir, dentry, inode, 0, index);
+		err = btrfs_add_nondir(trans, BTRFS_I(dir), dentry,
+				BTRFS_I(inode), 0, index);
 	if (err) {
 		drop_inode = 1;
 		goto out_unlock_inode;
@@ -10388,7 +10494,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 			break;
 		}
 
-		btrfs_drop_extent_cache(inode, cur_offset,
+		btrfs_drop_extent_cache(BTRFS_I(inode), cur_offset,
 					cur_offset + ins.offset -1, 0);
 
 		em = alloc_extent_map();
@@ -10415,7 +10521,7 @@ static int __btrfs_prealloc_file_range(struct inode *inode, int mode,
 			write_unlock(&em_tree->lock);
 			if (ret != -EEXIST)
 				break;
-			btrfs_drop_extent_cache(inode, cur_offset,
+			btrfs_drop_extent_cache(BTRFS_I(inode), cur_offset,
 						cur_offset + ins.offset - 1,
 						0);
 		}
@@ -10452,7 +10558,7 @@ next:
 			btrfs_end_transaction(trans);
 	}
 	if (cur_offset < end)
-		btrfs_free_reserved_data_space(inode, cur_offset,
+		btrfs_free_reserved_data_space(inode, NULL, cur_offset,
 			end - cur_offset + 1);
 	return ret;
 }
@@ -10517,7 +10623,7 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 		goto out;
 
 	inode = btrfs_new_inode(trans, root, dir, NULL, 0,
-				btrfs_ino(dir), objectid, mode, &index);
+			btrfs_ino(BTRFS_I(dir)), objectid, mode, &index);
 	if (IS_ERR(inode)) {
 		ret = PTR_ERR(inode);
 		inode = NULL;
@@ -10537,7 +10643,7 @@ static int btrfs_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode)
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret)
 		goto out_inode;
-	ret = btrfs_orphan_add(trans, inode);
+	ret = btrfs_orphan_add(trans, BTRFS_I(inode));
 	if (ret)
 		goto out_inode;
 
@@ -10567,6 +10673,48 @@ out_inode:
 
 }
 
+__attribute__((const))
+static int btrfs_readpage_io_failed_hook(struct page *page, int failed_mirror)
+{
+	return -EAGAIN;
+}
+
+static struct btrfs_fs_info *iotree_fs_info(void *private_data)
+{
+	struct inode *inode = private_data;
+	return btrfs_sb(inode->i_sb);
+}
+
+static void btrfs_check_extent_io_range(void *private_data, const char *caller,
+					u64 start, u64 end)
+{
+	struct inode *inode = private_data;
+	u64 isize;
+
+	isize = i_size_read(inode);
+	if (end >= PAGE_SIZE && (end % 2) == 0 && end != isize - 1) {
+		btrfs_debug_rl(BTRFS_I(inode)->root->fs_info,
+		    "%s: ino %llu isize %llu odd range [%llu,%llu]",
+			caller, btrfs_ino(BTRFS_I(inode)), isize, start, end);
+	}
+}
+
+void btrfs_set_range_writeback(void *private_data, u64 start, u64 end)
+{
+	struct inode *inode = private_data;
+	unsigned long index = start >> PAGE_SHIFT;
+	unsigned long end_index = end >> PAGE_SHIFT;
+	struct page *page;
+
+	while (index <= end_index) {
+		page = find_get_page(inode->i_mapping, index);
+		ASSERT(page); /* Pages should be in the extent_io_tree */
+		set_page_writeback(page);
+		put_page(page);
+		index++;
+	}
+}
+
 static const struct inode_operations btrfs_dir_inode_operations = {
 	.getattr	= btrfs_getattr,
 	.lookup		= btrfs_lookup,
@@ -10605,16 +10753,23 @@ static const struct file_operations btrfs_dir_file_operations = {
 };
 
 static const struct extent_io_ops btrfs_extent_io_ops = {
-	.fill_delalloc = run_delalloc_range,
+	/* mandatory callbacks */
 	.submit_bio_hook = btrfs_submit_bio_hook,
-	.merge_bio_hook = btrfs_merge_bio_hook,
 	.readpage_end_io_hook = btrfs_readpage_end_io_hook,
+	.merge_bio_hook = btrfs_merge_bio_hook,
+	.readpage_io_failed_hook = btrfs_readpage_io_failed_hook,
+	.tree_fs_info = iotree_fs_info,
+	.set_range_writeback = btrfs_set_range_writeback,
+
+	/* optional callbacks */
+	.fill_delalloc = run_delalloc_range,
 	.writepage_end_io_hook = btrfs_writepage_end_io_hook,
 	.writepage_start_hook = btrfs_writepage_start_hook,
 	.set_bit_hook = btrfs_set_bit_hook,
 	.clear_bit_hook = btrfs_clear_bit_hook,
 	.merge_extent_hook = btrfs_merge_extent_hook,
 	.split_extent_hook = btrfs_split_extent_hook,
+	.check_extent_io_range = btrfs_check_extent_io_range,
 };
 
 /*
diff --git a/fs/btrfs/ioctl.c b/fs/btrfs/ioctl.c
index 33f967d30b2a..fa1b78cf25f6 100644
--- a/fs/btrfs/ioctl.c
+++ b/fs/btrfs/ioctl.c
@@ -37,7 +37,7 @@
 #include <linux/bit_spinlock.h>
 #include <linux/security.h>
 #include <linux/xattr.h>
-#include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include <linux/slab.h>
 #include <linux/blkdev.h>
 #include <linux/uuid.h>
@@ -395,7 +395,7 @@ static noinline int btrfs_ioctl_fitrim(struct file *file, void __user *arg)
 		q = bdev_get_queue(device->bdev);
 		if (blk_queue_discard(q)) {
 			num_devices++;
-			minlen = min((u64)q->limits.discard_granularity,
+			minlen = min_t(u64, q->limits.discard_granularity,
 				     minlen);
 		}
 	}
@@ -434,7 +434,7 @@ int btrfs_is_empty_uuid(u8 *uuid)
 
 static noinline int create_subvol(struct inode *dir,
 				  struct dentry *dentry,
-				  char *name, int namelen,
+				  const char *name, int namelen,
 				  u64 *async_transid,
 				  struct btrfs_qgroup_inherit *inherit)
 {
@@ -487,8 +487,7 @@ static noinline int create_subvol(struct inode *dir,
 	trans = btrfs_start_transaction(root, 0);
 	if (IS_ERR(trans)) {
 		ret = PTR_ERR(trans);
-		btrfs_subvolume_release_metadata(fs_info, &block_rsv,
-						 qgroup_reserved);
+		btrfs_subvolume_release_metadata(fs_info, &block_rsv);
 		goto fail_free;
 	}
 	trans->block_rsv = &block_rsv;
@@ -581,27 +580,27 @@ static noinline int create_subvol(struct inode *dir,
 	/*
 	 * insert the directory item
 	 */
-	ret = btrfs_set_inode_index(dir, &index);
+	ret = btrfs_set_inode_index(BTRFS_I(dir), &index);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 
 	ret = btrfs_insert_dir_item(trans, root,
-				    name, namelen, dir, &key,
+				    name, namelen, BTRFS_I(dir), &key,
 				    BTRFS_FT_DIR, index);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
 		goto fail;
 	}
 
-	btrfs_i_size_write(dir, dir->i_size + namelen * 2);
+	btrfs_i_size_write(BTRFS_I(dir), dir->i_size + namelen * 2);
 	ret = btrfs_update_inode(trans, root, dir);
 	BUG_ON(ret);
 
 	ret = btrfs_add_root_ref(trans, fs_info,
 				 objectid, root->root_key.objectid,
-				 btrfs_ino(dir), index, name, namelen);
+				 btrfs_ino(BTRFS_I(dir)), index, name, namelen);
 	BUG_ON(ret);
 
 	ret = btrfs_uuid_tree_add(trans, fs_info, root_item->uuid,
@@ -613,7 +612,7 @@ fail:
 	kfree(root_item);
 	trans->block_rsv = NULL;
 	trans->bytes_reserved = 0;
-	btrfs_subvolume_release_metadata(fs_info, &block_rsv, qgroup_reserved);
+	btrfs_subvolume_release_metadata(fs_info, &block_rsv);
 
 	if (async_transid) {
 		*async_transid = trans->transid;
@@ -657,7 +656,7 @@ static void btrfs_wait_for_no_snapshoting_writes(struct btrfs_root *root)
 }
 
 static int create_snapshot(struct btrfs_root *root, struct inode *dir,
-			   struct dentry *dentry, char *name, int namelen,
+			   struct dentry *dentry,
 			   u64 *async_transid, bool readonly,
 			   struct btrfs_qgroup_inherit *inherit)
 {
@@ -670,12 +669,12 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	if (!test_bit(BTRFS_ROOT_REF_COWS, &root->state))
 		return -EINVAL;
 
-	pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_NOFS);
+	pending_snapshot = kzalloc(sizeof(*pending_snapshot), GFP_KERNEL);
 	if (!pending_snapshot)
 		return -ENOMEM;
 
 	pending_snapshot->root_item = kzalloc(sizeof(struct btrfs_root_item),
-			GFP_NOFS);
+			GFP_KERNEL);
 	pending_snapshot->path = btrfs_alloc_path();
 	if (!pending_snapshot->root_item || !pending_snapshot->path) {
 		ret = -ENOMEM;
@@ -690,7 +689,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	if (ret)
 		goto dec_and_free;
 
-	btrfs_wait_ordered_extents(root, -1, 0, (u64)-1);
+	btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1);
 
 	btrfs_init_block_rsv(&pending_snapshot->block_rsv,
 			     BTRFS_BLOCK_RSV_TEMP);
@@ -753,9 +752,7 @@ static int create_snapshot(struct btrfs_root *root, struct inode *dir,
 	d_instantiate(dentry, inode);
 	ret = 0;
 fail:
-	btrfs_subvolume_release_metadata(fs_info,
-					 &pending_snapshot->block_rsv,
-					 pending_snapshot->qgroup_reserved);
+	btrfs_subvolume_release_metadata(fs_info, &pending_snapshot->block_rsv);
 dec_and_free:
 	if (atomic_dec_and_test(&root->will_be_snapshoted))
 		wake_up_atomic_t(&root->will_be_snapshoted);
@@ -835,7 +832,7 @@ static inline int btrfs_may_create(struct inode *dir, struct dentry *child)
  * inside this filesystem so it's quite a bit simpler.
  */
 static noinline int btrfs_mksubvol(const struct path *parent,
-				   char *name, int namelen,
+				   const char *name, int namelen,
 				   struct btrfs_root *snap_src,
 				   u64 *async_transid, bool readonly,
 				   struct btrfs_qgroup_inherit *inherit)
@@ -874,7 +871,7 @@ static noinline int btrfs_mksubvol(const struct path *parent,
 		goto out_up_read;
 
 	if (snap_src) {
-		error = create_snapshot(snap_src, dir, dentry, name, namelen,
+		error = create_snapshot(snap_src, dir, dentry,
 					async_transid, readonly, inherit);
 	} else {
 		error = create_subvol(dir, dentry, name, namelen,
@@ -941,7 +938,7 @@ static int find_new_extents(struct btrfs_root *root,
 	struct btrfs_file_extent_item *extent;
 	int type;
 	int ret;
-	u64 ino = btrfs_ino(inode);
+	u64 ino = btrfs_ino(BTRFS_I(inode));
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -1012,7 +1009,7 @@ static struct extent_map *defrag_lookup_extent(struct inode *inode, u64 start)
 
 		/* get the big lock and read metadata off disk */
 		lock_extent_bits(io_tree, start, end, &cached);
-		em = btrfs_get_extent(inode, NULL, 0, start, len, 0);
+		em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, start, len, 0);
 		unlock_extent_cached(io_tree, start, end, &cached, GFP_NOFS);
 
 		if (IS_ERR(em))
@@ -1130,6 +1127,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 	struct btrfs_ordered_extent *ordered;
 	struct extent_state *cached_state = NULL;
 	struct extent_io_tree *tree;
+	struct extent_changeset *data_reserved = NULL;
 	gfp_t mask = btrfs_alloc_write_mask(inode->i_mapping);
 
 	file_end = (isize - 1) >> PAGE_SHIFT;
@@ -1138,7 +1136,7 @@ static int cluster_pages_for_defrag(struct inode *inode,
 
 	page_cnt = min_t(u64, (u64)num_pages, (u64)file_end - start_index + 1);
 
-	ret = btrfs_delalloc_reserve_space(inode,
+	ret = btrfs_delalloc_reserve_space(inode, &data_reserved,
 			start_index << PAGE_SHIFT,
 			page_cnt << PAGE_SHIFT);
 	if (ret)
@@ -1229,7 +1227,7 @@ again:
 		spin_lock(&BTRFS_I(inode)->lock);
 		BTRFS_I(inode)->outstanding_extents++;
 		spin_unlock(&BTRFS_I(inode)->lock);
-		btrfs_delalloc_release_space(inode,
+		btrfs_delalloc_release_space(inode, data_reserved,
 				start_index << PAGE_SHIFT,
 				(page_cnt - i_done) << PAGE_SHIFT);
 	}
@@ -1250,15 +1248,17 @@ again:
 		unlock_page(pages[i]);
 		put_page(pages[i]);
 	}
+	extent_changeset_free(data_reserved);
 	return i_done;
 out:
 	for (i = 0; i < i_done; i++) {
 		unlock_page(pages[i]);
 		put_page(pages[i]);
 	}
-	btrfs_delalloc_release_space(inode,
+	btrfs_delalloc_release_space(inode, data_reserved,
 			start_index << PAGE_SHIFT,
 			page_cnt << PAGE_SHIFT);
+	extent_changeset_free(data_reserved);
 	return ret;
 
 }
@@ -1507,7 +1507,7 @@ static noinline int btrfs_ioctl_resize(struct file *file,
 	if (ret)
 		return ret;
 
-	if (atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1)) {
+	if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
 		mnt_drop_write_file(file);
 		return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
 	}
@@ -1622,13 +1622,13 @@ out_free:
 	kfree(vol_args);
 out:
 	mutex_unlock(&fs_info->volume_mutex);
-	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 	mnt_drop_write_file(file);
 	return ret;
 }
 
 static noinline int btrfs_ioctl_snap_create_transid(struct file *file,
-				char *name, unsigned long fd, int subvol,
+				const char *name, unsigned long fd, int subvol,
 				u64 *transid, bool readonly,
 				struct btrfs_qgroup_inherit *inherit)
 {
@@ -1780,7 +1780,7 @@ static noinline int btrfs_ioctl_subvol_getflags(struct file *file,
 	int ret = 0;
 	u64 flags = 0;
 
-	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID)
+	if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID)
 		return -EINVAL;
 
 	down_read(&fs_info->subvol_sem);
@@ -1812,7 +1812,7 @@ static noinline int btrfs_ioctl_subvol_setflags(struct file *file,
 	if (ret)
 		goto out;
 
-	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
+	if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID) {
 		ret = -EINVAL;
 		goto out_drop_write;
 	}
@@ -2446,7 +2446,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	if (err)
 		goto out_dput;
 
-	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
+	if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID) {
 		err = -EINVAL;
 		goto out_dput;
 	}
@@ -2497,7 +2497,7 @@ static noinline int btrfs_ioctl_snap_destroy(struct file *file,
 	trans->block_rsv = &block_rsv;
 	trans->bytes_reserved = block_rsv.size;
 
-	btrfs_record_snapshot_destroy(trans, dir);
+	btrfs_record_snapshot_destroy(trans, BTRFS_I(dir));
 
 	ret = btrfs_unlink_subvol(trans, root, dir,
 				dest->root_key.objectid,
@@ -2555,7 +2555,7 @@ out_end_trans:
 		err = ret;
 	inode->i_flags |= S_DEAD;
 out_release:
-	btrfs_subvolume_release_metadata(fs_info, &block_rsv, qgroup_reserved);
+	btrfs_subvolume_release_metadata(fs_info, &block_rsv);
 out_up_write:
 	up_write(&fs_info->subvol_sem);
 	if (err) {
@@ -2613,9 +2613,6 @@ static int btrfs_ioctl_defrag(struct file *file, void __user *argp)
 			goto out;
 		}
 		ret = btrfs_defrag_root(root);
-		if (ret)
-			goto out;
-		ret = btrfs_defrag_root(root->fs_info->extent_root);
 		break;
 	case S_IFREG:
 		if (!(file->f_mode & FMODE_WRITE)) {
@@ -2667,7 +2664,7 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1))
+	if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags))
 		return BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
 
 	mutex_lock(&fs_info->volume_mutex);
@@ -2686,7 +2683,7 @@ static long btrfs_ioctl_add_dev(struct btrfs_fs_info *fs_info, void __user *arg)
 	kfree(vol_args);
 out:
 	mutex_unlock(&fs_info->volume_mutex);
-	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 	return ret;
 }
 
@@ -2714,7 +2711,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 	if (vol_args->flags & ~BTRFS_VOL_ARG_V2_FLAGS_SUPPORTED)
 		return -EOPNOTSUPP;
 
-	if (atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1)) {
+	if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
 		ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
 		goto out;
 	}
@@ -2727,7 +2724,7 @@ static long btrfs_ioctl_rm_dev_v2(struct file *file, void __user *arg)
 		ret = btrfs_rm_device(fs_info, vol_args->name, 0);
 	}
 	mutex_unlock(&fs_info->volume_mutex);
-	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 
 	if (!ret) {
 		if (vol_args->flags & BTRFS_DEVICE_SPEC_BY_ID)
@@ -2758,7 +2755,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 	if (ret)
 		return ret;
 
-	if (atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1)) {
+	if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
 		ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
 		goto out_drop_write;
 	}
@@ -2778,7 +2775,7 @@ static long btrfs_ioctl_rm_dev(struct file *file, void __user *arg)
 		btrfs_info(fs_info, "disk deleted %s", vol_args->name);
 	kfree(vol_args);
 out:
-	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 out_drop_write:
 	mnt_drop_write_file(file);
 
@@ -3047,11 +3044,21 @@ static int btrfs_cmp_data_prepare(struct inode *src, u64 loff,
 	cmp->src_pages = src_pgarr;
 	cmp->dst_pages = dst_pgarr;
 
-	ret = gather_extent_pages(src, cmp->src_pages, cmp->num_pages, loff);
+	/*
+	 * If deduping ranges in the same inode, locking rules make it mandatory
+	 * to always lock pages in ascending order to avoid deadlocks with
+	 * concurrent tasks (such as starting writeback/delalloc).
+	 */
+	if (src == dst && dst_loff < loff) {
+		swap(src_pgarr, dst_pgarr);
+		swap(loff, dst_loff);
+	}
+
+	ret = gather_extent_pages(src, src_pgarr, cmp->num_pages, loff);
 	if (ret)
 		goto out;
 
-	ret = gather_extent_pages(dst, cmp->dst_pages, cmp->num_pages, dst_loff);
+	ret = gather_extent_pages(dst, dst_pgarr, cmp->num_pages, dst_loff);
 
 out:
 	if (ret)
@@ -3059,8 +3066,7 @@ out:
 	return 0;
 }
 
-static int btrfs_cmp_data(struct inode *src, u64 loff, struct inode *dst,
-			  u64 dst_loff, u64 len, struct cmp_pages *cmp)
+static int btrfs_cmp_data(u64 len, struct cmp_pages *cmp)
 {
 	int ret = 0;
 	int i;
@@ -3128,26 +3134,27 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 	int ret;
 	u64 len = olen;
 	struct cmp_pages cmp;
-	int same_inode = 0;
+	bool same_inode = (src == dst);
 	u64 same_lock_start = 0;
 	u64 same_lock_len = 0;
 
-	if (src == dst)
-		same_inode = 1;
-
 	if (len == 0)
 		return 0;
 
-	if (same_inode) {
+	if (same_inode)
 		inode_lock(src);
+	else
+		btrfs_double_inode_lock(src, dst);
 
-		ret = extent_same_check_offsets(src, loff, &len, olen);
-		if (ret)
-			goto out_unlock;
-		ret = extent_same_check_offsets(src, dst_loff, &len, olen);
-		if (ret)
-			goto out_unlock;
+	ret = extent_same_check_offsets(src, loff, &len, olen);
+	if (ret)
+		goto out_unlock;
 
+	ret = extent_same_check_offsets(dst, dst_loff, &len, olen);
+	if (ret)
+		goto out_unlock;
+
+	if (same_inode) {
 		/*
 		 * Single inode case wants the same checks, except we
 		 * don't want our length pushed out past i_size as
@@ -3175,16 +3182,6 @@ static int btrfs_extent_same(struct inode *src, u64 loff, u64 olen,
 
 		same_lock_start = min_t(u64, loff, dst_loff);
 		same_lock_len = max_t(u64, loff, dst_loff) + len - same_lock_start;
-	} else {
-		btrfs_double_inode_lock(src, dst);
-
-		ret = extent_same_check_offsets(src, loff, &len, olen);
-		if (ret)
-			goto out_unlock;
-
-		ret = extent_same_check_offsets(dst, dst_loff, &len, olen);
-		if (ret)
-			goto out_unlock;
 	}
 
 	/* don't make the dst file partly checksummed */
@@ -3236,7 +3233,7 @@ again:
 	}
 
 	/* pass original length for comparison so we stay within i_size */
-	ret = btrfs_cmp_data(src, loff, dst, dst_loff, olen, &cmp);
+	ret = btrfs_cmp_data(olen, &cmp);
 	if (ret == 0)
 		ret = btrfs_clone(src, dst, loff, olen, len, dst_loff, 1);
 
@@ -3304,7 +3301,7 @@ static int clone_finish_inode_update(struct btrfs_trans_handle *trans,
 	if (endoff > destoff + olen)
 		endoff = destoff + olen;
 	if (endoff > inode->i_size)
-		btrfs_i_size_write(inode, endoff);
+		btrfs_i_size_write(BTRFS_I(inode), endoff);
 
 	ret = btrfs_update_inode(trans, root, inode);
 	if (ret) {
@@ -3317,20 +3314,19 @@ out:
 	return ret;
 }
 
-static void clone_update_extent_map(struct inode *inode,
+static void clone_update_extent_map(struct btrfs_inode *inode,
 				    const struct btrfs_trans_handle *trans,
 				    const struct btrfs_path *path,
 				    const u64 hole_offset,
 				    const u64 hole_len)
 {
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	struct extent_map *em;
 	int ret;
 
 	em = alloc_extent_map();
 	if (!em) {
-		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-			&BTRFS_I(inode)->runtime_flags);
+		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags);
 		return;
 	}
 
@@ -3344,7 +3340,7 @@ static void clone_update_extent_map(struct inode *inode,
 		if (btrfs_file_extent_type(path->nodes[0], fi) ==
 		    BTRFS_FILE_EXTENT_INLINE)
 			set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-				&BTRFS_I(inode)->runtime_flags);
+					&inode->runtime_flags);
 	} else {
 		em->start = hole_offset;
 		em->len = hole_len;
@@ -3370,8 +3366,7 @@ static void clone_update_extent_map(struct inode *inode,
 	}
 
 	if (ret)
-		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-			&BTRFS_I(inode)->runtime_flags);
+		set_bit(BTRFS_INODE_NEEDS_FULL_SYNC, &inode->runtime_flags);
 }
 
 /*
@@ -3399,8 +3394,7 @@ static void clone_update_extent_map(struct inode *inode,
  * data into the destination inode's inline extent if the later is greater then
  * the former.
  */
-static int clone_copy_inline_extent(struct inode *src,
-				    struct inode *dst,
+static int clone_copy_inline_extent(struct inode *dst,
 				    struct btrfs_trans_handle *trans,
 				    struct btrfs_path *path,
 				    struct btrfs_key *new_key,
@@ -3420,7 +3414,7 @@ static int clone_copy_inline_extent(struct inode *src,
 	if (new_key->offset > 0)
 		return -EOPNOTSUPP;
 
-	key.objectid = btrfs_ino(dst);
+	key.objectid = btrfs_ino(BTRFS_I(dst));
 	key.type = BTRFS_EXTENT_DATA_KEY;
 	key.offset = 0;
 	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
@@ -3435,7 +3429,7 @@ static int clone_copy_inline_extent(struct inode *src,
 				goto copy_inline_extent;
 		}
 		btrfs_item_key_to_cpu(path->nodes[0], &key, path->slots[0]);
-		if (key.objectid == btrfs_ino(dst) &&
+		if (key.objectid == btrfs_ino(BTRFS_I(dst)) &&
 		    key.type == BTRFS_EXTENT_DATA_KEY) {
 			ASSERT(key.offset > 0);
 			return -EOPNOTSUPP;
@@ -3469,7 +3463,7 @@ static int clone_copy_inline_extent(struct inode *src,
 		} else if (ret == 0) {
 			btrfs_item_key_to_cpu(path->nodes[0], &key,
 					      path->slots[0]);
-			if (key.objectid == btrfs_ino(dst) &&
+			if (key.objectid == btrfs_ino(BTRFS_I(dst)) &&
 			    key.type == BTRFS_EXTENT_DATA_KEY)
 				return -EOPNOTSUPP;
 		}
@@ -3548,12 +3542,9 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 	u64 last_dest_end = destoff;
 
 	ret = -ENOMEM;
-	buf = kmalloc(fs_info->nodesize, GFP_KERNEL | __GFP_NOWARN);
-	if (!buf) {
-		buf = vmalloc(fs_info->nodesize);
-		if (!buf)
-			return ret;
-	}
+	buf = kvmalloc(fs_info->nodesize, GFP_KERNEL);
+	if (!buf)
+		return ret;
 
 	path = btrfs_alloc_path();
 	if (!path) {
@@ -3563,7 +3554,7 @@ static int btrfs_clone(struct inode *src, struct inode *inode,
 
 	path->reada = READA_FORWARD;
 	/* clone data */
-	key.objectid = btrfs_ino(src);
+	key.objectid = btrfs_ino(BTRFS_I(src));
 	key.type = BTRFS_EXTENT_DATA_KEY;
 	key.offset = off;
 
@@ -3606,7 +3597,7 @@ process_slot:
 
 		btrfs_item_key_to_cpu(leaf, &key, slot);
 		if (key.type > BTRFS_EXTENT_DATA_KEY ||
-		    key.objectid != btrfs_ino(src))
+		    key.objectid != btrfs_ino(BTRFS_I(src)))
 			break;
 
 		if (key.type == BTRFS_EXTENT_DATA_KEY) {
@@ -3659,7 +3650,7 @@ process_slot:
 			path->leave_spinning = 0;
 
 			memcpy(&new_key, &key, sizeof(new_key));
-			new_key.objectid = btrfs_ino(inode);
+			new_key.objectid = btrfs_ino(BTRFS_I(inode));
 			if (off <= key.offset)
 				new_key.offset = key.offset + destoff - off;
 			else
@@ -3749,7 +3740,7 @@ process_slot:
 							fs_info,
 							disko, diskl, 0,
 							root->root_key.objectid,
-							btrfs_ino(inode),
+							btrfs_ino(BTRFS_I(inode)),
 							new_key.offset - datao);
 					if (ret) {
 						btrfs_abort_transaction(trans,
@@ -3779,7 +3770,7 @@ process_slot:
 				size -= skip + trim;
 				datal -= skip + trim;
 
-				ret = clone_copy_inline_extent(src, inode,
+				ret = clone_copy_inline_extent(inode,
 							       trans, path,
 							       &new_key,
 							       drop_start,
@@ -3798,11 +3789,12 @@ process_slot:
 
 			/* If we have an implicit hole (NO_HOLES feature). */
 			if (drop_start < new_key.offset)
-				clone_update_extent_map(inode, trans,
+				clone_update_extent_map(BTRFS_I(inode), trans,
 						NULL, drop_start,
 						new_key.offset - drop_start);
 
-			clone_update_extent_map(inode, trans, path, 0, 0);
+			clone_update_extent_map(BTRFS_I(inode), trans,
+					path, 0, 0);
 
 			btrfs_mark_buffer_dirty(leaf);
 			btrfs_release_path(path);
@@ -3852,8 +3844,9 @@ process_slot:
 			btrfs_end_transaction(trans);
 			goto out;
 		}
-		clone_update_extent_map(inode, trans, NULL, last_dest_end,
-					destoff + len - last_dest_end);
+		clone_update_extent_map(BTRFS_I(inode), trans, NULL,
+				last_dest_end,
+				destoff + len - last_dest_end);
 		ret = clone_finish_inode_update(trans, inode, destoff + len,
 						destoff, olen, no_time_update);
 	}
@@ -4449,13 +4442,11 @@ static long btrfs_ioctl_dev_replace(struct btrfs_fs_info *fs_info,
 			ret = -EROFS;
 			goto out;
 		}
-		if (atomic_xchg(
-			&fs_info->mutually_exclusive_operation_running, 1)) {
+		if (test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
 			ret = BTRFS_ERROR_DEV_EXCL_RUN_IN_PROGRESS;
 		} else {
 			ret = btrfs_dev_replace_by_ioctl(fs_info, p);
-			atomic_set(
-			 &fs_info->mutually_exclusive_operation_running, 0);
+			clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 		}
 		break;
 	case BTRFS_IOCTL_DEV_REPLACE_CMD_STATUS:
@@ -4600,7 +4591,7 @@ static long btrfs_ioctl_logical_to_ino(struct btrfs_fs_info *fs_info,
 
 out:
 	btrfs_free_path(path);
-	vfree(inodes);
+	kvfree(inodes);
 	kfree(loi);
 
 	return ret;
@@ -4650,7 +4641,7 @@ static long btrfs_ioctl_balance(struct file *file, void __user *arg)
 		return ret;
 
 again:
-	if (!atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1)) {
+	if (!test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags)) {
 		mutex_lock(&fs_info->volume_mutex);
 		mutex_lock(&fs_info->balance_mutex);
 		need_unlock = true;
@@ -4696,7 +4687,7 @@ again:
 	}
 
 locked:
-	BUG_ON(!atomic_read(&fs_info->mutually_exclusive_operation_running));
+	BUG_ON(!test_bit(BTRFS_FS_EXCL_OP, &fs_info->flags));
 
 	if (arg) {
 		bargs = memdup_user(arg, sizeof(*bargs));
@@ -4752,11 +4743,10 @@ locked:
 
 do_balance:
 	/*
-	 * Ownership of bctl and mutually_exclusive_operation_running
+	 * Ownership of bctl and filesystem flag BTRFS_FS_EXCL_OP
 	 * goes to to btrfs_balance.  bctl is freed in __cancel_balance,
 	 * or, if restriper was paused all the way until unmount, in
-	 * free_fs_info.  mutually_exclusive_operation_running is
-	 * cleared in __cancel_balance.
+	 * free_fs_info.  The flag is cleared in __cancel_balance.
 	 */
 	need_unlock = false;
 
@@ -4776,7 +4766,7 @@ out_unlock:
 	mutex_unlock(&fs_info->balance_mutex);
 	mutex_unlock(&fs_info->volume_mutex);
 	if (need_unlock)
-		atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+		clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 out:
 	mnt_drop_write_file(file);
 	return ret;
@@ -4910,7 +4900,6 @@ static long btrfs_ioctl_qgroup_assign(struct file *file, void __user *arg)
 		goto out;
 	}
 
-	/* FIXME: check if the IDs really exist */
 	if (sa->assign) {
 		ret = btrfs_add_qgroup_relation(trans, fs_info,
 						sa->src, sa->dst);
@@ -4969,7 +4958,6 @@ static long btrfs_ioctl_qgroup_create(struct file *file, void __user *arg)
 		goto out;
 	}
 
-	/* FIXME: check if the IDs really exist */
 	if (sa->create) {
 		ret = btrfs_create_qgroup(trans, fs_info, sa->qgroupid);
 	} else {
@@ -5023,7 +5011,6 @@ static long btrfs_ioctl_qgroup_limit(struct file *file, void __user *arg)
 		qgroupid = root->root_key.objectid;
 	}
 
-	/* FIXME: check if the IDs really exist */
 	ret = btrfs_limit_qgroup(trans, fs_info, qgroupid, &sa->lim);
 
 	err = btrfs_end_transaction(trans);
@@ -5129,7 +5116,7 @@ static long _btrfs_ioctl_set_received_subvol(struct file *file,
 
 	down_write(&fs_info->subvol_sem);
 
-	if (btrfs_ino(inode) != BTRFS_FIRST_FREE_OBJECTID) {
+	if (btrfs_ino(BTRFS_I(inode)) != BTRFS_FIRST_FREE_OBJECTID) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -5653,6 +5640,10 @@ long btrfs_ioctl(struct file *file, unsigned int
 #ifdef CONFIG_COMPAT
 long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 {
+	/*
+	 * These all access 32-bit values anyway so no further
+	 * handling is necessary.
+	 */
 	switch (cmd) {
 	case FS_IOC32_GETFLAGS:
 		cmd = FS_IOC_GETFLAGS;
@@ -5663,8 +5654,6 @@ long btrfs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case FS_IOC32_GETVERSION:
 		cmd = FS_IOC_GETVERSION;
 		break;
-	default:
-		return -ENOIOCTLCMD;
 	}
 
 	return btrfs_ioctl(file, cmd, (unsigned long) compat_ptr(arg));
diff --git a/fs/btrfs/lzo.c b/fs/btrfs/lzo.c
index 45d26980caf9..d433e75d489a 100644
--- a/fs/btrfs/lzo.c
+++ b/fs/btrfs/lzo.c
@@ -18,13 +18,14 @@
 
 #include <linux/kernel.h>
 #include <linux/slab.h>
-#include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/pagemap.h>
 #include <linux/bio.h>
 #include <linux/lzo.h>
+#include <linux/refcount.h>
 #include "compression.h"
 
 #define LZO_LEN	4
@@ -40,9 +41,9 @@ static void lzo_free_workspace(struct list_head *ws)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 
-	vfree(workspace->buf);
-	vfree(workspace->cbuf);
-	vfree(workspace->mem);
+	kvfree(workspace->buf);
+	kvfree(workspace->cbuf);
+	kvfree(workspace->mem);
 	kfree(workspace);
 }
 
@@ -50,13 +51,13 @@ static struct list_head *lzo_alloc_workspace(void)
 {
 	struct workspace *workspace;
 
-	workspace = kzalloc(sizeof(*workspace), GFP_NOFS);
+	workspace = kzalloc(sizeof(*workspace), GFP_KERNEL);
 	if (!workspace)
 		return ERR_PTR(-ENOMEM);
 
-	workspace->mem = vmalloc(LZO1X_MEM_COMPRESS);
-	workspace->buf = vmalloc(lzo1x_worst_compress(PAGE_SIZE));
-	workspace->cbuf = vmalloc(lzo1x_worst_compress(PAGE_SIZE));
+	workspace->mem = kvmalloc(LZO1X_MEM_COMPRESS, GFP_KERNEL);
+	workspace->buf = kvmalloc(lzo1x_worst_compress(PAGE_SIZE), GFP_KERNEL);
+	workspace->cbuf = kvmalloc(lzo1x_worst_compress(PAGE_SIZE), GFP_KERNEL);
 	if (!workspace->mem || !workspace->buf || !workspace->cbuf)
 		goto fail;
 
@@ -76,7 +77,7 @@ static inline void write_compress_length(char *buf, size_t len)
 	memcpy(buf, &dlen, LZO_LEN);
 }
 
-static inline size_t read_compress_length(char *buf)
+static inline size_t read_compress_length(const char *buf)
 {
 	__le32 dlen;
 
@@ -86,13 +87,11 @@ static inline size_t read_compress_length(char *buf)
 
 static int lzo_compress_pages(struct list_head *ws,
 			      struct address_space *mapping,
-			      u64 start, unsigned long len,
+			      u64 start,
 			      struct page **pages,
-			      unsigned long nr_dest_pages,
 			      unsigned long *out_pages,
 			      unsigned long *total_in,
-			      unsigned long *total_out,
-			      unsigned long max_out)
+			      unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0;
@@ -102,7 +101,9 @@ static int lzo_compress_pages(struct list_head *ws,
 	struct page *in_page = NULL;
 	struct page *out_page = NULL;
 	unsigned long bytes_left;
-
+	unsigned long len = *total_out;
+	unsigned long nr_dest_pages = *out_pages;
+	const unsigned long max_out = nr_dest_pages * PAGE_SIZE;
 	size_t in_len;
 	size_t out_len;
 	char *buf;
@@ -141,7 +142,7 @@ static int lzo_compress_pages(struct list_head *ws,
 		ret = lzo1x_1_compress(data_in, in_len, workspace->cbuf,
 				       &out_len, workspace->mem);
 		if (ret != LZO_E_OK) {
-			pr_debug("BTRFS: deflate in loop returned %d\n",
+			pr_debug("BTRFS: lzo in loop returned %d\n",
 			       ret);
 			ret = -EIO;
 			goto out;
@@ -229,8 +230,10 @@ static int lzo_compress_pages(struct list_head *ws,
 		in_len = min(bytes_left, PAGE_SIZE);
 	}
 
-	if (tot_out > tot_in)
+	if (tot_out >= tot_in) {
+		ret = -E2BIG;
 		goto out;
+	}
 
 	/* store the size of all chunks of compressed data */
 	cpage_out = kmap(pages[0]);
@@ -254,16 +257,13 @@ out:
 	return ret;
 }
 
-static int lzo_decompress_bio(struct list_head *ws,
-				 struct page **pages_in,
-				 u64 disk_start,
-				 struct bio *orig_bio,
-				 size_t srclen)
+static int lzo_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0, ret2;
 	char *data_in;
 	unsigned long page_in_index = 0;
+	size_t srclen = cb->compressed_len;
 	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
 	unsigned long buf_start;
 	unsigned long buf_offset = 0;
@@ -278,6 +278,9 @@ static int lzo_decompress_bio(struct list_head *ws,
 	unsigned long tot_len;
 	char *buf;
 	bool may_late_unmap, need_unmap;
+	struct page **pages_in = cb->compressed_pages;
+	u64 disk_start = cb->start;
+	struct bio *orig_bio = cb->orig_bio;
 
 	data_in = kmap(pages_in[0]);
 	tot_len = read_compress_length(data_in);
diff --git a/fs/btrfs/ordered-data.c b/fs/btrfs/ordered-data.c
index 041c3326d109..a3aca495e33e 100644
--- a/fs/btrfs/ordered-data.c
+++ b/fs/btrfs/ordered-data.c
@@ -212,7 +212,7 @@ static int __btrfs_add_ordered_extent(struct inode *inode, u64 file_offset,
 		set_bit(BTRFS_ORDERED_DIRECT, &entry->flags);
 
 	/* one ref for the tree */
-	atomic_set(&entry->refs, 1);
+	refcount_set(&entry->refs, 1);
 	init_waitqueue_head(&entry->wait);
 	INIT_LIST_HEAD(&entry->list);
 	INIT_LIST_HEAD(&entry->root_extent_list);
@@ -358,7 +358,7 @@ int btrfs_dec_test_first_ordered_pending(struct inode *inode,
 out:
 	if (!ret && cached && entry) {
 		*cached = entry;
-		atomic_inc(&entry->refs);
+		refcount_inc(&entry->refs);
 	}
 	spin_unlock_irqrestore(&tree->lock, flags);
 	return ret == 0;
@@ -425,14 +425,14 @@ have_entry:
 out:
 	if (!ret && cached && entry) {
 		*cached = entry;
-		atomic_inc(&entry->refs);
+		refcount_inc(&entry->refs);
 	}
 	spin_unlock_irqrestore(&tree->lock, flags);
 	return ret == 0;
 }
 
 /* Needs to either be called under a log transaction or the log_mutex */
-void btrfs_get_logged_extents(struct inode *inode,
+void btrfs_get_logged_extents(struct btrfs_inode *inode,
 			      struct list_head *logged_list,
 			      const loff_t start,
 			      const loff_t end)
@@ -442,7 +442,7 @@ void btrfs_get_logged_extents(struct inode *inode,
 	struct rb_node *n;
 	struct rb_node *prev;
 
-	tree = &BTRFS_I(inode)->ordered_tree;
+	tree = &inode->ordered_tree;
 	spin_lock_irq(&tree->lock);
 	n = __tree_search(&tree->tree, end, &prev);
 	if (!n)
@@ -456,7 +456,7 @@ void btrfs_get_logged_extents(struct inode *inode,
 		if (test_and_set_bit(BTRFS_ORDERED_LOGGED, &ordered->flags))
 			continue;
 		list_add(&ordered->log_list, logged_list);
-		atomic_inc(&ordered->refs);
+		refcount_inc(&ordered->refs);
 	}
 	spin_unlock_irq(&tree->lock);
 }
@@ -565,7 +565,7 @@ void btrfs_put_ordered_extent(struct btrfs_ordered_extent *entry)
 
 	trace_btrfs_ordered_extent_put(entry->inode, entry);
 
-	if (atomic_dec_and_test(&entry->refs)) {
+	if (refcount_dec_and_test(&entry->refs)) {
 		ASSERT(list_empty(&entry->log_list));
 		ASSERT(list_empty(&entry->trans_list));
 		ASSERT(list_empty(&entry->root_extent_list));
@@ -623,7 +623,7 @@ void btrfs_remove_ordered_extent(struct inode *inode,
 		spin_lock(&fs_info->trans_lock);
 		trans = fs_info->running_transaction;
 		if (trans)
-			atomic_inc(&trans->use_count);
+			refcount_inc(&trans->use_count);
 		spin_unlock(&fs_info->trans_lock);
 
 		ASSERT(trans);
@@ -663,7 +663,7 @@ static void btrfs_run_ordered_extent_work(struct btrfs_work *work)
  * wait for all the ordered extents in a root.  This is done when balancing
  * space between drives.
  */
-int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
+u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 			       const u64 range_start, const u64 range_len)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -671,7 +671,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
 	LIST_HEAD(skipped);
 	LIST_HEAD(works);
 	struct btrfs_ordered_extent *ordered, *next;
-	int count = 0;
+	u64 count = 0;
 	const u64 range_end = range_start + range_len;
 
 	mutex_lock(&root->ordered_extent_mutex);
@@ -690,7 +690,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
 
 		list_move_tail(&ordered->root_extent_list,
 			       &root->ordered_extents);
-		atomic_inc(&ordered->refs);
+		refcount_inc(&ordered->refs);
 		spin_unlock(&root->ordered_extent_lock);
 
 		btrfs_init_work(&ordered->flush_work,
@@ -701,7 +701,7 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
 
 		cond_resched();
 		spin_lock(&root->ordered_extent_lock);
-		if (nr != -1)
+		if (nr != U64_MAX)
 			nr--;
 		count++;
 	}
@@ -720,13 +720,13 @@ int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
 	return count;
 }
 
-int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
-			      const u64 range_start, const u64 range_len)
+u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
+			     const u64 range_start, const u64 range_len)
 {
 	struct btrfs_root *root;
 	struct list_head splice;
-	int done;
-	int total_done = 0;
+	u64 total_done = 0;
+	u64 done;
 
 	INIT_LIST_HEAD(&splice);
 
@@ -748,9 +748,8 @@ int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
 		total_done += done;
 
 		spin_lock(&fs_info->ordered_root_lock);
-		if (nr != -1) {
+		if (nr != U64_MAX) {
 			nr -= done;
-			WARN_ON(nr < 0);
 		}
 	}
 	list_splice_tail(&splice, &fs_info->ordered_roots);
@@ -870,7 +869,7 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_extent(struct inode *inode,
 	if (!offset_in_entry(entry, file_offset))
 		entry = NULL;
 	if (entry)
-		atomic_inc(&entry->refs);
+		refcount_inc(&entry->refs);
 out:
 	spin_unlock_irq(&tree->lock);
 	return entry;
@@ -879,15 +878,14 @@ out:
 /* Since the DIO code tries to lock a wide area we need to look for any ordered
  * extents that exist in the range, rather than just the start of the range.
  */
-struct btrfs_ordered_extent *btrfs_lookup_ordered_range(struct inode *inode,
-							u64 file_offset,
-							u64 len)
+struct btrfs_ordered_extent *btrfs_lookup_ordered_range(
+		struct btrfs_inode *inode, u64 file_offset, u64 len)
 {
 	struct btrfs_ordered_inode_tree *tree;
 	struct rb_node *node;
 	struct btrfs_ordered_extent *entry = NULL;
 
-	tree = &BTRFS_I(inode)->ordered_tree;
+	tree = &inode->ordered_tree;
 	spin_lock_irq(&tree->lock);
 	node = tree_search(tree, file_offset);
 	if (!node) {
@@ -912,7 +910,7 @@ struct btrfs_ordered_extent *btrfs_lookup_ordered_range(struct inode *inode,
 	}
 out:
 	if (entry)
-		atomic_inc(&entry->refs);
+		refcount_inc(&entry->refs);
 	spin_unlock_irq(&tree->lock);
 	return entry;
 }
@@ -923,7 +921,7 @@ bool btrfs_have_ordered_extents_in_range(struct inode *inode,
 {
 	struct btrfs_ordered_extent *oe;
 
-	oe = btrfs_lookup_ordered_range(inode, file_offset, len);
+	oe = btrfs_lookup_ordered_range(BTRFS_I(inode), file_offset, len);
 	if (oe) {
 		btrfs_put_ordered_extent(oe);
 		return true;
@@ -949,7 +947,7 @@ btrfs_lookup_first_ordered_extent(struct inode *inode, u64 file_offset)
 		goto out;
 
 	entry = rb_entry(node, struct btrfs_ordered_extent, rb_node);
-	atomic_inc(&entry->refs);
+	refcount_inc(&entry->refs);
 out:
 	spin_unlock_irq(&tree->lock);
 	return entry;
@@ -984,8 +982,18 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 	}
 	disk_i_size = BTRFS_I(inode)->disk_i_size;
 
-	/* truncate file */
-	if (disk_i_size > i_size) {
+	/*
+	 * truncate file.
+	 * If ordered is not NULL, then this is called from endio and
+	 * disk_i_size will be updated by either truncate itself or any
+	 * in-flight IOs which are inside the disk_i_size.
+	 *
+	 * Because btrfs_setsize() may set i_size with disk_i_size if truncate
+	 * fails somehow, we need to make sure we have a precise disk_i_size by
+	 * updating it as usual.
+	 *
+	 */
+	if (!ordered && disk_i_size > i_size) {
 		BTRFS_I(inode)->disk_i_size = orig_offset;
 		ret = 0;
 		goto out;
@@ -1032,25 +1040,22 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 		/* We treat this entry as if it doesn't exist */
 		if (test_bit(BTRFS_ORDERED_UPDATED_ISIZE, &test->flags))
 			continue;
-		if (test->file_offset + test->len <= disk_i_size)
+
+		if (entry_end(test) <= disk_i_size)
 			break;
 		if (test->file_offset >= i_size)
 			break;
-		if (entry_end(test) > disk_i_size) {
-			/*
-			 * we don't update disk_i_size now, so record this
-			 * undealt i_size. Or we will not know the real
-			 * i_size.
-			 */
-			if (test->outstanding_isize < offset)
-				test->outstanding_isize = offset;
-			if (ordered &&
-			    ordered->outstanding_isize >
-			    test->outstanding_isize)
-				test->outstanding_isize =
-						ordered->outstanding_isize;
-			goto out;
-		}
+
+		/*
+		 * We don't update disk_i_size now, so record this undealt
+		 * i_size. Or we will not know the real i_size.
+		 */
+		if (test->outstanding_isize < offset)
+			test->outstanding_isize = offset;
+		if (ordered &&
+		    ordered->outstanding_isize > test->outstanding_isize)
+			test->outstanding_isize = ordered->outstanding_isize;
+		goto out;
 	}
 	new_i_size = min_t(u64, offset, i_size);
 
diff --git a/fs/btrfs/ordered-data.h b/fs/btrfs/ordered-data.h
index 5f2b0ca28705..56c4c0ee6381 100644
--- a/fs/btrfs/ordered-data.h
+++ b/fs/btrfs/ordered-data.h
@@ -75,6 +75,8 @@ struct btrfs_ordered_sum {
 				 * in the logging code. */
 #define BTRFS_ORDERED_PENDING 11 /* We are waiting for this ordered extent to
 				  * complete in the current transaction. */
+#define BTRFS_ORDERED_REGULAR 12 /* Regular IO for COW */
+
 struct btrfs_ordered_extent {
 	/* logical offset in the file */
 	u64 file_offset;
@@ -111,7 +113,7 @@ struct btrfs_ordered_extent {
 	int compress_type;
 
 	/* reference count */
-	atomic_t refs;
+	refcount_t refs;
 
 	/* the inode we belong to */
 	struct inode *inode;
@@ -187,9 +189,10 @@ void btrfs_start_ordered_extent(struct inode *inode,
 int btrfs_wait_ordered_range(struct inode *inode, u64 start, u64 len);
 struct btrfs_ordered_extent *
 btrfs_lookup_first_ordered_extent(struct inode * inode, u64 file_offset);
-struct btrfs_ordered_extent *btrfs_lookup_ordered_range(struct inode *inode,
-							u64 file_offset,
-							u64 len);
+struct btrfs_ordered_extent *btrfs_lookup_ordered_range(
+		struct btrfs_inode *inode,
+		u64 file_offset,
+		u64 len);
 bool btrfs_have_ordered_extents_in_range(struct inode *inode,
 					 u64 file_offset,
 					 u64 len);
@@ -197,11 +200,11 @@ int btrfs_ordered_update_i_size(struct inode *inode, u64 offset,
 				struct btrfs_ordered_extent *ordered);
 int btrfs_find_ordered_sum(struct inode *inode, u64 offset, u64 disk_bytenr,
 			   u32 *sum, int len);
-int btrfs_wait_ordered_extents(struct btrfs_root *root, int nr,
+u64 btrfs_wait_ordered_extents(struct btrfs_root *root, u64 nr,
 			       const u64 range_start, const u64 range_len);
-int btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, int nr,
+u64 btrfs_wait_ordered_roots(struct btrfs_fs_info *fs_info, u64 nr,
 			      const u64 range_start, const u64 range_len);
-void btrfs_get_logged_extents(struct inode *inode,
+void btrfs_get_logged_extents(struct btrfs_inode *inode,
 			      struct list_head *logged_list,
 			      const loff_t start,
 			      const loff_t end);
diff --git a/fs/btrfs/print-tree.c b/fs/btrfs/print-tree.c
index cdafbf92ef0c..fcae61e175f3 100644
--- a/fs/btrfs/print-tree.c
+++ b/fs/btrfs/print-tree.c
@@ -261,8 +261,11 @@ void btrfs_print_leaf(struct btrfs_fs_info *fs_info, struct extent_buffer *l)
 		case BTRFS_BLOCK_GROUP_ITEM_KEY:
 			bi = btrfs_item_ptr(l, i,
 					    struct btrfs_block_group_item);
-			pr_info("\t\tblock group used %llu\n",
-			       btrfs_disk_block_group_used(l, bi));
+			pr_info(
+		   "\t\tblock group used %llu chunk_objectid %llu flags %llu\n",
+				btrfs_disk_block_group_used(l, bi),
+				btrfs_disk_block_group_chunk_objectid(l, bi),
+				btrfs_disk_block_group_flags(l, bi));
 			break;
 		case BTRFS_CHUNK_ITEM_KEY:
 			print_chunk(l, btrfs_item_ptr(l, i,
diff --git a/fs/btrfs/props.c b/fs/btrfs/props.c
index f2621e330954..4b23ae5d0e5c 100644
--- a/fs/btrfs/props.c
+++ b/fs/btrfs/props.c
@@ -164,6 +164,7 @@ static int iterate_object_props(struct btrfs_root *root,
 						 size_t),
 				void *ctx)
 {
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
 	char *name_buf = NULL;
 	char *value_buf = NULL;
@@ -214,6 +215,12 @@ static int iterate_object_props(struct btrfs_root *root,
 			name_ptr = (unsigned long)(di + 1);
 			data_ptr = name_ptr + name_len;
 
+			if (verify_dir_item(fs_info, leaf,
+					    path->slots[0], di)) {
+				ret = -EIO;
+				goto out;
+			}
+
 			if (name_len <= XATTR_BTRFS_PREFIX_LEN ||
 			    memcmp_extent_buffer(leaf, XATTR_BTRFS_PREFIX,
 						 name_ptr,
@@ -279,7 +286,7 @@ static void inode_prop_iterator(void *ctx,
 	if (unlikely(ret))
 		btrfs_warn(root->fs_info,
 			   "error applying prop %s to ino %llu (root %llu): %d",
-			   handler->xattr_name, btrfs_ino(inode),
+			   handler->xattr_name, btrfs_ino(BTRFS_I(inode)),
 			   root->root_key.objectid, ret);
 	else
 		set_bit(BTRFS_INODE_HAS_PROPS, &BTRFS_I(inode)->runtime_flags);
@@ -288,7 +295,7 @@ static void inode_prop_iterator(void *ctx,
 int btrfs_load_inode_props(struct inode *inode, struct btrfs_path *path)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	u64 ino = btrfs_ino(inode);
+	u64 ino = btrfs_ino(BTRFS_I(inode));
 	int ret;
 
 	ret = iterate_object_props(root, path, ino, inode_prop_iterator, inode);
diff --git a/fs/btrfs/qgroup.c b/fs/btrfs/qgroup.c
index 662821f1252c..4ce351efe281 100644
--- a/fs/btrfs/qgroup.c
+++ b/fs/btrfs/qgroup.c
@@ -47,50 +47,6 @@
  *  - check all ioctl parameters
  */
 
-/*
- * one struct for each qgroup, organized in fs_info->qgroup_tree.
- */
-struct btrfs_qgroup {
-	u64 qgroupid;
-
-	/*
-	 * state
-	 */
-	u64 rfer;	/* referenced */
-	u64 rfer_cmpr;	/* referenced compressed */
-	u64 excl;	/* exclusive */
-	u64 excl_cmpr;	/* exclusive compressed */
-
-	/*
-	 * limits
-	 */
-	u64 lim_flags;	/* which limits are set */
-	u64 max_rfer;
-	u64 max_excl;
-	u64 rsv_rfer;
-	u64 rsv_excl;
-
-	/*
-	 * reservation tracking
-	 */
-	u64 reserved;
-
-	/*
-	 * lists
-	 */
-	struct list_head groups;  /* groups this group is member of */
-	struct list_head members; /* groups that are members of this group */
-	struct list_head dirty;   /* dirty groups */
-	struct rb_node node;	  /* tree of qgroups */
-
-	/*
-	 * temp variables for accounting operations
-	 * Refer to qgroup_shared_accounting() for details.
-	 */
-	u64 old_refcnt;
-	u64 new_refcnt;
-};
-
 static void btrfs_qgroup_update_old_refcnt(struct btrfs_qgroup *qg, u64 seq,
 					   int mod)
 {
@@ -319,7 +275,7 @@ int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info)
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
 		return 0;
 
-	fs_info->qgroup_ulist = ulist_alloc(GFP_NOFS);
+	fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
 	if (!fs_info->qgroup_ulist) {
 		ret = -ENOMEM;
 		goto out;
@@ -876,7 +832,7 @@ int btrfs_quota_enable(struct btrfs_trans_handle *trans,
 		goto out;
 	}
 
-	fs_info->qgroup_ulist = ulist_alloc(GFP_NOFS);
+	fs_info->qgroup_ulist = ulist_alloc(GFP_KERNEL);
 	if (!fs_info->qgroup_ulist) {
 		ret = -ENOMEM;
 		goto out;
@@ -1019,7 +975,7 @@ int btrfs_quota_disable(struct btrfs_trans_handle *trans,
 	list_del(&quota_root->dirty_list);
 
 	btrfs_tree_lock(quota_root->node);
-	clean_tree_block(trans, fs_info, quota_root->node);
+	clean_tree_block(fs_info, quota_root->node);
 	btrfs_tree_unlock(quota_root->node);
 	btrfs_free_tree_block(trans, quota_root, quota_root->node, 0, 1);
 
@@ -1038,6 +994,18 @@ static void qgroup_dirty(struct btrfs_fs_info *fs_info,
 		list_add(&qgroup->dirty, &fs_info->dirty_qgroups);
 }
 
+static void report_reserved_underflow(struct btrfs_fs_info *fs_info,
+				      struct btrfs_qgroup *qgroup,
+				      u64 num_bytes)
+{
+#ifdef CONFIG_BTRFS_DEBUG
+	WARN_ON(qgroup->reserved < num_bytes);
+	btrfs_debug(fs_info,
+		"qgroup %llu reserved space underflow, have: %llu, to free: %llu",
+		qgroup->qgroupid, qgroup->reserved, num_bytes);
+#endif
+	qgroup->reserved = 0;
+}
 /*
  * The easy accounting, if we are adding/removing the only ref for an extent
  * then this qgroup and all of the parent qgroups get their reference and
@@ -1065,8 +1033,13 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 	WARN_ON(sign < 0 && qgroup->excl < num_bytes);
 	qgroup->excl += sign * num_bytes;
 	qgroup->excl_cmpr += sign * num_bytes;
-	if (sign > 0)
-		qgroup->reserved -= num_bytes;
+	if (sign > 0) {
+		trace_qgroup_update_reserve(fs_info, qgroup, -(s64)num_bytes);
+		if (qgroup->reserved < num_bytes)
+			report_reserved_underflow(fs_info, qgroup, num_bytes);
+		else
+			qgroup->reserved -= num_bytes;
+	}
 
 	qgroup_dirty(fs_info, qgroup);
 
@@ -1086,8 +1059,15 @@ static int __qgroup_excl_accounting(struct btrfs_fs_info *fs_info,
 		qgroup->rfer_cmpr += sign * num_bytes;
 		WARN_ON(sign < 0 && qgroup->excl < num_bytes);
 		qgroup->excl += sign * num_bytes;
-		if (sign > 0)
-			qgroup->reserved -= num_bytes;
+		if (sign > 0) {
+			trace_qgroup_update_reserve(fs_info, qgroup,
+						    -(s64)num_bytes);
+			if (qgroup->reserved < num_bytes)
+				report_reserved_underflow(fs_info, qgroup,
+							  num_bytes);
+			else
+				qgroup->reserved -= num_bytes;
+		}
 		qgroup->excl_cmpr += sign * num_bytes;
 		qgroup_dirty(fs_info, qgroup);
 
@@ -1156,7 +1136,7 @@ int btrfs_add_qgroup_relation(struct btrfs_trans_handle *trans,
 	if (btrfs_qgroup_level(src) >= btrfs_qgroup_level(dst))
 		return -EINVAL;
 
-	tmp = ulist_alloc(GFP_NOFS);
+	tmp = ulist_alloc(GFP_KERNEL);
 	if (!tmp)
 		return -ENOMEM;
 
@@ -1205,7 +1185,7 @@ out:
 	return ret;
 }
 
-int __del_qgroup_relation(struct btrfs_trans_handle *trans,
+static int __del_qgroup_relation(struct btrfs_trans_handle *trans,
 			      struct btrfs_fs_info *fs_info, u64 src, u64 dst)
 {
 	struct btrfs_root *quota_root;
@@ -1216,7 +1196,7 @@ int __del_qgroup_relation(struct btrfs_trans_handle *trans,
 	int ret = 0;
 	int err;
 
-	tmp = ulist_alloc(GFP_NOFS);
+	tmp = ulist_alloc(GFP_KERNEL);
 	if (!tmp)
 		return -ENOMEM;
 
@@ -1426,37 +1406,6 @@ out:
 	return ret;
 }
 
-int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
-					 struct btrfs_fs_info *fs_info)
-{
-	struct btrfs_qgroup_extent_record *record;
-	struct btrfs_delayed_ref_root *delayed_refs;
-	struct rb_node *node;
-	u64 qgroup_to_skip;
-	int ret = 0;
-
-	delayed_refs = &trans->transaction->delayed_refs;
-	qgroup_to_skip = delayed_refs->qgroup_to_skip;
-
-	/*
-	 * No need to do lock, since this function will only be called in
-	 * btrfs_commit_transaction().
-	 */
-	node = rb_first(&delayed_refs->dirty_extent_root);
-	while (node) {
-		record = rb_entry(node, struct btrfs_qgroup_extent_record,
-				  node);
-		ret = btrfs_find_all_roots(NULL, fs_info, record->bytenr, 0,
-					   &record->old_roots);
-		if (ret < 0)
-			break;
-		if (qgroup_to_skip)
-			ulist_del(record->old_roots, qgroup_to_skip, 0);
-		node = rb_next(node);
-	}
-	return ret;
-}
-
 int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
 				struct btrfs_delayed_ref_root *delayed_refs,
 				struct btrfs_qgroup_extent_record *record)
@@ -1486,6 +1435,28 @@ int btrfs_qgroup_trace_extent_nolock(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
+				   struct btrfs_qgroup_extent_record *qrecord)
+{
+	struct ulist *old_root;
+	u64 bytenr = qrecord->bytenr;
+	int ret;
+
+	ret = btrfs_find_all_roots(NULL, fs_info, bytenr, 0, &old_root);
+	if (ret < 0)
+		return ret;
+
+	/*
+	 * Here we don't need to get the lock of
+	 * trans->transaction->delayed_refs, since inserted qrecord won't
+	 * be deleted, only qrecord->node may be modified (new qrecord insert)
+	 *
+	 * So modifying qrecord->old_roots is safe here
+	 */
+	qrecord->old_roots = old_root;
+	return 0;
+}
+
 int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
 		struct btrfs_fs_info *fs_info, u64 bytenr, u64 num_bytes,
 		gfp_t gfp_flag)
@@ -1511,9 +1482,11 @@ int btrfs_qgroup_trace_extent(struct btrfs_trans_handle *trans,
 	spin_lock(&delayed_refs->lock);
 	ret = btrfs_qgroup_trace_extent_nolock(fs_info, delayed_refs, record);
 	spin_unlock(&delayed_refs->lock);
-	if (ret > 0)
+	if (ret > 0) {
 		kfree(record);
-	return 0;
+		return 0;
+	}
+	return btrfs_qgroup_trace_extent_post(fs_info, record);
 }
 
 int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
@@ -1554,6 +1527,7 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
 		if (ret)
 			return ret;
 	}
+	cond_resched();
 	return 0;
 }
 
@@ -1571,8 +1545,7 @@ int btrfs_qgroup_trace_leaf_items(struct btrfs_trans_handle *trans,
  * If we increment the root nodes slot counter past the number of
  * elements, 1 is returned to signal completion of the search.
  */
-static int adjust_slots_upwards(struct btrfs_root *root,
-				struct btrfs_path *path, int root_level)
+static int adjust_slots_upwards(struct btrfs_path *path, int root_level)
 {
 	int level = 0;
 	int nr, slot;
@@ -1713,7 +1686,7 @@ walk_down:
 				goto out;
 
 			/* Nonzero return here means we completed our search */
-			ret = adjust_slots_upwards(root, path, root_level);
+			ret = adjust_slots_upwards(path, root_level);
 			if (ret)
 				break;
 
@@ -1914,6 +1887,35 @@ static int qgroup_update_counters(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
+/*
+ * Check if the @roots potentially is a list of fs tree roots
+ *
+ * Return 0 for definitely not a fs/subvol tree roots ulist
+ * Return 1 for possible fs/subvol tree roots in the list (considering an empty
+ *          one as well)
+ */
+static int maybe_fs_roots(struct ulist *roots)
+{
+	struct ulist_node *unode;
+	struct ulist_iterator uiter;
+
+	/* Empty one, still possible for fs roots */
+	if (!roots || roots->nnodes == 0)
+		return 1;
+
+	ULIST_ITER_INIT(&uiter);
+	unode = ulist_next(roots, &uiter);
+	if (!unode)
+		return 1;
+
+	/*
+	 * If it contains fs tree roots, then it must belong to fs/subvol
+	 * trees.
+	 * If it contains a non-fs tree, it won't be shared with fs/subvol trees.
+	 */
+	return is_fstree(unode->val);
+}
+
 int
 btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
 			    struct btrfs_fs_info *fs_info,
@@ -1927,13 +1929,24 @@ btrfs_qgroup_account_extent(struct btrfs_trans_handle *trans,
 	u64 nr_old_roots = 0;
 	int ret = 0;
 
-	if (new_roots)
+	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+		return 0;
+
+	if (new_roots) {
+		if (!maybe_fs_roots(new_roots))
+			goto out_free;
 		nr_new_roots = new_roots->nnodes;
-	if (old_roots)
+	}
+	if (old_roots) {
+		if (!maybe_fs_roots(old_roots))
+			goto out_free;
 		nr_old_roots = old_roots->nnodes;
+	}
 
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
+	/* Quick exit, either not fs tree roots, or won't affect any qgroup */
+	if (nr_old_roots == 0 && nr_new_roots == 0)
 		goto out_free;
+
 	BUG_ON(!fs_info->quota_root);
 
 	trace_btrfs_qgroup_account_extent(fs_info, bytenr, num_bytes,
@@ -2012,16 +2025,32 @@ int btrfs_qgroup_account_extents(struct btrfs_trans_handle *trans,
 
 		if (!ret) {
 			/*
-			 * Use (u64)-1 as time_seq to do special search, which
+			 * Old roots should be searched when inserting qgroup
+			 * extent record
+			 */
+			if (WARN_ON(!record->old_roots)) {
+				/* Search commit root to find old_roots */
+				ret = btrfs_find_all_roots(NULL, fs_info,
+						record->bytenr, 0,
+						&record->old_roots);
+				if (ret < 0)
+					goto cleanup;
+			}
+
+			/*
+			 * Use SEQ_LAST as time_seq to do special search, which
 			 * doesn't lock tree or delayed_refs and search current
 			 * root. It's safe inside commit_transaction().
 			 */
 			ret = btrfs_find_all_roots(trans, fs_info,
-					record->bytenr, (u64)-1, &new_roots);
+					record->bytenr, SEQ_LAST, &new_roots);
 			if (ret < 0)
 				goto cleanup;
-			if (qgroup_to_skip)
+			if (qgroup_to_skip) {
 				ulist_del(new_roots, qgroup_to_skip, 0);
+				ulist_del(record->old_roots, qgroup_to_skip,
+					  0);
+			}
 			ret = btrfs_qgroup_account_extent(trans, fs_info,
 					record->bytenr, record->num_bytes,
 					record->old_roots, new_roots);
@@ -2170,9 +2199,7 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 			goto out;
 		}
 
-		rcu_read_lock();
 		level_size = fs_info->nodesize;
-		rcu_read_unlock();
 	}
 
 	/*
@@ -2306,13 +2333,27 @@ out:
 	return ret;
 }
 
-static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
+static bool qgroup_check_limits(const struct btrfs_qgroup *qg, u64 num_bytes)
+{
+	if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
+	    qg->reserved + (s64)qg->rfer + num_bytes > qg->max_rfer)
+		return false;
+
+	if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) &&
+	    qg->reserved + (s64)qg->excl + num_bytes > qg->max_excl)
+		return false;
+
+	return true;
+}
+
+static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes, bool enforce)
 {
 	struct btrfs_root *quota_root;
 	struct btrfs_qgroup *qgroup;
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	u64 ref_root = root->root_key.objectid;
 	int ret = 0;
+	int retried = 0;
 	struct ulist_node *unode;
 	struct ulist_iterator uiter;
 
@@ -2322,6 +2363,11 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
 	if (num_bytes == 0)
 		return 0;
 
+	if (test_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags) &&
+	    capable(CAP_SYS_RESOURCE))
+		enforce = false;
+
+retry:
 	spin_lock(&fs_info->qgroup_lock);
 	quota_root = fs_info->quota_root;
 	if (!quota_root)
@@ -2347,16 +2393,28 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
 
 		qg = unode_aux_to_qgroup(unode);
 
-		if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_RFER) &&
-		    qg->reserved + (s64)qg->rfer + num_bytes >
-		    qg->max_rfer) {
-			ret = -EDQUOT;
-			goto out;
-		}
+		if (enforce && !qgroup_check_limits(qg, num_bytes)) {
+			/*
+			 * Commit the tree and retry, since we may have
+			 * deletions which would free up space.
+			 */
+			if (!retried && qg->reserved > 0) {
+				struct btrfs_trans_handle *trans;
 
-		if ((qg->lim_flags & BTRFS_QGROUP_LIMIT_MAX_EXCL) &&
-		    qg->reserved + (s64)qg->excl + num_bytes >
-		    qg->max_excl) {
+				spin_unlock(&fs_info->qgroup_lock);
+				ret = btrfs_start_delalloc_inodes(root, 0);
+				if (ret)
+					return ret;
+				btrfs_wait_ordered_extents(root, U64_MAX, 0, (u64)-1);
+				trans = btrfs_join_transaction(root);
+				if (IS_ERR(trans))
+					return PTR_ERR(trans);
+				ret = btrfs_commit_transaction(trans);
+				if (ret)
+					return ret;
+				retried++;
+				goto retry;
+			}
 			ret = -EDQUOT;
 			goto out;
 		}
@@ -2379,6 +2437,7 @@ static int qgroup_reserve(struct btrfs_root *root, u64 num_bytes)
 
 		qg = unode_aux_to_qgroup(unode);
 
+		trace_qgroup_update_reserve(fs_info, qg, num_bytes);
 		qg->reserved += num_bytes;
 	}
 
@@ -2424,7 +2483,11 @@ void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 
 		qg = unode_aux_to_qgroup(unode);
 
-		qg->reserved -= num_bytes;
+		trace_qgroup_update_reserve(fs_info, qg, -(s64)num_bytes);
+		if (qg->reserved < num_bytes)
+			report_reserved_underflow(fs_info, qg, num_bytes);
+		else
+			qg->reserved -= num_bytes;
 
 		list_for_each_entry(glist, &qg->groups, next_group) {
 			ret = ulist_add(fs_info->qgroup_ulist,
@@ -2439,23 +2502,6 @@ out:
 	spin_unlock(&fs_info->qgroup_lock);
 }
 
-static inline void qgroup_free(struct btrfs_root *root, u64 num_bytes)
-{
-	return btrfs_qgroup_free_refroot(root->fs_info, root->objectid,
-					 num_bytes);
-}
-void assert_qgroups_uptodate(struct btrfs_trans_handle *trans)
-{
-	if (list_empty(&trans->qgroup_ref_list) && !trans->delayed_ref_elem.seq)
-		return;
-	btrfs_err(trans->fs_info,
-		"qgroups not uptodate in trans handle %p:  list is%s empty, seq is %#x.%x",
-		trans, list_empty(&trans->qgroup_ref_list) ? "" : " not",
-		(u32)(trans->delayed_ref_elem.seq >> 32),
-		(u32)trans->delayed_ref_elem.seq);
-	BUG();
-}
-
 /*
  * returns < 0 on error, 0 when more leafs are to be scanned.
  * returns 1 when done.
@@ -2789,71 +2835,146 @@ btrfs_qgroup_rescan_resume(struct btrfs_fs_info *fs_info)
  * Return <0 for error (including -EQUOT)
  *
  * NOTE: this function may sleep for memory allocation.
+ *       if btrfs_qgroup_reserve_data() is called multiple times with
+ *       same @reserved, caller must ensure when error happens it's OK
+ *       to free *ALL* reserved space.
  */
-int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len)
+int btrfs_qgroup_reserve_data(struct inode *inode,
+			struct extent_changeset **reserved_ret, u64 start,
+			u64 len)
 {
 	struct btrfs_root *root = BTRFS_I(inode)->root;
-	struct extent_changeset changeset;
 	struct ulist_node *unode;
 	struct ulist_iterator uiter;
+	struct extent_changeset *reserved;
+	u64 orig_reserved;
+	u64 to_reserve;
 	int ret;
 
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &root->fs_info->flags) ||
 	    !is_fstree(root->objectid) || len == 0)
 		return 0;
 
-	changeset.bytes_changed = 0;
-	changeset.range_changed = ulist_alloc(GFP_NOFS);
+	/* @reserved parameter is mandatory for qgroup */
+	if (WARN_ON(!reserved_ret))
+		return -EINVAL;
+	if (!*reserved_ret) {
+		*reserved_ret = extent_changeset_alloc();
+		if (!*reserved_ret)
+			return -ENOMEM;
+	}
+	reserved = *reserved_ret;
+	/* Record already reserved space */
+	orig_reserved = reserved->bytes_changed;
 	ret = set_record_extent_bits(&BTRFS_I(inode)->io_tree, start,
-			start + len -1, EXTENT_QGROUP_RESERVED, &changeset);
+			start + len -1, EXTENT_QGROUP_RESERVED, reserved);
+
+	/* Newly reserved space */
+	to_reserve = reserved->bytes_changed - orig_reserved;
 	trace_btrfs_qgroup_reserve_data(inode, start, len,
-					changeset.bytes_changed,
-					QGROUP_RESERVE);
+					to_reserve, QGROUP_RESERVE);
 	if (ret < 0)
 		goto cleanup;
-	ret = qgroup_reserve(root, changeset.bytes_changed);
+	ret = qgroup_reserve(root, to_reserve, true);
 	if (ret < 0)
 		goto cleanup;
 
-	ulist_free(changeset.range_changed);
 	return ret;
 
 cleanup:
-	/* cleanup already reserved ranges */
+	/* cleanup *ALL* already reserved ranges */
 	ULIST_ITER_INIT(&uiter);
-	while ((unode = ulist_next(changeset.range_changed, &uiter)))
+	while ((unode = ulist_next(&reserved->range_changed, &uiter)))
 		clear_extent_bit(&BTRFS_I(inode)->io_tree, unode->val,
 				 unode->aux, EXTENT_QGROUP_RESERVED, 0, 0, NULL,
 				 GFP_NOFS);
-	ulist_free(changeset.range_changed);
+	extent_changeset_release(reserved);
 	return ret;
 }
 
-static int __btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len,
-				       int free)
+/* Free ranges specified by @reserved, normally in error path */
+static int qgroup_free_reserved_data(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len)
 {
+	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct ulist_node *unode;
+	struct ulist_iterator uiter;
 	struct extent_changeset changeset;
-	int trace_op = QGROUP_RELEASE;
+	int freed = 0;
 	int ret;
 
-	changeset.bytes_changed = 0;
-	changeset.range_changed = ulist_alloc(GFP_NOFS);
-	if (!changeset.range_changed)
-		return -ENOMEM;
+	extent_changeset_init(&changeset);
+	len = round_up(start + len, root->fs_info->sectorsize);
+	start = round_down(start, root->fs_info->sectorsize);
 
+	ULIST_ITER_INIT(&uiter);
+	while ((unode = ulist_next(&reserved->range_changed, &uiter))) {
+		u64 range_start = unode->val;
+		/* unode->aux is the inclusive end */
+		u64 range_len = unode->aux - range_start + 1;
+		u64 free_start;
+		u64 free_len;
+
+		extent_changeset_release(&changeset);
+
+		/* Only free range in range [start, start + len) */
+		if (range_start >= start + len ||
+		    range_start + range_len <= start)
+			continue;
+		free_start = max(range_start, start);
+		free_len = min(start + len, range_start + range_len) -
+			   free_start;
+		/*
+		 * TODO: To also modify reserved->ranges_reserved to reflect
+		 * the modification.
+		 *
+		 * However as long as we free qgroup reserved according to
+		 * EXTENT_QGROUP_RESERVED, we won't double free.
+		 * So not need to rush.
+		 */
+		ret = clear_record_extent_bits(&BTRFS_I(inode)->io_failure_tree,
+				free_start, free_start + free_len - 1,
+				EXTENT_QGROUP_RESERVED, &changeset);
+		if (ret < 0)
+			goto out;
+		freed += changeset.bytes_changed;
+	}
+	btrfs_qgroup_free_refroot(root->fs_info, root->objectid, freed);
+	ret = freed;
+out:
+	extent_changeset_release(&changeset);
+	return ret;
+}
+
+static int __btrfs_qgroup_release_data(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len,
+			int free)
+{
+	struct extent_changeset changeset;
+	int trace_op = QGROUP_RELEASE;
+	int ret;
+
+	/* In release case, we shouldn't have @reserved */
+	WARN_ON(!free && reserved);
+	if (free && reserved)
+		return qgroup_free_reserved_data(inode, reserved, start, len);
+	extent_changeset_init(&changeset);
 	ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, start, 
 			start + len -1, EXTENT_QGROUP_RESERVED, &changeset);
 	if (ret < 0)
 		goto out;
 
-	if (free) {
-		qgroup_free(BTRFS_I(inode)->root, changeset.bytes_changed);
+	if (free)
 		trace_op = QGROUP_FREE;
-	}
 	trace_btrfs_qgroup_release_data(inode, start, len,
 					changeset.bytes_changed, trace_op);
+	if (free)
+		btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info,
+				BTRFS_I(inode)->root->objectid,
+				changeset.bytes_changed);
+	ret = changeset.bytes_changed;
 out:
-	ulist_free(changeset.range_changed);
+	extent_changeset_release(&changeset);
 	return ret;
 }
 
@@ -2862,14 +2983,17 @@ out:
  *
  * Should be called when a range of pages get invalidated before reaching disk.
  * Or for error cleanup case.
+ * if @reserved is given, only reserved range in [@start, @start + @len) will
+ * be freed.
  *
  * For data written to disk, use btrfs_qgroup_release_data().
  *
  * NOTE: This function may sleep for memory allocation.
  */
-int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len)
+int btrfs_qgroup_free_data(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len)
 {
-	return __btrfs_qgroup_release_data(inode, start, len, 1);
+	return __btrfs_qgroup_release_data(inode, reserved, start, len, 1);
 }
 
 /*
@@ -2889,10 +3013,11 @@ int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len)
  */
 int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len)
 {
-	return __btrfs_qgroup_release_data(inode, start, len, 0);
+	return __btrfs_qgroup_release_data(inode, NULL, start, len, 0);
 }
 
-int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes)
+int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
+			      bool enforce)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	int ret;
@@ -2902,26 +3027,28 @@ int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes)
 		return 0;
 
 	BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
-	ret = qgroup_reserve(root, num_bytes);
+	trace_qgroup_meta_reserve(root, (s64)num_bytes);
+	ret = qgroup_reserve(root, num_bytes, enforce);
 	if (ret < 0)
 		return ret;
-	atomic_add(num_bytes, &root->qgroup_meta_rsv);
+	atomic64_add(num_bytes, &root->qgroup_meta_rsv);
 	return ret;
 }
 
 void btrfs_qgroup_free_meta_all(struct btrfs_root *root)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
-	int reserved;
+	u64 reserved;
 
 	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags) ||
 	    !is_fstree(root->objectid))
 		return;
 
-	reserved = atomic_xchg(&root->qgroup_meta_rsv, 0);
+	reserved = atomic64_xchg(&root->qgroup_meta_rsv, 0);
 	if (reserved == 0)
 		return;
-	qgroup_free(root, reserved);
+	trace_qgroup_meta_reserve(root, -(s64)reserved);
+	btrfs_qgroup_free_refroot(fs_info, root->objectid, reserved);
 }
 
 void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes)
@@ -2933,9 +3060,10 @@ void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes)
 		return;
 
 	BUG_ON(num_bytes != round_down(num_bytes, fs_info->nodesize));
-	WARN_ON(atomic_read(&root->qgroup_meta_rsv) < num_bytes);
-	atomic_sub(num_bytes, &root->qgroup_meta_rsv);
-	qgroup_free(root, num_bytes);
+	WARN_ON(atomic64_read(&root->qgroup_meta_rsv) < num_bytes);
+	atomic64_sub(num_bytes, &root->qgroup_meta_rsv);
+	trace_qgroup_meta_reserve(root, -(s64)num_bytes);
+	btrfs_qgroup_free_refroot(fs_info, root->objectid, num_bytes);
 }
 
 /*
@@ -2949,23 +3077,22 @@ void btrfs_qgroup_check_reserved_leak(struct inode *inode)
 	struct ulist_iterator iter;
 	int ret;
 
-	changeset.bytes_changed = 0;
-	changeset.range_changed = ulist_alloc(GFP_NOFS);
-	if (WARN_ON(!changeset.range_changed))
-		return;
-
+	extent_changeset_init(&changeset);
 	ret = clear_record_extent_bits(&BTRFS_I(inode)->io_tree, 0, (u64)-1,
 			EXTENT_QGROUP_RESERVED, &changeset);
 
 	WARN_ON(ret < 0);
 	if (WARN_ON(changeset.bytes_changed)) {
 		ULIST_ITER_INIT(&iter);
-		while ((unode = ulist_next(changeset.range_changed, &iter))) {
+		while ((unode = ulist_next(&changeset.range_changed, &iter))) {
 			btrfs_warn(BTRFS_I(inode)->root->fs_info,
 				"leaking qgroup reserved space, ino: %lu, start: %llu, end: %llu",
 				inode->i_ino, unode->val, unode->aux);
 		}
-		qgroup_free(BTRFS_I(inode)->root, changeset.bytes_changed);
+		btrfs_qgroup_free_refroot(BTRFS_I(inode)->root->fs_info,
+				BTRFS_I(inode)->root->objectid,
+				changeset.bytes_changed);
+
 	}
-	ulist_free(changeset.range_changed);
+	extent_changeset_release(&changeset);
 }
diff --git a/fs/btrfs/qgroup.h b/fs/btrfs/qgroup.h
index 416ae8e1d23c..d9984e87cddf 100644
--- a/fs/btrfs/qgroup.h
+++ b/fs/btrfs/qgroup.h
@@ -62,6 +62,50 @@ struct btrfs_qgroup_extent_record {
 };
 
 /*
+ * one struct for each qgroup, organized in fs_info->qgroup_tree.
+ */
+struct btrfs_qgroup {
+	u64 qgroupid;
+
+	/*
+	 * state
+	 */
+	u64 rfer;	/* referenced */
+	u64 rfer_cmpr;	/* referenced compressed */
+	u64 excl;	/* exclusive */
+	u64 excl_cmpr;	/* exclusive compressed */
+
+	/*
+	 * limits
+	 */
+	u64 lim_flags;	/* which limits are set */
+	u64 max_rfer;
+	u64 max_excl;
+	u64 rsv_rfer;
+	u64 rsv_excl;
+
+	/*
+	 * reservation tracking
+	 */
+	u64 reserved;
+
+	/*
+	 * lists
+	 */
+	struct list_head groups;  /* groups this group is member of */
+	struct list_head members; /* groups that are members of this group */
+	struct list_head dirty;   /* dirty groups */
+	struct rb_node node;	  /* tree of qgroups */
+
+	/*
+	 * temp variables for accounting operations
+	 * Refer to qgroup_shared_accounting() for details.
+	 */
+	u64 old_refcnt;
+	u64 new_refcnt;
+};
+
+/*
  * For qgroup event trace points only
  */
 #define QGROUP_RESERVE		(1<<0)
@@ -90,13 +134,13 @@ int btrfs_limit_qgroup(struct btrfs_trans_handle *trans,
 int btrfs_read_qgroup_config(struct btrfs_fs_info *fs_info);
 void btrfs_free_qgroup_config(struct btrfs_fs_info *fs_info);
 struct btrfs_delayed_extent_op;
-int btrfs_qgroup_prepare_account_extents(struct btrfs_trans_handle *trans,
-					 struct btrfs_fs_info *fs_info);
+
 /*
  * Inform qgroup to trace one dirty extent, its info is recorded in @record.
- * So qgroup can account it at commit trans time.
+ * So qgroup can account it at transaction committing time.
  *
- * No lock version, caller must acquire delayed ref lock and allocate memory.
+ * No lock version, caller must acquire delayed ref lock and allocated memory,
+ * then call btrfs_qgroup_trace_extent_post() after exiting lock context.
  *
  * Return 0 for success insert
  * Return >0 for existing record, caller can free @record safely.
@@ -108,11 +152,37 @@ int btrfs_qgroup_trace_extent_nolock(
 		struct btrfs_qgroup_extent_record *record);
 
 /*
+ * Post handler after qgroup_trace_extent_nolock().
+ *
+ * NOTE: Current qgroup does the expensive backref walk at transaction
+ * committing time with TRANS_STATE_COMMIT_DOING, this blocks incoming
+ * new transaction.
+ * This is designed to allow btrfs_find_all_roots() to get correct new_roots
+ * result.
+ *
+ * However for old_roots there is no need to do backref walk at that time,
+ * since we search commit roots to walk backref and result will always be
+ * correct.
+ *
+ * Due to the nature of no lock version, we can't do backref there.
+ * So we must call btrfs_qgroup_trace_extent_post() after exiting
+ * spinlock context.
+ *
+ * TODO: If we can fix and prove btrfs_find_all_roots() can get correct result
+ * using current root, then we can move all expensive backref walk out of
+ * transaction committing, but not now as qgroup accounting will be wrong again.
+ */
+int btrfs_qgroup_trace_extent_post(struct btrfs_fs_info *fs_info,
+				   struct btrfs_qgroup_extent_record *qrecord);
+
+/*
  * Inform qgroup to trace one dirty extent, specified by @bytenr and
  * @num_bytes.
  * So qgroup can account it at commit trans time.
  *
- * Better encapsulated version.
+ * Better encapsulated version, with memory allocation and backref walk for
+ * commit roots.
+ * So this can sleep.
  *
  * Return 0 if the operation is done.
  * Return <0 for error, like memory allocation failure or invalid parameter
@@ -159,17 +229,12 @@ int btrfs_qgroup_inherit(struct btrfs_trans_handle *trans,
 			 struct btrfs_qgroup_inherit *inherit);
 void btrfs_qgroup_free_refroot(struct btrfs_fs_info *fs_info,
 			       u64 ref_root, u64 num_bytes);
-/*
- * TODO: Add proper trace point for it, as btrfs_qgroup_free() is
- * called by everywhere, can't provide good trace for delayed ref case.
- */
 static inline void btrfs_qgroup_free_delayed_ref(struct btrfs_fs_info *fs_info,
 						 u64 ref_root, u64 num_bytes)
 {
-	btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes);
 	trace_btrfs_qgroup_free_delayed_ref(fs_info, ref_root, num_bytes);
+	btrfs_qgroup_free_refroot(fs_info, ref_root, num_bytes);
 }
-void assert_qgroups_uptodate(struct btrfs_trans_handle *trans);
 
 #ifdef CONFIG_BTRFS_FS_RUN_SANITY_TESTS
 int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
@@ -177,11 +242,14 @@ int btrfs_verify_qgroup_counts(struct btrfs_fs_info *fs_info, u64 qgroupid,
 #endif
 
 /* New io_tree based accurate qgroup reserve API */
-int btrfs_qgroup_reserve_data(struct inode *inode, u64 start, u64 len);
+int btrfs_qgroup_reserve_data(struct inode *inode,
+			struct extent_changeset **reserved, u64 start, u64 len);
 int btrfs_qgroup_release_data(struct inode *inode, u64 start, u64 len);
-int btrfs_qgroup_free_data(struct inode *inode, u64 start, u64 len);
+int btrfs_qgroup_free_data(struct inode *inode,
+			struct extent_changeset *reserved, u64 start, u64 len);
 
-int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes);
+int btrfs_qgroup_reserve_meta(struct btrfs_root *root, int num_bytes,
+			      bool enforce);
 void btrfs_qgroup_free_meta_all(struct btrfs_root *root);
 void btrfs_qgroup_free_meta(struct btrfs_root *root, int num_bytes);
 void btrfs_qgroup_check_reserved_leak(struct inode *inode);
diff --git a/fs/btrfs/raid56.c b/fs/btrfs/raid56.c
index d2a9a1ee5361..208638384cd2 100644
--- a/fs/btrfs/raid56.c
+++ b/fs/btrfs/raid56.c
@@ -31,7 +31,7 @@
 #include <linux/hash.h>
 #include <linux/list_sort.h>
 #include <linux/raid/xor.h>
-#include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include <asm/div64.h>
 #include "ctree.h"
 #include "extent_map.h"
@@ -149,7 +149,7 @@ struct btrfs_raid_bio {
 
 	int generic_bio_cnt;
 
-	atomic_t refs;
+	refcount_t refs;
 
 	atomic_t stripes_pending;
 
@@ -218,12 +218,9 @@ int btrfs_alloc_stripe_hash_table(struct btrfs_fs_info *info)
 	 * of a failing mount.
 	 */
 	table_size = sizeof(*table) + sizeof(*h) * num_entries;
-	table = kzalloc(table_size, GFP_KERNEL | __GFP_NOWARN | __GFP_REPEAT);
-	if (!table) {
-		table = vzalloc(table_size);
-		if (!table)
-			return -ENOMEM;
-	}
+	table = kvzalloc(table_size, GFP_KERNEL);
+	if (!table)
+		return -ENOMEM;
 
 	spin_lock_init(&table->cache_lock);
 	INIT_LIST_HEAD(&table->stripe_cache);
@@ -389,7 +386,7 @@ static void __remove_rbio_from_cache(struct btrfs_raid_bio *rbio)
 		if (bio_list_empty(&rbio->bio_list)) {
 			if (!list_empty(&rbio->hash_list)) {
 				list_del_init(&rbio->hash_list);
-				atomic_dec(&rbio->refs);
+				refcount_dec(&rbio->refs);
 				BUG_ON(!list_empty(&rbio->plug_list));
 			}
 		}
@@ -480,7 +477,7 @@ static void cache_rbio(struct btrfs_raid_bio *rbio)
 
 	/* bump our ref if we were not in the list before */
 	if (!test_and_set_bit(RBIO_CACHE_BIT, &rbio->flags))
-		atomic_inc(&rbio->refs);
+		refcount_inc(&rbio->refs);
 
 	if (!list_empty(&rbio->stripe_cache)){
 		list_move(&rbio->stripe_cache, &table->stripe_cache);
@@ -677,11 +674,9 @@ static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
 	struct btrfs_raid_bio *freeit = NULL;
 	struct btrfs_raid_bio *cache_drop = NULL;
 	int ret = 0;
-	int walk = 0;
 
 	spin_lock_irqsave(&h->lock, flags);
 	list_for_each_entry(cur, &h->hash_list, hash_list) {
-		walk++;
 		if (cur->bbio->raid_map[0] == rbio->bbio->raid_map[0]) {
 			spin_lock(&cur->bio_list_lock);
 
@@ -691,7 +686,7 @@ static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
 			    test_bit(RBIO_CACHE_BIT, &cur->flags) &&
 			    !test_bit(RBIO_RMW_LOCKED_BIT, &cur->flags)) {
 				list_del_init(&cur->hash_list);
-				atomic_dec(&cur->refs);
+				refcount_dec(&cur->refs);
 
 				steal_rbio(cur, rbio);
 				cache_drop = cur;
@@ -740,7 +735,7 @@ static noinline int lock_stripe_add(struct btrfs_raid_bio *rbio)
 		}
 	}
 lockit:
-	atomic_inc(&rbio->refs);
+	refcount_inc(&rbio->refs);
 	list_add(&rbio->hash_list, &h->hash_list);
 out:
 	spin_unlock_irqrestore(&h->lock, flags);
@@ -786,7 +781,7 @@ static noinline void unlock_stripe(struct btrfs_raid_bio *rbio)
 		}
 
 		list_del_init(&rbio->hash_list);
-		atomic_dec(&rbio->refs);
+		refcount_dec(&rbio->refs);
 
 		/*
 		 * we use the plug list to hold all the rbios
@@ -803,7 +798,7 @@ static noinline void unlock_stripe(struct btrfs_raid_bio *rbio)
 			list_del_init(&rbio->plug_list);
 
 			list_add(&next->hash_list, &h->hash_list);
-			atomic_inc(&next->refs);
+			refcount_inc(&next->refs);
 			spin_unlock(&rbio->bio_list_lock);
 			spin_unlock_irqrestore(&h->lock, flags);
 
@@ -845,8 +840,7 @@ static void __free_raid_bio(struct btrfs_raid_bio *rbio)
 {
 	int i;
 
-	WARN_ON(atomic_read(&rbio->refs) < 0);
-	if (!atomic_dec_and_test(&rbio->refs))
+	if (!refcount_dec_and_test(&rbio->refs))
 		return;
 
 	WARN_ON(!list_empty(&rbio->stripe_cache));
@@ -874,7 +868,7 @@ static void free_raid_bio(struct btrfs_raid_bio *rbio)
  * this frees the rbio and runs through all the bios in the
  * bio_list and calls end_io on them
  */
-static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err)
+static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, blk_status_t err)
 {
 	struct bio *cur = bio_list_get(&rbio->bio_list);
 	struct bio *next;
@@ -887,7 +881,7 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err)
 	while (cur) {
 		next = cur->bi_next;
 		cur->bi_next = NULL;
-		cur->bi_error = err;
+		cur->bi_status = err;
 		bio_endio(cur);
 		cur = next;
 	}
@@ -900,7 +894,7 @@ static void rbio_orig_end_io(struct btrfs_raid_bio *rbio, int err)
 static void raid_write_end_io(struct bio *bio)
 {
 	struct btrfs_raid_bio *rbio = bio->bi_private;
-	int err = bio->bi_error;
+	blk_status_t err = bio->bi_status;
 	int max_errors;
 
 	if (err)
@@ -917,7 +911,7 @@ static void raid_write_end_io(struct bio *bio)
 	max_errors = (rbio->operation == BTRFS_RBIO_PARITY_SCRUB) ?
 		     0 : rbio->bbio->max_errors;
 	if (atomic_read(&rbio->error) > max_errors)
-		err = -EIO;
+		err = BLK_STS_IOERR;
 
 	rbio_orig_end_io(rbio, err);
 }
@@ -999,7 +993,7 @@ static struct btrfs_raid_bio *alloc_rbio(struct btrfs_fs_info *fs_info,
 	rbio->stripe_npages = stripe_npages;
 	rbio->faila = -1;
 	rbio->failb = -1;
-	atomic_set(&rbio->refs, 1);
+	refcount_set(&rbio->refs, 1);
 	atomic_set(&rbio->error, 0);
 	atomic_set(&rbio->stripes_pending, 0);
 
@@ -1095,7 +1089,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 		 * devices or if they are not contiguous
 		 */
 		if (last_end == disk_start && stripe->dev->bdev &&
-		    !last->bi_error &&
+		    !last->bi_status &&
 		    last->bi_bdev == stripe->dev->bdev) {
 			ret = bio_add_page(last, page, PAGE_SIZE, 0);
 			if (ret == PAGE_SIZE)
@@ -1104,10 +1098,7 @@ static int rbio_add_io_page(struct btrfs_raid_bio *rbio,
 	}
 
 	/* put a new bio on the list */
-	bio = btrfs_io_bio_alloc(GFP_NOFS, bio_max_len >> PAGE_SHIFT?:1);
-	if (!bio)
-		return -ENOMEM;
-
+	bio = btrfs_io_bio_alloc(bio_max_len >> PAGE_SHIFT ?: 1);
 	bio->bi_iter.bi_size = 0;
 	bio->bi_bdev = stripe->dev->bdev;
 	bio->bi_iter.bi_sector = disk_start >> 9;
@@ -1145,20 +1136,27 @@ static void validate_rbio_for_rmw(struct btrfs_raid_bio *rbio)
 static void index_rbio_pages(struct btrfs_raid_bio *rbio)
 {
 	struct bio *bio;
-	struct bio_vec *bvec;
 	u64 start;
 	unsigned long stripe_offset;
 	unsigned long page_index;
-	int i;
 
 	spin_lock_irq(&rbio->bio_list_lock);
 	bio_list_for_each(bio, &rbio->bio_list) {
+		struct bio_vec bvec;
+		struct bvec_iter iter;
+		int i = 0;
+
 		start = (u64)bio->bi_iter.bi_sector << 9;
 		stripe_offset = start - rbio->bbio->raid_map[0];
 		page_index = stripe_offset >> PAGE_SHIFT;
 
-		bio_for_each_segment_all(bvec, bio, i)
-			rbio->bio_pages[page_index + i] = bvec->bv_page;
+		if (bio_flagged(bio, BIO_CLONED))
+			bio->bi_iter = btrfs_io_bio(bio)->iter;
+
+		bio_for_each_segment(bvec, bio, iter) {
+			rbio->bio_pages[page_index + i] = bvec.bv_page;
+			i++;
+		}
 	}
 	spin_unlock_irq(&rbio->bio_list_lock);
 }
@@ -1432,11 +1430,14 @@ static int fail_bio_stripe(struct btrfs_raid_bio *rbio,
  */
 static void set_bio_pages_uptodate(struct bio *bio)
 {
-	struct bio_vec *bvec;
-	int i;
+	struct bio_vec bvec;
+	struct bvec_iter iter;
+
+	if (bio_flagged(bio, BIO_CLONED))
+		bio->bi_iter = btrfs_io_bio(bio)->iter;
 
-	bio_for_each_segment_all(bvec, bio, i)
-		SetPageUptodate(bvec->bv_page);
+	bio_for_each_segment(bvec, bio, iter)
+		SetPageUptodate(bvec.bv_page);
 }
 
 /*
@@ -1451,7 +1452,7 @@ static void raid_rmw_end_io(struct bio *bio)
 {
 	struct btrfs_raid_bio *rbio = bio->bi_private;
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		fail_bio_stripe(rbio, bio);
 	else
 		set_bio_pages_uptodate(bio);
@@ -1994,7 +1995,7 @@ static void raid_recover_end_io(struct bio *bio)
 	 * we only read stripe pages off the disk, set them
 	 * up to date if there were no errors
 	 */
-	if (bio->bi_error)
+	if (bio->bi_status)
 		fail_bio_stripe(rbio, bio);
 	else
 		set_bio_pages_uptodate(bio);
@@ -2120,6 +2121,11 @@ int raid56_parity_recover(struct btrfs_fs_info *fs_info, struct bio *bio,
 	struct btrfs_raid_bio *rbio;
 	int ret;
 
+	if (generic_io) {
+		ASSERT(bbio->mirror_num == mirror_num);
+		btrfs_io_bio(bio)->mirror_num = mirror_num;
+	}
+
 	rbio = alloc_rbio(fs_info, bbio, stripe_len);
 	if (IS_ERR(rbio)) {
 		if (generic_io)
@@ -2196,6 +2202,8 @@ static void read_rebuild_work(struct btrfs_work *work)
 /*
  * The following code is used to scrub/replace the parity stripe
  *
+ * Caller must have already increased bio_counter for getting @bbio.
+ *
  * Note: We need make sure all the pages that add into the scrub/replace
  * raid bio are correct and not be changed during the scrub/replace. That
  * is those pages just hold metadata or file data with checksum.
@@ -2233,6 +2241,12 @@ raid56_parity_alloc_scrub_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	ASSERT(rbio->stripe_npages == stripe_nsectors);
 	bitmap_copy(rbio->dbitmap, dbitmap, stripe_nsectors);
 
+	/*
+	 * We have already increased bio_counter when getting bbio, record it
+	 * so we can free it at rbio_orig_end_io().
+	 */
+	rbio->generic_bio_cnt = 1;
+
 	return rbio;
 }
 
@@ -2520,7 +2534,7 @@ static void raid56_parity_scrub_end_io(struct bio *bio)
 {
 	struct btrfs_raid_bio *rbio = bio->bi_private;
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		fail_bio_stripe(rbio, bio);
 	else
 		set_bio_pages_uptodate(bio);
@@ -2675,6 +2689,12 @@ raid56_alloc_missing_rbio(struct btrfs_fs_info *fs_info, struct bio *bio,
 		return NULL;
 	}
 
+	/*
+	 * When we get bbio, we have already increased bio_counter, record it
+	 * so we can free it at rbio_orig_end_io()
+	 */
+	rbio->generic_bio_cnt = 1;
+
 	return rbio;
 }
 
diff --git a/fs/btrfs/reada.c b/fs/btrfs/reada.c
index e88bca87f5d2..ab852b8e3e37 100644
--- a/fs/btrfs/reada.c
+++ b/fs/btrfs/reada.c
@@ -66,7 +66,6 @@ struct reada_extctl {
 struct reada_extent {
 	u64			logical;
 	struct btrfs_key	top;
-	int			err;
 	struct list_head	extctl;
 	int 			refcnt;
 	spinlock_t		lock;
@@ -209,9 +208,9 @@ cleanup:
 	return;
 }
 
-int btree_readahead_hook(struct btrfs_fs_info *fs_info,
-			 struct extent_buffer *eb, int err)
+int btree_readahead_hook(struct extent_buffer *eb, int err)
 {
+	struct btrfs_fs_info *fs_info = eb->fs_info;
 	int ret = 0;
 	struct reada_extent *re;
 
@@ -235,10 +234,10 @@ start_machine:
 	return ret;
 }
 
-static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
-					  struct btrfs_device *dev, u64 logical,
+static struct reada_zone *reada_find_zone(struct btrfs_device *dev, u64 logical,
 					  struct btrfs_bio *bbio)
 {
+	struct btrfs_fs_info *fs_info = dev->fs_info;
 	int ret;
 	struct reada_zone *zone;
 	struct btrfs_block_group_cache *cache = NULL;
@@ -270,6 +269,12 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
 	if (!zone)
 		return NULL;
 
+	ret = radix_tree_preload(GFP_KERNEL);
+	if (ret) {
+		kfree(zone);
+		return NULL;
+	}
+
 	zone->start = start;
 	zone->end = end;
 	INIT_LIST_HEAD(&zone->list);
@@ -299,6 +304,7 @@ static struct reada_zone *reada_find_zone(struct btrfs_fs_info *fs_info,
 			zone = NULL;
 	}
 	spin_unlock(&fs_info->reada_lock);
+	radix_tree_preload_end();
 
 	return zone;
 }
@@ -313,7 +319,6 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 	struct btrfs_bio *bbio = NULL;
 	struct btrfs_device *dev;
 	struct btrfs_device *prev_dev;
-	u32 blocksize;
 	u64 length;
 	int real_stripes;
 	int nzones = 0;
@@ -334,7 +339,6 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 	if (!re)
 		return NULL;
 
-	blocksize = fs_info->nodesize;
 	re->logical = logical;
 	re->top = *top;
 	INIT_LIST_HEAD(&re->extctl);
@@ -344,10 +348,10 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 	/*
 	 * map block
 	 */
-	length = blocksize;
+	length = fs_info->nodesize;
 	ret = btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
 			&length, &bbio, 0);
-	if (ret || !bbio || length < blocksize)
+	if (ret || !bbio || length < fs_info->nodesize)
 		goto error;
 
 	if (bbio->num_stripes > BTRFS_MAX_MIRRORS) {
@@ -367,7 +371,7 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 		 if (!dev->bdev)
 			continue;
 
-		zone = reada_find_zone(fs_info, dev, logical, bbio);
+		zone = reada_find_zone(dev, logical, bbio);
 		if (!zone)
 			continue;
 
@@ -386,6 +390,10 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 		goto error;
 	}
 
+	ret = radix_tree_preload(GFP_KERNEL);
+	if (ret)
+		goto error;
+
 	/* insert extent in reada_tree + all per-device trees, all or nothing */
 	btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
 	spin_lock(&fs_info->reada_lock);
@@ -395,13 +403,16 @@ static struct reada_extent *reada_find_extent(struct btrfs_fs_info *fs_info,
 		re_exist->refcnt++;
 		spin_unlock(&fs_info->reada_lock);
 		btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
+		radix_tree_preload_end();
 		goto error;
 	}
 	if (ret) {
 		spin_unlock(&fs_info->reada_lock);
 		btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
+		radix_tree_preload_end();
 		goto error;
 	}
+	radix_tree_preload_end();
 	prev_dev = NULL;
 	dev_replace_is_ongoing = btrfs_dev_replace_is_ongoing(
 			&fs_info->dev_replace);
@@ -639,9 +650,9 @@ static int reada_pick_zone(struct btrfs_device *dev)
 	return 1;
 }
 
-static int reada_start_machine_dev(struct btrfs_fs_info *fs_info,
-				   struct btrfs_device *dev)
+static int reada_start_machine_dev(struct btrfs_device *dev)
 {
+	struct btrfs_fs_info *fs_info = dev->fs_info;
 	struct reada_extent *re = NULL;
 	int mirror_num = 0;
 	struct extent_buffer *eb = NULL;
@@ -754,8 +765,7 @@ static void __reada_start_machine(struct btrfs_fs_info *fs_info)
 		list_for_each_entry(device, &fs_devices->devices, dev_list) {
 			if (atomic_read(&device->reada_in_flight) <
 			    MAX_IN_FLIGHT)
-				enqueued += reada_start_machine_dev(fs_info,
-								    device);
+				enqueued += reada_start_machine_dev(device);
 		}
 		mutex_unlock(&fs_devices->device_list_mutex);
 		total += enqueued;
diff --git a/fs/btrfs/relocation.c b/fs/btrfs/relocation.c
index 379711048fb0..65661d1aae4e 100644
--- a/fs/btrfs/relocation.c
+++ b/fs/btrfs/relocation.c
@@ -1548,9 +1548,9 @@ again:
 		prev = node;
 		entry = rb_entry(node, struct btrfs_inode, rb_node);
 
-		if (objectid < btrfs_ino(&entry->vfs_inode))
+		if (objectid < btrfs_ino(entry))
 			node = node->rb_left;
-		else if (objectid > btrfs_ino(&entry->vfs_inode))
+		else if (objectid > btrfs_ino(entry))
 			node = node->rb_right;
 		else
 			break;
@@ -1558,7 +1558,7 @@ again:
 	if (!node) {
 		while (prev) {
 			entry = rb_entry(prev, struct btrfs_inode, rb_node);
-			if (objectid <= btrfs_ino(&entry->vfs_inode)) {
+			if (objectid <= btrfs_ino(entry)) {
 				node = prev;
 				break;
 			}
@@ -1573,7 +1573,7 @@ again:
 			return inode;
 		}
 
-		objectid = btrfs_ino(&entry->vfs_inode) + 1;
+		objectid = btrfs_ino(entry) + 1;
 		if (cond_resched_lock(&root->inode_lock))
 			goto again;
 
@@ -1609,8 +1609,8 @@ static int get_new_location(struct inode *reloc_inode, u64 *new_bytenr,
 		return -ENOMEM;
 
 	bytenr -= BTRFS_I(reloc_inode)->index_cnt;
-	ret = btrfs_lookup_file_extent(NULL, root, path, btrfs_ino(reloc_inode),
-				       bytenr, 0);
+	ret = btrfs_lookup_file_extent(NULL, root, path,
+			btrfs_ino(BTRFS_I(reloc_inode)), bytenr, 0);
 	if (ret < 0)
 		goto out;
 	if (ret > 0) {
@@ -1698,11 +1698,11 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 			if (first) {
 				inode = find_next_inode(root, key.objectid);
 				first = 0;
-			} else if (inode && btrfs_ino(inode) < key.objectid) {
+			} else if (inode && btrfs_ino(BTRFS_I(inode)) < key.objectid) {
 				btrfs_add_delayed_iput(inode);
 				inode = find_next_inode(root, key.objectid);
 			}
-			if (inode && btrfs_ino(inode) == key.objectid) {
+			if (inode && btrfs_ino(BTRFS_I(inode)) == key.objectid) {
 				end = key.offset +
 				      btrfs_file_extent_num_bytes(leaf, fi);
 				WARN_ON(!IS_ALIGNED(key.offset,
@@ -1714,8 +1714,8 @@ int replace_file_extents(struct btrfs_trans_handle *trans,
 				if (!ret)
 					continue;
 
-				btrfs_drop_extent_cache(inode, key.offset, end,
-							1);
+				btrfs_drop_extent_cache(BTRFS_I(inode),
+						key.offset,	end, 1);
 				unlock_extent(&BTRFS_I(inode)->io_tree,
 					      key.offset, end);
 			}
@@ -2088,7 +2088,7 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 		inode = find_next_inode(root, objectid);
 		if (!inode)
 			break;
-		ino = btrfs_ino(inode);
+		ino = btrfs_ino(BTRFS_I(inode));
 
 		if (ino > max_key->objectid) {
 			iput(inode);
@@ -2130,7 +2130,7 @@ static int invalidate_extent_cache(struct btrfs_root *root,
 
 		/* the lock_extent waits for readpage to complete */
 		lock_extent(&BTRFS_I(inode)->io_tree, start, end);
-		btrfs_drop_extent_cache(inode, start, end, 1);
+		btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 1);
 		unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
 	}
 	return 0;
@@ -3093,11 +3093,12 @@ int prealloc_file_extent_cluster(struct inode *inode,
 	u64 prealloc_start = cluster->start - offset;
 	u64 prealloc_end = cluster->end - offset;
 	u64 cur_offset;
+	struct extent_changeset *data_reserved = NULL;
 
 	BUG_ON(cluster->start != cluster->boundary[0]);
 	inode_lock(inode);
 
-	ret = btrfs_check_data_free_space(inode, prealloc_start,
+	ret = btrfs_check_data_free_space(inode, &data_reserved, prealloc_start,
 					  prealloc_end + 1 - prealloc_start);
 	if (ret)
 		goto out;
@@ -3113,8 +3114,8 @@ int prealloc_file_extent_cluster(struct inode *inode,
 		lock_extent(&BTRFS_I(inode)->io_tree, start, end);
 		num_bytes = end + 1 - start;
 		if (cur_offset < start)
-			btrfs_free_reserved_data_space(inode, cur_offset,
-					start - cur_offset);
+			btrfs_free_reserved_data_space(inode, data_reserved,
+					cur_offset, start - cur_offset);
 		ret = btrfs_prealloc_file_range(inode, 0, start,
 						num_bytes, num_bytes,
 						end + 1, &alloc_hint);
@@ -3125,10 +3126,11 @@ int prealloc_file_extent_cluster(struct inode *inode,
 		nr++;
 	}
 	if (cur_offset < prealloc_end)
-		btrfs_free_reserved_data_space(inode, cur_offset,
-				       prealloc_end + 1 - cur_offset);
+		btrfs_free_reserved_data_space(inode, data_reserved,
+				cur_offset, prealloc_end + 1 - cur_offset);
 out:
 	inode_unlock(inode);
+	extent_changeset_free(data_reserved);
 	return ret;
 }
 
@@ -3161,7 +3163,7 @@ int setup_extent_mapping(struct inode *inode, u64 start, u64 end,
 			free_extent_map(em);
 			break;
 		}
-		btrfs_drop_extent_cache(inode, start, end, 0);
+		btrfs_drop_extent_cache(BTRFS_I(inode), start, end, 0);
 	}
 	unlock_extent(&BTRFS_I(inode)->io_tree, start, end);
 	return ret;
@@ -3203,7 +3205,8 @@ static int relocate_file_extent_cluster(struct inode *inode,
 	index = (cluster->start - offset) >> PAGE_SHIFT;
 	last_index = (cluster->end - offset) >> PAGE_SHIFT;
 	while (index <= last_index) {
-		ret = btrfs_delalloc_reserve_metadata(inode, PAGE_SIZE);
+		ret = btrfs_delalloc_reserve_metadata(BTRFS_I(inode),
+				PAGE_SIZE);
 		if (ret)
 			goto out;
 
@@ -3215,7 +3218,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 			page = find_or_create_page(inode->i_mapping, index,
 						   mask);
 			if (!page) {
-				btrfs_delalloc_release_metadata(inode,
+				btrfs_delalloc_release_metadata(BTRFS_I(inode),
 							PAGE_SIZE);
 				ret = -ENOMEM;
 				goto out;
@@ -3234,7 +3237,7 @@ static int relocate_file_extent_cluster(struct inode *inode,
 			if (!PageUptodate(page)) {
 				unlock_page(page);
 				put_page(page);
-				btrfs_delalloc_release_metadata(inode,
+				btrfs_delalloc_release_metadata(BTRFS_I(inode),
 							PAGE_SIZE);
 				ret = -EIO;
 				goto out;
@@ -3543,7 +3546,7 @@ truncate:
 		goto out;
 	}
 
-	ret = btrfs_truncate_free_space_cache(root, trans, block_group, inode);
+	ret = btrfs_truncate_free_space_cache(trans, block_group, inode);
 
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
@@ -4245,7 +4248,7 @@ struct inode *create_reloc_inode(struct btrfs_fs_info *fs_info,
 	BUG_ON(IS_ERR(inode) || is_bad_inode(inode));
 	BTRFS_I(inode)->index_cnt = group->key.objectid;
 
-	err = btrfs_orphan_add(trans, inode);
+	err = btrfs_orphan_add(trans, BTRFS_I(inode));
 out:
 	btrfs_end_transaction(trans);
 	btrfs_btree_balance_dirty(fs_info);
@@ -4268,8 +4271,7 @@ static struct reloc_control *alloc_reloc_control(struct btrfs_fs_info *fs_info)
 	INIT_LIST_HEAD(&rc->reloc_roots);
 	backref_cache_init(&rc->backref_cache);
 	mapping_tree_init(&rc->reloc_root_tree);
-	extent_io_tree_init(&rc->processed_blocks,
-			    fs_info->btree_inode->i_mapping);
+	extent_io_tree_init(&rc->processed_blocks, NULL);
 	return rc;
 }
 
@@ -4334,7 +4336,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 	rc->block_group = btrfs_lookup_block_group(fs_info, group_start);
 	BUG_ON(!rc->block_group);
 
-	ret = btrfs_inc_block_group_ro(extent_root, rc->block_group);
+	ret = btrfs_inc_block_group_ro(fs_info, rc->block_group);
 	if (ret) {
 		err = ret;
 		goto out;
@@ -4347,8 +4349,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 		goto out;
 	}
 
-	inode = lookup_free_space_inode(fs_info->tree_root, rc->block_group,
-					path);
+	inode = lookup_free_space_inode(fs_info, rc->block_group, path);
 	btrfs_free_path(path);
 
 	if (!IS_ERR(inode))
@@ -4372,7 +4373,7 @@ int btrfs_relocate_block_group(struct btrfs_fs_info *fs_info, u64 group_start)
 
 	btrfs_wait_block_group_reservations(rc->block_group);
 	btrfs_wait_nocow_writers(rc->block_group);
-	btrfs_wait_ordered_roots(fs_info, -1,
+	btrfs_wait_ordered_roots(fs_info, U64_MAX,
 				 rc->block_group->key.objectid,
 				 rc->block_group->key.offset);
 
diff --git a/fs/btrfs/root-tree.c b/fs/btrfs/root-tree.c
index 4c6735491ee0..460db0cb2d07 100644
--- a/fs/btrfs/root-tree.c
+++ b/fs/btrfs/root-tree.c
@@ -74,7 +74,7 @@ static void btrfs_read_root_item(struct extent_buffer *eb, int slot,
  *
  * If we find something return 0, otherwise > 0, < 0 on error.
  */
-int btrfs_find_root(struct btrfs_root *root, struct btrfs_key *search_key,
+int btrfs_find_root(struct btrfs_root *root, const struct btrfs_key *search_key,
 		    struct btrfs_path *path, struct btrfs_root_item *root_item,
 		    struct btrfs_key *root_key)
 {
@@ -207,7 +207,7 @@ out:
 }
 
 int btrfs_insert_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		      struct btrfs_key *key, struct btrfs_root_item *item)
+		      const struct btrfs_key *key, struct btrfs_root_item *item)
 {
 	/*
 	 * Make sure generation v1 and v2 match. See update_root for details.
@@ -337,7 +337,7 @@ int btrfs_find_orphan_roots(struct btrfs_fs_info *fs_info)
 
 /* drop the root item for 'key' from 'root' */
 int btrfs_del_root(struct btrfs_trans_handle *trans, struct btrfs_root *root,
-		   struct btrfs_key *key)
+		   const struct btrfs_key *key)
 {
 	struct btrfs_path *path;
 	int ret;
@@ -390,6 +390,13 @@ again:
 		WARN_ON(btrfs_root_ref_dirid(leaf, ref) != dirid);
 		WARN_ON(btrfs_root_ref_name_len(leaf, ref) != name_len);
 		ptr = (unsigned long)(ref + 1);
+		ret = btrfs_is_name_len_valid(leaf, path->slots[0], ptr,
+					      name_len);
+		if (!ret) {
+			err = -EIO;
+			goto out;
+		}
+
 		WARN_ON(memcmp_extent_buffer(leaf, name, ptr, name_len));
 		*sequence = btrfs_root_ref_sequence(leaf, ref);
 
@@ -501,8 +508,9 @@ void btrfs_update_root_times(struct btrfs_trans_handle *trans,
 			     struct btrfs_root *root)
 {
 	struct btrfs_root_item *item = &root->root_item;
-	struct timespec ct = current_fs_time(root->fs_info->sb);
+	struct timespec ct;
 
+	ktime_get_real_ts(&ct);
 	spin_lock(&root->root_item_lock);
 	btrfs_set_root_ctransid(item, trans->transid);
 	btrfs_set_stack_timespec_sec(&item->ctime, ct.tv_sec);
diff --git a/fs/btrfs/scrub.c b/fs/btrfs/scrub.c
index 9a94670536a6..6f1e4c984b94 100644
--- a/fs/btrfs/scrub.c
+++ b/fs/btrfs/scrub.c
@@ -18,6 +18,7 @@
 
 #include <linux/blkdev.h>
 #include <linux/ratelimit.h>
+#include <linux/sched/mm.h>
 #include "ctree.h"
 #include "volumes.h"
 #include "disk-io.h"
@@ -64,7 +65,7 @@ struct scrub_ctx;
 #define SCRUB_MAX_PAGES_PER_BLOCK	16	/* 64k per node/leaf/sector */
 
 struct scrub_recover {
-	atomic_t		refs;
+	refcount_t		refs;
 	struct btrfs_bio	*bbio;
 	u64			map_length;
 };
@@ -95,7 +96,7 @@ struct scrub_bio {
 	struct scrub_ctx	*sctx;
 	struct btrfs_device	*dev;
 	struct bio		*bio;
-	int			err;
+	blk_status_t		status;
 	u64			logical;
 	u64			physical;
 #if SCRUB_PAGES_PER_WR_BIO >= SCRUB_PAGES_PER_RD_BIO
@@ -112,7 +113,7 @@ struct scrub_block {
 	struct scrub_page	*pagev[SCRUB_MAX_PAGES_PER_BLOCK];
 	int			page_count;
 	atomic_t		outstanding_pages;
-	atomic_t		refs; /* free mem on transition to zero */
+	refcount_t		refs; /* free mem on transition to zero */
 	struct scrub_ctx	*sctx;
 	struct scrub_parity	*sparity;
 	struct {
@@ -140,9 +141,9 @@ struct scrub_parity {
 
 	int			nsectors;
 
-	int			stripe_len;
+	u64			stripe_len;
 
-	atomic_t		refs;
+	refcount_t		refs;
 
 	struct list_head	spages;
 
@@ -161,14 +162,6 @@ struct scrub_parity {
 	unsigned long		bitmap[0];
 };
 
-struct scrub_wr_ctx {
-	struct scrub_bio *wr_curr_bio;
-	struct btrfs_device *tgtdev;
-	int pages_per_wr_bio; /* <= SCRUB_PAGES_PER_WR_BIO */
-	atomic_t flush_all_writes;
-	struct mutex wr_lock;
-};
-
 struct scrub_ctx {
 	struct scrub_bio	*bios[SCRUB_BIOS_PER_SCTX];
 	struct btrfs_fs_info	*fs_info;
@@ -183,11 +176,14 @@ struct scrub_ctx {
 	atomic_t		cancel_req;
 	int			readonly;
 	int			pages_per_rd_bio;
-	u32			sectorsize;
-	u32			nodesize;
 
 	int			is_dev_replace;
-	struct scrub_wr_ctx	wr_ctx;
+
+	struct scrub_bio        *wr_curr_bio;
+	struct mutex            wr_lock;
+	int                     pages_per_wr_bio; /* <= SCRUB_PAGES_PER_WR_BIO */
+	atomic_t                flush_all_writes;
+	struct btrfs_device     *wr_tgtdev;
 
 	/*
 	 * statistics
@@ -202,7 +198,7 @@ struct scrub_ctx {
 	 * doesn't free the scrub context before or while the workers are
 	 * doing the wakeup() call.
 	 */
-	atomic_t                refs;
+	refcount_t              refs;
 };
 
 struct scrub_fixup_nodatasum {
@@ -240,6 +236,13 @@ struct scrub_warning {
 	struct btrfs_device	*dev;
 };
 
+struct full_stripe_lock {
+	struct rb_node node;
+	u64 logical;
+	u64 refs;
+	struct mutex mutex;
+};
+
 static void scrub_pending_bio_inc(struct scrub_ctx *sctx);
 static void scrub_pending_bio_dec(struct scrub_ctx *sctx);
 static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx);
@@ -282,12 +285,6 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
 			       u64 *extent_physical,
 			       struct btrfs_device **extent_dev,
 			       int *extent_mirror_num);
-static int scrub_setup_wr_ctx(struct scrub_ctx *sctx,
-			      struct scrub_wr_ctx *wr_ctx,
-			      struct btrfs_fs_info *fs_info,
-			      struct btrfs_device *dev,
-			      int is_dev_replace);
-static void scrub_free_wr_ctx(struct scrub_wr_ctx *wr_ctx);
 static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
 				    struct scrub_page *spage);
 static void scrub_wr_submit(struct scrub_ctx *sctx);
@@ -307,7 +304,7 @@ static void scrub_put_ctx(struct scrub_ctx *sctx);
 
 static void scrub_pending_bio_inc(struct scrub_ctx *sctx)
 {
-	atomic_inc(&sctx->refs);
+	refcount_inc(&sctx->refs);
 	atomic_inc(&sctx->bios_in_flight);
 }
 
@@ -351,6 +348,222 @@ static void scrub_blocked_if_needed(struct btrfs_fs_info *fs_info)
 }
 
 /*
+ * Insert new full stripe lock into full stripe locks tree
+ *
+ * Return pointer to existing or newly inserted full_stripe_lock structure if
+ * everything works well.
+ * Return ERR_PTR(-ENOMEM) if we failed to allocate memory
+ *
+ * NOTE: caller must hold full_stripe_locks_root->lock before calling this
+ * function
+ */
+static struct full_stripe_lock *insert_full_stripe_lock(
+		struct btrfs_full_stripe_locks_tree *locks_root,
+		u64 fstripe_logical)
+{
+	struct rb_node **p;
+	struct rb_node *parent = NULL;
+	struct full_stripe_lock *entry;
+	struct full_stripe_lock *ret;
+
+	WARN_ON(!mutex_is_locked(&locks_root->lock));
+
+	p = &locks_root->root.rb_node;
+	while (*p) {
+		parent = *p;
+		entry = rb_entry(parent, struct full_stripe_lock, node);
+		if (fstripe_logical < entry->logical) {
+			p = &(*p)->rb_left;
+		} else if (fstripe_logical > entry->logical) {
+			p = &(*p)->rb_right;
+		} else {
+			entry->refs++;
+			return entry;
+		}
+	}
+
+	/* Insert new lock */
+	ret = kmalloc(sizeof(*ret), GFP_KERNEL);
+	if (!ret)
+		return ERR_PTR(-ENOMEM);
+	ret->logical = fstripe_logical;
+	ret->refs = 1;
+	mutex_init(&ret->mutex);
+
+	rb_link_node(&ret->node, parent, p);
+	rb_insert_color(&ret->node, &locks_root->root);
+	return ret;
+}
+
+/*
+ * Search for a full stripe lock of a block group
+ *
+ * Return pointer to existing full stripe lock if found
+ * Return NULL if not found
+ */
+static struct full_stripe_lock *search_full_stripe_lock(
+		struct btrfs_full_stripe_locks_tree *locks_root,
+		u64 fstripe_logical)
+{
+	struct rb_node *node;
+	struct full_stripe_lock *entry;
+
+	WARN_ON(!mutex_is_locked(&locks_root->lock));
+
+	node = locks_root->root.rb_node;
+	while (node) {
+		entry = rb_entry(node, struct full_stripe_lock, node);
+		if (fstripe_logical < entry->logical)
+			node = node->rb_left;
+		else if (fstripe_logical > entry->logical)
+			node = node->rb_right;
+		else
+			return entry;
+	}
+	return NULL;
+}
+
+/*
+ * Helper to get full stripe logical from a normal bytenr.
+ *
+ * Caller must ensure @cache is a RAID56 block group.
+ */
+static u64 get_full_stripe_logical(struct btrfs_block_group_cache *cache,
+				   u64 bytenr)
+{
+	u64 ret;
+
+	/*
+	 * Due to chunk item size limit, full stripe length should not be
+	 * larger than U32_MAX. Just a sanity check here.
+	 */
+	WARN_ON_ONCE(cache->full_stripe_len >= U32_MAX);
+
+	/*
+	 * round_down() can only handle power of 2, while RAID56 full
+	 * stripe length can be 64KiB * n, so we need to manually round down.
+	 */
+	ret = div64_u64(bytenr - cache->key.objectid, cache->full_stripe_len) *
+		cache->full_stripe_len + cache->key.objectid;
+	return ret;
+}
+
+/*
+ * Lock a full stripe to avoid concurrency of recovery and read
+ *
+ * It's only used for profiles with parities (RAID5/6), for other profiles it
+ * does nothing.
+ *
+ * Return 0 if we locked full stripe covering @bytenr, with a mutex held.
+ * So caller must call unlock_full_stripe() at the same context.
+ *
+ * Return <0 if encounters error.
+ */
+static int lock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr,
+			    bool *locked_ret)
+{
+	struct btrfs_block_group_cache *bg_cache;
+	struct btrfs_full_stripe_locks_tree *locks_root;
+	struct full_stripe_lock *existing;
+	u64 fstripe_start;
+	int ret = 0;
+
+	*locked_ret = false;
+	bg_cache = btrfs_lookup_block_group(fs_info, bytenr);
+	if (!bg_cache) {
+		ASSERT(0);
+		return -ENOENT;
+	}
+
+	/* Profiles not based on parity don't need full stripe lock */
+	if (!(bg_cache->flags & BTRFS_BLOCK_GROUP_RAID56_MASK))
+		goto out;
+	locks_root = &bg_cache->full_stripe_locks_root;
+
+	fstripe_start = get_full_stripe_logical(bg_cache, bytenr);
+
+	/* Now insert the full stripe lock */
+	mutex_lock(&locks_root->lock);
+	existing = insert_full_stripe_lock(locks_root, fstripe_start);
+	mutex_unlock(&locks_root->lock);
+	if (IS_ERR(existing)) {
+		ret = PTR_ERR(existing);
+		goto out;
+	}
+	mutex_lock(&existing->mutex);
+	*locked_ret = true;
+out:
+	btrfs_put_block_group(bg_cache);
+	return ret;
+}
+
+/*
+ * Unlock a full stripe.
+ *
+ * NOTE: Caller must ensure it's the same context calling corresponding
+ * lock_full_stripe().
+ *
+ * Return 0 if we unlock full stripe without problem.
+ * Return <0 for error
+ */
+static int unlock_full_stripe(struct btrfs_fs_info *fs_info, u64 bytenr,
+			      bool locked)
+{
+	struct btrfs_block_group_cache *bg_cache;
+	struct btrfs_full_stripe_locks_tree *locks_root;
+	struct full_stripe_lock *fstripe_lock;
+	u64 fstripe_start;
+	bool freeit = false;
+	int ret = 0;
+
+	/* If we didn't acquire full stripe lock, no need to continue */
+	if (!locked)
+		return 0;
+
+	bg_cache = btrfs_lookup_block_group(fs_info, bytenr);
+	if (!bg_cache) {
+		ASSERT(0);
+		return -ENOENT;
+	}
+	if (!(bg_cache->flags & BTRFS_BLOCK_GROUP_RAID56_MASK))
+		goto out;
+
+	locks_root = &bg_cache->full_stripe_locks_root;
+	fstripe_start = get_full_stripe_logical(bg_cache, bytenr);
+
+	mutex_lock(&locks_root->lock);
+	fstripe_lock = search_full_stripe_lock(locks_root, fstripe_start);
+	/* Unpaired unlock_full_stripe() detected */
+	if (!fstripe_lock) {
+		WARN_ON(1);
+		ret = -ENOENT;
+		mutex_unlock(&locks_root->lock);
+		goto out;
+	}
+
+	if (fstripe_lock->refs == 0) {
+		WARN_ON(1);
+		btrfs_warn(fs_info, "full stripe lock at %llu refcount underflow",
+			fstripe_lock->logical);
+	} else {
+		fstripe_lock->refs--;
+	}
+
+	if (fstripe_lock->refs == 0) {
+		rb_erase(&fstripe_lock->node, &locks_root->root);
+		freeit = true;
+	}
+	mutex_unlock(&locks_root->lock);
+
+	mutex_unlock(&fstripe_lock->mutex);
+	if (freeit)
+		kfree(fstripe_lock);
+out:
+	btrfs_put_block_group(bg_cache);
+	return ret;
+}
+
+/*
  * used for workers that require transaction commits (i.e., for the
  * NOCOW case)
  */
@@ -358,7 +571,7 @@ static void scrub_pending_trans_workers_inc(struct scrub_ctx *sctx)
 {
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 
-	atomic_inc(&sctx->refs);
+	refcount_inc(&sctx->refs);
 	/*
 	 * increment scrubs_running to prevent cancel requests from
 	 * completing as long as a worker is running. we must also
@@ -422,8 +635,6 @@ static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx)
 	if (!sctx)
 		return;
 
-	scrub_free_wr_ctx(&sctx->wr_ctx);
-
 	/* this can happen when scrub is cancelled */
 	if (sctx->curr != -1) {
 		struct scrub_bio *sbio = sctx->bios[sctx->curr];
@@ -443,13 +654,14 @@ static noinline_for_stack void scrub_free_ctx(struct scrub_ctx *sctx)
 		kfree(sbio);
 	}
 
+	kfree(sctx->wr_curr_bio);
 	scrub_free_csums(sctx);
 	kfree(sctx);
 }
 
 static void scrub_put_ctx(struct scrub_ctx *sctx)
 {
-	if (atomic_dec_and_test(&sctx->refs))
+	if (refcount_dec_and_test(&sctx->refs))
 		scrub_free_ctx(sctx);
 }
 
@@ -459,12 +671,11 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 	struct scrub_ctx *sctx;
 	int		i;
 	struct btrfs_fs_info *fs_info = dev->fs_info;
-	int ret;
 
 	sctx = kzalloc(sizeof(*sctx), GFP_KERNEL);
 	if (!sctx)
 		goto nomem;
-	atomic_set(&sctx->refs, 1);
+	refcount_set(&sctx->refs, 1);
 	sctx->is_dev_replace = is_dev_replace;
 	sctx->pages_per_rd_bio = SCRUB_PAGES_PER_RD_BIO;
 	sctx->curr = -1;
@@ -489,8 +700,6 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 			sctx->bios[i]->next_free = -1;
 	}
 	sctx->first_free = 0;
-	sctx->nodesize = fs_info->nodesize;
-	sctx->sectorsize = fs_info->sectorsize;
 	atomic_set(&sctx->bios_in_flight, 0);
 	atomic_set(&sctx->workers_pending, 0);
 	atomic_set(&sctx->cancel_req, 0);
@@ -501,12 +710,16 @@ struct scrub_ctx *scrub_setup_ctx(struct btrfs_device *dev, int is_dev_replace)
 	spin_lock_init(&sctx->stat_lock);
 	init_waitqueue_head(&sctx->list_wait);
 
-	ret = scrub_setup_wr_ctx(sctx, &sctx->wr_ctx, fs_info,
-				 fs_info->dev_replace.tgtdev, is_dev_replace);
-	if (ret) {
-		scrub_free_ctx(sctx);
-		return ERR_PTR(ret);
+	WARN_ON(sctx->wr_curr_bio != NULL);
+	mutex_init(&sctx->wr_lock);
+	sctx->wr_curr_bio = NULL;
+	if (is_dev_replace) {
+		WARN_ON(!fs_info->dev_replace.tgtdev);
+		sctx->pages_per_wr_bio = SCRUB_PAGES_PER_WR_BIO;
+		sctx->wr_tgtdev = fs_info->dev_replace.tgtdev;
+		atomic_set(&sctx->flush_all_writes, 0);
 	}
+
 	return sctx;
 
 nomem:
@@ -521,6 +734,7 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root,
 	u32 nlink;
 	int ret;
 	int i;
+	unsigned nofs_flag;
 	struct extent_buffer *eb;
 	struct btrfs_inode_item *inode_item;
 	struct scrub_warning *swarn = warn_ctx;
@@ -559,7 +773,14 @@ static int scrub_print_warning_inode(u64 inum, u64 offset, u64 root,
 	nlink = btrfs_inode_nlink(eb, inode_item);
 	btrfs_release_path(swarn->path);
 
+	/*
+	 * init_path might indirectly call vmalloc, or use GFP_KERNEL. Scrub
+	 * uses GFP_NOFS in this context, so we keep it consistent but it does
+	 * not seem to be strictly necessary.
+	 */
+	nofs_flag = memalloc_nofs_save();
 	ipath = init_ipath(4096, local_root, swarn->path);
+	memalloc_nofs_restore(nofs_flag);
 	if (IS_ERR(ipath)) {
 		ret = PTR_ERR(ipath);
 		ipath = NULL;
@@ -733,7 +954,7 @@ static int scrub_fixup_readpage(u64 inum, u64 offset, u64 root, void *fixup_ctx)
 			ret = -EIO;
 			goto out;
 		}
-		ret = repair_io_failure(inode, offset, PAGE_SIZE,
+		ret = repair_io_failure(fs_info, inum, offset, PAGE_SIZE,
 					fixup->logical, page,
 					offset - page_offset(page),
 					fixup->mirror_num);
@@ -859,12 +1080,14 @@ out:
 
 static inline void scrub_get_recover(struct scrub_recover *recover)
 {
-	atomic_inc(&recover->refs);
+	refcount_inc(&recover->refs);
 }
 
-static inline void scrub_put_recover(struct scrub_recover *recover)
+static inline void scrub_put_recover(struct btrfs_fs_info *fs_info,
+				     struct scrub_recover *recover)
 {
-	if (atomic_dec_and_test(&recover->refs)) {
+	if (refcount_dec_and_test(&recover->refs)) {
+		btrfs_bio_counter_dec(fs_info);
 		btrfs_put_bbio(recover->bbio);
 		kfree(recover);
 	}
@@ -894,6 +1117,7 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 	int mirror_index;
 	int page_num;
 	int success;
+	bool full_stripe_locked;
 	static DEFINE_RATELIMIT_STATE(_rs, DEFAULT_RATELIMIT_INTERVAL,
 				      DEFAULT_RATELIMIT_BURST);
 
@@ -919,6 +1143,24 @@ static int scrub_handle_errored_block(struct scrub_block *sblock_to_check)
 	have_csum = sblock_to_check->pagev[0]->have_csum;
 	dev = sblock_to_check->pagev[0]->dev;
 
+	/*
+	 * For RAID5/6, race can happen for a different device scrub thread.
+	 * For data corruption, Parity and Data threads will both try
+	 * to recovery the data.
+	 * Race can lead to doubly added csum error, or even unrecoverable
+	 * error.
+	 */
+	ret = lock_full_stripe(fs_info, logical, &full_stripe_locked);
+	if (ret < 0) {
+		spin_lock(&sctx->stat_lock);
+		if (ret == -ENOMEM)
+			sctx->stat.malloc_errors++;
+		sctx->stat.read_errors++;
+		sctx->stat.uncorrectable_errors++;
+		spin_unlock(&sctx->stat_lock);
+		return ret;
+	}
+
 	if (sctx->is_dev_replace && !is_metadata && !have_csum) {
 		sblocks_for_recheck = NULL;
 		goto nodatasum_case;
@@ -1243,7 +1485,7 @@ out:
 				sblock->pagev[page_index]->sblock = NULL;
 				recover = sblock->pagev[page_index]->recover;
 				if (recover) {
-					scrub_put_recover(recover);
+					scrub_put_recover(fs_info, recover);
 					sblock->pagev[page_index]->recover =
 									NULL;
 				}
@@ -1253,6 +1495,9 @@ out:
 		kfree(sblocks_for_recheck);
 	}
 
+	ret = unlock_full_stripe(fs_info, logical, full_stripe_locked);
+	if (ret < 0)
+		return ret;
 	return 0;
 }
 
@@ -1332,20 +1577,23 @@ static int scrub_setup_recheck_block(struct scrub_block *original_sblock,
 		 * with a length of PAGE_SIZE, each returned stripe
 		 * represents one mirror
 		 */
+		btrfs_bio_counter_inc_blocked(fs_info);
 		ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS,
-				logical, &mapped_length, &bbio, 0, 1);
+				logical, &mapped_length, &bbio);
 		if (ret || !bbio || mapped_length < sublen) {
 			btrfs_put_bbio(bbio);
+			btrfs_bio_counter_dec(fs_info);
 			return -EIO;
 		}
 
 		recover = kzalloc(sizeof(struct scrub_recover), GFP_NOFS);
 		if (!recover) {
 			btrfs_put_bbio(bbio);
+			btrfs_bio_counter_dec(fs_info);
 			return -ENOMEM;
 		}
 
-		atomic_set(&recover->refs, 1);
+		refcount_set(&recover->refs, 1);
 		recover->bbio = bbio;
 		recover->map_length = mapped_length;
 
@@ -1367,7 +1615,7 @@ leave_nomem:
 				spin_lock(&sctx->stat_lock);
 				sctx->stat.malloc_errors++;
 				spin_unlock(&sctx->stat_lock);
-				scrub_put_recover(recover);
+				scrub_put_recover(fs_info, recover);
 				return -ENOMEM;
 			}
 			scrub_page_get(page);
@@ -1409,7 +1657,7 @@ leave_nomem:
 			scrub_get_recover(recover);
 			page->recover = recover;
 		}
-		scrub_put_recover(recover);
+		scrub_put_recover(fs_info, recover);
 		length -= sublen;
 		logical += sublen;
 		page_index++;
@@ -1420,14 +1668,14 @@ leave_nomem:
 
 struct scrub_bio_ret {
 	struct completion event;
-	int error;
+	blk_status_t status;
 };
 
 static void scrub_bio_wait_endio(struct bio *bio)
 {
 	struct scrub_bio_ret *ret = bio->bi_private;
 
-	ret->error = bio->bi_error;
+	ret->status = bio->bi_status;
 	complete(&ret->event);
 }
 
@@ -1445,7 +1693,7 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
 	int ret;
 
 	init_completion(&done.event);
-	done.error = 0;
+	done.status = 0;
 	bio->bi_iter.bi_sector = page->logical >> 9;
 	bio->bi_private = &done;
 	bio->bi_end_io = scrub_bio_wait_endio;
@@ -1457,7 +1705,7 @@ static int scrub_submit_raid56_bio_wait(struct btrfs_fs_info *fs_info,
 		return ret;
 
 	wait_for_completion(&done.event);
-	if (done.error)
+	if (done.status)
 		return -EIO;
 
 	return 0;
@@ -1489,24 +1737,23 @@ static void scrub_recheck_block(struct btrfs_fs_info *fs_info,
 		}
 
 		WARN_ON(!page->page);
-		bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
-		if (!bio) {
-			page->io_error = 1;
-			sblock->no_io_error_seen = 0;
-			continue;
-		}
+		bio = btrfs_io_bio_alloc(1);
 		bio->bi_bdev = page->dev->bdev;
 
 		bio_add_page(bio, page->page, PAGE_SIZE, 0);
 		if (!retry_failed_mirror && scrub_is_page_on_raid56(page)) {
-			if (scrub_submit_raid56_bio_wait(fs_info, bio, page))
+			if (scrub_submit_raid56_bio_wait(fs_info, bio, page)) {
+				page->io_error = 1;
 				sblock->no_io_error_seen = 0;
+			}
 		} else {
 			bio->bi_iter.bi_sector = page->physical >> 9;
 			bio_set_op_attrs(bio, REQ_OP_READ, 0);
 
-			if (btrfsic_submit_bio_wait(bio))
+			if (btrfsic_submit_bio_wait(bio)) {
+				page->io_error = 1;
 				sblock->no_io_error_seen = 0;
+			}
 		}
 
 		bio_put(bio);
@@ -1578,9 +1825,7 @@ static int scrub_repair_page_from_good_copy(struct scrub_block *sblock_bad,
 			return -EIO;
 		}
 
-		bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
-		if (!bio)
-			return -EIO;
+		bio = btrfs_io_bio_alloc(1);
 		bio->bi_bdev = page_bad->dev->bdev;
 		bio->bi_iter.bi_sector = page_bad->physical >> 9;
 		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
@@ -1636,7 +1881,7 @@ static int scrub_write_page_to_dev_replace(struct scrub_block *sblock,
 	if (spage->io_error) {
 		void *mapped_buffer = kmap_atomic(spage->page);
 
-		memset(mapped_buffer, 0, PAGE_SIZE);
+		clear_page(mapped_buffer);
 		flush_dcache_page(spage->page);
 		kunmap_atomic(mapped_buffer);
 	}
@@ -1646,37 +1891,31 @@ static int scrub_write_page_to_dev_replace(struct scrub_block *sblock,
 static int scrub_add_page_to_wr_bio(struct scrub_ctx *sctx,
 				    struct scrub_page *spage)
 {
-	struct scrub_wr_ctx *wr_ctx = &sctx->wr_ctx;
 	struct scrub_bio *sbio;
 	int ret;
 
-	mutex_lock(&wr_ctx->wr_lock);
+	mutex_lock(&sctx->wr_lock);
 again:
-	if (!wr_ctx->wr_curr_bio) {
-		wr_ctx->wr_curr_bio = kzalloc(sizeof(*wr_ctx->wr_curr_bio),
+	if (!sctx->wr_curr_bio) {
+		sctx->wr_curr_bio = kzalloc(sizeof(*sctx->wr_curr_bio),
 					      GFP_KERNEL);
-		if (!wr_ctx->wr_curr_bio) {
-			mutex_unlock(&wr_ctx->wr_lock);
+		if (!sctx->wr_curr_bio) {
+			mutex_unlock(&sctx->wr_lock);
 			return -ENOMEM;
 		}
-		wr_ctx->wr_curr_bio->sctx = sctx;
-		wr_ctx->wr_curr_bio->page_count = 0;
+		sctx->wr_curr_bio->sctx = sctx;
+		sctx->wr_curr_bio->page_count = 0;
 	}
-	sbio = wr_ctx->wr_curr_bio;
+	sbio = sctx->wr_curr_bio;
 	if (sbio->page_count == 0) {
 		struct bio *bio;
 
 		sbio->physical = spage->physical_for_dev_replace;
 		sbio->logical = spage->logical;
-		sbio->dev = wr_ctx->tgtdev;
+		sbio->dev = sctx->wr_tgtdev;
 		bio = sbio->bio;
 		if (!bio) {
-			bio = btrfs_io_bio_alloc(GFP_KERNEL,
-					wr_ctx->pages_per_wr_bio);
-			if (!bio) {
-				mutex_unlock(&wr_ctx->wr_lock);
-				return -ENOMEM;
-			}
+			bio = btrfs_io_bio_alloc(sctx->pages_per_wr_bio);
 			sbio->bio = bio;
 		}
 
@@ -1685,7 +1924,7 @@ again:
 		bio->bi_bdev = sbio->dev->bdev;
 		bio->bi_iter.bi_sector = sbio->physical >> 9;
 		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-		sbio->err = 0;
+		sbio->status = 0;
 	} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
 		   spage->physical_for_dev_replace ||
 		   sbio->logical + sbio->page_count * PAGE_SIZE !=
@@ -1699,7 +1938,7 @@ again:
 		if (sbio->page_count < 1) {
 			bio_put(sbio->bio);
 			sbio->bio = NULL;
-			mutex_unlock(&wr_ctx->wr_lock);
+			mutex_unlock(&sctx->wr_lock);
 			return -EIO;
 		}
 		scrub_wr_submit(sctx);
@@ -1709,23 +1948,22 @@ again:
 	sbio->pagev[sbio->page_count] = spage;
 	scrub_page_get(spage);
 	sbio->page_count++;
-	if (sbio->page_count == wr_ctx->pages_per_wr_bio)
+	if (sbio->page_count == sctx->pages_per_wr_bio)
 		scrub_wr_submit(sctx);
-	mutex_unlock(&wr_ctx->wr_lock);
+	mutex_unlock(&sctx->wr_lock);
 
 	return 0;
 }
 
 static void scrub_wr_submit(struct scrub_ctx *sctx)
 {
-	struct scrub_wr_ctx *wr_ctx = &sctx->wr_ctx;
 	struct scrub_bio *sbio;
 
-	if (!wr_ctx->wr_curr_bio)
+	if (!sctx->wr_curr_bio)
 		return;
 
-	sbio = wr_ctx->wr_curr_bio;
-	wr_ctx->wr_curr_bio = NULL;
+	sbio = sctx->wr_curr_bio;
+	sctx->wr_curr_bio = NULL;
 	WARN_ON(!sbio->bio->bi_bdev);
 	scrub_pending_bio_inc(sctx);
 	/* process all writes in a single worker thread. Then the block layer
@@ -1740,7 +1978,7 @@ static void scrub_wr_bio_end_io(struct bio *bio)
 	struct scrub_bio *sbio = bio->bi_private;
 	struct btrfs_fs_info *fs_info = sbio->dev->fs_info;
 
-	sbio->err = bio->bi_error;
+	sbio->status = bio->bi_status;
 	sbio->bio = bio;
 
 	btrfs_init_work(&sbio->work, btrfs_scrubwrc_helper,
@@ -1755,7 +1993,7 @@ static void scrub_wr_bio_end_io_worker(struct btrfs_work *work)
 	int i;
 
 	WARN_ON(sbio->page_count > SCRUB_PAGES_PER_WR_BIO);
-	if (sbio->err) {
+	if (sbio->status) {
 		struct btrfs_dev_replace *dev_replace =
 			&sbio->sctx->fs_info->dev_replace;
 
@@ -1829,7 +2067,7 @@ static int scrub_checksum_data(struct scrub_block *sblock)
 	page = sblock->pagev[0]->page;
 	buffer = kmap_atomic(page);
 
-	len = sctx->sectorsize;
+	len = sctx->fs_info->sectorsize;
 	index = 0;
 	for (;;) {
 		u64 l = min_t(u64, len, PAGE_SIZE);
@@ -1894,7 +2132,7 @@ static int scrub_checksum_tree_block(struct scrub_block *sblock)
 		   BTRFS_UUID_SIZE))
 		sblock->header_error = 1;
 
-	len = sctx->nodesize - BTRFS_CSUM_SIZE;
+	len = sctx->fs_info->nodesize - BTRFS_CSUM_SIZE;
 	mapped_size = PAGE_SIZE - BTRFS_CSUM_SIZE;
 	p = ((u8 *)mapped_buffer) + BTRFS_CSUM_SIZE;
 	index = 0;
@@ -2000,12 +2238,12 @@ static int scrub_checksum_super(struct scrub_block *sblock)
 
 static void scrub_block_get(struct scrub_block *sblock)
 {
-	atomic_inc(&sblock->refs);
+	refcount_inc(&sblock->refs);
 }
 
 static void scrub_block_put(struct scrub_block *sblock)
 {
-	if (atomic_dec_and_test(&sblock->refs)) {
+	if (refcount_dec_and_test(&sblock->refs)) {
 		int i;
 
 		if (sblock->sparity)
@@ -2077,10 +2315,7 @@ again:
 		sbio->dev = spage->dev;
 		bio = sbio->bio;
 		if (!bio) {
-			bio = btrfs_io_bio_alloc(GFP_KERNEL,
-					sctx->pages_per_rd_bio);
-			if (!bio)
-				return -ENOMEM;
+			bio = btrfs_io_bio_alloc(sctx->pages_per_rd_bio);
 			sbio->bio = bio;
 		}
 
@@ -2089,7 +2324,7 @@ again:
 		bio->bi_bdev = sbio->dev->bdev;
 		bio->bi_iter.bi_sector = sbio->physical >> 9;
 		bio_set_op_attrs(bio, REQ_OP_READ, 0);
-		sbio->err = 0;
+		sbio->status = 0;
 	} else if (sbio->physical + sbio->page_count * PAGE_SIZE !=
 		   spage->physical ||
 		   sbio->logical + sbio->page_count * PAGE_SIZE !=
@@ -2125,7 +2360,7 @@ static void scrub_missing_raid56_end_io(struct bio *bio)
 	struct scrub_block *sblock = bio->bi_private;
 	struct btrfs_fs_info *fs_info = sblock->sctx->fs_info;
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		sblock->no_io_error_seen = 0;
 
 	bio_put(bio);
@@ -2168,10 +2403,10 @@ static void scrub_missing_raid56_worker(struct btrfs_work *work)
 	scrub_block_put(sblock);
 
 	if (sctx->is_dev_replace &&
-	    atomic_read(&sctx->wr_ctx.flush_all_writes)) {
-		mutex_lock(&sctx->wr_ctx.wr_lock);
+	    atomic_read(&sctx->flush_all_writes)) {
+		mutex_lock(&sctx->wr_lock);
 		scrub_wr_submit(sctx);
-		mutex_unlock(&sctx->wr_ctx.wr_lock);
+		mutex_unlock(&sctx->wr_lock);
 	}
 
 	scrub_pending_bio_dec(sctx);
@@ -2189,8 +2424,9 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 	int ret;
 	int i;
 
+	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = btrfs_map_sblock(fs_info, BTRFS_MAP_GET_READ_MIRRORS, logical,
-			&length, &bbio, 0, 1);
+			&length, &bbio);
 	if (ret || !bbio || !bbio->raid_map)
 		goto bbio_out;
 
@@ -2205,10 +2441,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 		goto bbio_out;
 	}
 
-	bio = btrfs_io_bio_alloc(GFP_NOFS, 0);
-	if (!bio)
-		goto bbio_out;
-
+	bio = btrfs_io_bio_alloc(0);
 	bio->bi_iter.bi_sector = logical >> 9;
 	bio->bi_private = sblock;
 	bio->bi_end_io = scrub_missing_raid56_end_io;
@@ -2233,6 +2466,7 @@ static void scrub_missing_raid56_pages(struct scrub_block *sblock)
 rbio_out:
 	bio_put(bio);
 bbio_out:
+	btrfs_bio_counter_dec(fs_info);
 	btrfs_put_bbio(bbio);
 	spin_lock(&sctx->stat_lock);
 	sctx->stat.malloc_errors++;
@@ -2257,7 +2491,7 @@ static int scrub_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 
 	/* one ref inside this function, plus one for each page added to
 	 * a bio later on */
-	atomic_set(&sblock->refs, 1);
+	refcount_set(&sblock->refs, 1);
 	sblock->sctx = sctx;
 	sblock->no_io_error_seen = 1;
 
@@ -2334,7 +2568,7 @@ static void scrub_bio_end_io(struct bio *bio)
 	struct scrub_bio *sbio = bio->bi_private;
 	struct btrfs_fs_info *fs_info = sbio->dev->fs_info;
 
-	sbio->err = bio->bi_error;
+	sbio->status = bio->bi_status;
 	sbio->bio = bio;
 
 	btrfs_queue_work(fs_info->scrub_workers, &sbio->work);
@@ -2347,7 +2581,7 @@ static void scrub_bio_end_io_worker(struct btrfs_work *work)
 	int i;
 
 	BUG_ON(sbio->page_count > SCRUB_PAGES_PER_RD_BIO);
-	if (sbio->err) {
+	if (sbio->status) {
 		for (i = 0; i < sbio->page_count; i++) {
 			struct scrub_page *spage = sbio->pagev[i];
 
@@ -2374,10 +2608,10 @@ static void scrub_bio_end_io_worker(struct btrfs_work *work)
 	spin_unlock(&sctx->list_lock);
 
 	if (sctx->is_dev_replace &&
-	    atomic_read(&sctx->wr_ctx.flush_all_writes)) {
-		mutex_lock(&sctx->wr_ctx.wr_lock);
+	    atomic_read(&sctx->flush_all_writes)) {
+		mutex_lock(&sctx->wr_lock);
 		scrub_wr_submit(sctx);
-		mutex_unlock(&sctx->wr_ctx.wr_lock);
+		mutex_unlock(&sctx->wr_lock);
 	}
 
 	scrub_pending_bio_dec(sctx);
@@ -2387,7 +2621,7 @@ static inline void __scrub_mark_bitmap(struct scrub_parity *sparity,
 				       unsigned long *bitmap,
 				       u64 start, u64 len)
 {
-	u32 offset;
+	u64 offset;
 	int nsectors;
 	int sectorsize = sparity->sctx->fs_info->sectorsize;
 
@@ -2397,8 +2631,8 @@ static inline void __scrub_mark_bitmap(struct scrub_parity *sparity,
 	}
 
 	start -= sparity->logic_start;
-	start = div_u64_rem(start, sparity->stripe_len, &offset);
-	offset /= sectorsize;
+	start = div64_u64_rem(start, sparity->stripe_len, &offset);
+	offset = div_u64(offset, sectorsize);
 	nsectors = (int)len / sectorsize;
 
 	if (offset + nsectors <= sparity->nsectors) {
@@ -2472,8 +2706,8 @@ static int scrub_find_csum(struct scrub_ctx *sctx, u64 logical, u8 *csum)
 	if (!sum)
 		return 0;
 
-	index = ((u32)(logical - sum->bytenr)) / sctx->sectorsize;
-	num_sectors = sum->len / sctx->sectorsize;
+	index = ((u32)(logical - sum->bytenr)) / sctx->fs_info->sectorsize;
+	num_sectors = sum->len / sctx->fs_info->sectorsize;
 	memcpy(csum, sum->sums + index, sctx->csum_size);
 	if (index == num_sectors - 1) {
 		list_del(&sum->list);
@@ -2492,19 +2726,19 @@ static int scrub_extent(struct scrub_ctx *sctx, u64 logical, u64 len,
 	u32 blocksize;
 
 	if (flags & BTRFS_EXTENT_FLAG_DATA) {
-		blocksize = sctx->sectorsize;
+		blocksize = sctx->fs_info->sectorsize;
 		spin_lock(&sctx->stat_lock);
 		sctx->stat.data_extents_scrubbed++;
 		sctx->stat.data_bytes_scrubbed += len;
 		spin_unlock(&sctx->stat_lock);
 	} else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
-		blocksize = sctx->nodesize;
+		blocksize = sctx->fs_info->nodesize;
 		spin_lock(&sctx->stat_lock);
 		sctx->stat.tree_extents_scrubbed++;
 		sctx->stat.tree_bytes_scrubbed += len;
 		spin_unlock(&sctx->stat_lock);
 	} else {
-		blocksize = sctx->sectorsize;
+		blocksize = sctx->fs_info->sectorsize;
 		WARN_ON(1);
 	}
 
@@ -2557,7 +2791,7 @@ static int scrub_pages_for_parity(struct scrub_parity *sparity,
 
 	/* one ref inside this function, plus one for each page added to
 	 * a bio later on */
-	atomic_set(&sblock->refs, 1);
+	refcount_set(&sblock->refs, 1);
 	sblock->sctx = sctx;
 	sblock->no_io_error_seen = 1;
 	sblock->sparity = sparity;
@@ -2638,11 +2872,11 @@ static int scrub_extent_for_parity(struct scrub_parity *sparity,
 	}
 
 	if (flags & BTRFS_EXTENT_FLAG_DATA) {
-		blocksize = sctx->sectorsize;
+		blocksize = sctx->fs_info->sectorsize;
 	} else if (flags & BTRFS_EXTENT_FLAG_TREE_BLOCK) {
-		blocksize = sctx->nodesize;
+		blocksize = sctx->fs_info->nodesize;
 	} else {
-		blocksize = sctx->sectorsize;
+		blocksize = sctx->fs_info->sectorsize;
 		WARN_ON(1);
 	}
 
@@ -2696,7 +2930,7 @@ static int get_raid56_logic_offset(u64 physical, int num,
 	for (i = 0; i < nr_data_stripes(map); i++) {
 		*offset = last_offset + i * map->stripe_len;
 
-		stripe_nr = div_u64(*offset, map->stripe_len);
+		stripe_nr = div64_u64(*offset, map->stripe_len);
 		stripe_nr = div_u64(stripe_nr, nr_data_stripes(map));
 
 		/* Work out the disk rotation on this stripe-set */
@@ -2750,7 +2984,7 @@ static void scrub_parity_bio_endio(struct bio *bio)
 	struct scrub_parity *sparity = (struct scrub_parity *)bio->bi_private;
 	struct btrfs_fs_info *fs_info = sparity->sctx->fs_info;
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap,
 			  sparity->nsectors);
 
@@ -2767,7 +3001,6 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 	struct btrfs_fs_info *fs_info = sctx->fs_info;
 	struct bio *bio;
 	struct btrfs_raid_bio *rbio;
-	struct scrub_page *spage;
 	struct btrfs_bio *bbio = NULL;
 	u64 length;
 	int ret;
@@ -2777,15 +3010,14 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 		goto out;
 
 	length = sparity->logic_end - sparity->logic_start;
+
+	btrfs_bio_counter_inc_blocked(fs_info);
 	ret = btrfs_map_sblock(fs_info, BTRFS_MAP_WRITE, sparity->logic_start,
-			       &length, &bbio, 0, 1);
+			       &length, &bbio);
 	if (ret || !bbio || !bbio->raid_map)
 		goto bbio_out;
 
-	bio = btrfs_io_bio_alloc(GFP_NOFS, 0);
-	if (!bio)
-		goto bbio_out;
-
+	bio = btrfs_io_bio_alloc(0);
 	bio->bi_iter.bi_sector = sparity->logic_start >> 9;
 	bio->bi_private = sparity;
 	bio->bi_end_io = scrub_parity_bio_endio;
@@ -2797,9 +3029,6 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 	if (!rbio)
 		goto rbio_out;
 
-	list_for_each_entry(spage, &sparity->spages, list)
-		raid56_add_scrub_pages(rbio, spage->page, spage->logical);
-
 	scrub_pending_bio_inc(sctx);
 	raid56_parity_submit_scrub_rbio(rbio);
 	return;
@@ -2807,6 +3036,7 @@ static void scrub_parity_check_and_repair(struct scrub_parity *sparity)
 rbio_out:
 	bio_put(bio);
 bbio_out:
+	btrfs_bio_counter_dec(fs_info);
 	btrfs_put_bbio(bbio);
 	bitmap_or(sparity->ebitmap, sparity->ebitmap, sparity->dbitmap,
 		  sparity->nsectors);
@@ -2824,12 +3054,12 @@ static inline int scrub_calc_parity_bitmap_len(int nsectors)
 
 static void scrub_parity_get(struct scrub_parity *sparity)
 {
-	atomic_inc(&sparity->refs);
+	refcount_inc(&sparity->refs);
 }
 
 static void scrub_parity_put(struct scrub_parity *sparity)
 {
-	if (!atomic_dec_and_test(&sparity->refs))
+	if (!refcount_dec_and_test(&sparity->refs))
 		return;
 
 	scrub_parity_check_and_repair(sparity);
@@ -2881,7 +3111,7 @@ static noinline_for_stack int scrub_raid56_parity(struct scrub_ctx *sctx,
 	sparity->scrub_dev = sdev;
 	sparity->logic_start = logic_start;
 	sparity->logic_end = logic_end;
-	atomic_set(&sparity->refs, 1);
+	refcount_set(&sparity->refs, 1);
 	INIT_LIST_HEAD(&sparity->spages);
 	sparity->dbitmap = sparity->bitmap;
 	sparity->ebitmap = (void *)sparity->bitmap + bitmap_len;
@@ -3052,9 +3282,9 @@ out:
 						logic_end - logic_start);
 	scrub_parity_put(sparity);
 	scrub_submit(sctx);
-	mutex_lock(&sctx->wr_ctx.wr_lock);
+	mutex_lock(&sctx->wr_lock);
 	scrub_wr_submit(sctx);
-	mutex_unlock(&sctx->wr_ctx.wr_lock);
+	mutex_unlock(&sctx->wr_lock);
 
 	btrfs_release_path(path);
 	return ret < 0 ? ret : 0;
@@ -3100,7 +3330,7 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 
 	physical = map->stripes[num].physical;
 	offset = 0;
-	nstripes = div_u64(length, map->stripe_len);
+	nstripes = div64_u64(length, map->stripe_len);
 	if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
 		offset = map->stripe_len * num;
 		increment = map->stripe_len * map->num_stripes;
@@ -3210,14 +3440,14 @@ static noinline_for_stack int scrub_stripe(struct scrub_ctx *sctx,
 		 */
 		if (atomic_read(&fs_info->scrub_pause_req)) {
 			/* push queued extents */
-			atomic_set(&sctx->wr_ctx.flush_all_writes, 1);
+			atomic_set(&sctx->flush_all_writes, 1);
 			scrub_submit(sctx);
-			mutex_lock(&sctx->wr_ctx.wr_lock);
+			mutex_lock(&sctx->wr_lock);
 			scrub_wr_submit(sctx);
-			mutex_unlock(&sctx->wr_ctx.wr_lock);
+			mutex_unlock(&sctx->wr_lock);
 			wait_event(sctx->list_wait,
 				   atomic_read(&sctx->bios_in_flight) == 0);
-			atomic_set(&sctx->wr_ctx.flush_all_writes, 0);
+			atomic_set(&sctx->flush_all_writes, 0);
 			scrub_blocked_if_needed(fs_info);
 		}
 
@@ -3424,9 +3654,9 @@ skip:
 out:
 	/* push queued extents */
 	scrub_submit(sctx);
-	mutex_lock(&sctx->wr_ctx.wr_lock);
+	mutex_lock(&sctx->wr_lock);
 	scrub_wr_submit(sctx);
-	mutex_unlock(&sctx->wr_ctx.wr_lock);
+	mutex_unlock(&sctx->wr_lock);
 
 	blk_finish_plug(&plug);
 	btrfs_free_path(path);
@@ -3584,7 +3814,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 * -> btrfs_scrub_pause()
 		 */
 		scrub_pause_on(fs_info);
-		ret = btrfs_inc_block_group_ro(root, cache);
+		ret = btrfs_inc_block_group_ro(fs_info, cache);
 		if (!ret && is_dev_replace) {
 			/*
 			 * If we are doing a device replace wait for any tasks
@@ -3606,7 +3836,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 			 */
 			btrfs_wait_block_group_reservations(cache);
 			btrfs_wait_nocow_writers(cache);
-			ret = btrfs_wait_ordered_roots(fs_info, -1,
+			ret = btrfs_wait_ordered_roots(fs_info, U64_MAX,
 						       cache->key.objectid,
 						       cache->key.offset);
 			if (ret > 0) {
@@ -3663,11 +3893,11 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 * write requests are really completed when bios_in_flight
 		 * changes to 0.
 		 */
-		atomic_set(&sctx->wr_ctx.flush_all_writes, 1);
+		atomic_set(&sctx->flush_all_writes, 1);
 		scrub_submit(sctx);
-		mutex_lock(&sctx->wr_ctx.wr_lock);
+		mutex_lock(&sctx->wr_lock);
 		scrub_wr_submit(sctx);
-		mutex_unlock(&sctx->wr_ctx.wr_lock);
+		mutex_unlock(&sctx->wr_lock);
 
 		wait_event(sctx->list_wait,
 			   atomic_read(&sctx->bios_in_flight) == 0);
@@ -3681,7 +3911,7 @@ int scrub_enumerate_chunks(struct scrub_ctx *sctx,
 		 */
 		wait_event(sctx->list_wait,
 			   atomic_read(&sctx->workers_pending) == 0);
-		atomic_set(&sctx->wr_ctx.flush_all_writes, 0);
+		atomic_set(&sctx->flush_all_writes, 0);
 
 		scrub_pause_off(fs_info);
 
@@ -4084,34 +4314,6 @@ static void scrub_remap_extent(struct btrfs_fs_info *fs_info,
 	btrfs_put_bbio(bbio);
 }
 
-static int scrub_setup_wr_ctx(struct scrub_ctx *sctx,
-			      struct scrub_wr_ctx *wr_ctx,
-			      struct btrfs_fs_info *fs_info,
-			      struct btrfs_device *dev,
-			      int is_dev_replace)
-{
-	WARN_ON(wr_ctx->wr_curr_bio != NULL);
-
-	mutex_init(&wr_ctx->wr_lock);
-	wr_ctx->wr_curr_bio = NULL;
-	if (!is_dev_replace)
-		return 0;
-
-	WARN_ON(!dev->bdev);
-	wr_ctx->pages_per_wr_bio = SCRUB_PAGES_PER_WR_BIO;
-	wr_ctx->tgtdev = dev;
-	atomic_set(&wr_ctx->flush_all_writes, 0);
-	return 0;
-}
-
-static void scrub_free_wr_ctx(struct scrub_wr_ctx *wr_ctx)
-{
-	mutex_lock(&wr_ctx->wr_lock);
-	kfree(wr_ctx->wr_curr_bio);
-	wr_ctx->wr_curr_bio = NULL;
-	mutex_unlock(&wr_ctx->wr_lock);
-}
-
 static int copy_nocow_pages(struct scrub_ctx *sctx, u64 logical, u64 len,
 			    int mirror_num, u64 physical_for_dev_replace)
 {
@@ -4240,7 +4442,7 @@ out:
 	scrub_pending_trans_workers_dec(sctx);
 }
 
-static int check_extent_to_block(struct inode *inode, u64 start, u64 len,
+static int check_extent_to_block(struct btrfs_inode *inode, u64 start, u64 len,
 				 u64 logical)
 {
 	struct extent_state *cached_state = NULL;
@@ -4250,7 +4452,7 @@ static int check_extent_to_block(struct inode *inode, u64 start, u64 len,
 	u64 lockstart = start, lockend = start + len - 1;
 	int ret = 0;
 
-	io_tree = &BTRFS_I(inode)->io_tree;
+	io_tree = &inode->io_tree;
 
 	lock_extent_bits(io_tree, lockstart, lockend, &cached_state);
 	ordered = btrfs_lookup_ordered_range(inode, lockstart, len);
@@ -4329,7 +4531,8 @@ static int copy_nocow_pages_for_inode(u64 inum, u64 offset, u64 root,
 	io_tree = &BTRFS_I(inode)->io_tree;
 	nocow_ctx_logical = nocow_ctx->logical;
 
-	ret = check_extent_to_block(inode, offset, len, nocow_ctx_logical);
+	ret = check_extent_to_block(BTRFS_I(inode), offset, len,
+			nocow_ctx_logical);
 	if (ret) {
 		ret = ret > 0 ? 0 : ret;
 		goto out;
@@ -4376,7 +4579,7 @@ again:
 			}
 		}
 
-		ret = check_extent_to_block(inode, offset, len,
+		ret = check_extent_to_block(BTRFS_I(inode), offset, len,
 					    nocow_ctx_logical);
 		if (ret) {
 			ret = ret > 0 ? 0 : ret;
@@ -4413,7 +4616,7 @@ static int write_page_nocow(struct scrub_ctx *sctx,
 	struct btrfs_device *dev;
 	int ret;
 
-	dev = sctx->wr_ctx.tgtdev;
+	dev = sctx->wr_tgtdev;
 	if (!dev)
 		return -EIO;
 	if (!dev->bdev) {
@@ -4421,13 +4624,7 @@ static int write_page_nocow(struct scrub_ctx *sctx,
 			"scrub write_page_nocow(bdev == NULL) is unexpected");
 		return -EIO;
 	}
-	bio = btrfs_io_bio_alloc(GFP_NOFS, 1);
-	if (!bio) {
-		spin_lock(&sctx->stat_lock);
-		sctx->stat.malloc_errors++;
-		spin_unlock(&sctx->stat_lock);
-		return -ENOMEM;
-	}
+	bio = btrfs_io_bio_alloc(1);
 	bio->bi_iter.bi_size = 0;
 	bio->bi_iter.bi_sector = physical_for_dev_replace >> 9;
 	bio->bi_bdev = dev->bdev;
diff --git a/fs/btrfs/send.c b/fs/btrfs/send.c
index d145ce804620..b082210df9c8 100644
--- a/fs/btrfs/send.c
+++ b/fs/btrfs/send.c
@@ -1069,6 +1069,12 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 			}
 		}
 
+		ret = btrfs_is_name_len_valid(eb, path->slots[0],
+			  (unsigned long)(di + 1), name_len + data_len);
+		if (!ret) {
+			ret = -EIO;
+			goto out;
+		}
 		if (name_len + data_len > buf_len) {
 			buf_len = name_len + data_len;
 			if (is_vmalloc_addr(buf)) {
@@ -1083,7 +1089,7 @@ static int iterate_dir_item(struct btrfs_root *root, struct btrfs_path *path,
 				buf = tmp;
 			}
 			if (!buf) {
-				buf = vmalloc(buf_len);
+				buf = kvmalloc(buf_len, GFP_KERNEL);
 				if (!buf) {
 					ret = -ENOMEM;
 					goto out;
@@ -1681,6 +1687,9 @@ static int is_inode_existent(struct send_ctx *sctx, u64 ino, u64 gen)
 {
 	int ret;
 
+	if (ino == BTRFS_FIRST_FREE_OBJECTID)
+		return 1;
+
 	ret = get_cur_inode_state(sctx, ino, gen);
 	if (ret < 0)
 		goto out;
@@ -1847,7 +1856,7 @@ out:
  */
 static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 			      const char *name, int name_len,
-			      u64 *who_ino, u64 *who_gen)
+			      u64 *who_ino, u64 *who_gen, u64 *who_mode)
 {
 	int ret = 0;
 	u64 gen;
@@ -1866,7 +1875,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 	 * not deleted and then re-created, if it was then we have no overwrite
 	 * and we can just unlink this entry.
 	 */
-	if (sctx->parent_root) {
+	if (sctx->parent_root && dir != BTRFS_FIRST_FREE_OBJECTID) {
 		ret = get_inode_info(sctx->parent_root, dir, NULL, &gen, NULL,
 				     NULL, NULL, NULL);
 		if (ret < 0 && ret != -ENOENT)
@@ -1896,7 +1905,7 @@ static int will_overwrite_ref(struct send_ctx *sctx, u64 dir, u64 dir_gen,
 	if (other_inode > sctx->send_progress ||
 	    is_waiting_for_move(sctx, other_inode)) {
 		ret = get_inode_info(sctx->parent_root, other_inode, NULL,
-				who_gen, NULL, NULL, NULL, NULL);
+				who_gen, who_mode, NULL, NULL, NULL);
 		if (ret < 0)
 			goto out;
 
@@ -1934,6 +1943,19 @@ static int did_overwrite_ref(struct send_ctx *sctx,
 	if (ret <= 0)
 		goto out;
 
+	if (dir != BTRFS_FIRST_FREE_OBJECTID) {
+		ret = get_inode_info(sctx->send_root, dir, NULL, &gen, NULL,
+				     NULL, NULL, NULL);
+		if (ret < 0 && ret != -ENOENT)
+			goto out;
+		if (ret) {
+			ret = 0;
+			goto out;
+		}
+		if (gen != dir_gen)
+			goto out;
+	}
+
 	/* check if the ref was overwritten by another ref */
 	ret = lookup_dir_item_inode(sctx->send_root, dir, name, name_len,
 			&ow_inode, &other_type);
@@ -2753,15 +2775,20 @@ out:
 
 struct recorded_ref {
 	struct list_head list;
-	char *dir_path;
 	char *name;
 	struct fs_path *full_path;
 	u64 dir;
 	u64 dir_gen;
-	int dir_path_len;
 	int name_len;
 };
 
+static void set_ref_path(struct recorded_ref *ref, struct fs_path *path)
+{
+	ref->full_path = path;
+	ref->name = (char *)kbasename(ref->full_path->start);
+	ref->name_len = ref->full_path->end - ref->name;
+}
+
 /*
  * We need to process new refs before deleted refs, but compare_tree gives us
  * everything mixed. So we first record all refs and later process them.
@@ -2778,17 +2805,7 @@ static int __record_ref(struct list_head *head, u64 dir,
 
 	ref->dir = dir;
 	ref->dir_gen = dir_gen;
-	ref->full_path = path;
-
-	ref->name = (char *)kbasename(ref->full_path->start);
-	ref->name_len = ref->full_path->end - ref->name;
-	ref->dir_path = ref->full_path->start;
-	if (ref->name == ref->full_path->start)
-		ref->dir_path_len = 0;
-	else
-		ref->dir_path_len = ref->full_path->end -
-				ref->full_path->start - 1 - ref->name_len;
-
+	set_ref_path(ref, path);
 	list_add_tail(&ref->list, head);
 	return 0;
 }
@@ -3530,9 +3547,17 @@ static int is_ancestor(struct btrfs_root *root,
 		       struct fs_path *fs_path)
 {
 	u64 ino = ino2;
+	bool free_path = false;
+	int ret = 0;
+
+	if (!fs_path) {
+		fs_path = fs_path_alloc();
+		if (!fs_path)
+			return -ENOMEM;
+		free_path = true;
+	}
 
 	while (ino > BTRFS_FIRST_FREE_OBJECTID) {
-		int ret;
 		u64 parent;
 		u64 parent_gen;
 
@@ -3541,13 +3566,18 @@ static int is_ancestor(struct btrfs_root *root,
 		if (ret < 0) {
 			if (ret == -ENOENT && ino == ino2)
 				ret = 0;
-			return ret;
+			goto out;
+		}
+		if (parent == ino1) {
+			ret = parent_gen == ino1_gen ? 1 : 0;
+			goto out;
 		}
-		if (parent == ino1)
-			return parent_gen == ino1_gen ? 1 : 0;
 		ino = parent;
 	}
-	return 0;
+ out:
+	if (free_path)
+		fs_path_free(fs_path);
+	return ret;
 }
 
 static int wait_for_parent_move(struct send_ctx *sctx,
@@ -3556,6 +3586,7 @@ static int wait_for_parent_move(struct send_ctx *sctx,
 {
 	int ret = 0;
 	u64 ino = parent_ref->dir;
+	u64 ino_gen = parent_ref->dir_gen;
 	u64 parent_ino_before, parent_ino_after;
 	struct fs_path *path_before = NULL;
 	struct fs_path *path_after = NULL;
@@ -3576,6 +3607,8 @@ static int wait_for_parent_move(struct send_ctx *sctx,
 	 * at get_cur_path()).
 	 */
 	while (ino > BTRFS_FIRST_FREE_OBJECTID) {
+		u64 parent_ino_after_gen;
+
 		if (is_waiting_for_move(sctx, ino)) {
 			/*
 			 * If the current inode is an ancestor of ino in the
@@ -3598,7 +3631,7 @@ static int wait_for_parent_move(struct send_ctx *sctx,
 		fs_path_reset(path_after);
 
 		ret = get_first_ref(sctx->send_root, ino, &parent_ino_after,
-				    NULL, path_after);
+				    &parent_ino_after_gen, path_after);
 		if (ret < 0)
 			goto out;
 		ret = get_first_ref(sctx->parent_root, ino, &parent_ino_before,
@@ -3615,10 +3648,20 @@ static int wait_for_parent_move(struct send_ctx *sctx,
 		if (ino > sctx->cur_ino &&
 		    (parent_ino_before != parent_ino_after || len1 != len2 ||
 		     memcmp(path_before->start, path_after->start, len1))) {
-			ret = 1;
-			break;
+			u64 parent_ino_gen;
+
+			ret = get_inode_info(sctx->parent_root, ino, NULL,
+					     &parent_ino_gen, NULL, NULL, NULL,
+					     NULL);
+			if (ret < 0)
+				goto out;
+			if (ino_gen == parent_ino_gen) {
+				ret = 1;
+				break;
+			}
 		}
 		ino = parent_ino_after;
+		ino_gen = parent_ino_after_gen;
 	}
 
 out:
@@ -3640,6 +3683,36 @@ out:
 	return ret;
 }
 
+static int update_ref_path(struct send_ctx *sctx, struct recorded_ref *ref)
+{
+	int ret;
+	struct fs_path *new_path;
+
+	/*
+	 * Our reference's name member points to its full_path member string, so
+	 * we use here a new path.
+	 */
+	new_path = fs_path_alloc();
+	if (!new_path)
+		return -ENOMEM;
+
+	ret = get_cur_path(sctx, ref->dir, ref->dir_gen, new_path);
+	if (ret < 0) {
+		fs_path_free(new_path);
+		return ret;
+	}
+	ret = fs_path_add(new_path, ref->name, ref->name_len);
+	if (ret < 0) {
+		fs_path_free(new_path);
+		return ret;
+	}
+
+	fs_path_free(ref->full_path);
+	set_ref_path(ref, new_path);
+
+	return 0;
+}
+
 /*
  * This does all the move/link/unlink/rmdir magic.
  */
@@ -3653,10 +3726,13 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 	struct fs_path *valid_path = NULL;
 	u64 ow_inode = 0;
 	u64 ow_gen;
+	u64 ow_mode;
 	int did_overwrite = 0;
 	int is_orphan = 0;
 	u64 last_dir_ino_rm = 0;
 	bool can_rename = true;
+	bool orphanized_dir = false;
+	bool orphanized_ancestor = false;
 
 	btrfs_debug(fs_info, "process_recorded_refs %llu", sctx->cur_ino);
 
@@ -3754,7 +3830,7 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 		 */
 		ret = will_overwrite_ref(sctx, cur->dir, cur->dir_gen,
 				cur->name, cur->name_len,
-				&ow_inode, &ow_gen);
+				&ow_inode, &ow_gen, &ow_mode);
 		if (ret < 0)
 			goto out;
 		if (ret) {
@@ -3771,6 +3847,8 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 						cur->full_path);
 				if (ret < 0)
 					goto out;
+				if (S_ISDIR(ow_mode))
+					orphanized_dir = true;
 
 				/*
 				 * If ow_inode has its rename operation delayed
@@ -3808,9 +3886,16 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 				 * might contain the pre-orphanization name of
 				 * ow_inode, which is no longer valid.
 				 */
-				fs_path_reset(valid_path);
-				ret = get_cur_path(sctx, sctx->cur_ino,
-					   sctx->cur_inode_gen, valid_path);
+				ret = is_ancestor(sctx->parent_root,
+						  ow_inode, ow_gen,
+						  sctx->cur_ino, NULL);
+				if (ret > 0) {
+					orphanized_ancestor = true;
+					fs_path_reset(valid_path);
+					ret = get_cur_path(sctx, sctx->cur_ino,
+							   sctx->cur_inode_gen,
+							   valid_path);
+				}
 				if (ret < 0)
 					goto out;
 			} else {
@@ -3869,6 +3954,18 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 				if (ret < 0)
 					goto out;
 			} else {
+				/*
+				 * We might have previously orphanized an inode
+				 * which is an ancestor of our current inode,
+				 * so our reference's full path, which was
+				 * computed before any such orphanizations, must
+				 * be updated.
+				 */
+				if (orphanized_dir) {
+					ret = update_ref_path(sctx, cur);
+					if (ret < 0)
+						goto out;
+				}
 				ret = send_link(sctx, cur->full_path,
 						valid_path);
 				if (ret < 0)
@@ -3931,6 +4028,18 @@ static int process_recorded_refs(struct send_ctx *sctx, int *pending_move)
 			if (ret < 0)
 				goto out;
 			if (!ret) {
+				/*
+				 * If we orphanized any ancestor before, we need
+				 * to recompute the full path for deleted names,
+				 * since any such path was computed before we
+				 * processed any references and orphanized any
+				 * ancestor inode.
+				 */
+				if (orphanized_ancestor) {
+					ret = update_ref_path(sctx, cur);
+					if (ret < 0)
+						goto out;
+				}
 				ret = send_unlink(sctx, cur->full_path);
 				if (ret < 0)
 					goto out;
@@ -5155,15 +5264,18 @@ static int is_extent_unchanged(struct send_ctx *sctx,
 	while (key.offset < ekey->offset + left_len) {
 		ei = btrfs_item_ptr(eb, slot, struct btrfs_file_extent_item);
 		right_type = btrfs_file_extent_type(eb, ei);
-		if (right_type != BTRFS_FILE_EXTENT_REG) {
+		if (right_type != BTRFS_FILE_EXTENT_REG &&
+		    right_type != BTRFS_FILE_EXTENT_INLINE) {
 			ret = 0;
 			goto out;
 		}
 
-		right_disknr = btrfs_file_extent_disk_bytenr(eb, ei);
-		right_len = btrfs_file_extent_num_bytes(eb, ei);
-		right_offset = btrfs_file_extent_offset(eb, ei);
-		right_gen = btrfs_file_extent_generation(eb, ei);
+		if (right_type == BTRFS_FILE_EXTENT_INLINE) {
+			right_len = btrfs_file_extent_inline_len(eb, slot, ei);
+			right_len = PAGE_ALIGN(right_len);
+		} else {
+			right_len = btrfs_file_extent_num_bytes(eb, ei);
+		}
 
 		/*
 		 * Are we at extent 8? If yes, we know the extent is changed.
@@ -5175,6 +5287,23 @@ static int is_extent_unchanged(struct send_ctx *sctx,
 			goto out;
 		}
 
+		/*
+		 * We just wanted to see if when we have an inline extent, what
+		 * follows it is a regular extent (wanted to check the above
+		 * condition for inline extents too). This should normally not
+		 * happen but it's possible for example when we have an inline
+		 * compressed extent representing data with a size matching
+		 * the page size (currently the same as sector size).
+		 */
+		if (right_type == BTRFS_FILE_EXTENT_INLINE) {
+			ret = 0;
+			goto out;
+		}
+
+		right_disknr = btrfs_file_extent_disk_bytenr(eb, ei);
+		right_offset = btrfs_file_extent_offset(eb, ei);
+		right_gen = btrfs_file_extent_generation(eb, ei);
+
 		left_offset_fixed = left_offset;
 		if (key.offset < ekey->offset) {
 			/* Fix the right offset for 2a and 7. */
@@ -5277,6 +5406,81 @@ out:
 	return ret;
 }
 
+static int range_is_hole_in_parent(struct send_ctx *sctx,
+				   const u64 start,
+				   const u64 end)
+{
+	struct btrfs_path *path;
+	struct btrfs_key key;
+	struct btrfs_root *root = sctx->parent_root;
+	u64 search_start = start;
+	int ret;
+
+	path = alloc_path_for_send();
+	if (!path)
+		return -ENOMEM;
+
+	key.objectid = sctx->cur_ino;
+	key.type = BTRFS_EXTENT_DATA_KEY;
+	key.offset = search_start;
+	ret = btrfs_search_slot(NULL, root, &key, path, 0, 0);
+	if (ret < 0)
+		goto out;
+	if (ret > 0 && path->slots[0] > 0)
+		path->slots[0]--;
+
+	while (search_start < end) {
+		struct extent_buffer *leaf = path->nodes[0];
+		int slot = path->slots[0];
+		struct btrfs_file_extent_item *fi;
+		u64 extent_end;
+
+		if (slot >= btrfs_header_nritems(leaf)) {
+			ret = btrfs_next_leaf(root, path);
+			if (ret < 0)
+				goto out;
+			else if (ret > 0)
+				break;
+			continue;
+		}
+
+		btrfs_item_key_to_cpu(leaf, &key, slot);
+		if (key.objectid < sctx->cur_ino ||
+		    key.type < BTRFS_EXTENT_DATA_KEY)
+			goto next;
+		if (key.objectid > sctx->cur_ino ||
+		    key.type > BTRFS_EXTENT_DATA_KEY ||
+		    key.offset >= end)
+			break;
+
+		fi = btrfs_item_ptr(leaf, slot, struct btrfs_file_extent_item);
+		if (btrfs_file_extent_type(leaf, fi) ==
+		    BTRFS_FILE_EXTENT_INLINE) {
+			u64 size = btrfs_file_extent_inline_len(leaf, slot, fi);
+
+			extent_end = ALIGN(key.offset + size,
+					   root->fs_info->sectorsize);
+		} else {
+			extent_end = key.offset +
+				btrfs_file_extent_num_bytes(leaf, fi);
+		}
+		if (extent_end <= start)
+			goto next;
+		if (btrfs_file_extent_disk_bytenr(leaf, fi) == 0) {
+			search_start = extent_end;
+			goto next;
+		}
+		ret = 0;
+		goto out;
+next:
+		path->slots[0]++;
+	}
+	ret = 1;
+out:
+	btrfs_free_path(path);
+	return ret;
+}
+
 static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
 			   struct btrfs_key *key)
 {
@@ -5321,8 +5525,17 @@ static int maybe_send_hole(struct send_ctx *sctx, struct btrfs_path *path,
 			return ret;
 	}
 
-	if (sctx->cur_inode_last_extent < key->offset)
-		ret = send_hole(sctx, key->offset);
+	if (sctx->cur_inode_last_extent < key->offset) {
+		ret = range_is_hole_in_parent(sctx,
+					      sctx->cur_inode_last_extent,
+					      key->offset);
+		if (ret < 0)
+			return ret;
+		else if (ret == 0)
+			ret = send_hole(sctx, key->offset);
+		else
+			ret = 0;
+	}
 	sctx->cur_inode_last_extent = extent_end;
 	return ret;
 }
@@ -6192,8 +6405,13 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 		goto out;
 	}
 
+	/*
+	 * Check that we don't overflow at later allocations, we request
+	 * clone_sources_count + 1 items, and compare to unsigned long inside
+	 * access_ok.
+	 */
 	if (arg->clone_sources_count >
-	    ULLONG_MAX / sizeof(*arg->clone_sources)) {
+	    ULONG_MAX / sizeof(struct clone_root) - 1) {
 		ret = -EINVAL;
 		goto out;
 	}
@@ -6242,22 +6460,16 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 	sctx->clone_roots_cnt = arg->clone_sources_count;
 
 	sctx->send_max_size = BTRFS_SEND_BUF_SIZE;
-	sctx->send_buf = kmalloc(sctx->send_max_size, GFP_KERNEL | __GFP_NOWARN);
+	sctx->send_buf = kvmalloc(sctx->send_max_size, GFP_KERNEL);
 	if (!sctx->send_buf) {
-		sctx->send_buf = vmalloc(sctx->send_max_size);
-		if (!sctx->send_buf) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		ret = -ENOMEM;
+		goto out;
 	}
 
-	sctx->read_buf = kmalloc(BTRFS_SEND_READ_SIZE, GFP_KERNEL | __GFP_NOWARN);
+	sctx->read_buf = kvmalloc(BTRFS_SEND_READ_SIZE, GFP_KERNEL);
 	if (!sctx->read_buf) {
-		sctx->read_buf = vmalloc(BTRFS_SEND_READ_SIZE);
-		if (!sctx->read_buf) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		ret = -ENOMEM;
+		goto out;
 	}
 
 	sctx->pending_dir_moves = RB_ROOT;
@@ -6266,25 +6478,19 @@ long btrfs_ioctl_send(struct file *mnt_file, void __user *arg_)
 
 	alloc_size = sizeof(struct clone_root) * (arg->clone_sources_count + 1);
 
-	sctx->clone_roots = kzalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN);
+	sctx->clone_roots = kzalloc(alloc_size, GFP_KERNEL);
 	if (!sctx->clone_roots) {
-		sctx->clone_roots = vzalloc(alloc_size);
-		if (!sctx->clone_roots) {
-			ret = -ENOMEM;
-			goto out;
-		}
+		ret = -ENOMEM;
+		goto out;
 	}
 
 	alloc_size = arg->clone_sources_count * sizeof(*arg->clone_sources);
 
 	if (arg->clone_sources_count) {
-		clone_sources_tmp = kmalloc(alloc_size, GFP_KERNEL | __GFP_NOWARN);
+		clone_sources_tmp = kvmalloc(alloc_size, GFP_KERNEL);
 		if (!clone_sources_tmp) {
-			clone_sources_tmp = vmalloc(alloc_size);
-			if (!clone_sources_tmp) {
-				ret = -ENOMEM;
-				goto out;
-			}
+			ret = -ENOMEM;
+			goto out;
 		}
 
 		ret = copy_from_user(clone_sources_tmp, arg->clone_sources,
diff --git a/fs/btrfs/super.c b/fs/btrfs/super.c
index b5ae7d3d1896..12540b6104b5 100644
--- a/fs/btrfs/super.c
+++ b/fs/btrfs/super.c
@@ -265,7 +265,7 @@ void __btrfs_abort_transaction(struct btrfs_trans_handle *trans,
 		           function, line, errstr);
 		return;
 	}
-	ACCESS_ONCE(trans->transaction->aborted) = errno;
+	WRITE_ONCE(trans->transaction->aborted, errno);
 	/* Wake up anybody who may be waiting on this transaction */
 	wake_up(&fs_info->transaction_wait);
 	wake_up(&fs_info->transaction_blocked_wait);
@@ -549,16 +549,19 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 		case Opt_ssd:
 			btrfs_set_and_info(info, SSD,
 					   "use ssd allocation scheme");
+			btrfs_clear_opt(info->mount_opt, NOSSD);
 			break;
 		case Opt_ssd_spread:
 			btrfs_set_and_info(info, SSD_SPREAD,
 					   "use spread ssd allocation scheme");
 			btrfs_set_opt(info->mount_opt, SSD);
+			btrfs_clear_opt(info->mount_opt, NOSSD);
 			break;
 		case Opt_nossd:
 			btrfs_set_and_info(info, NOSSD,
 					     "not using ssd allocation scheme");
 			btrfs_clear_opt(info->mount_opt, SSD);
+			btrfs_clear_opt(info->mount_opt, SSD_SPREAD);
 			break;
 		case Opt_barrier:
 			btrfs_clear_and_info(info, NOBARRIER,
@@ -598,18 +601,8 @@ int btrfs_parse_options(struct btrfs_fs_info *info, char *options,
 			}
 			break;
 		case Opt_alloc_start:
-			num = match_strdup(&args[0]);
-			if (num) {
-				mutex_lock(&info->chunk_mutex);
-				info->alloc_start = memparse(num, NULL);
-				mutex_unlock(&info->chunk_mutex);
-				kfree(num);
-				btrfs_info(info, "allocations start at %llu",
-					   info->alloc_start);
-			} else {
-				ret = -ENOMEM;
-				goto out;
-			}
+			btrfs_info(info,
+				"option alloc_start is obsolete, ignored");
 			break;
 		case Opt_acl:
 #ifdef CONFIG_BTRFS_FS_POSIX_ACL
@@ -1114,7 +1107,7 @@ static int get_default_subvol_objectid(struct btrfs_fs_info *fs_info, u64 *objec
 
 static int btrfs_fill_super(struct super_block *sb,
 			    struct btrfs_fs_devices *fs_devices,
-			    void *data, int silent)
+			    void *data)
 {
 	struct inode *inode;
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
@@ -1133,6 +1126,13 @@ static int btrfs_fill_super(struct super_block *sb,
 #endif
 	sb->s_flags |= MS_I_VERSION;
 	sb->s_iflags |= SB_I_CGROUPWB;
+
+	err = super_setup_bdi(sb);
+	if (err) {
+		btrfs_err(fs_info, "super_setup_bdi failed");
+		return err;
+	}
+
 	err = open_ctree(sb, fs_devices, (char *)data);
 	if (err) {
 		btrfs_err(fs_info, "open_ctree failed");
@@ -1154,7 +1154,6 @@ static int btrfs_fill_super(struct super_block *sb,
 		goto fail_close;
 	}
 
-	save_mount_options(sb, data);
 	cleancache_init_fs(sb);
 	sb->s_flags |= MS_ACTIVE;
 	return 0;
@@ -1177,7 +1176,7 @@ int btrfs_sync_fs(struct super_block *sb, int wait)
 		return 0;
 	}
 
-	btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
+	btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
 
 	trans = btrfs_attach_transaction_barrier(root);
 	if (IS_ERR(trans)) {
@@ -1222,8 +1221,6 @@ static int btrfs_show_options(struct seq_file *seq, struct dentry *dentry)
 		seq_puts(seq, ",nobarrier");
 	if (info->max_inline != BTRFS_DEFAULT_MAX_INLINE)
 		seq_printf(seq, ",max_inline=%llu", info->max_inline);
-	if (info->alloc_start != 0)
-		seq_printf(seq, ",alloc_start=%llu", info->alloc_start);
 	if (info->thread_pool_size !=  min_t(unsigned long,
 					     num_online_cpus() + 2, 8))
 		seq_printf(seq, ",thread_pool=%d", info->thread_pool_size);
@@ -1611,8 +1608,7 @@ static struct dentry *btrfs_mount(struct file_system_type *fs_type, int flags,
 	} else {
 		snprintf(s->s_id, sizeof(s->s_id), "%pg", bdev);
 		btrfs_sb(s)->bdev_holder = fs_type;
-		error = btrfs_fill_super(s, fs_devices, data,
-					 flags & MS_SILENT ? 1 : 0);
+		error = btrfs_fill_super(s, fs_devices, data);
 	}
 	if (error) {
 		deactivate_locked_super(s);
@@ -1707,7 +1703,6 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 	unsigned long old_opts = fs_info->mount_opt;
 	unsigned long old_compress_type = fs_info->compress_type;
 	u64 old_max_inline = fs_info->max_inline;
-	u64 old_alloc_start = fs_info->alloc_start;
 	int old_thread_pool_size = fs_info->thread_pool_size;
 	unsigned int old_metadata_ratio = fs_info->metadata_ratio;
 	int ret;
@@ -1786,8 +1781,7 @@ static int btrfs_remount(struct super_block *sb, int *flags, char *data)
 		}
 
 		if (fs_info->fs_devices->missing_devices >
-		     fs_info->num_tolerated_disk_barrier_failures &&
-		    !(*flags & MS_RDONLY)) {
+		     fs_info->num_tolerated_disk_barrier_failures) {
 			btrfs_warn(fs_info,
 				"too many missing devices, writeable remount is not allowed");
 			ret = -EACCES;
@@ -1847,9 +1841,6 @@ restore:
 	fs_info->mount_opt = old_opts;
 	fs_info->compress_type = old_compress_type;
 	fs_info->max_inline = old_max_inline;
-	mutex_lock(&fs_info->chunk_mutex);
-	fs_info->alloc_start = old_alloc_start;
-	mutex_unlock(&fs_info->chunk_mutex);
 	btrfs_resize_thread_pool(fs_info,
 		old_thread_pool_size, fs_info->thread_pool_size);
 	fs_info->metadata_ratio = old_metadata_ratio;
@@ -1890,18 +1881,15 @@ static inline void btrfs_descending_sort_devices(
 static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
 				       u64 *free_bytes)
 {
-	struct btrfs_root *root = fs_info->tree_root;
 	struct btrfs_device_info *devices_info;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 	struct btrfs_device *device;
 	u64 skip_space;
 	u64 type;
 	u64 avail_space;
-	u64 used_space;
 	u64 min_stripe_size;
 	int min_stripes = 1, num_stripes = 1;
 	int i = 0, nr_devices;
-	int ret;
 
 	/*
 	 * We aren't under the device list lock, so this is racy-ish, but good
@@ -1919,12 +1907,12 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
 	}
 
 	devices_info = kmalloc_array(nr_devices, sizeof(*devices_info),
-			       GFP_NOFS);
+			       GFP_KERNEL);
 	if (!devices_info)
 		return -ENOMEM;
 
 	/* calc min stripe number for data space allocation */
-	type = btrfs_get_alloc_profile(root, 1);
+	type = btrfs_data_alloc_profile(fs_info);
 	if (type & BTRFS_BLOCK_GROUP_RAID0) {
 		min_stripes = 2;
 		num_stripes = nr_devices;
@@ -1941,8 +1929,6 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
 	else
 		min_stripe_size = BTRFS_STRIPE_LEN;
 
-	if (fs_info->alloc_start)
-		mutex_lock(&fs_devices->device_list_mutex);
 	rcu_read_lock();
 	list_for_each_entry_rcu(device, &fs_devices->devices, dev_list) {
 		if (!device->in_fs_metadata || !device->bdev ||
@@ -1965,34 +1951,6 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
 		 */
 		skip_space = SZ_1M;
 
-		/* user can set the offset in fs_info->alloc_start. */
-		if (fs_info->alloc_start &&
-		    fs_info->alloc_start + BTRFS_STRIPE_LEN <=
-		    device->total_bytes) {
-			rcu_read_unlock();
-			skip_space = max(fs_info->alloc_start, skip_space);
-
-			/*
-			 * btrfs can not use the free space in
-			 * [0, skip_space - 1], we must subtract it from the
-			 * total. In order to implement it, we account the used
-			 * space in this range first.
-			 */
-			ret = btrfs_account_dev_extents_size(device, 0,
-							     skip_space - 1,
-							     &used_space);
-			if (ret) {
-				kfree(devices_info);
-				mutex_unlock(&fs_devices->device_list_mutex);
-				return ret;
-			}
-
-			rcu_read_lock();
-
-			/* calc the free space in [0, skip_space - 1] */
-			skip_space -= used_space;
-		}
-
 		/*
 		 * we can use the free space in [0, skip_space - 1], subtract
 		 * it from the total.
@@ -2011,8 +1969,6 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
 		i++;
 	}
 	rcu_read_unlock();
-	if (fs_info->alloc_start)
-		mutex_unlock(&fs_devices->device_list_mutex);
 
 	nr_devices = i;
 
@@ -2049,10 +2005,9 @@ static int btrfs_calc_avail_data_space(struct btrfs_fs_info *fs_info,
  * multiplier to scale the sizes.
  *
  * Unused device space usage is based on simulating the chunk allocator
- * algorithm that respects the device sizes, order of allocations and the
- * 'alloc_start' value, this is a close approximation of the actual use but
- * there are other factors that may change the result (like a new metadata
- * chunk).
+ * algorithm that respects the device sizes and order of allocations.  This is
+ * a close approximation of the actual use but there are other factors that may
+ * change the result (like a new metadata chunk).
  *
  * If metadata is exhausted, f_bavail will be 0.
  */
@@ -2235,7 +2190,7 @@ static int btrfs_freeze(struct super_block *sb)
 	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
 	struct btrfs_root *root = fs_info->tree_root;
 
-	fs_info->fs_frozen = 1;
+	set_bit(BTRFS_FS_FROZEN, &fs_info->flags);
 	/*
 	 * We don't need a barrier here, we'll wait for any transaction that
 	 * could be in progress on other threads (and do delayed iputs that
@@ -2254,7 +2209,9 @@ static int btrfs_freeze(struct super_block *sb)
 
 static int btrfs_unfreeze(struct super_block *sb)
 {
-	btrfs_sb(sb)->fs_frozen = 0;
+	struct btrfs_fs_info *fs_info = btrfs_sb(sb);
+
+	clear_bit(BTRFS_FS_FROZEN, &fs_info->flags);
 	return 0;
 }
 
diff --git a/fs/btrfs/sysfs.c b/fs/btrfs/sysfs.c
index 1f157fba8940..c2d5f3580b4c 100644
--- a/fs/btrfs/sysfs.c
+++ b/fs/btrfs/sysfs.c
@@ -447,11 +447,52 @@ static ssize_t btrfs_clone_alignment_show(struct kobject *kobj,
 
 BTRFS_ATTR(clone_alignment, btrfs_clone_alignment_show);
 
+static ssize_t quota_override_show(struct kobject *kobj,
+				   struct kobj_attribute *a, char *buf)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+	int quota_override;
+
+	quota_override = test_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags);
+	return snprintf(buf, PAGE_SIZE, "%d\n", quota_override);
+}
+
+static ssize_t quota_override_store(struct kobject *kobj,
+				    struct kobj_attribute *a,
+				    const char *buf, size_t len)
+{
+	struct btrfs_fs_info *fs_info = to_fs_info(kobj);
+	unsigned long knob;
+	int err;
+
+	if (!fs_info)
+		return -EPERM;
+
+	if (!capable(CAP_SYS_RESOURCE))
+		return -EPERM;
+
+	err = kstrtoul(buf, 10, &knob);
+	if (err)
+		return err;
+	if (knob > 1)
+		return -EINVAL;
+
+	if (knob)
+		set_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags);
+	else
+		clear_bit(BTRFS_FS_QUOTA_OVERRIDE, &fs_info->flags);
+
+	return len;
+}
+
+BTRFS_ATTR_RW(quota_override, quota_override_show, quota_override_store);
+
 static const struct attribute *btrfs_attrs[] = {
 	BTRFS_ATTR_PTR(label),
 	BTRFS_ATTR_PTR(nodesize),
 	BTRFS_ATTR_PTR(sectorsize),
 	BTRFS_ATTR_PTR(clone_alignment),
+	BTRFS_ATTR_PTR(quota_override),
 	NULL,
 };
 
diff --git a/fs/btrfs/tests/btrfs-tests.c b/fs/btrfs/tests/btrfs-tests.c
index ea272432c930..b18ab8f327a5 100644
--- a/fs/btrfs/tests/btrfs-tests.c
+++ b/fs/btrfs/tests/btrfs-tests.c
@@ -237,7 +237,6 @@ void btrfs_init_dummy_trans(struct btrfs_trans_handle *trans)
 {
 	memset(trans, 0, sizeof(*trans));
 	trans->transid = 1;
-	INIT_LIST_HEAD(&trans->qgroup_ref_list);
 	trans->type = __TRANS_DUMMY;
 }
 
diff --git a/fs/btrfs/tests/extent-io-tests.c b/fs/btrfs/tests/extent-io-tests.c
index 133753232a94..d06b1c931d05 100644
--- a/fs/btrfs/tests/extent-io-tests.c
+++ b/fs/btrfs/tests/extent-io-tests.c
@@ -87,7 +87,7 @@ static int test_find_delalloc(u32 sectorsize)
 		return -ENOMEM;
 	}
 
-	extent_io_tree_init(&tmp, &inode->i_data);
+	extent_io_tree_init(&tmp, inode);
 
 	/*
 	 * First go through and create and mark all of our pages dirty, we pin
diff --git a/fs/btrfs/tests/inode-tests.c b/fs/btrfs/tests/inode-tests.c
index 4d0f038e14f1..8c91d03cc82d 100644
--- a/fs/btrfs/tests/inode-tests.c
+++ b/fs/btrfs/tests/inode-tests.c
@@ -278,7 +278,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 
 	/* First with no extents */
 	BTRFS_I(inode)->root = root;
-	em = btrfs_get_extent(inode, NULL, 0, 0, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, sectorsize, 0);
 	if (IS_ERR(em)) {
 		em = NULL;
 		test_msg("Got an error when we shouldn't have\n");
@@ -293,7 +293,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 		goto out;
 	}
 	free_extent_map(em);
-	btrfs_drop_extent_cache(inode, 0, (u64)-1, 0);
+	btrfs_drop_extent_cache(BTRFS_I(inode), 0, (u64)-1, 0);
 
 	/*
 	 * All of the magic numbers are based on the mapping setup in
@@ -302,7 +302,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	 */
 	setup_file_extents(root, sectorsize);
 
-	em = btrfs_get_extent(inode, NULL, 0, 0, (u64)-1, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, (u64)-1, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -323,7 +323,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -350,7 +350,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -372,7 +372,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Regular extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -399,7 +399,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* The next 3 are split extents */
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -428,7 +428,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -450,7 +450,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -484,7 +484,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Prealloc extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -513,7 +513,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* The next 3 are a half written prealloc extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -543,7 +543,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -576,7 +576,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -611,7 +611,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Now for the compressed extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -645,7 +645,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* Split compressed extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -680,7 +680,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -707,7 +707,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -742,7 +742,8 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	free_extent_map(em);
 
 	/* A hole between regular extents but no hole extent */
-	em = btrfs_get_extent(inode, NULL, 0, offset + 6, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset + 6,
+			sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -769,7 +770,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, 4096 * 1024, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, 4096 * 1024, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -802,7 +803,7 @@ static noinline int test_btrfs_get_extent(u32 sectorsize, u32 nodesize)
 	offset = em->start + em->len;
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, offset, sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, offset, sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -885,7 +886,7 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 	insert_inode_item_key(root);
 	insert_extent(root, sectorsize, sectorsize, sectorsize, 0, sectorsize,
 		      sectorsize, BTRFS_FILE_EXTENT_REG, 0, 1);
-	em = btrfs_get_extent(inode, NULL, 0, 0, 2 * sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, 0, 2 * sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
@@ -907,7 +908,8 @@ static int test_hole_first(u32 sectorsize, u32 nodesize)
 	}
 	free_extent_map(em);
 
-	em = btrfs_get_extent(inode, NULL, 0, sectorsize, 2 * sectorsize, 0);
+	em = btrfs_get_extent(BTRFS_I(inode), NULL, 0, sectorsize,
+			2 * sectorsize, 0);
 	if (IS_ERR(em)) {
 		test_msg("Got an error when we shouldn't have\n");
 		goto out;
diff --git a/fs/btrfs/transaction.c b/fs/btrfs/transaction.c
index 0e0508f488b2..f615d59b0489 100644
--- a/fs/btrfs/transaction.c
+++ b/fs/btrfs/transaction.c
@@ -60,8 +60,8 @@ static const unsigned int btrfs_blocked_trans_types[TRANS_STATE_MAX] = {
 
 void btrfs_put_transaction(struct btrfs_transaction *transaction)
 {
-	WARN_ON(atomic_read(&transaction->use_count) == 0);
-	if (atomic_dec_and_test(&transaction->use_count)) {
+	WARN_ON(refcount_read(&transaction->use_count) == 0);
+	if (refcount_dec_and_test(&transaction->use_count)) {
 		BUG_ON(!list_empty(&transaction->list));
 		WARN_ON(!RB_EMPTY_ROOT(&transaction->delayed_refs.href_root));
 		if (transaction->delayed_refs.pending_csums)
@@ -93,7 +93,7 @@ void btrfs_put_transaction(struct btrfs_transaction *transaction)
 			btrfs_put_block_group_trimming(cache);
 			btrfs_put_block_group(cache);
 		}
-		kmem_cache_free(btrfs_transaction_cachep, transaction);
+		kfree(transaction);
 	}
 }
 
@@ -207,7 +207,7 @@ loop:
 			spin_unlock(&fs_info->trans_lock);
 			return -EBUSY;
 		}
-		atomic_inc(&cur_trans->use_count);
+		refcount_inc(&cur_trans->use_count);
 		atomic_inc(&cur_trans->num_writers);
 		extwriter_counter_inc(cur_trans, type);
 		spin_unlock(&fs_info->trans_lock);
@@ -228,7 +228,7 @@ loop:
 	 */
 	BUG_ON(type == TRANS_JOIN_NOLOCK);
 
-	cur_trans = kmem_cache_alloc(btrfs_transaction_cachep, GFP_NOFS);
+	cur_trans = kmalloc(sizeof(*cur_trans), GFP_NOFS);
 	if (!cur_trans)
 		return -ENOMEM;
 
@@ -238,11 +238,11 @@ loop:
 		 * someone started a transaction after we unlocked.  Make sure
 		 * to redo the checks above
 		 */
-		kmem_cache_free(btrfs_transaction_cachep, cur_trans);
+		kfree(cur_trans);
 		goto loop;
 	} else if (test_bit(BTRFS_FS_STATE_ERROR, &fs_info->fs_state)) {
 		spin_unlock(&fs_info->trans_lock);
-		kmem_cache_free(btrfs_transaction_cachep, cur_trans);
+		kfree(cur_trans);
 		return -EROFS;
 	}
 
@@ -257,7 +257,7 @@ loop:
 	 * One for this trans handle, one so it will live on until we
 	 * commit the transaction.
 	 */
-	atomic_set(&cur_trans->use_count, 2);
+	refcount_set(&cur_trans->use_count, 2);
 	atomic_set(&cur_trans->pending_ordered, 0);
 	cur_trans->flags = 0;
 	cur_trans->start_time = get_seconds();
@@ -294,7 +294,7 @@ loop:
 	spin_lock_init(&cur_trans->dropped_roots_lock);
 	list_add_tail(&cur_trans->list, &fs_info->trans_list);
 	extent_io_tree_init(&cur_trans->dirty_pages,
-			     fs_info->btree_inode->i_mapping);
+			     fs_info->btree_inode);
 	fs_info->generation++;
 	cur_trans->transid = fs_info->generation;
 	fs_info->running_transaction = cur_trans;
@@ -432,7 +432,7 @@ static void wait_current_trans(struct btrfs_fs_info *fs_info)
 	spin_lock(&fs_info->trans_lock);
 	cur_trans = fs_info->running_transaction;
 	if (cur_trans && is_transaction_blocked(cur_trans)) {
-		atomic_inc(&cur_trans->use_count);
+		refcount_inc(&cur_trans->use_count);
 		spin_unlock(&fs_info->trans_lock);
 
 		wait_event(fs_info->transaction_wait,
@@ -474,7 +474,8 @@ static inline bool need_reserve_reloc_root(struct btrfs_root *root)
 
 static struct btrfs_trans_handle *
 start_transaction(struct btrfs_root *root, unsigned int num_items,
-		  unsigned int type, enum btrfs_reserve_flush_enum flush)
+		  unsigned int type, enum btrfs_reserve_flush_enum flush,
+		  bool enforce_qgroups)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 
@@ -505,9 +506,10 @@ start_transaction(struct btrfs_root *root, unsigned int num_items,
 	 * Do the reservation before we join the transaction so we can do all
 	 * the appropriate flushing if need be.
 	 */
-	if (num_items > 0 && root != fs_info->chunk_root) {
+	if (num_items && root != fs_info->chunk_root) {
 		qgroup_reserved = num_items * fs_info->nodesize;
-		ret = btrfs_qgroup_reserve_meta(root, qgroup_reserved);
+		ret = btrfs_qgroup_reserve_meta(root, qgroup_reserved,
+						enforce_qgroups);
 		if (ret)
 			return ERR_PTR(ret);
 
@@ -570,7 +572,6 @@ again:
 
 	h->type = type;
 	h->can_flush_pending_bgs = true;
-	INIT_LIST_HEAD(&h->qgroup_ref_list);
 	INIT_LIST_HEAD(&h->new_bgs);
 
 	smp_mb();
@@ -613,8 +614,9 @@ struct btrfs_trans_handle *btrfs_start_transaction(struct btrfs_root *root,
 						   unsigned int num_items)
 {
 	return start_transaction(root, num_items, TRANS_START,
-				 BTRFS_RESERVE_FLUSH_ALL);
+				 BTRFS_RESERVE_FLUSH_ALL, true);
 }
+
 struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
 					struct btrfs_root *root,
 					unsigned int num_items,
@@ -625,7 +627,14 @@ struct btrfs_trans_handle *btrfs_start_transaction_fallback_global_rsv(
 	u64 num_bytes;
 	int ret;
 
-	trans = btrfs_start_transaction(root, num_items);
+	/*
+	 * We have two callers: unlink and block group removal.  The
+	 * former should succeed even if we will temporarily exceed
+	 * quota and the latter operates on the extent root so
+	 * qgroup enforcement is ignored anyway.
+	 */
+	trans = start_transaction(root, num_items, TRANS_START,
+				  BTRFS_RESERVE_FLUSH_ALL, false);
 	if (!IS_ERR(trans) || PTR_ERR(trans) != -ENOSPC)
 		return trans;
 
@@ -654,25 +663,25 @@ struct btrfs_trans_handle *btrfs_start_transaction_lflush(
 					unsigned int num_items)
 {
 	return start_transaction(root, num_items, TRANS_START,
-				 BTRFS_RESERVE_FLUSH_LIMIT);
+				 BTRFS_RESERVE_FLUSH_LIMIT, true);
 }
 
 struct btrfs_trans_handle *btrfs_join_transaction(struct btrfs_root *root)
 {
-	return start_transaction(root, 0, TRANS_JOIN,
-				 BTRFS_RESERVE_NO_FLUSH);
+	return start_transaction(root, 0, TRANS_JOIN, BTRFS_RESERVE_NO_FLUSH,
+				 true);
 }
 
 struct btrfs_trans_handle *btrfs_join_transaction_nolock(struct btrfs_root *root)
 {
 	return start_transaction(root, 0, TRANS_JOIN_NOLOCK,
-				 BTRFS_RESERVE_NO_FLUSH);
+				 BTRFS_RESERVE_NO_FLUSH, true);
 }
 
 struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root)
 {
 	return start_transaction(root, 0, TRANS_USERSPACE,
-				 BTRFS_RESERVE_NO_FLUSH);
+				 BTRFS_RESERVE_NO_FLUSH, true);
 }
 
 /*
@@ -691,7 +700,7 @@ struct btrfs_trans_handle *btrfs_start_ioctl_transaction(struct btrfs_root *root
 struct btrfs_trans_handle *btrfs_attach_transaction(struct btrfs_root *root)
 {
 	return start_transaction(root, 0, TRANS_ATTACH,
-				 BTRFS_RESERVE_NO_FLUSH);
+				 BTRFS_RESERVE_NO_FLUSH, true);
 }
 
 /*
@@ -707,7 +716,7 @@ btrfs_attach_transaction_barrier(struct btrfs_root *root)
 	struct btrfs_trans_handle *trans;
 
 	trans = start_transaction(root, 0, TRANS_ATTACH,
-				  BTRFS_RESERVE_NO_FLUSH);
+				  BTRFS_RESERVE_NO_FLUSH, true);
 	if (IS_ERR(trans) && PTR_ERR(trans) == -ENOENT)
 		btrfs_wait_for_commit(root->fs_info, 0);
 
@@ -734,7 +743,7 @@ int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid)
 		list_for_each_entry(t, &fs_info->trans_list, list) {
 			if (t->transid == transid) {
 				cur_trans = t;
-				atomic_inc(&cur_trans->use_count);
+				refcount_inc(&cur_trans->use_count);
 				ret = 0;
 				break;
 			}
@@ -763,7 +772,7 @@ int btrfs_wait_for_commit(struct btrfs_fs_info *fs_info, u64 transid)
 				if (t->state == TRANS_STATE_COMPLETED)
 					break;
 				cur_trans = t;
-				atomic_inc(&cur_trans->use_count);
+				refcount_inc(&cur_trans->use_count);
 				break;
 			}
 		}
@@ -866,14 +875,14 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 
 	if (lock && !atomic_read(&info->open_ioctl_trans) &&
 	    should_end_transaction(trans) &&
-	    ACCESS_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) {
+	    READ_ONCE(cur_trans->state) == TRANS_STATE_RUNNING) {
 		spin_lock(&info->trans_lock);
 		if (cur_trans->state == TRANS_STATE_RUNNING)
 			cur_trans->state = TRANS_STATE_BLOCKED;
 		spin_unlock(&info->trans_lock);
 	}
 
-	if (lock && ACCESS_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) {
+	if (lock && READ_ONCE(cur_trans->state) == TRANS_STATE_BLOCKED) {
 		if (throttle)
 			return btrfs_commit_transaction(trans);
 		else
@@ -907,7 +916,6 @@ static int __btrfs_end_transaction(struct btrfs_trans_handle *trans,
 		wake_up_process(info->transaction_kthread);
 		err = -EIO;
 	}
-	assert_qgroups_uptodate(trans);
 
 	kmem_cache_free(btrfs_trans_handle_cachep, trans);
 	if (must_run_delayed_refs) {
@@ -1354,12 +1362,8 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 	 * enabled. If this check races with the ioctl, rescan will
 	 * kick in anyway.
 	 */
-	mutex_lock(&fs_info->qgroup_ioctl_lock);
-	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags)) {
-		mutex_unlock(&fs_info->qgroup_ioctl_lock);
+	if (!test_bit(BTRFS_FS_QUOTA_ENABLED, &fs_info->flags))
 		return 0;
-	}
-	mutex_unlock(&fs_info->qgroup_ioctl_lock);
 
 	/*
 	 * We are going to commit transaction, see btrfs_commit_transaction()
@@ -1370,9 +1374,6 @@ static int qgroup_account_snapshot(struct btrfs_trans_handle *trans,
 	ret = commit_fs_roots(trans, fs_info);
 	if (ret)
 		goto out;
-	ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
-	if (ret < 0)
-		goto out;
 	ret = btrfs_qgroup_account_extents(trans, fs_info);
 	if (ret < 0)
 		goto out;
@@ -1499,12 +1500,12 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	/*
 	 * insert the directory item
 	 */
-	ret = btrfs_set_inode_index(parent_inode, &index);
+	ret = btrfs_set_inode_index(BTRFS_I(parent_inode), &index);
 	BUG_ON(ret); /* -ENOMEM */
 
 	/* check if there is a file/dir which has the same name. */
 	dir_item = btrfs_lookup_dir_item(NULL, parent_root, path,
-					 btrfs_ino(parent_inode),
+					 btrfs_ino(BTRFS_I(parent_inode)),
 					 dentry->d_name.name,
 					 dentry->d_name.len, 0);
 	if (dir_item != NULL && !IS_ERR(dir_item)) {
@@ -1598,7 +1599,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 	 */
 	ret = btrfs_add_root_ref(trans, fs_info, objectid,
 				 parent_root->root_key.objectid,
-				 btrfs_ino(parent_inode), index,
+				 btrfs_ino(BTRFS_I(parent_inode)), index,
 				 dentry->d_name.name, dentry->d_name.len);
 	if (ret) {
 		btrfs_abort_transaction(trans, ret);
@@ -1638,7 +1639,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 
 	ret = btrfs_insert_dir_item(trans, parent_root,
 				    dentry->d_name.name, dentry->d_name.len,
-				    parent_inode, &key,
+				    BTRFS_I(parent_inode), &key,
 				    BTRFS_FT_DIR, index);
 	/* We have check then name at the beginning, so it is impossible. */
 	BUG_ON(ret == -EEXIST || ret == -EOVERFLOW);
@@ -1647,7 +1648,7 @@ static noinline int create_pending_snapshot(struct btrfs_trans_handle *trans,
 		goto fail;
 	}
 
-	btrfs_i_size_write(parent_inode, parent_inode->i_size +
+	btrfs_i_size_write(BTRFS_I(parent_inode), parent_inode->i_size +
 					 dentry->d_name.len * 2);
 	parent_inode->i_mtime = parent_inode->i_ctime =
 		current_time(parent_inode);
@@ -1833,7 +1834,7 @@ int btrfs_commit_transaction_async(struct btrfs_trans_handle *trans,
 
 	/* take transaction reference */
 	cur_trans = trans->transaction;
-	atomic_inc(&cur_trans->use_count);
+	refcount_inc(&cur_trans->use_count);
 
 	btrfs_end_transaction(trans);
 
@@ -1922,7 +1923,7 @@ static inline int btrfs_start_delalloc_flush(struct btrfs_fs_info *fs_info)
 static inline void btrfs_wait_delalloc_flush(struct btrfs_fs_info *fs_info)
 {
 	if (btrfs_test_opt(fs_info, FLUSHONCOMMIT))
-		btrfs_wait_ordered_roots(fs_info, -1, 0, (u64)-1);
+		btrfs_wait_ordered_roots(fs_info, U64_MAX, 0, (u64)-1);
 }
 
 static inline void
@@ -1940,7 +1941,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	int ret;
 
 	/* Stop the commit early if ->aborted is set */
-	if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
+	if (unlikely(READ_ONCE(cur_trans->aborted))) {
 		ret = cur_trans->aborted;
 		btrfs_end_transaction(trans);
 		return ret;
@@ -2009,7 +2010,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	spin_lock(&fs_info->trans_lock);
 	if (cur_trans->state >= TRANS_STATE_COMMIT_START) {
 		spin_unlock(&fs_info->trans_lock);
-		atomic_inc(&cur_trans->use_count);
+		refcount_inc(&cur_trans->use_count);
 		ret = btrfs_end_transaction(trans);
 
 		wait_for_commit(cur_trans);
@@ -2029,7 +2030,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		prev_trans = list_entry(cur_trans->list.prev,
 					struct btrfs_transaction, list);
 		if (prev_trans->state != TRANS_STATE_COMPLETED) {
-			atomic_inc(&prev_trans->use_count);
+			refcount_inc(&prev_trans->use_count);
 			spin_unlock(&fs_info->trans_lock);
 
 			wait_for_commit(prev_trans);
@@ -2080,7 +2081,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		   atomic_read(&cur_trans->num_writers) == 1);
 
 	/* ->aborted might be set after the previous check, so check it */
-	if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
+	if (unlikely(READ_ONCE(cur_trans->aborted))) {
 		ret = cur_trans->aborted;
 		goto scrub_continue;
 	}
@@ -2124,13 +2125,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		goto scrub_continue;
 	}
 
-	/* Reocrd old roots for later qgroup accounting */
-	ret = btrfs_qgroup_prepare_account_extents(trans, fs_info);
-	if (ret) {
-		mutex_unlock(&fs_info->reloc_mutex);
-		goto scrub_continue;
-	}
-
 	/*
 	 * make sure none of the code above managed to slip in a
 	 * delayed item
@@ -2173,6 +2167,17 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	btrfs_free_log_root_tree(trans, fs_info);
 
 	/*
+	 * commit_fs_roots() can call btrfs_save_ino_cache(), which generates
+	 * new delayed refs. Must handle them or qgroup can be wrong.
+	 */
+	ret = btrfs_run_delayed_refs(trans, fs_info, (unsigned long)-1);
+	if (ret) {
+		mutex_unlock(&fs_info->tree_log_mutex);
+		mutex_unlock(&fs_info->reloc_mutex);
+		goto scrub_continue;
+	}
+
+	/*
 	 * Since fs roots are all committed, we can get a quite accurate
 	 * new_roots. So let's do quota accounting.
 	 */
@@ -2194,14 +2199,14 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	 * The tasks which save the space cache and inode cache may also
 	 * update ->aborted, check it.
 	 */
-	if (unlikely(ACCESS_ONCE(cur_trans->aborted))) {
+	if (unlikely(READ_ONCE(cur_trans->aborted))) {
 		ret = cur_trans->aborted;
 		mutex_unlock(&fs_info->tree_log_mutex);
 		mutex_unlock(&fs_info->reloc_mutex);
 		goto scrub_continue;
 	}
 
-	btrfs_prepare_extent_commit(trans, fs_info);
+	btrfs_prepare_extent_commit(fs_info);
 
 	cur_trans = fs_info->running_transaction;
 
@@ -2217,7 +2222,6 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 
 	switch_commit_roots(cur_trans, fs_info);
 
-	assert_qgroups_uptodate(trans);
 	ASSERT(list_empty(&cur_trans->dirty_bgs));
 	ASSERT(list_empty(&cur_trans->io_bgs));
 	update_super_roots(fs_info);
@@ -2251,7 +2255,7 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 		goto scrub_continue;
 	}
 
-	ret = write_ctree_super(trans, fs_info, 0);
+	ret = write_all_supers(fs_info, 0);
 	if (ret) {
 		mutex_unlock(&fs_info->tree_log_mutex);
 		goto scrub_continue;
@@ -2300,7 +2304,8 @@ int btrfs_commit_transaction(struct btrfs_trans_handle *trans)
 	 * it'll result in deadlock about SB_FREEZE_FS.
 	 */
 	if (current != fs_info->transaction_kthread &&
-	    current != fs_info->cleaner_kthread && !fs_info->fs_frozen)
+	    current != fs_info->cleaner_kthread &&
+	    !test_bit(BTRFS_FS_FROZEN, &fs_info->flags))
 		btrfs_run_delayed_iputs(fs_info);
 
 	return ret;
diff --git a/fs/btrfs/transaction.h b/fs/btrfs/transaction.h
index 5dfb5590fff6..c55e44560103 100644
--- a/fs/btrfs/transaction.h
+++ b/fs/btrfs/transaction.h
@@ -18,6 +18,8 @@
 
 #ifndef __BTRFS_TRANSACTION__
 #define __BTRFS_TRANSACTION__
+
+#include <linux/refcount.h>
 #include "btrfs_inode.h"
 #include "delayed-ref.h"
 #include "ctree.h"
@@ -49,7 +51,7 @@ struct btrfs_transaction {
 	 * transaction can end
 	 */
 	atomic_t num_writers;
-	atomic_t use_count;
+	refcount_t use_count;
 	atomic_t pending_ordered;
 
 	unsigned long flags;
@@ -125,8 +127,6 @@ struct btrfs_trans_handle {
 	unsigned int type;
 	struct btrfs_root *root;
 	struct btrfs_fs_info *fs_info;
-	struct seq_list delayed_ref_elem;
-	struct list_head qgroup_ref_list;
 	struct list_head new_bgs;
 };
 
diff --git a/fs/btrfs/tree-log.c b/fs/btrfs/tree-log.c
index eeffff84f280..f20ef211a73d 100644
--- a/fs/btrfs/tree-log.c
+++ b/fs/btrfs/tree-log.c
@@ -97,7 +97,7 @@
 #define LOG_WALK_REPLAY_ALL 3
 
 static int btrfs_log_inode(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *root, struct inode *inode,
+			   struct btrfs_root *root, struct btrfs_inode *inode,
 			   int inode_only,
 			   const loff_t start,
 			   const loff_t end,
@@ -631,8 +631,8 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	 * file.  This must be done before the btrfs_drop_extents run
 	 * so we don't try to drop this extent.
 	 */
-	ret = btrfs_lookup_file_extent(trans, root, path, btrfs_ino(inode),
-				       start, 0);
+	ret = btrfs_lookup_file_extent(trans, root, path,
+			btrfs_ino(BTRFS_I(inode)), start, 0);
 
 	if (ret == 0 &&
 	    (found_type == BTRFS_FILE_EXTENT_REG ||
@@ -673,6 +673,10 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 		unsigned long dest_offset;
 		struct btrfs_key ins;
 
+		if (btrfs_file_extent_disk_bytenr(eb, item) == 0 &&
+		    btrfs_fs_incompat(fs_info, NO_HOLES))
+			goto update_inode;
+
 		ret = btrfs_insert_empty_item(trans, root, path, key,
 					      sizeof(*item));
 		if (ret)
@@ -825,6 +829,7 @@ static noinline int replay_one_extent(struct btrfs_trans_handle *trans,
 	}
 
 	inode_add_bytes(inode, nbytes);
+update_inode:
 	ret = btrfs_update_inode(trans, root, inode);
 out:
 	if (inode)
@@ -843,7 +848,7 @@ out:
 static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
 				      struct btrfs_root *root,
 				      struct btrfs_path *path,
-				      struct inode *dir,
+				      struct btrfs_inode *dir,
 				      struct btrfs_dir_item *di)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -875,7 +880,8 @@ static noinline int drop_one_dir_item(struct btrfs_trans_handle *trans,
 	if (ret)
 		goto out;
 
-	ret = btrfs_unlink_inode(trans, root, dir, inode, name, name_len);
+	ret = btrfs_unlink_inode(trans, root, dir, BTRFS_I(inode), name,
+			name_len);
 	if (ret)
 		goto out;
 	else
@@ -991,8 +997,8 @@ static inline int __add_inode_ref(struct btrfs_trans_handle *trans,
 				  struct btrfs_root *root,
 				  struct btrfs_path *path,
 				  struct btrfs_root *log_root,
-				  struct inode *dir, struct inode *inode,
-				  struct extent_buffer *eb,
+				  struct btrfs_inode *dir,
+				  struct btrfs_inode *inode,
 				  u64 inode_objectid, u64 parent_objectid,
 				  u64 ref_index, char *name, int namelen,
 				  int *search_done)
@@ -1047,12 +1053,11 @@ again:
 					    parent_objectid,
 					    victim_name,
 					    victim_name_len)) {
-				inc_nlink(inode);
+				inc_nlink(&inode->vfs_inode);
 				btrfs_release_path(path);
 
-				ret = btrfs_unlink_inode(trans, root, dir,
-							 inode, victim_name,
-							 victim_name_len);
+				ret = btrfs_unlink_inode(trans, root, dir, inode,
+						victim_name, victim_name_len);
 				kfree(victim_name);
 				if (ret)
 					return ret;
@@ -1115,16 +1120,16 @@ again:
 					    victim_name_len)) {
 				ret = -ENOENT;
 				victim_parent = read_one_inode(root,
-							       parent_objectid);
+						parent_objectid);
 				if (victim_parent) {
-					inc_nlink(inode);
+					inc_nlink(&inode->vfs_inode);
 					btrfs_release_path(path);
 
 					ret = btrfs_unlink_inode(trans, root,
-								 victim_parent,
-								 inode,
-								 victim_name,
-								 victim_name_len);
+							BTRFS_I(victim_parent),
+							inode,
+							victim_name,
+							victim_name_len);
 					if (!ret)
 						ret = btrfs_run_delayed_items(
 								  trans,
@@ -1170,15 +1175,19 @@ next:
 	return 0;
 }
 
-static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
-			     u32 *namelen, char **name, u64 *index,
-			     u64 *parent_objectid)
+static int extref_get_fields(struct extent_buffer *eb, int slot,
+			     unsigned long ref_ptr, u32 *namelen, char **name,
+			     u64 *index, u64 *parent_objectid)
 {
 	struct btrfs_inode_extref *extref;
 
 	extref = (struct btrfs_inode_extref *)ref_ptr;
 
 	*namelen = btrfs_inode_extref_name_len(eb, extref);
+	if (!btrfs_is_name_len_valid(eb, slot, (unsigned long)&extref->name,
+				     *namelen))
+		return -EIO;
+
 	*name = kmalloc(*namelen, GFP_NOFS);
 	if (*name == NULL)
 		return -ENOMEM;
@@ -1193,14 +1202,19 @@ static int extref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
 	return 0;
 }
 
-static int ref_get_fields(struct extent_buffer *eb, unsigned long ref_ptr,
-			  u32 *namelen, char **name, u64 *index)
+static int ref_get_fields(struct extent_buffer *eb, int slot,
+			  unsigned long ref_ptr, u32 *namelen, char **name,
+			  u64 *index)
 {
 	struct btrfs_inode_ref *ref;
 
 	ref = (struct btrfs_inode_ref *)ref_ptr;
 
 	*namelen = btrfs_inode_ref_name_len(eb, ref);
+	if (!btrfs_is_name_len_valid(eb, slot, (unsigned long)(ref + 1),
+				     *namelen))
+		return -EIO;
+
 	*name = kmalloc(*namelen, GFP_NOFS);
 	if (*name == NULL)
 		return -ENOMEM;
@@ -1275,8 +1289,8 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 
 	while (ref_ptr < ref_end) {
 		if (log_ref_ver) {
-			ret = extref_get_fields(eb, ref_ptr, &namelen, &name,
-						&ref_index, &parent_objectid);
+			ret = extref_get_fields(eb, slot, ref_ptr, &namelen,
+					  &name, &ref_index, &parent_objectid);
 			/*
 			 * parent object can change from one array
 			 * item to another.
@@ -1288,15 +1302,16 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 				goto out;
 			}
 		} else {
-			ret = ref_get_fields(eb, ref_ptr, &namelen, &name,
-					     &ref_index);
+			ret = ref_get_fields(eb, slot, ref_ptr, &namelen,
+					     &name, &ref_index);
 		}
 		if (ret)
 			goto out;
 
 		/* if we already have a perfect match, we're done */
-		if (!inode_in_dir(root, path, btrfs_ino(dir), btrfs_ino(inode),
-				  ref_index, name, namelen)) {
+		if (!inode_in_dir(root, path, btrfs_ino(BTRFS_I(dir)),
+					btrfs_ino(BTRFS_I(inode)), ref_index,
+					name, namelen)) {
 			/*
 			 * look for a conflicting back reference in the
 			 * metadata. if we find one we have to unlink that name
@@ -1307,7 +1322,8 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 
 			if (!search_done) {
 				ret = __add_inode_ref(trans, root, path, log,
-						      dir, inode, eb,
+						      BTRFS_I(dir),
+						      BTRFS_I(inode),
 						      inode_objectid,
 						      parent_objectid,
 						      ref_index, name, namelen,
@@ -1320,8 +1336,9 @@ static noinline int add_inode_ref(struct btrfs_trans_handle *trans,
 			}
 
 			/* insert our name */
-			ret = btrfs_add_link(trans, dir, inode, name, namelen,
-					     0, ref_index);
+			ret = btrfs_add_link(trans, BTRFS_I(dir),
+					BTRFS_I(inode),
+					name, namelen, 0, ref_index);
 			if (ret)
 				goto out;
 
@@ -1360,7 +1377,7 @@ static int insert_orphan_item(struct btrfs_trans_handle *trans,
 }
 
 static int count_inode_extrefs(struct btrfs_root *root,
-			       struct inode *inode, struct btrfs_path *path)
+		struct btrfs_inode *inode, struct btrfs_path *path)
 {
 	int ret = 0;
 	int name_len;
@@ -1404,7 +1421,7 @@ static int count_inode_extrefs(struct btrfs_root *root,
 }
 
 static int count_inode_refs(struct btrfs_root *root,
-			       struct inode *inode, struct btrfs_path *path)
+			struct btrfs_inode *inode, struct btrfs_path *path)
 {
 	int ret;
 	struct btrfs_key key;
@@ -1477,19 +1494,19 @@ static noinline int fixup_inode_link_count(struct btrfs_trans_handle *trans,
 	struct btrfs_path *path;
 	int ret;
 	u64 nlink = 0;
-	u64 ino = btrfs_ino(inode);
+	u64 ino = btrfs_ino(BTRFS_I(inode));
 
 	path = btrfs_alloc_path();
 	if (!path)
 		return -ENOMEM;
 
-	ret = count_inode_refs(root, inode, path);
+	ret = count_inode_refs(root, BTRFS_I(inode), path);
 	if (ret < 0)
 		goto out;
 
 	nlink = ret;
 
-	ret = count_inode_extrefs(root, inode, path);
+	ret = count_inode_extrefs(root, BTRFS_I(inode), path);
 	if (ret < 0)
 		goto out;
 
@@ -1639,7 +1656,8 @@ static noinline int insert_one_name(struct btrfs_trans_handle *trans,
 		return -EIO;
 	}
 
-	ret = btrfs_add_link(trans, dir, inode, name, name_len, 1, index);
+	ret = btrfs_add_link(trans, BTRFS_I(dir), BTRFS_I(inode), name,
+			name_len, 1, index);
 
 	/* FIXME, put inode into FIXUP list */
 
@@ -1769,7 +1787,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 	if (!exists)
 		goto out;
 
-	ret = drop_one_dir_item(trans, root, path, dir, dst_di);
+	ret = drop_one_dir_item(trans, root, path, BTRFS_I(dir), dst_di);
 	if (ret)
 		goto out;
 
@@ -1778,7 +1796,7 @@ static noinline int replay_one_name(struct btrfs_trans_handle *trans,
 out:
 	btrfs_release_path(path);
 	if (!ret && update_size) {
-		btrfs_i_size_write(dir, dir->i_size + name_len * 2);
+		btrfs_i_size_write(BTRFS_I(dir), dir->i_size + name_len * 2);
 		ret = btrfs_update_inode(trans, root, dir);
 	}
 	kfree(name);
@@ -1832,7 +1850,7 @@ static noinline int replay_one_dir_item(struct btrfs_trans_handle *trans,
 	ptr_end = ptr + item_size;
 	while (ptr < ptr_end) {
 		di = (struct btrfs_dir_item *)ptr;
-		if (verify_dir_item(fs_info, eb, di))
+		if (verify_dir_item(fs_info, eb, slot, di))
 			return -EIO;
 		name_len = btrfs_dir_name_len(eb, di);
 		ret = replay_one_name(trans, root, path, eb, di, key);
@@ -2008,7 +2026,7 @@ again:
 	ptr_end = ptr + item_size;
 	while (ptr < ptr_end) {
 		di = (struct btrfs_dir_item *)ptr;
-		if (verify_dir_item(fs_info, eb, di)) {
+		if (verify_dir_item(fs_info, eb, slot, di)) {
 			ret = -EIO;
 			goto out;
 		}
@@ -2052,8 +2070,8 @@ again:
 			}
 
 			inc_nlink(inode);
-			ret = btrfs_unlink_inode(trans, root, dir, inode,
-						 name, name_len);
+			ret = btrfs_unlink_inode(trans, root, BTRFS_I(dir),
+					BTRFS_I(inode), name, name_len);
 			if (!ret)
 				ret = btrfs_run_delayed_items(trans, fs_info);
 			kfree(name);
@@ -2093,6 +2111,7 @@ static int replay_xattr_deletes(struct btrfs_trans_handle *trans,
 			      struct btrfs_path *path,
 			      const u64 ino)
 {
+	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_key search_key;
 	struct btrfs_path *log_path;
 	int i;
@@ -2134,6 +2153,12 @@ process_leaf:
 			u32 this_len = sizeof(*di) + name_len + data_len;
 			char *name;
 
+			ret = verify_dir_item(fs_info, path->nodes[0],
+					      path->slots[0], di);
+			if (ret) {
+				ret = -EIO;
+				goto out;
+			}
 			name = kmalloc(name_len, GFP_NOFS);
 			if (!name) {
 				ret = -ENOMEM;
@@ -2469,7 +2494,7 @@ static noinline int walk_down_log_tree(struct btrfs_trans_handle *trans,
 				if (trans) {
 					btrfs_tree_lock(next);
 					btrfs_set_lock_blocking(next);
-					clean_tree_block(trans, fs_info, next);
+					clean_tree_block(fs_info, next);
 					btrfs_wait_tree_block_writeback(next);
 					btrfs_tree_unlock(next);
 				}
@@ -2549,7 +2574,7 @@ static noinline int walk_up_log_tree(struct btrfs_trans_handle *trans,
 				if (trans) {
 					btrfs_tree_lock(next);
 					btrfs_set_lock_blocking(next);
-					clean_tree_block(trans, fs_info, next);
+					clean_tree_block(fs_info, next);
 					btrfs_wait_tree_block_writeback(next);
 					btrfs_tree_unlock(next);
 				}
@@ -2627,7 +2652,7 @@ static int walk_log_tree(struct btrfs_trans_handle *trans,
 			if (trans) {
 				btrfs_tree_lock(next);
 				btrfs_set_lock_blocking(next);
-				clean_tree_block(trans, fs_info, next);
+				clean_tree_block(fs_info, next);
 				btrfs_wait_tree_block_writeback(next);
 				btrfs_tree_unlock(next);
 			}
@@ -2958,7 +2983,7 @@ int btrfs_sync_log(struct btrfs_trans_handle *trans,
 	 * the running transaction open, so a full commit can't hop
 	 * in and cause problems either.
 	 */
-	ret = write_ctree_super(trans, fs_info, 1);
+	ret = write_all_supers(fs_info, 1);
 	if (ret) {
 		btrfs_set_log_full_commit(fs_info, trans);
 		btrfs_abort_transaction(trans, ret);
@@ -3084,7 +3109,7 @@ int btrfs_free_log_root_tree(struct btrfs_trans_handle *trans,
 int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 				 struct btrfs_root *root,
 				 const char *name, int name_len,
-				 struct inode *dir, u64 index)
+				 struct btrfs_inode *dir, u64 index)
 {
 	struct btrfs_root *log;
 	struct btrfs_dir_item *di;
@@ -3094,14 +3119,14 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 	int bytes_del = 0;
 	u64 dir_ino = btrfs_ino(dir);
 
-	if (BTRFS_I(dir)->logged_trans < trans->transid)
+	if (dir->logged_trans < trans->transid)
 		return 0;
 
 	ret = join_running_log_trans(root);
 	if (ret)
 		return 0;
 
-	mutex_lock(&BTRFS_I(dir)->log_mutex);
+	mutex_lock(&dir->log_mutex);
 
 	log = root->log_root;
 	path = btrfs_alloc_path();
@@ -3176,7 +3201,7 @@ int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 fail:
 	btrfs_free_path(path);
 out_unlock:
-	mutex_unlock(&BTRFS_I(dir)->log_mutex);
+	mutex_unlock(&dir->log_mutex);
 	if (ret == -ENOSPC) {
 		btrfs_set_log_full_commit(root->fs_info, trans);
 		ret = 0;
@@ -3192,25 +3217,25 @@ out_unlock:
 int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root,
 			       const char *name, int name_len,
-			       struct inode *inode, u64 dirid)
+			       struct btrfs_inode *inode, u64 dirid)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
 	struct btrfs_root *log;
 	u64 index;
 	int ret;
 
-	if (BTRFS_I(inode)->logged_trans < trans->transid)
+	if (inode->logged_trans < trans->transid)
 		return 0;
 
 	ret = join_running_log_trans(root);
 	if (ret)
 		return 0;
 	log = root->log_root;
-	mutex_lock(&BTRFS_I(inode)->log_mutex);
+	mutex_lock(&inode->log_mutex);
 
 	ret = btrfs_del_inode_ref(trans, log, name, name_len, btrfs_ino(inode),
 				  dirid, &index);
-	mutex_unlock(&BTRFS_I(inode)->log_mutex);
+	mutex_unlock(&inode->log_mutex);
 	if (ret == -ENOSPC) {
 		btrfs_set_log_full_commit(fs_info, trans);
 		ret = 0;
@@ -3260,7 +3285,7 @@ static noinline int insert_dir_log_key(struct btrfs_trans_handle *trans,
  * to replay anything deleted before the fsync
  */
 static noinline int log_dir_items(struct btrfs_trans_handle *trans,
-			  struct btrfs_root *root, struct inode *inode,
+			  struct btrfs_root *root, struct btrfs_inode *inode,
 			  struct btrfs_path *path,
 			  struct btrfs_path *dst_path, int key_type,
 			  struct btrfs_log_ctx *ctx,
@@ -3450,7 +3475,7 @@ done:
  * key logged by this transaction.
  */
 static noinline int log_directory_changes(struct btrfs_trans_handle *trans,
-			  struct btrfs_root *root, struct inode *inode,
+			  struct btrfs_root *root, struct btrfs_inode *inode,
 			  struct btrfs_path *path,
 			  struct btrfs_path *dst_path,
 			  struct btrfs_log_ctx *ctx)
@@ -3464,9 +3489,8 @@ again:
 	min_key = 0;
 	max_key = 0;
 	while (1) {
-		ret = log_dir_items(trans, root, inode, path,
-				    dst_path, key_type, ctx, min_key,
-				    &max_key);
+		ret = log_dir_items(trans, root, inode, path, dst_path, key_type,
+				ctx, min_key, &max_key);
 		if (ret)
 			return ret;
 		if (max_key == (u64)-1)
@@ -3595,34 +3619,34 @@ static void fill_inode_item(struct btrfs_trans_handle *trans,
 
 static int log_inode_item(struct btrfs_trans_handle *trans,
 			  struct btrfs_root *log, struct btrfs_path *path,
-			  struct inode *inode)
+			  struct btrfs_inode *inode)
 {
 	struct btrfs_inode_item *inode_item;
 	int ret;
 
 	ret = btrfs_insert_empty_item(trans, log, path,
-				      &BTRFS_I(inode)->location,
-				      sizeof(*inode_item));
+				      &inode->location, sizeof(*inode_item));
 	if (ret && ret != -EEXIST)
 		return ret;
 	inode_item = btrfs_item_ptr(path->nodes[0], path->slots[0],
 				    struct btrfs_inode_item);
-	fill_inode_item(trans, path->nodes[0], inode_item, inode, 0, 0);
+	fill_inode_item(trans, path->nodes[0], inode_item, &inode->vfs_inode,
+			0, 0);
 	btrfs_release_path(path);
 	return 0;
 }
 
 static noinline int copy_items(struct btrfs_trans_handle *trans,
-			       struct inode *inode,
+			       struct btrfs_inode *inode,
 			       struct btrfs_path *dst_path,
 			       struct btrfs_path *src_path, u64 *last_extent,
 			       int start_slot, int nr, int inode_only,
 			       u64 logged_isize)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	unsigned long src_offset;
 	unsigned long dst_offset;
-	struct btrfs_root *log = BTRFS_I(inode)->root->log_root;
+	struct btrfs_root *log = inode->root->log_root;
 	struct btrfs_file_extent_item *extent;
 	struct btrfs_inode_item *inode_item;
 	struct extent_buffer *src = src_path->nodes[0];
@@ -3633,7 +3657,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	char *ins_data;
 	int i;
 	struct list_head ordered_sums;
-	int skip_csum = BTRFS_I(inode)->flags & BTRFS_INODE_NODATASUM;
+	int skip_csum = inode->flags & BTRFS_INODE_NODATASUM;
 	bool has_extents = false;
 	bool need_find_last_extent = true;
 	bool done = false;
@@ -3675,7 +3699,8 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 						    dst_path->slots[0],
 						    struct btrfs_inode_item);
 			fill_inode_item(trans, dst_path->nodes[0], inode_item,
-					inode, inode_only == LOG_INODE_EXISTS,
+					&inode->vfs_inode,
+					inode_only == LOG_INODE_EXISTS,
 					logged_isize);
 		} else {
 			copy_extent_buffer(dst_path->nodes[0], src, dst_offset,
@@ -3783,7 +3808,7 @@ static noinline int copy_items(struct btrfs_trans_handle *trans,
 	if (need_find_last_extent) {
 		u64 len;
 
-		ret = btrfs_prev_leaf(BTRFS_I(inode)->root, src_path);
+		ret = btrfs_prev_leaf(inode->root, src_path);
 		if (ret < 0)
 			return ret;
 		if (ret)
@@ -3825,8 +3850,8 @@ fill_holes:
 	if (need_find_last_extent) {
 		/* btrfs_prev_leaf could return 1 without releasing the path */
 		btrfs_release_path(src_path);
-		ret = btrfs_search_slot(NULL, BTRFS_I(inode)->root, &first_key,
-					src_path, 0, 0);
+		ret = btrfs_search_slot(NULL, inode->root, &first_key,
+				src_path, 0, 0);
 		if (ret < 0)
 			return ret;
 		ASSERT(ret == 0);
@@ -3846,7 +3871,7 @@ fill_holes:
 		u64 extent_end;
 
 		if (i >= btrfs_header_nritems(src_path->nodes[0])) {
-			ret = btrfs_next_leaf(BTRFS_I(inode)->root, src_path);
+			ret = btrfs_next_leaf(inode->root, src_path);
 			if (ret < 0)
 				return ret;
 			ASSERT(ret == 0);
@@ -3881,8 +3906,7 @@ fill_holes:
 		offset = *last_extent;
 		len = key.offset - *last_extent;
 		ret = btrfs_insert_file_extent(trans, log, btrfs_ino(inode),
-					       offset, 0, 0, len, 0, len, 0,
-					       0, 0);
+				offset, 0, 0, len, 0, len, 0, 0, 0);
 		if (ret)
 			break;
 		*last_extent = extent_end;
@@ -4055,7 +4079,7 @@ static int wait_ordered_extents(struct btrfs_trans_handle *trans,
 }
 
 static int log_one_extent(struct btrfs_trans_handle *trans,
-			  struct inode *inode, struct btrfs_root *root,
+			  struct btrfs_inode *inode, struct btrfs_root *root,
 			  const struct extent_map *em,
 			  struct btrfs_path *path,
 			  const struct list_head *logged_list,
@@ -4072,8 +4096,8 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 	int extent_inserted = 0;
 	bool ordered_io_err = false;
 
-	ret = wait_ordered_extents(trans, inode, root, em, logged_list,
-				   &ordered_io_err);
+	ret = wait_ordered_extents(trans, &inode->vfs_inode, root, em,
+			logged_list, &ordered_io_err);
 	if (ret)
 		return ret;
 
@@ -4084,7 +4108,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 
 	btrfs_init_map_token(&token);
 
-	ret = __btrfs_drop_extents(trans, log, inode, path, em->start,
+	ret = __btrfs_drop_extents(trans, log, &inode->vfs_inode, path, em->start,
 				   em->start + em->len, NULL, 0, 1,
 				   sizeof(*fi), &extent_inserted);
 	if (ret)
@@ -4150,7 +4174,7 @@ static int log_one_extent(struct btrfs_trans_handle *trans,
 
 static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 				     struct btrfs_root *root,
-				     struct inode *inode,
+				     struct btrfs_inode *inode,
 				     struct btrfs_path *path,
 				     struct list_head *logged_list,
 				     struct btrfs_log_ctx *ctx,
@@ -4159,14 +4183,14 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 {
 	struct extent_map *em, *n;
 	struct list_head extents;
-	struct extent_map_tree *tree = &BTRFS_I(inode)->extent_tree;
+	struct extent_map_tree *tree = &inode->extent_tree;
 	u64 test_gen;
 	int ret = 0;
 	int num = 0;
 
 	INIT_LIST_HEAD(&extents);
 
-	down_write(&BTRFS_I(inode)->dio_sem);
+	down_write(&inode->dio_sem);
 	write_lock(&tree->lock);
 	test_gen = root->fs_info->last_trans_committed;
 
@@ -4188,7 +4212,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 		if (em->generation <= test_gen)
 			continue;
 		/* Need a ref to keep it from getting evicted from cache */
-		atomic_inc(&em->refs);
+		refcount_inc(&em->refs);
 		set_bit(EXTENT_FLAG_LOGGING, &em->flags);
 		list_add_tail(&em->list, &extents);
 		num++;
@@ -4206,7 +4230,7 @@ static int btrfs_log_changed_extents(struct btrfs_trans_handle *trans,
 	 * without writing to the log tree and the fsync must report the
 	 * file data write error and not commit the current transaction.
 	 */
-	ret = filemap_check_errors(inode->i_mapping);
+	ret = filemap_check_errors(inode->vfs_inode.i_mapping);
 	if (ret)
 		ctx->io_err = ret;
 process:
@@ -4235,13 +4259,13 @@ process:
 	}
 	WARN_ON(!list_empty(&extents));
 	write_unlock(&tree->lock);
-	up_write(&BTRFS_I(inode)->dio_sem);
+	up_write(&inode->dio_sem);
 
 	btrfs_release_path(path);
 	return ret;
 }
 
-static int logged_inode_size(struct btrfs_root *log, struct inode *inode,
+static int logged_inode_size(struct btrfs_root *log, struct btrfs_inode *inode,
 			     struct btrfs_path *path, u64 *size_ret)
 {
 	struct btrfs_key key;
@@ -4279,7 +4303,7 @@ static int logged_inode_size(struct btrfs_root *log, struct inode *inode,
  */
 static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
-				struct inode *inode,
+				struct btrfs_inode *inode,
 				struct btrfs_path *path,
 				struct btrfs_path *dst_path)
 {
@@ -4374,7 +4398,7 @@ static int btrfs_log_all_xattrs(struct btrfs_trans_handle *trans,
  */
 static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 				   struct btrfs_root *root,
-				   struct inode *inode,
+				   struct btrfs_inode *inode,
 				   struct btrfs_path *path)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -4385,7 +4409,7 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 	struct extent_buffer *leaf;
 	struct btrfs_root *log = root->log_root;
 	const u64 ino = btrfs_ino(inode);
-	const u64 i_size = i_size_read(inode);
+	const u64 i_size = i_size_read(&inode->vfs_inode);
 
 	if (!btrfs_fs_incompat(fs_info, NO_HOLES))
 		return 0;
@@ -4495,7 +4519,7 @@ static int btrfs_log_trailing_hole(struct btrfs_trans_handle *trans,
 static int btrfs_check_ref_name_override(struct extent_buffer *eb,
 					 const int slot,
 					 const struct btrfs_key *key,
-					 struct inode *inode,
+					 struct btrfs_inode *inode,
 					 u64 *other_ino)
 {
 	int ret;
@@ -4538,6 +4562,12 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb,
 			this_len = sizeof(*extref) + this_name_len;
 		}
 
+		ret = btrfs_is_name_len_valid(eb, slot, name_ptr,
+					      this_name_len);
+		if (!ret) {
+			ret = -EIO;
+			goto out;
+		}
 		if (this_name_len > name_len) {
 			char *new_name;
 
@@ -4551,9 +4581,8 @@ static int btrfs_check_ref_name_override(struct extent_buffer *eb,
 		}
 
 		read_extent_buffer(eb, name, name_ptr, this_name_len);
-		di = btrfs_lookup_dir_item(NULL, BTRFS_I(inode)->root,
-					   search_path, parent,
-					   name, this_name_len, 0);
+		di = btrfs_lookup_dir_item(NULL, inode->root, search_path,
+				parent, name, this_name_len, 0);
 		if (di && !IS_ERR(di)) {
 			struct btrfs_key di_key;
 
@@ -4596,7 +4625,7 @@ out:
  * This handles both files and directories.
  */
 static int btrfs_log_inode(struct btrfs_trans_handle *trans,
-			   struct btrfs_root *root, struct inode *inode,
+			   struct btrfs_root *root, struct btrfs_inode *inode,
 			   int inode_only,
 			   const loff_t start,
 			   const loff_t end,
@@ -4618,7 +4647,7 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	int ins_nr;
 	bool fast_search = false;
 	u64 ino = btrfs_ino(inode);
-	struct extent_map_tree *em_tree = &BTRFS_I(inode)->extent_tree;
+	struct extent_map_tree *em_tree = &inode->extent_tree;
 	u64 logged_isize = 0;
 	bool need_log_inode_item = true;
 
@@ -4639,9 +4668,9 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 
 
 	/* today the code can only do partial logging of directories */
-	if (S_ISDIR(inode->i_mode) ||
+	if (S_ISDIR(inode->vfs_inode.i_mode) ||
 	    (!test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-		       &BTRFS_I(inode)->runtime_flags) &&
+		       &inode->runtime_flags) &&
 	     inode_only >= LOG_INODE_EXISTS))
 		max_key.type = BTRFS_XATTR_ITEM_KEY;
 	else
@@ -4654,8 +4683,8 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 	 * order for the log replay code to mark inodes for link count
 	 * fixup (create temporary BTRFS_TREE_LOG_FIXUP_OBJECTID items).
 	 */
-	if (S_ISDIR(inode->i_mode) ||
-	    BTRFS_I(inode)->generation > fs_info->last_trans_committed)
+	if (S_ISDIR(inode->vfs_inode.i_mode) ||
+	    inode->generation > fs_info->last_trans_committed)
 		ret = btrfs_commit_inode_delayed_items(trans, inode);
 	else
 		ret = btrfs_commit_inode_delayed_inode(inode);
@@ -4668,17 +4697,16 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 
 	if (inode_only == LOG_OTHER_INODE) {
 		inode_only = LOG_INODE_EXISTS;
-		mutex_lock_nested(&BTRFS_I(inode)->log_mutex,
-				  SINGLE_DEPTH_NESTING);
+		mutex_lock_nested(&inode->log_mutex, SINGLE_DEPTH_NESTING);
 	} else {
-		mutex_lock(&BTRFS_I(inode)->log_mutex);
+		mutex_lock(&inode->log_mutex);
 	}
 
 	/*
 	 * a brute force approach to making sure we get the most uptodate
 	 * copies of everything.
 	 */
-	if (S_ISDIR(inode->i_mode)) {
+	if (S_ISDIR(inode->vfs_inode.i_mode)) {
 		int max_key_type = BTRFS_DIR_LOG_INDEX_KEY;
 
 		if (inode_only == LOG_INODE_EXISTS)
@@ -4699,31 +4727,30 @@ static int btrfs_log_inode(struct btrfs_trans_handle *trans,
 			 * (zeroes), as if an expanding truncate happened,
 			 * instead of getting a file of 4Kb only.
 			 */
-			err = logged_inode_size(log, inode, path,
-						&logged_isize);
+			err = logged_inode_size(log, inode, path, &logged_isize);
 			if (err)
 				goto out_unlock;
 		}
 		if (test_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-			     &BTRFS_I(inode)->runtime_flags)) {
+			     &inode->runtime_flags)) {
 			if (inode_only == LOG_INODE_EXISTS) {
 				max_key.type = BTRFS_XATTR_ITEM_KEY;
 				ret = drop_objectid_items(trans, log, path, ino,
 							  max_key.type);
 			} else {
 				clear_bit(BTRFS_INODE_NEEDS_FULL_SYNC,
-					  &BTRFS_I(inode)->runtime_flags);
+					  &inode->runtime_flags);
 				clear_bit(BTRFS_INODE_COPY_EVERYTHING,
-					  &BTRFS_I(inode)->runtime_flags);
+					  &inode->runtime_flags);
 				while(1) {
 					ret = btrfs_truncate_inode_items(trans,
-							 log, inode, 0, 0);
+						log, &inode->vfs_inode, 0, 0);
 					if (ret != -EAGAIN)
 						break;
 				}
 			}
 		} else if (test_and_clear_bit(BTRFS_INODE_COPY_EVERYTHING,
-					      &BTRFS_I(inode)->runtime_flags) ||
+					      &inode->runtime_flags) ||
 			   inode_only == LOG_INODE_EXISTS) {
 			if (inode_only == LOG_INODE_ALL)
 				fast_search = true;
@@ -4764,18 +4791,17 @@ again:
 
 		if ((min_key.type == BTRFS_INODE_REF_KEY ||
 		     min_key.type == BTRFS_INODE_EXTREF_KEY) &&
-		    BTRFS_I(inode)->generation == trans->transid) {
+		    inode->generation == trans->transid) {
 			u64 other_ino = 0;
 
 			ret = btrfs_check_ref_name_override(path->nodes[0],
-							    path->slots[0],
-							    &min_key, inode,
-							    &other_ino);
+					path->slots[0], &min_key, inode,
+					&other_ino);
 			if (ret < 0) {
 				err = ret;
 				goto out_unlock;
 			} else if (ret > 0 && ctx &&
-				   other_ino != btrfs_ino(ctx->inode)) {
+				   other_ino != btrfs_ino(BTRFS_I(ctx->inode))) {
 				struct btrfs_key inode_key;
 				struct inode *other_inode;
 
@@ -4823,9 +4849,10 @@ again:
 				 * update the log with the new name before we
 				 * unpin it.
 				 */
-				err = btrfs_log_inode(trans, root, other_inode,
-						      LOG_OTHER_INODE,
-						      0, LLONG_MAX, ctx);
+				err = btrfs_log_inode(trans, root,
+						BTRFS_I(other_inode),
+						LOG_OTHER_INODE, 0, LLONG_MAX,
+						ctx);
 				iput(other_inode);
 				if (err)
 					goto out_unlock;
@@ -4979,25 +5006,25 @@ log_extents:
 		write_unlock(&em_tree->lock);
 	}
 
-	if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->i_mode)) {
+	if (inode_only == LOG_INODE_ALL && S_ISDIR(inode->vfs_inode.i_mode)) {
 		ret = log_directory_changes(trans, root, inode, path, dst_path,
-					    ctx);
+					ctx);
 		if (ret) {
 			err = ret;
 			goto out_unlock;
 		}
 	}
 
-	spin_lock(&BTRFS_I(inode)->lock);
-	BTRFS_I(inode)->logged_trans = trans->transid;
-	BTRFS_I(inode)->last_log_commit = BTRFS_I(inode)->last_sub_trans;
-	spin_unlock(&BTRFS_I(inode)->lock);
+	spin_lock(&inode->lock);
+	inode->logged_trans = trans->transid;
+	inode->last_log_commit = inode->last_sub_trans;
+	spin_unlock(&inode->lock);
 out_unlock:
 	if (unlikely(err))
 		btrfs_put_logged_extents(&logged_list);
 	else
 		btrfs_submit_logged_extents(&logged_list, log);
-	mutex_unlock(&BTRFS_I(inode)->log_mutex);
+	mutex_unlock(&inode->log_mutex);
 
 	btrfs_free_path(path);
 	btrfs_free_path(dst_path);
@@ -5021,13 +5048,13 @@ out_unlock:
  * we logged the inode or it might have also done the unlink).
  */
 static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
-					  struct inode *inode)
+					  struct btrfs_inode *inode)
 {
-	struct btrfs_fs_info *fs_info = BTRFS_I(inode)->root->fs_info;
+	struct btrfs_fs_info *fs_info = inode->root->fs_info;
 	bool ret = false;
 
-	mutex_lock(&BTRFS_I(inode)->log_mutex);
-	if (BTRFS_I(inode)->last_unlink_trans > fs_info->last_trans_committed) {
+	mutex_lock(&inode->log_mutex);
+	if (inode->last_unlink_trans > fs_info->last_trans_committed) {
 		/*
 		 * Make sure any commits to the log are forced to be full
 		 * commits.
@@ -5035,7 +5062,7 @@ static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
 		btrfs_set_log_full_commit(fs_info, trans);
 		ret = true;
 	}
-	mutex_unlock(&BTRFS_I(inode)->log_mutex);
+	mutex_unlock(&inode->log_mutex);
 
 	return ret;
 }
@@ -5047,14 +5074,14 @@ static bool btrfs_must_commit_transaction(struct btrfs_trans_handle *trans,
  * a full commit is required.
  */
 static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
-					       struct inode *inode,
+					       struct btrfs_inode *inode,
 					       struct dentry *parent,
 					       struct super_block *sb,
 					       u64 last_committed)
 {
 	int ret = 0;
 	struct dentry *old_parent = NULL;
-	struct inode *orig_inode = inode;
+	struct btrfs_inode *orig_inode = inode;
 
 	/*
 	 * for regular files, if its inode is already on disk, we don't
@@ -5062,15 +5089,15 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 	 * we can use the last_unlink_trans field to record renames
 	 * and other fun in this file.
 	 */
-	if (S_ISREG(inode->i_mode) &&
-	    BTRFS_I(inode)->generation <= last_committed &&
-	    BTRFS_I(inode)->last_unlink_trans <= last_committed)
-			goto out;
+	if (S_ISREG(inode->vfs_inode.i_mode) &&
+	    inode->generation <= last_committed &&
+	    inode->last_unlink_trans <= last_committed)
+		goto out;
 
-	if (!S_ISDIR(inode->i_mode)) {
+	if (!S_ISDIR(inode->vfs_inode.i_mode)) {
 		if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
 			goto out;
-		inode = d_inode(parent);
+		inode = BTRFS_I(d_inode(parent));
 	}
 
 	while (1) {
@@ -5081,7 +5108,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 		 * think this inode has already been logged.
 		 */
 		if (inode != orig_inode)
-			BTRFS_I(inode)->logged_trans = trans->transid;
+			inode->logged_trans = trans->transid;
 		smp_mb();
 
 		if (btrfs_must_commit_transaction(trans, inode)) {
@@ -5093,7 +5120,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 			break;
 
 		if (IS_ROOT(parent)) {
-			inode = d_inode(parent);
+			inode = BTRFS_I(d_inode(parent));
 			if (btrfs_must_commit_transaction(trans, inode))
 				ret = 1;
 			break;
@@ -5102,7 +5129,7 @@ static noinline int check_parent_dirs_for_sync(struct btrfs_trans_handle *trans,
 		parent = dget_parent(parent);
 		dput(old_parent);
 		old_parent = parent;
-		inode = d_inode(parent);
+		inode = BTRFS_I(d_inode(parent));
 
 	}
 	dput(old_parent);
@@ -5159,7 +5186,7 @@ struct btrfs_dir_list {
  */
 static int log_new_dir_dentries(struct btrfs_trans_handle *trans,
 				struct btrfs_root *root,
-				struct inode *start_inode,
+				struct btrfs_inode *start_inode,
 				struct btrfs_log_ctx *ctx)
 {
 	struct btrfs_fs_info *fs_info = root->fs_info;
@@ -5237,7 +5264,7 @@ process_leaf:
 				goto next_dir_inode;
 			}
 
-			if (btrfs_inode_in_log(di_inode, trans->transid)) {
+			if (btrfs_inode_in_log(BTRFS_I(di_inode), trans->transid)) {
 				iput(di_inode);
 				break;
 			}
@@ -5245,10 +5272,10 @@ process_leaf:
 			ctx->log_new_dentries = false;
 			if (type == BTRFS_FT_DIR || type == BTRFS_FT_SYMLINK)
 				log_mode = LOG_INODE_ALL;
-			ret = btrfs_log_inode(trans, root, di_inode,
+			ret = btrfs_log_inode(trans, root, BTRFS_I(di_inode),
 					      log_mode, 0, LLONG_MAX, ctx);
 			if (!ret &&
-			    btrfs_must_commit_transaction(trans, di_inode))
+			    btrfs_must_commit_transaction(trans, BTRFS_I(di_inode)))
 				ret = 1;
 			iput(di_inode);
 			if (ret)
@@ -5289,14 +5316,14 @@ next_dir_inode:
 }
 
 static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
-				 struct inode *inode,
+				 struct btrfs_inode *inode,
 				 struct btrfs_log_ctx *ctx)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
 	int ret;
 	struct btrfs_path *path;
 	struct btrfs_key key;
-	struct btrfs_root *root = BTRFS_I(inode)->root;
+	struct btrfs_root *root = inode->root;
 	const u64 ino = btrfs_ino(inode);
 
 	path = btrfs_alloc_path();
@@ -5365,14 +5392,14 @@ static int btrfs_log_all_parents(struct btrfs_trans_handle *trans,
 
 			if (ctx)
 				ctx->log_new_dentries = false;
-			ret = btrfs_log_inode(trans, root, dir_inode,
+			ret = btrfs_log_inode(trans, root, BTRFS_I(dir_inode),
 					      LOG_INODE_ALL, 0, LLONG_MAX, ctx);
 			if (!ret &&
-			    btrfs_must_commit_transaction(trans, dir_inode))
+			    btrfs_must_commit_transaction(trans, BTRFS_I(dir_inode)))
 				ret = 1;
 			if (!ret && ctx && ctx->log_new_dentries)
 				ret = log_new_dir_dentries(trans, root,
-							   dir_inode, ctx);
+						   BTRFS_I(dir_inode), ctx);
 			iput(dir_inode);
 			if (ret)
 				goto out;
@@ -5392,7 +5419,8 @@ out:
  * the last committed transaction
  */
 static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
-			    	  struct btrfs_root *root, struct inode *inode,
+				  struct btrfs_root *root,
+				  struct btrfs_inode *inode,
 				  struct dentry *parent,
 				  const loff_t start,
 				  const loff_t end,
@@ -5406,9 +5434,9 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	int ret = 0;
 	u64 last_committed = fs_info->last_trans_committed;
 	bool log_dentries = false;
-	struct inode *orig_inode = inode;
+	struct btrfs_inode *orig_inode = inode;
 
-	sb = inode->i_sb;
+	sb = inode->vfs_inode.i_sb;
 
 	if (btrfs_test_opt(fs_info, NOTREELOG)) {
 		ret = 1;
@@ -5425,14 +5453,13 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		goto end_no_trans;
 	}
 
-	if (root != BTRFS_I(inode)->root ||
-	    btrfs_root_refs(&root->root_item) == 0) {
+	if (root != inode->root || btrfs_root_refs(&root->root_item) == 0) {
 		ret = 1;
 		goto end_no_trans;
 	}
 
-	ret = check_parent_dirs_for_sync(trans, inode, parent,
-					 sb, last_committed);
+	ret = check_parent_dirs_for_sync(trans, inode, parent, sb,
+			last_committed);
 	if (ret)
 		goto end_no_trans;
 
@@ -5455,14 +5482,14 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	 * we can use the last_unlink_trans field to record renames
 	 * and other fun in this file.
 	 */
-	if (S_ISREG(inode->i_mode) &&
-	    BTRFS_I(inode)->generation <= last_committed &&
-	    BTRFS_I(inode)->last_unlink_trans <= last_committed) {
+	if (S_ISREG(inode->vfs_inode.i_mode) &&
+	    inode->generation <= last_committed &&
+	    inode->last_unlink_trans <= last_committed) {
 		ret = 0;
 		goto end_trans;
 	}
 
-	if (S_ISDIR(inode->i_mode) && ctx && ctx->log_new_dentries)
+	if (S_ISDIR(inode->vfs_inode.i_mode) && ctx && ctx->log_new_dentries)
 		log_dentries = true;
 
 	/*
@@ -5506,7 +5533,7 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 	 * but the file inode does not have a matching BTRFS_INODE_REF_KEY item
 	 * and has a link count of 2.
 	 */
-	if (BTRFS_I(inode)->last_unlink_trans > last_committed) {
+	if (inode->last_unlink_trans > last_committed) {
 		ret = btrfs_log_all_parents(trans, orig_inode, ctx);
 		if (ret)
 			goto end_trans;
@@ -5516,14 +5543,13 @@ static int btrfs_log_inode_parent(struct btrfs_trans_handle *trans,
 		if (!parent || d_really_is_negative(parent) || sb != parent->d_sb)
 			break;
 
-		inode = d_inode(parent);
-		if (root != BTRFS_I(inode)->root)
+		inode = BTRFS_I(d_inode(parent));
+		if (root != inode->root)
 			break;
 
-		if (BTRFS_I(inode)->generation > last_committed) {
+		if (inode->generation > last_committed) {
 			ret = btrfs_log_inode(trans, root, inode,
-					      LOG_INODE_EXISTS,
-					      0, LLONG_MAX, ctx);
+					LOG_INODE_EXISTS, 0, LLONG_MAX, ctx);
 			if (ret)
 				goto end_trans;
 		}
@@ -5567,8 +5593,8 @@ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
 	struct dentry *parent = dget_parent(dentry);
 	int ret;
 
-	ret = btrfs_log_inode_parent(trans, root, d_inode(dentry), parent,
-				     start, end, 0, ctx);
+	ret = btrfs_log_inode_parent(trans, root, BTRFS_I(d_inode(dentry)),
+			parent, start, end, 0, ctx);
 	dput(parent);
 
 	return ret;
@@ -5730,7 +5756,7 @@ error:
  * inodes, etc) are done.
  */
 void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
-			     struct inode *dir, struct inode *inode,
+			     struct btrfs_inode *dir, struct btrfs_inode *inode,
 			     int for_rename)
 {
 	/*
@@ -5743,23 +5769,23 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 	 * into the file.  When the file is logged we check it and
 	 * don't log the parents if the file is fully on disk.
 	 */
-	mutex_lock(&BTRFS_I(inode)->log_mutex);
-	BTRFS_I(inode)->last_unlink_trans = trans->transid;
-	mutex_unlock(&BTRFS_I(inode)->log_mutex);
+	mutex_lock(&inode->log_mutex);
+	inode->last_unlink_trans = trans->transid;
+	mutex_unlock(&inode->log_mutex);
 
 	/*
 	 * if this directory was already logged any new
 	 * names for this file/dir will get recorded
 	 */
 	smp_mb();
-	if (BTRFS_I(dir)->logged_trans == trans->transid)
+	if (dir->logged_trans == trans->transid)
 		return;
 
 	/*
 	 * if the inode we're about to unlink was logged,
 	 * the log will be properly updated for any new names
 	 */
-	if (BTRFS_I(inode)->logged_trans == trans->transid)
+	if (inode->logged_trans == trans->transid)
 		return;
 
 	/*
@@ -5776,9 +5802,9 @@ void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
 	return;
 
 record:
-	mutex_lock(&BTRFS_I(dir)->log_mutex);
-	BTRFS_I(dir)->last_unlink_trans = trans->transid;
-	mutex_unlock(&BTRFS_I(dir)->log_mutex);
+	mutex_lock(&dir->log_mutex);
+	dir->last_unlink_trans = trans->transid;
+	mutex_unlock(&dir->log_mutex);
 }
 
 /*
@@ -5794,11 +5820,11 @@ record:
  * parent root and tree of tree roots trees, etc) are done.
  */
 void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
-				   struct inode *dir)
+				   struct btrfs_inode *dir)
 {
-	mutex_lock(&BTRFS_I(dir)->log_mutex);
-	BTRFS_I(dir)->last_unlink_trans = trans->transid;
-	mutex_unlock(&BTRFS_I(dir)->log_mutex);
+	mutex_lock(&dir->log_mutex);
+	dir->last_unlink_trans = trans->transid;
+	mutex_unlock(&dir->log_mutex);
 }
 
 /*
@@ -5809,27 +5835,25 @@ void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
  * full transaction commit is required.
  */
 int btrfs_log_new_name(struct btrfs_trans_handle *trans,
-			struct inode *inode, struct inode *old_dir,
+			struct btrfs_inode *inode, struct btrfs_inode *old_dir,
 			struct dentry *parent)
 {
-	struct btrfs_fs_info *fs_info = btrfs_sb(inode->i_sb);
-	struct btrfs_root * root = BTRFS_I(inode)->root;
+	struct btrfs_fs_info *fs_info = btrfs_sb(inode->vfs_inode.i_sb);
+	struct btrfs_root *root = inode->root;
 
 	/*
 	 * this will force the logging code to walk the dentry chain
 	 * up for the file
 	 */
-	if (S_ISREG(inode->i_mode))
-		BTRFS_I(inode)->last_unlink_trans = trans->transid;
+	if (S_ISREG(inode->vfs_inode.i_mode))
+		inode->last_unlink_trans = trans->transid;
 
 	/*
 	 * if this inode hasn't been logged and directory we're renaming it
 	 * from hasn't been logged, we don't need to log it
 	 */
-	if (BTRFS_I(inode)->logged_trans <=
-	    fs_info->last_trans_committed &&
-	    (!old_dir || BTRFS_I(old_dir)->logged_trans <=
-		    fs_info->last_trans_committed))
+	if (inode->logged_trans <= fs_info->last_trans_committed &&
+	    (!old_dir || old_dir->logged_trans <= fs_info->last_trans_committed))
 		return 0;
 
 	return btrfs_log_inode_parent(trans, root, inode, parent, 0,
diff --git a/fs/btrfs/tree-log.h b/fs/btrfs/tree-log.h
index ab858e31ccbc..483027f9a7f4 100644
--- a/fs/btrfs/tree-log.h
+++ b/fs/btrfs/tree-log.h
@@ -48,13 +48,13 @@ static inline void btrfs_init_log_ctx(struct btrfs_log_ctx *ctx,
 static inline void btrfs_set_log_full_commit(struct btrfs_fs_info *fs_info,
 					     struct btrfs_trans_handle *trans)
 {
-	ACCESS_ONCE(fs_info->last_trans_log_full_commit) = trans->transid;
+	WRITE_ONCE(fs_info->last_trans_log_full_commit, trans->transid);
 }
 
 static inline int btrfs_need_log_full_commit(struct btrfs_fs_info *fs_info,
 					     struct btrfs_trans_handle *trans)
 {
-	return ACCESS_ONCE(fs_info->last_trans_log_full_commit) ==
+	return READ_ONCE(fs_info->last_trans_log_full_commit) ==
 		trans->transid;
 }
 
@@ -72,19 +72,19 @@ int btrfs_log_dentry_safe(struct btrfs_trans_handle *trans,
 int btrfs_del_dir_entries_in_log(struct btrfs_trans_handle *trans,
 				 struct btrfs_root *root,
 				 const char *name, int name_len,
-				 struct inode *dir, u64 index);
+				 struct btrfs_inode *dir, u64 index);
 int btrfs_del_inode_ref_in_log(struct btrfs_trans_handle *trans,
 			       struct btrfs_root *root,
 			       const char *name, int name_len,
-			       struct inode *inode, u64 dirid);
+			       struct btrfs_inode *inode, u64 dirid);
 void btrfs_end_log_trans(struct btrfs_root *root);
 int btrfs_pin_log_trans(struct btrfs_root *root);
 void btrfs_record_unlink_dir(struct btrfs_trans_handle *trans,
-			     struct inode *dir, struct inode *inode,
+			     struct btrfs_inode *dir, struct btrfs_inode *inode,
 			     int for_rename);
 void btrfs_record_snapshot_destroy(struct btrfs_trans_handle *trans,
-				   struct inode *dir);
+				   struct btrfs_inode *dir);
 int btrfs_log_new_name(struct btrfs_trans_handle *trans,
-			struct inode *inode, struct inode *old_dir,
+			struct btrfs_inode *inode, struct btrfs_inode *old_dir,
 			struct dentry *parent);
 #endif
diff --git a/fs/btrfs/ulist.c b/fs/btrfs/ulist.c
index b1434bb57e36..d8edf164f81c 100644
--- a/fs/btrfs/ulist.c
+++ b/fs/btrfs/ulist.c
@@ -52,13 +52,13 @@ void ulist_init(struct ulist *ulist)
 }
 
 /**
- * ulist_fini - free up additionally allocated memory for the ulist
+ * ulist_release - free up additionally allocated memory for the ulist
  * @ulist:	the ulist from which to free the additional memory
  *
  * This is useful in cases where the base 'struct ulist' has been statically
  * allocated.
  */
-static void ulist_fini(struct ulist *ulist)
+void ulist_release(struct ulist *ulist)
 {
 	struct ulist_node *node;
 	struct ulist_node *next;
@@ -79,7 +79,7 @@ static void ulist_fini(struct ulist *ulist)
  */
 void ulist_reinit(struct ulist *ulist)
 {
-	ulist_fini(ulist);
+	ulist_release(ulist);
 	ulist_init(ulist);
 }
 
@@ -105,13 +105,13 @@ struct ulist *ulist_alloc(gfp_t gfp_mask)
  * ulist_free - free dynamically allocated ulist
  * @ulist:	ulist to free
  *
- * It is not necessary to call ulist_fini before.
+ * It is not necessary to call ulist_release before.
  */
 void ulist_free(struct ulist *ulist)
 {
 	if (!ulist)
 		return;
-	ulist_fini(ulist);
+	ulist_release(ulist);
 	kfree(ulist);
 }
 
diff --git a/fs/btrfs/ulist.h b/fs/btrfs/ulist.h
index a01a2c45825f..53c913632733 100644
--- a/fs/btrfs/ulist.h
+++ b/fs/btrfs/ulist.h
@@ -19,9 +19,6 @@
  *
  */
 struct ulist_iterator {
-#ifdef CONFIG_BTRFS_DEBUG
-	int i;
-#endif
 	struct list_head *cur_list;  /* hint to start search */
 };
 
@@ -32,10 +29,6 @@ struct ulist_node {
 	u64 val;		/* value to store */
 	u64 aux;		/* auxiliary value saved along with the val */
 
-#ifdef CONFIG_BTRFS_DEBUG
-	int seqnum;		/* sequence number this node is added */
-#endif
-
 	struct list_head list;  /* used to link node */
 	struct rb_node rb_node;	/* used to speed up search */
 };
@@ -51,6 +44,7 @@ struct ulist {
 };
 
 void ulist_init(struct ulist *ulist);
+void ulist_release(struct ulist *ulist);
 void ulist_reinit(struct ulist *ulist);
 struct ulist *ulist_alloc(gfp_t gfp_mask);
 void ulist_free(struct ulist *ulist);
diff --git a/fs/btrfs/volumes.c b/fs/btrfs/volumes.c
index 3c3c69c0eee4..5eb7217738ed 100644
--- a/fs/btrfs/volumes.c
+++ b/fs/btrfs/volumes.c
@@ -134,12 +134,16 @@ const int btrfs_raid_mindev_error[BTRFS_NR_RAID_TYPES] = {
 };
 
 static int init_first_rw_device(struct btrfs_trans_handle *trans,
-				struct btrfs_fs_info *fs_info,
-				struct btrfs_device *device);
+				struct btrfs_fs_info *fs_info);
 static int btrfs_relocate_sys_chunks(struct btrfs_fs_info *fs_info);
 static void __btrfs_reset_dev_stats(struct btrfs_device *dev);
 static void btrfs_dev_stat_print_on_error(struct btrfs_device *dev);
 static void btrfs_dev_stat_print_on_load(struct btrfs_device *device);
+static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
+			     enum btrfs_map_op op,
+			     u64 logical, u64 *length,
+			     struct btrfs_bio **bbio_ret,
+			     int mirror_num, int need_raid_map);
 
 DEFINE_MUTEX(uuid_mutex);
 static LIST_HEAD(fs_uuids);
@@ -238,6 +242,17 @@ static struct btrfs_device *__alloc_device(void)
 	if (!dev)
 		return ERR_PTR(-ENOMEM);
 
+	/*
+	 * Preallocate a bio that's always going to be used for flushing device
+	 * barriers and matches the device lifespan
+	 */
+	dev->flush_bio = bio_alloc_bioset(GFP_KERNEL, 0, NULL);
+	if (!dev->flush_bio) {
+		kfree(dev);
+		return ERR_PTR(-ENOMEM);
+	}
+	bio_get(dev->flush_bio);
+
 	INIT_LIST_HEAD(&dev->dev_list);
 	INIT_LIST_HEAD(&dev->dev_alloc_list);
 	INIT_LIST_HEAD(&dev->resized_list);
@@ -366,7 +381,7 @@ static noinline void run_scheduled_bios(struct btrfs_device *device)
 	 */
 	blk_start_plug(&plug);
 
-	bdi = blk_get_backing_dev_info(device->bdev);
+	bdi = device->bdev->bd_bdi;
 	limit = btrfs_async_submit_limit(fs_info);
 	limit = limit * 2 / 3;
 
@@ -834,6 +849,7 @@ static void __free_device(struct work_struct *work)
 
 	device = container_of(work, struct btrfs_device, rcu_work);
 	rcu_string_free(device->name);
+	bio_put(device->flush_bio);
 	kfree(device);
 }
 
@@ -1009,14 +1025,13 @@ static int __btrfs_open_devices(struct btrfs_fs_devices *fs_devices,
 		q = bdev_get_queue(bdev);
 		if (blk_queue_discard(q))
 			device->can_discard = 1;
+		if (!blk_queue_nonrot(q))
+			fs_devices->rotating = 1;
 
 		device->bdev = bdev;
 		device->in_fs_metadata = 0;
 		device->mode = flags;
 
-		if (!blk_queue_nonrot(bdev_get_queue(bdev)))
-			fs_devices->rotating = 1;
-
 		fs_devices->open_devices++;
 		if (device->writeable &&
 		    device->devid != BTRFS_DEV_REPLACE_DEVID) {
@@ -1350,15 +1365,13 @@ int find_free_dev_extent_start(struct btrfs_transaction *transaction,
 	int ret;
 	int slot;
 	struct extent_buffer *l;
-	u64 min_search_start;
 
 	/*
 	 * We don't want to overwrite the superblock on the drive nor any area
 	 * used by the boot loader (grub for example), so we make sure to start
 	 * at an offset of at least 1MB.
 	 */
-	min_search_start = max(fs_info->alloc_start, 1024ull * 1024);
-	search_start = max(search_start, min_search_start);
+	search_start = max_t(u64, search_start, SZ_1M);
 
 	path = btrfs_alloc_path();
 	if (!path)
@@ -1726,7 +1739,7 @@ out:
  * Function to update ctime/mtime for a given device path.
  * Mainly used for ctime/mtime based probe like libblkid.
  */
-static void update_dev_time(char *path_name)
+static void update_dev_time(const char *path_name)
 {
 	struct file *filp;
 
@@ -1852,7 +1865,8 @@ void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
 		fs_info->fs_devices->latest_bdev = next_device->bdev;
 }
 
-int btrfs_rm_device(struct btrfs_fs_info *fs_info, char *device_path, u64 devid)
+int btrfs_rm_device(struct btrfs_fs_info *fs_info, const char *device_path,
+		u64 devid)
 {
 	struct btrfs_device *device;
 	struct btrfs_fs_devices *cur_devices;
@@ -2092,7 +2106,7 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 }
 
 static int btrfs_find_device_by_path(struct btrfs_fs_info *fs_info,
-				     char *device_path,
+				     const char *device_path,
 				     struct btrfs_device **device)
 {
 	int ret = 0;
@@ -2119,7 +2133,7 @@ static int btrfs_find_device_by_path(struct btrfs_fs_info *fs_info,
 }
 
 int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
-					 char *device_path,
+					 const char *device_path,
 					 struct btrfs_device **device)
 {
 	*device = NULL;
@@ -2152,7 +2166,8 @@ int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
  * Lookup a device given by device id, or the path if the id is 0.
  */
 int btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, u64 devid,
-				 char *devpath, struct btrfs_device **device)
+				 const char *devpath,
+				 struct btrfs_device **device)
 {
 	int ret;
 
@@ -2308,7 +2323,7 @@ error:
 	return ret;
 }
 
-int btrfs_init_new_device(struct btrfs_fs_info *fs_info, char *device_path)
+int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *device_path)
 {
 	struct btrfs_root *root = fs_info->dev_root;
 	struct request_queue *q;
@@ -2382,7 +2397,8 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, char *device_path)
 	device->io_width = fs_info->sectorsize;
 	device->io_align = fs_info->sectorsize;
 	device->sector_size = fs_info->sectorsize;
-	device->total_bytes = i_size_read(bdev->bd_inode);
+	device->total_bytes = round_down(i_size_read(bdev->bd_inode),
+					 fs_info->sectorsize);
 	device->disk_total_bytes = device->total_bytes;
 	device->commit_total_bytes = device->total_bytes;
 	device->fs_info = fs_info;
@@ -2412,16 +2428,14 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, char *device_path)
 	fs_info->fs_devices->total_devices++;
 	fs_info->fs_devices->total_rw_bytes += device->total_bytes;
 
-	spin_lock(&fs_info->free_chunk_lock);
-	fs_info->free_chunk_space += device->total_bytes;
-	spin_unlock(&fs_info->free_chunk_lock);
+	atomic64_add(device->total_bytes, &fs_info->free_chunk_space);
 
-	if (!blk_queue_nonrot(bdev_get_queue(bdev)))
+	if (!blk_queue_nonrot(q))
 		fs_info->fs_devices->rotating = 1;
 
 	tmp = btrfs_super_total_bytes(fs_info->super_copy);
 	btrfs_set_super_total_bytes(fs_info->super_copy,
-				    tmp + device->total_bytes);
+		round_down(tmp + device->total_bytes, fs_info->sectorsize));
 
 	tmp = btrfs_super_num_devices(fs_info->super_copy);
 	btrfs_set_super_num_devices(fs_info->super_copy, tmp + 1);
@@ -2440,7 +2454,7 @@ int btrfs_init_new_device(struct btrfs_fs_info *fs_info, char *device_path)
 
 	if (seeding_dev) {
 		mutex_lock(&fs_info->chunk_mutex);
-		ret = init_first_rw_device(trans, fs_info, device);
+		ret = init_first_rw_device(trans, fs_info);
 		mutex_unlock(&fs_info->chunk_mutex);
 		if (ret) {
 			btrfs_abort_transaction(trans, ret);
@@ -2516,7 +2530,7 @@ error:
 }
 
 int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-				  char *device_path,
+				  const char *device_path,
 				  struct btrfs_device *srcdev,
 				  struct btrfs_device **device_out)
 {
@@ -2569,7 +2583,7 @@ int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 		goto error;
 	}
 
-	name = rcu_string_strdup(device_path, GFP_NOFS);
+	name = rcu_string_strdup(device_path, GFP_KERNEL);
 	if (!name) {
 		kfree(device);
 		ret = -ENOMEM;
@@ -2684,6 +2698,8 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans,
 	if (!device->writeable)
 		return -EACCES;
 
+	new_size = round_down(new_size, fs_info->sectorsize);
+
 	mutex_lock(&fs_info->chunk_mutex);
 	old_total = btrfs_super_total_bytes(super_copy);
 	diff = new_size - device->total_bytes;
@@ -2696,7 +2712,8 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans,
 
 	fs_devices = fs_info->fs_devices;
 
-	btrfs_set_super_total_bytes(super_copy, old_total + diff);
+	btrfs_set_super_total_bytes(super_copy,
+			round_down(old_total + diff, fs_info->sectorsize));
 	device->fs_devices->total_rw_bytes += diff;
 
 	btrfs_device_set_total_bytes(device, new_size);
@@ -2794,10 +2811,38 @@ static int btrfs_del_sys_chunk(struct btrfs_fs_info *fs_info,
 	return ret;
 }
 
+static struct extent_map *get_chunk_map(struct btrfs_fs_info *fs_info,
+					u64 logical, u64 length)
+{
+	struct extent_map_tree *em_tree;
+	struct extent_map *em;
+
+	em_tree = &fs_info->mapping_tree.map_tree;
+	read_lock(&em_tree->lock);
+	em = lookup_extent_mapping(em_tree, logical, length);
+	read_unlock(&em_tree->lock);
+
+	if (!em) {
+		btrfs_crit(fs_info, "unable to find logical %llu length %llu",
+			   logical, length);
+		return ERR_PTR(-EINVAL);
+	}
+
+	if (em->start > logical || em->start + em->len < logical) {
+		btrfs_crit(fs_info,
+			   "found a bad mapping, wanted %llu-%llu, found %llu-%llu",
+			   logical, length, em->start, em->start + em->len);
+		free_extent_map(em);
+		return ERR_PTR(-EINVAL);
+	}
+
+	/* callers are responsible for dropping em's ref. */
+	return em;
+}
+
 int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 		       struct btrfs_fs_info *fs_info, u64 chunk_offset)
 {
-	struct extent_map_tree *em_tree;
 	struct extent_map *em;
 	struct map_lookup *map;
 	u64 dev_extent_len = 0;
@@ -2805,23 +2850,15 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 	int i, ret = 0;
 	struct btrfs_fs_devices *fs_devices = fs_info->fs_devices;
 
-	em_tree = &fs_info->mapping_tree.map_tree;
-
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, chunk_offset, 1);
-	read_unlock(&em_tree->lock);
-
-	if (!em || em->start > chunk_offset ||
-	    em->start + em->len < chunk_offset) {
+	em = get_chunk_map(fs_info, chunk_offset, 1);
+	if (IS_ERR(em)) {
 		/*
 		 * This is a logic error, but we don't want to just rely on the
 		 * user having built with ASSERT enabled, so if ASSERT doesn't
 		 * do anything we still error out.
 		 */
 		ASSERT(0);
-		if (em)
-			free_extent_map(em);
-		return -EINVAL;
+		return PTR_ERR(em);
 	}
 	map = em->map_lookup;
 	mutex_lock(&fs_info->chunk_mutex);
@@ -2849,9 +2886,7 @@ int btrfs_remove_chunk(struct btrfs_trans_handle *trans,
 			mutex_lock(&fs_info->chunk_mutex);
 			btrfs_device_set_bytes_used(device,
 					device->bytes_used - dev_extent_len);
-			spin_lock(&fs_info->free_chunk_lock);
-			fs_info->free_chunk_space += dev_extent_len;
-			spin_unlock(&fs_info->free_chunk_lock);
+			atomic64_add(dev_extent_len, &fs_info->free_chunk_space);
 			btrfs_clear_space_info_full(fs_info);
 			mutex_unlock(&fs_info->chunk_mutex);
 		}
@@ -3735,7 +3770,7 @@ static void __cancel_balance(struct btrfs_fs_info *fs_info)
 	if (ret)
 		btrfs_handle_fs_error(fs_info, ret, NULL);
 
-	atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+	clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 }
 
 /* Non-zero return value signifies invalidity */
@@ -3754,6 +3789,7 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		  struct btrfs_ioctl_balance_args *bargs)
 {
 	struct btrfs_fs_info *fs_info = bctl->fs_info;
+	u64 meta_target, data_target;
 	u64 allowed;
 	int mixed = 0;
 	int ret;
@@ -3850,11 +3886,16 @@ int btrfs_balance(struct btrfs_balance_control *bctl,
 		}
 	} while (read_seqretry(&fs_info->profiles_lock, seq));
 
-	if (btrfs_get_num_tolerated_disk_barrier_failures(bctl->meta.target) <
-		btrfs_get_num_tolerated_disk_barrier_failures(bctl->data.target)) {
+	/* if we're not converting, the target field is uninitialized */
+	meta_target = (bctl->meta.flags & BTRFS_BALANCE_ARGS_CONVERT) ?
+		bctl->meta.target : fs_info->avail_metadata_alloc_bits;
+	data_target = (bctl->data.flags & BTRFS_BALANCE_ARGS_CONVERT) ?
+		bctl->data.target : fs_info->avail_data_alloc_bits;
+	if (btrfs_get_num_tolerated_disk_barrier_failures(meta_target) <
+		btrfs_get_num_tolerated_disk_barrier_failures(data_target)) {
 		btrfs_warn(fs_info,
 			   "metadata profile 0x%llx has lower redundancy than data profile 0x%llx",
-			   bctl->meta.target, bctl->data.target);
+			   meta_target, data_target);
 	}
 
 	if (bctl->sys.flags & BTRFS_BALANCE_ARGS_CONVERT) {
@@ -3909,7 +3950,7 @@ out:
 		__cancel_balance(fs_info);
 	else {
 		kfree(bctl);
-		atomic_set(&fs_info->mutually_exclusive_operation_running, 0);
+		clear_bit(BTRFS_FS_EXCL_OP, &fs_info->flags);
 	}
 	return ret;
 }
@@ -3999,7 +4040,7 @@ int btrfs_recover_balance(struct btrfs_fs_info *fs_info)
 	btrfs_balance_sys(leaf, item, &disk_bargs);
 	btrfs_disk_balance_args_to_cpu(&bctl->sys, &disk_bargs);
 
-	WARN_ON(atomic_xchg(&fs_info->mutually_exclusive_operation_running, 1));
+	WARN_ON(test_and_set_bit(BTRFS_FS_EXCL_OP, &fs_info->flags));
 
 	mutex_lock(&fs_info->volume_mutex);
 	mutex_lock(&fs_info->balance_mutex);
@@ -4362,7 +4403,10 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size)
 	struct btrfs_super_block *super_copy = fs_info->super_copy;
 	u64 old_total = btrfs_super_total_bytes(super_copy);
 	u64 old_size = btrfs_device_get_total_bytes(device);
-	u64 diff = old_size - new_size;
+	u64 diff;
+
+	new_size = round_down(new_size, fs_info->sectorsize);
+	diff = old_size - new_size;
 
 	if (device->is_tgtdev_for_dev_replace)
 		return -EINVAL;
@@ -4378,9 +4422,7 @@ int btrfs_shrink_device(struct btrfs_device *device, u64 new_size)
 	btrfs_device_set_total_bytes(device, new_size);
 	if (device->writeable) {
 		device->fs_devices->total_rw_bytes -= diff;
-		spin_lock(&fs_info->free_chunk_lock);
-		fs_info->free_chunk_space -= diff;
-		spin_unlock(&fs_info->free_chunk_lock);
+		atomic64_sub(diff, &fs_info->free_chunk_space);
 	}
 	mutex_unlock(&fs_info->chunk_mutex);
 
@@ -4491,7 +4533,8 @@ again:
 			      &fs_info->fs_devices->resized_devices);
 
 	WARN_ON(diff > old_total);
-	btrfs_set_super_total_bytes(super_copy, old_total - diff);
+	btrfs_set_super_total_bytes(super_copy,
+			round_down(old_total - diff, fs_info->sectorsize));
 	mutex_unlock(&fs_info->chunk_mutex);
 
 	/* Now btrfs_update_device() will change the on-disk size. */
@@ -4504,9 +4547,7 @@ done:
 		btrfs_device_set_total_bytes(device, old_size);
 		if (device->writeable)
 			device->fs_devices->total_rw_bytes += diff;
-		spin_lock(&fs_info->free_chunk_lock);
-		fs_info->free_chunk_space += diff;
-		spin_unlock(&fs_info->free_chunk_lock);
+		atomic64_add(diff, &fs_info->free_chunk_space);
 		mutex_unlock(&fs_info->chunk_mutex);
 	}
 	return ret;
@@ -4584,8 +4625,7 @@ static void check_raid56_incompat_flag(struct btrfs_fs_info *info, u64 type)
 				/ sizeof(struct btrfs_stripe) + 1)
 
 static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
-			       struct btrfs_fs_info *fs_info, u64 start,
-			       u64 type)
+			       u64 start, u64 type)
 {
 	struct btrfs_fs_info *info = trans->fs_info;
 	struct btrfs_fs_devices *fs_devices = info->fs_devices;
@@ -4785,7 +4825,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	stripe_size = div_u64(stripe_size, dev_stripes);
 
 	/* align to BTRFS_STRIPE_LEN */
-	stripe_size = div_u64(stripe_size, raid_stripe_len);
+	stripe_size = div64_u64(stripe_size, raid_stripe_len);
 	stripe_size *= raid_stripe_len;
 
 	map = kmalloc(map_lookup_size(num_stripes), GFP_NOFS);
@@ -4833,7 +4873,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 	ret = add_extent_mapping(em_tree, em, 0);
 	if (!ret) {
 		list_add_tail(&em->list, &trans->transaction->pending_chunks);
-		atomic_inc(&em->refs);
+		refcount_inc(&em->refs);
 	}
 	write_unlock(&em_tree->lock);
 	if (ret) {
@@ -4852,9 +4892,7 @@ static int __btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 		btrfs_device_set_bytes_used(map->stripes[i].dev, num_bytes);
 	}
 
-	spin_lock(&info->free_chunk_lock);
-	info->free_chunk_space -= (stripe_size * map->num_stripes);
-	spin_unlock(&info->free_chunk_lock);
+	atomic64_sub(stripe_size * map->num_stripes, &info->free_chunk_space);
 
 	free_extent_map(em);
 	check_raid56_incompat_flag(info, type);
@@ -4888,7 +4926,6 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 	struct btrfs_device *device;
 	struct btrfs_chunk *chunk;
 	struct btrfs_stripe *stripe;
-	struct extent_map_tree *em_tree;
 	struct extent_map *em;
 	struct map_lookup *map;
 	size_t item_size;
@@ -4897,24 +4934,9 @@ int btrfs_finish_chunk_alloc(struct btrfs_trans_handle *trans,
 	int i = 0;
 	int ret = 0;
 
-	em_tree = &fs_info->mapping_tree.map_tree;
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, chunk_offset, chunk_size);
-	read_unlock(&em_tree->lock);
-
-	if (!em) {
-		btrfs_crit(fs_info, "unable to find logical %Lu len %Lu",
-			   chunk_offset, chunk_size);
-		return -EINVAL;
-	}
-
-	if (em->start != chunk_offset || em->len != chunk_size) {
-		btrfs_crit(fs_info,
-			   "found a bad mapping, wanted %Lu-%Lu, found %Lu-%Lu",
-			    chunk_offset, chunk_size, em->start, em->len);
-		free_extent_map(em);
-		return -EINVAL;
-	}
+	em = get_chunk_map(fs_info, chunk_offset, chunk_size);
+	if (IS_ERR(em))
+		return PTR_ERR(em);
 
 	map = em->map_lookup;
 	item_size = btrfs_chunk_item_size(map->num_stripes);
@@ -5009,29 +5031,26 @@ int btrfs_alloc_chunk(struct btrfs_trans_handle *trans,
 
 	ASSERT(mutex_is_locked(&fs_info->chunk_mutex));
 	chunk_offset = find_next_chunk(fs_info);
-	return __btrfs_alloc_chunk(trans, fs_info, chunk_offset, type);
+	return __btrfs_alloc_chunk(trans, chunk_offset, type);
 }
 
 static noinline int init_first_rw_device(struct btrfs_trans_handle *trans,
-					 struct btrfs_fs_info *fs_info,
-					 struct btrfs_device *device)
+					 struct btrfs_fs_info *fs_info)
 {
-	struct btrfs_root *extent_root = fs_info->extent_root;
 	u64 chunk_offset;
 	u64 sys_chunk_offset;
 	u64 alloc_profile;
 	int ret;
 
 	chunk_offset = find_next_chunk(fs_info);
-	alloc_profile = btrfs_get_alloc_profile(extent_root, 0);
-	ret = __btrfs_alloc_chunk(trans, fs_info, chunk_offset, alloc_profile);
+	alloc_profile = btrfs_metadata_alloc_profile(fs_info);
+	ret = __btrfs_alloc_chunk(trans, chunk_offset, alloc_profile);
 	if (ret)
 		return ret;
 
 	sys_chunk_offset = find_next_chunk(fs_info);
-	alloc_profile = btrfs_get_alloc_profile(fs_info->chunk_root, 0);
-	ret = __btrfs_alloc_chunk(trans, fs_info, sys_chunk_offset,
-				  alloc_profile);
+	alloc_profile = btrfs_system_alloc_profile(fs_info);
+	ret = __btrfs_alloc_chunk(trans, sys_chunk_offset, alloc_profile);
 	return ret;
 }
 
@@ -5057,15 +5076,12 @@ int btrfs_chunk_readonly(struct btrfs_fs_info *fs_info, u64 chunk_offset)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
-	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
 	int readonly = 0;
 	int miss_ndevs = 0;
 	int i;
 
-	read_lock(&map_tree->map_tree.lock);
-	em = lookup_extent_mapping(&map_tree->map_tree, chunk_offset, 1);
-	read_unlock(&map_tree->map_tree.lock);
-	if (!em)
+	em = get_chunk_map(fs_info, chunk_offset, 1);
+	if (IS_ERR(em))
 		return 1;
 
 	map = em->map_lookup;
@@ -5119,34 +5135,19 @@ void btrfs_mapping_tree_free(struct btrfs_mapping_tree *tree)
 
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 {
-	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
 	struct extent_map *em;
 	struct map_lookup *map;
-	struct extent_map_tree *em_tree = &map_tree->map_tree;
 	int ret;
 
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, logical, len);
-	read_unlock(&em_tree->lock);
-
-	/*
-	 * We could return errors for these cases, but that could get ugly and
-	 * we'd probably do the same thing which is just not do anything else
-	 * and exit, so return 1 so the callers don't try to use other copies.
-	 */
-	if (!em) {
-		btrfs_crit(fs_info, "No mapping for %Lu-%Lu", logical,
-			    logical+len);
-		return 1;
-	}
-
-	if (em->start > logical || em->start + em->len < logical) {
-		btrfs_crit(fs_info, "Invalid mapping for %Lu-%Lu, got %Lu-%Lu",
-			   logical, logical+len, em->start,
-			   em->start + em->len);
-		free_extent_map(em);
+	em = get_chunk_map(fs_info, logical, len);
+	if (IS_ERR(em))
+		/*
+		 * We could return errors for these cases, but that could get
+		 * ugly and we'd probably do the same thing which is just not do
+		 * anything else and exit, so return 1 so the callers don't try
+		 * to use other copies.
+		 */
 		return 1;
-	}
 
 	map = em->map_lookup;
 	if (map->type & (BTRFS_BLOCK_GROUP_DUP | BTRFS_BLOCK_GROUP_RAID1))
@@ -5162,7 +5163,8 @@ int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len)
 	free_extent_map(em);
 
 	btrfs_dev_replace_lock(&fs_info->dev_replace, 0);
-	if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace))
+	if (btrfs_dev_replace_is_ongoing(&fs_info->dev_replace) &&
+	    fs_info->dev_replace.tgtdev)
 		ret++;
 	btrfs_dev_replace_unlock(&fs_info->dev_replace, 0);
 
@@ -5175,15 +5177,11 @@ unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 {
 	struct extent_map *em;
 	struct map_lookup *map;
-	struct extent_map_tree *em_tree = &map_tree->map_tree;
 	unsigned long len = fs_info->sectorsize;
 
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, logical, len);
-	read_unlock(&em_tree->lock);
-	BUG_ON(!em);
+	em = get_chunk_map(fs_info, logical, len);
+	WARN_ON(IS_ERR(em));
 
-	BUG_ON(em->start > logical || em->start + em->len < logical);
 	map = em->map_lookup;
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		len = map->stripe_len * nr_data_stripes(map);
@@ -5191,20 +5189,16 @@ unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 	return len;
 }
 
-int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
+int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info,
 			   u64 logical, u64 len, int mirror_num)
 {
 	struct extent_map *em;
 	struct map_lookup *map;
-	struct extent_map_tree *em_tree = &map_tree->map_tree;
 	int ret = 0;
 
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, logical, len);
-	read_unlock(&em_tree->lock);
-	BUG_ON(!em);
+	em = get_chunk_map(fs_info, logical, len);
+	WARN_ON(IS_ERR(em));
 
-	BUG_ON(em->start > logical || em->start + em->len < logical);
 	map = em->map_lookup;
 	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK)
 		ret = 1;
@@ -5297,25 +5291,353 @@ static struct btrfs_bio *alloc_btrfs_bio(int total_stripes, int real_stripes)
 		GFP_NOFS|__GFP_NOFAIL);
 
 	atomic_set(&bbio->error, 0);
-	atomic_set(&bbio->refs, 1);
+	refcount_set(&bbio->refs, 1);
 
 	return bbio;
 }
 
 void btrfs_get_bbio(struct btrfs_bio *bbio)
 {
-	WARN_ON(!atomic_read(&bbio->refs));
-	atomic_inc(&bbio->refs);
+	WARN_ON(!refcount_read(&bbio->refs));
+	refcount_inc(&bbio->refs);
 }
 
 void btrfs_put_bbio(struct btrfs_bio *bbio)
 {
 	if (!bbio)
 		return;
-	if (atomic_dec_and_test(&bbio->refs))
+	if (refcount_dec_and_test(&bbio->refs))
 		kfree(bbio);
 }
 
+/* can REQ_OP_DISCARD be sent with other REQ like REQ_OP_WRITE? */
+/*
+ * Please note that, discard won't be sent to target device of device
+ * replace.
+ */
+static int __btrfs_map_block_for_discard(struct btrfs_fs_info *fs_info,
+					 u64 logical, u64 length,
+					 struct btrfs_bio **bbio_ret)
+{
+	struct extent_map *em;
+	struct map_lookup *map;
+	struct btrfs_bio *bbio;
+	u64 offset;
+	u64 stripe_nr;
+	u64 stripe_nr_end;
+	u64 stripe_end_offset;
+	u64 stripe_cnt;
+	u64 stripe_len;
+	u64 stripe_offset;
+	u64 num_stripes;
+	u32 stripe_index;
+	u32 factor = 0;
+	u32 sub_stripes = 0;
+	u64 stripes_per_dev = 0;
+	u32 remaining_stripes = 0;
+	u32 last_stripe = 0;
+	int ret = 0;
+	int i;
+
+	/* discard always return a bbio */
+	ASSERT(bbio_ret);
+
+	em = get_chunk_map(fs_info, logical, length);
+	if (IS_ERR(em))
+		return PTR_ERR(em);
+
+	map = em->map_lookup;
+	/* we don't discard raid56 yet */
+	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
+		ret = -EOPNOTSUPP;
+		goto out;
+	}
+
+	offset = logical - em->start;
+	length = min_t(u64, em->len - offset, length);
+
+	stripe_len = map->stripe_len;
+	/*
+	 * stripe_nr counts the total number of stripes we have to stride
+	 * to get to this block
+	 */
+	stripe_nr = div64_u64(offset, stripe_len);
+
+	/* stripe_offset is the offset of this block in its stripe */
+	stripe_offset = offset - stripe_nr * stripe_len;
+
+	stripe_nr_end = round_up(offset + length, map->stripe_len);
+	stripe_nr_end = div64_u64(stripe_nr_end, map->stripe_len);
+	stripe_cnt = stripe_nr_end - stripe_nr;
+	stripe_end_offset = stripe_nr_end * map->stripe_len -
+			    (offset + length);
+	/*
+	 * after this, stripe_nr is the number of stripes on this
+	 * device we have to walk to find the data, and stripe_index is
+	 * the number of our device in the stripe array
+	 */
+	num_stripes = 1;
+	stripe_index = 0;
+	if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
+			 BTRFS_BLOCK_GROUP_RAID10)) {
+		if (map->type & BTRFS_BLOCK_GROUP_RAID0)
+			sub_stripes = 1;
+		else
+			sub_stripes = map->sub_stripes;
+
+		factor = map->num_stripes / sub_stripes;
+		num_stripes = min_t(u64, map->num_stripes,
+				    sub_stripes * stripe_cnt);
+		stripe_nr = div_u64_rem(stripe_nr, factor, &stripe_index);
+		stripe_index *= sub_stripes;
+		stripes_per_dev = div_u64_rem(stripe_cnt, factor,
+					      &remaining_stripes);
+		div_u64_rem(stripe_nr_end - 1, factor, &last_stripe);
+		last_stripe *= sub_stripes;
+	} else if (map->type & (BTRFS_BLOCK_GROUP_RAID1 |
+				BTRFS_BLOCK_GROUP_DUP)) {
+		num_stripes = map->num_stripes;
+	} else {
+		stripe_nr = div_u64_rem(stripe_nr, map->num_stripes,
+					&stripe_index);
+	}
+
+	bbio = alloc_btrfs_bio(num_stripes, 0);
+	if (!bbio) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	for (i = 0; i < num_stripes; i++) {
+		bbio->stripes[i].physical =
+			map->stripes[stripe_index].physical +
+			stripe_offset + stripe_nr * map->stripe_len;
+		bbio->stripes[i].dev = map->stripes[stripe_index].dev;
+
+		if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
+				 BTRFS_BLOCK_GROUP_RAID10)) {
+			bbio->stripes[i].length = stripes_per_dev *
+				map->stripe_len;
+
+			if (i / sub_stripes < remaining_stripes)
+				bbio->stripes[i].length +=
+					map->stripe_len;
+
+			/*
+			 * Special for the first stripe and
+			 * the last stripe:
+			 *
+			 * |-------|...|-------|
+			 *     |----------|
+			 *    off     end_off
+			 */
+			if (i < sub_stripes)
+				bbio->stripes[i].length -=
+					stripe_offset;
+
+			if (stripe_index >= last_stripe &&
+			    stripe_index <= (last_stripe +
+					     sub_stripes - 1))
+				bbio->stripes[i].length -=
+					stripe_end_offset;
+
+			if (i == sub_stripes - 1)
+				stripe_offset = 0;
+		} else {
+			bbio->stripes[i].length = length;
+		}
+
+		stripe_index++;
+		if (stripe_index == map->num_stripes) {
+			stripe_index = 0;
+			stripe_nr++;
+		}
+	}
+
+	*bbio_ret = bbio;
+	bbio->map_type = map->type;
+	bbio->num_stripes = num_stripes;
+out:
+	free_extent_map(em);
+	return ret;
+}
+
+/*
+ * In dev-replace case, for repair case (that's the only case where the mirror
+ * is selected explicitly when calling btrfs_map_block), blocks left of the
+ * left cursor can also be read from the target drive.
+ *
+ * For REQ_GET_READ_MIRRORS, the target drive is added as the last one to the
+ * array of stripes.
+ * For READ, it also needs to be supported using the same mirror number.
+ *
+ * If the requested block is not left of the left cursor, EIO is returned. This
+ * can happen because btrfs_num_copies() returns one more in the dev-replace
+ * case.
+ */
+static int get_extra_mirror_from_replace(struct btrfs_fs_info *fs_info,
+					 u64 logical, u64 length,
+					 u64 srcdev_devid, int *mirror_num,
+					 u64 *physical)
+{
+	struct btrfs_bio *bbio = NULL;
+	int num_stripes;
+	int index_srcdev = 0;
+	int found = 0;
+	u64 physical_of_found = 0;
+	int i;
+	int ret = 0;
+
+	ret = __btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS,
+				logical, &length, &bbio, 0, 0);
+	if (ret) {
+		ASSERT(bbio == NULL);
+		return ret;
+	}
+
+	num_stripes = bbio->num_stripes;
+	if (*mirror_num > num_stripes) {
+		/*
+		 * BTRFS_MAP_GET_READ_MIRRORS does not contain this mirror,
+		 * that means that the requested area is not left of the left
+		 * cursor
+		 */
+		btrfs_put_bbio(bbio);
+		return -EIO;
+	}
+
+	/*
+	 * process the rest of the function using the mirror_num of the source
+	 * drive. Therefore look it up first.  At the end, patch the device
+	 * pointer to the one of the target drive.
+	 */
+	for (i = 0; i < num_stripes; i++) {
+		if (bbio->stripes[i].dev->devid != srcdev_devid)
+			continue;
+
+		/*
+		 * In case of DUP, in order to keep it simple, only add the
+		 * mirror with the lowest physical address
+		 */
+		if (found &&
+		    physical_of_found <= bbio->stripes[i].physical)
+			continue;
+
+		index_srcdev = i;
+		found = 1;
+		physical_of_found = bbio->stripes[i].physical;
+	}
+
+	btrfs_put_bbio(bbio);
+
+	ASSERT(found);
+	if (!found)
+		return -EIO;
+
+	*mirror_num = index_srcdev + 1;
+	*physical = physical_of_found;
+	return ret;
+}
+
+static void handle_ops_on_dev_replace(enum btrfs_map_op op,
+				      struct btrfs_bio **bbio_ret,
+				      struct btrfs_dev_replace *dev_replace,
+				      int *num_stripes_ret, int *max_errors_ret)
+{
+	struct btrfs_bio *bbio = *bbio_ret;
+	u64 srcdev_devid = dev_replace->srcdev->devid;
+	int tgtdev_indexes = 0;
+	int num_stripes = *num_stripes_ret;
+	int max_errors = *max_errors_ret;
+	int i;
+
+	if (op == BTRFS_MAP_WRITE) {
+		int index_where_to_add;
+
+		/*
+		 * duplicate the write operations while the dev replace
+		 * procedure is running. Since the copying of the old disk to
+		 * the new disk takes place at run time while the filesystem is
+		 * mounted writable, the regular write operations to the old
+		 * disk have to be duplicated to go to the new disk as well.
+		 *
+		 * Note that device->missing is handled by the caller, and that
+		 * the write to the old disk is already set up in the stripes
+		 * array.
+		 */
+		index_where_to_add = num_stripes;
+		for (i = 0; i < num_stripes; i++) {
+			if (bbio->stripes[i].dev->devid == srcdev_devid) {
+				/* write to new disk, too */
+				struct btrfs_bio_stripe *new =
+					bbio->stripes + index_where_to_add;
+				struct btrfs_bio_stripe *old =
+					bbio->stripes + i;
+
+				new->physical = old->physical;
+				new->length = old->length;
+				new->dev = dev_replace->tgtdev;
+				bbio->tgtdev_map[i] = index_where_to_add;
+				index_where_to_add++;
+				max_errors++;
+				tgtdev_indexes++;
+			}
+		}
+		num_stripes = index_where_to_add;
+	} else if (op == BTRFS_MAP_GET_READ_MIRRORS) {
+		int index_srcdev = 0;
+		int found = 0;
+		u64 physical_of_found = 0;
+
+		/*
+		 * During the dev-replace procedure, the target drive can also
+		 * be used to read data in case it is needed to repair a corrupt
+		 * block elsewhere. This is possible if the requested area is
+		 * left of the left cursor. In this area, the target drive is a
+		 * full copy of the source drive.
+		 */
+		for (i = 0; i < num_stripes; i++) {
+			if (bbio->stripes[i].dev->devid == srcdev_devid) {
+				/*
+				 * In case of DUP, in order to keep it simple,
+				 * only add the mirror with the lowest physical
+				 * address
+				 */
+				if (found &&
+				    physical_of_found <=
+				     bbio->stripes[i].physical)
+					continue;
+				index_srcdev = i;
+				found = 1;
+				physical_of_found = bbio->stripes[i].physical;
+			}
+		}
+		if (found) {
+			struct btrfs_bio_stripe *tgtdev_stripe =
+				bbio->stripes + num_stripes;
+
+			tgtdev_stripe->physical = physical_of_found;
+			tgtdev_stripe->length =
+				bbio->stripes[index_srcdev].length;
+			tgtdev_stripe->dev = dev_replace->tgtdev;
+			bbio->tgtdev_map[index_srcdev] = num_stripes;
+
+			tgtdev_indexes++;
+			num_stripes++;
+		}
+	}
+
+	*num_stripes_ret = num_stripes;
+	*max_errors_ret = max_errors;
+	bbio->num_tgtdevs = tgtdev_indexes;
+	*bbio_ret = bbio;
+}
+
+static bool need_full_stripe(enum btrfs_map_op op)
+{
+	return (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS);
+}
+
 static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 			     enum btrfs_map_op op,
 			     u64 logical, u64 *length,
@@ -5324,14 +5646,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 {
 	struct extent_map *em;
 	struct map_lookup *map;
-	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
-	struct extent_map_tree *em_tree = &map_tree->map_tree;
 	u64 offset;
 	u64 stripe_offset;
-	u64 stripe_end_offset;
 	u64 stripe_nr;
-	u64 stripe_nr_orig;
-	u64 stripe_nr_end;
 	u64 stripe_len;
 	u32 stripe_index;
 	int i;
@@ -5347,23 +5664,13 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 	u64 physical_to_patch_in_first_stripe = 0;
 	u64 raid56_full_stripe_start = (u64)-1;
 
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, logical, *length);
-	read_unlock(&em_tree->lock);
-
-	if (!em) {
-		btrfs_crit(fs_info, "unable to find logical %llu len %llu",
-			logical, *length);
-		return -EINVAL;
-	}
+	if (op == BTRFS_MAP_DISCARD)
+		return __btrfs_map_block_for_discard(fs_info, logical,
+						     *length, bbio_ret);
 
-	if (em->start > logical || em->start + em->len < logical) {
-		btrfs_crit(fs_info,
-			   "found a bad mapping, wanted %Lu, found %Lu-%Lu",
-			   logical, em->start, em->start + em->len);
-		free_extent_map(em);
-		return -EINVAL;
-	}
+	em = get_chunk_map(fs_info, logical, *length);
+	if (IS_ERR(em))
+		return PTR_ERR(em);
 
 	map = em->map_lookup;
 	offset = logical - em->start;
@@ -5402,14 +5709,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 		raid56_full_stripe_start *= full_stripe_len;
 	}
 
-	if (op == BTRFS_MAP_DISCARD) {
-		/* we don't discard raid56 yet */
-		if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK) {
-			ret = -EOPNOTSUPP;
-			goto out;
-		}
-		*length = min_t(u64, em->len - offset, *length);
-	} else if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
+	if (map->type & BTRFS_BLOCK_GROUP_PROFILE_MASK) {
 		u64 max_len;
 		/* For writes to RAID[56], allow a full stripeset across all disks.
 		   For other RAID types and for RAID[56] reads, just allow a single
@@ -5440,105 +5740,28 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 		btrfs_dev_replace_set_lock_blocking(dev_replace);
 
 	if (dev_replace_is_ongoing && mirror_num == map->num_stripes + 1 &&
-	    op != BTRFS_MAP_WRITE && op != BTRFS_MAP_DISCARD &&
-	    op != BTRFS_MAP_GET_READ_MIRRORS && dev_replace->tgtdev != NULL) {
-		/*
-		 * in dev-replace case, for repair case (that's the only
-		 * case where the mirror is selected explicitly when
-		 * calling btrfs_map_block), blocks left of the left cursor
-		 * can also be read from the target drive.
-		 * For REQ_GET_READ_MIRRORS, the target drive is added as
-		 * the last one to the array of stripes. For READ, it also
-		 * needs to be supported using the same mirror number.
-		 * If the requested block is not left of the left cursor,
-		 * EIO is returned. This can happen because btrfs_num_copies()
-		 * returns one more in the dev-replace case.
-		 */
-		u64 tmp_length = *length;
-		struct btrfs_bio *tmp_bbio = NULL;
-		int tmp_num_stripes;
-		u64 srcdev_devid = dev_replace->srcdev->devid;
-		int index_srcdev = 0;
-		int found = 0;
-		u64 physical_of_found = 0;
-
-		ret = __btrfs_map_block(fs_info, BTRFS_MAP_GET_READ_MIRRORS,
-			     logical, &tmp_length, &tmp_bbio, 0, 0);
-		if (ret) {
-			WARN_ON(tmp_bbio != NULL);
-			goto out;
-		}
-
-		tmp_num_stripes = tmp_bbio->num_stripes;
-		if (mirror_num > tmp_num_stripes) {
-			/*
-			 * BTRFS_MAP_GET_READ_MIRRORS does not contain this
-			 * mirror, that means that the requested area
-			 * is not left of the left cursor
-			 */
-			ret = -EIO;
-			btrfs_put_bbio(tmp_bbio);
-			goto out;
-		}
-
-		/*
-		 * process the rest of the function using the mirror_num
-		 * of the source drive. Therefore look it up first.
-		 * At the end, patch the device pointer to the one of the
-		 * target drive.
-		 */
-		for (i = 0; i < tmp_num_stripes; i++) {
-			if (tmp_bbio->stripes[i].dev->devid != srcdev_devid)
-				continue;
-
-			/*
-			 * In case of DUP, in order to keep it simple, only add
-			 * the mirror with the lowest physical address
-			 */
-			if (found &&
-			    physical_of_found <= tmp_bbio->stripes[i].physical)
-				continue;
-
-			index_srcdev = i;
-			found = 1;
-			physical_of_found = tmp_bbio->stripes[i].physical;
-		}
-
-		btrfs_put_bbio(tmp_bbio);
-
-		if (!found) {
-			WARN_ON(1);
-			ret = -EIO;
+	    !need_full_stripe(op) && dev_replace->tgtdev != NULL) {
+		ret = get_extra_mirror_from_replace(fs_info, logical, *length,
+						    dev_replace->srcdev->devid,
+						    &mirror_num,
+					    &physical_to_patch_in_first_stripe);
+		if (ret)
 			goto out;
-		}
-
-		mirror_num = index_srcdev + 1;
-		patch_the_first_stripe_for_dev_replace = 1;
-		physical_to_patch_in_first_stripe = physical_of_found;
+		else
+			patch_the_first_stripe_for_dev_replace = 1;
 	} else if (mirror_num > map->num_stripes) {
 		mirror_num = 0;
 	}
 
 	num_stripes = 1;
 	stripe_index = 0;
-	stripe_nr_orig = stripe_nr;
-	stripe_nr_end = ALIGN(offset + *length, map->stripe_len);
-	stripe_nr_end = div_u64(stripe_nr_end, map->stripe_len);
-	stripe_end_offset = stripe_nr_end * map->stripe_len -
-			    (offset + *length);
-
 	if (map->type & BTRFS_BLOCK_GROUP_RAID0) {
-		if (op == BTRFS_MAP_DISCARD)
-			num_stripes = min_t(u64, map->num_stripes,
-					    stripe_nr_end - stripe_nr_orig);
 		stripe_nr = div_u64_rem(stripe_nr, map->num_stripes,
 				&stripe_index);
-		if (op != BTRFS_MAP_WRITE && op != BTRFS_MAP_DISCARD &&
-		    op != BTRFS_MAP_GET_READ_MIRRORS)
+		if (op != BTRFS_MAP_WRITE && op != BTRFS_MAP_GET_READ_MIRRORS)
 			mirror_num = 1;
 	} else if (map->type & BTRFS_BLOCK_GROUP_RAID1) {
-		if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_DISCARD ||
-		    op == BTRFS_MAP_GET_READ_MIRRORS)
+		if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS)
 			num_stripes = map->num_stripes;
 		else if (mirror_num)
 			stripe_index = mirror_num - 1;
@@ -5551,8 +5774,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 		}
 
 	} else if (map->type & BTRFS_BLOCK_GROUP_DUP) {
-		if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_DISCARD ||
-		    op == BTRFS_MAP_GET_READ_MIRRORS) {
+		if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS) {
 			num_stripes = map->num_stripes;
 		} else if (mirror_num) {
 			stripe_index = mirror_num - 1;
@@ -5568,10 +5790,6 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 
 		if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS)
 			num_stripes = map->sub_stripes;
-		else if (op == BTRFS_MAP_DISCARD)
-			num_stripes = min_t(u64, map->sub_stripes *
-					    (stripe_nr_end - stripe_nr_orig),
-					    map->num_stripes);
 		else if (mirror_num)
 			stripe_index += mirror_num - 1;
 		else {
@@ -5589,7 +5807,7 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 		    (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS ||
 		     mirror_num > 1)) {
 			/* push stripe_nr back to the start of the full stripe */
-			stripe_nr = div_u64(raid56_full_stripe_start,
+			stripe_nr = div64_u64(raid56_full_stripe_start,
 					stripe_len * nr_data_stripes(map));
 
 			/* RAID[56] write or recovery. Return all stripes */
@@ -5614,8 +5832,9 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 			/* We distribute the parity blocks across stripes */
 			div_u64_rem(stripe_nr + stripe_index, map->num_stripes,
 					&stripe_index);
-			if ((op != BTRFS_MAP_WRITE && op != BTRFS_MAP_DISCARD &&
-			    op != BTRFS_MAP_GET_READ_MIRRORS) && mirror_num <= 1)
+			if ((op != BTRFS_MAP_WRITE &&
+			     op != BTRFS_MAP_GET_READ_MIRRORS) &&
+			    mirror_num <= 1)
 				mirror_num = 1;
 		}
 	} else {
@@ -5637,8 +5856,8 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 	}
 
 	num_alloc_stripes = num_stripes;
-	if (dev_replace_is_ongoing) {
-		if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_DISCARD)
+	if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL) {
+		if (op == BTRFS_MAP_WRITE)
 			num_alloc_stripes <<= 1;
 		if (op == BTRFS_MAP_GET_READ_MIRRORS)
 			num_alloc_stripes++;
@@ -5650,14 +5869,12 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 		ret = -ENOMEM;
 		goto out;
 	}
-	if (dev_replace_is_ongoing)
+	if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL)
 		bbio->tgtdev_map = (int *)(bbio->stripes + num_alloc_stripes);
 
 	/* build raid_map */
-	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK &&
-	    need_raid_map &&
-	    ((op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS) ||
-	    mirror_num > 1)) {
+	if (map->type & BTRFS_BLOCK_GROUP_RAID56_MASK && need_raid_map &&
+	    (need_full_stripe(op) || mirror_num > 1)) {
 		u64 tmp;
 		unsigned rot;
 
@@ -5681,173 +5898,27 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 				RAID6_Q_STRIPE;
 	}
 
-	if (op == BTRFS_MAP_DISCARD) {
-		u32 factor = 0;
-		u32 sub_stripes = 0;
-		u64 stripes_per_dev = 0;
-		u32 remaining_stripes = 0;
-		u32 last_stripe = 0;
 
-		if (map->type &
-		    (BTRFS_BLOCK_GROUP_RAID0 | BTRFS_BLOCK_GROUP_RAID10)) {
-			if (map->type & BTRFS_BLOCK_GROUP_RAID0)
-				sub_stripes = 1;
-			else
-				sub_stripes = map->sub_stripes;
-
-			factor = map->num_stripes / sub_stripes;
-			stripes_per_dev = div_u64_rem(stripe_nr_end -
-						      stripe_nr_orig,
-						      factor,
-						      &remaining_stripes);
-			div_u64_rem(stripe_nr_end - 1, factor, &last_stripe);
-			last_stripe *= sub_stripes;
-		}
-
-		for (i = 0; i < num_stripes; i++) {
-			bbio->stripes[i].physical =
-				map->stripes[stripe_index].physical +
-				stripe_offset + stripe_nr * map->stripe_len;
-			bbio->stripes[i].dev = map->stripes[stripe_index].dev;
-
-			if (map->type & (BTRFS_BLOCK_GROUP_RAID0 |
-					 BTRFS_BLOCK_GROUP_RAID10)) {
-				bbio->stripes[i].length = stripes_per_dev *
-							  map->stripe_len;
-
-				if (i / sub_stripes < remaining_stripes)
-					bbio->stripes[i].length +=
-						map->stripe_len;
-
-				/*
-				 * Special for the first stripe and
-				 * the last stripe:
-				 *
-				 * |-------|...|-------|
-				 *     |----------|
-				 *    off     end_off
-				 */
-				if (i < sub_stripes)
-					bbio->stripes[i].length -=
-						stripe_offset;
-
-				if (stripe_index >= last_stripe &&
-				    stripe_index <= (last_stripe +
-						     sub_stripes - 1))
-					bbio->stripes[i].length -=
-						stripe_end_offset;
-
-				if (i == sub_stripes - 1)
-					stripe_offset = 0;
-			} else
-				bbio->stripes[i].length = *length;
-
-			stripe_index++;
-			if (stripe_index == map->num_stripes) {
-				/* This could only happen for RAID0/10 */
-				stripe_index = 0;
-				stripe_nr++;
-			}
-		}
-	} else {
-		for (i = 0; i < num_stripes; i++) {
-			bbio->stripes[i].physical =
-				map->stripes[stripe_index].physical +
-				stripe_offset +
-				stripe_nr * map->stripe_len;
-			bbio->stripes[i].dev =
-				map->stripes[stripe_index].dev;
-			stripe_index++;
-		}
+	for (i = 0; i < num_stripes; i++) {
+		bbio->stripes[i].physical =
+			map->stripes[stripe_index].physical +
+			stripe_offset +
+			stripe_nr * map->stripe_len;
+		bbio->stripes[i].dev =
+			map->stripes[stripe_index].dev;
+		stripe_index++;
 	}
 
-	if (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_GET_READ_MIRRORS)
+	if (need_full_stripe(op))
 		max_errors = btrfs_chunk_max_errors(map);
 
 	if (bbio->raid_map)
 		sort_parity_stripes(bbio, num_stripes);
 
-	tgtdev_indexes = 0;
-	if (dev_replace_is_ongoing &&
-	   (op == BTRFS_MAP_WRITE || op == BTRFS_MAP_DISCARD) &&
-	    dev_replace->tgtdev != NULL) {
-		int index_where_to_add;
-		u64 srcdev_devid = dev_replace->srcdev->devid;
-
-		/*
-		 * duplicate the write operations while the dev replace
-		 * procedure is running. Since the copying of the old disk
-		 * to the new disk takes place at run time while the
-		 * filesystem is mounted writable, the regular write
-		 * operations to the old disk have to be duplicated to go
-		 * to the new disk as well.
-		 * Note that device->missing is handled by the caller, and
-		 * that the write to the old disk is already set up in the
-		 * stripes array.
-		 */
-		index_where_to_add = num_stripes;
-		for (i = 0; i < num_stripes; i++) {
-			if (bbio->stripes[i].dev->devid == srcdev_devid) {
-				/* write to new disk, too */
-				struct btrfs_bio_stripe *new =
-					bbio->stripes + index_where_to_add;
-				struct btrfs_bio_stripe *old =
-					bbio->stripes + i;
-
-				new->physical = old->physical;
-				new->length = old->length;
-				new->dev = dev_replace->tgtdev;
-				bbio->tgtdev_map[i] = index_where_to_add;
-				index_where_to_add++;
-				max_errors++;
-				tgtdev_indexes++;
-			}
-		}
-		num_stripes = index_where_to_add;
-	} else if (dev_replace_is_ongoing &&
-		   op == BTRFS_MAP_GET_READ_MIRRORS &&
-		   dev_replace->tgtdev != NULL) {
-		u64 srcdev_devid = dev_replace->srcdev->devid;
-		int index_srcdev = 0;
-		int found = 0;
-		u64 physical_of_found = 0;
-
-		/*
-		 * During the dev-replace procedure, the target drive can
-		 * also be used to read data in case it is needed to repair
-		 * a corrupt block elsewhere. This is possible if the
-		 * requested area is left of the left cursor. In this area,
-		 * the target drive is a full copy of the source drive.
-		 */
-		for (i = 0; i < num_stripes; i++) {
-			if (bbio->stripes[i].dev->devid == srcdev_devid) {
-				/*
-				 * In case of DUP, in order to keep it
-				 * simple, only add the mirror with the
-				 * lowest physical address
-				 */
-				if (found &&
-				    physical_of_found <=
-				     bbio->stripes[i].physical)
-					continue;
-				index_srcdev = i;
-				found = 1;
-				physical_of_found = bbio->stripes[i].physical;
-			}
-		}
-		if (found) {
-			struct btrfs_bio_stripe *tgtdev_stripe =
-				bbio->stripes + num_stripes;
-
-			tgtdev_stripe->physical = physical_of_found;
-			tgtdev_stripe->length =
-				bbio->stripes[index_srcdev].length;
-			tgtdev_stripe->dev = dev_replace->tgtdev;
-			bbio->tgtdev_map[index_srcdev] = num_stripes;
-
-			tgtdev_indexes++;
-			num_stripes++;
-		}
+	if (dev_replace_is_ongoing && dev_replace->tgtdev != NULL &&
+	    need_full_stripe(op)) {
+		handle_ops_on_dev_replace(op, &bbio, dev_replace, &num_stripes,
+					  &max_errors);
 	}
 
 	*bbio_ret = bbio;
@@ -5855,7 +5926,6 @@ static int __btrfs_map_block(struct btrfs_fs_info *fs_info,
 	bbio->num_stripes = num_stripes;
 	bbio->max_errors = max_errors;
 	bbio->mirror_num = mirror_num;
-	bbio->num_tgtdevs = tgtdev_indexes;
 
 	/*
 	 * this is the case that REQ_READ && dev_replace_is_ongoing &&
@@ -5888,19 +5958,15 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 /* For Scrub/replace */
 int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		     u64 logical, u64 *length,
-		     struct btrfs_bio **bbio_ret, int mirror_num,
-		     int need_raid_map)
+		     struct btrfs_bio **bbio_ret)
 {
-	return __btrfs_map_block(fs_info, op, logical, length, bbio_ret,
-				 mirror_num, need_raid_map);
+	return __btrfs_map_block(fs_info, op, logical, length, bbio_ret, 0, 1);
 }
 
 int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
 		     u64 chunk_start, u64 physical, u64 devid,
 		     u64 **logical, int *naddrs, int *stripe_len)
 {
-	struct btrfs_mapping_tree *map_tree = &fs_info->mapping_tree;
-	struct extent_map_tree *em_tree = &map_tree->map_tree;
 	struct extent_map *em;
 	struct map_lookup *map;
 	u64 *buf;
@@ -5910,24 +5976,11 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
 	u64 rmap_len;
 	int i, j, nr = 0;
 
-	read_lock(&em_tree->lock);
-	em = lookup_extent_mapping(em_tree, chunk_start, 1);
-	read_unlock(&em_tree->lock);
-
-	if (!em) {
-		btrfs_err(fs_info, "couldn't find em for chunk %Lu",
-			chunk_start);
+	em = get_chunk_map(fs_info, chunk_start, 1);
+	if (IS_ERR(em))
 		return -EIO;
-	}
 
-	if (em->start != chunk_start) {
-		btrfs_err(fs_info, "bad chunk start, em=%Lu, wanted=%Lu",
-		       em->start, chunk_start);
-		free_extent_map(em);
-		return -EIO;
-	}
 	map = em->map_lookup;
-
 	length = em->len;
 	rmap_len = map->stripe_len;
 
@@ -5951,7 +6004,7 @@ int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
 			continue;
 
 		stripe_nr = physical - map->stripes[i].physical;
-		stripe_nr = div_u64(stripe_nr, map->stripe_len);
+		stripe_nr = div64_u64(stripe_nr, map->stripe_len);
 
 		if (map->type & BTRFS_BLOCK_GROUP_RAID10) {
 			stripe_nr = stripe_nr * map->num_stripes + i;
@@ -5996,9 +6049,10 @@ static void btrfs_end_bio(struct bio *bio)
 	struct btrfs_bio *bbio = bio->bi_private;
 	int is_orig_bio = 0;
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		atomic_inc(&bbio->error);
-		if (bio->bi_error == -EIO || bio->bi_error == -EREMOTEIO) {
+		if (bio->bi_status == BLK_STS_IOERR ||
+		    bio->bi_status == BLK_STS_TARGET) {
 			unsigned int stripe_index =
 				btrfs_io_bio(bio)->stripe_index;
 			struct btrfs_device *dev;
@@ -6036,13 +6090,13 @@ static void btrfs_end_bio(struct bio *bio)
 		 * beyond the tolerance of the btrfs bio
 		 */
 		if (atomic_read(&bbio->error) > bbio->max_errors) {
-			bio->bi_error = -EIO;
+			bio->bi_status = BLK_STS_IOERR;
 		} else {
 			/*
 			 * this bio is actually up to date, we didn't
 			 * go over the max number of errors
 			 */
-			bio->bi_error = 0;
+			bio->bi_status = 0;
 		}
 
 		btrfs_end_bbio(bbio, bio);
@@ -6153,7 +6207,7 @@ static void bbio_error(struct btrfs_bio *bbio, struct bio *bio, u64 logical)
 
 		btrfs_io_bio(bio)->mirror_num = bbio->mirror_num;
 		bio->bi_iter.bi_sector = logical >> 9;
-		bio->bi_error = -EIO;
+		bio->bi_status = BLK_STS_IOERR;
 		btrfs_end_bbio(bbio, bio);
 	}
 }
@@ -6215,15 +6269,14 @@ int btrfs_map_bio(struct btrfs_fs_info *fs_info, struct bio *bio,
 	for (dev_nr = 0; dev_nr < total_devs; dev_nr++) {
 		dev = bbio->stripes[dev_nr].dev;
 		if (!dev || !dev->bdev ||
-		    (bio_op(bio) == REQ_OP_WRITE && !dev->writeable)) {
+		    (bio_op(first_bio) == REQ_OP_WRITE && !dev->writeable)) {
 			bbio_error(bbio, first_bio, logical);
 			continue;
 		}
 
-		if (dev_nr < total_devs - 1) {
-			bio = btrfs_bio_clone(first_bio, GFP_NOFS);
-			BUG_ON(!bio); /* -ENOMEM */
-		} else
+		if (dev_nr < total_devs - 1)
+			bio = btrfs_bio_clone(first_bio);
+		else
 			bio = first_bio;
 
 		submit_stripe_bio(bbio, bio, bbio->stripes[dev_nr].physical,
@@ -6638,10 +6691,8 @@ static int read_one_dev(struct btrfs_fs_info *fs_info,
 	device->in_fs_metadata = 1;
 	if (device->writeable && !device->is_tgtdev_for_dev_replace) {
 		device->fs_devices->total_rw_bytes += device->total_bytes;
-		spin_lock(&fs_info->free_chunk_lock);
-		fs_info->free_chunk_space += device->total_bytes -
-			device->bytes_used;
-		spin_unlock(&fs_info->free_chunk_lock);
+		atomic64_add(device->total_bytes - device->bytes_used,
+				&fs_info->free_chunk_space);
 	}
 	ret = 0;
 	return ret;
@@ -6958,7 +7009,8 @@ static int update_dev_stat_item(struct btrfs_trans_handle *trans,
 	key.offset = device->devid;
 
 	path = btrfs_alloc_path();
-	BUG_ON(!path);
+	if (!path)
+		return -ENOMEM;
 	ret = btrfs_search_slot(trans, dev_root, &key, path, -1, 1);
 	if (ret < 0) {
 		btrfs_warn_in_rcu(fs_info,
@@ -7106,7 +7158,7 @@ int btrfs_get_dev_stats(struct btrfs_fs_info *fs_info,
 	return 0;
 }
 
-void btrfs_scratch_superblocks(struct block_device *bdev, char *device_path)
+void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path)
 {
 	struct buffer_head *bh;
 	struct btrfs_super_block *disk_super;
diff --git a/fs/btrfs/volumes.h b/fs/btrfs/volumes.h
index 24ba6bc3ec34..6f45fd60d15a 100644
--- a/fs/btrfs/volumes.h
+++ b/fs/btrfs/volumes.h
@@ -74,6 +74,8 @@ struct btrfs_device {
 	int missing;
 	int can_discard;
 	int is_tgtdev_for_dev_replace;
+	int last_flush_error;
+	int flush_bio_sent;
 
 #ifdef __BTRFS_NEED_DEVICE_DATA_ORDERED
 	seqcount_t data_seqcount;
@@ -123,7 +125,6 @@ struct btrfs_device {
 	struct list_head resized_list;
 
 	/* for sending down flush barriers */
-	int nobarriers;
 	struct bio *flush_bio;
 	struct completion flush_wait;
 
@@ -280,6 +281,11 @@ struct btrfs_io_bio {
 	u8 csum_inline[BTRFS_BIO_INLINE_CSUM_SIZE];
 	u8 *csum_allocated;
 	btrfs_io_bio_end_io_t *end_io;
+	struct bvec_iter iter;
+	/*
+	 * This member must come last, bio_alloc_bioset will allocate enough
+	 * bytes for entire btrfs_io_bio but relies on bio being last.
+	 */
 	struct bio bio;
 };
 
@@ -298,7 +304,7 @@ struct btrfs_bio;
 typedef void (btrfs_bio_end_io_t) (struct btrfs_bio *bio, int err);
 
 struct btrfs_bio {
-	atomic_t refs;
+	refcount_t refs;
 	atomic_t stripes_pending;
 	struct btrfs_fs_info *fs_info;
 	u64 map_type; /* get from map_lookup->type */
@@ -400,8 +406,7 @@ int btrfs_map_block(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		    struct btrfs_bio **bbio_ret, int mirror_num);
 int btrfs_map_sblock(struct btrfs_fs_info *fs_info, enum btrfs_map_op op,
 		     u64 logical, u64 *length,
-		     struct btrfs_bio **bbio_ret, int mirror_num,
-		     int need_raid_map);
+		     struct btrfs_bio **bbio_ret);
 int btrfs_rmap_block(struct btrfs_fs_info *fs_info,
 		     u64 chunk_start, u64 physical, u64 devid,
 		     u64 **logical, int *naddrs, int *stripe_len);
@@ -422,16 +427,16 @@ void btrfs_close_extra_devices(struct btrfs_fs_devices *fs_devices, int step);
 void btrfs_assign_next_active_device(struct btrfs_fs_info *fs_info,
 		struct btrfs_device *device, struct btrfs_device *this_dev);
 int btrfs_find_device_missing_or_by_path(struct btrfs_fs_info *fs_info,
-					 char *device_path,
+					 const char *device_path,
 					 struct btrfs_device **device);
 int btrfs_find_device_by_devspec(struct btrfs_fs_info *fs_info, u64 devid,
-					 char *devpath,
+					 const char *devpath,
 					 struct btrfs_device **device);
 struct btrfs_device *btrfs_alloc_device(struct btrfs_fs_info *fs_info,
 					const u64 *devid,
 					const u8 *uuid);
 int btrfs_rm_device(struct btrfs_fs_info *fs_info,
-		    char *device_path, u64 devid);
+		    const char *device_path, u64 devid);
 void btrfs_cleanup_fs_uuids(void);
 int btrfs_num_copies(struct btrfs_fs_info *fs_info, u64 logical, u64 len);
 int btrfs_grow_device(struct btrfs_trans_handle *trans,
@@ -439,9 +444,9 @@ int btrfs_grow_device(struct btrfs_trans_handle *trans,
 struct btrfs_device *btrfs_find_device(struct btrfs_fs_info *fs_info, u64 devid,
 				       u8 *uuid, u8 *fsid);
 int btrfs_shrink_device(struct btrfs_device *device, u64 new_size);
-int btrfs_init_new_device(struct btrfs_fs_info *fs_info, char *path);
+int btrfs_init_new_device(struct btrfs_fs_info *fs_info, const char *path);
 int btrfs_init_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
-				  char *device_path,
+				  const char *device_path,
 				  struct btrfs_device *srcdev,
 				  struct btrfs_device **device_out);
 int btrfs_balance(struct btrfs_balance_control *bctl,
@@ -474,8 +479,8 @@ void btrfs_destroy_dev_replace_tgtdev(struct btrfs_fs_info *fs_info,
 				      struct btrfs_device *tgtdev);
 void btrfs_init_dev_replace_tgtdev_for_resume(struct btrfs_fs_info *fs_info,
 					      struct btrfs_device *tgtdev);
-void btrfs_scratch_superblocks(struct block_device *bdev, char *device_path);
-int btrfs_is_parity_mirror(struct btrfs_mapping_tree *map_tree,
+void btrfs_scratch_superblocks(struct block_device *bdev, const char *device_path);
+int btrfs_is_parity_mirror(struct btrfs_fs_info *fs_info,
 			   u64 logical, u64 len, int mirror_num);
 unsigned long btrfs_full_stripe_len(struct btrfs_fs_info *fs_info,
 				    struct btrfs_mapping_tree *map_tree,
diff --git a/fs/btrfs/xattr.c b/fs/btrfs/xattr.c
index 9621c7f2503e..2c7e53f9ff1b 100644
--- a/fs/btrfs/xattr.c
+++ b/fs/btrfs/xattr.c
@@ -47,8 +47,8 @@ ssize_t __btrfs_getxattr(struct inode *inode, const char *name,
 		return -ENOMEM;
 
 	/* lookup the xattr by name */
-	di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode), name,
-				strlen(name), 0);
+	di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(BTRFS_I(inode)),
+			name, strlen(name), 0);
 	if (!di) {
 		ret = -ENODATA;
 		goto out;
@@ -108,8 +108,8 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 	path->skip_release_on_error = 1;
 
 	if (!value) {
-		di = btrfs_lookup_xattr(trans, root, path, btrfs_ino(inode),
-					name, name_len, -1);
+		di = btrfs_lookup_xattr(trans, root, path,
+				btrfs_ino(BTRFS_I(inode)), name, name_len, -1);
 		if (!di && (flags & XATTR_REPLACE))
 			ret = -ENODATA;
 		else if (IS_ERR(di))
@@ -128,8 +128,8 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 	 */
 	if (flags & XATTR_REPLACE) {
 		ASSERT(inode_is_locked(inode));
-		di = btrfs_lookup_xattr(NULL, root, path, btrfs_ino(inode),
-					name, name_len, 0);
+		di = btrfs_lookup_xattr(NULL, root, path,
+				btrfs_ino(BTRFS_I(inode)), name, name_len, 0);
 		if (!di)
 			ret = -ENODATA;
 		else if (IS_ERR(di))
@@ -140,7 +140,7 @@ static int do_setxattr(struct btrfs_trans_handle *trans,
 		di = NULL;
 	}
 
-	ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(inode),
+	ret = btrfs_insert_xattr_item(trans, root, path, btrfs_ino(BTRFS_I(inode)),
 				      name, name_len, value, size);
 	if (ret == -EOVERFLOW) {
 		/*
@@ -278,7 +278,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 	 * NOTE: we set key.offset = 0; because we want to start with the
 	 * first xattr that we find and walk forward
 	 */
-	key.objectid = btrfs_ino(inode);
+	key.objectid = btrfs_ino(BTRFS_I(inode));
 	key.type = BTRFS_XATTR_ITEM_KEY;
 	key.offset = 0;
 
@@ -336,7 +336,7 @@ ssize_t btrfs_listxattr(struct dentry *dentry, char *buffer, size_t size)
 			u32 this_len = sizeof(*di) + name_len + data_len;
 			unsigned long name_ptr = (unsigned long)(di + 1);
 
-			if (verify_dir_item(fs_info, leaf, di)) {
+			if (verify_dir_item(fs_info, leaf, slot, di)) {
 				ret = -EIO;
 				goto err;
 			}
diff --git a/fs/btrfs/zlib.c b/fs/btrfs/zlib.c
index da497f184ff4..c248f9286366 100644
--- a/fs/btrfs/zlib.c
+++ b/fs/btrfs/zlib.c
@@ -24,12 +24,13 @@
 #include <linux/slab.h>
 #include <linux/zlib.h>
 #include <linux/zutil.h>
-#include <linux/vmalloc.h>
+#include <linux/mm.h>
 #include <linux/init.h>
 #include <linux/err.h>
 #include <linux/sched.h>
 #include <linux/pagemap.h>
 #include <linux/bio.h>
+#include <linux/refcount.h>
 #include "compression.h"
 
 struct workspace {
@@ -42,7 +43,7 @@ static void zlib_free_workspace(struct list_head *ws)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 
-	vfree(workspace->strm.workspace);
+	kvfree(workspace->strm.workspace);
 	kfree(workspace->buf);
 	kfree(workspace);
 }
@@ -52,14 +53,14 @@ static struct list_head *zlib_alloc_workspace(void)
 	struct workspace *workspace;
 	int workspacesize;
 
-	workspace = kzalloc(sizeof(*workspace), GFP_NOFS);
+	workspace = kzalloc(sizeof(*workspace), GFP_KERNEL);
 	if (!workspace)
 		return ERR_PTR(-ENOMEM);
 
 	workspacesize = max(zlib_deflate_workspacesize(MAX_WBITS, MAX_MEM_LEVEL),
 			zlib_inflate_workspacesize());
-	workspace->strm.workspace = vmalloc(workspacesize);
-	workspace->buf = kmalloc(PAGE_SIZE, GFP_NOFS);
+	workspace->strm.workspace = kvmalloc(workspacesize, GFP_KERNEL);
+	workspace->buf = kmalloc(PAGE_SIZE, GFP_KERNEL);
 	if (!workspace->strm.workspace || !workspace->buf)
 		goto fail;
 
@@ -73,13 +74,11 @@ fail:
 
 static int zlib_compress_pages(struct list_head *ws,
 			       struct address_space *mapping,
-			       u64 start, unsigned long len,
+			       u64 start,
 			       struct page **pages,
-			       unsigned long nr_dest_pages,
 			       unsigned long *out_pages,
 			       unsigned long *total_in,
-			       unsigned long *total_out,
-			       unsigned long max_out)
+			       unsigned long *total_out)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret;
@@ -89,6 +88,9 @@ static int zlib_compress_pages(struct list_head *ws,
 	struct page *in_page = NULL;
 	struct page *out_page = NULL;
 	unsigned long bytes_left;
+	unsigned long len = *total_out;
+	unsigned long nr_dest_pages = *out_pages;
+	const unsigned long max_out = nr_dest_pages * PAGE_SIZE;
 
 	*out_pages = 0;
 	*total_out = 0;
@@ -210,10 +212,7 @@ out:
 	return ret;
 }
 
-static int zlib_decompress_bio(struct list_head *ws, struct page **pages_in,
-				  u64 disk_start,
-				  struct bio *orig_bio,
-				  size_t srclen)
+static int zlib_decompress_bio(struct list_head *ws, struct compressed_bio *cb)
 {
 	struct workspace *workspace = list_entry(ws, struct workspace, list);
 	int ret = 0, ret2;
@@ -221,8 +220,12 @@ static int zlib_decompress_bio(struct list_head *ws, struct page **pages_in,
 	char *data_in;
 	size_t total_out = 0;
 	unsigned long page_in_index = 0;
+	size_t srclen = cb->compressed_len;
 	unsigned long total_pages_in = DIV_ROUND_UP(srclen, PAGE_SIZE);
 	unsigned long buf_start;
+	struct page **pages_in = cb->compressed_pages;
+	u64 disk_start = cb->start;
+	struct bio *orig_bio = cb->orig_bio;
 
 	data_in = kmap(pages_in[page_in_index]);
 	workspace->strm.next_in = data_in;
diff --git a/fs/buffer.c b/fs/buffer.c
index 0e87401cf335..5715dac7821f 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -19,6 +19,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/sched/signal.h>
 #include <linux/syscalls.h>
 #include <linux/fs.h>
 #include <linux/iomap.h>
@@ -48,8 +49,7 @@
 
 static int fsync_buffers_list(spinlock_t *lock, struct list_head *list);
 static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
-			 unsigned long bio_flags,
-			 struct writeback_control *wbc);
+			 enum rw_hint hint, struct writeback_control *wbc);
 
 #define BH_ENTRY(list) list_entry((list), struct buffer_head, b_assoc_buffers)
 
@@ -178,7 +178,7 @@ void end_buffer_write_sync(struct buffer_head *bh, int uptodate)
 		set_buffer_uptodate(bh);
 	} else {
 		buffer_io_error(bh, ", lost sync page write");
-		set_buffer_write_io_error(bh);
+		mark_buffer_write_io_error(bh);
 		clear_buffer_uptodate(bh);
 	}
 	unlock_buffer(bh);
@@ -352,8 +352,7 @@ void end_buffer_async_write(struct buffer_head *bh, int uptodate)
 		set_buffer_uptodate(bh);
 	} else {
 		buffer_io_error(bh, ", lost async page write");
-		mapping_set_error(page->mapping, -EIO);
-		set_buffer_write_io_error(bh);
+		mark_buffer_write_io_error(bh);
 		clear_buffer_uptodate(bh);
 		SetPageError(page);
 	}
@@ -481,8 +480,6 @@ static void __remove_assoc_queue(struct buffer_head *bh)
 {
 	list_del_init(&bh->b_assoc_buffers);
 	WARN_ON(!bh->b_assoc_map);
-	if (buffer_write_io_error(bh))
-		set_bit(AS_EIO, &bh->b_assoc_map->flags);
 	bh->b_assoc_map = NULL;
 }
 
@@ -1181,6 +1178,17 @@ void mark_buffer_dirty(struct buffer_head *bh)
 }
 EXPORT_SYMBOL(mark_buffer_dirty);
 
+void mark_buffer_write_io_error(struct buffer_head *bh)
+{
+	set_buffer_write_io_error(bh);
+	/* FIXME: do we need to set this in both places? */
+	if (bh->b_page && bh->b_page->mapping)
+		mapping_set_error(bh->b_page->mapping, -EIO);
+	if (bh->b_assoc_map)
+		mapping_set_error(bh->b_assoc_map, -EIO);
+}
+EXPORT_SYMBOL(mark_buffer_write_io_error);
+
 /*
  * Decrement a buffer_head's reference count.  If all buffers against a page
  * have zero reference count, are clean and unlocked, and if the page is clean
@@ -1273,44 +1281,31 @@ static inline void check_irqs_on(void)
 }
 
 /*
- * The LRU management algorithm is dopey-but-simple.  Sorry.
+ * Install a buffer_head into this cpu's LRU.  If not already in the LRU, it is
+ * inserted at the front, and the buffer_head at the back if any is evicted.
+ * Or, if already in the LRU it is moved to the front.
  */
 static void bh_lru_install(struct buffer_head *bh)
 {
-	struct buffer_head *evictee = NULL;
+	struct buffer_head *evictee = bh;
+	struct bh_lru *b;
+	int i;
 
 	check_irqs_on();
 	bh_lru_lock();
-	if (__this_cpu_read(bh_lrus.bhs[0]) != bh) {
-		struct buffer_head *bhs[BH_LRU_SIZE];
-		int in;
-		int out = 0;
 
-		get_bh(bh);
-		bhs[out++] = bh;
-		for (in = 0; in < BH_LRU_SIZE; in++) {
-			struct buffer_head *bh2 =
-				__this_cpu_read(bh_lrus.bhs[in]);
-
-			if (bh2 == bh) {
-				__brelse(bh2);
-			} else {
-				if (out >= BH_LRU_SIZE) {
-					BUG_ON(evictee != NULL);
-					evictee = bh2;
-				} else {
-					bhs[out++] = bh2;
-				}
-			}
+	b = this_cpu_ptr(&bh_lrus);
+	for (i = 0; i < BH_LRU_SIZE; i++) {
+		swap(evictee, b->bhs[i]);
+		if (evictee == bh) {
+			bh_lru_unlock();
+			return;
 		}
-		while (out < BH_LRU_SIZE)
-			bhs[out++] = NULL;
-		memcpy(this_cpu_ptr(&bh_lrus.bhs), bhs, sizeof(bhs));
 	}
-	bh_lru_unlock();
 
-	if (evictee)
-		__brelse(evictee);
+	get_bh(bh);
+	bh_lru_unlock();
+	brelse(evictee);
 }
 
 /*
@@ -1829,7 +1824,8 @@ int __block_write_full_page(struct inode *inode, struct page *page,
 	do {
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
-			submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, 0, wbc);
+			submit_bh_wbc(REQ_OP_WRITE, write_flags, bh,
+					inode->i_write_hint, wbc);
 			nr_underway++;
 		}
 		bh = next;
@@ -1883,7 +1879,8 @@ recover:
 		struct buffer_head *next = bh->b_this_page;
 		if (buffer_async_write(bh)) {
 			clear_buffer_dirty(bh);
-			submit_bh_wbc(REQ_OP_WRITE, write_flags, bh, 0, wbc);
+			submit_bh_wbc(REQ_OP_WRITE, write_flags, bh,
+					inode->i_write_hint, wbc);
 			nr_underway++;
 		}
 		bh = next;
@@ -2378,8 +2375,7 @@ int generic_cont_expand_simple(struct inode *inode, loff_t size)
 		goto out;
 
 	err = pagecache_write_begin(NULL, mapping, size, 0,
-				AOP_FLAG_UNINTERRUPTIBLE|AOP_FLAG_CONT_EXPAND,
-				&page, &fsdata);
+				    AOP_FLAG_CONT_EXPAND, &page, &fsdata);
 	if (err)
 		goto out;
 
@@ -2395,7 +2391,7 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 			    loff_t pos, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
-	unsigned blocksize = 1 << inode->i_blkbits;
+	unsigned int blocksize = i_blocksize(inode);
 	struct page *page;
 	void *fsdata;
 	pgoff_t index, curidx;
@@ -2414,9 +2410,8 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		}
 		len = PAGE_SIZE - zerofrom;
 
-		err = pagecache_write_begin(file, mapping, curpos, len,
-						AOP_FLAG_UNINTERRUPTIBLE,
-						&page, &fsdata);
+		err = pagecache_write_begin(file, mapping, curpos, len, 0,
+					    &page, &fsdata);
 		if (err)
 			goto out;
 		zero_user(page, zerofrom, len);
@@ -2448,9 +2443,8 @@ static int cont_expand_zero(struct file *file, struct address_space *mapping,
 		}
 		len = offset - zerofrom;
 
-		err = pagecache_write_begin(file, mapping, curpos, len,
-						AOP_FLAG_UNINTERRUPTIBLE,
-						&page, &fsdata);
+		err = pagecache_write_begin(file, mapping, curpos, len, 0,
+					    &page, &fsdata);
 		if (err)
 			goto out;
 		zero_user(page, zerofrom, len);
@@ -2475,8 +2469,8 @@ int cont_write_begin(struct file *file, struct address_space *mapping,
 			get_block_t *get_block, loff_t *bytes)
 {
 	struct inode *inode = mapping->host;
-	unsigned blocksize = 1 << inode->i_blkbits;
-	unsigned zerofrom;
+	unsigned int blocksize = i_blocksize(inode);
+	unsigned int zerofrom;
 	int err;
 
 	err = cont_expand_zero(file, mapping, pos, bytes);
@@ -2838,7 +2832,7 @@ int nobh_truncate_page(struct address_space *mapping,
 	struct buffer_head map_bh;
 	int err;
 
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	length = offset & (blocksize - 1);
 
 	/* Block boundary? Nothing to do */
@@ -2916,7 +2910,7 @@ int block_truncate_page(struct address_space *mapping,
 	struct buffer_head *bh;
 	int err;
 
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	length = offset & (blocksize - 1);
 
 	/* Block boundary? Nothing to do */
@@ -3024,11 +3018,11 @@ EXPORT_SYMBOL(block_write_full_page);
 sector_t generic_block_bmap(struct address_space *mapping, sector_t block,
 			    get_block_t *get_block)
 {
-	struct buffer_head tmp;
 	struct inode *inode = mapping->host;
-	tmp.b_state = 0;
-	tmp.b_blocknr = 0;
-	tmp.b_size = 1 << inode->i_blkbits;
+	struct buffer_head tmp = {
+		.b_size = i_blocksize(inode),
+	};
+
 	get_block(inode, block, &tmp, 0);
 	return tmp.b_blocknr;
 }
@@ -3041,7 +3035,7 @@ static void end_bio_bh_io_sync(struct bio *bio)
 	if (unlikely(bio_flagged(bio, BIO_QUIET)))
 		set_bit(BH_Quiet, &bh->b_state);
 
-	bh->b_end_io(bh, !bio->bi_error);
+	bh->b_end_io(bh, !bio->bi_status);
 	bio_put(bio);
 }
 
@@ -3094,7 +3088,7 @@ void guard_bio_eod(int op, struct bio *bio)
 }
 
 static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
-			 unsigned long bio_flags, struct writeback_control *wbc)
+			 enum rw_hint write_hint, struct writeback_control *wbc)
 {
 	struct bio *bio;
 
@@ -3123,13 +3117,13 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
 
 	bio->bi_iter.bi_sector = bh->b_blocknr * (bh->b_size >> 9);
 	bio->bi_bdev = bh->b_bdev;
+	bio->bi_write_hint = write_hint;
 
 	bio_add_page(bio, bh->b_page, bh->b_size, bh_offset(bh));
 	BUG_ON(bio->bi_iter.bi_size != bh->b_size);
 
 	bio->bi_end_io = end_bio_bh_io_sync;
 	bio->bi_private = bh;
-	bio->bi_flags |= bio_flags;
 
 	/* Take care of bh's that straddle the end of the device */
 	guard_bio_eod(op, bio);
@@ -3144,14 +3138,7 @@ static int submit_bh_wbc(int op, int op_flags, struct buffer_head *bh,
 	return 0;
 }
 
-int _submit_bh(int op, int op_flags, struct buffer_head *bh,
-	       unsigned long bio_flags)
-{
-	return submit_bh_wbc(op, op_flags, bh, bio_flags, NULL);
-}
-EXPORT_SYMBOL_GPL(_submit_bh);
-
-int submit_bh(int op, int op_flags,  struct buffer_head *bh)
+int submit_bh(int op, int op_flags, struct buffer_head *bh)
 {
 	return submit_bh_wbc(op, op_flags, bh, 0, NULL);
 }
@@ -3290,8 +3277,6 @@ drop_buffers(struct page *page, struct buffer_head **buffers_to_free)
 
 	bh = head;
 	do {
-		if (buffer_write_io_error(bh) && page->mapping)
-			mapping_set_error(page->mapping, -EIO);
 		if (buffer_busy(bh))
 			goto failed;
 		bh = bh->b_this_page;
@@ -3503,6 +3488,130 @@ int bh_submit_read(struct buffer_head *bh)
 }
 EXPORT_SYMBOL(bh_submit_read);
 
+/*
+ * Seek for SEEK_DATA / SEEK_HOLE within @page, starting at @lastoff.
+ *
+ * Returns the offset within the file on success, and -ENOENT otherwise.
+ */
+static loff_t
+page_seek_hole_data(struct page *page, loff_t lastoff, int whence)
+{
+	loff_t offset = page_offset(page);
+	struct buffer_head *bh, *head;
+	bool seek_data = whence == SEEK_DATA;
+
+	if (lastoff < offset)
+		lastoff = offset;
+
+	bh = head = page_buffers(page);
+	do {
+		offset += bh->b_size;
+		if (lastoff >= offset)
+			continue;
+
+		/*
+		 * Unwritten extents that have data in the page cache covering
+		 * them can be identified by the BH_Unwritten state flag.
+		 * Pages with multiple buffers might have a mix of holes, data
+		 * and unwritten extents - any buffer with valid data in it
+		 * should have BH_Uptodate flag set on it.
+		 */
+
+		if ((buffer_unwritten(bh) || buffer_uptodate(bh)) == seek_data)
+			return lastoff;
+
+		lastoff = offset;
+	} while ((bh = bh->b_this_page) != head);
+	return -ENOENT;
+}
+
+/*
+ * Seek for SEEK_DATA / SEEK_HOLE in the page cache.
+ *
+ * Within unwritten extents, the page cache determines which parts are holes
+ * and which are data: unwritten and uptodate buffer heads count as data;
+ * everything else counts as a hole.
+ *
+ * Returns the resulting offset on successs, and -ENOENT otherwise.
+ */
+loff_t
+page_cache_seek_hole_data(struct inode *inode, loff_t offset, loff_t length,
+			  int whence)
+{
+	pgoff_t index = offset >> PAGE_SHIFT;
+	pgoff_t end = DIV_ROUND_UP(offset + length, PAGE_SIZE);
+	loff_t lastoff = offset;
+	struct pagevec pvec;
+
+	if (length <= 0)
+		return -ENOENT;
+
+	pagevec_init(&pvec, 0);
+
+	do {
+		unsigned want, nr_pages, i;
+
+		want = min_t(unsigned, end - index, PAGEVEC_SIZE);
+		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index, want);
+		if (nr_pages == 0)
+			break;
+
+		for (i = 0; i < nr_pages; i++) {
+			struct page *page = pvec.pages[i];
+
+			/*
+			 * At this point, the page may be truncated or
+			 * invalidated (changing page->mapping to NULL), or
+			 * even swizzled back from swapper_space to tmpfs file
+			 * mapping.  However, page->index will not change
+			 * because we have a reference on the page.
+                         *
+			 * If current page offset is beyond where we've ended,
+			 * we've found a hole.
+                         */
+			if (whence == SEEK_HOLE &&
+			    lastoff < page_offset(page))
+				goto check_range;
+
+			/* Searching done if the page index is out of range. */
+			if (page->index >= end)
+				goto not_found;
+
+			lock_page(page);
+			if (likely(page->mapping == inode->i_mapping) &&
+			    page_has_buffers(page)) {
+				lastoff = page_seek_hole_data(page, lastoff, whence);
+				if (lastoff >= 0) {
+					unlock_page(page);
+					goto check_range;
+				}
+			}
+			unlock_page(page);
+			lastoff = page_offset(page) + PAGE_SIZE;
+		}
+
+		/* Searching done if fewer pages returned than wanted. */
+		if (nr_pages < want)
+			break;
+
+		index = pvec.pages[i - 1]->index + 1;
+		pagevec_release(&pvec);
+	} while (index < end);
+
+	/* When no page at lastoff and we are not done, we found a hole. */
+	if (whence != SEEK_HOLE)
+		goto not_found;
+
+check_range:
+	if (lastoff < offset + length)
+		goto out;
+not_found:
+	lastoff = -ENOENT;
+out:
+	pagevec_release(&pvec);
+	return lastoff;
+}
+
 void __init buffer_init(void)
 {
 	unsigned long nrpages;
diff --git a/fs/cachefiles/internal.h b/fs/cachefiles/internal.h
index cd1effee8a49..bb3a02ca9da4 100644
--- a/fs/cachefiles/internal.h
+++ b/fs/cachefiles/internal.h
@@ -18,7 +18,8 @@
 
 #include <linux/fscache-cache.h>
 #include <linux/timer.h>
-#include <linux/wait.h>
+#include <linux/wait_bit.h>
+#include <linux/cred.h>
 #include <linux/workqueue.h>
 #include <linux/security.h>
 
@@ -96,7 +97,7 @@ struct cachefiles_cache {
  * backing file read tracking
  */
 struct cachefiles_one_read {
-	wait_queue_t			monitor;	/* link into monitored waitqueue */
+	wait_queue_entry_t			monitor;	/* link into monitored waitqueue */
 	struct page			*back_page;	/* backing file page we're waiting for */
 	struct page			*netfs_page;	/* netfs page we're going to fill */
 	struct fscache_retrieval	*op;		/* retrieval op covering this */
diff --git a/fs/cachefiles/namei.c b/fs/cachefiles/namei.c
index 41df8a27d7eb..3978b324cbca 100644
--- a/fs/cachefiles/namei.c
+++ b/fs/cachefiles/namei.c
@@ -204,7 +204,7 @@ wait_for_old_object:
 		wait_queue_head_t *wq;
 
 		signed long timeout = 60 * HZ;
-		wait_queue_t wait;
+		wait_queue_entry_t wait;
 		bool requeue;
 
 		/* if the object we're waiting for is queued for processing,
diff --git a/fs/cachefiles/rdwr.c b/fs/cachefiles/rdwr.c
index afbdc418966d..18d7aa61ef0f 100644
--- a/fs/cachefiles/rdwr.c
+++ b/fs/cachefiles/rdwr.c
@@ -21,7 +21,7 @@
  * - we use this to detect read completion of backing pages
  * - the caller holds the waitqueue lock
  */
-static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode,
+static int cachefiles_read_waiter(wait_queue_entry_t *wait, unsigned mode,
 				  int sync, void *_key)
 {
 	struct cachefiles_one_read *monitor =
@@ -48,7 +48,7 @@ static int cachefiles_read_waiter(wait_queue_t *wait, unsigned mode,
 	}
 
 	/* remove from the waitqueue */
-	list_del(&wait->task_list);
+	list_del(&wait->entry);
 
 	/* move onto the action list and queue for FS-Cache thread pool */
 	ASSERT(monitor->op);
diff --git a/fs/ceph/acl.c b/fs/ceph/acl.c
index 987044bca1c2..59cb307b15fb 100644
--- a/fs/ceph/acl.c
+++ b/fs/ceph/acl.c
@@ -131,6 +131,7 @@ int ceph_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	}
 
 	if (new_mode != old_mode) {
+		newattrs.ia_ctime = current_time(inode);
 		newattrs.ia_mode = new_mode;
 		newattrs.ia_valid = ATTR_MODE;
 		ret = __ceph_setattr(inode, &newattrs);
diff --git a/fs/ceph/addr.c b/fs/ceph/addr.c
index e4b066cd912a..50836280a6f8 100644
--- a/fs/ceph/addr.c
+++ b/fs/ceph/addr.c
@@ -8,6 +8,7 @@
 #include <linux/slab.h>
 #include <linux/pagevec.h>
 #include <linux/task_io_accounting_ops.h>
+#include <linux/signal.h>
 
 #include "super.h"
 #include "mds_client.h"
@@ -391,6 +392,7 @@ static int start_read(struct inode *inode, struct list_head *page_list, int max)
 			nr_pages = i;
 			if (nr_pages > 0) {
 				len = nr_pages << PAGE_SHIFT;
+				osd_req_op_extent_update(req, 0, len);
 				break;
 			}
 			goto out_pages;
@@ -528,14 +530,10 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	long writeback_stat;
 	u64 truncate_size;
 	u32 truncate_seq;
-	int err = 0, len = PAGE_SIZE;
+	int err, len = PAGE_SIZE;
 
 	dout("writepage %p idx %lu\n", page, page->index);
 
-	if (!page->mapping || !page->mapping->host) {
-		dout("writepage %p - no mapping\n", page);
-		return -EFAULT;
-	}
 	inode = page->mapping->host;
 	ci = ceph_inode(inode);
 	fsc = ceph_inode_to_client(inode);
@@ -545,7 +543,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	snapc = page_snap_context(page);
 	if (snapc == NULL) {
 		dout("writepage %p page %p not dirty?\n", inode, page);
-		goto out;
+		return 0;
 	}
 	oldest = get_oldest_context(inode, &snap_size,
 				    &truncate_size, &truncate_seq);
@@ -553,9 +551,10 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 		dout("writepage %p page %p snapc %p not writeable - noop\n",
 		     inode, page, snapc);
 		/* we should only noop if called by kswapd */
-		WARN_ON((current->flags & PF_MEMALLOC) == 0);
+		WARN_ON(!(current->flags & PF_MEMALLOC));
 		ceph_put_snap_context(oldest);
-		goto out;
+		redirty_page_for_writepage(wbc, page);
+		return 0;
 	}
 	ceph_put_snap_context(oldest);
 
@@ -565,8 +564,9 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	/* is this a partial page at end of file? */
 	if (page_off >= snap_size) {
 		dout("%p page eof %llu\n", page, snap_size);
-		goto out;
+		return 0;
 	}
+
 	if (snap_size < page_off + len)
 		len = snap_size - page_off;
 
@@ -576,7 +576,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	writeback_stat = atomic_long_inc_return(&fsc->writeback_count);
 	if (writeback_stat >
 	    CONGESTION_ON_THRESH(fsc->mount_options->congestion_kb))
-		set_bdi_congested(&fsc->backing_dev_info, BLK_RW_ASYNC);
+		set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
 
 	set_page_writeback(page);
 	err = ceph_osdc_writepages(osdc, ceph_vino(inode),
@@ -593,7 +593,7 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 			dout("writepage interrupted page %p\n", page);
 			redirty_page_for_writepage(wbc, page);
 			end_page_writeback(page);
-			goto out;
+			return err;
 		}
 		dout("writepage setting page/mapping error %d %p\n",
 		     err, page);
@@ -609,7 +609,6 @@ static int writepage_nounlock(struct page *page, struct writeback_control *wbc)
 	end_page_writeback(page);
 	ceph_put_wrbuffer_cap_refs(ci, 1, snapc);
 	ceph_put_snap_context(snapc);  /* page's reference */
-out:
 	return err;
 }
 
@@ -668,8 +667,12 @@ static void writepages_finish(struct ceph_osd_request *req)
 	bool remove_page;
 
 	dout("writepages_finish %p rc %d\n", inode, rc);
-	if (rc < 0)
+	if (rc < 0) {
 		mapping_set_error(mapping, rc);
+		ceph_set_error_write(ci);
+	} else {
+		ceph_clear_error_write(ci);
+	}
 
 	/*
 	 * We lost the cache cap, need to truncate the page before
@@ -698,12 +701,9 @@ static void writepages_finish(struct ceph_osd_request *req)
 			if (atomic_long_dec_return(&fsc->writeback_count) <
 			     CONGESTION_OFF_THRESH(
 					fsc->mount_options->congestion_kb))
-				clear_bdi_congested(&fsc->backing_dev_info,
+				clear_bdi_congested(inode_to_bdi(inode),
 						    BLK_RW_ASYNC);
 
-			if (rc < 0)
-				SetPageError(page);
-
 			ceph_put_snap_context(page_snap_context(page));
 			page->private = 0;
 			ClearPagePrivate(page);
@@ -751,7 +751,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	struct pagevec pvec;
 	int done = 0;
 	int rc = 0;
-	unsigned wsize = 1 << inode->i_blkbits;
+	unsigned int wsize = i_blocksize(inode);
 	struct ceph_osd_request *req = NULL;
 	int do_sync = 0;
 	loff_t snap_size, i_size;
@@ -771,7 +771,7 @@ static int ceph_writepages_start(struct address_space *mapping,
 	     wbc->sync_mode == WB_SYNC_NONE ? "NONE" :
 	     (wbc->sync_mode == WB_SYNC_ALL ? "ALL" : "HOLD"));
 
-	if (ACCESS_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+	if (READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
 		if (ci->i_wrbuffer_ref > 0) {
 			pr_warn_ratelimited(
 				"writepage_start %p %lld forced umount\n",
@@ -977,7 +977,7 @@ get_more_pages:
 			if (atomic_long_inc_return(&fsc->writeback_count) >
 			    CONGESTION_ON_THRESH(
 				    fsc->mount_options->congestion_kb)) {
-				set_bdi_congested(&fsc->backing_dev_info,
+				set_bdi_congested(inode_to_bdi(inode),
 						  BLK_RW_ASYNC);
 			}
 
@@ -1017,8 +1017,7 @@ new_request:
 					&ci->i_layout, vino,
 					offset, &len, 0, num_ops,
 					CEPH_OSD_OP_WRITE,
-					CEPH_OSD_FLAG_WRITE |
-					CEPH_OSD_FLAG_ONDISK,
+					CEPH_OSD_FLAG_WRITE,
 					snapc, truncate_seq,
 					truncate_size, false);
 		if (IS_ERR(req)) {
@@ -1028,8 +1027,7 @@ new_request:
 						min(num_ops,
 						    CEPH_OSD_SLAB_OPS),
 						CEPH_OSD_OP_WRITE,
-						CEPH_OSD_FLAG_WRITE |
-						CEPH_OSD_FLAG_ONDISK,
+						CEPH_OSD_FLAG_WRITE,
 						snapc, truncate_seq,
 						truncate_size, true);
 			BUG_ON(IS_ERR(req));
@@ -1194,7 +1192,7 @@ static int ceph_update_writeable_page(struct file *file,
 	int r;
 	struct ceph_snap_context *snapc, *oldest;
 
-	if (ACCESS_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+	if (READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
 		dout(" page %p forced umount\n", page);
 		unlock_page(page);
 		return -EIO;
@@ -1317,7 +1315,7 @@ static int ceph_write_end(struct file *file, struct address_space *mapping,
 			  struct page *page, void *fsdata)
 {
 	struct inode *inode = file_inode(file);
-	int check_cap = 0;
+	bool check_cap = false;
 
 	dout("write_end file %p inode %p page %p %d~%d (%d)\n", file,
 	     inode, page, (int)pos, (int)copied, (int)len);
@@ -1386,8 +1384,9 @@ static void ceph_restore_sigs(sigset_t *oldset)
 /*
  * vm ops
  */
-static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int ceph_filemap_fault(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_file_info *fi = vma->vm_file->private_data;
@@ -1416,7 +1415,7 @@ static int ceph_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if ((got & (CEPH_CAP_FILE_CACHE | CEPH_CAP_FILE_LAZYIO)) ||
 	    ci->i_inline_version == CEPH_INLINE_NONE) {
 		current->journal_info = vma->vm_file;
-		ret = filemap_fault(vma, vmf);
+		ret = filemap_fault(vmf);
 		current->journal_info = NULL;
 	} else
 		ret = -EAGAIN;
@@ -1477,8 +1476,9 @@ out_restore:
 /*
  * Reuse write_begin here for simplicity.
  */
-static int ceph_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int ceph_page_mkwrite(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	struct ceph_file_info *fi = vma->vm_file->private_data;
@@ -1679,8 +1679,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 				    ceph_vino(inode), 0, &len, 0, 1,
-				    CEPH_OSD_OP_CREATE,
-				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
+				    CEPH_OSD_OP_CREATE, CEPH_OSD_FLAG_WRITE,
 				    NULL, 0, 0, false);
 	if (IS_ERR(req)) {
 		err = PTR_ERR(req);
@@ -1697,8 +1696,7 @@ int ceph_uninline_data(struct file *filp, struct page *locked_page)
 
 	req = ceph_osdc_new_request(&fsc->client->osdc, &ci->i_layout,
 				    ceph_vino(inode), 0, &len, 1, 3,
-				    CEPH_OSD_OP_WRITE,
-				    CEPH_OSD_FLAG_ONDISK | CEPH_OSD_FLAG_WRITE,
+				    CEPH_OSD_OP_WRITE, CEPH_OSD_FLAG_WRITE,
 				    NULL, ci->i_truncate_seq,
 				    ci->i_truncate_size, false);
 	if (IS_ERR(req)) {
@@ -1871,7 +1869,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 		goto out_unlock;
 	}
 
-	wr_req->r_flags = CEPH_OSD_FLAG_WRITE | CEPH_OSD_FLAG_ACK;
+	wr_req->r_flags = CEPH_OSD_FLAG_WRITE;
 	osd_req_op_init(wr_req, 0, CEPH_OSD_OP_CREATE, CEPH_OSD_OP_FLAG_EXCL);
 	ceph_oloc_copy(&wr_req->r_base_oloc, &rd_req->r_base_oloc);
 	ceph_oid_copy(&wr_req->r_base_oid, &rd_req->r_base_oid);
@@ -1892,6 +1890,7 @@ static int __ceph_pool_perm_get(struct ceph_inode_info *ci,
 	err = ceph_osdc_start_request(&fsc->client->osdc, rd_req, false);
 
 	wr_req->r_mtime = ci->vfs_inode.i_mtime;
+	wr_req->r_abort_on_full = true;
 	err2 = ceph_osdc_start_request(&fsc->client->osdc, wr_req, false);
 
 	if (!err)
diff --git a/fs/ceph/cache.c b/fs/ceph/cache.c
index 5bc5d37b1217..fd1172823f86 100644
--- a/fs/ceph/cache.c
+++ b/fs/ceph/cache.c
@@ -35,18 +35,34 @@ struct fscache_netfs ceph_cache_netfs = {
 	.version	= 0,
 };
 
+static DEFINE_MUTEX(ceph_fscache_lock);
+static LIST_HEAD(ceph_fscache_list);
+
+struct ceph_fscache_entry {
+	struct list_head list;
+	struct fscache_cookie *fscache;
+	struct ceph_fsid fsid;
+	size_t uniq_len;
+	char uniquifier[0];
+};
+
 static uint16_t ceph_fscache_session_get_key(const void *cookie_netfs_data,
 					     void *buffer, uint16_t maxbuf)
 {
 	const struct ceph_fs_client* fsc = cookie_netfs_data;
-	uint16_t klen;
+	const char *fscache_uniq = fsc->mount_options->fscache_uniq;
+	uint16_t fsid_len, uniq_len;
 
-	klen = sizeof(fsc->client->fsid);
-	if (klen > maxbuf)
+	fsid_len = sizeof(fsc->client->fsid);
+	uniq_len = fscache_uniq ? strlen(fscache_uniq) : 0;
+	if (fsid_len + uniq_len > maxbuf)
 		return 0;
 
-	memcpy(buffer, &fsc->client->fsid, klen);
-	return klen;
+	memcpy(buffer, &fsc->client->fsid, fsid_len);
+	if (uniq_len)
+		memcpy(buffer + fsid_len, fscache_uniq, uniq_len);
+
+	return fsid_len + uniq_len;
 }
 
 static const struct fscache_cookie_def ceph_fscache_fsid_object_def = {
@@ -67,13 +83,54 @@ void ceph_fscache_unregister(void)
 
 int ceph_fscache_register_fs(struct ceph_fs_client* fsc)
 {
+	const struct ceph_fsid *fsid = &fsc->client->fsid;
+	const char *fscache_uniq = fsc->mount_options->fscache_uniq;
+	size_t uniq_len = fscache_uniq ? strlen(fscache_uniq) : 0;
+	struct ceph_fscache_entry *ent;
+	int err = 0;
+
+	mutex_lock(&ceph_fscache_lock);
+	list_for_each_entry(ent, &ceph_fscache_list, list) {
+		if (memcmp(&ent->fsid, fsid, sizeof(*fsid)))
+			continue;
+		if (ent->uniq_len != uniq_len)
+			continue;
+		if (uniq_len && memcmp(ent->uniquifier, fscache_uniq, uniq_len))
+			continue;
+
+		pr_err("fscache cookie already registered for fsid %pU\n", fsid);
+		pr_err("  use fsc=%%s mount option to specify a uniquifier\n");
+		err = -EBUSY;
+		goto out_unlock;
+	}
+
+	ent = kzalloc(sizeof(*ent) + uniq_len, GFP_KERNEL);
+	if (!ent) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+
 	fsc->fscache = fscache_acquire_cookie(ceph_cache_netfs.primary_index,
 					      &ceph_fscache_fsid_object_def,
 					      fsc, true);
-	if (!fsc->fscache)
-		pr_err("Unable to register fsid: %p fscache cookie\n", fsc);
 
-	return 0;
+	if (fsc->fscache) {
+		memcpy(&ent->fsid, fsid, sizeof(*fsid));
+		if (uniq_len > 0) {
+			memcpy(&ent->uniquifier, fscache_uniq, uniq_len);
+			ent->uniq_len = uniq_len;
+		}
+		ent->fscache = fsc->fscache;
+		list_add_tail(&ent->list, &ceph_fscache_list);
+	} else {
+		kfree(ent);
+		pr_err("unable to register fscache cookie for fsid %pU\n",
+		       fsid);
+		/* all other fs ignore this error */
+	}
+out_unlock:
+	mutex_unlock(&ceph_fscache_lock);
+	return err;
 }
 
 static uint16_t ceph_fscache_inode_get_key(const void *cookie_netfs_data,
@@ -234,7 +291,7 @@ void ceph_fscache_file_set_cookie(struct inode *inode, struct file *filp)
 		fscache_enable_cookie(ci->fscache, ceph_fscache_can_enable,
 				inode);
 		if (fscache_cookie_enabled(ci->fscache)) {
-			dout("fscache_file_set_cookie %p %p enabing cache\n",
+			dout("fscache_file_set_cookie %p %p enabling cache\n",
 			     inode, filp);
 		}
 	}
@@ -349,7 +406,24 @@ void ceph_invalidate_fscache_page(struct inode* inode, struct page *page)
 
 void ceph_fscache_unregister_fs(struct ceph_fs_client* fsc)
 {
-	fscache_relinquish_cookie(fsc->fscache, 0);
+	if (fscache_cookie_valid(fsc->fscache)) {
+		struct ceph_fscache_entry *ent;
+		bool found = false;
+
+		mutex_lock(&ceph_fscache_lock);
+		list_for_each_entry(ent, &ceph_fscache_list, list) {
+			if (ent->fscache == fsc->fscache) {
+				list_del(&ent->list);
+				kfree(ent);
+				found = true;
+				break;
+			}
+		}
+		WARN_ON_ONCE(!found);
+		mutex_unlock(&ceph_fscache_lock);
+
+		__fscache_relinquish_cookie(fsc->fscache, 0);
+	}
 	fsc->fscache = NULL;
 }
 
diff --git a/fs/ceph/caps.c b/fs/ceph/caps.c
index 94fd76d04683..7007ae2a5ad2 100644
--- a/fs/ceph/caps.c
+++ b/fs/ceph/caps.c
@@ -2,7 +2,7 @@
 
 #include <linux/fs.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/wait.h>
@@ -867,7 +867,7 @@ int __ceph_caps_file_wanted(struct ceph_inode_info *ci)
 /*
  * Return caps we have registered with the MDS(s) as 'wanted'.
  */
-int __ceph_caps_mds_wanted(struct ceph_inode_info *ci)
+int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check)
 {
 	struct ceph_cap *cap;
 	struct rb_node *p;
@@ -875,7 +875,7 @@ int __ceph_caps_mds_wanted(struct ceph_inode_info *ci)
 
 	for (p = rb_first(&ci->i_caps); p; p = rb_next(p)) {
 		cap = rb_entry(p, struct ceph_cap, ci_node);
-		if (!__cap_is_valid(cap))
+		if (check && !__cap_is_valid(cap))
 			continue;
 		if (cap == ci->i_auth_cap)
 			mds_wanted |= cap->mds_wanted;
@@ -1015,6 +1015,7 @@ static int send_cap_msg(struct cap_msg_args *arg)
 	void *p;
 	size_t extra_len;
 	struct timespec zerotime = {0};
+	struct ceph_osd_client *osdc = &arg->session->s_mdsc->fsc->client->osdc;
 
 	dout("send_cap_msg %s %llx %llx caps %s wanted %s dirty %s"
 	     " seq %u/%u tid %llu/%llu mseq %u follows %lld size %llu/%llu"
@@ -1076,8 +1077,12 @@ static int send_cap_msg(struct cap_msg_args *arg)
 	ceph_encode_64(&p, arg->inline_data ? 0 : CEPH_INLINE_NONE);
 	/* inline data size */
 	ceph_encode_32(&p, 0);
-	/* osd_epoch_barrier (version 5) */
-	ceph_encode_32(&p, 0);
+	/*
+	 * osd_epoch_barrier (version 5)
+	 * The epoch_barrier is protected osdc->lock, so READ_ONCE here in
+	 * case it was recently changed
+	 */
+	ceph_encode_32(&p, READ_ONCE(osdc->epoch_barrier));
 	/* oldest_flush_tid (version 6) */
 	ceph_encode_64(&p, arg->oldest_flush_tid);
 
@@ -1184,6 +1189,13 @@ static int __send_cap(struct ceph_mds_client *mdsc, struct ceph_cap *cap,
 		delayed = 1;
 	}
 	ci->i_ceph_flags &= ~(CEPH_I_NODELAY | CEPH_I_FLUSH);
+	if (want & ~cap->mds_wanted) {
+		/* user space may open/close single file frequently.
+		 * This avoids droping mds_wanted immediately after
+		 * requesting new mds_wanted.
+		 */
+		__cap_set_timeouts(mdsc, ci);
+	}
 
 	cap->issued &= retain;  /* drop bits we don't want */
 	if (cap->implemented & ~cap->issued) {
@@ -1382,7 +1394,7 @@ static void __ceph_flush_snaps(struct ceph_inode_info *ci,
 		first_tid = cf->tid + 1;
 
 		capsnap = container_of(cf, struct ceph_cap_snap, cap_flush);
-		atomic_inc(&capsnap->nref);
+		refcount_inc(&capsnap->nref);
 		spin_unlock(&ci->i_ceph_lock);
 
 		dout("__flush_snaps %p capsnap %p tid %llu %s\n",
@@ -1641,6 +1653,21 @@ static int try_nonblocking_invalidate(struct inode *inode)
 	return -1;
 }
 
+bool __ceph_should_report_size(struct ceph_inode_info *ci)
+{
+	loff_t size = ci->vfs_inode.i_size;
+	/* mds will adjust max size according to the reported size */
+	if (ci->i_flushing_caps & CEPH_CAP_FILE_WR)
+		return false;
+	if (size >= ci->i_max_size)
+		return true;
+	/* half of previous max_size increment has been used */
+	if (ci->i_max_size > ci->i_reported_size &&
+	    (size << 1) >= ci->i_max_size + ci->i_reported_size)
+		return true;
+	return false;
+}
+
 /*
  * Swiss army knife function to examine currently used and wanted
  * versus held caps.  Release, flush, ack revoked caps to mds as
@@ -1794,8 +1821,7 @@ retry_locked:
 			}
 
 			/* approaching file_max? */
-			if ((inode->i_size << 1) >= ci->i_max_size &&
-			    (ci->i_reported_size << 1) < ci->i_max_size) {
+			if (__ceph_should_report_size(ci)) {
 				dout("i_size approaching max_size\n");
 				goto ack;
 			}
@@ -2084,8 +2110,6 @@ int ceph_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 
 	dout("fsync %p%s\n", inode, datasync ? " datasync" : "");
 
-	ceph_sync_write_wait(inode);
-
 	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
 	if (ret < 0)
 		goto out;
@@ -2197,7 +2221,7 @@ static void __kick_flushing_caps(struct ceph_mds_client *mdsc,
 			     inode, capsnap, cf->tid,
 			     ceph_cap_string(capsnap->dirty));
 
-			atomic_inc(&capsnap->nref);
+			refcount_inc(&capsnap->nref);
 			spin_unlock(&ci->i_ceph_lock);
 
 			ret = __send_flush_snap(inode, session, capsnap, cap->mseq,
@@ -2477,23 +2501,22 @@ again:
 
 		if (ci->i_ceph_flags & CEPH_I_CAP_DROPPED) {
 			int mds_wanted;
-			if (ACCESS_ONCE(mdsc->fsc->mount_state) ==
+			if (READ_ONCE(mdsc->fsc->mount_state) ==
 			    CEPH_MOUNT_SHUTDOWN) {
 				dout("get_cap_refs %p forced umount\n", inode);
 				*err = -EIO;
 				ret = 1;
 				goto out_unlock;
 			}
-			mds_wanted = __ceph_caps_mds_wanted(ci);
-			if ((mds_wanted & need) != need) {
+			mds_wanted = __ceph_caps_mds_wanted(ci, false);
+			if (need & ~(mds_wanted & need)) {
 				dout("get_cap_refs %p caps were dropped"
 				     " (session killed?)\n", inode);
 				*err = -ESTALE;
 				ret = 1;
 				goto out_unlock;
 			}
-			if ((mds_wanted & file_wanted) ==
-			    (file_wanted & (CEPH_CAP_FILE_RD|CEPH_CAP_FILE_WR)))
+			if (!(file_wanted & ~mds_wanted))
 				ci->i_ceph_flags &= ~CEPH_I_CAP_DROPPED;
 		}
 
@@ -3018,8 +3041,10 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 					le32_to_cpu(grant->truncate_seq),
 					le64_to_cpu(grant->truncate_size),
 					size);
-		/* max size increase? */
-		if (ci->i_auth_cap == cap && max_size != ci->i_max_size) {
+	}
+
+	if (ci->i_auth_cap == cap && (newcaps & CEPH_CAP_ANY_FILE_WR)) {
+		if (max_size != ci->i_max_size) {
 			dout("max_size %lld -> %llu\n",
 			     ci->i_max_size, max_size);
 			ci->i_max_size = max_size;
@@ -3028,6 +3053,10 @@ static void handle_cap_grant(struct ceph_mds_client *mdsc,
 				ci->i_requested_max_size = 0;
 			}
 			wake = true;
+		} else if (ci->i_wanted_max_size > ci->i_max_size &&
+			   ci->i_wanted_max_size > ci->i_requested_max_size) {
+			/* CEPH_CAP_OP_IMPORT */
+			wake = true;
 		}
 	}
 
@@ -3404,6 +3433,7 @@ retry:
 			tcap->implemented |= issued;
 			if (cap == ci->i_auth_cap)
 				ci->i_auth_cap = tcap;
+
 			if (!list_empty(&ci->i_cap_flush_list) &&
 			    ci->i_auth_cap == tcap) {
 				spin_lock(&mdsc->cap_dirty_lock);
@@ -3417,9 +3447,18 @@ retry:
 	} else if (tsession) {
 		/* add placeholder for the export tagert */
 		int flag = (cap == ci->i_auth_cap) ? CEPH_CAP_FLAG_AUTH : 0;
+		tcap = new_cap;
 		ceph_add_cap(inode, tsession, t_cap_id, -1, issued, 0,
 			     t_seq - 1, t_mseq, (u64)-1, flag, &new_cap);
 
+		if (!list_empty(&ci->i_cap_flush_list) &&
+		    ci->i_auth_cap == tcap) {
+			spin_lock(&mdsc->cap_dirty_lock);
+			list_move_tail(&ci->i_flushing_item,
+				       &tcap->session->s_cap_flushing);
+			spin_unlock(&mdsc->cap_dirty_lock);
+		}
+
 		__ceph_remove_cap(cap, false);
 		goto out_unlock;
 	}
@@ -3535,7 +3574,6 @@ retry:
 	}
 
 	/* make sure we re-request max_size, if necessary */
-	ci->i_wanted_max_size = 0;
 	ci->i_requested_max_size = 0;
 
 	*old_issued = issued;
@@ -3619,13 +3657,19 @@ void ceph_handle_caps(struct ceph_mds_session *session,
 		p += inline_len;
 	}
 
+	if (le16_to_cpu(msg->hdr.version) >= 5) {
+		struct ceph_osd_client	*osdc = &mdsc->fsc->client->osdc;
+		u32			epoch_barrier;
+
+		ceph_decode_32_safe(&p, end, epoch_barrier, bad);
+		ceph_osdc_update_epoch_barrier(osdc, epoch_barrier);
+	}
+
 	if (le16_to_cpu(msg->hdr.version) >= 8) {
 		u64 flush_tid;
 		u32 caller_uid, caller_gid;
-		u32 osd_epoch_barrier;
 		u32 pool_ns_len;
-		/* version >= 5 */
-		ceph_decode_32_safe(&p, end, osd_epoch_barrier, bad);
+
 		/* version >= 6 */
 		ceph_decode_64_safe(&p, end, flush_tid, bad);
 		/* version >= 7 */
@@ -3765,6 +3809,7 @@ bad:
  */
 void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
 {
+	struct inode *inode;
 	struct ceph_inode_info *ci;
 	int flags = CHECK_CAPS_NODELAY;
 
@@ -3780,9 +3825,15 @@ void ceph_check_delayed_caps(struct ceph_mds_client *mdsc)
 		    time_before(jiffies, ci->i_hold_caps_max))
 			break;
 		list_del_init(&ci->i_cap_delay_list);
+
+		inode = igrab(&ci->vfs_inode);
 		spin_unlock(&mdsc->cap_delay_lock);
-		dout("check_delayed_caps on %p\n", &ci->vfs_inode);
-		ceph_check_caps(ci, flags, NULL);
+
+		if (inode) {
+			dout("check_delayed_caps on %p\n", inode);
+			ceph_check_caps(ci, flags, NULL);
+			iput(inode);
+		}
 	}
 	spin_unlock(&mdsc->cap_delay_lock);
 }
@@ -3924,9 +3975,10 @@ int ceph_encode_inode_release(void **p, struct inode *inode,
 }
 
 int ceph_encode_dentry_release(void **p, struct dentry *dentry,
+			       struct inode *dir,
 			       int mds, int drop, int unless)
 {
-	struct inode *dir = d_inode(dentry->d_parent);
+	struct dentry *parent = NULL;
 	struct ceph_mds_request_release *rel = *p;
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
 	int force = 0;
@@ -3941,9 +3993,14 @@ int ceph_encode_dentry_release(void **p, struct dentry *dentry,
 	spin_lock(&dentry->d_lock);
 	if (di->lease_session && di->lease_session->s_mds == mds)
 		force = 1;
+	if (!dir) {
+		parent = dget(dentry->d_parent);
+		dir = d_inode(parent);
+	}
 	spin_unlock(&dentry->d_lock);
 
 	ret = ceph_encode_inode_release(p, dir, mds, drop, unless, force);
+	dput(parent);
 
 	spin_lock(&dentry->d_lock);
 	if (ret && di->lease_session && di->lease_session->s_mds == mds) {
diff --git a/fs/ceph/debugfs.c b/fs/ceph/debugfs.c
index 39ff678e567f..4e2d112c982f 100644
--- a/fs/ceph/debugfs.c
+++ b/fs/ceph/debugfs.c
@@ -22,20 +22,19 @@ static int mdsmap_show(struct seq_file *s, void *p)
 {
 	int i;
 	struct ceph_fs_client *fsc = s->private;
+	struct ceph_mdsmap *mdsmap;
 
 	if (fsc->mdsc == NULL || fsc->mdsc->mdsmap == NULL)
 		return 0;
-	seq_printf(s, "epoch %d\n", fsc->mdsc->mdsmap->m_epoch);
-	seq_printf(s, "root %d\n", fsc->mdsc->mdsmap->m_root);
-	seq_printf(s, "session_timeout %d\n",
-		       fsc->mdsc->mdsmap->m_session_timeout);
-	seq_printf(s, "session_autoclose %d\n",
-		       fsc->mdsc->mdsmap->m_session_autoclose);
-	for (i = 0; i < fsc->mdsc->mdsmap->m_max_mds; i++) {
-		struct ceph_entity_addr *addr =
-			&fsc->mdsc->mdsmap->m_info[i].addr;
-		int state = fsc->mdsc->mdsmap->m_info[i].state;
-
+	mdsmap = fsc->mdsc->mdsmap;
+	seq_printf(s, "epoch %d\n", mdsmap->m_epoch);
+	seq_printf(s, "root %d\n", mdsmap->m_root);
+	seq_printf(s, "max_mds %d\n", mdsmap->m_max_mds);
+	seq_printf(s, "session_timeout %d\n", mdsmap->m_session_timeout);
+	seq_printf(s, "session_autoclose %d\n", mdsmap->m_session_autoclose);
+	for (i = 0; i < mdsmap->m_num_mds; i++) {
+		struct ceph_entity_addr *addr = &mdsmap->m_info[i].addr;
+		int state = mdsmap->m_info[i].state;
 		seq_printf(s, "\tmds%d\t%s\t(%s)\n", i,
 			       ceph_pr_addr(&addr->in_addr),
 			       ceph_mds_state_name(state));
@@ -70,7 +69,7 @@ static int mdsc_show(struct seq_file *s, void *p)
 
 		seq_printf(s, "%s", ceph_mds_op_name(req->r_op));
 
-		if (req->r_got_unsafe)
+		if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags))
 			seq_puts(s, "\t(unsafe)");
 		else
 			seq_puts(s, "\t");
@@ -251,7 +250,7 @@ int ceph_fs_debugfs_init(struct ceph_fs_client *fsc)
 		goto out;
 
 	snprintf(name, sizeof(name), "../../bdi/%s",
-		 dev_name(fsc->backing_dev_info.dev));
+		 dev_name(fsc->sb->s_bdi->dev));
 	fsc->debugfs_bdi =
 		debugfs_create_symlink("bdi",
 				       fsc->client->debugfs_dir,
diff --git a/fs/ceph/dir.c b/fs/ceph/dir.c
index 8ab1fdf0bd49..ef7240ace576 100644
--- a/fs/ceph/dir.c
+++ b/fs/ceph/dir.c
@@ -271,6 +271,11 @@ out:
 		if (ret < 0)
 			err = ret;
 		dput(last);
+		/* last_name no longer match cache index */
+		if (fi->readdir_cache_idx >= 0) {
+			fi->readdir_cache_idx = -1;
+			fi->dir_release_count = 0;
+		}
 	}
 	return err;
 }
@@ -294,7 +299,7 @@ static int ceph_readdir(struct file *file, struct dir_context *ctx)
 	struct ceph_mds_client *mdsc = fsc->mdsc;
 	int i;
 	int err;
-	u32 ftype;
+	unsigned frag = -1;
 	struct ceph_mds_reply_info_parsed *rinfo;
 
 	dout("readdir %p file %p pos %llx\n", inode, file, ctx->pos);
@@ -341,7 +346,6 @@ more:
 	/* do we have the correct frag content buffered? */
 	if (need_send_readdir(fi, ctx->pos)) {
 		struct ceph_mds_request *req;
-		unsigned frag;
 		int op = ceph_snap(inode) == CEPH_SNAPDIR ?
 			CEPH_MDS_OP_LSSNAP : CEPH_MDS_OP_READDIR;
 
@@ -352,8 +356,11 @@ more:
 		}
 
 		if (is_hash_order(ctx->pos)) {
-			frag = ceph_choose_frag(ci, fpos_hash(ctx->pos),
-						NULL, NULL);
+			/* fragtree isn't always accurate. choose frag
+			 * based on previous reply when possible. */
+			if (frag == (unsigned)-1)
+				frag = ceph_choose_frag(ci, fpos_hash(ctx->pos),
+							NULL, NULL);
 		} else {
 			frag = fpos_frag(ctx->pos);
 		}
@@ -371,14 +378,18 @@ more:
 		/* hints to request -> mds selection code */
 		req->r_direct_mode = USE_AUTH_MDS;
 		req->r_direct_hash = ceph_frag_value(frag);
-		req->r_direct_is_hash = true;
+		__set_bit(CEPH_MDS_R_DIRECT_IS_HASH, &req->r_req_flags);
 		if (fi->last_name) {
 			req->r_path2 = kstrdup(fi->last_name, GFP_KERNEL);
 			if (!req->r_path2) {
 				ceph_mdsc_put_request(req);
 				return -ENOMEM;
 			}
+		} else if (is_hash_order(ctx->pos)) {
+			req->r_args.readdir.offset_hash =
+				cpu_to_le32(fpos_hash(ctx->pos));
 		}
+
 		req->r_dir_release_cnt = fi->dir_release_count;
 		req->r_dir_ordered_cnt = fi->dir_ordered_count;
 		req->r_readdir_cache_idx = fi->readdir_cache_idx;
@@ -417,7 +428,7 @@ more:
 		fi->frag = frag;
 		fi->last_readdir = req;
 
-		if (req->r_did_prepopulate) {
+		if (test_bit(CEPH_MDS_R_DID_PREPOPULATE, &req->r_req_flags)) {
 			fi->readdir_cache_idx = req->r_readdir_cache_idx;
 			if (fi->readdir_cache_idx < 0) {
 				/* preclude from marking dir ordered */
@@ -476,6 +487,7 @@ more:
 		struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
 		struct ceph_vino vino;
 		ino_t ino;
+		u32 ftype;
 
 		BUG_ON(rde->offset < ctx->pos);
 
@@ -498,15 +510,17 @@ more:
 		ctx->pos++;
 	}
 
+	ceph_mdsc_put_request(fi->last_readdir);
+	fi->last_readdir = NULL;
+
 	if (fi->next_offset > 2) {
-		ceph_mdsc_put_request(fi->last_readdir);
-		fi->last_readdir = NULL;
+		frag = fi->frag;
 		goto more;
 	}
 
 	/* more frags? */
 	if (!ceph_frag_is_rightmost(fi->frag)) {
-		unsigned frag = ceph_frag_next(fi->frag);
+		frag = ceph_frag_next(fi->frag);
 		if (is_hash_order(ctx->pos)) {
 			loff_t new_pos = ceph_make_fpos(ceph_frag_value(frag),
 							fi->next_offset, true);
@@ -752,7 +766,8 @@ static struct dentry *ceph_lookup(struct inode *dir, struct dentry *dentry,
 		mask |= CEPH_CAP_XATTR_SHARED;
 	req->r_args.getattr.mask = cpu_to_le32(mask);
 
-	req->r_locked_dir = dir;
+	req->r_parent = dir;
+	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 	err = ceph_handle_snapdir(req, dentry, err);
 	dentry = ceph_finish_lookup(req, dentry, err);
@@ -813,7 +828,8 @@ static int ceph_mknod(struct inode *dir, struct dentry *dentry,
 	}
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
-	req->r_locked_dir = dir;
+	req->r_parent = dir;
+	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	req->r_args.mknod.mode = cpu_to_le32(mode);
 	req->r_args.mknod.rdev = cpu_to_le32(rdev);
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
@@ -864,7 +880,8 @@ static int ceph_symlink(struct inode *dir, struct dentry *dentry,
 		ceph_mdsc_put_request(req);
 		goto out;
 	}
-	req->r_locked_dir = dir;
+	req->r_parent = dir;
+	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
@@ -913,7 +930,8 @@ static int ceph_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
-	req->r_locked_dir = dir;
+	req->r_parent = dir;
+	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	req->r_args.mkdir.mode = cpu_to_le32(mode);
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
@@ -957,7 +975,8 @@ static int ceph_link(struct dentry *old_dentry, struct inode *dir,
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
 	req->r_old_dentry = dget(old_dentry);
-	req->r_locked_dir = dir;
+	req->r_parent = dir;
+	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
 	/* release LINK_SHARED on source inode (mds will lock it) */
@@ -1023,7 +1042,8 @@ static int ceph_unlink(struct inode *dir, struct dentry *dentry)
 	}
 	req->r_dentry = dget(dentry);
 	req->r_num_caps = 2;
-	req->r_locked_dir = dir;
+	req->r_parent = dir;
+	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
 	req->r_dentry_unless = CEPH_CAP_FILE_EXCL;
 	req->r_inode_drop = drop_caps_for_unlink(inode);
@@ -1066,7 +1086,8 @@ static int ceph_rename(struct inode *old_dir, struct dentry *old_dentry,
 	req->r_num_caps = 2;
 	req->r_old_dentry = dget(old_dentry);
 	req->r_old_dentry_dir = old_dir;
-	req->r_locked_dir = new_dir;
+	req->r_parent = new_dir;
+	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	req->r_old_dentry_drop = CEPH_CAP_FILE_SHARED;
 	req->r_old_dentry_unless = CEPH_CAP_FILE_EXCL;
 	req->r_dentry_drop = CEPH_CAP_FILE_SHARED;
@@ -1194,7 +1215,7 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 	struct inode *dir;
 
 	if (flags & LOOKUP_RCU) {
-		parent = ACCESS_ONCE(dentry->d_parent);
+		parent = READ_ONCE(dentry->d_parent);
 		dir = d_inode_rcu(parent);
 		if (!dir)
 			return -ECHILD;
@@ -1237,11 +1258,12 @@ static int ceph_d_revalidate(struct dentry *dentry, unsigned int flags)
 			return -ECHILD;
 
 		op = ceph_snap(dir) == CEPH_SNAPDIR ?
-			CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_GETATTR;
+			CEPH_MDS_OP_LOOKUPSNAP : CEPH_MDS_OP_LOOKUP;
 		req = ceph_mdsc_create_request(mdsc, op, USE_ANY_MDS);
 		if (!IS_ERR(req)) {
 			req->r_dentry = dget(dentry);
-			req->r_num_caps = op == CEPH_MDS_OP_GETATTR ? 1 : 2;
+			req->r_num_caps = 2;
+			req->r_parent = dir;
 
 			mask = CEPH_STAT_CAP_INODE | CEPH_CAP_AUTH_SHARED;
 			if (ceph_security_xattr_wanted(dir))
diff --git a/fs/ceph/export.c b/fs/ceph/export.c
index 180bbef760f2..7df550c13d7f 100644
--- a/fs/ceph/export.c
+++ b/fs/ceph/export.c
@@ -91,6 +91,10 @@ static struct dentry *__fh_to_dentry(struct super_block *sb, u64 ino)
 		ceph_mdsc_put_request(req);
 		if (!inode)
 			return ERR_PTR(-ESTALE);
+		if (inode->i_nlink == 0) {
+			iput(inode);
+			return ERR_PTR(-ESTALE);
+		}
 	}
 
 	return d_obtain_alias(inode);
@@ -207,7 +211,8 @@ static int ceph_get_name(struct dentry *parent, char *name,
 	req->r_inode = d_inode(child);
 	ihold(d_inode(child));
 	req->r_ino2 = ceph_vino(d_inode(parent));
-	req->r_locked_dir = d_inode(parent);
+	req->r_parent = d_inode(parent);
+	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	req->r_num_caps = 2;
 	err = ceph_mdsc_do_request(mdsc, NULL, req);
 
diff --git a/fs/ceph/file.c b/fs/ceph/file.c
index 045d30d26624..3d48c415f3cb 100644
--- a/fs/ceph/file.c
+++ b/fs/ceph/file.c
@@ -13,6 +13,38 @@
 #include "mds_client.h"
 #include "cache.h"
 
+static __le32 ceph_flags_sys2wire(u32 flags)
+{
+	u32 wire_flags = 0;
+
+	switch (flags & O_ACCMODE) {
+	case O_RDONLY:
+		wire_flags |= CEPH_O_RDONLY;
+		break;
+	case O_WRONLY:
+		wire_flags |= CEPH_O_WRONLY;
+		break;
+	case O_RDWR:
+		wire_flags |= CEPH_O_RDWR;
+		break;
+	}
+
+#define ceph_sys2wire(a) if (flags & a) { wire_flags |= CEPH_##a; flags &= ~a; }
+
+	ceph_sys2wire(O_CREAT);
+	ceph_sys2wire(O_EXCL);
+	ceph_sys2wire(O_TRUNC);
+	ceph_sys2wire(O_DIRECTORY);
+	ceph_sys2wire(O_NOFOLLOW);
+
+#undef ceph_sys2wire
+
+	if (flags)
+		dout("unused open flags: %x", flags);
+
+	return cpu_to_le32(wire_flags);
+}
+
 /*
  * Ceph file operations
  *
@@ -74,12 +106,9 @@ dio_get_pages_alloc(const struct iov_iter *it, size_t nbytes,
 	align = (unsigned long)(it->iov->iov_base + it->iov_offset) &
 		(PAGE_SIZE - 1);
 	npages = calc_pages_for(align, nbytes);
-	pages = kmalloc(sizeof(*pages) * npages, GFP_KERNEL);
-	if (!pages) {
-		pages = vmalloc(sizeof(*pages) * npages);
-		if (!pages)
-			return ERR_PTR(-ENOMEM);
-	}
+	pages = kvmalloc(sizeof(*pages) * npages, GFP_KERNEL);
+	if (!pages)
+		return ERR_PTR(-ENOMEM);
 
 	for (idx = 0; idx < npages; ) {
 		size_t start;
@@ -123,7 +152,7 @@ prepare_open_request(struct super_block *sb, int flags, int create_mode)
 	if (IS_ERR(req))
 		goto out;
 	req->r_fmode = ceph_flags_to_mode(flags);
-	req->r_args.open.flags = cpu_to_le32(flags);
+	req->r_args.open.flags = ceph_flags_sys2wire(flags);
 	req->r_args.open.mode = cpu_to_le32(create_mode);
 out:
 	return req;
@@ -192,7 +221,7 @@ int ceph_renew_caps(struct inode *inode)
 	spin_lock(&ci->i_ceph_lock);
 	wanted = __ceph_caps_file_wanted(ci);
 	if (__ceph_is_any_real_caps(ci) &&
-	    (!(wanted & CEPH_CAP_ANY_WR) == 0 || ci->i_auth_cap)) {
+	    (!(wanted & CEPH_CAP_ANY_WR) || ci->i_auth_cap)) {
 		int issued = __ceph_caps_issued(ci, NULL);
 		spin_unlock(&ci->i_ceph_lock);
 		dout("renew caps %p want %s issued %s updating mds_wanted\n",
@@ -283,7 +312,7 @@ int ceph_open(struct inode *inode, struct file *file)
 	spin_lock(&ci->i_ceph_lock);
 	if (__ceph_is_any_real_caps(ci) &&
 	    (((fmode & CEPH_FILE_MODE_WR) == 0) || ci->i_auth_cap)) {
-		int mds_wanted = __ceph_caps_mds_wanted(ci);
+		int mds_wanted = __ceph_caps_mds_wanted(ci, true);
 		int issued = __ceph_caps_issued(ci, NULL);
 
 		dout("open %p fmode %d want %s issued %s using existing\n",
@@ -379,7 +408,8 @@ int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
                mask |= CEPH_CAP_XATTR_SHARED;
        req->r_args.open.mask = cpu_to_le32(mask);
 
-	req->r_locked_dir = dir;           /* caller holds dir->i_mutex */
+	req->r_parent = dir;
+	set_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags);
 	err = ceph_mdsc_do_request(mdsc,
 				   (flags & (O_CREAT|O_TRUNC)) ? dir : NULL,
 				   req);
@@ -758,9 +788,7 @@ static void ceph_aio_retry_work(struct work_struct *work)
 		goto out;
 	}
 
-	req->r_flags =	CEPH_OSD_FLAG_ORDERSNAP |
-			CEPH_OSD_FLAG_ONDISK |
-			CEPH_OSD_FLAG_WRITE;
+	req->r_flags = CEPH_OSD_FLAG_ORDERSNAP | CEPH_OSD_FLAG_WRITE;
 	ceph_oloc_copy(&req->r_base_oloc, &orig_req->r_base_oloc);
 	ceph_oid_copy(&req->r_base_oid, &orig_req->r_base_oid);
 
@@ -782,6 +810,7 @@ static void ceph_aio_retry_work(struct work_struct *work)
 	req->r_callback = ceph_aio_complete_req;
 	req->r_inode = inode;
 	req->r_priv = aio_req;
+	req->r_abort_on_full = true;
 
 	ret = ceph_osdc_start_request(req->r_osdc, req, false);
 out:
@@ -794,89 +823,6 @@ out:
 	kfree(aio_work);
 }
 
-/*
- * Write commit request unsafe callback, called to tell us when a
- * request is unsafe (that is, in flight--has been handed to the
- * messenger to send to its target osd).  It is called again when
- * we've received a response message indicating the request is
- * "safe" (its CEPH_OSD_FLAG_ONDISK flag is set), or when a request
- * is completed early (and unsuccessfully) due to a timeout or
- * interrupt.
- *
- * This is used if we requested both an ACK and ONDISK commit reply
- * from the OSD.
- */
-static void ceph_sync_write_unsafe(struct ceph_osd_request *req, bool unsafe)
-{
-	struct ceph_inode_info *ci = ceph_inode(req->r_inode);
-
-	dout("%s %p tid %llu %ssafe\n", __func__, req, req->r_tid,
-		unsafe ? "un" : "");
-	if (unsafe) {
-		ceph_get_cap_refs(ci, CEPH_CAP_FILE_WR);
-		spin_lock(&ci->i_unsafe_lock);
-		list_add_tail(&req->r_unsafe_item,
-			      &ci->i_unsafe_writes);
-		spin_unlock(&ci->i_unsafe_lock);
-
-		complete_all(&req->r_completion);
-	} else {
-		spin_lock(&ci->i_unsafe_lock);
-		list_del_init(&req->r_unsafe_item);
-		spin_unlock(&ci->i_unsafe_lock);
-		ceph_put_cap_refs(ci, CEPH_CAP_FILE_WR);
-	}
-}
-
-/*
- * Wait on any unsafe replies for the given inode.  First wait on the
- * newest request, and make that the upper bound.  Then, if there are
- * more requests, keep waiting on the oldest as long as it is still older
- * than the original request.
- */
-void ceph_sync_write_wait(struct inode *inode)
-{
-	struct ceph_inode_info *ci = ceph_inode(inode);
-	struct list_head *head = &ci->i_unsafe_writes;
-	struct ceph_osd_request *req;
-	u64 last_tid;
-
-	if (!S_ISREG(inode->i_mode))
-		return;
-
-	spin_lock(&ci->i_unsafe_lock);
-	if (list_empty(head))
-		goto out;
-
-	/* set upper bound as _last_ entry in chain */
-
-	req = list_last_entry(head, struct ceph_osd_request,
-			      r_unsafe_item);
-	last_tid = req->r_tid;
-
-	do {
-		ceph_osdc_get_request(req);
-		spin_unlock(&ci->i_unsafe_lock);
-
-		dout("sync_write_wait on tid %llu (until %llu)\n",
-		     req->r_tid, last_tid);
-		wait_for_completion(&req->r_done_completion);
-		ceph_osdc_put_request(req);
-
-		spin_lock(&ci->i_unsafe_lock);
-		/*
-		 * from here on look at first entry in chain, since we
-		 * only want to wait for anything older than last_tid
-		 */
-		if (list_empty(head))
-			break;
-		req = list_first_entry(head, struct ceph_osd_request,
-				       r_unsafe_item);
-	} while (req->r_tid < last_tid);
-out:
-	spin_unlock(&ci->i_unsafe_lock);
-}
-
 static ssize_t
 ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		       struct ceph_snap_context *snapc,
@@ -915,9 +861,7 @@ ceph_direct_read_write(struct kiocb *iocb, struct iov_iter *iter,
 		if (ret2 < 0)
 			dout("invalidate_inode_pages2_range returned %d\n", ret2);
 
-		flags = CEPH_OSD_FLAG_ORDERSNAP |
-			CEPH_OSD_FLAG_ONDISK |
-			CEPH_OSD_FLAG_WRITE;
+		flags = CEPH_OSD_FLAG_ORDERSNAP | CEPH_OSD_FLAG_WRITE;
 	} else {
 		flags = CEPH_OSD_FLAG_READ;
 	}
@@ -1096,8 +1040,8 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	int num_pages;
 	int written = 0;
 	int flags;
-	int check_caps = 0;
 	int ret;
+	bool check_caps = false;
 	struct timespec mtime = current_time(inode);
 	size_t count = iov_iter_count(from);
 
@@ -1116,10 +1060,7 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 	if (ret < 0)
 		dout("invalidate_inode_pages2_range returned %d\n", ret);
 
-	flags = CEPH_OSD_FLAG_ORDERSNAP |
-		CEPH_OSD_FLAG_ONDISK |
-		CEPH_OSD_FLAG_WRITE |
-		CEPH_OSD_FLAG_ACK;
+	flags = CEPH_OSD_FLAG_ORDERSNAP | CEPH_OSD_FLAG_WRITE;
 
 	while ((len = iov_iter_count(from)) > 0) {
 		size_t left;
@@ -1165,8 +1106,6 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 			goto out;
 		}
 
-		/* get a second commit callback */
-		req->r_unsafe_callback = ceph_sync_write_unsafe;
 		req->r_inode = inode;
 
 		osd_req_op_extent_osd_data_pages(req, 0, pages, len, 0,
@@ -1179,19 +1118,22 @@ ceph_sync_write(struct kiocb *iocb, struct iov_iter *from, loff_t pos,
 
 out:
 		ceph_osdc_put_request(req);
-		if (ret == 0) {
-			pos += len;
-			written += len;
-
-			if (pos > i_size_read(inode)) {
-				check_caps = ceph_inode_set_size(inode, pos);
-				if (check_caps)
-					ceph_check_caps(ceph_inode(inode),
-							CHECK_CAPS_AUTHONLY,
-							NULL);
-			}
-		} else
+		if (ret != 0) {
+			ceph_set_error_write(ci);
 			break;
+		}
+
+		ceph_clear_error_write(ci);
+		pos += len;
+		written += len;
+		if (pos > i_size_read(inode)) {
+			check_caps = ceph_inode_set_size(inode, pos);
+			if (check_caps)
+				ceph_check_caps(ceph_inode(inode),
+						CHECK_CAPS_AUTHONLY,
+						NULL);
+		}
+
 	}
 
 	if (ret != -EOLDSNAPC && written > 0) {
@@ -1397,6 +1339,7 @@ static ssize_t ceph_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	}
 
 retry_snap:
+	/* FIXME: not complete since it doesn't account for being at quota */
 	if (ceph_osdmap_flag(osdc, CEPH_OSDMAP_FULL)) {
 		err = -ENOSPC;
 		goto out;
@@ -1418,7 +1361,8 @@ retry_snap:
 	     inode, ceph_vinop(inode), pos, count, ceph_cap_string(got));
 
 	if ((got & (CEPH_CAP_FILE_BUFFER|CEPH_CAP_FILE_LAZYIO)) == 0 ||
-	    (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC)) {
+	    (iocb->ki_flags & IOCB_DIRECT) || (fi->flags & CEPH_F_SYNC) ||
+	    (ci->i_ceph_flags & CEPH_I_ERROR_WRITE)) {
 		struct ceph_snap_context *snapc;
 		struct iov_iter data;
 		inode_unlock(inode);
@@ -1616,8 +1560,7 @@ static int ceph_zero_partial_object(struct inode *inode,
 					ceph_vino(inode),
 					offset, length,
 					0, 1, op,
-					CEPH_OSD_FLAG_WRITE |
-					CEPH_OSD_FLAG_ONDISK,
+					CEPH_OSD_FLAG_WRITE,
 					NULL, 0, 0, false);
 	if (IS_ERR(req)) {
 		ret = PTR_ERR(req);
@@ -1728,8 +1671,12 @@ static long ceph_fallocate(struct file *file, int mode,
 	}
 
 	size = i_size_read(inode);
-	if (!(mode & FALLOC_FL_KEEP_SIZE))
+	if (!(mode & FALLOC_FL_KEEP_SIZE)) {
 		endoff = offset + length;
+		ret = inode_newsize_ok(inode, endoff);
+		if (ret)
+			goto unlock;
+	}
 
 	if (fi->fmode & CEPH_FILE_MODE_LAZY)
 		want = CEPH_CAP_FILE_BUFFER | CEPH_CAP_FILE_LAZYIO;
diff --git a/fs/ceph/inode.c b/fs/ceph/inode.c
index 5e659d054b40..220dfd87cbfa 100644
--- a/fs/ceph/inode.c
+++ b/fs/ceph/inode.c
@@ -499,7 +499,6 @@ struct inode *ceph_alloc_inode(struct super_block *sb)
 	ci->i_rdcache_gen = 0;
 	ci->i_rdcache_revoking = 0;
 
-	INIT_LIST_HEAD(&ci->i_unsafe_writes);
 	INIT_LIST_HEAD(&ci->i_unsafe_dirops);
 	INIT_LIST_HEAD(&ci->i_unsafe_iops);
 	spin_lock_init(&ci->i_unsafe_lock);
@@ -583,14 +582,6 @@ int ceph_drop_inode(struct inode *inode)
 	return 1;
 }
 
-void ceph_evict_inode(struct inode *inode)
-{
-	/* wait unsafe sync writes */
-	ceph_sync_write_wait(inode);
-	truncate_inode_pages_final(&inode->i_data);
-	clear_inode(inode);
-}
-
 static inline blkcnt_t calc_inode_blocks(u64 size)
 {
 	return (size + (1<<9) - 1) >> 9;
@@ -1016,21 +1007,38 @@ out:
 static void update_dentry_lease(struct dentry *dentry,
 				struct ceph_mds_reply_lease *lease,
 				struct ceph_mds_session *session,
-				unsigned long from_time)
+				unsigned long from_time,
+				struct ceph_vino *tgt_vino,
+				struct ceph_vino *dir_vino)
 {
 	struct ceph_dentry_info *di = ceph_dentry(dentry);
 	long unsigned duration = le32_to_cpu(lease->duration_ms);
 	long unsigned ttl = from_time + (duration * HZ) / 1000;
 	long unsigned half_ttl = from_time + (duration * HZ / 2) / 1000;
 	struct inode *dir;
+	struct ceph_mds_session *old_lease_session = NULL;
+
+	/*
+	 * Make sure dentry's inode matches tgt_vino. NULL tgt_vino means that
+	 * we expect a negative dentry.
+	 */
+	if (!tgt_vino && d_really_is_positive(dentry))
+		return;
+
+	if (tgt_vino && (d_really_is_negative(dentry) ||
+			!ceph_ino_compare(d_inode(dentry), tgt_vino)))
+		return;
 
 	spin_lock(&dentry->d_lock);
 	dout("update_dentry_lease %p duration %lu ms ttl %lu\n",
 	     dentry, duration, ttl);
 
-	/* make lease_rdcache_gen match directory */
 	dir = d_inode(dentry->d_parent);
 
+	/* make sure parent matches dir_vino */
+	if (!ceph_ino_compare(dir, dir_vino))
+		goto out_unlock;
+
 	/* only track leases on regular dentries */
 	if (ceph_snap(dir) != CEPH_NOSNAP)
 		goto out_unlock;
@@ -1044,8 +1052,10 @@ static void update_dentry_lease(struct dentry *dentry,
 	    time_before(ttl, di->time))
 		goto out_unlock;  /* we already have a newer lease. */
 
-	if (di->lease_session && di->lease_session != session)
-		goto out_unlock;
+	if (di->lease_session && di->lease_session != session) {
+		old_lease_session = di->lease_session;
+		di->lease_session = NULL;
+	}
 
 	ceph_dentry_lru_touch(dentry);
 
@@ -1058,6 +1068,8 @@ static void update_dentry_lease(struct dentry *dentry,
 	di->time = ttl;
 out_unlock:
 	spin_unlock(&dentry->d_lock);
+	if (old_lease_session)
+		ceph_put_mds_session(old_lease_session);
 	return;
 }
 
@@ -1108,61 +1120,27 @@ out:
  *
  * Called with snap_rwsem (read).
  */
-int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
-		    struct ceph_mds_session *session)
+int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req)
 {
+	struct ceph_mds_session *session = req->r_session;
 	struct ceph_mds_reply_info_parsed *rinfo = &req->r_reply_info;
 	struct inode *in = NULL;
-	struct ceph_vino vino;
+	struct ceph_vino tvino, dvino;
 	struct ceph_fs_client *fsc = ceph_sb_to_client(sb);
 	int err = 0;
 
 	dout("fill_trace %p is_dentry %d is_target %d\n", req,
 	     rinfo->head->is_dentry, rinfo->head->is_target);
 
-#if 0
-	/*
-	 * Debugging hook:
-	 *
-	 * If we resend completed ops to a recovering mds, we get no
-	 * trace.  Since that is very rare, pretend this is the case
-	 * to ensure the 'no trace' handlers in the callers behave.
-	 *
-	 * Fill in inodes unconditionally to avoid breaking cap
-	 * invariants.
-	 */
-	if (rinfo->head->op & CEPH_MDS_OP_WRITE) {
-		pr_info("fill_trace faking empty trace on %lld %s\n",
-			req->r_tid, ceph_mds_op_name(rinfo->head->op));
-		if (rinfo->head->is_dentry) {
-			rinfo->head->is_dentry = 0;
-			err = fill_inode(req->r_locked_dir,
-					 &rinfo->diri, rinfo->dirfrag,
-					 session, req->r_request_started, -1);
-		}
-		if (rinfo->head->is_target) {
-			rinfo->head->is_target = 0;
-			ininfo = rinfo->targeti.in;
-			vino.ino = le64_to_cpu(ininfo->ino);
-			vino.snap = le64_to_cpu(ininfo->snapid);
-			in = ceph_get_inode(sb, vino);
-			err = fill_inode(in, &rinfo->targeti, NULL,
-					 session, req->r_request_started,
-					 req->r_fmode);
-			iput(in);
-		}
-	}
-#endif
-
 	if (!rinfo->head->is_target && !rinfo->head->is_dentry) {
 		dout("fill_trace reply is empty!\n");
-		if (rinfo->head->result == 0 && req->r_locked_dir)
+		if (rinfo->head->result == 0 && req->r_parent)
 			ceph_invalidate_dir_request(req);
 		return 0;
 	}
 
 	if (rinfo->head->is_dentry) {
-		struct inode *dir = req->r_locked_dir;
+		struct inode *dir = req->r_parent;
 
 		if (dir) {
 			err = fill_inode(dir, NULL,
@@ -1188,8 +1166,8 @@ int ceph_fill_trace(struct super_block *sb, struct ceph_mds_request *req,
 			dname.name = rinfo->dname;
 			dname.len = rinfo->dname_len;
 			dname.hash = full_name_hash(parent, dname.name, dname.len);
-			vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
-			vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
+			tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+			tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
 retry_lookup:
 			dn = d_lookup(parent, &dname);
 			dout("d_lookup on parent=%p name=%.*s got %p\n",
@@ -1206,8 +1184,8 @@ retry_lookup:
 				}
 				err = 0;
 			} else if (d_really_is_positive(dn) &&
-				   (ceph_ino(d_inode(dn)) != vino.ino ||
-				    ceph_snap(d_inode(dn)) != vino.snap)) {
+				   (ceph_ino(d_inode(dn)) != tvino.ino ||
+				    ceph_snap(d_inode(dn)) != tvino.snap)) {
 				dout(" dn %p points to wrong inode %p\n",
 				     dn, d_inode(dn));
 				d_delete(dn);
@@ -1221,10 +1199,10 @@ retry_lookup:
 	}
 
 	if (rinfo->head->is_target) {
-		vino.ino = le64_to_cpu(rinfo->targeti.in->ino);
-		vino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
+		tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+		tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
 
-		in = ceph_get_inode(sb, vino);
+		in = ceph_get_inode(sb, tvino);
 		if (IS_ERR(in)) {
 			err = PTR_ERR(in);
 			goto done;
@@ -1233,8 +1211,8 @@ retry_lookup:
 
 		err = fill_inode(in, req->r_locked_page, &rinfo->targeti, NULL,
 				session, req->r_request_started,
-				(!req->r_aborted && rinfo->head->result == 0) ?
-				req->r_fmode : -1,
+				(!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) &&
+				rinfo->head->result == 0) ?  req->r_fmode : -1,
 				&req->r_caps_reservation);
 		if (err < 0) {
 			pr_err("fill_inode badness %p %llx.%llx\n",
@@ -1247,8 +1225,9 @@ retry_lookup:
 	 * ignore null lease/binding on snapdir ENOENT, or else we
 	 * will have trouble splicing in the virtual snapdir later
 	 */
-	if (rinfo->head->is_dentry && !req->r_aborted &&
-	    req->r_locked_dir &&
+	if (rinfo->head->is_dentry &&
+            !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags) &&
+	    test_bit(CEPH_MDS_R_PARENT_LOCKED, &req->r_req_flags) &&
 	    (rinfo->head->is_target || strncmp(req->r_dentry->d_name.name,
 					       fsc->mount_options->snapdir_name,
 					       req->r_dentry->d_name.len))) {
@@ -1257,17 +1236,19 @@ retry_lookup:
 		 * mknod symlink mkdir  : null -> new inode
 		 * unlink               : linked -> null
 		 */
-		struct inode *dir = req->r_locked_dir;
+		struct inode *dir = req->r_parent;
 		struct dentry *dn = req->r_dentry;
 		bool have_dir_cap, have_lease;
 
 		BUG_ON(!dn);
 		BUG_ON(!dir);
 		BUG_ON(d_inode(dn->d_parent) != dir);
-		BUG_ON(ceph_ino(dir) !=
-		       le64_to_cpu(rinfo->diri.in->ino));
-		BUG_ON(ceph_snap(dir) !=
-		       le64_to_cpu(rinfo->diri.in->snapid));
+
+		dvino.ino = le64_to_cpu(rinfo->diri.in->ino);
+		dvino.snap = le64_to_cpu(rinfo->diri.in->snapid);
+
+		BUG_ON(ceph_ino(dir) != dvino.ino);
+		BUG_ON(ceph_snap(dir) != dvino.snap);
 
 		/* do we have a lease on the whole dir? */
 		have_dir_cap =
@@ -1319,12 +1300,13 @@ retry_lookup:
 				ceph_dir_clear_ordered(dir);
 				dout("d_delete %p\n", dn);
 				d_delete(dn);
-			} else {
-				if (have_lease && d_unhashed(dn))
+			} else if (have_lease) {
+				if (d_unhashed(dn))
 					d_add(dn, NULL);
 				update_dentry_lease(dn, rinfo->dlease,
 						    session,
-						    req->r_request_started);
+						    req->r_request_started,
+						    NULL, &dvino);
 			}
 			goto done;
 		}
@@ -1347,15 +1329,19 @@ retry_lookup:
 			have_lease = false;
 		}
 
-		if (have_lease)
+		if (have_lease) {
+			tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+			tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
 			update_dentry_lease(dn, rinfo->dlease, session,
-					    req->r_request_started);
+					    req->r_request_started,
+					    &tvino, &dvino);
+		}
 		dout(" final dn %p\n", dn);
-	} else if (!req->r_aborted &&
-		   (req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
-		    req->r_op == CEPH_MDS_OP_MKSNAP)) {
+	} else if ((req->r_op == CEPH_MDS_OP_LOOKUPSNAP ||
+		    req->r_op == CEPH_MDS_OP_MKSNAP) &&
+		   !test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
 		struct dentry *dn = req->r_dentry;
-		struct inode *dir = req->r_locked_dir;
+		struct inode *dir = req->r_parent;
 
 		/* fill out a snapdir LOOKUPSNAP dentry */
 		BUG_ON(!dn);
@@ -1370,6 +1356,26 @@ retry_lookup:
 			goto done;
 		}
 		req->r_dentry = dn;  /* may have spliced */
+	} else if (rinfo->head->is_dentry) {
+		struct ceph_vino *ptvino = NULL;
+
+		if ((le32_to_cpu(rinfo->diri.in->cap.caps) & CEPH_CAP_FILE_SHARED) ||
+		    le32_to_cpu(rinfo->dlease->duration_ms)) {
+			dvino.ino = le64_to_cpu(rinfo->diri.in->ino);
+			dvino.snap = le64_to_cpu(rinfo->diri.in->snapid);
+
+			if (rinfo->head->is_target) {
+				tvino.ino = le64_to_cpu(rinfo->targeti.in->ino);
+				tvino.snap = le64_to_cpu(rinfo->targeti.in->snapid);
+				ptvino = &tvino;
+			}
+
+			update_dentry_lease(req->r_dentry, rinfo->dlease,
+				session, req->r_request_started, ptvino,
+				&dvino);
+		} else {
+			dout("%s: no dentry lease or dir cap\n", __func__);
+		}
 	}
 done:
 	dout("fill_trace done err=%d\n", err);
@@ -1478,13 +1484,20 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 	u32 fpos_offset;
 	struct ceph_readdir_cache_control cache_ctl = {};
 
-	if (req->r_aborted)
+	if (test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags))
 		return readdir_prepopulate_inodes_only(req, session);
 
-	if (rinfo->hash_order && req->r_path2) {
-		last_hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
-					  req->r_path2, strlen(req->r_path2));
-		last_hash = ceph_frag_value(last_hash);
+	if (rinfo->hash_order) {
+		if (req->r_path2) {
+			last_hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
+						  req->r_path2,
+						  strlen(req->r_path2));
+			last_hash = ceph_frag_value(last_hash);
+		} else if (rinfo->offset_hash) {
+			/* mds understands offset_hash */
+			WARN_ON_ONCE(req->r_readdir_offset != 2);
+			last_hash = le32_to_cpu(rhead->args.readdir.offset_hash);
+		}
 	}
 
 	if (rinfo->dir_dir &&
@@ -1509,7 +1522,7 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 	}
 
 	if (ceph_frag_is_leftmost(frag) && req->r_readdir_offset == 2 &&
-	    !(rinfo->hash_order && req->r_path2)) {
+	    !(rinfo->hash_order && last_hash)) {
 		/* note dir version at start of readdir so we can tell
 		 * if any dentries get dropped */
 		req->r_dir_release_cnt = atomic64_read(&ci->i_release_count);
@@ -1523,14 +1536,14 @@ int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 	/* FIXME: release caps/leases if error occurs */
 	for (i = 0; i < rinfo->dir_nr; i++) {
 		struct ceph_mds_reply_dir_entry *rde = rinfo->dir_entries + i;
-		struct ceph_vino vino;
+		struct ceph_vino tvino, dvino;
 
 		dname.name = rde->name;
 		dname.len = rde->name_len;
 		dname.hash = full_name_hash(parent, dname.name, dname.len);
 
-		vino.ino = le64_to_cpu(rde->inode.in->ino);
-		vino.snap = le64_to_cpu(rde->inode.in->snapid);
+		tvino.ino = le64_to_cpu(rde->inode.in->ino);
+		tvino.snap = le64_to_cpu(rde->inode.in->snapid);
 
 		if (rinfo->hash_order) {
 			u32 hash = ceph_str_hash(ci->i_dir_layout.dl_dir_hash,
@@ -1559,8 +1572,8 @@ retry_lookup:
 				goto out;
 			}
 		} else if (d_really_is_positive(dn) &&
-			   (ceph_ino(d_inode(dn)) != vino.ino ||
-			    ceph_snap(d_inode(dn)) != vino.snap)) {
+			   (ceph_ino(d_inode(dn)) != tvino.ino ||
+			    ceph_snap(d_inode(dn)) != tvino.snap)) {
 			dout(" dn %p points to wrong inode %p\n",
 			     dn, d_inode(dn));
 			d_delete(dn);
@@ -1572,7 +1585,7 @@ retry_lookup:
 		if (d_really_is_positive(dn)) {
 			in = d_inode(dn);
 		} else {
-			in = ceph_get_inode(parent->d_sb, vino);
+			in = ceph_get_inode(parent->d_sb, tvino);
 			if (IS_ERR(in)) {
 				dout("new_inode badness\n");
 				d_drop(dn);
@@ -1617,8 +1630,9 @@ retry_lookup:
 
 		ceph_dentry(dn)->offset = rde->offset;
 
+		dvino = ceph_vino(d_inode(parent));
 		update_dentry_lease(dn, rde->lease, req->r_session,
-				    req->r_request_started);
+				    req->r_request_started, &tvino, &dvino);
 
 		if (err == 0 && skipped == 0 && cache_ctl.index >= 0) {
 			ret = fill_readdir_cache(d_inode(parent), dn,
@@ -1632,7 +1646,7 @@ next_item:
 	}
 out:
 	if (err == 0 && skipped == 0) {
-		req->r_did_prepopulate = true;
+		set_bit(CEPH_MDS_R_DID_PREPOPULATE, &req->r_req_flags);
 		req->r_readdir_cache_idx = cache_ctl.index;
 	}
 	ceph_readdir_cache_release(&cache_ctl);
@@ -1644,20 +1658,17 @@ out:
 	return err;
 }
 
-int ceph_inode_set_size(struct inode *inode, loff_t size)
+bool ceph_inode_set_size(struct inode *inode, loff_t size)
 {
 	struct ceph_inode_info *ci = ceph_inode(inode);
-	int ret = 0;
+	bool ret;
 
 	spin_lock(&ci->i_ceph_lock);
 	dout("set_size %p %llu -> %llu\n", inode, inode->i_size, size);
 	i_size_write(inode, size);
 	inode->i_blocks = calc_inode_blocks(size);
 
-	/* tell the MDS if we are approaching max_size */
-	if ((size << 1) >= ci->i_max_size &&
-	    (ci->i_reported_size << 1) < ci->i_max_size)
-		ret = 1;
+	ret = __ceph_should_report_size(ci);
 
 	spin_unlock(&ci->i_ceph_lock);
 	return ret;
@@ -1720,7 +1731,7 @@ static void ceph_invalidate_work(struct work_struct *work)
 
 	mutex_lock(&ci->i_truncate_mutex);
 
-	if (ACCESS_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+	if (READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
 		pr_warn_ratelimited("invalidate_pages %p %lld forced umount\n",
 				    inode, ceph_ino(inode));
 		mapping_set_error(inode->i_mapping, -EIO);
@@ -2013,7 +2024,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 		    attr->ia_size > inode->i_size) {
 			i_size_write(inode, attr->ia_size);
 			inode->i_blocks = calc_inode_blocks(attr->ia_size);
-			inode->i_ctime = attr->ia_ctime;
 			ci->i_reported_size = attr->ia_size;
 			dirtied |= CEPH_CAP_FILE_EXCL;
 		} else if ((issued & CEPH_CAP_FILE_SHARED) == 0 ||
@@ -2035,7 +2045,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 		     inode->i_ctime.tv_sec, inode->i_ctime.tv_nsec,
 		     attr->ia_ctime.tv_sec, attr->ia_ctime.tv_nsec,
 		     only ? "ctime only" : "ignored");
-		inode->i_ctime = attr->ia_ctime;
 		if (only) {
 			/*
 			 * if kernel wants to dirty ctime but nothing else,
@@ -2058,7 +2067,7 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 	if (dirtied) {
 		inode_dirty_flags = __ceph_mark_dirty_caps(ci, dirtied,
 							   &prealloc_cf);
-		inode->i_ctime = current_time(inode);
+		inode->i_ctime = attr->ia_ctime;
 	}
 
 	release &= issued;
@@ -2069,11 +2078,6 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 	if (inode_dirty_flags)
 		__mark_inode_dirty(inode, inode_dirty_flags);
 
-	if (ia_valid & ATTR_MODE) {
-		err = posix_acl_chmod(inode, attr->ia_mode);
-		if (err)
-			goto out_put;
-	}
 
 	if (mask) {
 		req->r_inode = inode;
@@ -2081,19 +2085,18 @@ int __ceph_setattr(struct inode *inode, struct iattr *attr)
 		req->r_inode_drop = release;
 		req->r_args.setattr.mask = cpu_to_le32(mask);
 		req->r_num_caps = 1;
+		req->r_stamp = attr->ia_ctime;
 		err = ceph_mdsc_do_request(mdsc, NULL, req);
 	}
 	dout("setattr %p result=%d (%s locally, %d remote)\n", inode, err,
 	     ceph_cap_string(dirtied), mask);
 
 	ceph_mdsc_put_request(req);
-	if (mask & CEPH_SETATTR_SIZE)
-		__ceph_do_pending_vmtruncate(inode);
-	ceph_free_cap_flush(prealloc_cf);
-	return err;
-out_put:
-	ceph_mdsc_put_request(req);
 	ceph_free_cap_flush(prealloc_cf);
+
+	if (err >= 0 && (mask & CEPH_SETATTR_SIZE))
+		__ceph_do_pending_vmtruncate(inode);
+
 	return err;
 }
 
@@ -2112,7 +2115,12 @@ int ceph_setattr(struct dentry *dentry, struct iattr *attr)
 	if (err != 0)
 		return err;
 
-	return __ceph_setattr(inode, attr);
+	err = __ceph_setattr(inode, attr);
+
+	if (err >= 0 && (attr->ia_valid & ATTR_MODE))
+		err = posix_acl_chmod(inode, attr->ia_mode);
+
+	return err;
 }
 
 /*
@@ -2185,10 +2193,10 @@ int ceph_permission(struct inode *inode, int mask)
  * Get all attributes.  Hopefully somedata we'll have a statlite()
  * and can limit the fields we require to be accurate.
  */
-int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		 struct kstat *stat)
+int ceph_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct ceph_inode_info *ci = ceph_inode(inode);
 	int err;
 
diff --git a/fs/ceph/ioctl.c b/fs/ceph/ioctl.c
index 7d752d53353a..4c9c72f26eb9 100644
--- a/fs/ceph/ioctl.c
+++ b/fs/ceph/ioctl.c
@@ -25,7 +25,7 @@ static long ceph_ioctl_get_layout(struct file *file, void __user *arg)
 		l.stripe_count = ci->i_layout.stripe_count;
 		l.object_size = ci->i_layout.object_size;
 		l.data_pool = ci->i_layout.pool_id;
-		l.preferred_osd = (s32)-1;
+		l.preferred_osd = -1;
 		if (copy_to_user(arg, &l, sizeof(l)))
 			return -EFAULT;
 	}
@@ -97,7 +97,7 @@ static long ceph_ioctl_set_layout(struct file *file, void __user *arg)
 		nl.data_pool = ci->i_layout.pool_id;
 
 	/* this is obsolete, and always -1 */
-	nl.preferred_osd = le64_to_cpu(-1);
+	nl.preferred_osd = -1;
 
 	err = __validate_layout(mdsc, &nl);
 	if (err)
diff --git a/fs/ceph/locks.c b/fs/ceph/locks.c
index 6806dbeaee19..64ae74472046 100644
--- a/fs/ceph/locks.c
+++ b/fs/ceph/locks.c
@@ -127,6 +127,29 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
 	dout("ceph_lock_wait_for_completion: request %llu was interrupted\n",
 	     req->r_tid);
 
+	mutex_lock(&mdsc->mutex);
+	if (test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags)) {
+		err = 0;
+	} else {
+		/*
+		 * ensure we aren't running concurrently with
+		 * ceph_fill_trace or ceph_readdir_prepopulate, which
+		 * rely on locks (dir mutex) held by our caller.
+		 */
+		mutex_lock(&req->r_fill_mutex);
+		req->r_err = err;
+		set_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags);
+		mutex_unlock(&req->r_fill_mutex);
+
+		if (!req->r_session) {
+			// haven't sent the request
+			err = 0;
+		}
+	}
+	mutex_unlock(&mdsc->mutex);
+	if (!err)
+		return 0;
+
 	intr_req = ceph_mdsc_create_request(mdsc, CEPH_MDS_OP_SETFILELOCK,
 					    USE_AUTH_MDS);
 	if (IS_ERR(intr_req))
@@ -146,7 +169,7 @@ static int ceph_lock_wait_for_completion(struct ceph_mds_client *mdsc,
 	if (err && err != -ERESTARTSYS)
 		return err;
 
-	wait_for_completion(&req->r_completion);
+	wait_for_completion_killable(&req->r_safe_completion);
 	return 0;
 }
 
diff --git a/fs/ceph/mds_client.c b/fs/ceph/mds_client.c
index c9d2e553a6c4..666a9f274832 100644
--- a/fs/ceph/mds_client.c
+++ b/fs/ceph/mds_client.c
@@ -189,6 +189,7 @@ static int parse_reply_info_dir(void **p, void *end,
 		info->dir_end = !!(flags & CEPH_READDIR_FRAG_END);
 		info->dir_complete = !!(flags & CEPH_READDIR_FRAG_COMPLETE);
 		info->hash_order = !!(flags & CEPH_READDIR_HASH_ORDER);
+		info->offset_hash = !!(flags & CEPH_READDIR_OFFSET_HASH);
 	}
 	if (num == 0)
 		goto done;
@@ -378,9 +379,9 @@ const char *ceph_session_state_name(int s)
 
 static struct ceph_mds_session *get_session(struct ceph_mds_session *s)
 {
-	if (atomic_inc_not_zero(&s->s_ref)) {
+	if (refcount_inc_not_zero(&s->s_ref)) {
 		dout("mdsc get_session %p %d -> %d\n", s,
-		     atomic_read(&s->s_ref)-1, atomic_read(&s->s_ref));
+		     refcount_read(&s->s_ref)-1, refcount_read(&s->s_ref));
 		return s;
 	} else {
 		dout("mdsc get_session %p 0 -- FAIL", s);
@@ -391,8 +392,8 @@ static struct ceph_mds_session *get_session(struct ceph_mds_session *s)
 void ceph_put_mds_session(struct ceph_mds_session *s)
 {
 	dout("mdsc put_session %p %d -> %d\n", s,
-	     atomic_read(&s->s_ref), atomic_read(&s->s_ref)-1);
-	if (atomic_dec_and_test(&s->s_ref)) {
+	     refcount_read(&s->s_ref), refcount_read(&s->s_ref)-1);
+	if (refcount_dec_and_test(&s->s_ref)) {
 		if (s->s_auth.authorizer)
 			ceph_auth_destroy_authorizer(s->s_auth.authorizer);
 		kfree(s);
@@ -411,7 +412,7 @@ struct ceph_mds_session *__ceph_lookup_mds_session(struct ceph_mds_client *mdsc,
 		return NULL;
 	session = mdsc->sessions[mds];
 	dout("lookup_mds_session %p %d\n", session,
-	     atomic_read(&session->s_ref));
+	     refcount_read(&session->s_ref));
 	get_session(session);
 	return session;
 }
@@ -441,7 +442,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 {
 	struct ceph_mds_session *s;
 
-	if (mds >= mdsc->mdsmap->m_max_mds)
+	if (mds >= mdsc->mdsmap->m_num_mds)
 		return ERR_PTR(-EINVAL);
 
 	s = kzalloc(sizeof(*s), GFP_NOFS);
@@ -466,7 +467,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	INIT_LIST_HEAD(&s->s_caps);
 	s->s_nr_caps = 0;
 	s->s_trim_caps = 0;
-	atomic_set(&s->s_ref, 1);
+	refcount_set(&s->s_ref, 1);
 	INIT_LIST_HEAD(&s->s_waiting);
 	INIT_LIST_HEAD(&s->s_unsafe);
 	s->s_num_cap_releases = 0;
@@ -494,7 +495,7 @@ static struct ceph_mds_session *register_session(struct ceph_mds_client *mdsc,
 	}
 	mdsc->sessions[mds] = s;
 	atomic_inc(&mdsc->num_sessions);
-	atomic_inc(&s->s_ref);  /* one ref to sessions[], one to caller */
+	refcount_inc(&s->s_ref);  /* one ref to sessions[], one to caller */
 
 	ceph_con_open(&s->s_con, CEPH_ENTITY_TYPE_MDS, mds,
 		      ceph_mdsmap_get_addr(mdsc->mdsmap, mds));
@@ -547,8 +548,8 @@ void ceph_mdsc_release_request(struct kref *kref)
 		ceph_put_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN);
 		iput(req->r_inode);
 	}
-	if (req->r_locked_dir)
-		ceph_put_cap_refs(ceph_inode(req->r_locked_dir), CEPH_CAP_PIN);
+	if (req->r_parent)
+		ceph_put_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN);
 	iput(req->r_target_inode);
 	if (req->r_dentry)
 		dput(req->r_dentry);
@@ -628,6 +629,9 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
 {
 	dout("__unregister_request %p tid %lld\n", req, req->r_tid);
 
+	/* Never leave an unregistered request on an unsafe list! */
+	list_del_init(&req->r_unsafe_item);
+
 	if (req->r_tid == mdsc->oldest_tid) {
 		struct rb_node *p = rb_next(&req->r_node);
 		mdsc->oldest_tid = 0;
@@ -644,13 +648,15 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
 
 	erase_request(&mdsc->request_tree, req);
 
-	if (req->r_unsafe_dir && req->r_got_unsafe) {
+	if (req->r_unsafe_dir  &&
+	    test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags)) {
 		struct ceph_inode_info *ci = ceph_inode(req->r_unsafe_dir);
 		spin_lock(&ci->i_unsafe_lock);
 		list_del_init(&req->r_unsafe_dir_item);
 		spin_unlock(&ci->i_unsafe_lock);
 	}
-	if (req->r_target_inode && req->r_got_unsafe) {
+	if (req->r_target_inode &&
+	    test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags)) {
 		struct ceph_inode_info *ci = ceph_inode(req->r_target_inode);
 		spin_lock(&ci->i_unsafe_lock);
 		list_del_init(&req->r_unsafe_target_item);
@@ -668,6 +674,28 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
 }
 
 /*
+ * Walk back up the dentry tree until we hit a dentry representing a
+ * non-snapshot inode. We do this using the rcu_read_lock (which must be held
+ * when calling this) to ensure that the objects won't disappear while we're
+ * working with them. Once we hit a candidate dentry, we attempt to take a
+ * reference to it, and return that as the result.
+ */
+static struct inode *get_nonsnap_parent(struct dentry *dentry)
+{
+	struct inode *inode = NULL;
+
+	while (dentry && !IS_ROOT(dentry)) {
+		inode = d_inode_rcu(dentry);
+		if (!inode || ceph_snap(inode) == CEPH_NOSNAP)
+			break;
+		dentry = dentry->d_parent;
+	}
+	if (inode)
+		inode = igrab(inode);
+	return inode;
+}
+
+/*
  * Choose mds to send request to next.  If there is a hint set in the
  * request (e.g., due to a prior forward hint from the mds), use that.
  * Otherwise, consult frag tree and/or caps to identify the
@@ -675,19 +703,6 @@ static void __unregister_request(struct ceph_mds_client *mdsc,
  *
  * Called under mdsc->mutex.
  */
-static struct dentry *get_nonsnap_parent(struct dentry *dentry)
-{
-	/*
-	 * we don't need to worry about protecting the d_parent access
-	 * here because we never renaming inside the snapped namespace
-	 * except to resplice to another snapdir, and either the old or new
-	 * result is a valid result.
-	 */
-	while (!IS_ROOT(dentry) && ceph_snap(d_inode(dentry)) != CEPH_NOSNAP)
-		dentry = dentry->d_parent;
-	return dentry;
-}
-
 static int __choose_mds(struct ceph_mds_client *mdsc,
 			struct ceph_mds_request *req)
 {
@@ -697,7 +712,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 	int mode = req->r_direct_mode;
 	int mds = -1;
 	u32 hash = req->r_direct_hash;
-	bool is_hash = req->r_direct_is_hash;
+	bool is_hash = test_bit(CEPH_MDS_R_DIRECT_IS_HASH, &req->r_req_flags);
 
 	/*
 	 * is there a specific mds we should try?  ignore hint if we have
@@ -717,30 +732,39 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 	inode = NULL;
 	if (req->r_inode) {
 		inode = req->r_inode;
+		ihold(inode);
 	} else if (req->r_dentry) {
 		/* ignore race with rename; old or new d_parent is okay */
-		struct dentry *parent = req->r_dentry->d_parent;
-		struct inode *dir = d_inode(parent);
+		struct dentry *parent;
+		struct inode *dir;
+
+		rcu_read_lock();
+		parent = req->r_dentry->d_parent;
+		dir = req->r_parent ? : d_inode_rcu(parent);
 
-		if (dir->i_sb != mdsc->fsc->sb) {
-			/* not this fs! */
+		if (!dir || dir->i_sb != mdsc->fsc->sb) {
+			/*  not this fs or parent went negative */
 			inode = d_inode(req->r_dentry);
+			if (inode)
+				ihold(inode);
 		} else if (ceph_snap(dir) != CEPH_NOSNAP) {
 			/* direct snapped/virtual snapdir requests
 			 * based on parent dir inode */
-			struct dentry *dn = get_nonsnap_parent(parent);
-			inode = d_inode(dn);
+			inode = get_nonsnap_parent(parent);
 			dout("__choose_mds using nonsnap parent %p\n", inode);
 		} else {
 			/* dentry target */
 			inode = d_inode(req->r_dentry);
 			if (!inode || mode == USE_AUTH_MDS) {
 				/* dir + name */
-				inode = dir;
+				inode = igrab(dir);
 				hash = ceph_dentry_hash(dir, req->r_dentry);
 				is_hash = true;
+			} else {
+				ihold(inode);
 			}
 		}
+		rcu_read_unlock();
 	}
 
 	dout("__choose_mds %p is_hash=%d (%d) mode %d\n", inode, (int)is_hash,
@@ -769,7 +793,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 				     (int)r, frag.ndist);
 				if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
 				    CEPH_MDS_STATE_ACTIVE)
-					return mds;
+					goto out;
 			}
 
 			/* since this file/dir wasn't known to be
@@ -784,7 +808,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 				     inode, ceph_vinop(inode), frag.frag, mds);
 				if (ceph_mdsmap_get_state(mdsc->mdsmap, mds) >=
 				    CEPH_MDS_STATE_ACTIVE)
-					return mds;
+					goto out;
 			}
 		}
 	}
@@ -797,6 +821,7 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 		cap = rb_entry(rb_first(&ci->i_caps), struct ceph_cap, ci_node);
 	if (!cap) {
 		spin_unlock(&ci->i_ceph_lock);
+		iput(inode);
 		goto random;
 	}
 	mds = cap->session->s_mds;
@@ -804,6 +829,8 @@ static int __choose_mds(struct ceph_mds_client *mdsc,
 	     inode, ceph_vinop(inode), mds,
 	     cap == ci->i_auth_cap ? "auth " : "", cap);
 	spin_unlock(&ci->i_ceph_lock);
+out:
+	iput(inode);
 	return mds;
 
 random:
@@ -978,7 +1005,7 @@ static void __open_export_target_sessions(struct ceph_mds_client *mdsc,
 	struct ceph_mds_session *ts;
 	int i, mds = session->s_mds;
 
-	if (mds >= mdsc->mdsmap->m_max_mds)
+	if (mds >= mdsc->mdsmap->m_num_mds)
 		return;
 
 	mi = &mdsc->mdsmap->m_info[mds];
@@ -1036,7 +1063,6 @@ static void cleanup_session_requests(struct ceph_mds_client *mdsc,
 	while (!list_empty(&session->s_unsafe)) {
 		req = list_first_entry(&session->s_unsafe,
 				       struct ceph_mds_request, r_unsafe_item);
-		list_del_init(&req->r_unsafe_item);
 		pr_warn_ratelimited(" dropping unsafe request %llu\n",
 				    req->r_tid);
 		__unregister_request(mdsc, req);
@@ -1146,7 +1172,7 @@ static int remove_session_caps_cb(struct inode *inode, struct ceph_cap *cap,
 		ci->i_ceph_flags |= CEPH_I_CAP_DROPPED;
 
 		if (ci->i_wrbuffer_ref > 0 &&
-		    ACCESS_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
+		    READ_ONCE(fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
 			invalidate = true;
 
 		while (!list_empty(&ci->i_cap_flush_list)) {
@@ -1526,9 +1552,15 @@ void ceph_send_cap_releases(struct ceph_mds_client *mdsc,
 	struct ceph_msg *msg = NULL;
 	struct ceph_mds_cap_release *head;
 	struct ceph_mds_cap_item *item;
+	struct ceph_osd_client *osdc = &mdsc->fsc->client->osdc;
 	struct ceph_cap *cap;
 	LIST_HEAD(tmp_list);
 	int num_cap_releases;
+	__le32	barrier, *cap_barrier;
+
+	down_read(&osdc->lock);
+	barrier = cpu_to_le32(osdc->epoch_barrier);
+	up_read(&osdc->lock);
 
 	spin_lock(&session->s_cap_lock);
 again:
@@ -1546,7 +1578,11 @@ again:
 			head = msg->front.iov_base;
 			head->num = cpu_to_le32(0);
 			msg->front.iov_len = sizeof(*head);
+
+			msg->hdr.version = cpu_to_le16(2);
+			msg->hdr.compat_version = cpu_to_le16(1);
 		}
+
 		cap = list_first_entry(&tmp_list, struct ceph_cap,
 					session_caps);
 		list_del(&cap->session_caps);
@@ -1564,6 +1600,11 @@ again:
 		ceph_put_cap(mdsc, cap);
 
 		if (le32_to_cpu(head->num) == CEPH_CAPS_PER_RELEASE) {
+			// Append cap_barrier field
+			cap_barrier = msg->front.iov_base + msg->front.iov_len;
+			*cap_barrier = barrier;
+			msg->front.iov_len += sizeof(*cap_barrier);
+
 			msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 			dout("send_cap_releases mds%d %p\n", session->s_mds, msg);
 			ceph_con_send(&session->s_con, msg);
@@ -1579,6 +1620,11 @@ again:
 	spin_unlock(&session->s_cap_lock);
 
 	if (msg) {
+		// Append cap_barrier field
+		cap_barrier = msg->front.iov_base + msg->front.iov_len;
+		*cap_barrier = barrier;
+		msg->front.iov_len += sizeof(*cap_barrier);
+
 		msg->hdr.front_len = cpu_to_le32(msg->front.iov_len);
 		dout("send_cap_releases mds%d %p\n", session->s_mds, msg);
 		ceph_con_send(&session->s_con, msg);
@@ -1659,7 +1705,7 @@ ceph_mdsc_create_request(struct ceph_mds_client *mdsc, int op, int mode)
 	init_completion(&req->r_safe_completion);
 	INIT_LIST_HEAD(&req->r_unsafe_item);
 
-	req->r_stamp = current_fs_time(mdsc->fsc->sb);
+	req->r_stamp = timespec_trunc(current_kernel_time(), mdsc->fsc->sb->s_time_gran);
 
 	req->r_op = op;
 	req->r_direct_mode = mode;
@@ -1775,18 +1821,23 @@ retry:
 	return path;
 }
 
-static int build_dentry_path(struct dentry *dentry,
+static int build_dentry_path(struct dentry *dentry, struct inode *dir,
 			     const char **ppath, int *ppathlen, u64 *pino,
 			     int *pfreepath)
 {
 	char *path;
 
-	if (ceph_snap(d_inode(dentry->d_parent)) == CEPH_NOSNAP) {
-		*pino = ceph_ino(d_inode(dentry->d_parent));
+	rcu_read_lock();
+	if (!dir)
+		dir = d_inode_rcu(dentry->d_parent);
+	if (dir && ceph_snap(dir) == CEPH_NOSNAP) {
+		*pino = ceph_ino(dir);
+		rcu_read_unlock();
 		*ppath = dentry->d_name.name;
 		*ppathlen = dentry->d_name.len;
 		return 0;
 	}
+	rcu_read_unlock();
 	path = ceph_mdsc_build_path(dentry, ppathlen, pino, 1);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
@@ -1822,8 +1873,8 @@ static int build_inode_path(struct inode *inode,
  * an explicit ino+path.
  */
 static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
-				  const char *rpath, u64 rino,
-				  const char **ppath, int *pathlen,
+				  struct inode *rdiri, const char *rpath,
+				  u64 rino, const char **ppath, int *pathlen,
 				  u64 *ino, int *freepath)
 {
 	int r = 0;
@@ -1833,7 +1884,8 @@ static int set_request_path_attr(struct inode *rinode, struct dentry *rdentry,
 		dout(" inode %p %llx.%llx\n", rinode, ceph_ino(rinode),
 		     ceph_snap(rinode));
 	} else if (rdentry) {
-		r = build_dentry_path(rdentry, ppath, pathlen, ino, freepath);
+		r = build_dentry_path(rdentry, rdiri, ppath, pathlen, ino,
+					freepath);
 		dout(" dentry %p %llx/%.*s\n", rdentry, *ino, *pathlen,
 		     *ppath);
 	} else if (rpath || rino) {
@@ -1866,7 +1918,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 	int ret;
 
 	ret = set_request_path_attr(req->r_inode, req->r_dentry,
-			      req->r_path1, req->r_ino1.ino,
+			      req->r_parent, req->r_path1, req->r_ino1.ino,
 			      &path1, &pathlen1, &ino1, &freepath1);
 	if (ret < 0) {
 		msg = ERR_PTR(ret);
@@ -1874,6 +1926,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 	}
 
 	ret = set_request_path_attr(NULL, req->r_old_dentry,
+			      req->r_old_dentry_dir,
 			      req->r_path2, req->r_ino2.ino,
 			      &path2, &pathlen2, &ino2, &freepath2);
 	if (ret < 0) {
@@ -1927,10 +1980,13 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 		      mds, req->r_inode_drop, req->r_inode_unless, 0);
 	if (req->r_dentry_drop)
 		releases += ceph_encode_dentry_release(&p, req->r_dentry,
-		       mds, req->r_dentry_drop, req->r_dentry_unless);
+				req->r_parent, mds, req->r_dentry_drop,
+				req->r_dentry_unless);
 	if (req->r_old_dentry_drop)
 		releases += ceph_encode_dentry_release(&p, req->r_old_dentry,
-		       mds, req->r_old_dentry_drop, req->r_old_dentry_unless);
+				req->r_old_dentry_dir, mds,
+				req->r_old_dentry_drop,
+				req->r_old_dentry_unless);
 	if (req->r_old_inode_drop)
 		releases += ceph_encode_inode_release(&p,
 		      d_inode(req->r_old_dentry),
@@ -1956,7 +2012,7 @@ static struct ceph_msg *create_request_message(struct ceph_mds_client *mdsc,
 
 	if (req->r_pagelist) {
 		struct ceph_pagelist *pagelist = req->r_pagelist;
-		atomic_inc(&pagelist->refcnt);
+		refcount_inc(&pagelist->refcnt);
 		ceph_msg_data_add_pagelist(msg, pagelist);
 		msg->hdr.data_len = cpu_to_le32(pagelist->length);
 	} else {
@@ -2012,7 +2068,7 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc,
 	dout("prepare_send_request %p tid %lld %s (attempt %d)\n", req,
 	     req->r_tid, ceph_mds_op_name(req->r_op), req->r_attempts);
 
-	if (req->r_got_unsafe) {
+	if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags)) {
 		void *p;
 		/*
 		 * Replay.  Do not regenerate message (and rebuild
@@ -2061,16 +2117,16 @@ static int __prepare_send_request(struct ceph_mds_client *mdsc,
 
 	rhead = msg->front.iov_base;
 	rhead->oldest_client_tid = cpu_to_le64(__get_oldest_tid(mdsc));
-	if (req->r_got_unsafe)
+	if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags))
 		flags |= CEPH_MDS_FLAG_REPLAY;
-	if (req->r_locked_dir)
+	if (req->r_parent)
 		flags |= CEPH_MDS_FLAG_WANT_DENTRY;
 	rhead->flags = cpu_to_le32(flags);
 	rhead->num_fwd = req->r_num_fwd;
 	rhead->num_retry = req->r_attempts - 1;
 	rhead->ino = 0;
 
-	dout(" r_locked_dir = %p\n", req->r_locked_dir);
+	dout(" r_parent = %p\n", req->r_parent);
 	return 0;
 }
 
@@ -2084,8 +2140,8 @@ static int __do_request(struct ceph_mds_client *mdsc,
 	int mds = -1;
 	int err = 0;
 
-	if (req->r_err || req->r_got_result) {
-		if (req->r_aborted)
+	if (req->r_err || test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags)) {
+		if (test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags))
 			__unregister_request(mdsc, req);
 		goto out;
 	}
@@ -2096,12 +2152,12 @@ static int __do_request(struct ceph_mds_client *mdsc,
 		err = -EIO;
 		goto finish;
 	}
-	if (ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
+	if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN) {
 		dout("do_request forced umount\n");
 		err = -EIO;
 		goto finish;
 	}
-	if (ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_MOUNTING) {
+	if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_MOUNTING) {
 		if (mdsc->mdsmap_err) {
 			err = mdsc->mdsmap_err;
 			dout("do_request mdsmap err %d\n", err);
@@ -2215,7 +2271,7 @@ static void kick_requests(struct ceph_mds_client *mdsc, int mds)
 	while (p) {
 		req = rb_entry(p, struct ceph_mds_request, r_node);
 		p = rb_next(p);
-		if (req->r_got_unsafe)
+		if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags))
 			continue;
 		if (req->r_attempts > 0)
 			continue; /* only new requests */
@@ -2250,11 +2306,11 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 
 	dout("do_request on %p\n", req);
 
-	/* take CAP_PIN refs for r_inode, r_locked_dir, r_old_dentry */
+	/* take CAP_PIN refs for r_inode, r_parent, r_old_dentry */
 	if (req->r_inode)
 		ceph_get_cap_refs(ceph_inode(req->r_inode), CEPH_CAP_PIN);
-	if (req->r_locked_dir)
-		ceph_get_cap_refs(ceph_inode(req->r_locked_dir), CEPH_CAP_PIN);
+	if (req->r_parent)
+		ceph_get_cap_refs(ceph_inode(req->r_parent), CEPH_CAP_PIN);
 	if (req->r_old_dentry_dir)
 		ceph_get_cap_refs(ceph_inode(req->r_old_dentry_dir),
 				  CEPH_CAP_PIN);
@@ -2289,7 +2345,7 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 	mutex_lock(&mdsc->mutex);
 
 	/* only abort if we didn't race with a real reply */
-	if (req->r_got_result) {
+	if (test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags)) {
 		err = le32_to_cpu(req->r_reply_info.head->result);
 	} else if (err < 0) {
 		dout("aborted request %lld with %d\n", req->r_tid, err);
@@ -2301,10 +2357,10 @@ int ceph_mdsc_do_request(struct ceph_mds_client *mdsc,
 		 */
 		mutex_lock(&req->r_fill_mutex);
 		req->r_err = err;
-		req->r_aborted = true;
+		set_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags);
 		mutex_unlock(&req->r_fill_mutex);
 
-		if (req->r_locked_dir &&
+		if (req->r_parent &&
 		    (req->r_op & CEPH_MDS_OP_WRITE))
 			ceph_invalidate_dir_request(req);
 	} else {
@@ -2323,7 +2379,7 @@ out:
  */
 void ceph_invalidate_dir_request(struct ceph_mds_request *req)
 {
-	struct inode *inode = req->r_locked_dir;
+	struct inode *inode = req->r_parent;
 
 	dout("invalidate_dir_request %p (complete, lease(s))\n", inode);
 
@@ -2379,14 +2435,14 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	}
 
 	/* dup? */
-	if ((req->r_got_unsafe && !head->safe) ||
-	    (req->r_got_safe && head->safe)) {
+	if ((test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags) && !head->safe) ||
+	    (test_bit(CEPH_MDS_R_GOT_SAFE, &req->r_req_flags) && head->safe)) {
 		pr_warn("got a dup %s reply on %llu from mds%d\n",
 			   head->safe ? "safe" : "unsafe", tid, mds);
 		mutex_unlock(&mdsc->mutex);
 		goto out;
 	}
-	if (req->r_got_safe) {
+	if (test_bit(CEPH_MDS_R_GOT_SAFE, &req->r_req_flags)) {
 		pr_warn("got unsafe after safe on %llu from mds%d\n",
 			   tid, mds);
 		mutex_unlock(&mdsc->mutex);
@@ -2425,10 +2481,10 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 
 
 	if (head->safe) {
-		req->r_got_safe = true;
+		set_bit(CEPH_MDS_R_GOT_SAFE, &req->r_req_flags);
 		__unregister_request(mdsc, req);
 
-		if (req->r_got_unsafe) {
+		if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags)) {
 			/*
 			 * We already handled the unsafe response, now do the
 			 * cleanup.  No need to examine the response; the MDS
@@ -2437,7 +2493,6 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 			 * useful we could do with a revised return value.
 			 */
 			dout("got safe reply %llu, mds%d\n", tid, mds);
-			list_del_init(&req->r_unsafe_item);
 
 			/* last unsafe request during umount? */
 			if (mdsc->stopping && !__get_oldest_req(mdsc))
@@ -2446,7 +2501,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 			goto out;
 		}
 	} else {
-		req->r_got_unsafe = true;
+		set_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags);
 		list_add_tail(&req->r_unsafe_item, &req->r_session->s_unsafe);
 		if (req->r_unsafe_dir) {
 			struct ceph_inode_info *ci =
@@ -2486,7 +2541,7 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	/* insert trace into our cache */
 	mutex_lock(&req->r_fill_mutex);
 	current->journal_info = req;
-	err = ceph_fill_trace(mdsc->fsc->sb, req, req->r_session);
+	err = ceph_fill_trace(mdsc->fsc->sb, req);
 	if (err == 0) {
 		if (result == 0 && (req->r_op == CEPH_MDS_OP_READDIR ||
 				    req->r_op == CEPH_MDS_OP_LSSNAP))
@@ -2500,7 +2555,8 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	if (realm)
 		ceph_put_snap_realm(mdsc, realm);
 
-	if (err == 0 && req->r_got_unsafe && req->r_target_inode) {
+	if (err == 0 && req->r_target_inode &&
+	    test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags)) {
 		struct ceph_inode_info *ci = ceph_inode(req->r_target_inode);
 		spin_lock(&ci->i_unsafe_lock);
 		list_add_tail(&req->r_unsafe_target_item, &ci->i_unsafe_iops);
@@ -2508,12 +2564,12 @@ static void handle_reply(struct ceph_mds_session *session, struct ceph_msg *msg)
 	}
 out_err:
 	mutex_lock(&mdsc->mutex);
-	if (!req->r_aborted) {
+	if (!test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
 		if (err) {
 			req->r_err = err;
 		} else {
 			req->r_reply =  ceph_msg_get(msg);
-			req->r_got_result = true;
+			set_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags);
 		}
 	} else {
 		dout("reply arrived after request %lld was aborted\n", tid);
@@ -2557,7 +2613,7 @@ static void handle_forward(struct ceph_mds_client *mdsc,
 		goto out;  /* dup reply? */
 	}
 
-	if (req->r_aborted) {
+	if (test_bit(CEPH_MDS_R_ABORTED, &req->r_req_flags)) {
 		dout("forward tid %llu aborted, unregistering\n", tid);
 		__unregister_request(mdsc, req);
 	} else if (fwd_seq <= req->r_num_fwd) {
@@ -2567,7 +2623,7 @@ static void handle_forward(struct ceph_mds_client *mdsc,
 		/* resend. forward race not possible; mds would drop */
 		dout("forward tid %llu to mds%d (we resend)\n", tid, next_mds);
 		BUG_ON(req->r_err);
-		BUG_ON(req->r_got_result);
+		BUG_ON(test_bit(CEPH_MDS_R_GOT_RESULT, &req->r_req_flags));
 		req->r_attempts = 0;
 		req->r_num_fwd = fwd_seq;
 		req->r_resend_mds = next_mds;
@@ -2603,8 +2659,10 @@ static void handle_session(struct ceph_mds_session *session,
 	seq = le64_to_cpu(h->seq);
 
 	mutex_lock(&mdsc->mutex);
-	if (op == CEPH_SESSION_CLOSE)
+	if (op == CEPH_SESSION_CLOSE) {
+		get_session(session);
 		__unregister_session(mdsc, session);
+	}
 	/* FIXME: this ttl calculation is generous */
 	session->s_ttl = jiffies + HZ*mdsc->mdsmap->m_session_autoclose;
 	mutex_unlock(&mdsc->mutex);
@@ -2693,6 +2751,8 @@ static void handle_session(struct ceph_mds_session *session,
 			kick_requests(mdsc, mds);
 		mutex_unlock(&mdsc->mutex);
 	}
+	if (op == CEPH_SESSION_CLOSE)
+		ceph_put_mds_session(session);
 	return;
 
 bad:
@@ -2732,7 +2792,7 @@ static void replay_unsafe_requests(struct ceph_mds_client *mdsc,
 	while (p) {
 		req = rb_entry(p, struct ceph_mds_request, r_node);
 		p = rb_next(p);
-		if (req->r_got_unsafe)
+		if (test_bit(CEPH_MDS_R_GOT_UNSAFE, &req->r_req_flags))
 			continue;
 		if (req->r_attempts == 0)
 			continue; /* only old requests */
@@ -3072,7 +3132,7 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 	dout("check_new_map new %u old %u\n",
 	     newmap->m_epoch, oldmap->m_epoch);
 
-	for (i = 0; i < oldmap->m_max_mds && i < mdsc->max_sessions; i++) {
+	for (i = 0; i < oldmap->m_num_mds && i < mdsc->max_sessions; i++) {
 		if (mdsc->sessions[i] == NULL)
 			continue;
 		s = mdsc->sessions[i];
@@ -3086,15 +3146,33 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		     ceph_mdsmap_is_laggy(newmap, i) ? " (laggy)" : "",
 		     ceph_session_state_name(s->s_state));
 
-		if (i >= newmap->m_max_mds ||
+		if (i >= newmap->m_num_mds ||
 		    memcmp(ceph_mdsmap_get_addr(oldmap, i),
 			   ceph_mdsmap_get_addr(newmap, i),
 			   sizeof(struct ceph_entity_addr))) {
 			if (s->s_state == CEPH_MDS_SESSION_OPENING) {
 				/* the session never opened, just close it
 				 * out now */
+				get_session(s);
+				__unregister_session(mdsc, s);
 				__wake_requests(mdsc, &s->s_waiting);
+				ceph_put_mds_session(s);
+			} else if (i >= newmap->m_num_mds) {
+				/* force close session for stopped mds */
+				get_session(s);
 				__unregister_session(mdsc, s);
+				__wake_requests(mdsc, &s->s_waiting);
+				kick_requests(mdsc, i);
+				mutex_unlock(&mdsc->mutex);
+
+				mutex_lock(&s->s_mutex);
+				cleanup_session_requests(mdsc, s);
+				remove_session_caps(s);
+				mutex_unlock(&s->s_mutex);
+
+				ceph_put_mds_session(s);
+
+				mutex_lock(&mdsc->mutex);
 			} else {
 				/* just close it */
 				mutex_unlock(&mdsc->mutex);
@@ -3132,7 +3210,7 @@ static void check_new_map(struct ceph_mds_client *mdsc,
 		}
 	}
 
-	for (i = 0; i < newmap->m_max_mds && i < mdsc->max_sessions; i++) {
+	for (i = 0; i < newmap->m_num_mds && i < mdsc->max_sessions; i++) {
 		s = mdsc->sessions[i];
 		if (!s)
 			continue;
@@ -3556,7 +3634,7 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
 {
 	u64 want_tid, want_flush;
 
-	if (ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
+	if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
 		return;
 
 	dout("sync\n");
@@ -3587,7 +3665,7 @@ void ceph_mdsc_sync(struct ceph_mds_client *mdsc)
  */
 static bool done_closing_sessions(struct ceph_mds_client *mdsc, int skipped)
 {
-	if (ACCESS_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
+	if (READ_ONCE(mdsc->fsc->mount_state) == CEPH_MOUNT_SHUTDOWN)
 		return true;
 	return atomic_read(&mdsc->num_sessions) <= skipped;
 }
@@ -3691,13 +3769,13 @@ static void ceph_mdsc_stop(struct ceph_mds_client *mdsc)
 void ceph_mdsc_destroy(struct ceph_fs_client *fsc)
 {
 	struct ceph_mds_client *mdsc = fsc->mdsc;
-
 	dout("mdsc_destroy %p\n", mdsc);
-	ceph_mdsc_stop(mdsc);
 
 	/* flush out any connection work with references to us */
 	ceph_msgr_flush();
 
+	ceph_mdsc_stop(mdsc);
+
 	fsc->mdsc = NULL;
 	kfree(mdsc);
 	dout("mdsc_destroy %p done\n", mdsc);
@@ -3846,7 +3924,7 @@ static struct ceph_connection *con_get(struct ceph_connection *con)
 	struct ceph_mds_session *s = con->private;
 
 	if (get_session(s)) {
-		dout("mdsc con_get %p ok (%d)\n", s, atomic_read(&s->s_ref));
+		dout("mdsc con_get %p ok (%d)\n", s, refcount_read(&s->s_ref));
 		return con;
 	}
 	dout("mdsc con_get %p FAIL\n", s);
@@ -3857,7 +3935,7 @@ static void con_put(struct ceph_connection *con)
 {
 	struct ceph_mds_session *s = con->private;
 
-	dout("mdsc con_put %p (%d)\n", s, atomic_read(&s->s_ref) - 1);
+	dout("mdsc con_put %p (%d)\n", s, refcount_read(&s->s_ref) - 1);
 	ceph_put_mds_session(s);
 }
 
diff --git a/fs/ceph/mds_client.h b/fs/ceph/mds_client.h
index 3c6f77b7bb02..db57ae98ed34 100644
--- a/fs/ceph/mds_client.h
+++ b/fs/ceph/mds_client.h
@@ -7,6 +7,7 @@
 #include <linux/mutex.h>
 #include <linux/rbtree.h>
 #include <linux/spinlock.h>
+#include <linux/refcount.h>
 
 #include <linux/ceph/types.h>
 #include <linux/ceph/messenger.h>
@@ -82,9 +83,10 @@ struct ceph_mds_reply_info_parsed {
 			struct ceph_mds_reply_dirfrag *dir_dir;
 			size_t			      dir_buf_size;
 			int                           dir_nr;
-			bool			      dir_complete;
 			bool			      dir_end;
+			bool			      dir_complete;
 			bool			      hash_order;
+			bool			      offset_hash;
 			struct ceph_mds_reply_dir_entry  *dir_entries;
 		};
 
@@ -104,10 +106,13 @@ struct ceph_mds_reply_info_parsed {
 
 /*
  * cap releases are batched and sent to the MDS en masse.
+ *
+ * Account for per-message overhead of mds_cap_release header
+ * and __le32 for osd epoch barrier trailing field.
  */
-#define CEPH_CAPS_PER_RELEASE ((PAGE_SIZE -			\
+#define CEPH_CAPS_PER_RELEASE ((PAGE_SIZE - sizeof(u32) -		\
 				sizeof(struct ceph_mds_cap_release)) /	\
-			       sizeof(struct ceph_mds_cap_item))
+			        sizeof(struct ceph_mds_cap_item))
 
 
 /*
@@ -156,7 +161,7 @@ struct ceph_mds_session {
 	unsigned long     s_renew_requested; /* last time we sent a renew req */
 	u64               s_renew_seq;
 
-	atomic_t          s_ref;
+	refcount_t          s_ref;
 	struct list_head  s_waiting;  /* waiting requests */
 	struct list_head  s_unsafe;   /* unsafe requests */
 };
@@ -202,9 +207,18 @@ struct ceph_mds_request {
 	char *r_path1, *r_path2;
 	struct ceph_vino r_ino1, r_ino2;
 
-	struct inode *r_locked_dir; /* dir (if any) i_mutex locked by vfs */
+	struct inode *r_parent;		    /* parent dir inode */
 	struct inode *r_target_inode;       /* resulting inode */
 
+#define CEPH_MDS_R_DIRECT_IS_HASH	(1) /* r_direct_hash is valid */
+#define CEPH_MDS_R_ABORTED		(2) /* call was aborted */
+#define CEPH_MDS_R_GOT_UNSAFE		(3) /* got an unsafe reply */
+#define CEPH_MDS_R_GOT_SAFE		(4) /* got a safe reply */
+#define CEPH_MDS_R_GOT_RESULT		(5) /* got a result */
+#define CEPH_MDS_R_DID_PREPOPULATE	(6) /* prepopulated readdir */
+#define CEPH_MDS_R_PARENT_LOCKED	(7) /* is r_parent->i_rwsem wlocked? */
+	unsigned long	r_req_flags;
+
 	struct mutex r_fill_mutex;
 
 	union ceph_mds_request_args r_args;
@@ -216,7 +230,6 @@ struct ceph_mds_request {
 	/* for choosing which mds to send this request to */
 	int r_direct_mode;
 	u32 r_direct_hash;      /* choose dir frag based on this dentry hash */
-	bool r_direct_is_hash;  /* true if r_direct_hash is valid */
 
 	/* data payload is used for xattr ops */
 	struct ceph_pagelist *r_pagelist;
@@ -234,7 +247,6 @@ struct ceph_mds_request {
 	struct ceph_mds_reply_info_parsed r_reply_info;
 	struct page *r_locked_page;
 	int r_err;
-	bool r_aborted;
 
 	unsigned long r_timeout;  /* optional.  jiffies, 0 is "wait forever" */
 	unsigned long r_started;  /* start time to measure timeout against */
@@ -262,9 +274,7 @@ struct ceph_mds_request {
 	ceph_mds_request_callback_t r_callback;
 	ceph_mds_request_wait_callback_t r_wait_for_completion;
 	struct list_head  r_unsafe_item;  /* per-session unsafe list item */
-	bool		  r_got_unsafe, r_got_safe, r_got_result;
 
-	bool              r_did_prepopulate;
 	long long	  r_dir_release_cnt;
 	long long	  r_dir_ordered_cnt;
 	int		  r_readdir_cache_idx;
@@ -368,7 +378,7 @@ __ceph_lookup_mds_session(struct ceph_mds_client *, int mds);
 static inline struct ceph_mds_session *
 ceph_get_mds_session(struct ceph_mds_session *s)
 {
-	atomic_inc(&s->s_ref);
+	refcount_inc(&s->s_ref);
 	return s;
 }
 
diff --git a/fs/ceph/mdsmap.c b/fs/ceph/mdsmap.c
index 5454e2327a5f..1a748cf88535 100644
--- a/fs/ceph/mdsmap.c
+++ b/fs/ceph/mdsmap.c
@@ -22,11 +22,11 @@ int ceph_mdsmap_get_random_mds(struct ceph_mdsmap *m)
 	int i;
 
 	/* special case for one mds */
-	if (1 == m->m_max_mds && m->m_info[0].state > 0)
+	if (1 == m->m_num_mds && m->m_info[0].state > 0)
 		return 0;
 
 	/* count */
-	for (i = 0; i < m->m_max_mds; i++)
+	for (i = 0; i < m->m_num_mds; i++)
 		if (m->m_info[i].state > 0)
 			n++;
 	if (n == 0)
@@ -135,8 +135,9 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 	m->m_session_autoclose = ceph_decode_32(p);
 	m->m_max_file_size = ceph_decode_64(p);
 	m->m_max_mds = ceph_decode_32(p);
+	m->m_num_mds = m->m_max_mds;
 
-	m->m_info = kcalloc(m->m_max_mds, sizeof(*m->m_info), GFP_NOFS);
+	m->m_info = kcalloc(m->m_num_mds, sizeof(*m->m_info), GFP_NOFS);
 	if (m->m_info == NULL)
 		goto nomem;
 
@@ -207,9 +208,20 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 		     ceph_pr_addr(&addr.in_addr),
 		     ceph_mds_state_name(state));
 
-		if (mds < 0 || mds >= m->m_max_mds || state <= 0)
+		if (mds < 0 || state <= 0)
 			continue;
 
+		if (mds >= m->m_num_mds) {
+			int new_num = max(mds + 1, m->m_num_mds * 2);
+			void *new_m_info = krealloc(m->m_info,
+						new_num * sizeof(*m->m_info),
+						GFP_NOFS | __GFP_ZERO);
+			if (!new_m_info)
+				goto nomem;
+			m->m_info = new_m_info;
+			m->m_num_mds = new_num;
+		}
+
 		info = &m->m_info[mds];
 		info->global_id = global_id;
 		info->state = state;
@@ -229,6 +241,14 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 			info->export_targets = NULL;
 		}
 	}
+	if (m->m_num_mds > m->m_max_mds) {
+		/* find max up mds */
+		for (i = m->m_num_mds; i >= m->m_max_mds; i--) {
+			if (i == 0 || m->m_info[i-1].state > 0)
+				break;
+		}
+		m->m_num_mds = i;
+	}
 
 	/* pg_pools */
 	ceph_decode_32_safe(p, end, n, bad);
@@ -270,12 +290,22 @@ struct ceph_mdsmap *ceph_mdsmap_decode(void **p, void *end)
 
 		for (i = 0; i < n; i++) {
 			s32 mds = ceph_decode_32(p);
-			if (mds >= 0 && mds < m->m_max_mds) {
+			if (mds >= 0 && mds < m->m_num_mds) {
 				if (m->m_info[mds].laggy)
 					num_laggy++;
 			}
 		}
 		m->m_num_laggy = num_laggy;
+
+		if (n > m->m_num_mds) {
+			void *new_m_info = krealloc(m->m_info,
+						    n * sizeof(*m->m_info),
+						    GFP_NOFS | __GFP_ZERO);
+			if (!new_m_info)
+				goto nomem;
+			m->m_info = new_m_info;
+		}
+		m->m_num_mds = n;
 	}
 
 	/* inc */
@@ -341,7 +371,7 @@ void ceph_mdsmap_destroy(struct ceph_mdsmap *m)
 {
 	int i;
 
-	for (i = 0; i < m->m_max_mds; i++)
+	for (i = 0; i < m->m_num_mds; i++)
 		kfree(m->m_info[i].export_targets);
 	kfree(m->m_info);
 	kfree(m->m_data_pg_pools);
@@ -357,7 +387,7 @@ bool ceph_mdsmap_is_cluster_available(struct ceph_mdsmap *m)
 		return false;
 	if (m->m_num_laggy > 0)
 		return false;
-	for (i = 0; i < m->m_max_mds; i++) {
+	for (i = 0; i < m->m_num_mds; i++) {
 		if (m->m_info[i].state == CEPH_MDS_STATE_ACTIVE)
 			nr_active++;
 	}
diff --git a/fs/ceph/snap.c b/fs/ceph/snap.c
index 8f8b41c2ef0f..dab5d6732345 100644
--- a/fs/ceph/snap.c
+++ b/fs/ceph/snap.c
@@ -519,7 +519,7 @@ void ceph_queue_cap_snap(struct ceph_inode_info *ci)
 	     capsnap->need_flush ? "" : "no_flush");
 	ihold(inode);
 
-	atomic_set(&capsnap->nref, 1);
+	refcount_set(&capsnap->nref, 1);
 	INIT_LIST_HEAD(&capsnap->ci_item);
 
 	capsnap->follows = old_snapc->seq;
diff --git a/fs/ceph/super.c b/fs/ceph/super.c
index 6bd20d707bfd..aa06a8c24792 100644
--- a/fs/ceph/super.c
+++ b/fs/ceph/super.c
@@ -121,6 +121,7 @@ enum {
 	/* int args above */
 	Opt_snapdirname,
 	Opt_mds_namespace,
+	Opt_fscache_uniq,
 	Opt_last_string,
 	/* string args above */
 	Opt_dirstat,
@@ -158,6 +159,7 @@ static match_table_t fsopt_tokens = {
 	/* int args above */
 	{Opt_snapdirname, "snapdirname=%s"},
 	{Opt_mds_namespace, "mds_namespace=%s"},
+	{Opt_fscache_uniq, "fsc=%s"},
 	/* string args above */
 	{Opt_dirstat, "dirstat"},
 	{Opt_nodirstat, "nodirstat"},
@@ -223,6 +225,14 @@ static int parse_fsopt_token(char *c, void *private)
 		if (!fsopt->mds_namespace)
 			return -ENOMEM;
 		break;
+	case Opt_fscache_uniq:
+		fsopt->fscache_uniq = kstrndup(argstr[0].from,
+					       argstr[0].to-argstr[0].from,
+					       GFP_KERNEL);
+		if (!fsopt->fscache_uniq)
+			return -ENOMEM;
+		fsopt->flags |= CEPH_MOUNT_OPT_FSCACHE;
+		break;
 		/* misc */
 	case Opt_wsize:
 		fsopt->wsize = intval;
@@ -317,6 +327,7 @@ static void destroy_mount_options(struct ceph_mount_options *args)
 	kfree(args->snapdir_name);
 	kfree(args->mds_namespace);
 	kfree(args->server_path);
+	kfree(args->fscache_uniq);
 	kfree(args);
 }
 
@@ -350,10 +361,12 @@ static int compare_mount_options(struct ceph_mount_options *new_fsopt,
 	ret = strcmp_null(fsopt1->mds_namespace, fsopt2->mds_namespace);
 	if (ret)
 		return ret;
-
 	ret = strcmp_null(fsopt1->server_path, fsopt2->server_path);
 	if (ret)
 		return ret;
+	ret = strcmp_null(fsopt1->fscache_uniq, fsopt2->fscache_uniq);
+	if (ret)
+		return ret;
 
 	return ceph_compare_options(new_opt, fsc->client);
 }
@@ -475,8 +488,12 @@ static int ceph_show_options(struct seq_file *m, struct dentry *root)
 		seq_puts(m, ",noasyncreaddir");
 	if ((fsopt->flags & CEPH_MOUNT_OPT_DCACHE) == 0)
 		seq_puts(m, ",nodcache");
-	if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE)
-		seq_puts(m, ",fsc");
+	if (fsopt->flags & CEPH_MOUNT_OPT_FSCACHE) {
+		if (fsopt->fscache_uniq)
+			seq_printf(m, ",fsc=%s", fsopt->fscache_uniq);
+		else
+			seq_puts(m, ",fsc");
+	}
 	if (fsopt->flags & CEPH_MOUNT_OPT_NOPOOLPERM)
 		seq_puts(m, ",nopoolperm");
 
@@ -544,10 +561,6 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 					struct ceph_options *opt)
 {
 	struct ceph_fs_client *fsc;
-	const u64 supported_features =
-		CEPH_FEATURE_FLOCK | CEPH_FEATURE_DIRLAYOUTHASH |
-		CEPH_FEATURE_MDSENC | CEPH_FEATURE_MDS_INLINE_DATA;
-	const u64 required_features = 0;
 	int page_count;
 	size_t size;
 	int err = -ENOMEM;
@@ -556,8 +569,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	if (!fsc)
 		return ERR_PTR(-ENOMEM);
 
-	fsc->client = ceph_create_client(opt, fsc, supported_features,
-					 required_features);
+	fsc->client = ceph_create_client(opt, fsc);
 	if (IS_ERR(fsc->client)) {
 		err = PTR_ERR(fsc->client);
 		goto fail;
@@ -579,10 +591,6 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 
 	atomic_long_set(&fsc->writeback_count, 0);
 
-	err = bdi_init(&fsc->backing_dev_info);
-	if (err < 0)
-		goto fail_client;
-
 	err = -ENOMEM;
 	/*
 	 * The number of concurrent works can be high but they don't need
@@ -590,7 +598,7 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	 */
 	fsc->wb_wq = alloc_workqueue("ceph-writeback", 0, 1);
 	if (fsc->wb_wq == NULL)
-		goto fail_bdi;
+		goto fail_client;
 	fsc->pg_inv_wq = alloc_workqueue("ceph-pg-invalid", 0, 1);
 	if (fsc->pg_inv_wq == NULL)
 		goto fail_wb_wq;
@@ -606,26 +614,17 @@ static struct ceph_fs_client *create_fs_client(struct ceph_mount_options *fsopt,
 	if (!fsc->wb_pagevec_pool)
 		goto fail_trunc_wq;
 
-	/* setup fscache */
-	if ((fsopt->flags & CEPH_MOUNT_OPT_FSCACHE) &&
-	    (ceph_fscache_register_fs(fsc) != 0))
-		goto fail_fscache;
-
 	/* caps */
 	fsc->min_caps = fsopt->max_readdir;
 
 	return fsc;
 
-fail_fscache:
-	ceph_fscache_unregister_fs(fsc);
 fail_trunc_wq:
 	destroy_workqueue(fsc->trunc_wq);
 fail_pg_inv_wq:
 	destroy_workqueue(fsc->pg_inv_wq);
 fail_wb_wq:
 	destroy_workqueue(fsc->wb_wq);
-fail_bdi:
-	bdi_destroy(&fsc->backing_dev_info);
 fail_client:
 	ceph_destroy_client(fsc->client);
 fail:
@@ -637,20 +636,14 @@ static void destroy_fs_client(struct ceph_fs_client *fsc)
 {
 	dout("destroy_fs_client %p\n", fsc);
 
-	ceph_fscache_unregister_fs(fsc);
-
 	destroy_workqueue(fsc->wb_wq);
 	destroy_workqueue(fsc->pg_inv_wq);
 	destroy_workqueue(fsc->trunc_wq);
 
-	bdi_destroy(&fsc->backing_dev_info);
-
 	mempool_destroy(fsc->wb_pagevec_pool);
 
 	destroy_mount_options(fsc->mount_options);
 
-	ceph_fs_debugfs_cleanup(fsc);
-
 	ceph_destroy_client(fsc->client);
 
 	kfree(fsc);
@@ -757,7 +750,6 @@ static const struct super_operations ceph_super_ops = {
 	.destroy_inode	= ceph_destroy_inode,
 	.write_inode    = ceph_write_inode,
 	.drop_inode	= ceph_drop_inode,
-	.evict_inode	= ceph_evict_inode,
 	.sync_fs        = ceph_sync_fs,
 	.put_super	= ceph_put_super,
 	.show_options   = ceph_show_options,
@@ -836,6 +828,13 @@ static struct dentry *ceph_real_mount(struct ceph_fs_client *fsc)
 		if (err < 0)
 			goto out;
 
+		/* setup fscache */
+		if (fsc->mount_options->flags & CEPH_MOUNT_OPT_FSCACHE) {
+			err = ceph_fscache_register_fs(fsc);
+			if (err < 0)
+				goto out;
+		}
+
 		if (!fsc->mount_options->server_path) {
 			path = "";
 			dout("mount opening path \\t\n");
@@ -938,25 +937,32 @@ static int ceph_compare_super(struct super_block *sb, void *data)
  */
 static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
 
-static int ceph_register_bdi(struct super_block *sb,
-			     struct ceph_fs_client *fsc)
+static int ceph_setup_bdi(struct super_block *sb, struct ceph_fs_client *fsc)
 {
 	int err;
 
+	err = super_setup_bdi_name(sb, "ceph-%ld",
+				   atomic_long_inc_return(&bdi_seq));
+	if (err)
+		return err;
+
 	/* set ra_pages based on rasize mount option? */
 	if (fsc->mount_options->rasize >= PAGE_SIZE)
-		fsc->backing_dev_info.ra_pages =
+		sb->s_bdi->ra_pages =
 			(fsc->mount_options->rasize + PAGE_SIZE - 1)
 			>> PAGE_SHIFT;
 	else
-		fsc->backing_dev_info.ra_pages =
-			VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
+		sb->s_bdi->ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_SIZE;
 
-	err = bdi_register(&fsc->backing_dev_info, NULL, "ceph-%ld",
-			   atomic_long_inc_return(&bdi_seq));
-	if (!err)
-		sb->s_bdi = &fsc->backing_dev_info;
-	return err;
+	if (fsc->mount_options->rsize > fsc->mount_options->rasize &&
+	    fsc->mount_options->rsize >= PAGE_SIZE)
+		sb->s_bdi->io_pages =
+			(fsc->mount_options->rsize + PAGE_SIZE - 1)
+			>> PAGE_SHIFT;
+	else if (fsc->mount_options->rsize == 0)
+		sb->s_bdi->io_pages = ULONG_MAX;
+
+	return 0;
 }
 
 static struct dentry *ceph_mount(struct file_system_type *fs_type,
@@ -1011,7 +1017,7 @@ static struct dentry *ceph_mount(struct file_system_type *fs_type,
 		dout("get_sb got existing client %p\n", fsc);
 	} else {
 		dout("get_sb using new client %p\n", fsc);
-		err = ceph_register_bdi(sb, fsc);
+		err = ceph_setup_bdi(sb, fsc);
 		if (err < 0) {
 			res = ERR_PTR(err);
 			goto out_splat;
@@ -1047,6 +1053,12 @@ static void ceph_kill_sb(struct super_block *s)
 
 	ceph_mdsc_pre_umount(fsc->mdsc);
 	generic_shutdown_super(s);
+
+	fsc->client->extra_mon_dispatch = NULL;
+	ceph_fs_debugfs_cleanup(fsc);
+
+	ceph_fscache_unregister_fs(fsc);
+
 	ceph_mdsc_destroy(fsc);
 
 	destroy_fs_client(fsc);
diff --git a/fs/ceph/super.h b/fs/ceph/super.h
index 3373b61faefd..f02a2225fe42 100644
--- a/fs/ceph/super.h
+++ b/fs/ceph/super.h
@@ -14,6 +14,7 @@
 #include <linux/writeback.h>
 #include <linux/slab.h>
 #include <linux/posix_acl.h>
+#include <linux/refcount.h>
 
 #include <linux/ceph/libceph.h>
 
@@ -45,8 +46,8 @@
 #define ceph_test_mount_opt(fsc, opt) \
 	(!!((fsc)->mount_options->flags & CEPH_MOUNT_OPT_##opt))
 
-#define CEPH_RSIZE_DEFAULT             0           /* max read size */
-#define CEPH_RASIZE_DEFAULT            (8192*1024) /* readahead */
+#define CEPH_RSIZE_DEFAULT              (64*1024*1024) /* max read size */
+#define CEPH_RASIZE_DEFAULT             (8192*1024)    /* max readahead */
 #define CEPH_MAX_READDIR_DEFAULT        1024
 #define CEPH_MAX_READDIR_BYTES_DEFAULT  (512*1024)
 #define CEPH_SNAPDIRNAME_DEFAULT        ".snap"
@@ -72,6 +73,7 @@ struct ceph_mount_options {
 	char *snapdir_name;   /* default ".snap" */
 	char *mds_namespace;  /* default NULL */
 	char *server_path;    /* default  "/" */
+	char *fscache_uniq;   /* default NULL */
 };
 
 struct ceph_fs_client {
@@ -92,8 +94,6 @@ struct ceph_fs_client {
 	struct workqueue_struct *trunc_wq;
 	atomic_long_t writeback_count;
 
-	struct backing_dev_info backing_dev_info;
-
 #ifdef CONFIG_DEBUG_FS
 	struct dentry *debugfs_dentry_lru, *debugfs_caps;
 	struct dentry *debugfs_congestion_kb;
@@ -162,7 +162,7 @@ struct ceph_cap_flush {
  * data before flushing the snapped state (tracked here) back to the MDS.
  */
 struct ceph_cap_snap {
-	atomic_t nref;
+	refcount_t nref;
 	struct list_head ci_item;
 
 	struct ceph_cap_flush cap_flush;
@@ -191,7 +191,7 @@ struct ceph_cap_snap {
 
 static inline void ceph_put_cap_snap(struct ceph_cap_snap *capsnap)
 {
-	if (atomic_dec_and_test(&capsnap->nref)) {
+	if (refcount_dec_and_test(&capsnap->nref)) {
 		if (capsnap->xattr_blob)
 			ceph_buffer_put(capsnap->xattr_blob);
 		kfree(capsnap);
@@ -343,7 +343,6 @@ struct ceph_inode_info {
 	u32 i_rdcache_gen;      /* incremented each time we get FILE_CACHE. */
 	u32 i_rdcache_revoking; /* RDCACHE gen to async invalidate, if any */
 
-	struct list_head i_unsafe_writes; /* uncommitted sync writes */
 	struct list_head i_unsafe_dirops; /* uncommitted mds dir ops */
 	struct list_head i_unsafe_iops;   /* uncommitted mds inode ops */
 	spinlock_t i_unsafe_lock;
@@ -474,6 +473,32 @@ static inline struct inode *ceph_find_inode(struct super_block *sb,
 #define CEPH_I_CAP_DROPPED	(1 << 8)  /* caps were forcibly dropped */
 #define CEPH_I_KICK_FLUSH	(1 << 9)  /* kick flushing caps */
 #define CEPH_I_FLUSH_SNAPS	(1 << 10) /* need flush snapss */
+#define CEPH_I_ERROR_WRITE	(1 << 11) /* have seen write errors */
+
+/*
+ * We set the ERROR_WRITE bit when we start seeing write errors on an inode
+ * and then clear it when they start succeeding. Note that we do a lockless
+ * check first, and only take the lock if it looks like it needs to be changed.
+ * The write submission code just takes this as a hint, so we're not too
+ * worried if a few slip through in either direction.
+ */
+static inline void ceph_set_error_write(struct ceph_inode_info *ci)
+{
+	if (!(READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE)) {
+		spin_lock(&ci->i_ceph_lock);
+		ci->i_ceph_flags |= CEPH_I_ERROR_WRITE;
+		spin_unlock(&ci->i_ceph_lock);
+	}
+}
+
+static inline void ceph_clear_error_write(struct ceph_inode_info *ci)
+{
+	if (READ_ONCE(ci->i_ceph_flags) & CEPH_I_ERROR_WRITE) {
+		spin_lock(&ci->i_ceph_lock);
+		ci->i_ceph_flags &= ~CEPH_I_ERROR_WRITE;
+		spin_unlock(&ci->i_ceph_lock);
+	}
+}
 
 static inline void __ceph_dir_set_complete(struct ceph_inode_info *ci,
 					   long long release_count,
@@ -602,7 +627,7 @@ static inline int __ceph_caps_wanted(struct ceph_inode_info *ci)
 }
 
 /* what the mds thinks we want */
-extern int __ceph_caps_mds_wanted(struct ceph_inode_info *ci);
+extern int __ceph_caps_mds_wanted(struct ceph_inode_info *ci, bool check);
 
 extern void ceph_caps_init(struct ceph_mds_client *mdsc);
 extern void ceph_caps_finalize(struct ceph_mds_client *mdsc);
@@ -753,7 +778,6 @@ extern const struct inode_operations ceph_file_iops;
 extern struct inode *ceph_alloc_inode(struct super_block *sb);
 extern void ceph_destroy_inode(struct inode *inode);
 extern int ceph_drop_inode(struct inode *inode);
-extern void ceph_evict_inode(struct inode *inode);
 
 extern struct inode *ceph_get_inode(struct super_block *sb,
 				    struct ceph_vino vino);
@@ -764,14 +788,13 @@ extern void ceph_fill_file_time(struct inode *inode, int issued,
 				u64 time_warp_seq, struct timespec *ctime,
 				struct timespec *mtime, struct timespec *atime);
 extern int ceph_fill_trace(struct super_block *sb,
-			   struct ceph_mds_request *req,
-			   struct ceph_mds_session *session);
+			   struct ceph_mds_request *req);
 extern int ceph_readdir_prepopulate(struct ceph_mds_request *req,
 				    struct ceph_mds_session *session);
 
 extern int ceph_inode_holds_cap(struct inode *inode, int mask);
 
-extern int ceph_inode_set_size(struct inode *inode, loff_t size);
+extern bool ceph_inode_set_size(struct inode *inode, loff_t size);
 extern void __ceph_do_pending_vmtruncate(struct inode *inode);
 extern void ceph_queue_vmtruncate(struct inode *inode);
 
@@ -787,8 +810,8 @@ static inline int ceph_do_getattr(struct inode *inode, int mask, bool force)
 extern int ceph_permission(struct inode *inode, int mask);
 extern int __ceph_setattr(struct inode *inode, struct iattr *attr);
 extern int ceph_setattr(struct dentry *dentry, struct iattr *attr);
-extern int ceph_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			struct kstat *stat);
+extern int ceph_getattr(const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int flags);
 
 /* xattr.c */
 int __ceph_setxattr(struct inode *, const char *, const void *, size_t, int);
@@ -896,6 +919,7 @@ extern void ceph_put_wrbuffer_cap_refs(struct ceph_inode_info *ci, int nr,
 				       struct ceph_snap_context *snapc);
 extern void ceph_flush_snaps(struct ceph_inode_info *ci,
 			     struct ceph_mds_session **psession);
+extern bool __ceph_should_report_size(struct ceph_inode_info *ci);
 extern void ceph_check_caps(struct ceph_inode_info *ci, int flags,
 			    struct ceph_mds_session *session);
 extern void ceph_check_delayed_caps(struct ceph_mds_client *mdsc);
@@ -904,6 +928,7 @@ extern void ceph_flush_dirty_caps(struct ceph_mds_client *mdsc);
 extern int ceph_encode_inode_release(void **p, struct inode *inode,
 				     int mds, int drop, int unless, int force);
 extern int ceph_encode_dentry_release(void **p, struct dentry *dn,
+				      struct inode *dir,
 				      int mds, int drop, int unless);
 
 extern int ceph_get_caps(struct ceph_inode_info *ci, int need, int want,
@@ -933,7 +958,7 @@ extern int ceph_atomic_open(struct inode *dir, struct dentry *dentry,
 extern int ceph_release(struct inode *inode, struct file *filp);
 extern void ceph_fill_inline_data(struct inode *inode, struct page *locked_page,
 				  char *data, size_t len);
-extern void ceph_sync_write_wait(struct inode *inode);
+
 /* dir.c */
 extern const struct file_operations ceph_dir_fops;
 extern const struct file_operations ceph_snapdir_fops;
diff --git a/fs/ceph/xattr.c b/fs/ceph/xattr.c
index febc28f9e2c2..11263f102e4c 100644
--- a/fs/ceph/xattr.c
+++ b/fs/ceph/xattr.c
@@ -392,6 +392,7 @@ static int __set_xattr(struct ceph_inode_info *ci,
 
 	if (update_xattr) {
 		int err = 0;
+
 		if (xattr && (flags & XATTR_CREATE))
 			err = -EEXIST;
 		else if (!xattr && (flags & XATTR_REPLACE))
@@ -399,12 +400,14 @@ static int __set_xattr(struct ceph_inode_info *ci,
 		if (err) {
 			kfree(name);
 			kfree(val);
+			kfree(*newxattr);
 			return err;
 		}
 		if (update_xattr < 0) {
 			if (xattr)
 				__remove_xattr(ci, xattr);
 			kfree(name);
+			kfree(*newxattr);
 			return 0;
 		}
 	}
@@ -753,6 +756,9 @@ ssize_t __ceph_getxattr(struct inode *inode, const char *name, void *value,
 	/* let's see if a virtual xattr was requested */
 	vxattr = ceph_match_vxattr(inode, name);
 	if (vxattr) {
+		err = ceph_do_getattr(inode, 0, true);
+		if (err)
+			return err;
 		err = -ENODATA;
 		if (!(vxattr->exists_cb && !vxattr->exists_cb(ci)))
 			err = vxattr->getxattr_cb(ci, value, size);
diff --git a/fs/char_dev.c b/fs/char_dev.c
index 44a240c4bb65..fb8507f521b2 100644
--- a/fs/char_dev.c
+++ b/fs/char_dev.c
@@ -471,6 +471,85 @@ int cdev_add(struct cdev *p, dev_t dev, unsigned count)
 	return 0;
 }
 
+/**
+ * cdev_set_parent() - set the parent kobject for a char device
+ * @p: the cdev structure
+ * @kobj: the kobject to take a reference to
+ *
+ * cdev_set_parent() sets a parent kobject which will be referenced
+ * appropriately so the parent is not freed before the cdev. This
+ * should be called before cdev_add.
+ */
+void cdev_set_parent(struct cdev *p, struct kobject *kobj)
+{
+	WARN_ON(!kobj->state_initialized);
+	p->kobj.parent = kobj;
+}
+
+/**
+ * cdev_device_add() - add a char device and it's corresponding
+ *	struct device, linkink
+ * @dev: the device structure
+ * @cdev: the cdev structure
+ *
+ * cdev_device_add() adds the char device represented by @cdev to the system,
+ * just as cdev_add does. It then adds @dev to the system using device_add
+ * The dev_t for the char device will be taken from the struct device which
+ * needs to be initialized first. This helper function correctly takes a
+ * reference to the parent device so the parent will not get released until
+ * all references to the cdev are released.
+ *
+ * This helper uses dev->devt for the device number. If it is not set
+ * it will not add the cdev and it will be equivalent to device_add.
+ *
+ * This function should be used whenever the struct cdev and the
+ * struct device are members of the same structure whose lifetime is
+ * managed by the struct device.
+ *
+ * NOTE: Callers must assume that userspace was able to open the cdev and
+ * can call cdev fops callbacks at any time, even if this function fails.
+ */
+int cdev_device_add(struct cdev *cdev, struct device *dev)
+{
+	int rc = 0;
+
+	if (dev->devt) {
+		cdev_set_parent(cdev, &dev->kobj);
+
+		rc = cdev_add(cdev, dev->devt, 1);
+		if (rc)
+			return rc;
+	}
+
+	rc = device_add(dev);
+	if (rc)
+		cdev_del(cdev);
+
+	return rc;
+}
+
+/**
+ * cdev_device_del() - inverse of cdev_device_add
+ * @dev: the device structure
+ * @cdev: the cdev structure
+ *
+ * cdev_device_del() is a helper function to call cdev_del and device_del.
+ * It should be used whenever cdev_device_add is used.
+ *
+ * If dev->devt is not set it will not remove the cdev and will be equivalent
+ * to device_del.
+ *
+ * NOTE: This guarantees that associated sysfs callbacks are not running
+ * or runnable, however any cdevs already open will remain and their fops
+ * will still be callable even after this function returns.
+ */
+void cdev_device_del(struct cdev *cdev, struct device *dev)
+{
+	device_del(dev);
+	if (dev->devt)
+		cdev_del(cdev);
+}
+
 static void cdev_unmap(dev_t dev, unsigned count)
 {
 	kobj_unmap(cdev_map, dev, count);
@@ -482,6 +561,10 @@ static void cdev_unmap(dev_t dev, unsigned count)
  *
  * cdev_del() removes @p from the system, possibly freeing the structure
  * itself.
+ *
+ * NOTE: This guarantees that cdev device will no longer be able to be
+ * opened, however any cdevs already open will remain and their fops will
+ * still be callable even after cdev_del returns.
  */
 void cdev_del(struct cdev *p)
 {
@@ -570,5 +653,8 @@ EXPORT_SYMBOL(cdev_init);
 EXPORT_SYMBOL(cdev_alloc);
 EXPORT_SYMBOL(cdev_del);
 EXPORT_SYMBOL(cdev_add);
+EXPORT_SYMBOL(cdev_set_parent);
+EXPORT_SYMBOL(cdev_device_add);
+EXPORT_SYMBOL(cdev_device_del);
 EXPORT_SYMBOL(__register_chrdev);
 EXPORT_SYMBOL(__unregister_chrdev);
diff --git a/fs/cifs/Kconfig b/fs/cifs/Kconfig
index e7b478b49985..f7243617316c 100644
--- a/fs/cifs/Kconfig
+++ b/fs/cifs/Kconfig
@@ -1,5 +1,5 @@
 config CIFS
-	tristate "CIFS support (advanced network filesystem, SMBFS successor)"
+	tristate "SMB3 and CIFS support (advanced network filesystem)"
 	depends on INET
 	select NLS
 	select CRYPTO
@@ -9,31 +9,36 @@ config CIFS
 	select CRYPTO_ARC4
 	select CRYPTO_ECB
 	select CRYPTO_DES
-	select CRYPTO_SHA256
-	select CRYPTO_CMAC
 	help
-	  This is the client VFS module for the Common Internet File System
-	  (CIFS) protocol which is the successor to the Server Message Block
-	  (SMB) protocol, the native file sharing mechanism for most early
-	  PC operating systems.  The CIFS protocol is fully supported by
-	  file servers such as Windows 2000 (including Windows 2003, Windows 2008,
-	  NT 4 and Windows XP) as well by Samba (which provides excellent CIFS
+	  This is the client VFS module for the SMB3 family of NAS protocols,
+	  as well as for earlier dialects such as SMB2.1, SMB2 and the
+	  Common Internet File System (CIFS) protocol.  CIFS was the successor
+	  to the original dialect, the Server Message Block (SMB) protocol, the
+	  native file sharing mechanism for most early PC operating systems.
+
+	  The SMB3 protocol is supported by most modern operating systems and
+	  NAS appliances (e.g. Samba, Windows 8, Windows 2012, MacOS).
+	  The older CIFS protocol was included in Windows NT4, 2000 and XP (and
+	  later) as well by Samba (which provides excellent CIFS and SMB3
 	  server support for Linux and many other operating systems). Limited
-	  support for OS/2 and Windows ME and similar servers is provided as
-	  well.
+	  support for OS/2 and Windows ME and similar very old servers is
+	  provided as well.
 
-	  The module also provides optional support for the followon
-	  protocols for CIFS including SMB3, which enables
-	  useful performance and security features (see the description
-	  of CONFIG_CIFS_SMB2).
-
-	  The cifs module provides an advanced network file system
-	  client for mounting to CIFS compliant servers.  It includes
+	  The cifs module provides an advanced network file system client
+	  for mounting to SMB3 (and CIFS) compliant servers.  It includes
 	  support for DFS (hierarchical name space), secure per-user
 	  session establishment via Kerberos or NTLM or NTLMv2,
 	  safe distributed caching (oplock), optional packet
 	  signing, Unicode and other internationalization improvements.
-	  If you need to mount to Samba or Windows from this machine, say Y.
+
+	  In general, the default dialects, SMB3 and later, enable better
+	  performance, security and features, than would be possible with CIFS.
+	  Note that when mounting to Samba, due to the CIFS POSIX extensions,
+	  CIFS mounts can provide slightly better POSIX compatibility
+	  than SMB3 mounts. SMB2/SMB3 mount options are also
+	  slightly simpler (compared to CIFS) due to protocol improvements.
+
+	  If you need to mount to Samba, Macs or Windows from this machine, say Y.
 
 config CIFS_STATS
         bool "CIFS statistics"
@@ -91,7 +96,7 @@ config CIFS_UPCALL
 	  Enables an upcall mechanism for CIFS which accesses userspace helper
 	  utilities to provide SPNEGO packaged (RFC 4178) Kerberos tickets
 	  which are needed to mount to certain secure servers (for which more
-	  secure Kerberos authentication is required). If unsure, say N.
+	  secure Kerberos authentication is required). If unsure, say Y.
 
 config CIFS_XATTR
         bool "CIFS extended attributes"
@@ -107,7 +112,7 @@ config CIFS_XATTR
           (used by some filesystems to store ACLs) is not supported at
           this time.
 
-          If unsure, say N.
+          If unsure, say Y.
 
 config CIFS_POSIX
         bool "CIFS POSIX Extensions"
@@ -127,7 +132,7 @@ config CIFS_ACL
 	  help
 	    Allows fetching CIFS/NTFS ACL from the server.  The DACL blob
 	    is handed over to the application/caller.  See the man
-	    page for getcifsacl for more information.
+	    page for getcifsacl for more information.  If unsure, say Y.
 
 config CIFS_DEBUG
 	bool "Enable CIFS debugging routines"
@@ -148,6 +153,16 @@ config CIFS_DEBUG2
 	   option can be turned off unless you are debugging
 	   cifs problems.  If unsure, say N.
 
+config CIFS_DEBUG_DUMP_KEYS
+	bool "Dump encryption keys for offline decryption (Unsafe)"
+	depends on CIFS_DEBUG
+	help
+	   Enabling this will dump the encryption and decryption keys
+	   used to communicate on an encrypted share connection on the
+	   console. This allows Wireshark to decrypt and dissect
+	   encrypted network captures. Enable this carefully.
+	   If unsure, say N.
+
 config CIFS_DFS_UPCALL
 	  bool "DFS feature support"
 	  depends on CIFS && KEYS
@@ -159,7 +174,7 @@ config CIFS_DFS_UPCALL
 	    an upcall mechanism for CIFS which contacts userspace helper
 	    utilities to provide server name resolution (host names to
 	    IP addresses) which is needed for implicit mounts of DFS junction
-	    points. If unsure, say N.
+	    points. If unsure, say Y.
 
 config CIFS_NFSD_EXPORT
 	  bool "Allow nfsd to export CIFS file system"
@@ -167,34 +182,9 @@ config CIFS_NFSD_EXPORT
 	  help
 	   Allows NFS server to export a CIFS mounted share (nfsd over cifs)
 
-config CIFS_SMB2
-	bool "SMB2 and SMB3 network file system support"
-	depends on CIFS && INET
-	select NLS
-	select KEYS
-	select FSCACHE
-	select DNS_RESOLVER
-
-	help
-	  This enables support for the Server Message Block version 2
-	  family of protocols, including SMB3.  SMB3 support is
-	  enabled on mount by specifying "vers=3.0" in the mount
-	  options. These protocols are the successors to the popular
-	  CIFS and SMB network file sharing protocols. SMB3 is the
-	  native file sharing mechanism for the more recent
-	  versions of Windows (Windows 8 and Windows 2012 and
-	  later) and Samba server and many others support SMB3 well.
-	  In general SMB3 enables better performance, security
-	  and features, than would be possible with CIFS (Note that
-	  when mounting to Samba, due to the CIFS POSIX extensions,
-	  CIFS mounts can provide slightly better POSIX compatibility
-	  than SMB3 mounts do though). Note that SMB2/SMB3 mount
-	  options are also slightly simpler (compared to CIFS) due
-	  to protocol improvements.
-
 config CIFS_SMB311
 	bool "SMB3.1.1 network file system support (Experimental)"
-	depends on CIFS_SMB2 && INET
+	depends on CIFS
 
 	help
 	  This enables experimental support for the newest, SMB3.1.1, dialect.
diff --git a/fs/cifs/Makefile b/fs/cifs/Makefile
index eed7eb09f46f..5e853a395b92 100644
--- a/fs/cifs/Makefile
+++ b/fs/cifs/Makefile
@@ -6,7 +6,9 @@ obj-$(CONFIG_CIFS) += cifs.o
 cifs-y := cifsfs.o cifssmb.o cifs_debug.o connect.o dir.o file.o inode.o \
 	  link.o misc.o netmisc.o smbencrypt.o transport.o asn1.o \
 	  cifs_unicode.o nterr.o cifsencrypt.o \
-	  readdir.o ioctl.o sess.o export.o smb1ops.o winucase.o
+	  readdir.o ioctl.o sess.o export.o smb1ops.o winucase.o \
+	  smb2ops.o smb2maperror.o smb2transport.o \
+	  smb2misc.o smb2pdu.o smb2inode.o smb2file.o
 
 cifs-$(CONFIG_CIFS_XATTR) += xattr.o
 cifs-$(CONFIG_CIFS_ACL) += cifsacl.o
@@ -16,6 +18,3 @@ cifs-$(CONFIG_CIFS_UPCALL) += cifs_spnego.o
 cifs-$(CONFIG_CIFS_DFS_UPCALL) += dns_resolve.o cifs_dfs_ref.o
 
 cifs-$(CONFIG_CIFS_FSCACHE) += fscache.o cache.o
-
-cifs-$(CONFIG_CIFS_SMB2) += smb2ops.o smb2maperror.o smb2transport.o \
-			    smb2misc.o smb2pdu.o smb2inode.o smb2file.o
diff --git a/fs/cifs/cifs_dfs_ref.c b/fs/cifs/cifs_dfs_ref.c
index ec9dbbcca3b9..6b61df117fd4 100644
--- a/fs/cifs/cifs_dfs_ref.c
+++ b/fs/cifs/cifs_dfs_ref.c
@@ -245,7 +245,8 @@ compose_mount_options_err:
  * @fullpath:		full path in UNC format
  * @ref:		server's referral
  */
-static struct vfsmount *cifs_dfs_do_refmount(struct cifs_sb_info *cifs_sb,
+static struct vfsmount *cifs_dfs_do_refmount(struct dentry *mntpt,
+		struct cifs_sb_info *cifs_sb,
 		const char *fullpath, const struct dfs_info3_param *ref)
 {
 	struct vfsmount *mnt;
@@ -259,7 +260,7 @@ static struct vfsmount *cifs_dfs_do_refmount(struct cifs_sb_info *cifs_sb,
 	if (IS_ERR(mountdata))
 		return (struct vfsmount *)mountdata;
 
-	mnt = vfs_kern_mount(&cifs_fs_type, 0, devname, mountdata);
+	mnt = vfs_submount(mntpt, &cifs_fs_type, devname, mountdata);
 	kfree(mountdata);
 	kfree(devname);
 	return mnt;
@@ -302,7 +303,9 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 	 * gives us the latter, so we must adjust the result.
 	 */
 	mnt = ERR_PTR(-ENOMEM);
-	full_path = build_path_from_dentry(mntpt);
+
+	/* always use tree name prefix */
+	full_path = build_path_from_dentry_optional_prefix(mntpt, true);
 	if (full_path == NULL)
 		goto cdda_exit;
 
@@ -334,7 +337,7 @@ static struct vfsmount *cifs_dfs_do_automount(struct dentry *mntpt)
 			mnt = ERR_PTR(-EINVAL);
 			break;
 		}
-		mnt = cifs_dfs_do_refmount(cifs_sb,
+		mnt = cifs_dfs_do_refmount(mntpt, cifs_sb,
 				full_path, referrals + i);
 		cifs_dbg(FYI, "%s: cifs_dfs_do_refmount:%s , mnt:%p\n",
 			 __func__, referrals[i].node_name, mnt);
diff --git a/fs/cifs/cifs_fs_sb.h b/fs/cifs/cifs_fs_sb.h
index 07ed81cf1552..cbd216b57239 100644
--- a/fs/cifs/cifs_fs_sb.h
+++ b/fs/cifs/cifs_fs_sb.h
@@ -68,7 +68,6 @@ struct cifs_sb_info {
 	umode_t	mnt_dir_mode;
 	unsigned int mnt_cifs_flags;
 	char   *mountdata; /* options received at mount time or via DFS refs */
-	struct backing_dev_info bdi;
 	struct delayed_work prune_tlinks;
 	struct rcu_head rcu;
 	char *prepath;
diff --git a/fs/cifs/cifs_unicode.c b/fs/cifs/cifs_unicode.c
index 02b071bf3732..b380e0871372 100644
--- a/fs/cifs/cifs_unicode.c
+++ b/fs/cifs/cifs_unicode.c
@@ -79,10 +79,17 @@ convert_sfu_char(const __u16 src_char, char *target)
 static bool
 convert_sfm_char(const __u16 src_char, char *target)
 {
+	if (src_char >= 0xF001 && src_char <= 0xF01F) {
+		*target = src_char - 0xF000;
+		return true;
+	}
 	switch (src_char) {
 	case SFM_COLON:
 		*target = ':';
 		break;
+	case SFM_DOUBLEQUOTE:
+		*target = '"';
+		break;
 	case SFM_ASTERISK:
 		*target = '*';
 		break;
@@ -414,10 +421,17 @@ static __le16 convert_to_sfm_char(char src_char, bool end_of_string)
 {
 	__le16 dest_char;
 
+	if (src_char >= 0x01 && src_char <= 0x1F) {
+		dest_char = cpu_to_le16(src_char + 0xF000);
+		return dest_char;
+	}
 	switch (src_char) {
 	case ':':
 		dest_char = cpu_to_le16(SFM_COLON);
 		break;
+	case '"':
+		dest_char = cpu_to_le16(SFM_DOUBLEQUOTE);
+		break;
 	case '*':
 		dest_char = cpu_to_le16(SFM_ASTERISK);
 		break;
@@ -574,7 +588,6 @@ ctoUTF16_out:
 	return j;
 }
 
-#ifdef CONFIG_CIFS_SMB2
 /*
  * cifs_local_to_utf16_bytes - how long will a string be after conversion?
  * @from - pointer to input string
@@ -633,4 +646,3 @@ cifs_strndup_to_utf16(const char *src, const int maxlen, int *utf16_len,
 	*utf16_len = len;
 	return dst;
 }
-#endif /* CONFIG_CIFS_SMB2 */
diff --git a/fs/cifs/cifs_unicode.h b/fs/cifs/cifs_unicode.h
index 479bc0a941f3..8360b74530a9 100644
--- a/fs/cifs/cifs_unicode.h
+++ b/fs/cifs/cifs_unicode.h
@@ -57,6 +57,7 @@
  * not conflict (although almost does) with the mapping above.
  */
 
+#define SFM_DOUBLEQUOTE ((__u16) 0xF020)
 #define SFM_ASTERISK    ((__u16) 0xF021)
 #define SFM_QUESTION    ((__u16) 0xF025)
 #define SFM_COLON       ((__u16) 0xF022)
@@ -64,8 +65,8 @@
 #define SFM_LESSTHAN    ((__u16) 0xF023)
 #define SFM_PIPE        ((__u16) 0xF027)
 #define SFM_SLASH       ((__u16) 0xF026)
-#define SFM_PERIOD	((__u16) 0xF028)
-#define SFM_SPACE	((__u16) 0xF029)
+#define SFM_SPACE	((__u16) 0xF028)
+#define SFM_PERIOD	((__u16) 0xF029)
 
 /*
  * Mapping mechanism to use when one of the seven reserved characters is
@@ -115,11 +116,9 @@ char *cifs_strndup_from_utf16(const char *src, const int maxlen,
 extern int cifsConvertToUTF16(__le16 *target, const char *source, int maxlen,
 			      const struct nls_table *cp, int mapChars);
 extern int cifs_remap(struct cifs_sb_info *cifs_sb);
-#ifdef CONFIG_CIFS_SMB2
 extern __le16 *cifs_strndup_to_utf16(const char *src, const int maxlen,
 				     int *utf16_len, const struct nls_table *cp,
 				     int remap);
-#endif /* CONFIG_CIFS_SMB2 */
 #endif
 
 wchar_t cifs_toupper(wchar_t in);
@@ -130,10 +129,10 @@ wchar_t cifs_toupper(wchar_t in);
  * Returns:
  *     Address of the first string
  */
-static inline wchar_t *
-UniStrcat(wchar_t *ucs1, const wchar_t *ucs2)
+static inline __le16 *
+UniStrcat(__le16 *ucs1, const __le16 *ucs2)
 {
-	wchar_t *anchor = ucs1;	/* save a pointer to start of ucs1 */
+	__le16 *anchor = ucs1;	/* save a pointer to start of ucs1 */
 
 	while (*ucs1++) ;	/* To end of first string */
 	ucs1--;			/* Return to the null */
diff --git a/fs/cifs/cifsacl.c b/fs/cifs/cifsacl.c
index 15bac390dff9..b98436f5c7c7 100644
--- a/fs/cifs/cifsacl.c
+++ b/fs/cifs/cifsacl.c
@@ -1135,20 +1135,19 @@ cifs_acl_to_fattr(struct cifs_sb_info *cifs_sb, struct cifs_fattr *fattr,
 	u32 acllen = 0;
 	int rc = 0;
 	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
-	struct cifs_tcon *tcon;
+	struct smb_version_operations *ops;
 
 	cifs_dbg(NOISY, "converting ACL to mode for %s\n", path);
 
 	if (IS_ERR(tlink))
 		return PTR_ERR(tlink);
-	tcon = tlink_tcon(tlink);
 
-	if (pfid && (tcon->ses->server->ops->get_acl_by_fid))
-		pntsd = tcon->ses->server->ops->get_acl_by_fid(cifs_sb, pfid,
-							  &acllen);
-	else if (tcon->ses->server->ops->get_acl)
-		pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
-							&acllen);
+	ops = tlink_tcon(tlink)->ses->server->ops;
+
+	if (pfid && (ops->get_acl_by_fid))
+		pntsd = ops->get_acl_by_fid(cifs_sb, pfid, &acllen);
+	else if (ops->get_acl)
+		pntsd = ops->get_acl(cifs_sb, inode, path, &acllen);
 	else {
 		cifs_put_tlink(tlink);
 		return -EOPNOTSUPP;
@@ -1181,23 +1180,23 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
 	struct cifs_ntsd *pnntsd = NULL; /* modified acl to be sent to server */
 	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
-	struct cifs_tcon *tcon;
+	struct smb_version_operations *ops;
 
 	if (IS_ERR(tlink))
 		return PTR_ERR(tlink);
-	tcon = tlink_tcon(tlink);
+
+	ops = tlink_tcon(tlink)->ses->server->ops;
 
 	cifs_dbg(NOISY, "set ACL from mode for %s\n", path);
 
 	/* Get the security descriptor */
 
-	if (tcon->ses->server->ops->get_acl == NULL) {
+	if (ops->get_acl == NULL) {
 		cifs_put_tlink(tlink);
 		return -EOPNOTSUPP;
 	}
 
-	pntsd = tcon->ses->server->ops->get_acl(cifs_sb, inode, path,
-						&secdesclen);
+	pntsd = ops->get_acl(cifs_sb, inode, path, &secdesclen);
 	if (IS_ERR(pntsd)) {
 		rc = PTR_ERR(pntsd);
 		cifs_dbg(VFS, "%s: error %d getting sec desc\n", __func__, rc);
@@ -1224,13 +1223,12 @@ id_mode_to_cifs_acl(struct inode *inode, const char *path, __u64 nmode,
 
 	cifs_dbg(NOISY, "build_sec_desc rc: %d\n", rc);
 
-	if (tcon->ses->server->ops->set_acl == NULL)
+	if (ops->set_acl == NULL)
 		rc = -EOPNOTSUPP;
 
 	if (!rc) {
 		/* Set the security descriptor */
-		rc = tcon->ses->server->ops->set_acl(pnntsd, secdesclen, inode,
-						     path, aclflag);
+		rc = ops->set_acl(pnntsd, secdesclen, inode, path, aclflag);
 		cifs_dbg(NOISY, "set_cifs_acl rc: %d\n", rc);
 	}
 	cifs_put_tlink(tlink);
diff --git a/fs/cifs/cifsencrypt.c b/fs/cifs/cifsencrypt.c
index 66bd7fa9b7a6..68abbb0db608 100644
--- a/fs/cifs/cifsencrypt.c
+++ b/fs/cifs/cifsencrypt.c
@@ -34,6 +34,7 @@
 #include <linux/random.h>
 #include <linux/highmem.h>
 #include <crypto/skcipher.h>
+#include <crypto/aead.h>
 
 static int
 cifs_crypto_shash_md5_allocate(struct TCP_Server_Info *server)
@@ -75,24 +76,20 @@ int __cifs_calc_signature(struct smb_rqst *rqst,
 	struct kvec *iov = rqst->rq_iov;
 	int n_vec = rqst->rq_nvec;
 
-	for (i = 0; i < n_vec; i++) {
+	if (n_vec < 2 || iov[0].iov_len != 4)
+		return -EIO;
+
+	for (i = 1; i < n_vec; i++) {
 		if (iov[i].iov_len == 0)
 			continue;
 		if (iov[i].iov_base == NULL) {
 			cifs_dbg(VFS, "null iovec entry\n");
 			return -EIO;
 		}
-		/* The first entry includes a length field (which does not get
-		   signed that occupies the first 4 bytes before the header */
-		if (i == 0) {
-			if (iov[0].iov_len <= 8) /* cmd field at offset 9 */
-				break; /* nothing to sign or corrupt header */
-			rc = crypto_shash_update(shash,
-				iov[i].iov_base + 4, iov[i].iov_len - 4);
-		} else {
-			rc = crypto_shash_update(shash,
-				iov[i].iov_base, iov[i].iov_len);
-		}
+		if (i == 1 && iov[1].iov_len <= 4)
+			break; /* nothing to sign or corrupt header */
+		rc = crypto_shash_update(shash,
+					 iov[i].iov_base, iov[i].iov_len);
 		if (rc) {
 			cifs_dbg(VFS, "%s: Could not update with payload\n",
 				 __func__);
@@ -168,6 +165,10 @@ int cifs_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server,
 	char smb_signature[20];
 	struct smb_hdr *cifs_pdu = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
 
+	if (rqst->rq_iov[0].iov_len != 4 ||
+	    rqst->rq_iov[0].iov_base + 4 != rqst->rq_iov[1].iov_base)
+		return -EIO;
+
 	if ((cifs_pdu == NULL) || (server == NULL))
 		return -EINVAL;
 
@@ -209,12 +210,14 @@ int cifs_sign_smbv(struct kvec *iov, int n_vec, struct TCP_Server_Info *server,
 int cifs_sign_smb(struct smb_hdr *cifs_pdu, struct TCP_Server_Info *server,
 		  __u32 *pexpected_response_sequence_number)
 {
-	struct kvec iov;
+	struct kvec iov[2];
 
-	iov.iov_base = cifs_pdu;
-	iov.iov_len = be32_to_cpu(cifs_pdu->smb_buf_length) + 4;
+	iov[0].iov_base = cifs_pdu;
+	iov[0].iov_len = 4;
+	iov[1].iov_base = (char *)cifs_pdu + 4;
+	iov[1].iov_len = be32_to_cpu(cifs_pdu->smb_buf_length);
 
-	return cifs_sign_smbv(&iov, 1, server,
+	return cifs_sign_smbv(iov, 2, server,
 			      pexpected_response_sequence_number);
 }
 
@@ -227,6 +230,10 @@ int cifs_verify_signature(struct smb_rqst *rqst,
 	char what_we_think_sig_should_be[20];
 	struct smb_hdr *cifs_pdu = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
 
+	if (rqst->rq_iov[0].iov_len != 4 ||
+	    rqst->rq_iov[0].iov_base + 4 != rqst->rq_iov[1].iov_base)
+		return -EIO;
+
 	if (cifs_pdu == NULL || server == NULL)
 		return -EINVAL;
 
@@ -471,6 +478,7 @@ find_timestamp(struct cifs_ses *ses)
 	unsigned char *blobptr;
 	unsigned char *blobend;
 	struct ntlmssp2_name *attrptr;
+	struct timespec ts;
 
 	if (!ses->auth_key.len || !ses->auth_key.response)
 		return 0;
@@ -495,7 +503,8 @@ find_timestamp(struct cifs_ses *ses)
 		blobptr += attrsize; /* advance attr value */
 	}
 
-	return cpu_to_le64(cifs_UnixTimeToNT(CURRENT_TIME));
+	ktime_get_real_ts(&ts);
+	return cpu_to_le64(cifs_UnixTimeToNT(ts));
 }
 
 static int calc_ntlmv2_hash(struct cifs_ses *ses, char *ntlmv2_hash,
@@ -868,7 +877,7 @@ out:
 }
 
 void
-cifs_crypto_shash_release(struct TCP_Server_Info *server)
+cifs_crypto_secmech_release(struct TCP_Server_Info *server)
 {
 	if (server->secmech.cmacaes) {
 		crypto_free_shash(server->secmech.cmacaes);
@@ -890,6 +899,16 @@ cifs_crypto_shash_release(struct TCP_Server_Info *server)
 		server->secmech.hmacmd5 = NULL;
 	}
 
+	if (server->secmech.ccmaesencrypt) {
+		crypto_free_aead(server->secmech.ccmaesencrypt);
+		server->secmech.ccmaesencrypt = NULL;
+	}
+
+	if (server->secmech.ccmaesdecrypt) {
+		crypto_free_aead(server->secmech.ccmaesdecrypt);
+		server->secmech.ccmaesdecrypt = NULL;
+	}
+
 	kfree(server->secmech.sdesccmacaes);
 	server->secmech.sdesccmacaes = NULL;
 	kfree(server->secmech.sdeschmacsha256);
diff --git a/fs/cifs/cifsfs.c b/fs/cifs/cifsfs.c
index 70f4e65fced2..180b3356ff86 100644
--- a/fs/cifs/cifsfs.c
+++ b/fs/cifs/cifsfs.c
@@ -37,6 +37,7 @@
 #include <linux/freezer.h>
 #include <linux/namei.h>
 #include <linux/random.h>
+#include <linux/uuid.h>
 #include <linux/xattr.h>
 #include <net/ipv6.h>
 #include "cifsfs.h"
@@ -50,9 +51,7 @@
 #include <linux/key-type.h>
 #include "cifs_spnego.h"
 #include "fscache.h"
-#ifdef CONFIG_CIFS_SMB2
 #include "smb2pdu.h"
-#endif
 
 int cifsFYI = 0;
 bool traceSMB;
@@ -87,6 +86,7 @@ extern mempool_t *cifs_req_poolp;
 extern mempool_t *cifs_mid_poolp;
 
 struct workqueue_struct	*cifsiod_wq;
+struct workqueue_struct	*cifsoplockd_wq;
 __u32 cifs_lock_secret;
 
 /*
@@ -138,7 +138,12 @@ cifs_read_super(struct super_block *sb)
 	sb->s_magic = CIFS_MAGIC_NUMBER;
 	sb->s_op = &cifs_super_ops;
 	sb->s_xattr = cifs_xattr_handlers;
-	sb->s_bdi = &cifs_sb->bdi;
+	rc = super_setup_bdi(sb);
+	if (rc)
+		goto out_no_root;
+	/* tune readahead according to rsize */
+	sb->s_bdi->ra_pages = cifs_sb->rsize / PAGE_SIZE;
+
 	sb->s_blocksize = CIFS_MAX_MSGSIZE;
 	sb->s_blocksize_bits = 14;	/* default 2**14 = CIFS_MAX_MSGSIZE */
 	inode = cifs_root_iget(sb);
@@ -270,9 +275,8 @@ cifs_alloc_inode(struct super_block *sb)
 	cifs_inode->uniqueid = 0;
 	cifs_inode->createtime = 0;
 	cifs_inode->epoch = 0;
-#ifdef CONFIG_CIFS_SMB2
 	generate_random_uuid(cifs_inode->lease_key);
-#endif
+
 	/*
 	 * Can not set i_flags here - they get immediately overwritten to zero
 	 * by the VFS.
@@ -972,6 +976,86 @@ out:
 	return rc;
 }
 
+ssize_t cifs_file_copychunk_range(unsigned int xid,
+				struct file *src_file, loff_t off,
+				struct file *dst_file, loff_t destoff,
+				size_t len, unsigned int flags)
+{
+	struct inode *src_inode = file_inode(src_file);
+	struct inode *target_inode = file_inode(dst_file);
+	struct cifsFileInfo *smb_file_src;
+	struct cifsFileInfo *smb_file_target;
+	struct cifs_tcon *src_tcon;
+	struct cifs_tcon *target_tcon;
+	ssize_t rc;
+
+	cifs_dbg(FYI, "copychunk range\n");
+
+	if (src_inode == target_inode) {
+		rc = -EINVAL;
+		goto out;
+	}
+
+	if (!src_file->private_data || !dst_file->private_data) {
+		rc = -EBADF;
+		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
+		goto out;
+	}
+
+	rc = -EXDEV;
+	smb_file_target = dst_file->private_data;
+	smb_file_src = src_file->private_data;
+	src_tcon = tlink_tcon(smb_file_src->tlink);
+	target_tcon = tlink_tcon(smb_file_target->tlink);
+
+	if (src_tcon->ses != target_tcon->ses) {
+		cifs_dbg(VFS, "source and target of copy not on same server\n");
+		goto out;
+	}
+
+	/*
+	 * Note: cifs case is easier than btrfs since server responsible for
+	 * checks for proper open modes and file type and if it wants
+	 * server could even support copy of range where source = target
+	 */
+	lock_two_nondirectories(target_inode, src_inode);
+
+	cifs_dbg(FYI, "about to flush pages\n");
+	/* should we flush first and last page first */
+	truncate_inode_pages(&target_inode->i_data, 0);
+
+	if (target_tcon->ses->server->ops->copychunk_range)
+		rc = target_tcon->ses->server->ops->copychunk_range(xid,
+			smb_file_src, smb_file_target, off, len, destoff);
+	else
+		rc = -EOPNOTSUPP;
+
+	/* force revalidate of size and timestamps of target file now
+	 * that target is updated on the server
+	 */
+	CIFS_I(target_inode)->time = 0;
+	/* although unlocking in the reverse order from locking is not
+	 * strictly necessary here it is a little cleaner to be consistent
+	 */
+	unlock_two_nondirectories(src_inode, target_inode);
+
+out:
+	return rc;
+}
+
+static ssize_t cifs_copy_file_range(struct file *src_file, loff_t off,
+				struct file *dst_file, loff_t destoff,
+				size_t len, unsigned int flags)
+{
+	unsigned int xid = get_xid();
+	ssize_t rc;
+
+	rc = cifs_file_copychunk_range(xid, src_file, off, dst_file, destoff,
+					len, flags);
+	free_xid(xid);
+	return rc;
+}
+
 const struct file_operations cifs_file_ops = {
 	.read_iter = cifs_loose_read_iter,
 	.write_iter = cifs_file_write_iter,
@@ -984,6 +1068,7 @@ const struct file_operations cifs_file_ops = {
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -1001,6 +1086,7 @@ const struct file_operations cifs_file_strict_ops = {
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -1018,6 +1104,7 @@ const struct file_operations cifs_file_direct_ops = {
 	.mmap = cifs_file_mmap,
 	.splice_read = generic_file_splice_read,
 	.unlocked_ioctl  = cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.llseek = cifs_llseek,
 	.setlease = cifs_setlease,
@@ -1035,6 +1122,7 @@ const struct file_operations cifs_file_nobrl_ops = {
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -1051,6 +1139,7 @@ const struct file_operations cifs_file_strict_nobrl_ops = {
 	.splice_read = generic_file_splice_read,
 	.llseek = cifs_llseek,
 	.unlocked_ioctl	= cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.setlease = cifs_setlease,
 	.fallocate = cifs_fallocate,
@@ -1067,6 +1156,7 @@ const struct file_operations cifs_file_direct_nobrl_ops = {
 	.mmap = cifs_file_mmap,
 	.splice_read = generic_file_splice_read,
 	.unlocked_ioctl  = cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.llseek = cifs_llseek,
 	.setlease = cifs_setlease,
@@ -1078,6 +1168,7 @@ const struct file_operations cifs_dir_ops = {
 	.release = cifs_closedir,
 	.read    = generic_read_dir,
 	.unlocked_ioctl  = cifs_ioctl,
+	.copy_file_range = cifs_copy_file_range,
 	.clone_file_range = cifs_clone_file_range,
 	.llseek = generic_file_llseek,
 };
@@ -1119,14 +1210,12 @@ cifs_destroy_inodecache(void)
 static int
 cifs_init_request_bufs(void)
 {
-	size_t max_hdr_size = MAX_CIFS_HDR_SIZE;
-#ifdef CONFIG_CIFS_SMB2
 	/*
 	 * SMB2 maximum header size is bigger than CIFS one - no problems to
 	 * allocate some more bytes for CIFS.
 	 */
-	max_hdr_size = MAX_SMB2_HDR_SIZE;
-#endif
+	size_t max_hdr_size = MAX_SMB2_HDR_SIZE;
+
 	if (CIFSMaxBufSize < 8192) {
 	/* Buffer size can not be smaller than 2 * PATH_MAX since maximum
 	Unicode path name has to fit in any SMB/CIFS path based frames */
@@ -1265,7 +1354,7 @@ init_cifs(void)
 	spin_lock_init(&cifs_tcp_ses_lock);
 	spin_lock_init(&GlobalMid_Lock);
 
-	get_random_bytes(&cifs_lock_secret, sizeof(cifs_lock_secret));
+	cifs_lock_secret = get_random_u32();
 
 	if (cifs_max_pending < 2) {
 		cifs_max_pending = 2;
@@ -1282,9 +1371,16 @@ init_cifs(void)
 		goto out_clean_proc;
 	}
 
+	cifsoplockd_wq = alloc_workqueue("cifsoplockd",
+					 WQ_FREEZABLE|WQ_MEM_RECLAIM, 0);
+	if (!cifsoplockd_wq) {
+		rc = -ENOMEM;
+		goto out_destroy_cifsiod_wq;
+	}
+
 	rc = cifs_fscache_register();
 	if (rc)
-		goto out_destroy_wq;
+		goto out_destroy_cifsoplockd_wq;
 
 	rc = cifs_init_inodecache();
 	if (rc)
@@ -1332,7 +1428,9 @@ out_destroy_inodecache:
 	cifs_destroy_inodecache();
 out_unreg_fscache:
 	cifs_fscache_unregister();
-out_destroy_wq:
+out_destroy_cifsoplockd_wq:
+	destroy_workqueue(cifsoplockd_wq);
+out_destroy_cifsiod_wq:
 	destroy_workqueue(cifsiod_wq);
 out_clean_proc:
 	cifs_proc_clean();
@@ -1355,6 +1453,7 @@ exit_cifs(void)
 	cifs_destroy_mids();
 	cifs_destroy_inodecache();
 	cifs_fscache_unregister();
+	destroy_workqueue(cifsoplockd_wq);
 	destroy_workqueue(cifsiod_wq);
 	cifs_proc_clean();
 }
@@ -1365,5 +1464,17 @@ MODULE_DESCRIPTION
     ("VFS to access servers complying with the SNIA CIFS Specification "
      "e.g. Samba and Windows");
 MODULE_VERSION(CIFS_VERSION);
+MODULE_SOFTDEP("pre: arc4");
+MODULE_SOFTDEP("pre: des");
+MODULE_SOFTDEP("pre: ecb");
+MODULE_SOFTDEP("pre: hmac");
+MODULE_SOFTDEP("pre: md4");
+MODULE_SOFTDEP("pre: md5");
+MODULE_SOFTDEP("pre: nls");
+MODULE_SOFTDEP("pre: aes");
+MODULE_SOFTDEP("pre: cmac");
+MODULE_SOFTDEP("pre: sha256");
+MODULE_SOFTDEP("pre: aead2");
+MODULE_SOFTDEP("pre: ccm");
 module_init(init_cifs)
 module_exit(exit_cifs)
diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h
index c9c00a862036..30bf89b1fd9a 100644
--- a/fs/cifs/cifsfs.h
+++ b/fs/cifs/cifsfs.h
@@ -83,7 +83,7 @@ extern int cifs_revalidate_dentry(struct dentry *);
 extern int cifs_invalidate_mapping(struct inode *inode);
 extern int cifs_revalidate_mapping(struct inode *inode);
 extern int cifs_zap_mapping(struct inode *inode);
-extern int cifs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int cifs_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int cifs_setattr(struct dentry *, struct iattr *);
 
 extern const struct inode_operations cifs_file_inode_ops;
@@ -139,6 +139,11 @@ extern ssize_t	cifs_listxattr(struct dentry *, char *, size_t);
 # define cifs_listxattr NULL
 #endif
 
+extern ssize_t cifs_file_copychunk_range(unsigned int xid,
+					struct file *src_file, loff_t off,
+					struct file *dst_file, loff_t destoff,
+					size_t len, unsigned int flags);
+
 extern long cifs_ioctl(struct file *filep, unsigned int cmd, unsigned long arg);
 #ifdef CONFIG_CIFS_NFSD_EXPORT
 extern const struct export_operations cifs_export_ops;
diff --git a/fs/cifs/cifsglob.h b/fs/cifs/cifsglob.h
index 7ea8a3393936..221693fe49ec 100644
--- a/fs/cifs/cifsglob.h
+++ b/fs/cifs/cifsglob.h
@@ -29,9 +29,7 @@
 #include <crypto/internal/hash.h>
 #include <linux/scatterlist.h>
 #include <uapi/linux/cifs/cifs_mount.h>
-#ifdef CONFIG_CIFS_SMB2
 #include "smb2pdu.h"
-#endif
 
 #define CIFS_MAGIC_NUMBER 0xFF534D42      /* the first four bytes of SMB PDUs */
 
@@ -136,6 +134,8 @@ struct cifs_secmech {
 	struct sdesc *sdescmd5; /* ctxt to generate cifs/smb signature */
 	struct sdesc *sdeschmacsha256;  /* ctxt to generate smb2 signature */
 	struct sdesc *sdesccmacaes;  /* ctxt to generate smb3 signature */
+	struct crypto_aead *ccmaesencrypt; /* smb3 encryption aead */
+	struct crypto_aead *ccmaesdecrypt; /* smb3 decryption aead */
 };
 
 /* per smb session structure/fields */
@@ -208,7 +208,7 @@ struct cifsInodeInfo;
 struct cifs_open_parms;
 
 struct smb_version_operations {
-	int (*send_cancel)(struct TCP_Server_Info *, void *,
+	int (*send_cancel)(struct TCP_Server_Info *, struct smb_rqst *,
 			   struct mid_q_entry *);
 	bool (*compare_fids)(struct cifsFileInfo *, struct cifsFileInfo *);
 	/* setup request: allocate mid, sign message */
@@ -241,6 +241,7 @@ struct smb_version_operations {
 	/* verify the message */
 	int (*check_message)(char *, unsigned int, struct TCP_Server_Info *);
 	bool (*is_oplock_break)(char *, struct TCP_Server_Info *);
+	int (*handle_cancelled_mid)(char *, struct TCP_Server_Info *);
 	void (*downgrade_oplock)(struct TCP_Server_Info *,
 					struct cifsInodeInfo *, bool);
 	/* process transaction2 response */
@@ -364,6 +365,8 @@ struct smb_version_operations {
 	unsigned int (*calc_smb_size)(void *);
 	/* check for STATUS_PENDING and process it in a positive case */
 	bool (*is_status_pending)(char *, struct TCP_Server_Info *, int);
+	/* check for STATUS_NETWORK_SESSION_EXPIRED */
+	bool (*is_session_expired)(char *);
 	/* send oplock break response */
 	int (*oplock_response)(struct cifs_tcon *, struct cifs_fid *,
 			       struct cifsInodeInfo *);
@@ -405,16 +408,17 @@ struct smb_version_operations {
 	char * (*create_lease_buf)(u8 *, u8);
 	/* parse lease context buffer and return oplock/epoch info */
 	__u8 (*parse_lease_buf)(void *, unsigned int *);
-	int (*clone_range)(const unsigned int, struct cifsFileInfo *src_file,
-			struct cifsFileInfo *target_file, u64 src_off, u64 len,
-			u64 dest_off);
+	ssize_t (*copychunk_range)(const unsigned int,
+			struct cifsFileInfo *src_file,
+			struct cifsFileInfo *target_file,
+			u64 src_off, u64 len, u64 dest_off);
 	int (*duplicate_extents)(const unsigned int, struct cifsFileInfo *src,
 			struct cifsFileInfo *target_file, u64 src_off, u64 len,
 			u64 dest_off);
 	int (*validate_negotiate)(const unsigned int, struct cifs_tcon *);
 	ssize_t (*query_all_EAs)(const unsigned int, struct cifs_tcon *,
 			const unsigned char *, const unsigned char *, char *,
-			size_t, const struct nls_table *, int);
+			size_t, struct cifs_sb_info *);
 	int (*set_EA)(const unsigned int, struct cifs_tcon *, const char *,
 			const char *, const void *, const __u16,
 			const struct nls_table *, int);
@@ -433,6 +437,17 @@ struct smb_version_operations {
 	bool (*dir_needs_close)(struct cifsFileInfo *);
 	long (*fallocate)(struct file *, struct cifs_tcon *, int, loff_t,
 			  loff_t);
+	/* init transform request - used for encryption for now */
+	int (*init_transform_rq)(struct TCP_Server_Info *, struct smb_rqst *,
+				 struct smb_rqst *);
+	/* free transform request */
+	void (*free_transform_rq)(struct smb_rqst *);
+	int (*is_transform_hdr)(void *buf);
+	int (*receive_transform)(struct TCP_Server_Info *,
+				 struct mid_q_entry **);
+	enum securityEnum (*select_sectype)(struct TCP_Server_Info *,
+			    enum securityEnum);
+
 };
 
 struct smb_version_values {
@@ -595,12 +610,10 @@ struct TCP_Server_Info {
 	__u16 sec_mode;
 	bool sign; /* is signing enabled on this connection? */
 	bool session_estab; /* mark when very first sess is established */
-#ifdef CONFIG_CIFS_SMB2
 	int echo_credits;  /* echo reserved slots */
 	int oplock_credits;  /* oplock break reserved slots */
 	bool echoes:1; /* enable echoes */
 	__u8 client_guid[SMB2_CLIENT_GUID_SIZE]; /* Client GUID */
-#endif
 	u16 dialect; /* dialect index that server chose */
 	bool oplocks:1; /* enable oplocks */
 	unsigned int maxReq;	/* Clients should submit no more */
@@ -644,13 +657,11 @@ struct TCP_Server_Info {
 	atomic_t in_send; /* requests trying to send */
 	atomic_t num_waiters;   /* blocked waiting to get in sendrecv */
 #endif
-#ifdef CONFIG_CIFS_SMB2
 	unsigned int	max_read;
 	unsigned int	max_write;
 	__u8		preauth_hash[512];
 	struct delayed_work reconnect; /* reconnect workqueue job */
 	struct mutex reconnect_mutex; /* prevent simultaneous reconnects */
-#endif /* CONFIG_CIFS_SMB2 */
 	unsigned long echo_interval;
 };
 
@@ -812,7 +823,7 @@ struct cifs_ses {
 	int ses_count;		/* reference counter */
 	enum statusEnum status;
 	unsigned overrideSecFlg;  /* if non-zero override global sec flags */
-	__u16 ipc_tid;		/* special tid for connection to IPC share */
+	__u32 ipc_tid;		/* special tid for connection to IPC share */
 	char *serverOS;		/* name of operating system underlying server */
 	char *serverNOS;	/* name of network operating system of server */
 	char *serverDomain;	/* security realm of server */
@@ -832,13 +843,11 @@ struct cifs_ses {
 	bool sign;		/* is signing required? */
 	bool need_reconnect:1; /* connection reset, uid now invalid */
 	bool domainAuto:1;
-#ifdef CONFIG_CIFS_SMB2
 	__u16 session_flags;
 	__u8 smb3signingkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3encryptionkey[SMB3_SIGN_KEY_SIZE];
 	__u8 smb3decryptionkey[SMB3_SIGN_KEY_SIZE];
 	__u8 preauth_hash[512];
-#endif /* CONFIG_CIFS_SMB2 */
 };
 
 static inline bool
@@ -890,12 +899,10 @@ struct cifs_tcon {
 			atomic_t num_acl_get;
 			atomic_t num_acl_set;
 		} cifs_stats;
-#ifdef CONFIG_CIFS_SMB2
 		struct {
 			atomic_t smb2_com_sent[NUMBER_OF_SMB2_COMMANDS];
 			atomic_t smb2_com_failed[NUMBER_OF_SMB2_COMMANDS];
 		} smb2_stats;
-#endif /* CONFIG_CIFS_SMB2 */
 	} stats;
 #ifdef CONFIG_CIFS_STATS2
 	unsigned long long time_writes;
@@ -931,9 +938,7 @@ struct cifs_tcon {
 	bool need_reopen_files:1; /* need to reopen tcon file handles */
 	bool use_resilient:1; /* use resilient instead of durable handles */
 	bool use_persistent:1; /* use persistent instead of durable handles */
-#ifdef CONFIG_CIFS_SMB2
 	bool print:1;		/* set if connection to printer share */
-	bool bad_network_name:1; /* set if ret status STATUS_BAD_NETWORK_NAME */
 	__le32 capabilities;
 	__u32 share_flags;
 	__u32 maximal_access;
@@ -945,7 +950,6 @@ struct cifs_tcon {
 	__u32 max_chunks;
 	__u32 max_bytes_chunk;
 	__u32 max_bytes_copy;
-#endif /* CONFIG_CIFS_SMB2 */
 #ifdef CONFIG_CIFS_FSCACHE
 	u64 resource_id;		/* server resource id */
 	struct fscache_cookie *fscache;	/* cookie for share */
@@ -1048,12 +1052,10 @@ struct cifs_open_parms {
 
 struct cifs_fid {
 	__u16 netfid;
-#ifdef CONFIG_CIFS_SMB2
 	__u64 persistent_fid;	/* persist file id for smb2 */
 	__u64 volatile_fid;	/* volatile file id for smb2 */
 	__u8 lease_key[SMB2_LEASE_KEY_SIZE];	/* lease key for smb2 */
 	__u8 create_guid[16];
-#endif
 	struct cifs_pending_open *pending_open;
 	unsigned int epoch;
 	bool purge_cache;
@@ -1091,16 +1093,31 @@ struct cifsFileInfo {
 
 struct cifs_io_parms {
 	__u16 netfid;
-#ifdef CONFIG_CIFS_SMB2
 	__u64 persistent_fid;	/* persist file id for smb2 */
 	__u64 volatile_fid;	/* volatile file id for smb2 */
-#endif
 	__u32 pid;
 	__u64 offset;
 	unsigned int length;
 	struct cifs_tcon *tcon;
 };
 
+struct cifs_aio_ctx {
+	struct kref		refcount;
+	struct list_head	list;
+	struct mutex		aio_mutex;
+	struct completion	done;
+	struct iov_iter		iter;
+	struct kiocb		*iocb;
+	struct cifsFileInfo	*cfile;
+	struct bio_vec		*bv;
+	loff_t			pos;
+	unsigned int		npages;
+	ssize_t			rc;
+	unsigned int		len;
+	unsigned int		total_len;
+	bool			should_dirty;
+};
+
 struct cifs_readdata;
 
 /* asynchronous read support */
@@ -1110,6 +1127,7 @@ struct cifs_readdata {
 	struct completion		done;
 	struct cifsFileInfo		*cfile;
 	struct address_space		*mapping;
+	struct cifs_aio_ctx		*ctx;
 	__u64				offset;
 	unsigned int			bytes;
 	unsigned int			got_bytes;
@@ -1119,7 +1137,10 @@ struct cifs_readdata {
 	int (*read_into_pages)(struct TCP_Server_Info *server,
 				struct cifs_readdata *rdata,
 				unsigned int len);
-	struct kvec			iov;
+	int (*copy_into_pages)(struct TCP_Server_Info *server,
+				struct cifs_readdata *rdata,
+				struct iov_iter *iter);
+	struct kvec			iov[2];
 	unsigned int			pagesz;
 	unsigned int			tailsz;
 	unsigned int			credits;
@@ -1137,6 +1158,7 @@ struct cifs_writedata {
 	enum writeback_sync_modes	sync_mode;
 	struct work_struct		work;
 	struct cifsFileInfo		*cfile;
+	struct cifs_aio_ctx		*ctx;
 	__u64				offset;
 	pid_t				pid;
 	unsigned int			bytes;
@@ -1198,9 +1220,7 @@ struct cifsInodeInfo {
 	u64  server_eof;		/* current file size on server -- protected by i_lock */
 	u64  uniqueid;			/* server inode number */
 	u64  createtime;		/* creation time on server */
-#ifdef CONFIG_CIFS_SMB2
 	__u8 lease_key[SMB2_LEASE_KEY_SIZE];	/* lease key for this inode */
-#endif
 #ifdef CONFIG_CIFS_FSCACHE
 	struct fscache_cookie *fscache;
 #endif
@@ -1302,6 +1322,13 @@ typedef int (mid_receive_t)(struct TCP_Server_Info *server,
  */
 typedef void (mid_callback_t)(struct mid_q_entry *mid);
 
+/*
+ * This is the protopyte for mid handle function. This is called once the mid
+ * has been recognized after decryption of the message.
+ */
+typedef int (mid_handle_t)(struct TCP_Server_Info *server,
+			    struct mid_q_entry *mid);
+
 /* one of these for every pending CIFS request to the server */
 struct mid_q_entry {
 	struct list_head qhead;	/* mids waiting on reply from this server */
@@ -1316,13 +1343,22 @@ struct mid_q_entry {
 #endif
 	mid_receive_t *receive; /* call receive callback */
 	mid_callback_t *callback; /* call completion callback */
+	mid_handle_t *handle; /* call handle mid callback */
 	void *callback_data;	  /* general purpose pointer for callback */
 	void *resp_buf;		/* pointer to received SMB header */
 	int mid_state;	/* wish this were enum but can not pass to wait_event */
+	unsigned int mid_flags;
 	__le16 command;		/* smb command code */
 	bool large_buf:1;	/* if valid response, is pointer to large buf */
 	bool multiRsp:1;	/* multiple trans2 responses for one request  */
 	bool multiEnd:1;	/* both received */
+	bool decrypted:1;	/* decrypted entry */
+};
+
+struct close_cancelled_open {
+	struct cifs_fid         fid;
+	struct cifs_tcon        *tcon;
+	struct work_struct      work;
 };
 
 /*	Make code in transport.c a little cleaner by moving
@@ -1456,6 +1492,9 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param,
 #define   MID_RESPONSE_MALFORMED 0x10
 #define   MID_SHUTDOWN		 0x20
 
+/* Flags */
+#define   MID_WAIT_CANCELLED	 1 /* Cancelled while waiting for response */
+
 /* Types of response buffer returned from SendReceive2 */
 #define   CIFS_NO_BUFFER        0    /* Response buffer not returned */
 #define   CIFS_SMALL_BUFFER     1
@@ -1475,7 +1514,9 @@ static inline void free_dfs_info_array(struct dfs_info3_param *param,
 #define   CIFS_OBREAK_OP   0x0100    /* oplock break request */
 #define   CIFS_NEG_OP      0x0200    /* negotiate request */
 #define   CIFS_OP_MASK     0x0380    /* mask request type */
+
 #define   CIFS_HAS_CREDITS 0x0400    /* already has credits */
+#define   CIFS_TRANSFORM_REQ 0x0800    /* transform request before sending */
 
 /* Security Flags: indicate type of session setup needed */
 #define   CIFSSEC_MAY_SIGN	0x00001
@@ -1645,6 +1686,7 @@ void cifs_oplock_break(struct work_struct *work);
 
 extern const struct slow_work_ops cifs_oplock_break_ops;
 extern struct workqueue_struct *cifsiod_wq;
+extern struct workqueue_struct *cifsoplockd_wq;
 extern __u32 cifs_lock_secret;
 
 extern mempool_t *cifs_mid_poolp;
diff --git a/fs/cifs/cifspdu.h b/fs/cifs/cifspdu.h
index f5b87303ce46..1ce733f3582f 100644
--- a/fs/cifs/cifspdu.h
+++ b/fs/cifs/cifspdu.h
@@ -2086,17 +2086,21 @@ typedef struct dfs_referral_level_3 { /* version 4 is same, + one flag bit */
 	__u8   ServiceSiteGuid[16];  /* MBZ, ignored */
 } __attribute__((packed)) REFERRAL3;
 
-typedef struct smb_com_transaction_get_dfs_refer_rsp {
-	struct smb_hdr hdr;	/* wct = 10 */
-	struct trans2_resp t2;
-	__u16 ByteCount;
-	__u8 Pad;
+struct get_dfs_referral_rsp {
 	__le16 PathConsumed;
 	__le16 NumberOfReferrals;
 	__le32 DFSFlags;
 	REFERRAL3 referrals[1];	/* array of level 3 dfs_referral structures */
 	/* followed by the strings pointed to by the referral structures */
-} __attribute__((packed)) TRANSACTION2_GET_DFS_REFER_RSP;
+} __packed;
+
+typedef struct smb_com_transaction_get_dfs_refer_rsp {
+	struct smb_hdr hdr;	/* wct = 10 */
+	struct trans2_resp t2;
+	__u16 ByteCount;
+	__u8 Pad;
+	struct get_dfs_referral_rsp dfs_data;
+} __packed TRANSACTION2_GET_DFS_REFER_RSP;
 
 /* DFS Flags */
 #define DFSREF_REFERRAL_SERVER  0x00000001 /* all targets are DFS roots */
diff --git a/fs/cifs/cifsproto.h b/fs/cifs/cifsproto.h
index c7b3c841e660..6eb3147132e3 100644
--- a/fs/cifs/cifsproto.h
+++ b/fs/cifs/cifsproto.h
@@ -61,6 +61,8 @@ extern void exit_cifs_idmap(void);
 extern int init_cifs_spnego(void);
 extern void exit_cifs_spnego(void);
 extern char *build_path_from_dentry(struct dentry *);
+extern char *build_path_from_dentry_optional_prefix(struct dentry *direntry,
+						    bool prefix);
 extern char *cifs_build_path_to_root(struct smb_vol *vol,
 				     struct cifs_sb_info *cifs_sb,
 				     struct cifs_tcon *tcon,
@@ -75,10 +77,16 @@ extern struct mid_q_entry *AllocMidQEntry(const struct smb_hdr *smb_buffer,
 extern void DeleteMidQEntry(struct mid_q_entry *midEntry);
 extern void cifs_delete_mid(struct mid_q_entry *mid);
 extern void cifs_wake_up_task(struct mid_q_entry *mid);
+extern int cifs_handle_standard(struct TCP_Server_Info *server,
+				struct mid_q_entry *mid);
+extern int cifs_discard_remaining_data(struct TCP_Server_Info *server);
 extern int cifs_call_async(struct TCP_Server_Info *server,
 			struct smb_rqst *rqst,
 			mid_receive_t *receive, mid_callback_t *callback,
-			void *cbdata, const int flags);
+			mid_handle_t *handle, void *cbdata, const int flags);
+extern int cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
+			  struct smb_rqst *rqst, int *resp_buf_type,
+			  const int flags, struct kvec *resp_iov);
 extern int SendReceive(const unsigned int /* xid */ , struct cifs_ses *,
 			struct smb_hdr * /* input */ ,
 			struct smb_hdr * /* out */ ,
@@ -96,7 +104,8 @@ extern int cifs_wait_mtu_credits(struct TCP_Server_Info *server,
 				 unsigned int *credits);
 extern int SendReceive2(const unsigned int /* xid */ , struct cifs_ses *,
 			struct kvec *, int /* nvec to send */,
-			int * /* type of buf returned */ , const int flags);
+			int * /* type of buf returned */, const int flags,
+			struct kvec * /* resp vec */);
 extern int SendReceiveBlockingLock(const unsigned int xid,
 			struct cifs_tcon *ptcon,
 			struct smb_hdr *in_buf ,
@@ -277,6 +286,11 @@ extern int get_dfs_path(const unsigned int xid, struct cifs_ses *ses,
 			const struct nls_table *nls_codepage,
 			unsigned int *num_referrals,
 			struct dfs_info3_param **referrals, int remap);
+extern int parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size,
+			       unsigned int *num_of_nodes,
+			       struct dfs_info3_param **target_nodes,
+			       const struct nls_table *nls_codepage, int remap,
+			       const char *searchName, bool is_unicode);
 extern void reset_cifs_unix_caps(unsigned int xid, struct cifs_tcon *tcon,
 				 struct cifs_sb_info *cifs_sb,
 				 struct smb_vol *vol);
@@ -441,7 +455,7 @@ extern int SMBNTencrypt(unsigned char *, unsigned char *, unsigned char *,
 			const struct nls_table *);
 extern int setup_ntlm_response(struct cifs_ses *, const struct nls_table *);
 extern int setup_ntlmv2_rsp(struct cifs_ses *, const struct nls_table *);
-extern void cifs_crypto_shash_release(struct TCP_Server_Info *);
+extern void cifs_crypto_secmech_release(struct TCP_Server_Info *server);
 extern int calc_seckey(struct cifs_ses *);
 extern int generate_smb30signingkey(struct cifs_ses *);
 extern int generate_smb311signingkey(struct cifs_ses *);
@@ -466,8 +480,7 @@ extern int CIFSSMBCopy(unsigned int xid,
 extern ssize_t CIFSSMBQAllEAs(const unsigned int xid, struct cifs_tcon *tcon,
 			const unsigned char *searchName,
 			const unsigned char *ea_name, char *EAData,
-			size_t bufsize, const struct nls_table *nls_codepage,
-			int remap_special_chars);
+			size_t bufsize, struct cifs_sb_info *cifs_sb);
 extern int CIFSSMBSetEA(const unsigned int xid, struct cifs_tcon *tcon,
 		const char *fileName, const char *ea_name,
 		const void *ea_value, const __u16 ea_value_len,
@@ -519,4 +532,9 @@ int cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 int __cifs_calc_signature(struct smb_rqst *rqst,
 			struct TCP_Server_Info *server, char *signature,
 			struct shash_desc *shash);
+enum securityEnum cifs_select_sectype(struct TCP_Server_Info *,
+					enum securityEnum);
+struct cifs_aio_ctx *cifs_aio_ctx_alloc(void);
+void cifs_aio_ctx_release(struct kref *refcount);
+int setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw);
 #endif			/* _CIFSPROTO_H */
diff --git a/fs/cifs/cifssmb.c b/fs/cifs/cifssmb.c
index b47261858e6d..72a53bd19865 100644
--- a/fs/cifs/cifssmb.c
+++ b/fs/cifs/cifssmb.c
@@ -478,14 +478,14 @@ decode_lanman_negprot_rsp(struct TCP_Server_Info *server, NEGOTIATE_RSP *pSMBr)
 		 * this requirement.
 		 */
 		int val, seconds, remain, result;
-		struct timespec ts, utc;
-		utc = CURRENT_TIME;
+		struct timespec ts;
+		unsigned long utc = ktime_get_real_seconds();
 		ts = cnvrtDosUnixTm(rsp->SrvTime.Date,
 				    rsp->SrvTime.Time, 0);
 		cifs_dbg(FYI, "SrvTime %d sec since 1970 (utc: %d) diff: %d\n",
-			 (int)ts.tv_sec, (int)utc.tv_sec,
-			 (int)(utc.tv_sec - ts.tv_sec));
-		val = (int)(utc.tv_sec - ts.tv_sec);
+			 (int)ts.tv_sec, (int)utc,
+			 (int)(utc - ts.tv_sec));
+		val = (int)(utc - ts.tv_sec);
 		seconds = abs(val);
 		result = (seconds / MIN_TZ_ADJ) * MIN_TZ_ADJ;
 		remain = seconds % MIN_TZ_ADJ;
@@ -673,6 +673,7 @@ CIFSSMBTDis(const unsigned int xid, struct cifs_tcon *tcon)
 		return rc;
 
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *)smb_buffer, 0);
+	cifs_small_buf_release(smb_buffer);
 	if (rc)
 		cifs_dbg(FYI, "Tree disconnect failed %d\n", rc);
 
@@ -696,9 +697,7 @@ cifs_echo_callback(struct mid_q_entry *mid)
 {
 	struct TCP_Server_Info *server = mid->callback_data;
 
-	mutex_lock(&server->srv_mutex);
 	DeleteMidQEntry(mid);
-	mutex_unlock(&server->srv_mutex);
 	add_credits(server, 1, CIFS_ECHO_OP);
 }
 
@@ -707,9 +706,9 @@ CIFSSMBEcho(struct TCP_Server_Info *server)
 {
 	ECHO_REQ *smb;
 	int rc = 0;
-	struct kvec iov;
-	struct smb_rqst rqst = { .rq_iov = &iov,
-				 .rq_nvec = 1 };
+	struct kvec iov[2];
+	struct smb_rqst rqst = { .rq_iov = iov,
+				 .rq_nvec = 2 };
 
 	cifs_dbg(FYI, "In echo request\n");
 
@@ -717,6 +716,9 @@ CIFSSMBEcho(struct TCP_Server_Info *server)
 	if (rc)
 		return rc;
 
+	if (server->capabilities & CAP_UNICODE)
+		smb->hdr.Flags2 |= SMBFLG2_UNICODE;
+
 	/* set up echo request */
 	smb->hdr.Tid = 0xffff;
 	smb->hdr.WordCount = 1;
@@ -724,10 +726,13 @@ CIFSSMBEcho(struct TCP_Server_Info *server)
 	put_bcc(1, &smb->hdr);
 	smb->Data[0] = 'a';
 	inc_rfc1001_len(smb, 3);
-	iov.iov_base = smb;
-	iov.iov_len = be32_to_cpu(smb->hdr.smb_buf_length) + 4;
 
-	rc = cifs_call_async(server, &rqst, NULL, cifs_echo_callback,
+	iov[0].iov_len = 4;
+	iov[0].iov_base = smb;
+	iov[1].iov_len = get_rfc1002_length(smb);
+	iov[1].iov_base = (char *)smb + 4;
+
+	rc = cifs_call_async(server, &rqst, NULL, cifs_echo_callback, NULL,
 			     server, CIFS_ASYNC_OP | CIFS_ECHO_OP);
 	if (rc)
 		cifs_dbg(FYI, "Echo request failed: %d\n", rc);
@@ -772,6 +777,7 @@ CIFSSMBLogoff(const unsigned int xid, struct cifs_ses *ses)
 
 	pSMB->AndXCommand = 0xFF;
 	rc = SendReceiveNoRsp(xid, ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 session_already_dead:
 	mutex_unlock(&ses->session_mutex);
 
@@ -1394,8 +1400,8 @@ openRetry:
  * Discard any remaining data in the current SMB. To do this, we borrow the
  * current bigbuf.
  */
-static int
-discard_remaining_data(struct TCP_Server_Info *server)
+int
+cifs_discard_remaining_data(struct TCP_Server_Info *server)
 {
 	unsigned int rfclen = get_rfc1002_length(server->smallbuf);
 	int remaining = rfclen + 4 - server->total_read;
@@ -1421,8 +1427,10 @@ cifs_readv_discard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	int length;
 	struct cifs_readdata *rdata = mid->callback_data;
 
-	length = discard_remaining_data(server);
+	length = cifs_discard_remaining_data(server);
 	dequeue_mid(mid, rdata->result);
+	mid->resp_buf = server->smallbuf;
+	server->smallbuf = NULL;
 	return length;
 }
 
@@ -1452,9 +1460,16 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		return length;
 	server->total_read += length;
 
+	if (server->ops->is_session_expired &&
+	    server->ops->is_session_expired(buf)) {
+		cifs_reconnect(server);
+		wake_up(&server->response_q);
+		return -1;
+	}
+
 	if (server->ops->is_status_pending &&
 	    server->ops->is_status_pending(buf, server, 0)) {
-		discard_remaining_data(server);
+		cifs_discard_remaining_data(server);
 		return -1;
 	}
 
@@ -1507,10 +1522,12 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 	}
 
 	/* set up first iov for signature check */
-	rdata->iov.iov_base = buf;
-	rdata->iov.iov_len = server->total_read;
-	cifs_dbg(FYI, "0: iov_base=%p iov_len=%zu\n",
-		 rdata->iov.iov_base, rdata->iov.iov_len);
+	rdata->iov[0].iov_base = buf;
+	rdata->iov[0].iov_len = 4;
+	rdata->iov[1].iov_base = buf + 4;
+	rdata->iov[1].iov_len = server->total_read - 4;
+	cifs_dbg(FYI, "0: iov_base=%p iov_len=%u\n",
+		 rdata->iov[0].iov_base, server->total_read);
 
 	/* how much data is in the response? */
 	data_len = server->ops->read_data_length(buf);
@@ -1534,6 +1551,8 @@ cifs_readv_receive(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		return cifs_readv_discard(server, mid);
 
 	dequeue_mid(mid, false);
+	mid->resp_buf = server->smallbuf;
+	server->smallbuf = NULL;
 	return length;
 }
 
@@ -1543,8 +1562,8 @@ cifs_readv_callback(struct mid_q_entry *mid)
 	struct cifs_readdata *rdata = mid->callback_data;
 	struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
-	struct smb_rqst rqst = { .rq_iov = &rdata->iov,
-				 .rq_nvec = 1,
+	struct smb_rqst rqst = { .rq_iov = rdata->iov,
+				 .rq_nvec = 2,
 				 .rq_pages = rdata->pages,
 				 .rq_npages = rdata->nr_pages,
 				 .rq_pagesz = rdata->pagesz,
@@ -1585,9 +1604,7 @@ cifs_readv_callback(struct mid_q_entry *mid)
 	}
 
 	queue_work(cifsiod_wq, &rdata->work);
-	mutex_lock(&server->srv_mutex);
 	DeleteMidQEntry(mid);
-	mutex_unlock(&server->srv_mutex);
 	add_credits(server, 1, 0);
 }
 
@@ -1599,8 +1616,8 @@ cifs_async_readv(struct cifs_readdata *rdata)
 	READ_REQ *smb = NULL;
 	int wct;
 	struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
-	struct smb_rqst rqst = { .rq_iov = &rdata->iov,
-				 .rq_nvec = 1 };
+	struct smb_rqst rqst = { .rq_iov = rdata->iov,
+				 .rq_nvec = 2 };
 
 	cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n",
 		 __func__, rdata->offset, rdata->bytes);
@@ -1640,12 +1657,14 @@ cifs_async_readv(struct cifs_readdata *rdata)
 	}
 
 	/* 4 for RFC1001 length + 1 for BCC */
-	rdata->iov.iov_base = smb;
-	rdata->iov.iov_len = be32_to_cpu(smb->hdr.smb_buf_length) + 4;
+	rdata->iov[0].iov_base = smb;
+	rdata->iov[0].iov_len = 4;
+	rdata->iov[1].iov_base = (char *)smb + 4;
+	rdata->iov[1].iov_len = get_rfc1002_length(smb);
 
 	kref_get(&rdata->refcount);
 	rc = cifs_call_async(tcon->ses->server, &rqst, cifs_readv_receive,
-			     cifs_readv_callback, rdata, 0);
+			     cifs_readv_callback, NULL, rdata, 0);
 
 	if (rc == 0)
 		cifs_stats_inc(&tcon->stats.cifs_stats.num_reads);
@@ -1667,6 +1686,7 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms,
 	int wct;
 	int resp_buf_type = 0;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 	__u32 pid = io_parms->pid;
 	__u16 netfid = io_parms->netfid;
 	__u64 offset = io_parms->offset;
@@ -1716,10 +1736,11 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms,
 
 	iov[0].iov_base = (char *)pSMB;
 	iov[0].iov_len = be32_to_cpu(pSMB->hdr.smb_buf_length) + 4;
-	rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovecs */,
-			 &resp_buf_type, CIFS_LOG_ERROR);
+	rc = SendReceive2(xid, tcon->ses, iov, 1, &resp_buf_type,
+			  CIFS_LOG_ERROR, &rsp_iov);
+	cifs_small_buf_release(pSMB);
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_reads);
-	pSMBr = (READ_RSP *)iov[0].iov_base;
+	pSMBr = (READ_RSP *)rsp_iov.iov_base;
 	if (rc) {
 		cifs_dbg(VFS, "Send error in read = %d\n", rc);
 	} else {
@@ -1747,12 +1768,11 @@ CIFSSMBRead(const unsigned int xid, struct cifs_io_parms *io_parms,
 		}
 	}
 
-/*	cifs_small_buf_release(pSMB); */ /* Freed earlier now in SendReceive2 */
 	if (*buf) {
-		free_rsp_buf(resp_buf_type, iov[0].iov_base);
+		free_rsp_buf(resp_buf_type, rsp_iov.iov_base);
 	} else if (resp_buf_type != CIFS_NO_BUFFER) {
 		/* return buffer to caller to free */
-		*buf = iov[0].iov_base;
+		*buf = rsp_iov.iov_base;
 		if (resp_buf_type == CIFS_SMALL_BUFFER)
 			*pbuf_type = CIFS_SMALL_BUFFER;
 		else if (resp_buf_type == CIFS_LARGE_BUFFER)
@@ -2041,7 +2061,6 @@ cifs_writev_callback(struct mid_q_entry *mid)
 {
 	struct cifs_writedata *wdata = mid->callback_data;
 	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
-	struct TCP_Server_Info *server = tcon->ses->server;
 	unsigned int written;
 	WRITE_RSP *smb = (WRITE_RSP *)mid->resp_buf;
 
@@ -2078,9 +2097,7 @@ cifs_writev_callback(struct mid_q_entry *mid)
 	}
 
 	queue_work(cifsiod_wq, &wdata->work);
-	mutex_lock(&server->srv_mutex);
 	DeleteMidQEntry(mid);
-	mutex_unlock(&server->srv_mutex);
 	add_credits(tcon->ses->server, 1, 0);
 }
 
@@ -2093,7 +2110,7 @@ cifs_async_writev(struct cifs_writedata *wdata,
 	WRITE_REQ *smb = NULL;
 	int wct;
 	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
-	struct kvec iov;
+	struct kvec iov[2];
 	struct smb_rqst rqst = { };
 
 	if (tcon->ses->capabilities & CAP_LARGE_FILES) {
@@ -2126,11 +2143,13 @@ cifs_async_writev(struct cifs_writedata *wdata,
 	    cpu_to_le16(offsetof(struct smb_com_write_req, Data) - 4);
 
 	/* 4 for RFC1001 length + 1 for BCC */
-	iov.iov_len = be32_to_cpu(smb->hdr.smb_buf_length) + 4 + 1;
-	iov.iov_base = smb;
+	iov[0].iov_len = 4;
+	iov[0].iov_base = smb;
+	iov[1].iov_len = get_rfc1002_length(smb) + 1;
+	iov[1].iov_base = (char *)smb + 4;
 
-	rqst.rq_iov = &iov;
-	rqst.rq_nvec = 1;
+	rqst.rq_iov = iov;
+	rqst.rq_nvec = 2;
 	rqst.rq_pages = wdata->pages;
 	rqst.rq_npages = wdata->nr_pages;
 	rqst.rq_pagesz = wdata->pagesz;
@@ -2151,12 +2170,12 @@ cifs_async_writev(struct cifs_writedata *wdata,
 				(struct smb_com_writex_req *)smb;
 		inc_rfc1001_len(&smbw->hdr, wdata->bytes + 5);
 		put_bcc(wdata->bytes + 5, &smbw->hdr);
-		iov.iov_len += 4; /* pad bigger by four bytes */
+		iov[1].iov_len += 4; /* pad bigger by four bytes */
 	}
 
 	kref_get(&wdata->refcount);
 	rc = cifs_call_async(tcon->ses->server, &rqst, NULL,
-				cifs_writev_callback, wdata, 0);
+				cifs_writev_callback, NULL, wdata, 0);
 
 	if (rc == 0)
 		cifs_stats_inc(&tcon->stats.cifs_stats.num_writes);
@@ -2182,6 +2201,7 @@ CIFSSMBWrite2(const unsigned int xid, struct cifs_io_parms *io_parms,
 	__u64 offset = io_parms->offset;
 	struct cifs_tcon *tcon = io_parms->tcon;
 	unsigned int count = io_parms->length;
+	struct kvec rsp_iov;
 
 	*nbytes = 0;
 
@@ -2240,8 +2260,9 @@ CIFSSMBWrite2(const unsigned int xid, struct cifs_io_parms *io_parms,
 	else /* wct == 12 pad bigger by four bytes */
 		iov[0].iov_len = smb_hdr_len + 8;
 
-
-	rc = SendReceive2(xid, tcon->ses, iov, n_vec + 1, &resp_buf_type, 0);
+	rc = SendReceive2(xid, tcon->ses, iov, n_vec + 1, &resp_buf_type, 0,
+			  &rsp_iov);
+	cifs_small_buf_release(pSMB);
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_writes);
 	if (rc) {
 		cifs_dbg(FYI, "Send error Write2 = %d\n", rc);
@@ -2249,7 +2270,7 @@ CIFSSMBWrite2(const unsigned int xid, struct cifs_io_parms *io_parms,
 		/* presumably this can not happen, but best to be safe */
 		rc = -EIO;
 	} else {
-		WRITE_RSP *pSMBr = (WRITE_RSP *)iov[0].iov_base;
+		WRITE_RSP *pSMBr = (WRITE_RSP *)rsp_iov.iov_base;
 		*nbytes = le16_to_cpu(pSMBr->CountHigh);
 		*nbytes = (*nbytes) << 16;
 		*nbytes += le16_to_cpu(pSMBr->Count);
@@ -2263,8 +2284,7 @@ CIFSSMBWrite2(const unsigned int xid, struct cifs_io_parms *io_parms,
 			*nbytes &= 0xFFFF;
 	}
 
-/*	cifs_small_buf_release(pSMB); */ /* Freed earlier now in SendReceive2 */
-	free_rsp_buf(resp_buf_type, iov[0].iov_base);
+	free_rsp_buf(resp_buf_type, rsp_iov.iov_base);
 
 	/* Note: On -EAGAIN error only caller can retry on handle based calls
 		since file handle passed in no longer valid */
@@ -2279,6 +2299,7 @@ int cifs_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	LOCK_REQ *pSMB = NULL;
 	struct kvec iov[2];
+	struct kvec rsp_iov;
 	int resp_buf_type;
 	__u16 count;
 
@@ -2307,7 +2328,9 @@ int cifs_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	iov[1].iov_len = (num_unlock + num_lock) * sizeof(LOCKING_ANDX_RANGE);
 
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_locks);
-	rc = SendReceive2(xid, tcon->ses, iov, 2, &resp_buf_type, CIFS_NO_RESP);
+	rc = SendReceive2(xid, tcon->ses, iov, 2, &resp_buf_type, CIFS_NO_RESP,
+			  &rsp_iov);
+	cifs_small_buf_release(pSMB);
 	if (rc)
 		cifs_dbg(FYI, "Send error in cifs_lockv = %d\n", rc);
 
@@ -2368,14 +2391,12 @@ CIFSSMBLock(const unsigned int xid, struct cifs_tcon *tcon,
 	inc_rfc1001_len(pSMB, count);
 	pSMB->ByteCount = cpu_to_le16(count);
 
-	if (waitFlag) {
+	if (waitFlag)
 		rc = SendReceiveBlockingLock(xid, tcon, (struct smb_hdr *) pSMB,
 			(struct smb_hdr *) pSMB, &bytes_returned);
-		cifs_small_buf_release(pSMB);
-	} else {
+	else
 		rc = SendReceiveNoRsp(xid, tcon->ses, (char *)pSMB, flags);
-		/* SMB buffer freed by function above */
-	}
+	cifs_small_buf_release(pSMB);
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_locks);
 	if (rc)
 		cifs_dbg(FYI, "Send error in Lock = %d\n", rc);
@@ -2401,6 +2422,7 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon,
 	int resp_buf_type = 0;
 	__u16 params, param_offset, offset, byte_count, count;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 
 	cifs_dbg(FYI, "Posix Lock\n");
 
@@ -2462,11 +2484,10 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon,
 		iov[0].iov_base = (char *)pSMB;
 		iov[0].iov_len = be32_to_cpu(pSMB->hdr.smb_buf_length) + 4;
 		rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovecs */,
-				&resp_buf_type, timeout);
-		pSMB = NULL; /* request buf already freed by SendReceive2. Do
-				not try to free it twice below on exit */
-		pSMBr = (struct smb_com_transaction2_sfi_rsp *)iov[0].iov_base;
+				&resp_buf_type, timeout, &rsp_iov);
+		pSMBr = (struct smb_com_transaction2_sfi_rsp *)rsp_iov.iov_base;
 	}
+	cifs_small_buf_release(pSMB);
 
 	if (rc) {
 		cifs_dbg(FYI, "Send error in Posix Lock = %d\n", rc);
@@ -2506,10 +2527,7 @@ CIFSSMBPosixLock(const unsigned int xid, struct cifs_tcon *tcon,
 	}
 
 plk_err_exit:
-	if (pSMB)
-		cifs_small_buf_release(pSMB);
-
-	free_rsp_buf(resp_buf_type, iov[0].iov_base);
+	free_rsp_buf(resp_buf_type, rsp_iov.iov_base);
 
 	/* Note: On -EAGAIN error only caller can retry on handle based calls
 	   since file handle passed in no longer valid */
@@ -2536,6 +2554,7 @@ CIFSSMBClose(const unsigned int xid, struct cifs_tcon *tcon, int smb_file_id)
 	pSMB->LastWriteTime = 0xFFFFFFFF;
 	pSMB->ByteCount = 0;
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_closes);
 	if (rc) {
 		if (rc != -EINTR) {
@@ -2565,6 +2584,7 @@ CIFSSMBFlush(const unsigned int xid, struct cifs_tcon *tcon, int smb_file_id)
 	pSMB->FileID = (__u16) smb_file_id;
 	pSMB->ByteCount = 0;
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_flushes);
 	if (rc)
 		cifs_dbg(VFS, "Send error in Flush = %d\n", rc);
@@ -3820,6 +3840,7 @@ CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid,
 	int buf_type = 0;
 	QUERY_SEC_DESC_REQ *pSMB;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 
 	cifs_dbg(FYI, "GetCifsACL\n");
 
@@ -3843,7 +3864,8 @@ CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid,
 	iov[0].iov_len = be32_to_cpu(pSMB->hdr.smb_buf_length) + 4;
 
 	rc = SendReceive2(xid, tcon->ses, iov, 1 /* num iovec */, &buf_type,
-			 0);
+			  0, &rsp_iov);
+	cifs_small_buf_release(pSMB);
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_acl_get);
 	if (rc) {
 		cifs_dbg(FYI, "Send error in QuerySecDesc = %d\n", rc);
@@ -3855,11 +3877,11 @@ CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid,
 		char *pdata;
 
 /* validate_nttransact */
-		rc = validate_ntransact(iov[0].iov_base, (char **)&parm,
+		rc = validate_ntransact(rsp_iov.iov_base, (char **)&parm,
 					&pdata, &parm_len, pbuflen);
 		if (rc)
 			goto qsec_out;
-		pSMBr = (struct smb_com_ntransact_rsp *)iov[0].iov_base;
+		pSMBr = (struct smb_com_ntransact_rsp *)rsp_iov.iov_base;
 
 		cifs_dbg(FYI, "smb %p parm %p data %p\n",
 			 pSMBr, parm, *acl_inf);
@@ -3896,8 +3918,7 @@ CIFSSMBGetCIFSACL(const unsigned int xid, struct cifs_tcon *tcon, __u16 fid,
 		}
 	}
 qsec_out:
-	free_rsp_buf(buf_type, iov[0].iov_base);
-/*	cifs_small_buf_release(pSMB); */ /* Freed earlier now in SendReceive2 */
+	free_rsp_buf(buf_type, rsp_iov.iov_base);
 	return rc;
 }
 
@@ -4666,6 +4687,7 @@ CIFSFindClose(const unsigned int xid, struct cifs_tcon *tcon,
 	pSMB->FileID = searchHandle;
 	pSMB->ByteCount = 0;
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	if (rc)
 		cifs_dbg(VFS, "Send error in FindClose = %d\n", rc);
 
@@ -4771,117 +4793,6 @@ GetInodeNumOut:
 	return rc;
 }
 
-/* parses DFS refferal V3 structure
- * caller is responsible for freeing target_nodes
- * returns:
- * 	on success - 0
- *	on failure - errno
- */
-static int
-parse_DFS_referrals(TRANSACTION2_GET_DFS_REFER_RSP *pSMBr,
-		unsigned int *num_of_nodes,
-		struct dfs_info3_param **target_nodes,
-		const struct nls_table *nls_codepage, int remap,
-		const char *searchName)
-{
-	int i, rc = 0;
-	char *data_end;
-	bool is_unicode;
-	struct dfs_referral_level_3 *ref;
-
-	if (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE)
-		is_unicode = true;
-	else
-		is_unicode = false;
-	*num_of_nodes = le16_to_cpu(pSMBr->NumberOfReferrals);
-
-	if (*num_of_nodes < 1) {
-		cifs_dbg(VFS, "num_referrals: must be at least > 0, but we get num_referrals = %d\n",
-			 *num_of_nodes);
-		rc = -EINVAL;
-		goto parse_DFS_referrals_exit;
-	}
-
-	ref = (struct dfs_referral_level_3 *) &(pSMBr->referrals);
-	if (ref->VersionNumber != cpu_to_le16(3)) {
-		cifs_dbg(VFS, "Referrals of V%d version are not supported, should be V3\n",
-			 le16_to_cpu(ref->VersionNumber));
-		rc = -EINVAL;
-		goto parse_DFS_referrals_exit;
-	}
-
-	/* get the upper boundary of the resp buffer */
-	data_end = (char *)(&(pSMBr->PathConsumed)) +
-				le16_to_cpu(pSMBr->t2.DataCount);
-
-	cifs_dbg(FYI, "num_referrals: %d dfs flags: 0x%x ...\n",
-		 *num_of_nodes, le32_to_cpu(pSMBr->DFSFlags));
-
-	*target_nodes = kcalloc(*num_of_nodes, sizeof(struct dfs_info3_param),
-				GFP_KERNEL);
-	if (*target_nodes == NULL) {
-		rc = -ENOMEM;
-		goto parse_DFS_referrals_exit;
-	}
-
-	/* collect necessary data from referrals */
-	for (i = 0; i < *num_of_nodes; i++) {
-		char *temp;
-		int max_len;
-		struct dfs_info3_param *node = (*target_nodes)+i;
-
-		node->flags = le32_to_cpu(pSMBr->DFSFlags);
-		if (is_unicode) {
-			__le16 *tmp = kmalloc(strlen(searchName)*2 + 2,
-						GFP_KERNEL);
-			if (tmp == NULL) {
-				rc = -ENOMEM;
-				goto parse_DFS_referrals_exit;
-			}
-			cifsConvertToUTF16((__le16 *) tmp, searchName,
-					   PATH_MAX, nls_codepage, remap);
-			node->path_consumed = cifs_utf16_bytes(tmp,
-					le16_to_cpu(pSMBr->PathConsumed),
-					nls_codepage);
-			kfree(tmp);
-		} else
-			node->path_consumed = le16_to_cpu(pSMBr->PathConsumed);
-
-		node->server_type = le16_to_cpu(ref->ServerType);
-		node->ref_flag = le16_to_cpu(ref->ReferralEntryFlags);
-
-		/* copy DfsPath */
-		temp = (char *)ref + le16_to_cpu(ref->DfsPathOffset);
-		max_len = data_end - temp;
-		node->path_name = cifs_strndup_from_utf16(temp, max_len,
-						is_unicode, nls_codepage);
-		if (!node->path_name) {
-			rc = -ENOMEM;
-			goto parse_DFS_referrals_exit;
-		}
-
-		/* copy link target UNC */
-		temp = (char *)ref + le16_to_cpu(ref->NetworkAddressOffset);
-		max_len = data_end - temp;
-		node->node_name = cifs_strndup_from_utf16(temp, max_len,
-						is_unicode, nls_codepage);
-		if (!node->node_name) {
-			rc = -ENOMEM;
-			goto parse_DFS_referrals_exit;
-		}
-
-		ref++;
-	}
-
-parse_DFS_referrals_exit:
-	if (rc) {
-		free_dfs_info_array(*target_nodes, *num_of_nodes);
-		*target_nodes = NULL;
-		*num_of_nodes = 0;
-	}
-	return rc;
-}
-
 int
 CIFSGetDFSRefer(const unsigned int xid, struct cifs_ses *ses,
 		const char *search_name, struct dfs_info3_param **target_nodes,
@@ -4978,9 +4889,11 @@ getDFSRetry:
 		 get_bcc(&pSMBr->hdr), le16_to_cpu(pSMBr->t2.DataOffset));
 
 	/* parse returned result into more usable form */
-	rc = parse_DFS_referrals(pSMBr, num_of_nodes,
-				 target_nodes, nls_codepage, remap,
-				 search_name);
+	rc = parse_dfs_referrals(&pSMBr->dfs_data,
+				 le16_to_cpu(pSMBr->t2.DataCount),
+				 num_of_nodes, target_nodes, nls_codepage,
+				 remap, search_name,
+				 (pSMBr->hdr.Flags2 & SMBFLG2_UNICODE) != 0);
 
 GetDFSRefExit:
 	cifs_buf_release(pSMB);
@@ -5687,6 +5600,7 @@ CIFSSMBSetFileSize(const unsigned int xid, struct cifs_tcon *tcon,
 	inc_rfc1001_len(pSMB, byte_count);
 	pSMB->ByteCount = cpu_to_le16(byte_count);
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	if (rc) {
 		cifs_dbg(FYI, "Send error in SetFileInfo (SetFileSize) = %d\n",
 			 rc);
@@ -5758,6 +5672,7 @@ CIFSSMBSetFileInfo(const unsigned int xid, struct cifs_tcon *tcon,
 	pSMB->ByteCount = cpu_to_le16(byte_count);
 	memcpy(data_offset, data, sizeof(FILE_BASIC_INFO));
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	if (rc)
 		cifs_dbg(FYI, "Send error in Set Time (SetFileInfo) = %d\n",
 			 rc);
@@ -5818,6 +5733,7 @@ CIFSSMBSetFileDisposition(const unsigned int xid, struct cifs_tcon *tcon,
 	pSMB->ByteCount = cpu_to_le16(byte_count);
 	*data_offset = delete_file ? 1 : 0;
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	if (rc)
 		cifs_dbg(FYI, "Send error in SetFileDisposition = %d\n", rc);
 
@@ -6057,6 +5973,7 @@ CIFSSMBUnixSetFileInfo(const unsigned int xid, struct cifs_tcon *tcon,
 	cifs_fill_unix_set_info((FILE_UNIX_BASIC_INFO *)data_offset, args);
 
 	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) pSMB, 0);
+	cifs_small_buf_release(pSMB);
 	if (rc)
 		cifs_dbg(FYI, "Send error in Set Time (SetFileInfo) = %d\n",
 			 rc);
@@ -6159,11 +6076,13 @@ ssize_t
 CIFSSMBQAllEAs(const unsigned int xid, struct cifs_tcon *tcon,
 		const unsigned char *searchName, const unsigned char *ea_name,
 		char *EAData, size_t buf_size,
-		const struct nls_table *nls_codepage, int remap)
+		struct cifs_sb_info *cifs_sb)
 {
 		/* BB assumes one setup word */
 	TRANSACTION2_QPI_REQ *pSMB = NULL;
 	TRANSACTION2_QPI_RSP *pSMBr = NULL;
+	int remap = cifs_remap(cifs_sb);
+	struct nls_table *nls_codepage = cifs_sb->local_nls;
 	int rc = 0;
 	int bytes_returned;
 	int list_len;
diff --git a/fs/cifs/connect.c b/fs/cifs/connect.c
index 35ae49ed1f76..59647eb72c5f 100644
--- a/fs/cifs/connect.c
+++ b/fs/cifs/connect.c
@@ -21,6 +21,7 @@
 #include <linux/fs.h>
 #include <linux/net.h>
 #include <linux/string.h>
+#include <linux/sched/signal.h>
 #include <linux/list.h>
 #include <linux/wait.h>
 #include <linux/slab.h>
@@ -34,6 +35,7 @@
 #include <linux/pagevec.h>
 #include <linux/freezer.h>
 #include <linux/namei.h>
+#include <linux/uuid.h>
 #include <linux/uaccess.h>
 #include <asm/processor.h>
 #include <linux/inet.h>
@@ -53,9 +55,7 @@
 #include "nterr.h"
 #include "rfc1002pdu.h"
 #include "fscache.h"
-#ifdef CONFIG_CIFS_SMB2
 #include "smb2proto.h"
-#endif
 
 #define CIFS_PORT 445
 #define RFC1001_PORT 139
@@ -339,9 +339,7 @@ cifs_reconnect(struct TCP_Server_Info *server)
 		server->tcpStatus = CifsNeedReconnect;
 	spin_unlock(&GlobalMid_Lock);
 	server->maxBuf = 0;
-#ifdef CONFIG_CIFS_SMB2
 	server->max_read = 0;
-#endif
 
 	cifs_dbg(FYI, "Reconnecting tcp session\n");
 
@@ -787,6 +785,15 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 
 	dump_smb(buf, server->total_read);
 
+	return cifs_handle_standard(server, mid);
+}
+
+int
+cifs_handle_standard(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+{
+	char *buf = server->large_buf ? server->bigbuf : server->smallbuf;
+	int length;
+
 	/*
 	 * We know that we received enough to get to the MID as we
 	 * checked the pdu_length earlier. Now check to see
@@ -801,6 +808,13 @@ standard_receive3(struct TCP_Server_Info *server, struct mid_q_entry *mid)
 		cifs_dump_mem("Bad SMB: ", buf,
 			min_t(unsigned int, server->total_read, 48));
 
+	if (server->ops->is_session_expired &&
+	    server->ops->is_session_expired(buf)) {
+		cifs_reconnect(server);
+		wake_up(&server->response_q);
+		return -1;
+	}
+
 	if (server->ops->is_status_pending &&
 	    server->ops->is_status_pending(buf, server, length))
 		return -1;
@@ -872,12 +886,19 @@ cifs_demultiplex_thread(void *p)
 			continue;
 		server->total_read += length;
 
-		mid_entry = server->ops->find_mid(server, buf);
+		if (server->ops->is_transform_hdr &&
+		    server->ops->receive_transform &&
+		    server->ops->is_transform_hdr(buf)) {
+			length = server->ops->receive_transform(server,
+								&mid_entry);
+		} else {
+			mid_entry = server->ops->find_mid(server, buf);
 
-		if (!mid_entry || !mid_entry->receive)
-			length = standard_receive3(server, mid_entry);
-		else
-			length = mid_entry->receive(server, mid_entry);
+			if (!mid_entry || !mid_entry->receive)
+				length = standard_receive3(server, mid_entry);
+			else
+				length = mid_entry->receive(server, mid_entry);
+		}
 
 		if (length < 0)
 			continue;
@@ -887,10 +908,19 @@ cifs_demultiplex_thread(void *p)
 
 		server->lstrp = jiffies;
 		if (mid_entry != NULL) {
+			if ((mid_entry->mid_flags & MID_WAIT_CANCELLED) &&
+			     mid_entry->mid_state == MID_RESPONSE_RECEIVED &&
+					server->ops->handle_cancelled_mid)
+				server->ops->handle_cancelled_mid(
+							mid_entry->resp_buf,
+							server);
+
 			if (!mid_entry->multiRsp || mid_entry->multiEnd)
 				mid_entry->callback(mid_entry);
-		} else if (!server->ops->is_oplock_break ||
-			   !server->ops->is_oplock_break(buf, server)) {
+		} else if (server->ops->is_oplock_break &&
+			   server->ops->is_oplock_break(buf, server)) {
+			cifs_dbg(FYI, "Received oplock break\n");
+		} else {
 			cifs_dbg(VFS, "No task to wake, unknown frame received! NumMids %d\n",
 				 atomic_read(&midCount));
 			cifs_dump_mem("Received Data is: ", buf,
@@ -1095,7 +1125,6 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol)
 		vol->ops = &smb1_operations;
 		vol->vals = &smb1_values;
 		break;
-#ifdef CONFIG_CIFS_SMB2
 	case Smb_20:
 		vol->ops = &smb20_operations;
 		vol->vals = &smb20_values;
@@ -1118,7 +1147,6 @@ cifs_parse_smb_version(char *value, struct smb_vol *vol)
 		vol->vals = &smb311_values;
 		break;
 #endif /* SMB311 */
-#endif
 	default:
 		cifs_dbg(VFS, "Unknown vers= option specified: %s\n", value);
 		return 1;
@@ -1244,9 +1272,9 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 
 	vol->actimeo = CIFS_DEF_ACTIMEO;
 
-	/* FIXME: add autonegotiation -- for now, SMB1 is default */
-	vol->ops = &smb1_operations;
-	vol->vals = &smb1_values;
+	/* FIXME: add autonegotiation for SMB3 or later rather than just SMB3 */
+	vol->ops = &smb30_operations; /* both secure and accepted widely */
+	vol->vals = &smb30_values;
 
 	vol->echo_interval = SMB_ECHO_INTERVAL_DEFAULT;
 
@@ -1919,9 +1947,14 @@ cifs_parse_mount_options(const char *mountdata, const char *devname,
 	}
 
 	if (!got_ip) {
+		int len;
+		const char *slash;
+
 		/* No ip= option specified? Try to get it from UNC */
-		if (!cifs_convert_address(dstaddr, &vol->UNC[2],
-						strlen(&vol->UNC[2]))) {
+		/* Use the address part of the UNC. */
+		slash = strchr(&vol->UNC[2], '\\');
+		len = slash - &vol->UNC[2];
+		if (!cifs_convert_address(dstaddr, &vol->UNC[2], len)) {
 			pr_err("Unable to determine destination address.\n");
 			goto cifs_parse_mount_err;
 		}
@@ -2057,7 +2090,8 @@ match_security(struct TCP_Server_Info *server, struct smb_vol *vol)
 	 * that was specified, or "Unspecified" if that sectype was not
 	 * compatible with the given NEGOTIATE request.
 	 */
-	if (select_sectype(server, vol->sectype) == Unspecified)
+	if (server->ops->select_sectype(server, vol->sectype)
+	     == Unspecified)
 		return false;
 
 	/*
@@ -2137,7 +2171,6 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 
 	cancel_delayed_work_sync(&server->echo);
 
-#ifdef CONFIG_CIFS_SMB2
 	if (from_reconnect)
 		/*
 		 * Avoid deadlock here: reconnect work calls
@@ -2148,13 +2181,12 @@ cifs_put_tcp_session(struct TCP_Server_Info *server, int from_reconnect)
 		cancel_delayed_work(&server->reconnect);
 	else
 		cancel_delayed_work_sync(&server->reconnect);
-#endif
 
 	spin_lock(&GlobalMid_Lock);
 	server->tcpStatus = CifsExiting;
 	spin_unlock(&GlobalMid_Lock);
 
-	cifs_crypto_shash_release(server);
+	cifs_crypto_secmech_release(server);
 	cifs_fscache_release_client_cookie(server);
 
 	kfree(server->session_key.response);
@@ -2214,17 +2246,13 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 	INIT_LIST_HEAD(&tcp_ses->tcp_ses_list);
 	INIT_LIST_HEAD(&tcp_ses->smb_ses_list);
 	INIT_DELAYED_WORK(&tcp_ses->echo, cifs_echo_request);
-#ifdef CONFIG_CIFS_SMB2
 	INIT_DELAYED_WORK(&tcp_ses->reconnect, smb2_reconnect_server);
 	mutex_init(&tcp_ses->reconnect_mutex);
-#endif
 	memcpy(&tcp_ses->srcaddr, &volume_info->srcaddr,
 	       sizeof(tcp_ses->srcaddr));
 	memcpy(&tcp_ses->dstaddr, &volume_info->dstaddr,
 		sizeof(tcp_ses->dstaddr));
-#ifdef CONFIG_CIFS_SMB2
 	generate_random_uuid(tcp_ses->client_guid);
-#endif
 	/*
 	 * at this point we are the only ones with the pointer
 	 * to the struct since the kernel thread not created yet
@@ -2273,7 +2301,7 @@ cifs_get_tcp_session(struct smb_vol *volume_info)
 	return tcp_ses;
 
 out_err_crypto_release:
-	cifs_crypto_shash_release(tcp_ses);
+	cifs_crypto_secmech_release(tcp_ses);
 
 	put_net(cifs_net_ns(tcp_ses));
 
@@ -2439,7 +2467,7 @@ cifs_set_cifscreds(struct smb_vol *vol, struct cifs_ses *ses)
 	}
 
 	down_read(&key->sem);
-	upayload = user_key_payload(key);
+	upayload = user_key_payload_locked(key);
 	if (IS_ERR_OR_NULL(upayload)) {
 		rc = upayload ? PTR_ERR(upayload) : -EINVAL;
 		goto out_key_put;
@@ -2614,11 +2642,15 @@ get_ses_fail:
 	return ERR_PTR(rc);
 }
 
-static int match_tcon(struct cifs_tcon *tcon, const char *unc)
+static int match_tcon(struct cifs_tcon *tcon, struct smb_vol *volume_info)
 {
 	if (tcon->tidStatus == CifsExiting)
 		return 0;
-	if (strncmp(tcon->treeName, unc, MAX_TREE_SIZE))
+	if (strncmp(tcon->treeName, volume_info->UNC, MAX_TREE_SIZE))
+		return 0;
+	if (tcon->seal != volume_info->seal)
+		return 0;
+	if (tcon->snapshot_time != volume_info->snapshot_time)
 		return 0;
 	return 1;
 }
@@ -2632,14 +2664,8 @@ cifs_find_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each(tmp, &ses->tcon_list) {
 		tcon = list_entry(tmp, struct cifs_tcon, tcon_list);
-		if (!match_tcon(tcon, volume_info->UNC))
+		if (!match_tcon(tcon, volume_info))
 			continue;
-
-#ifdef CONFIG_CIFS_SMB2
-		if (tcon->snapshot_time != volume_info->snapshot_time)
-			continue;
-#endif /* CONFIG_CIFS_SMB2 */
-
 		++tcon->tc_count;
 		spin_unlock(&cifs_tcp_ses_lock);
 		return tcon;
@@ -2685,8 +2711,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		cifs_dbg(FYI, "Found match on UNC path\n");
 		/* existing tcon already has a reference */
 		cifs_put_smb_ses(ses);
-		if (tcon->seal != volume_info->seal)
-			cifs_dbg(VFS, "transport encryption setting conflicts with existing tid\n");
 		return tcon;
 	}
 
@@ -2702,7 +2726,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 	}
 
 	if (volume_info->snapshot_time) {
-#ifdef CONFIG_CIFS_SMB2
 		if (ses->server->vals->protocol_id == 0) {
 			cifs_dbg(VFS,
 			     "Use SMB2 or later for snapshot mount option\n");
@@ -2710,11 +2733,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 			goto out_fail;
 		} else
 			tcon->snapshot_time = volume_info->snapshot_time;
-#else
-		cifs_dbg(VFS, "Snapshot mount option requires SMB2 support\n");
-		rc = -EOPNOTSUPP;
-		goto out_fail;
-#endif /* CONFIG_CIFS_SMB2 */
 	}
 
 	tcon->ses = ses;
@@ -2742,7 +2760,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		tcon->Flags &= ~SMB_SHARE_IS_IN_DFS;
 		cifs_dbg(FYI, "DFS disabled (%d)\n", tcon->Flags);
 	}
-	tcon->seal = volume_info->seal;
 	tcon->use_persistent = false;
 	/* check if SMB2 or later, CIFS does not support persistent handles */
 	if (volume_info->persistent) {
@@ -2751,7 +2768,6 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 			     "SMB3 or later required for persistent handles\n");
 			rc = -EOPNOTSUPP;
 			goto out_fail;
-#ifdef CONFIG_CIFS_SMB2
 		} else if (ses->server->capabilities &
 			   SMB2_GLOBAL_CAP_PERSISTENT_HANDLES)
 			tcon->use_persistent = true;
@@ -2760,15 +2776,12 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 				"Persistent handles not supported on share\n");
 			rc = -EOPNOTSUPP;
 			goto out_fail;
-#endif /* CONFIG_CIFS_SMB2 */
 		}
-#ifdef CONFIG_CIFS_SMB2
 	} else if ((tcon->capabilities & SMB2_SHARE_CAP_CONTINUOUS_AVAILABILITY)
 	     && (ses->server->capabilities & SMB2_GLOBAL_CAP_PERSISTENT_HANDLES)
 	     && (volume_info->nopersistent == false)) {
 		cifs_dbg(FYI, "enabling persistent handles\n");
 		tcon->use_persistent = true;
-#endif /* CONFIG_CIFS_SMB2 */
 	} else if (volume_info->resilient) {
 		if (ses->server->vals->protocol_id == 0) {
 			cifs_dbg(VFS,
@@ -2779,6 +2792,22 @@ cifs_get_tcon(struct cifs_ses *ses, struct smb_vol *volume_info)
 		tcon->use_resilient = true;
 	}
 
+	if (volume_info->seal) {
+		if (ses->server->vals->protocol_id == 0) {
+			cifs_dbg(VFS,
+				 "SMB3 or later required for encryption\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
+		} else if (tcon->ses->server->capabilities &
+					SMB2_GLOBAL_CAP_ENCRYPTION)
+			tcon->seal = true;
+		else {
+			cifs_dbg(VFS, "Encryption is not supported on share\n");
+			rc = -EOPNOTSUPP;
+			goto out_fail;
+		}
+	}
+
 	/*
 	 * We can have only one retry value for a connection to a share so for
 	 * resources mounted more than once to the same server share the last
@@ -2870,16 +2899,14 @@ match_prepath(struct super_block *sb, struct cifs_mnt_data *mnt_data)
 {
 	struct cifs_sb_info *old = CIFS_SB(sb);
 	struct cifs_sb_info *new = mnt_data->cifs_sb;
+	bool old_set = old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH;
+	bool new_set = new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH;
 
-	if (old->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH) {
-		if (!(new->mnt_cifs_flags & CIFS_MOUNT_USE_PREFIX_PATH))
-			return 0;
-		/* The prepath should be null terminated strings */
-		if (strcmp(new->prepath, old->prepath))
-			return 0;
-
+	if (old_set && new_set && !strcmp(new->prepath, old->prepath))
 		return 1;
-	}
+	else if (!old_set && !new_set)
+		return 1;
+
 	return 0;
 }
 
@@ -2910,7 +2937,7 @@ cifs_match_super(struct super_block *sb, void *data)
 
 	if (!match_server(tcp_srv, volume_info) ||
 	    !match_session(ses, volume_info) ||
-	    !match_tcon(tcon, volume_info->UNC) ||
+	    !match_tcon(tcon, volume_info) ||
 	    !match_prepath(sb, mnt_data)) {
 		rc = 0;
 		goto out;
@@ -3650,10 +3677,6 @@ cifs_mount(struct cifs_sb_info *cifs_sb, struct smb_vol *volume_info)
 	int referral_walks_count = 0;
 #endif
 
-	rc = bdi_setup_and_register(&cifs_sb->bdi, "cifs");
-	if (rc)
-		return rc;
-
 #ifdef CONFIG_CIFS_DFS_UPCALL
 try_mount_again:
 	/* cleanup activities if we're chasing a referral */
@@ -3681,7 +3704,6 @@ try_mount_again:
 	server = cifs_get_tcp_session(volume_info);
 	if (IS_ERR(server)) {
 		rc = PTR_ERR(server);
-		bdi_destroy(&cifs_sb->bdi);
 		goto out;
 	}
 	if ((volume_info->max_credits < 20) ||
@@ -3697,20 +3719,21 @@ try_mount_again:
 		goto mount_fail_check;
 	}
 
-#ifdef CONFIG_CIFS_SMB2
 	if ((volume_info->persistent == true) && ((ses->server->capabilities &
 		SMB2_GLOBAL_CAP_PERSISTENT_HANDLES) == 0)) {
 		cifs_dbg(VFS, "persistent handles not supported by server\n");
 		rc = -EOPNOTSUPP;
 		goto mount_fail_check;
 	}
-#endif /* CONFIG_CIFS_SMB2*/
 
 	/* search for existing tcon to this server share */
 	tcon = cifs_get_tcon(ses, volume_info);
 	if (IS_ERR(tcon)) {
 		rc = PTR_ERR(tcon);
 		tcon = NULL;
+		if (rc == -EACCES)
+			goto mount_fail_check;
+
 		goto remote_path_check;
 	}
 
@@ -3735,9 +3758,6 @@ try_mount_again:
 	cifs_sb->wsize = server->ops->negotiate_wsize(tcon, volume_info);
 	cifs_sb->rsize = server->ops->negotiate_rsize(tcon, volume_info);
 
-	/* tune readahead according to rsize */
-	cifs_sb->bdi.ra_pages = cifs_sb->rsize / PAGE_SIZE;
-
 remote_path_check:
 #ifdef CONFIG_CIFS_DFS_UPCALL
 	/*
@@ -3854,7 +3874,6 @@ mount_fail_check:
 			cifs_put_smb_ses(ses);
 		else
 			cifs_put_tcp_session(server, 0);
-		bdi_destroy(&cifs_sb->bdi);
 	}
 
 out:
@@ -4057,7 +4076,6 @@ cifs_umount(struct cifs_sb_info *cifs_sb)
 	}
 	spin_unlock(&cifs_sb->tlink_tree_lock);
 
-	bdi_destroy(&cifs_sb->bdi);
 	kfree(cifs_sb->mountdata);
 	kfree(cifs_sb->prepath);
 	call_rcu(&cifs_sb->rcu, delayed_free);
diff --git a/fs/cifs/dir.c b/fs/cifs/dir.c
index 2c227a99f369..56366e984076 100644
--- a/fs/cifs/dir.c
+++ b/fs/cifs/dir.c
@@ -81,6 +81,17 @@ cifs_build_path_to_root(struct smb_vol *vol, struct cifs_sb_info *cifs_sb,
 char *
 build_path_from_dentry(struct dentry *direntry)
 {
+	struct cifs_sb_info *cifs_sb = CIFS_SB(direntry->d_sb);
+	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
+	bool prefix = tcon->Flags & SMB_SHARE_IS_IN_DFS;
+
+	return build_path_from_dentry_optional_prefix(direntry,
+						      prefix);
+}
+
+char *
+build_path_from_dentry_optional_prefix(struct dentry *direntry, bool prefix)
+{
 	struct dentry *temp;
 	int namelen;
 	int dfsplen;
@@ -92,7 +103,7 @@ build_path_from_dentry(struct dentry *direntry)
 	unsigned seq;
 
 	dirsep = CIFS_DIR_SEP(cifs_sb);
-	if (tcon->Flags & SMB_SHARE_IS_IN_DFS)
+	if (prefix)
 		dfsplen = strnlen(tcon->treeName, MAX_TREE_SIZE + 1);
 	else
 		dfsplen = 0;
diff --git a/fs/cifs/file.c b/fs/cifs/file.c
index 18a1e1d6671f..bc09df6b473a 100644
--- a/fs/cifs/file.c
+++ b/fs/cifs/file.c
@@ -582,7 +582,7 @@ cifs_relock_file(struct cifsFileInfo *cfile)
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 	int rc = 0;
 
-	down_read(&cinode->lock_sem);
+	down_read_nested(&cinode->lock_sem, SINGLE_DEPTH_NESTING);
 	if (cinode->can_cache_brlcks) {
 		/* can cache locks - no need to relock */
 		up_read(&cinode->lock_sem);
@@ -2234,14 +2234,16 @@ cifs_writepage_locked(struct page *page, struct writeback_control *wbc)
 	set_page_writeback(page);
 retry_write:
 	rc = cifs_partialpagewrite(page, 0, PAGE_SIZE);
-	if (rc == -EAGAIN && wbc->sync_mode == WB_SYNC_ALL)
-		goto retry_write;
-	else if (rc == -EAGAIN)
+	if (rc == -EAGAIN) {
+		if (wbc->sync_mode == WB_SYNC_ALL)
+			goto retry_write;
 		redirty_page_for_writepage(wbc, page);
-	else if (rc != 0)
+	} else if (rc != 0) {
 		SetPageError(page);
-	else
+		mapping_set_error(page->mapping, rc);
+	} else {
 		SetPageUptodate(page);
+	}
 	end_page_writeback(page);
 	put_page(page);
 	free_xid(xid);
@@ -2458,11 +2460,14 @@ cifs_uncached_writedata_release(struct kref *refcount)
 	struct cifs_writedata *wdata = container_of(refcount,
 					struct cifs_writedata, refcount);
 
+	kref_put(&wdata->ctx->refcount, cifs_aio_ctx_release);
 	for (i = 0; i < wdata->nr_pages; i++)
 		put_page(wdata->pages[i]);
 	cifs_writedata_release(refcount);
 }
 
+static void collect_uncached_write_data(struct cifs_aio_ctx *ctx);
+
 static void
 cifs_uncached_writev_complete(struct work_struct *work)
 {
@@ -2478,7 +2483,8 @@ cifs_uncached_writev_complete(struct work_struct *work)
 	spin_unlock(&inode->i_lock);
 
 	complete(&wdata->done);
-
+	collect_uncached_write_data(wdata->ctx);
+	/* the below call can possibly free the last ref to aio ctx */
 	kref_put(&wdata->refcount, cifs_uncached_writedata_release);
 }
 
@@ -2527,7 +2533,8 @@ wdata_fill_from_iovec(struct cifs_writedata *wdata, struct iov_iter *from,
 static int
 cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 		     struct cifsFileInfo *open_file,
-		     struct cifs_sb_info *cifs_sb, struct list_head *wdata_list)
+		     struct cifs_sb_info *cifs_sb, struct list_head *wdata_list,
+		     struct cifs_aio_ctx *ctx)
 {
 	int rc = 0;
 	size_t cur_len;
@@ -2595,9 +2602,11 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 		wdata->pagesz = PAGE_SIZE;
 		wdata->tailsz = cur_len - ((nr_pages - 1) * PAGE_SIZE);
 		wdata->credits = credits;
+		wdata->ctx = ctx;
+		kref_get(&ctx->refcount);
 
 		if (!wdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(wdata->cfile, false))
+		    !(rc = cifs_reopen_file(wdata->cfile, false)))
 			rc = server->ops->async_writev(wdata,
 					cifs_uncached_writedata_release);
 		if (rc) {
@@ -2620,81 +2629,61 @@ cifs_write_from_iter(loff_t offset, size_t len, struct iov_iter *from,
 	return rc;
 }
 
-ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
+static void collect_uncached_write_data(struct cifs_aio_ctx *ctx)
 {
-	struct file *file = iocb->ki_filp;
-	ssize_t total_written = 0;
-	struct cifsFileInfo *open_file;
+	struct cifs_writedata *wdata, *tmp;
 	struct cifs_tcon *tcon;
 	struct cifs_sb_info *cifs_sb;
-	struct cifs_writedata *wdata, *tmp;
-	struct list_head wdata_list;
-	struct iov_iter saved_from = *from;
+	struct dentry *dentry = ctx->cfile->dentry;
+	unsigned int i;
 	int rc;
 
-	/*
-	 * BB - optimize the way when signing is disabled. We can drop this
-	 * extra memory-to-memory copying and use iovec buffers for constructing
-	 * write request.
-	 */
-
-	rc = generic_write_checks(iocb, from);
-	if (rc <= 0)
-		return rc;
-
-	INIT_LIST_HEAD(&wdata_list);
-	cifs_sb = CIFS_FILE_SB(file);
-	open_file = file->private_data;
-	tcon = tlink_tcon(open_file->tlink);
-
-	if (!tcon->ses->server->ops->async_writev)
-		return -ENOSYS;
+	tcon = tlink_tcon(ctx->cfile->tlink);
+	cifs_sb = CIFS_SB(dentry->d_sb);
 
-	rc = cifs_write_from_iter(iocb->ki_pos, iov_iter_count(from), from,
-				  open_file, cifs_sb, &wdata_list);
+	mutex_lock(&ctx->aio_mutex);
 
-	/*
-	 * If at least one write was successfully sent, then discard any rc
-	 * value from the later writes. If the other write succeeds, then
-	 * we'll end up returning whatever was written. If it fails, then
-	 * we'll get a new rc value from that.
-	 */
-	if (!list_empty(&wdata_list))
-		rc = 0;
+	if (list_empty(&ctx->list)) {
+		mutex_unlock(&ctx->aio_mutex);
+		return;
+	}
 
+	rc = ctx->rc;
 	/*
 	 * Wait for and collect replies for any successful sends in order of
-	 * increasing offset. Once an error is hit or we get a fatal signal
-	 * while waiting, then return without waiting for any more replies.
+	 * increasing offset. Once an error is hit, then return without waiting
+	 * for any more replies.
 	 */
 restart_loop:
-	list_for_each_entry_safe(wdata, tmp, &wdata_list, list) {
+	list_for_each_entry_safe(wdata, tmp, &ctx->list, list) {
 		if (!rc) {
-			/* FIXME: freezable too? */
-			rc = wait_for_completion_killable(&wdata->done);
-			if (rc)
-				rc = -EINTR;
-			else if (wdata->result)
+			if (!try_wait_for_completion(&wdata->done)) {
+				mutex_unlock(&ctx->aio_mutex);
+				return;
+			}
+
+			if (wdata->result)
 				rc = wdata->result;
 			else
-				total_written += wdata->bytes;
+				ctx->total_len += wdata->bytes;
 
 			/* resend call if it's a retryable error */
 			if (rc == -EAGAIN) {
 				struct list_head tmp_list;
-				struct iov_iter tmp_from = saved_from;
+				struct iov_iter tmp_from = ctx->iter;
 
 				INIT_LIST_HEAD(&tmp_list);
 				list_del_init(&wdata->list);
 
 				iov_iter_advance(&tmp_from,
-						 wdata->offset - iocb->ki_pos);
+						 wdata->offset - ctx->pos);
 
 				rc = cifs_write_from_iter(wdata->offset,
 						wdata->bytes, &tmp_from,
-						open_file, cifs_sb, &tmp_list);
+						ctx->cfile, cifs_sb, &tmp_list,
+						ctx);
 
-				list_splice(&tmp_list, &wdata_list);
+				list_splice(&tmp_list, &ctx->list);
 
 				kref_put(&wdata->refcount,
 					 cifs_uncached_writedata_release);
@@ -2705,12 +2694,111 @@ restart_loop:
 		kref_put(&wdata->refcount, cifs_uncached_writedata_release);
 	}
 
+	for (i = 0; i < ctx->npages; i++)
+		put_page(ctx->bv[i].bv_page);
+
+	cifs_stats_bytes_written(tcon, ctx->total_len);
+	set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(dentry->d_inode)->flags);
+
+	ctx->rc = (rc == 0) ? ctx->total_len : rc;
+
+	mutex_unlock(&ctx->aio_mutex);
+
+	if (ctx->iocb && ctx->iocb->ki_complete)
+		ctx->iocb->ki_complete(ctx->iocb, ctx->rc, 0);
+	else
+		complete(&ctx->done);
+}
+
+ssize_t cifs_user_writev(struct kiocb *iocb, struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	ssize_t total_written = 0;
+	struct cifsFileInfo *cfile;
+	struct cifs_tcon *tcon;
+	struct cifs_sb_info *cifs_sb;
+	struct cifs_aio_ctx *ctx;
+	struct iov_iter saved_from = *from;
+	int rc;
+
+	/*
+	 * BB - optimize the way when signing is disabled. We can drop this
+	 * extra memory-to-memory copying and use iovec buffers for constructing
+	 * write request.
+	 */
+
+	rc = generic_write_checks(iocb, from);
+	if (rc <= 0)
+		return rc;
+
+	cifs_sb = CIFS_FILE_SB(file);
+	cfile = file->private_data;
+	tcon = tlink_tcon(cfile->tlink);
+
+	if (!tcon->ses->server->ops->async_writev)
+		return -ENOSYS;
+
+	ctx = cifs_aio_ctx_alloc();
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->cfile = cifsFileInfo_get(cfile);
+
+	if (!is_sync_kiocb(iocb))
+		ctx->iocb = iocb;
+
+	ctx->pos = iocb->ki_pos;
+
+	rc = setup_aio_ctx_iter(ctx, from, WRITE);
+	if (rc) {
+		kref_put(&ctx->refcount, cifs_aio_ctx_release);
+		return rc;
+	}
+
+	/* grab a lock here due to read response handlers can access ctx */
+	mutex_lock(&ctx->aio_mutex);
+
+	rc = cifs_write_from_iter(iocb->ki_pos, ctx->len, &saved_from,
+				  cfile, cifs_sb, &ctx->list, ctx);
+
+	/*
+	 * If at least one write was successfully sent, then discard any rc
+	 * value from the later writes. If the other write succeeds, then
+	 * we'll end up returning whatever was written. If it fails, then
+	 * we'll get a new rc value from that.
+	 */
+	if (!list_empty(&ctx->list))
+		rc = 0;
+
+	mutex_unlock(&ctx->aio_mutex);
+
+	if (rc) {
+		kref_put(&ctx->refcount, cifs_aio_ctx_release);
+		return rc;
+	}
+
+	if (!is_sync_kiocb(iocb)) {
+		kref_put(&ctx->refcount, cifs_aio_ctx_release);
+		return -EIOCBQUEUED;
+	}
+
+	rc = wait_for_completion_killable(&ctx->done);
+	if (rc) {
+		mutex_lock(&ctx->aio_mutex);
+		ctx->rc = rc = -EINTR;
+		total_written = ctx->total_len;
+		mutex_unlock(&ctx->aio_mutex);
+	} else {
+		rc = ctx->rc;
+		total_written = ctx->total_len;
+	}
+
+	kref_put(&ctx->refcount, cifs_aio_ctx_release);
+
 	if (unlikely(!total_written))
 		return rc;
 
 	iocb->ki_pos += total_written;
-	set_bit(CIFS_INO_INVALID_MAPPING, &CIFS_I(file_inode(file))->flags);
-	cifs_stats_bytes_written(tcon, total_written);
 	return total_written;
 }
 
@@ -2724,12 +2812,12 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 	struct TCP_Server_Info *server = tlink_tcon(cfile->tlink)->ses->server;
 	ssize_t rc;
 
+	inode_lock(inode);
 	/*
 	 * We need to hold the sem to be sure nobody modifies lock list
 	 * with a brlock that prevents writing.
 	 */
 	down_read(&cinode->lock_sem);
-	inode_lock(inode);
 
 	rc = generic_write_checks(iocb, from);
 	if (rc <= 0)
@@ -2742,11 +2830,11 @@ cifs_writev(struct kiocb *iocb, struct iov_iter *from)
 	else
 		rc = -EACCES;
 out:
+	up_read(&cinode->lock_sem);
 	inode_unlock(inode);
 
 	if (rc > 0)
 		rc = generic_write_sync(iocb, rc);
-	up_read(&cinode->lock_sem);
 	return rc;
 }
 
@@ -2859,6 +2947,7 @@ cifs_uncached_readdata_release(struct kref *refcount)
 					struct cifs_readdata, refcount);
 	unsigned int i;
 
+	kref_put(&rdata->ctx->refcount, cifs_aio_ctx_release);
 	for (i = 0; i < rdata->nr_pages; i++) {
 		put_page(rdata->pages[i]);
 		rdata->pages[i] = NULL;
@@ -2884,7 +2973,15 @@ cifs_readdata_to_iov(struct cifs_readdata *rdata, struct iov_iter *iter)
 	for (i = 0; i < rdata->nr_pages; i++) {
 		struct page *page = rdata->pages[i];
 		size_t copy = min_t(size_t, remaining, PAGE_SIZE);
-		size_t written = copy_page_to_iter(page, 0, copy, iter);
+		size_t written;
+
+		if (unlikely(iter->type & ITER_PIPE)) {
+			void *addr = kmap_atomic(page);
+
+			written = copy_to_iter(addr, copy, iter);
+			kunmap_atomic(addr);
+		} else
+			written = copy_page_to_iter(page, 0, copy, iter);
 		remaining -= written;
 		if (written < copy && iov_iter_count(iter) > 0)
 			break;
@@ -2892,6 +2989,8 @@ cifs_readdata_to_iov(struct cifs_readdata *rdata, struct iov_iter *iter)
 	return remaining ? -EFAULT : 0;
 }
 
+static void collect_uncached_read_data(struct cifs_aio_ctx *ctx);
+
 static void
 cifs_uncached_readv_complete(struct work_struct *work)
 {
@@ -2899,12 +2998,15 @@ cifs_uncached_readv_complete(struct work_struct *work)
 						struct cifs_readdata, work);
 
 	complete(&rdata->done);
+	collect_uncached_read_data(rdata->ctx);
+	/* the below call can possibly free the last ref to aio ctx */
 	kref_put(&rdata->refcount, cifs_uncached_readdata_release);
 }
 
 static int
-cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
-			struct cifs_readdata *rdata, unsigned int len)
+uncached_fill_pages(struct TCP_Server_Info *server,
+		    struct cifs_readdata *rdata, struct iov_iter *iter,
+		    unsigned int len)
 {
 	int result = 0;
 	unsigned int i;
@@ -2933,7 +3035,10 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
 			rdata->tailsz = len;
 			len = 0;
 		}
-		result = cifs_read_page_from_socket(server, page, n);
+		if (iter)
+			result = copy_page_from_iter(page, 0, n, iter);
+		else
+			result = cifs_read_page_from_socket(server, page, n);
 		if (result < 0)
 			break;
 
@@ -2945,8 +3050,24 @@ cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
 }
 
 static int
+cifs_uncached_read_into_pages(struct TCP_Server_Info *server,
+			      struct cifs_readdata *rdata, unsigned int len)
+{
+	return uncached_fill_pages(server, rdata, NULL, len);
+}
+
+static int
+cifs_uncached_copy_into_pages(struct TCP_Server_Info *server,
+			      struct cifs_readdata *rdata,
+			      struct iov_iter *iter)
+{
+	return uncached_fill_pages(server, rdata, iter, iter->count);
+}
+
+static int
 cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
-		     struct cifs_sb_info *cifs_sb, struct list_head *rdata_list)
+		     struct cifs_sb_info *cifs_sb, struct list_head *rdata_list,
+		     struct cifs_aio_ctx *ctx)
 {
 	struct cifs_readdata *rdata;
 	unsigned int npages, rsize, credits;
@@ -2991,10 +3112,13 @@ cifs_send_async_read(loff_t offset, size_t len, struct cifsFileInfo *open_file,
 		rdata->pid = pid;
 		rdata->pagesz = PAGE_SIZE;
 		rdata->read_into_pages = cifs_uncached_read_into_pages;
+		rdata->copy_into_pages = cifs_uncached_copy_into_pages;
 		rdata->credits = credits;
+		rdata->ctx = ctx;
+		kref_get(&ctx->refcount);
 
 		if (!rdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(rdata->cfile, true))
+		    !(rc = cifs_reopen_file(rdata->cfile, true)))
 			rc = server->ops->async_readv(rdata);
 error:
 		if (rc) {
@@ -3014,50 +3138,37 @@ error:
 	return rc;
 }
 
-ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
+static void
+collect_uncached_read_data(struct cifs_aio_ctx *ctx)
 {
-	struct file *file = iocb->ki_filp;
-	ssize_t rc;
-	size_t len;
-	ssize_t total_read = 0;
-	loff_t offset = iocb->ki_pos;
+	struct cifs_readdata *rdata, *tmp;
+	struct iov_iter *to = &ctx->iter;
 	struct cifs_sb_info *cifs_sb;
 	struct cifs_tcon *tcon;
-	struct cifsFileInfo *open_file;
-	struct cifs_readdata *rdata, *tmp;
-	struct list_head rdata_list;
-
-	len = iov_iter_count(to);
-	if (!len)
-		return 0;
-
-	INIT_LIST_HEAD(&rdata_list);
-	cifs_sb = CIFS_FILE_SB(file);
-	open_file = file->private_data;
-	tcon = tlink_tcon(open_file->tlink);
-
-	if (!tcon->ses->server->ops->async_readv)
-		return -ENOSYS;
+	unsigned int i;
+	int rc;
 
-	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
-		cifs_dbg(FYI, "attempting read on write only file instance\n");
+	tcon = tlink_tcon(ctx->cfile->tlink);
+	cifs_sb = CIFS_SB(ctx->cfile->dentry->d_sb);
 
-	rc = cifs_send_async_read(offset, len, open_file, cifs_sb, &rdata_list);
+	mutex_lock(&ctx->aio_mutex);
 
-	/* if at least one read request send succeeded, then reset rc */
-	if (!list_empty(&rdata_list))
-		rc = 0;
+	if (list_empty(&ctx->list)) {
+		mutex_unlock(&ctx->aio_mutex);
+		return;
+	}
 
-	len = iov_iter_count(to);
+	rc = ctx->rc;
 	/* the loop below should proceed in the order of increasing offsets */
 again:
-	list_for_each_entry_safe(rdata, tmp, &rdata_list, list) {
+	list_for_each_entry_safe(rdata, tmp, &ctx->list, list) {
 		if (!rc) {
-			/* FIXME: freezable sleep too? */
-			rc = wait_for_completion_killable(&rdata->done);
-			if (rc)
-				rc = -EINTR;
-			else if (rdata->result == -EAGAIN) {
+			if (!try_wait_for_completion(&rdata->done)) {
+				mutex_unlock(&ctx->aio_mutex);
+				return;
+			}
+
+			if (rdata->result == -EAGAIN) {
 				/* resend call if it's a retryable error */
 				struct list_head tmp_list;
 				unsigned int got_bytes = rdata->got_bytes;
@@ -3083,9 +3194,9 @@ again:
 						rdata->offset + got_bytes,
 						rdata->bytes - got_bytes,
 						rdata->cfile, cifs_sb,
-						&tmp_list);
+						&tmp_list, ctx);
 
-				list_splice(&tmp_list, &rdata_list);
+				list_splice(&tmp_list, &ctx->list);
 
 				kref_put(&rdata->refcount,
 					 cifs_uncached_readdata_release);
@@ -3103,14 +3214,110 @@ again:
 		kref_put(&rdata->refcount, cifs_uncached_readdata_release);
 	}
 
-	total_read = len - iov_iter_count(to);
+	for (i = 0; i < ctx->npages; i++) {
+		if (ctx->should_dirty)
+			set_page_dirty(ctx->bv[i].bv_page);
+		put_page(ctx->bv[i].bv_page);
+	}
+
+	ctx->total_len = ctx->len - iov_iter_count(to);
 
-	cifs_stats_bytes_read(tcon, total_read);
+	cifs_stats_bytes_read(tcon, ctx->total_len);
 
 	/* mask nodata case */
 	if (rc == -ENODATA)
 		rc = 0;
 
+	ctx->rc = (rc == 0) ? ctx->total_len : rc;
+
+	mutex_unlock(&ctx->aio_mutex);
+
+	if (ctx->iocb && ctx->iocb->ki_complete)
+		ctx->iocb->ki_complete(ctx->iocb, ctx->rc, 0);
+	else
+		complete(&ctx->done);
+}
+
+ssize_t cifs_user_readv(struct kiocb *iocb, struct iov_iter *to)
+{
+	struct file *file = iocb->ki_filp;
+	ssize_t rc;
+	size_t len;
+	ssize_t total_read = 0;
+	loff_t offset = iocb->ki_pos;
+	struct cifs_sb_info *cifs_sb;
+	struct cifs_tcon *tcon;
+	struct cifsFileInfo *cfile;
+	struct cifs_aio_ctx *ctx;
+
+	len = iov_iter_count(to);
+	if (!len)
+		return 0;
+
+	cifs_sb = CIFS_FILE_SB(file);
+	cfile = file->private_data;
+	tcon = tlink_tcon(cfile->tlink);
+
+	if (!tcon->ses->server->ops->async_readv)
+		return -ENOSYS;
+
+	if ((file->f_flags & O_ACCMODE) == O_WRONLY)
+		cifs_dbg(FYI, "attempting read on write only file instance\n");
+
+	ctx = cifs_aio_ctx_alloc();
+	if (!ctx)
+		return -ENOMEM;
+
+	ctx->cfile = cifsFileInfo_get(cfile);
+
+	if (!is_sync_kiocb(iocb))
+		ctx->iocb = iocb;
+
+	if (to->type == ITER_IOVEC)
+		ctx->should_dirty = true;
+
+	rc = setup_aio_ctx_iter(ctx, to, READ);
+	if (rc) {
+		kref_put(&ctx->refcount, cifs_aio_ctx_release);
+		return rc;
+	}
+
+	len = ctx->len;
+
+	/* grab a lock here due to read response handlers can access ctx */
+	mutex_lock(&ctx->aio_mutex);
+
+	rc = cifs_send_async_read(offset, len, cfile, cifs_sb, &ctx->list, ctx);
+
+	/* if at least one read request send succeeded, then reset rc */
+	if (!list_empty(&ctx->list))
+		rc = 0;
+
+	mutex_unlock(&ctx->aio_mutex);
+
+	if (rc) {
+		kref_put(&ctx->refcount, cifs_aio_ctx_release);
+		return rc;
+	}
+
+	if (!is_sync_kiocb(iocb)) {
+		kref_put(&ctx->refcount, cifs_aio_ctx_release);
+		return -EIOCBQUEUED;
+	}
+
+	rc = wait_for_completion_killable(&ctx->done);
+	if (rc) {
+		mutex_lock(&ctx->aio_mutex);
+		ctx->rc = rc = -EINTR;
+		total_read = ctx->total_len;
+		mutex_unlock(&ctx->aio_mutex);
+	} else {
+		rc = ctx->rc;
+		total_read = ctx->total_len;
+	}
+
+	kref_put(&ctx->refcount, cifs_aio_ctx_release);
+
 	if (total_read) {
 		iocb->ki_pos += total_read;
 		return total_read;
@@ -3254,7 +3461,7 @@ cifs_read(struct file *file, char *read_data, size_t read_size, loff_t *offset)
  * sure that it doesn't change while being written back.
  */
 static int
-cifs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+cifs_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
 
@@ -3341,8 +3548,9 @@ cifs_readv_complete(struct work_struct *work)
 }
 
 static int
-cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
-			struct cifs_readdata *rdata, unsigned int len)
+readpages_fill_pages(struct TCP_Server_Info *server,
+		     struct cifs_readdata *rdata, struct iov_iter *iter,
+		     unsigned int len)
 {
 	int result = 0;
 	unsigned int i;
@@ -3396,7 +3604,10 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
 			continue;
 		}
 
-		result = cifs_read_page_from_socket(server, page, n);
+		if (iter)
+			result = copy_page_from_iter(page, 0, n, iter);
+		else
+			result = cifs_read_page_from_socket(server, page, n);
 		if (result < 0)
 			break;
 
@@ -3408,6 +3619,21 @@ cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
 }
 
 static int
+cifs_readpages_read_into_pages(struct TCP_Server_Info *server,
+			       struct cifs_readdata *rdata, unsigned int len)
+{
+	return readpages_fill_pages(server, rdata, NULL, len);
+}
+
+static int
+cifs_readpages_copy_into_pages(struct TCP_Server_Info *server,
+			       struct cifs_readdata *rdata,
+			       struct iov_iter *iter)
+{
+	return readpages_fill_pages(server, rdata, iter, iter->count);
+}
+
+static int
 readpages_get_pages(struct address_space *mapping, struct list_head *page_list,
 		    unsigned int rsize, struct list_head *tmplist,
 		    unsigned int *nr_pages, loff_t *offset, unsigned int *bytes)
@@ -3561,6 +3787,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		rdata->pid = pid;
 		rdata->pagesz = PAGE_SIZE;
 		rdata->read_into_pages = cifs_readpages_read_into_pages;
+		rdata->copy_into_pages = cifs_readpages_copy_into_pages;
 		rdata->credits = credits;
 
 		list_for_each_entry_safe(page, tpage, &tmplist, lru) {
@@ -3569,7 +3796,7 @@ static int cifs_readpages(struct file *file, struct address_space *mapping,
 		}
 
 		if (!rdata->cfile->invalidHandle ||
-		    !cifs_reopen_file(rdata->cfile, true))
+		    !(rc = cifs_reopen_file(rdata->cfile, true)))
 			rc = server->ops->async_readv(rdata);
 		if (rc) {
 			add_credits_and_wake_if(server, rdata->credits, 0);
diff --git a/fs/cifs/inode.c b/fs/cifs/inode.c
index 7ab5be7944aa..a8693632235f 100644
--- a/fs/cifs/inode.c
+++ b/fs/cifs/inode.c
@@ -23,6 +23,9 @@
 #include <linux/slab.h>
 #include <linux/pagemap.h>
 #include <linux/freezer.h>
+#include <linux/sched/signal.h>
+#include <linux/wait_bit.h>
+
 #include <asm/div64.h>
 #include "cifsfs.h"
 #include "cifspdu.h"
@@ -320,9 +323,9 @@ cifs_create_dfs_fattr(struct cifs_fattr *fattr, struct super_block *sb)
 	fattr->cf_mode = S_IFDIR | S_IXUGO | S_IRWXU;
 	fattr->cf_uid = cifs_sb->mnt_uid;
 	fattr->cf_gid = cifs_sb->mnt_gid;
-	fattr->cf_atime = CURRENT_TIME;
-	fattr->cf_ctime = CURRENT_TIME;
-	fattr->cf_mtime = CURRENT_TIME;
+	ktime_get_real_ts(&fattr->cf_mtime);
+	fattr->cf_mtime = timespec_trunc(fattr->cf_mtime, sb->s_time_gran);
+	fattr->cf_atime = fattr->cf_ctime = fattr->cf_mtime;
 	fattr->cf_nlink = 2;
 	fattr->cf_flags |= CIFS_FATTR_DFS_REFERRAL;
 }
@@ -561,8 +564,7 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path,
 
 	rc = tcon->ses->server->ops->query_all_EAs(xid, tcon, path,
 			"SETFILEBITS", ea_value, 4 /* size of buf */,
-			cifs_sb->local_nls,
-			cifs_remap(cifs_sb));
+			cifs_sb);
 	cifs_put_tlink(tlink);
 	if (rc < 0)
 		return (int)rc;
@@ -584,9 +586,10 @@ static int cifs_sfu_mode(struct cifs_fattr *fattr, const unsigned char *path,
 /* Fill a cifs_fattr struct with info from FILE_ALL_INFO */
 static void
 cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
-		       struct cifs_sb_info *cifs_sb, bool adjust_tz,
+		       struct super_block *sb, bool adjust_tz,
 		       bool symlink)
 {
+	struct cifs_sb_info *cifs_sb = CIFS_SB(sb);
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 
 	memset(fattr, 0, sizeof(*fattr));
@@ -596,8 +599,10 @@ cifs_all_info_to_fattr(struct cifs_fattr *fattr, FILE_ALL_INFO *info,
 
 	if (info->LastAccessTime)
 		fattr->cf_atime = cifs_NTtimeToUnix(info->LastAccessTime);
-	else
-		fattr->cf_atime = CURRENT_TIME;
+	else {
+		ktime_get_real_ts(&fattr->cf_atime);
+		fattr->cf_atime = timespec_trunc(fattr->cf_atime, sb->s_time_gran);
+	}
 
 	fattr->cf_ctime = cifs_NTtimeToUnix(info->ChangeTime);
 	fattr->cf_mtime = cifs_NTtimeToUnix(info->LastWriteTime);
@@ -657,7 +662,6 @@ cifs_get_file_info(struct file *filp)
 	FILE_ALL_INFO find_data;
 	struct cifs_fattr fattr;
 	struct inode *inode = file_inode(filp);
-	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
 	struct cifsFileInfo *cfile = filp->private_data;
 	struct cifs_tcon *tcon = tlink_tcon(cfile->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
@@ -669,7 +673,7 @@ cifs_get_file_info(struct file *filp)
 	rc = server->ops->query_file_info(xid, tcon, &cfile->fid, &find_data);
 	switch (rc) {
 	case 0:
-		cifs_all_info_to_fattr(&fattr, &find_data, cifs_sb, false,
+		cifs_all_info_to_fattr(&fattr, &find_data, inode->i_sb, false,
 				       false);
 		break;
 	case -EREMOTE:
@@ -751,7 +755,7 @@ cifs_get_inode_info(struct inode **inode, const char *full_path,
 	}
 
 	if (!rc) {
-		cifs_all_info_to_fattr(&fattr, data, cifs_sb, adjust_tz,
+		cifs_all_info_to_fattr(&fattr, data, sb, adjust_tz,
 				       symlink);
 	} else if (rc == -EREMOTE) {
 		cifs_create_dfs_fattr(&fattr, sb);
@@ -1361,9 +1365,9 @@ out_reval:
 		cifs_inode = CIFS_I(inode);
 		cifs_inode->time = 0;	/* will force revalidate to get info
 					   when needed */
-		inode->i_ctime = current_fs_time(sb);
+		inode->i_ctime = current_time(inode);
 	}
-	dir->i_ctime = dir->i_mtime = current_fs_time(sb);
+	dir->i_ctime = dir->i_mtime = current_time(dir);
 	cifs_inode = CIFS_I(dir);
 	CIFS_I(dir)->time = 0;	/* force revalidate of dir as well */
 unlink_out:
@@ -1631,7 +1635,7 @@ int cifs_rmdir(struct inode *inode, struct dentry *direntry)
 	cifsInode->time = 0;
 
 	d_inode(direntry)->i_ctime = inode->i_ctime = inode->i_mtime =
-		current_fs_time(inode->i_sb);
+		current_time(inode);
 
 rmdir_exit:
 	kfree(full_path);
@@ -1804,7 +1808,7 @@ unlink_target:
 	CIFS_I(source_dir)->time = CIFS_I(target_dir)->time = 0;
 
 	source_dir->i_ctime = source_dir->i_mtime = target_dir->i_ctime =
-		target_dir->i_mtime = current_fs_time(source_dir->i_sb);
+		target_dir->i_mtime = current_time(source_dir);
 
 cifs_rename_exit:
 	kfree(info_buf_source);
@@ -1990,9 +1994,10 @@ int cifs_revalidate_dentry(struct dentry *dentry)
 	return cifs_revalidate_mapping(inode);
 }
 
-int cifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		 struct kstat *stat)
+int cifs_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	struct cifs_sb_info *cifs_sb = CIFS_SB(dentry->d_sb);
 	struct cifs_tcon *tcon = cifs_sb_master_tcon(cifs_sb);
 	struct inode *inode = d_inode(dentry);
diff --git a/fs/cifs/ioctl.c b/fs/cifs/ioctl.c
index 001528781b6b..54f32f9143a9 100644
--- a/fs/cifs/ioctl.c
+++ b/fs/cifs/ioctl.c
@@ -34,71 +34,14 @@
 #include "cifs_ioctl.h"
 #include <linux/btrfs.h>
 
-static int cifs_file_clone_range(unsigned int xid, struct file *src_file,
-			  struct file *dst_file)
-{
-	struct inode *src_inode = file_inode(src_file);
-	struct inode *target_inode = file_inode(dst_file);
-	struct cifsFileInfo *smb_file_src;
-	struct cifsFileInfo *smb_file_target;
-	struct cifs_tcon *src_tcon;
-	struct cifs_tcon *target_tcon;
-	int rc;
-
-	cifs_dbg(FYI, "ioctl clone range\n");
-
-	if (!src_file->private_data || !dst_file->private_data) {
-		rc = -EBADF;
-		cifs_dbg(VFS, "missing cifsFileInfo on copy range src file\n");
-		goto out;
-	}
-
-	rc = -EXDEV;
-	smb_file_target = dst_file->private_data;
-	smb_file_src = src_file->private_data;
-	src_tcon = tlink_tcon(smb_file_src->tlink);
-	target_tcon = tlink_tcon(smb_file_target->tlink);
-
-	if (src_tcon->ses != target_tcon->ses) {
-		cifs_dbg(VFS, "source and target of copy not on same server\n");
-		goto out;
-	}
-
-	/*
-	 * Note: cifs case is easier than btrfs since server responsible for
-	 * checks for proper open modes and file type and if it wants
-	 * server could even support copy of range where source = target
-	 */
-	lock_two_nondirectories(target_inode, src_inode);
-
-	cifs_dbg(FYI, "about to flush pages\n");
-	/* should we flush first and last page first */
-	truncate_inode_pages(&target_inode->i_data, 0);
-
-	if (target_tcon->ses->server->ops->clone_range)
-		rc = target_tcon->ses->server->ops->clone_range(xid,
-			smb_file_src, smb_file_target, 0, src_inode->i_size, 0);
-	else
-		rc = -EOPNOTSUPP;
-
-	/* force revalidate of size and timestamps of target file now
-	   that target is updated on the server */
-	CIFS_I(target_inode)->time = 0;
-	/* although unlocking in the reverse order from locking is not
-	   strictly necessary here it is a little cleaner to be consistent */
-	unlock_two_nondirectories(src_inode, target_inode);
-out:
-	return rc;
-}
-
-static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
+static long cifs_ioctl_copychunk(unsigned int xid, struct file *dst_file,
 			unsigned long srcfd)
 {
 	int rc;
 	struct fd src_file;
 	struct inode *src_inode;
 
-	cifs_dbg(FYI, "ioctl clone range\n");
+	cifs_dbg(FYI, "ioctl copychunk range\n");
 	/* the destination must be opened for writing */
 	if (!(dst_file->f_mode & FMODE_WRITE)) {
 		cifs_dbg(FYI, "file target not open for write\n");
@@ -129,8 +72,10 @@ static long cifs_ioctl_clone(unsigned int xid, struct file *dst_file,
 	if (S_ISDIR(src_inode->i_mode))
 		goto out_fput;
 
-	rc = cifs_file_clone_range(xid, src_file.file, dst_file);
-
+	rc = cifs_file_copychunk_range(xid, src_file.file, 0, dst_file, 0,
+					src_inode->i_size, 0);
+	if (rc > 0)
+		rc = 0;
 out_fput:
 	fdput(src_file);
 out_drop_write:
@@ -156,7 +101,6 @@ static long smb_mnt_get_fsinfo(unsigned int xid, struct cifs_tcon *tcon,
 	fsinf->fs_attributes = le32_to_cpu(tcon->fsAttrInfo.Attributes);
 	fsinf->max_path_component =
 		le32_to_cpu(tcon->fsAttrInfo.MaxPathNameComponentLength);
-#ifdef CONFIG_CIFS_SMB2
 	fsinf->vol_serial_number = tcon->vol_serial_number;
 	fsinf->vol_create_time = le64_to_cpu(tcon->vol_create_time);
 	fsinf->share_flags = tcon->share_flags;
@@ -165,7 +109,6 @@ static long smb_mnt_get_fsinfo(unsigned int xid, struct cifs_tcon *tcon,
 	fsinf->optimal_sector_size = tcon->perf_sector_size;
 	fsinf->max_bytes_chunk = tcon->max_bytes_chunk;
 	fsinf->maximal_access = tcon->maximal_access;
-#endif /* SMB2 */
 	fsinf->cifs_posix_caps = le64_to_cpu(tcon->fsUnixInfo.Capability);
 
 	if (copy_to_user(arg, fsinf, sizeof(struct smb_mnt_fs_info)))
@@ -251,7 +194,7 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 			}
 			break;
 		case CIFS_IOC_COPYCHUNK_FILE:
-			rc = cifs_ioctl_clone(xid, filep, arg);
+			rc = cifs_ioctl_copychunk(xid, filep, arg);
 			break;
 		case CIFS_IOC_SET_INTEGRITY:
 			if (pSMBFile == NULL)
@@ -264,10 +207,14 @@ long cifs_ioctl(struct file *filep, unsigned int command, unsigned long arg)
 				rc = -EOPNOTSUPP;
 			break;
 		case CIFS_IOC_GET_MNT_INFO:
+			if (pSMBFile == NULL)
+				break;
 			tcon = tlink_tcon(pSMBFile->tlink);
 			rc = smb_mnt_get_fsinfo(xid, tcon, (void __user *)arg);
 			break;
 		case CIFS_ENUMERATE_SNAPSHOTS:
+			if (pSMBFile == NULL)
+				break;
 			if (arg == 0) {
 				rc = -EINVAL;
 				goto cifs_ioc_exit;
diff --git a/fs/cifs/link.c b/fs/cifs/link.c
index c4d996f78e1c..60b5a11ee11b 100644
--- a/fs/cifs/link.c
+++ b/fs/cifs/link.c
@@ -29,9 +29,7 @@
 #include "cifs_debug.h"
 #include "cifs_fs_sb.h"
 #include "cifs_unicode.h"
-#ifdef CONFIG_CIFS_SMB2
 #include "smb2proto.h"
-#endif
 
 /*
  * M-F Symlink Functions - Begin
@@ -402,7 +400,6 @@ cifs_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 /*
  * SMB 2.1/SMB3 Protocol specific functions
  */
-#ifdef CONFIG_CIFS_SMB2
 int
 smb3_query_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 		      struct cifs_sb_info *cifs_sb, const unsigned char *path,
@@ -525,7 +522,6 @@ smb3_create_mf_symlink(unsigned int xid, struct cifs_tcon *tcon,
 	kfree(utf16_path);
 	return rc;
 }
-#endif /* CONFIG_CIFS_SMB2 */
 
 /*
  * M-F Symlink Functions - End
diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c
index c6729156f9a0..eea93ac15ef0 100644
--- a/fs/cifs/misc.c
+++ b/fs/cifs/misc.c
@@ -22,6 +22,7 @@
 #include <linux/slab.h>
 #include <linux/ctype.h>
 #include <linux/mempool.h>
+#include <linux/vmalloc.h>
 #include "cifspdu.h"
 #include "cifsglob.h"
 #include "cifsproto.h"
@@ -29,9 +30,7 @@
 #include "smberr.h"
 #include "nterr.h"
 #include "cifs_unicode.h"
-#ifdef CONFIG_CIFS_SMB2
 #include "smb2pdu.h"
-#endif
 
 extern mempool_t *cifs_sm_req_poolp;
 extern mempool_t *cifs_req_poolp;
@@ -148,15 +147,12 @@ struct smb_hdr *
 cifs_buf_get(void)
 {
 	struct smb_hdr *ret_buf = NULL;
-	size_t buf_size = sizeof(struct smb_hdr);
-
-#ifdef CONFIG_CIFS_SMB2
 	/*
 	 * SMB2 header is bigger than CIFS one - no problems to clean some
 	 * more bytes for CIFS.
 	 */
-	buf_size = sizeof(struct smb2_hdr);
-#endif
+	size_t buf_size = sizeof(struct smb2_hdr);
+
 	/*
 	 * We could use negotiated size instead of max_msgsize -
 	 * but it may be more efficient to always alloc same size
@@ -167,13 +163,11 @@ cifs_buf_get(void)
 
 	/* clear the first few header bytes */
 	/* for most paths, more is cleared in header_assemble */
-	if (ret_buf) {
-		memset(ret_buf, 0, buf_size + 3);
-		atomic_inc(&bufAllocCount);
+	memset(ret_buf, 0, buf_size + 3);
+	atomic_inc(&bufAllocCount);
 #ifdef CONFIG_CIFS_STATS2
-		atomic_inc(&totBufAllocCount);
+	atomic_inc(&totBufAllocCount);
 #endif /* CONFIG_CIFS_STATS2 */
-	}
 
 	return ret_buf;
 }
@@ -201,15 +195,13 @@ cifs_small_buf_get(void)
    albeit slightly larger than necessary and maxbuffersize
    defaults to this and can not be bigger */
 	ret_buf = mempool_alloc(cifs_sm_req_poolp, GFP_NOFS);
-	if (ret_buf) {
 	/* No need to clear memory here, cleared in header assemble */
 	/*	memset(ret_buf, 0, sizeof(struct smb_hdr) + 27);*/
-		atomic_inc(&smBufAllocCount);
+	atomic_inc(&smBufAllocCount);
 #ifdef CONFIG_CIFS_STATS2
-		atomic_inc(&totSmBufAllocCount);
+	atomic_inc(&totSmBufAllocCount);
 #endif /* CONFIG_CIFS_STATS2 */
 
-	}
 	return ret_buf;
 }
 
@@ -492,7 +484,7 @@ is_valid_oplock_break(char *buffer, struct TCP_Server_Info *srv)
 					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
 					   &pCifsInode->flags);
 
-				queue_work(cifsiod_wq,
+				queue_work(cifsoplockd_wq,
 					   &netfile->oplock_break);
 				netfile->oplock_break_cancelled = false;
 
@@ -623,9 +615,7 @@ void
 cifs_add_pending_open_locked(struct cifs_fid *fid, struct tcon_link *tlink,
 			     struct cifs_pending_open *open)
 {
-#ifdef CONFIG_CIFS_SMB2
 	memcpy(open->lease_key, fid->lease_key, SMB2_LEASE_KEY_SIZE);
-#endif
 	open->oplock = CIFS_OPLOCK_NO_CHANGE;
 	open->tlink = tlink;
 	fid->pending_open = open;
@@ -640,3 +630,227 @@ cifs_add_pending_open(struct cifs_fid *fid, struct tcon_link *tlink,
 	cifs_add_pending_open_locked(fid, tlink, open);
 	spin_unlock(&tlink_tcon(open->tlink)->open_file_lock);
 }
+
+/* parses DFS refferal V3 structure
+ * caller is responsible for freeing target_nodes
+ * returns:
+ * - on success - 0
+ * - on failure - errno
+ */
+int
+parse_dfs_referrals(struct get_dfs_referral_rsp *rsp, u32 rsp_size,
+		    unsigned int *num_of_nodes,
+		    struct dfs_info3_param **target_nodes,
+		    const struct nls_table *nls_codepage, int remap,
+		    const char *searchName, bool is_unicode)
+{
+	int i, rc = 0;
+	char *data_end;
+	struct dfs_referral_level_3 *ref;
+
+	*num_of_nodes = le16_to_cpu(rsp->NumberOfReferrals);
+
+	if (*num_of_nodes < 1) {
+		cifs_dbg(VFS, "num_referrals: must be at least > 0, but we get num_referrals = %d\n",
+			 *num_of_nodes);
+		rc = -EINVAL;
+		goto parse_DFS_referrals_exit;
+	}
+
+	ref = (struct dfs_referral_level_3 *) &(rsp->referrals);
+	if (ref->VersionNumber != cpu_to_le16(3)) {
+		cifs_dbg(VFS, "Referrals of V%d version are not supported, should be V3\n",
+			 le16_to_cpu(ref->VersionNumber));
+		rc = -EINVAL;
+		goto parse_DFS_referrals_exit;
+	}
+
+	/* get the upper boundary of the resp buffer */
+	data_end = (char *)rsp + rsp_size;
+
+	cifs_dbg(FYI, "num_referrals: %d dfs flags: 0x%x ...\n",
+		 *num_of_nodes, le32_to_cpu(rsp->DFSFlags));
+
+	*target_nodes = kcalloc(*num_of_nodes, sizeof(struct dfs_info3_param),
+				GFP_KERNEL);
+	if (*target_nodes == NULL) {
+		rc = -ENOMEM;
+		goto parse_DFS_referrals_exit;
+	}
+
+	/* collect necessary data from referrals */
+	for (i = 0; i < *num_of_nodes; i++) {
+		char *temp;
+		int max_len;
+		struct dfs_info3_param *node = (*target_nodes)+i;
+
+		node->flags = le32_to_cpu(rsp->DFSFlags);
+		if (is_unicode) {
+			__le16 *tmp = kmalloc(strlen(searchName)*2 + 2,
+						GFP_KERNEL);
+			if (tmp == NULL) {
+				rc = -ENOMEM;
+				goto parse_DFS_referrals_exit;
+			}
+			cifsConvertToUTF16((__le16 *) tmp, searchName,
+					   PATH_MAX, nls_codepage, remap);
+			node->path_consumed = cifs_utf16_bytes(tmp,
+					le16_to_cpu(rsp->PathConsumed),
+					nls_codepage);
+			kfree(tmp);
+		} else
+			node->path_consumed = le16_to_cpu(rsp->PathConsumed);
+
+		node->server_type = le16_to_cpu(ref->ServerType);
+		node->ref_flag = le16_to_cpu(ref->ReferralEntryFlags);
+
+		/* copy DfsPath */
+		temp = (char *)ref + le16_to_cpu(ref->DfsPathOffset);
+		max_len = data_end - temp;
+		node->path_name = cifs_strndup_from_utf16(temp, max_len,
+						is_unicode, nls_codepage);
+		if (!node->path_name) {
+			rc = -ENOMEM;
+			goto parse_DFS_referrals_exit;
+		}
+
+		/* copy link target UNC */
+		temp = (char *)ref + le16_to_cpu(ref->NetworkAddressOffset);
+		max_len = data_end - temp;
+		node->node_name = cifs_strndup_from_utf16(temp, max_len,
+						is_unicode, nls_codepage);
+		if (!node->node_name) {
+			rc = -ENOMEM;
+			goto parse_DFS_referrals_exit;
+		}
+
+		ref++;
+	}
+
+parse_DFS_referrals_exit:
+	if (rc) {
+		free_dfs_info_array(*target_nodes, *num_of_nodes);
+		*target_nodes = NULL;
+		*num_of_nodes = 0;
+	}
+	return rc;
+}
+
+struct cifs_aio_ctx *
+cifs_aio_ctx_alloc(void)
+{
+	struct cifs_aio_ctx *ctx;
+
+	ctx = kzalloc(sizeof(struct cifs_aio_ctx), GFP_KERNEL);
+	if (!ctx)
+		return NULL;
+
+	INIT_LIST_HEAD(&ctx->list);
+	mutex_init(&ctx->aio_mutex);
+	init_completion(&ctx->done);
+	kref_init(&ctx->refcount);
+	return ctx;
+}
+
+void
+cifs_aio_ctx_release(struct kref *refcount)
+{
+	struct cifs_aio_ctx *ctx = container_of(refcount,
+					struct cifs_aio_ctx, refcount);
+
+	cifsFileInfo_put(ctx->cfile);
+	kvfree(ctx->bv);
+	kfree(ctx);
+}
+
+#define CIFS_AIO_KMALLOC_LIMIT (1024 * 1024)
+
+int
+setup_aio_ctx_iter(struct cifs_aio_ctx *ctx, struct iov_iter *iter, int rw)
+{
+	ssize_t rc;
+	unsigned int cur_npages;
+	unsigned int npages = 0;
+	unsigned int i;
+	size_t len;
+	size_t count = iov_iter_count(iter);
+	unsigned int saved_len;
+	size_t start;
+	unsigned int max_pages = iov_iter_npages(iter, INT_MAX);
+	struct page **pages = NULL;
+	struct bio_vec *bv = NULL;
+
+	if (iter->type & ITER_KVEC) {
+		memcpy(&ctx->iter, iter, sizeof(struct iov_iter));
+		ctx->len = count;
+		iov_iter_advance(iter, count);
+		return 0;
+	}
+
+	if (max_pages * sizeof(struct bio_vec) <= CIFS_AIO_KMALLOC_LIMIT)
+		bv = kmalloc_array(max_pages, sizeof(struct bio_vec),
+				   GFP_KERNEL);
+
+	if (!bv) {
+		bv = vmalloc(max_pages * sizeof(struct bio_vec));
+		if (!bv)
+			return -ENOMEM;
+	}
+
+	if (max_pages * sizeof(struct page *) <= CIFS_AIO_KMALLOC_LIMIT)
+		pages = kmalloc_array(max_pages, sizeof(struct page *),
+				      GFP_KERNEL);
+
+	if (!pages) {
+		pages = vmalloc(max_pages * sizeof(struct page *));
+		if (!pages) {
+			kvfree(bv);
+			return -ENOMEM;
+		}
+	}
+
+	saved_len = count;
+
+	while (count && npages < max_pages) {
+		rc = iov_iter_get_pages(iter, pages, count, max_pages, &start);
+		if (rc < 0) {
+			cifs_dbg(VFS, "couldn't get user pages (rc=%zd)\n", rc);
+			break;
+		}
+
+		if (rc > count) {
+			cifs_dbg(VFS, "get pages rc=%zd more than %zu\n", rc,
+				 count);
+			break;
+		}
+
+		iov_iter_advance(iter, rc);
+		count -= rc;
+		rc += start;
+		cur_npages = DIV_ROUND_UP(rc, PAGE_SIZE);
+
+		if (npages + cur_npages > max_pages) {
+			cifs_dbg(VFS, "out of vec array capacity (%u vs %u)\n",
+				 npages + cur_npages, max_pages);
+			break;
+		}
+
+		for (i = 0; i < cur_npages; i++) {
+			len = rc > PAGE_SIZE ? PAGE_SIZE : rc;
+			bv[npages + i].bv_page = pages[i];
+			bv[npages + i].bv_offset = start;
+			bv[npages + i].bv_len = len - start;
+			rc -= len;
+			start = 0;
+		}
+
+		npages += cur_npages;
+	}
+
+	kvfree(pages);
+	ctx->bv = bv;
+	ctx->len = saved_len - count;
+	ctx->npages = npages;
+	iov_iter_bvec(&ctx->iter, ITER_BVEC | rw, ctx->bv, npages, ctx->len);
+	return 0;
+}
diff --git a/fs/cifs/netmisc.c b/fs/cifs/netmisc.c
index abae6dd2c6b9..cc88f4f0325e 100644
--- a/fs/cifs/netmisc.c
+++ b/fs/cifs/netmisc.c
@@ -980,10 +980,10 @@ struct timespec cnvrtDosUnixTm(__le16 le_date, __le16 le_time, int offset)
 		cifs_dbg(VFS, "illegal hours %d\n", st->Hours);
 	days = sd->Day;
 	month = sd->Month;
-	if ((days > 31) || (month > 12)) {
+	if (days < 1 || days > 31 || month < 1 || month > 12) {
 		cifs_dbg(VFS, "illegal date, month %d day: %d\n", month, days);
-		if (month > 12)
-			month = 12;
+		days = clamp(days, 1, 31);
+		month = clamp(month, 1, 12);
 	}
 	month -= 1;
 	days += total_days_of_prev_months[month];
diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c
index 538d9b55699a..8b0502cd39af 100644
--- a/fs/cifs/sess.c
+++ b/fs/cifs/sess.c
@@ -344,13 +344,12 @@ void build_ntlmssp_negotiate_blob(unsigned char *pbuffer,
 	/* BB is NTLMV2 session security format easier to use here? */
 	flags = NTLMSSP_NEGOTIATE_56 |	NTLMSSP_REQUEST_TARGET |
 		NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
-		NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC;
-	if (ses->server->sign) {
+		NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC |
+		NTLMSSP_NEGOTIATE_SEAL;
+	if (ses->server->sign)
 		flags |= NTLMSSP_NEGOTIATE_SIGN;
-		if (!ses->server->session_estab ||
-				ses->ntlmssp->sesskey_per_smbsess)
-			flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
-	}
+	if (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess)
+		flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
 
 	sec_blob->NegotiateFlags = cpu_to_le32(flags);
 
@@ -407,13 +406,12 @@ int build_ntlmssp_auth_blob(unsigned char **pbuffer,
 	flags = NTLMSSP_NEGOTIATE_56 |
 		NTLMSSP_REQUEST_TARGET | NTLMSSP_NEGOTIATE_TARGET_INFO |
 		NTLMSSP_NEGOTIATE_128 | NTLMSSP_NEGOTIATE_UNICODE |
-		NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC;
-	if (ses->server->sign) {
+		NTLMSSP_NEGOTIATE_NTLM | NTLMSSP_NEGOTIATE_EXTENDED_SEC |
+		NTLMSSP_NEGOTIATE_SEAL;
+	if (ses->server->sign)
 		flags |= NTLMSSP_NEGOTIATE_SIGN;
-		if (!ses->server->session_estab ||
-				ses->ntlmssp->sesskey_per_smbsess)
-			flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
-	}
+	if (!ses->server->session_estab || ses->ntlmssp->sesskey_per_smbsess)
+		flags |= NTLMSSP_NEGOTIATE_KEY_XCH;
 
 	tmp = *pbuffer + sizeof(AUTHENTICATE_MESSAGE);
 	sec_blob->NegotiateFlags = cpu_to_le32(flags);
@@ -500,7 +498,7 @@ setup_ntlmv2_ret:
 }
 
 enum securityEnum
-select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
+cifs_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
 {
 	switch (server->negflavor) {
 	case CIFS_NEGFLAVOR_EXTENDED:
@@ -652,6 +650,7 @@ sess_sendreceive(struct sess_data *sess_data)
 	int rc;
 	struct smb_hdr *smb_buf = (struct smb_hdr *) sess_data->iov[0].iov_base;
 	__u16 count;
+	struct kvec rsp_iov = { NULL, 0 };
 
 	count = sess_data->iov[1].iov_len + sess_data->iov[2].iov_len;
 	smb_buf->smb_buf_length =
@@ -661,7 +660,9 @@ sess_sendreceive(struct sess_data *sess_data)
 	rc = SendReceive2(sess_data->xid, sess_data->ses,
 			  sess_data->iov, 3 /* num_iovecs */,
 			  &sess_data->buf0_type,
-			  CIFS_LOG_ERROR);
+			  CIFS_LOG_ERROR, &rsp_iov);
+	cifs_small_buf_release(sess_data->iov[0].iov_base);
+	memcpy(&sess_data->iov[0], &rsp_iov, sizeof(struct kvec));
 
 	return rc;
 }
@@ -1390,7 +1391,7 @@ static int select_sec(struct cifs_ses *ses, struct sess_data *sess_data)
 {
 	int type;
 
-	type = select_sectype(ses->server, ses->sectype);
+	type = cifs_select_sectype(ses->server, ses->sectype);
 	cifs_dbg(FYI, "sess setup type %d\n", type);
 	if (type == Unspecified) {
 		cifs_dbg(VFS,
diff --git a/fs/cifs/smb1ops.c b/fs/cifs/smb1ops.c
index fc537c29044e..a723df3e0197 100644
--- a/fs/cifs/smb1ops.c
+++ b/fs/cifs/smb1ops.c
@@ -36,11 +36,11 @@
  * SMB_COM_NT_CANCEL request and then sends it.
  */
 static int
-send_nt_cancel(struct TCP_Server_Info *server, void *buf,
+send_nt_cancel(struct TCP_Server_Info *server, struct smb_rqst *rqst,
 	       struct mid_q_entry *mid)
 {
 	int rc = 0;
-	struct smb_hdr *in_buf = (struct smb_hdr *)buf;
+	struct smb_hdr *in_buf = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
 
 	/* -4 for RFC1001 length and +2 for BCC field */
 	in_buf->smb_buf_length = cpu_to_be32(sizeof(struct smb_hdr) - 4  + 2);
@@ -849,8 +849,13 @@ cifs_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 		     struct cifs_fid *fid, __u16 search_flags,
 		     struct cifs_search_info *srch_inf)
 {
-	return CIFSFindFirst(xid, tcon, path, cifs_sb,
-			     &fid->netfid, search_flags, srch_inf, true);
+	int rc;
+
+	rc = CIFSFindFirst(xid, tcon, path, cifs_sb,
+			   &fid->netfid, search_flags, srch_inf, true);
+	if (rc)
+		cifs_dbg(FYI, "find first failed=%d\n", rc);
+	return rc;
 }
 
 static int
@@ -1015,6 +1020,15 @@ cifs_dir_needs_close(struct cifsFileInfo *cfile)
 	return !cfile->srch_inf.endOfSearch && !cfile->invalidHandle;
 }
 
+static bool
+cifs_can_echo(struct TCP_Server_Info *server)
+{
+	if (server->tcpStatus == CifsGood)
+		return true;
+
+	return false;
+}
+
 struct smb_version_operations smb1_operations = {
 	.send_cancel = send_nt_cancel,
 	.compare_fids = cifs_compare_fids,
@@ -1049,6 +1063,7 @@ struct smb_version_operations smb1_operations = {
 	.get_dfs_refer = CIFSGetDFSRefer,
 	.qfs_tcon = cifs_qfs_tcon,
 	.is_path_accessible = cifs_is_path_accessible,
+	.can_echo = cifs_can_echo,
 	.query_path_info = cifs_query_path_info,
 	.query_file_info = cifs_query_file_info,
 	.get_srv_inum = cifs_get_srv_inum,
@@ -1087,6 +1102,7 @@ struct smb_version_operations smb1_operations = {
 	.is_read_op = cifs_is_read_op,
 	.wp_retry_size = cifs_wp_retry_size,
 	.dir_needs_close = cifs_dir_needs_close,
+	.select_sectype = cifs_select_sectype,
 #ifdef CONFIG_CIFS_XATTR
 	.query_all_EAs = CIFSSMBQAllEAs,
 	.set_EA = CIFSSMBSetEA,
diff --git a/fs/cifs/smb2file.c b/fs/cifs/smb2file.c
index b2aff0c6f22c..b4b1f0305f29 100644
--- a/fs/cifs/smb2file.c
+++ b/fs/cifs/smb2file.c
@@ -73,7 +73,8 @@ smb2_open_file(const unsigned int xid, struct cifs_open_parms *oparms,
 		nr_ioctl_req.Timeout = 0; /* use server default (120 seconds) */
 		nr_ioctl_req.Reserved = 0;
 		rc = SMB2_ioctl(xid, oparms->tcon, fid->persistent_fid,
-			fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY, true,
+			fid->volatile_fid, FSCTL_LMR_REQUEST_RESILIENCY,
+			true /* is_fsctl */, false /* use_ipc */,
 			(char *)&nr_ioctl_req, sizeof(nr_ioctl_req),
 			NULL, NULL /* no return info */);
 		if (rc == -EOPNOTSUPP) {
diff --git a/fs/cifs/smb2glob.h b/fs/cifs/smb2glob.h
index 0ffa18094335..401a5d856636 100644
--- a/fs/cifs/smb2glob.h
+++ b/fs/cifs/smb2glob.h
@@ -61,4 +61,9 @@
 /* Maximum buffer size value we can send with 1 credit */
 #define SMB2_MAX_BUFFER_SIZE 65536
 
+static inline struct smb2_sync_hdr *get_sync_hdr(void *buf)
+{
+	return &(((struct smb2_hdr *)buf)->sync_hdr);
+}
+
 #endif	/* _SMB2_GLOB_H */
diff --git a/fs/cifs/smb2maperror.c b/fs/cifs/smb2maperror.c
index 8257a5a97cc0..7ca9808a0daa 100644
--- a/fs/cifs/smb2maperror.c
+++ b/fs/cifs/smb2maperror.c
@@ -26,6 +26,7 @@
 #include "smb2pdu.h"
 #include "smb2proto.h"
 #include "smb2status.h"
+#include "smb2glob.h"
 
 struct status_to_posix_error {
 	__le32 smb2_status;
@@ -2449,10 +2450,10 @@ smb2_print_status(__le32 status)
 int
 map_smb2_to_linux_error(char *buf, bool log_err)
 {
-	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
 	unsigned int i;
 	int rc = -EIO;
-	__le32 smb2err = hdr->Status;
+	__le32 smb2err = shdr->Status;
 
 	if (smb2err == 0)
 		return 0;
@@ -2474,8 +2475,8 @@ map_smb2_to_linux_error(char *buf, bool log_err)
 
 	/* on error mapping not found  - return EIO */
 
-	cifs_dbg(FYI, "Mapping SMB2 status code %d to POSIX err %d\n",
-		 smb2err, rc);
+	cifs_dbg(FYI, "Mapping SMB2 status code 0x%08x to POSIX err %d\n",
+		 __le32_to_cpu(smb2err), rc);
 
 	return rc;
 }
diff --git a/fs/cifs/smb2misc.c b/fs/cifs/smb2misc.c
index 3d383489b9cf..7b08a1446a7f 100644
--- a/fs/cifs/smb2misc.c
+++ b/fs/cifs/smb2misc.c
@@ -28,31 +28,32 @@
 #include "cifs_debug.h"
 #include "cifs_unicode.h"
 #include "smb2status.h"
+#include "smb2glob.h"
 
 static int
-check_smb2_hdr(struct smb2_hdr *hdr, __u64 mid)
+check_smb2_hdr(struct smb2_sync_hdr *shdr, __u64 mid)
 {
-	__u64 wire_mid = le64_to_cpu(hdr->MessageId);
+	__u64 wire_mid = le64_to_cpu(shdr->MessageId);
 
 	/*
 	 * Make sure that this really is an SMB, that it is a response,
 	 * and that the message ids match.
 	 */
-	if ((hdr->ProtocolId == SMB2_PROTO_NUMBER) &&
+	if ((shdr->ProtocolId == SMB2_PROTO_NUMBER) &&
 	    (mid == wire_mid)) {
-		if (hdr->Flags & SMB2_FLAGS_SERVER_TO_REDIR)
+		if (shdr->Flags & SMB2_FLAGS_SERVER_TO_REDIR)
 			return 0;
 		else {
 			/* only one valid case where server sends us request */
-			if (hdr->Command == SMB2_OPLOCK_BREAK)
+			if (shdr->Command == SMB2_OPLOCK_BREAK)
 				return 0;
 			else
 				cifs_dbg(VFS, "Received Request not response\n");
 		}
 	} else { /* bad signature or mid */
-		if (hdr->ProtocolId != SMB2_PROTO_NUMBER)
+		if (shdr->ProtocolId != SMB2_PROTO_NUMBER)
 			cifs_dbg(VFS, "Bad protocol string signature header %x\n",
-				 le32_to_cpu(hdr->ProtocolId));
+				 le32_to_cpu(shdr->ProtocolId));
 		if (mid != wire_mid)
 			cifs_dbg(VFS, "Mids do not match: %llu and %llu\n",
 				 mid, wire_mid);
@@ -95,8 +96,9 @@ static const __le16 smb2_rsp_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
 int
 smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 {
-	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
-	struct smb2_pdu *pdu = (struct smb2_pdu *)hdr;
+	struct smb2_pdu *pdu = (struct smb2_pdu *)buf;
+	struct smb2_hdr *hdr = &pdu->hdr;
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
 	__u64 mid;
 	__u32 len = get_rfc1002_length(buf);
 	__u32 clc_len;  /* calculated length */
@@ -111,7 +113,7 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 	 * ie Validate the wct via smb2_struct_sizes table above
 	 */
 
-	if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
+	if (shdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
 		struct smb2_transform_hdr *thdr =
 			(struct smb2_transform_hdr *)buf;
 		struct cifs_ses *ses = NULL;
@@ -133,10 +135,10 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 		}
 	}
 
-
-	mid = le64_to_cpu(hdr->MessageId);
+	mid = le64_to_cpu(shdr->MessageId);
 	if (length < sizeof(struct smb2_pdu)) {
-		if ((length >= sizeof(struct smb2_hdr)) && (hdr->Status != 0)) {
+		if ((length >= sizeof(struct smb2_hdr))
+		    && (shdr->Status != 0)) {
 			pdu->StructureSize2 = 0;
 			/*
 			 * As with SMB/CIFS, on some error cases servers may
@@ -154,29 +156,30 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 		return 1;
 	}
 
-	if (check_smb2_hdr(hdr, mid))
+	if (check_smb2_hdr(shdr, mid))
 		return 1;
 
-	if (hdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) {
+	if (shdr->StructureSize != SMB2_HEADER_STRUCTURE_SIZE) {
 		cifs_dbg(VFS, "Illegal structure size %u\n",
-			 le16_to_cpu(hdr->StructureSize));
+			 le16_to_cpu(shdr->StructureSize));
 		return 1;
 	}
 
-	command = le16_to_cpu(hdr->Command);
+	command = le16_to_cpu(shdr->Command);
 	if (command >= NUMBER_OF_SMB2_COMMANDS) {
 		cifs_dbg(VFS, "Illegal SMB2 command %d\n", command);
 		return 1;
 	}
 
 	if (smb2_rsp_struct_sizes[command] != pdu->StructureSize2) {
-		if (command != SMB2_OPLOCK_BREAK_HE && (hdr->Status == 0 ||
+		if (command != SMB2_OPLOCK_BREAK_HE && (shdr->Status == 0 ||
 		    pdu->StructureSize2 != SMB2_ERROR_STRUCTURE_SIZE2)) {
 			/* error packets have 9 byte structure size */
 			cifs_dbg(VFS, "Illegal response size %u for command %d\n",
 				 le16_to_cpu(pdu->StructureSize2), command);
 			return 1;
-		} else if (command == SMB2_OPLOCK_BREAK_HE && (hdr->Status == 0)
+		} else if (command == SMB2_OPLOCK_BREAK_HE
+			   && (shdr->Status == 0)
 			   && (le16_to_cpu(pdu->StructureSize2) != 44)
 			   && (le16_to_cpu(pdu->StructureSize2) != 36)) {
 			/* special case for SMB2.1 lease break message */
@@ -199,7 +202,7 @@ smb2_check_message(char *buf, unsigned int length, struct TCP_Server_Info *srvr)
 			 clc_len, 4 + len, mid);
 		/* create failed on symlink */
 		if (command == SMB2_CREATE_HE &&
-		    hdr->Status == STATUS_STOPPED_ON_SYMLINK)
+		    shdr->Status == STATUS_STOPPED_ON_SYMLINK)
 			return 0;
 		/* Windows 7 server returns 24 bytes more */
 		if (clc_len + 20 == len && command == SMB2_OPLOCK_BREAK_HE)
@@ -261,11 +264,12 @@ static const bool has_smb2_data_area[NUMBER_OF_SMB2_COMMANDS] = {
 char *
 smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
 {
+	struct smb2_sync_hdr *shdr = get_sync_hdr(hdr);
 	*off = 0;
 	*len = 0;
 
 	/* error responses do not have data area */
-	if (hdr->Status && hdr->Status != STATUS_MORE_PROCESSING_REQUIRED &&
+	if (shdr->Status && shdr->Status != STATUS_MORE_PROCESSING_REQUIRED &&
 	    (((struct smb2_err_rsp *)hdr)->StructureSize) ==
 						SMB2_ERROR_STRUCTURE_SIZE2)
 		return NULL;
@@ -275,7 +279,7 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
 	 * of the data buffer offset and data buffer length for the particular
 	 * command.
 	 */
-	switch (hdr->Command) {
+	switch (shdr->Command) {
 	case SMB2_NEGOTIATE:
 		*off = le16_to_cpu(
 		    ((struct smb2_negotiate_rsp *)hdr)->SecurityBufferOffset);
@@ -346,7 +350,7 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
 
 	/* return pointer to beginning of data area, ie offset from SMB start */
 	if ((*off != 0) && (*len != 0))
-		return (char *)(&hdr->ProtocolId) + *off;
+		return (char *)shdr + *off;
 	else
 		return NULL;
 }
@@ -358,12 +362,13 @@ smb2_get_data_area_len(int *off, int *len, struct smb2_hdr *hdr)
 unsigned int
 smb2_calc_size(void *buf)
 {
-	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
-	struct smb2_pdu *pdu = (struct smb2_pdu *)hdr;
+	struct smb2_pdu *pdu = (struct smb2_pdu *)buf;
+	struct smb2_hdr *hdr = &pdu->hdr;
+	struct smb2_sync_hdr *shdr = get_sync_hdr(hdr);
 	int offset; /* the offset from the beginning of SMB to data area */
 	int data_length; /* the length of the variable length data area */
 	/* Structure Size has already been checked to make sure it is 64 */
-	int len = 4 + le16_to_cpu(pdu->hdr.StructureSize);
+	int len = 4 + le16_to_cpu(shdr->StructureSize);
 
 	/*
 	 * StructureSize2, ie length of fixed parameter area has already
@@ -371,7 +376,7 @@ smb2_calc_size(void *buf)
 	 */
 	len += le16_to_cpu(pdu->StructureSize2);
 
-	if (has_smb2_data_area[le16_to_cpu(hdr->Command)] == false)
+	if (has_smb2_data_area[le16_to_cpu(shdr->Command)] == false)
 		goto calc_size_exit;
 
 	smb2_get_data_area_len(&offset, &data_length, hdr);
@@ -494,7 +499,7 @@ smb2_tcon_has_lease(struct cifs_tcon *tcon, struct smb2_lease_break *rsp,
 		else
 			cfile->oplock_break_cancelled = true;
 
-		queue_work(cifsiod_wq, &cfile->oplock_break);
+		queue_work(cifsoplockd_wq, &cfile->oplock_break);
 		kfree(lw);
 		return true;
 	}
@@ -582,7 +587,7 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 
 	cifs_dbg(FYI, "Checking for oplock break\n");
 
-	if (rsp->hdr.Command != SMB2_OPLOCK_BREAK)
+	if (rsp->hdr.sync_hdr.Command != SMB2_OPLOCK_BREAK)
 		return false;
 
 	if (rsp->StructureSize !=
@@ -638,7 +643,8 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 					   CIFS_INODE_DOWNGRADE_OPLOCK_TO_L2,
 					   &cinode->flags);
 				spin_unlock(&cfile->file_info_lock);
-				queue_work(cifsiod_wq, &cfile->oplock_break);
+				queue_work(cifsoplockd_wq,
+					   &cfile->oplock_break);
 
 				spin_unlock(&tcon->open_file_lock);
 				spin_unlock(&cifs_tcp_ses_lock);
@@ -654,3 +660,49 @@ smb2_is_valid_oplock_break(char *buffer, struct TCP_Server_Info *server)
 	cifs_dbg(FYI, "Can not process oplock break for non-existent connection\n");
 	return false;
 }
+
+void
+smb2_cancelled_close_fid(struct work_struct *work)
+{
+	struct close_cancelled_open *cancelled = container_of(work,
+					struct close_cancelled_open, work);
+
+	cifs_dbg(VFS, "Close unmatched open\n");
+
+	SMB2_close(0, cancelled->tcon, cancelled->fid.persistent_fid,
+		   cancelled->fid.volatile_fid);
+	cifs_put_tcon(cancelled->tcon);
+	kfree(cancelled);
+}
+
+int
+smb2_handle_cancelled_mid(char *buffer, struct TCP_Server_Info *server)
+{
+	struct smb2_sync_hdr *sync_hdr = get_sync_hdr(buffer);
+	struct smb2_create_rsp *rsp = (struct smb2_create_rsp *)buffer;
+	struct cifs_tcon *tcon;
+	struct close_cancelled_open *cancelled;
+
+	if (sync_hdr->Command != SMB2_CREATE ||
+	    sync_hdr->Status != STATUS_SUCCESS)
+		return 0;
+
+	cancelled = kzalloc(sizeof(*cancelled), GFP_KERNEL);
+	if (!cancelled)
+		return -ENOMEM;
+
+	tcon = smb2_find_smb_tcon(server, sync_hdr->SessionId,
+				  sync_hdr->TreeId);
+	if (!tcon) {
+		kfree(cancelled);
+		return -ENOENT;
+	}
+
+	cancelled->fid.persistent_fid = rsp->PersistentFileId;
+	cancelled->fid.volatile_fid = rsp->VolatileFileId;
+	cancelled->tcon = tcon;
+	INIT_WORK(&cancelled->work, smb2_cancelled_close_fid);
+	queue_work(cifsiod_wq, &cancelled->work);
+
+	return 0;
+}
diff --git a/fs/cifs/smb2ops.c b/fs/cifs/smb2ops.c
index 5d456ebb3813..cfacf2c97e94 100644
--- a/fs/cifs/smb2ops.c
+++ b/fs/cifs/smb2ops.c
@@ -20,6 +20,9 @@
 #include <linux/pagemap.h>
 #include <linux/vfs.h>
 #include <linux/falloc.h>
+#include <linux/scatterlist.h>
+#include <linux/uuid.h>
+#include <crypto/aead.h>
 #include "cifsglob.h"
 #include "smb2pdu.h"
 #include "smb2proto.h"
@@ -119,7 +122,9 @@ smb2_get_credits_field(struct TCP_Server_Info *server, const int optype)
 static unsigned int
 smb2_get_credits(struct mid_q_entry *mid)
 {
-	return le16_to_cpu(((struct smb2_hdr *)mid->resp_buf)->CreditRequest);
+	struct smb2_sync_hdr *shdr = get_sync_hdr(mid->resp_buf);
+
+	return le16_to_cpu(shdr->CreditRequest);
 }
 
 static int
@@ -184,10 +189,10 @@ static struct mid_q_entry *
 smb2_find_mid(struct TCP_Server_Info *server, char *buf)
 {
 	struct mid_q_entry *mid;
-	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
-	__u64 wire_mid = le64_to_cpu(hdr->MessageId);
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+	__u64 wire_mid = le64_to_cpu(shdr->MessageId);
 
-	if (hdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
+	if (shdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM) {
 		cifs_dbg(VFS, "encrypted frame parsing not supported yet");
 		return NULL;
 	}
@@ -196,7 +201,7 @@ smb2_find_mid(struct TCP_Server_Info *server, char *buf)
 	list_for_each_entry(mid, &server->pending_mid_q, qhead) {
 		if ((mid->mid == wire_mid) &&
 		    (mid->mid_state == MID_REQUEST_SUBMITTED) &&
-		    (mid->command == hdr->Command)) {
+		    (mid->command == shdr->Command)) {
 			spin_unlock(&GlobalMid_Lock);
 			return mid;
 		}
@@ -209,12 +214,12 @@ static void
 smb2_dump_detail(void *buf)
 {
 #ifdef CONFIG_CIFS_DEBUG2
-	struct smb2_hdr *smb = (struct smb2_hdr *)buf;
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
 
 	cifs_dbg(VFS, "Cmd: %d Err: 0x%x Flags: 0x%x Mid: %llu Pid: %d\n",
-		 smb->Command, smb->Status, smb->Flags, smb->MessageId,
-		 smb->ProcessId);
-	cifs_dbg(VFS, "smb buf %p len %u\n", smb, smb2_calc_size(smb));
+		 shdr->Command, shdr->Status, shdr->Flags, shdr->MessageId,
+		 shdr->ProcessId);
+	cifs_dbg(VFS, "smb buf %p len %u\n", buf, smb2_calc_size(buf));
 #endif
 }
 
@@ -278,6 +283,7 @@ SMB3_request_interfaces(const unsigned int xid, struct cifs_tcon *tcon)
 
 	rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
 			FSCTL_QUERY_NETWORK_INTERFACE_INFO, true /* is_fsctl */,
+			false /* use_ipc */,
 			NULL /* no data input */, 0 /* no data input */,
 			(char **)&out_buf, &ret_data_len);
 	if (rc != 0)
@@ -567,6 +573,7 @@ SMB2_request_res_key(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
 			FSCTL_SRV_REQUEST_RESUME_KEY, true /* is_fsctl */,
+			false /* use_ipc */,
 			NULL, 0 /* no input */,
 			(char **)&res_key, &ret_data_len);
 
@@ -586,8 +593,8 @@ req_res_key_exit:
 	return rc;
 }
 
-static int
-smb2_clone_range(const unsigned int xid,
+static ssize_t
+smb2_copychunk_range(const unsigned int xid,
 			struct cifsFileInfo *srcfile,
 			struct cifsFileInfo *trgtfile, u64 src_off,
 			u64 len, u64 dest_off)
@@ -599,13 +606,14 @@ smb2_clone_range(const unsigned int xid,
 	struct cifs_tcon *tcon;
 	int chunks_copied = 0;
 	bool chunk_sizes_updated = false;
+	ssize_t bytes_written, total_bytes_written = 0;
 
 	pcchunk = kmalloc(sizeof(struct copychunk_ioctl), GFP_KERNEL);
 
 	if (pcchunk == NULL)
 		return -ENOMEM;
 
-	cifs_dbg(FYI, "in smb2_clone_range - about to call request res key\n");
+	cifs_dbg(FYI, "in smb2_copychunk_range - about to call request res key\n");
 	/* Request a key from the server to identify the source of the copy */
 	rc = SMB2_request_res_key(xid, tlink_tcon(srcfile->tlink),
 				srcfile->fid.persistent_fid,
@@ -631,7 +639,8 @@ smb2_clone_range(const unsigned int xid,
 		/* Request server copy to target from src identified by key */
 		rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
 			trgtfile->fid.volatile_fid, FSCTL_SRV_COPYCHUNK_WRITE,
-			true /* is_fsctl */, (char *)pcchunk,
+			true /* is_fsctl */, false /* use_ipc */,
+			(char *)pcchunk,
 			sizeof(struct copychunk_ioctl),	(char **)&retbuf,
 			&ret_data_len);
 		if (rc == 0) {
@@ -662,14 +671,16 @@ smb2_clone_range(const unsigned int xid,
 			}
 			chunks_copied++;
 
-			src_off += le32_to_cpu(retbuf->TotalBytesWritten);
-			dest_off += le32_to_cpu(retbuf->TotalBytesWritten);
-			len -= le32_to_cpu(retbuf->TotalBytesWritten);
+			bytes_written = le32_to_cpu(retbuf->TotalBytesWritten);
+			src_off += bytes_written;
+			dest_off += bytes_written;
+			len -= bytes_written;
+			total_bytes_written += bytes_written;
 
-			cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %d\n",
+			cifs_dbg(FYI, "Chunks %d PartialChunk %d Total %zu\n",
 				le32_to_cpu(retbuf->ChunksWritten),
 				le32_to_cpu(retbuf->ChunkBytesWritten),
-				le32_to_cpu(retbuf->TotalBytesWritten));
+				bytes_written);
 		} else if (rc == -EINVAL) {
 			if (ret_data_len != sizeof(struct copychunk_ioctl_rsp))
 				goto cchunk_out;
@@ -706,7 +717,10 @@ smb2_clone_range(const unsigned int xid,
 cchunk_out:
 	kfree(pcchunk);
 	kfree(retbuf);
-	return rc;
+	if (rc)
+		return rc;
+	else
+		return total_bytes_written;
 }
 
 static int
@@ -783,7 +797,8 @@ static bool smb2_set_sparse(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid, FSCTL_SET_SPARSE,
-			true /* is_fctl */, &setsparse, 1, NULL, NULL);
+			true /* is_fctl */, false /* use_ipc */,
+			&setsparse, 1, NULL, NULL);
 	if (rc) {
 		tcon->broken_sparse_sup = true;
 		cifs_dbg(FYI, "set sparse rc = %d\n", rc);
@@ -853,7 +868,8 @@ smb2_duplicate_extents(const unsigned int xid,
 	rc = SMB2_ioctl(xid, tcon, trgtfile->fid.persistent_fid,
 			trgtfile->fid.volatile_fid,
 			FSCTL_DUPLICATE_EXTENTS_TO_FILE,
-			true /* is_fsctl */, (char *)&dup_ext_buf,
+			true /* is_fsctl */, false /* use_ipc */,
+			(char *)&dup_ext_buf,
 			sizeof(struct duplicate_extents_to_file),
 			NULL,
 			&ret_data_len);
@@ -887,7 +903,8 @@ smb3_set_integrity(const unsigned int xid, struct cifs_tcon *tcon,
 	return SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid,
 			FSCTL_SET_INTEGRITY_INFORMATION,
-			true /* is_fsctl */, (char *)&integr_info,
+			true /* is_fsctl */, false /* use_ipc */,
+			(char *)&integr_info,
 			sizeof(struct fsctl_set_integrity_information_req),
 			NULL,
 			&ret_data_len);
@@ -906,7 +923,8 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid,
 			FSCTL_SRV_ENUMERATE_SNAPSHOTS,
-			true /* is_fsctl */, NULL, 0 /* no input data */,
+			true /* is_fsctl */, false /* use_ipc */,
+			NULL, 0 /* no input data */,
 			(char **)&retbuf,
 			&ret_data_len);
 	cifs_dbg(FYI, "enum snaphots ioctl returned %d and ret buflen is %d\n",
@@ -924,6 +942,7 @@ smb3_enum_snapshots(const unsigned int xid, struct cifs_tcon *tcon,
 		}
 		if (snapshot_in.snapshot_array_size < sizeof(struct smb_snapshot_array)) {
 			rc = -ERANGE;
+			kfree(retbuf);
 			return rc;
 		}
 
@@ -963,7 +982,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
 	kfree(utf16_path);
 	if (rc) {
-		cifs_dbg(VFS, "open dir failed\n");
+		cifs_dbg(FYI, "open dir failed rc=%d\n", rc);
 		return rc;
 	}
 
@@ -973,7 +992,7 @@ smb2_query_dir_first(const unsigned int xid, struct cifs_tcon *tcon,
 	rc = SMB2_query_directory(xid, tcon, fid->persistent_fid,
 				  fid->volatile_fid, 0, srch_inf);
 	if (rc) {
-		cifs_dbg(VFS, "query directory failed\n");
+		cifs_dbg(FYI, "query directory failed rc=%d\n", rc);
 		SMB2_close(xid, tcon, fid->persistent_fid, fid->volatile_fid);
 	}
 	return rc;
@@ -1002,14 +1021,14 @@ smb2_close_dir(const unsigned int xid, struct cifs_tcon *tcon,
 static bool
 smb2_is_status_pending(char *buf, struct TCP_Server_Info *server, int length)
 {
-	struct smb2_hdr *hdr = (struct smb2_hdr *)buf;
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
 
-	if (hdr->Status != STATUS_PENDING)
+	if (shdr->Status != STATUS_PENDING)
 		return false;
 
 	if (!length) {
 		spin_lock(&server->req_lock);
-		server->credits += le16_to_cpu(hdr->CreditRequest);
+		server->credits += le16_to_cpu(shdr->CreditRequest);
 		spin_unlock(&server->req_lock);
 		wake_up(&server->request_q);
 	}
@@ -1017,6 +1036,18 @@ smb2_is_status_pending(char *buf, struct TCP_Server_Info *server, int length)
 	return true;
 }
 
+static bool
+smb2_is_session_expired(char *buf)
+{
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+
+	if (shdr->Status != STATUS_NETWORK_SESSION_EXPIRED)
+		return false;
+
+	cifs_dbg(FYI, "Session expired\n");
+	return true;
+}
+
 static int
 smb2_oplock_response(struct cifs_tcon *tcon, struct cifs_fid *fid,
 		     struct cifsInodeInfo *cinode)
@@ -1093,6 +1124,103 @@ smb2_new_lease_key(struct cifs_fid *fid)
 	generate_random_uuid(fid->lease_key);
 }
 
+static int
+smb2_get_dfs_refer(const unsigned int xid, struct cifs_ses *ses,
+		   const char *search_name,
+		   struct dfs_info3_param **target_nodes,
+		   unsigned int *num_of_nodes,
+		   const struct nls_table *nls_codepage, int remap)
+{
+	int rc;
+	__le16 *utf16_path = NULL;
+	int utf16_path_len = 0;
+	struct cifs_tcon *tcon;
+	struct fsctl_get_dfs_referral_req *dfs_req = NULL;
+	struct get_dfs_referral_rsp *dfs_rsp = NULL;
+	u32 dfs_req_size = 0, dfs_rsp_size = 0;
+
+	cifs_dbg(FYI, "smb2_get_dfs_refer path <%s>\n", search_name);
+
+	/*
+	 * Use any tcon from the current session. Here, the first one.
+	 */
+	spin_lock(&cifs_tcp_ses_lock);
+	tcon = list_first_entry_or_null(&ses->tcon_list, struct cifs_tcon,
+					tcon_list);
+	if (tcon)
+		tcon->tc_count++;
+	spin_unlock(&cifs_tcp_ses_lock);
+
+	if (!tcon) {
+		cifs_dbg(VFS, "session %p has no tcon available for a dfs referral request\n",
+			 ses);
+		rc = -ENOTCONN;
+		goto out;
+	}
+
+	utf16_path = cifs_strndup_to_utf16(search_name, PATH_MAX,
+					   &utf16_path_len,
+					   nls_codepage, remap);
+	if (!utf16_path) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	dfs_req_size = sizeof(*dfs_req) + utf16_path_len;
+	dfs_req = kzalloc(dfs_req_size, GFP_KERNEL);
+	if (!dfs_req) {
+		rc = -ENOMEM;
+		goto out;
+	}
+
+	/* Highest DFS referral version understood */
+	dfs_req->MaxReferralLevel = DFS_VERSION;
+
+	/* Path to resolve in an UTF-16 null-terminated string */
+	memcpy(dfs_req->RequestFileName, utf16_path, utf16_path_len);
+
+	do {
+		/* try first with IPC */
+		rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
+				FSCTL_DFS_GET_REFERRALS,
+				true /* is_fsctl */, true /* use_ipc */,
+				(char *)dfs_req, dfs_req_size,
+				(char **)&dfs_rsp, &dfs_rsp_size);
+		if (rc == -ENOTCONN) {
+			/* try with normal tcon */
+			rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
+					FSCTL_DFS_GET_REFERRALS,
+					true /* is_fsctl */, false /*use_ipc*/,
+					(char *)dfs_req, dfs_req_size,
+					(char **)&dfs_rsp, &dfs_rsp_size);
+		}
+	} while (rc == -EAGAIN);
+
+	if (rc) {
+		cifs_dbg(VFS, "ioctl error in smb2_get_dfs_refer rc=%d\n", rc);
+		goto out;
+	}
+
+	rc = parse_dfs_referrals(dfs_rsp, dfs_rsp_size,
+				 num_of_nodes, target_nodes,
+				 nls_codepage, remap, search_name,
+				 true /* is_unicode */);
+	if (rc) {
+		cifs_dbg(VFS, "parse error in smb2_get_dfs_refer rc=%d\n", rc);
+		goto out;
+	}
+
+ out:
+	if (tcon) {
+		spin_lock(&cifs_tcp_ses_lock);
+		tcon->tc_count--;
+		spin_unlock(&cifs_tcp_ses_lock);
+	}
+	kfree(utf16_path);
+	kfree(dfs_req);
+	kfree(dfs_rsp);
+	return rc;
+}
 #define SMB2_SYMLINK_STRUCT_SIZE \
 	(sizeof(struct smb2_err_rsp) - 1 + sizeof(struct smb2_symlink_err_rsp))
 
@@ -1172,6 +1300,165 @@ smb2_query_symlink(const unsigned int xid, struct cifs_tcon *tcon,
 	return rc;
 }
 
+#ifdef CONFIG_CIFS_ACL
+static struct cifs_ntsd *
+get_smb2_acl_by_fid(struct cifs_sb_info *cifs_sb,
+		const struct cifs_fid *cifsfid, u32 *pacllen)
+{
+	struct cifs_ntsd *pntsd = NULL;
+	unsigned int xid;
+	int rc = -EOPNOTSUPP;
+	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+
+	if (IS_ERR(tlink))
+		return ERR_CAST(tlink);
+
+	xid = get_xid();
+	cifs_dbg(FYI, "trying to get acl\n");
+
+	rc = SMB2_query_acl(xid, tlink_tcon(tlink), cifsfid->persistent_fid,
+			    cifsfid->volatile_fid, (void **)&pntsd, pacllen);
+	free_xid(xid);
+
+	cifs_put_tlink(tlink);
+
+	cifs_dbg(FYI, "%s: rc = %d ACL len %d\n", __func__, rc, *pacllen);
+	if (rc)
+		return ERR_PTR(rc);
+	return pntsd;
+
+}
+
+static struct cifs_ntsd *
+get_smb2_acl_by_path(struct cifs_sb_info *cifs_sb,
+		const char *path, u32 *pacllen)
+{
+	struct cifs_ntsd *pntsd = NULL;
+	u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
+	unsigned int xid;
+	int rc;
+	struct cifs_tcon *tcon;
+	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+	struct cifs_fid fid;
+	struct cifs_open_parms oparms;
+	__le16 *utf16_path;
+
+	cifs_dbg(FYI, "get smb3 acl for path %s\n", path);
+	if (IS_ERR(tlink))
+		return ERR_CAST(tlink);
+
+	tcon = tlink_tcon(tlink);
+	xid = get_xid();
+
+	if (backup_cred(cifs_sb))
+		oparms.create_options = CREATE_OPEN_BACKUP_INTENT;
+	else
+		oparms.create_options = 0;
+
+	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
+	if (!utf16_path)
+		return ERR_PTR(-ENOMEM);
+
+	oparms.tcon = tcon;
+	oparms.desired_access = READ_CONTROL;
+	oparms.disposition = FILE_OPEN;
+	oparms.fid = &fid;
+	oparms.reconnect = false;
+
+	rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
+	kfree(utf16_path);
+	if (!rc) {
+		rc = SMB2_query_acl(xid, tlink_tcon(tlink), fid.persistent_fid,
+			    fid.volatile_fid, (void **)&pntsd, pacllen);
+		SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+	}
+
+	cifs_put_tlink(tlink);
+	free_xid(xid);
+
+	cifs_dbg(FYI, "%s: rc = %d ACL len %d\n", __func__, rc, *pacllen);
+	if (rc)
+		return ERR_PTR(rc);
+	return pntsd;
+}
+
+#ifdef CONFIG_CIFS_ACL
+static int
+set_smb2_acl(struct cifs_ntsd *pnntsd, __u32 acllen,
+		struct inode *inode, const char *path, int aclflag)
+{
+	u8 oplock = SMB2_OPLOCK_LEVEL_NONE;
+	unsigned int xid;
+	int rc, access_flags = 0;
+	struct cifs_tcon *tcon;
+	struct cifs_sb_info *cifs_sb = CIFS_SB(inode->i_sb);
+	struct tcon_link *tlink = cifs_sb_tlink(cifs_sb);
+	struct cifs_fid fid;
+	struct cifs_open_parms oparms;
+	__le16 *utf16_path;
+
+	cifs_dbg(FYI, "set smb3 acl for path %s\n", path);
+	if (IS_ERR(tlink))
+		return PTR_ERR(tlink);
+
+	tcon = tlink_tcon(tlink);
+	xid = get_xid();
+
+	if (backup_cred(cifs_sb))
+		oparms.create_options = CREATE_OPEN_BACKUP_INTENT;
+	else
+		oparms.create_options = 0;
+
+	if (aclflag == CIFS_ACL_OWNER || aclflag == CIFS_ACL_GROUP)
+		access_flags = WRITE_OWNER;
+	else
+		access_flags = WRITE_DAC;
+
+	utf16_path = cifs_convert_path_to_utf16(path, cifs_sb);
+	if (!utf16_path)
+		return -ENOMEM;
+
+	oparms.tcon = tcon;
+	oparms.desired_access = access_flags;
+	oparms.disposition = FILE_OPEN;
+	oparms.path = path;
+	oparms.fid = &fid;
+	oparms.reconnect = false;
+
+	rc = SMB2_open(xid, &oparms, utf16_path, &oplock, NULL, NULL);
+	kfree(utf16_path);
+	if (!rc) {
+		rc = SMB2_set_acl(xid, tlink_tcon(tlink), fid.persistent_fid,
+			    fid.volatile_fid, pnntsd, acllen, aclflag);
+		SMB2_close(xid, tcon, fid.persistent_fid, fid.volatile_fid);
+	}
+
+	cifs_put_tlink(tlink);
+	free_xid(xid);
+	return rc;
+}
+#endif /* CIFS_ACL */
+
+/* Retrieve an ACL from the server */
+static struct cifs_ntsd *
+get_smb2_acl(struct cifs_sb_info *cifs_sb,
+				      struct inode *inode, const char *path,
+				      u32 *pacllen)
+{
+	struct cifs_ntsd *pntsd = NULL;
+	struct cifsFileInfo *open_file = NULL;
+
+	if (inode)
+		open_file = find_readable_file(CIFS_I(inode), true);
+	if (!open_file)
+		return get_smb2_acl_by_path(cifs_sb, path, pacllen);
+
+	pntsd = get_smb2_acl_by_fid(cifs_sb, &open_file->fid, pacllen);
+	cifsFileInfo_put(open_file);
+	return pntsd;
+}
+#endif
+
 static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 			    loff_t offset, loff_t len, bool keep_size)
 {
@@ -1216,7 +1503,8 @@ static long smb3_zero_range(struct file *file, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA,
-			true /* is_fctl */, (char *)&fsctl_buf,
+			true /* is_fctl */, false /* use_ipc */,
+			(char *)&fsctl_buf,
 			sizeof(struct file_zero_data_information), NULL, NULL);
 	free_xid(xid);
 	return rc;
@@ -1250,7 +1538,8 @@ static long smb3_punch_hole(struct file *file, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, cfile->fid.persistent_fid,
 			cfile->fid.volatile_fid, FSCTL_SET_ZERO_DATA,
-			true /* is_fctl */, (char *)&fsctl_buf,
+			true /* is_fctl */, false /* use_ipc */,
+			(char *)&fsctl_buf,
 			sizeof(struct file_zero_data_information), NULL, NULL);
 	free_xid(xid);
 	return rc;
@@ -1545,6 +1834,662 @@ smb2_dir_needs_close(struct cifsFileInfo *cfile)
 	return !cfile->invalidHandle;
 }
 
+static void
+fill_transform_hdr(struct smb2_transform_hdr *tr_hdr, struct smb_rqst *old_rq)
+{
+	struct smb2_sync_hdr *shdr =
+			(struct smb2_sync_hdr *)old_rq->rq_iov[1].iov_base;
+	unsigned int orig_len = get_rfc1002_length(old_rq->rq_iov[0].iov_base);
+
+	memset(tr_hdr, 0, sizeof(struct smb2_transform_hdr));
+	tr_hdr->ProtocolId = SMB2_TRANSFORM_PROTO_NUM;
+	tr_hdr->OriginalMessageSize = cpu_to_le32(orig_len);
+	tr_hdr->Flags = cpu_to_le16(0x01);
+	get_random_bytes(&tr_hdr->Nonce, SMB3_AES128CMM_NONCE);
+	memcpy(&tr_hdr->SessionId, &shdr->SessionId, 8);
+	inc_rfc1001_len(tr_hdr, sizeof(struct smb2_transform_hdr) - 4);
+	inc_rfc1001_len(tr_hdr, orig_len);
+}
+
+static struct scatterlist *
+init_sg(struct smb_rqst *rqst, u8 *sign)
+{
+	unsigned int sg_len = rqst->rq_nvec + rqst->rq_npages + 1;
+	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24;
+	struct scatterlist *sg;
+	unsigned int i;
+	unsigned int j;
+
+	sg = kmalloc_array(sg_len, sizeof(struct scatterlist), GFP_KERNEL);
+	if (!sg)
+		return NULL;
+
+	sg_init_table(sg, sg_len);
+	sg_set_buf(&sg[0], rqst->rq_iov[0].iov_base + 24, assoc_data_len);
+	for (i = 1; i < rqst->rq_nvec; i++)
+		sg_set_buf(&sg[i], rqst->rq_iov[i].iov_base,
+						rqst->rq_iov[i].iov_len);
+	for (j = 0; i < sg_len - 1; i++, j++) {
+		unsigned int len = (j < rqst->rq_npages - 1) ? rqst->rq_pagesz
+							: rqst->rq_tailsz;
+		sg_set_page(&sg[i], rqst->rq_pages[j], len, 0);
+	}
+	sg_set_buf(&sg[sg_len - 1], sign, SMB2_SIGNATURE_SIZE);
+	return sg;
+}
+
+struct cifs_crypt_result {
+	int err;
+	struct completion completion;
+};
+
+static void cifs_crypt_complete(struct crypto_async_request *req, int err)
+{
+	struct cifs_crypt_result *res = req->data;
+
+	if (err == -EINPROGRESS)
+		return;
+
+	res->err = err;
+	complete(&res->completion);
+}
+
+static int
+smb2_get_enc_key(struct TCP_Server_Info *server, __u64 ses_id, int enc, u8 *key)
+{
+	struct cifs_ses *ses;
+	u8 *ses_enc_key;
+
+	spin_lock(&cifs_tcp_ses_lock);
+	list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
+		if (ses->Suid != ses_id)
+			continue;
+		ses_enc_key = enc ? ses->smb3encryptionkey :
+							ses->smb3decryptionkey;
+		memcpy(key, ses_enc_key, SMB3_SIGN_KEY_SIZE);
+		spin_unlock(&cifs_tcp_ses_lock);
+		return 0;
+	}
+	spin_unlock(&cifs_tcp_ses_lock);
+
+	return 1;
+}
+/*
+ * Encrypt or decrypt @rqst message. @rqst has the following format:
+ * iov[0] - transform header (associate data),
+ * iov[1-N] and pages - data to encrypt.
+ * On success return encrypted data in iov[1-N] and pages, leave iov[0]
+ * untouched.
+ */
+static int
+crypt_message(struct TCP_Server_Info *server, struct smb_rqst *rqst, int enc)
+{
+	struct smb2_transform_hdr *tr_hdr =
+			(struct smb2_transform_hdr *)rqst->rq_iov[0].iov_base;
+	unsigned int assoc_data_len = sizeof(struct smb2_transform_hdr) - 24;
+	int rc = 0;
+	struct scatterlist *sg;
+	u8 sign[SMB2_SIGNATURE_SIZE] = {};
+	u8 key[SMB3_SIGN_KEY_SIZE];
+	struct aead_request *req;
+	char *iv;
+	unsigned int iv_len;
+	struct cifs_crypt_result result = {0, };
+	struct crypto_aead *tfm;
+	unsigned int crypt_len = le32_to_cpu(tr_hdr->OriginalMessageSize);
+
+	init_completion(&result.completion);
+
+	rc = smb2_get_enc_key(server, tr_hdr->SessionId, enc, key);
+	if (rc) {
+		cifs_dbg(VFS, "%s: Could not get %scryption key\n", __func__,
+			 enc ? "en" : "de");
+		return 0;
+	}
+
+	rc = smb3_crypto_aead_allocate(server);
+	if (rc) {
+		cifs_dbg(VFS, "%s: crypto alloc failed\n", __func__);
+		return rc;
+	}
+
+	tfm = enc ? server->secmech.ccmaesencrypt :
+						server->secmech.ccmaesdecrypt;
+	rc = crypto_aead_setkey(tfm, key, SMB3_SIGN_KEY_SIZE);
+	if (rc) {
+		cifs_dbg(VFS, "%s: Failed to set aead key %d\n", __func__, rc);
+		return rc;
+	}
+
+	rc = crypto_aead_setauthsize(tfm, SMB2_SIGNATURE_SIZE);
+	if (rc) {
+		cifs_dbg(VFS, "%s: Failed to set authsize %d\n", __func__, rc);
+		return rc;
+	}
+
+	req = aead_request_alloc(tfm, GFP_KERNEL);
+	if (!req) {
+		cifs_dbg(VFS, "%s: Failed to alloc aead request", __func__);
+		return -ENOMEM;
+	}
+
+	if (!enc) {
+		memcpy(sign, &tr_hdr->Signature, SMB2_SIGNATURE_SIZE);
+		crypt_len += SMB2_SIGNATURE_SIZE;
+	}
+
+	sg = init_sg(rqst, sign);
+	if (!sg) {
+		cifs_dbg(VFS, "%s: Failed to init sg", __func__);
+		rc = -ENOMEM;
+		goto free_req;
+	}
+
+	iv_len = crypto_aead_ivsize(tfm);
+	iv = kzalloc(iv_len, GFP_KERNEL);
+	if (!iv) {
+		cifs_dbg(VFS, "%s: Failed to alloc IV", __func__);
+		rc = -ENOMEM;
+		goto free_sg;
+	}
+	iv[0] = 3;
+	memcpy(iv + 1, (char *)tr_hdr->Nonce, SMB3_AES128CMM_NONCE);
+
+	aead_request_set_crypt(req, sg, sg, crypt_len, iv);
+	aead_request_set_ad(req, assoc_data_len);
+
+	aead_request_set_callback(req, CRYPTO_TFM_REQ_MAY_BACKLOG,
+				  cifs_crypt_complete, &result);
+
+	rc = enc ? crypto_aead_encrypt(req) : crypto_aead_decrypt(req);
+
+	if (rc == -EINPROGRESS || rc == -EBUSY) {
+		wait_for_completion(&result.completion);
+		rc = result.err;
+	}
+
+	if (!rc && enc)
+		memcpy(&tr_hdr->Signature, sign, SMB2_SIGNATURE_SIZE);
+
+	kfree(iv);
+free_sg:
+	kfree(sg);
+free_req:
+	kfree(req);
+	return rc;
+}
+
+static int
+smb3_init_transform_rq(struct TCP_Server_Info *server, struct smb_rqst *new_rq,
+		       struct smb_rqst *old_rq)
+{
+	struct kvec *iov;
+	struct page **pages;
+	struct smb2_transform_hdr *tr_hdr;
+	unsigned int npages = old_rq->rq_npages;
+	int i;
+	int rc = -ENOMEM;
+
+	pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
+	if (!pages)
+		return rc;
+
+	new_rq->rq_pages = pages;
+	new_rq->rq_npages = old_rq->rq_npages;
+	new_rq->rq_pagesz = old_rq->rq_pagesz;
+	new_rq->rq_tailsz = old_rq->rq_tailsz;
+
+	for (i = 0; i < npages; i++) {
+		pages[i] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
+		if (!pages[i])
+			goto err_free_pages;
+	}
+
+	iov = kmalloc_array(old_rq->rq_nvec, sizeof(struct kvec), GFP_KERNEL);
+	if (!iov)
+		goto err_free_pages;
+
+	/* copy all iovs from the old except the 1st one (rfc1002 length) */
+	memcpy(&iov[1], &old_rq->rq_iov[1],
+				sizeof(struct kvec) * (old_rq->rq_nvec - 1));
+	new_rq->rq_iov = iov;
+	new_rq->rq_nvec = old_rq->rq_nvec;
+
+	tr_hdr = kmalloc(sizeof(struct smb2_transform_hdr), GFP_KERNEL);
+	if (!tr_hdr)
+		goto err_free_iov;
+
+	/* fill the 1st iov with a transform header */
+	fill_transform_hdr(tr_hdr, old_rq);
+	new_rq->rq_iov[0].iov_base = tr_hdr;
+	new_rq->rq_iov[0].iov_len = sizeof(struct smb2_transform_hdr);
+
+	/* copy pages form the old */
+	for (i = 0; i < npages; i++) {
+		char *dst = kmap(new_rq->rq_pages[i]);
+		char *src = kmap(old_rq->rq_pages[i]);
+		unsigned int len = (i < npages - 1) ? new_rq->rq_pagesz :
+							new_rq->rq_tailsz;
+		memcpy(dst, src, len);
+		kunmap(new_rq->rq_pages[i]);
+		kunmap(old_rq->rq_pages[i]);
+	}
+
+	rc = crypt_message(server, new_rq, 1);
+	cifs_dbg(FYI, "encrypt message returned %d", rc);
+	if (rc)
+		goto err_free_tr_hdr;
+
+	return rc;
+
+err_free_tr_hdr:
+	kfree(tr_hdr);
+err_free_iov:
+	kfree(iov);
+err_free_pages:
+	for (i = i - 1; i >= 0; i--)
+		put_page(pages[i]);
+	kfree(pages);
+	return rc;
+}
+
+static void
+smb3_free_transform_rq(struct smb_rqst *rqst)
+{
+	int i = rqst->rq_npages - 1;
+
+	for (; i >= 0; i--)
+		put_page(rqst->rq_pages[i]);
+	kfree(rqst->rq_pages);
+	/* free transform header */
+	kfree(rqst->rq_iov[0].iov_base);
+	kfree(rqst->rq_iov);
+}
+
+static int
+smb3_is_transform_hdr(void *buf)
+{
+	struct smb2_transform_hdr *trhdr = buf;
+
+	return trhdr->ProtocolId == SMB2_TRANSFORM_PROTO_NUM;
+}
+
+static int
+decrypt_raw_data(struct TCP_Server_Info *server, char *buf,
+		 unsigned int buf_data_size, struct page **pages,
+		 unsigned int npages, unsigned int page_data_size)
+{
+	struct kvec iov[2];
+	struct smb_rqst rqst = {NULL};
+	struct smb2_hdr *hdr;
+	int rc;
+
+	iov[0].iov_base = buf;
+	iov[0].iov_len = sizeof(struct smb2_transform_hdr);
+	iov[1].iov_base = buf + sizeof(struct smb2_transform_hdr);
+	iov[1].iov_len = buf_data_size;
+
+	rqst.rq_iov = iov;
+	rqst.rq_nvec = 2;
+	rqst.rq_pages = pages;
+	rqst.rq_npages = npages;
+	rqst.rq_pagesz = PAGE_SIZE;
+	rqst.rq_tailsz = (page_data_size % PAGE_SIZE) ? : PAGE_SIZE;
+
+	rc = crypt_message(server, &rqst, 0);
+	cifs_dbg(FYI, "decrypt message returned %d\n", rc);
+
+	if (rc)
+		return rc;
+
+	memmove(buf + 4, iov[1].iov_base, buf_data_size);
+	hdr = (struct smb2_hdr *)buf;
+	hdr->smb2_buf_length = cpu_to_be32(buf_data_size + page_data_size);
+	server->total_read = buf_data_size + page_data_size + 4;
+
+	return rc;
+}
+
+static int
+read_data_into_pages(struct TCP_Server_Info *server, struct page **pages,
+		     unsigned int npages, unsigned int len)
+{
+	int i;
+	int length;
+
+	for (i = 0; i < npages; i++) {
+		struct page *page = pages[i];
+		size_t n;
+
+		n = len;
+		if (len >= PAGE_SIZE) {
+			/* enough data to fill the page */
+			n = PAGE_SIZE;
+			len -= n;
+		} else {
+			zero_user(page, len, PAGE_SIZE - len);
+			len = 0;
+		}
+		length = cifs_read_page_from_socket(server, page, n);
+		if (length < 0)
+			return length;
+		server->total_read += length;
+	}
+
+	return 0;
+}
+
+static int
+init_read_bvec(struct page **pages, unsigned int npages, unsigned int data_size,
+	       unsigned int cur_off, struct bio_vec **page_vec)
+{
+	struct bio_vec *bvec;
+	int i;
+
+	bvec = kcalloc(npages, sizeof(struct bio_vec), GFP_KERNEL);
+	if (!bvec)
+		return -ENOMEM;
+
+	for (i = 0; i < npages; i++) {
+		bvec[i].bv_page = pages[i];
+		bvec[i].bv_offset = (i == 0) ? cur_off : 0;
+		bvec[i].bv_len = min_t(unsigned int, PAGE_SIZE, data_size);
+		data_size -= bvec[i].bv_len;
+	}
+
+	if (data_size != 0) {
+		cifs_dbg(VFS, "%s: something went wrong\n", __func__);
+		kfree(bvec);
+		return -EIO;
+	}
+
+	*page_vec = bvec;
+	return 0;
+}
+
+static int
+handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid,
+		 char *buf, unsigned int buf_len, struct page **pages,
+		 unsigned int npages, unsigned int page_data_size)
+{
+	unsigned int data_offset;
+	unsigned int data_len;
+	unsigned int cur_off;
+	unsigned int cur_page_idx;
+	unsigned int pad_len;
+	struct cifs_readdata *rdata = mid->callback_data;
+	struct smb2_sync_hdr *shdr = get_sync_hdr(buf);
+	struct bio_vec *bvec = NULL;
+	struct iov_iter iter;
+	struct kvec iov;
+	int length;
+
+	if (shdr->Command != SMB2_READ) {
+		cifs_dbg(VFS, "only big read responses are supported\n");
+		return -ENOTSUPP;
+	}
+
+	if (server->ops->is_session_expired &&
+	    server->ops->is_session_expired(buf)) {
+		cifs_reconnect(server);
+		wake_up(&server->response_q);
+		return -1;
+	}
+
+	if (server->ops->is_status_pending &&
+			server->ops->is_status_pending(buf, server, 0))
+		return -1;
+
+	rdata->result = server->ops->map_error(buf, false);
+	if (rdata->result != 0) {
+		cifs_dbg(FYI, "%s: server returned error %d\n",
+			 __func__, rdata->result);
+		dequeue_mid(mid, rdata->result);
+		return 0;
+	}
+
+	data_offset = server->ops->read_data_offset(buf) + 4;
+	data_len = server->ops->read_data_length(buf);
+
+	if (data_offset < server->vals->read_rsp_size) {
+		/*
+		 * win2k8 sometimes sends an offset of 0 when the read
+		 * is beyond the EOF. Treat it as if the data starts just after
+		 * the header.
+		 */
+		cifs_dbg(FYI, "%s: data offset (%u) inside read response header\n",
+			 __func__, data_offset);
+		data_offset = server->vals->read_rsp_size;
+	} else if (data_offset > MAX_CIFS_SMALL_BUFFER_SIZE) {
+		/* data_offset is beyond the end of smallbuf */
+		cifs_dbg(FYI, "%s: data offset (%u) beyond end of smallbuf\n",
+			 __func__, data_offset);
+		rdata->result = -EIO;
+		dequeue_mid(mid, rdata->result);
+		return 0;
+	}
+
+	pad_len = data_offset - server->vals->read_rsp_size;
+
+	if (buf_len <= data_offset) {
+		/* read response payload is in pages */
+		cur_page_idx = pad_len / PAGE_SIZE;
+		cur_off = pad_len % PAGE_SIZE;
+
+		if (cur_page_idx != 0) {
+			/* data offset is beyond the 1st page of response */
+			cifs_dbg(FYI, "%s: data offset (%u) beyond 1st page of response\n",
+				 __func__, data_offset);
+			rdata->result = -EIO;
+			dequeue_mid(mid, rdata->result);
+			return 0;
+		}
+
+		if (data_len > page_data_size - pad_len) {
+			/* data_len is corrupt -- discard frame */
+			rdata->result = -EIO;
+			dequeue_mid(mid, rdata->result);
+			return 0;
+		}
+
+		rdata->result = init_read_bvec(pages, npages, page_data_size,
+					       cur_off, &bvec);
+		if (rdata->result != 0) {
+			dequeue_mid(mid, rdata->result);
+			return 0;
+		}
+
+		iov_iter_bvec(&iter, WRITE | ITER_BVEC, bvec, npages, data_len);
+	} else if (buf_len >= data_offset + data_len) {
+		/* read response payload is in buf */
+		WARN_ONCE(npages > 0, "read data can be either in buf or in pages");
+		iov.iov_base = buf + data_offset;
+		iov.iov_len = data_len;
+		iov_iter_kvec(&iter, WRITE | ITER_KVEC, &iov, 1, data_len);
+	} else {
+		/* read response payload cannot be in both buf and pages */
+		WARN_ONCE(1, "buf can not contain only a part of read data");
+		rdata->result = -EIO;
+		dequeue_mid(mid, rdata->result);
+		return 0;
+	}
+
+	/* set up first iov for signature check */
+	rdata->iov[0].iov_base = buf;
+	rdata->iov[0].iov_len = 4;
+	rdata->iov[1].iov_base = buf + 4;
+	rdata->iov[1].iov_len = server->vals->read_rsp_size - 4;
+	cifs_dbg(FYI, "0: iov_base=%p iov_len=%zu\n",
+		 rdata->iov[0].iov_base, server->vals->read_rsp_size);
+
+	length = rdata->copy_into_pages(server, rdata, &iter);
+
+	kfree(bvec);
+
+	if (length < 0)
+		return length;
+
+	dequeue_mid(mid, false);
+	return length;
+}
+
+static int
+receive_encrypted_read(struct TCP_Server_Info *server, struct mid_q_entry **mid)
+{
+	char *buf = server->smallbuf;
+	struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf;
+	unsigned int npages;
+	struct page **pages;
+	unsigned int len;
+	unsigned int buflen = get_rfc1002_length(buf) + 4;
+	int rc;
+	int i = 0;
+
+	len = min_t(unsigned int, buflen, server->vals->read_rsp_size - 4 +
+		sizeof(struct smb2_transform_hdr)) - HEADER_SIZE(server) + 1;
+
+	rc = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1, len);
+	if (rc < 0)
+		return rc;
+	server->total_read += rc;
+
+	len = le32_to_cpu(tr_hdr->OriginalMessageSize) + 4 -
+						server->vals->read_rsp_size;
+	npages = DIV_ROUND_UP(len, PAGE_SIZE);
+
+	pages = kmalloc_array(npages, sizeof(struct page *), GFP_KERNEL);
+	if (!pages) {
+		rc = -ENOMEM;
+		goto discard_data;
+	}
+
+	for (; i < npages; i++) {
+		pages[i] = alloc_page(GFP_KERNEL|__GFP_HIGHMEM);
+		if (!pages[i]) {
+			rc = -ENOMEM;
+			goto discard_data;
+		}
+	}
+
+	/* read read data into pages */
+	rc = read_data_into_pages(server, pages, npages, len);
+	if (rc)
+		goto free_pages;
+
+	rc = cifs_discard_remaining_data(server);
+	if (rc)
+		goto free_pages;
+
+	rc = decrypt_raw_data(server, buf, server->vals->read_rsp_size - 4,
+			      pages, npages, len);
+	if (rc)
+		goto free_pages;
+
+	*mid = smb2_find_mid(server, buf);
+	if (*mid == NULL)
+		cifs_dbg(FYI, "mid not found\n");
+	else {
+		cifs_dbg(FYI, "mid found\n");
+		(*mid)->decrypted = true;
+		rc = handle_read_data(server, *mid, buf,
+				      server->vals->read_rsp_size,
+				      pages, npages, len);
+	}
+
+free_pages:
+	for (i = i - 1; i >= 0; i--)
+		put_page(pages[i]);
+	kfree(pages);
+	return rc;
+discard_data:
+	cifs_discard_remaining_data(server);
+	goto free_pages;
+}
+
+static int
+receive_encrypted_standard(struct TCP_Server_Info *server,
+			   struct mid_q_entry **mid)
+{
+	int length;
+	char *buf = server->smallbuf;
+	unsigned int pdu_length = get_rfc1002_length(buf);
+	unsigned int buf_size;
+	struct mid_q_entry *mid_entry;
+
+	/* switch to large buffer if too big for a small one */
+	if (pdu_length + 4 > MAX_CIFS_SMALL_BUFFER_SIZE) {
+		server->large_buf = true;
+		memcpy(server->bigbuf, buf, server->total_read);
+		buf = server->bigbuf;
+	}
+
+	/* now read the rest */
+	length = cifs_read_from_socket(server, buf + HEADER_SIZE(server) - 1,
+				pdu_length - HEADER_SIZE(server) + 1 + 4);
+	if (length < 0)
+		return length;
+	server->total_read += length;
+
+	buf_size = pdu_length + 4 - sizeof(struct smb2_transform_hdr);
+	length = decrypt_raw_data(server, buf, buf_size, NULL, 0, 0);
+	if (length)
+		return length;
+
+	mid_entry = smb2_find_mid(server, buf);
+	if (mid_entry == NULL)
+		cifs_dbg(FYI, "mid not found\n");
+	else {
+		cifs_dbg(FYI, "mid found\n");
+		mid_entry->decrypted = true;
+	}
+
+	*mid = mid_entry;
+
+	if (mid_entry && mid_entry->handle)
+		return mid_entry->handle(server, mid_entry);
+
+	return cifs_handle_standard(server, mid_entry);
+}
+
+static int
+smb3_receive_transform(struct TCP_Server_Info *server, struct mid_q_entry **mid)
+{
+	char *buf = server->smallbuf;
+	unsigned int pdu_length = get_rfc1002_length(buf);
+	struct smb2_transform_hdr *tr_hdr = (struct smb2_transform_hdr *)buf;
+	unsigned int orig_len = le32_to_cpu(tr_hdr->OriginalMessageSize);
+
+	if (pdu_length + 4 < sizeof(struct smb2_transform_hdr) +
+						sizeof(struct smb2_sync_hdr)) {
+		cifs_dbg(VFS, "Transform message is too small (%u)\n",
+			 pdu_length);
+		cifs_reconnect(server);
+		wake_up(&server->response_q);
+		return -ECONNABORTED;
+	}
+
+	if (pdu_length + 4 < orig_len + sizeof(struct smb2_transform_hdr)) {
+		cifs_dbg(VFS, "Transform message is broken\n");
+		cifs_reconnect(server);
+		wake_up(&server->response_q);
+		return -ECONNABORTED;
+	}
+
+	if (pdu_length + 4 > CIFSMaxBufSize + MAX_HEADER_SIZE(server))
+		return receive_encrypted_read(server, mid);
+
+	return receive_encrypted_standard(server, mid);
+}
+
+int
+smb3_handle_read_data(struct TCP_Server_Info *server, struct mid_q_entry *mid)
+{
+	char *buf = server->large_buf ? server->bigbuf : server->smallbuf;
+
+	return handle_read_data(server, mid, buf, get_rfc1002_length(buf) + 4,
+				NULL, 0, 0);
+}
+
 struct smb_version_operations smb20_operations = {
 	.compare_fids = smb2_compare_fids,
 	.setup_request = smb2_setup_request,
@@ -1565,6 +2510,7 @@ struct smb_version_operations smb20_operations = {
 	.clear_stats = smb2_clear_stats,
 	.print_stats = smb2_print_stats,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.handle_cancelled_mid = smb2_handle_cancelled_mid,
 	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
@@ -1607,6 +2553,7 @@ struct smb_version_operations smb20_operations = {
 	.close_dir = smb2_close_dir,
 	.calc_smb_size = smb2_calc_size,
 	.is_status_pending = smb2_is_status_pending,
+	.is_session_expired = smb2_is_session_expired,
 	.oplock_response = smb2_oplock_response,
 	.queryfs = smb2_queryfs,
 	.mand_lock = smb2_mand_lock,
@@ -1620,9 +2567,16 @@ struct smb_version_operations smb20_operations = {
 	.set_oplock_level = smb2_set_oplock_level,
 	.create_lease_buf = smb2_create_lease_buf,
 	.parse_lease_buf = smb2_parse_lease_buf,
-	.clone_range = smb2_clone_range,
+	.copychunk_range = smb2_copychunk_range,
 	.wp_retry_size = smb2_wp_retry_size,
 	.dir_needs_close = smb2_dir_needs_close,
+	.get_dfs_refer = smb2_get_dfs_refer,
+	.select_sectype = smb2_select_sectype,
+#ifdef CONFIG_CIFS_ACL
+	.get_acl = get_smb2_acl,
+	.get_acl_by_fid = get_smb2_acl_by_fid,
+	.set_acl = set_smb2_acl,
+#endif /* CIFS_ACL */
 };
 
 struct smb_version_operations smb21_operations = {
@@ -1645,6 +2599,7 @@ struct smb_version_operations smb21_operations = {
 	.clear_stats = smb2_clear_stats,
 	.print_stats = smb2_print_stats,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.handle_cancelled_mid = smb2_handle_cancelled_mid,
 	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
@@ -1687,6 +2642,7 @@ struct smb_version_operations smb21_operations = {
 	.close_dir = smb2_close_dir,
 	.calc_smb_size = smb2_calc_size,
 	.is_status_pending = smb2_is_status_pending,
+	.is_session_expired = smb2_is_session_expired,
 	.oplock_response = smb2_oplock_response,
 	.queryfs = smb2_queryfs,
 	.mand_lock = smb2_mand_lock,
@@ -1700,10 +2656,17 @@ struct smb_version_operations smb21_operations = {
 	.set_oplock_level = smb21_set_oplock_level,
 	.create_lease_buf = smb2_create_lease_buf,
 	.parse_lease_buf = smb2_parse_lease_buf,
-	.clone_range = smb2_clone_range,
+	.copychunk_range = smb2_copychunk_range,
 	.wp_retry_size = smb2_wp_retry_size,
 	.dir_needs_close = smb2_dir_needs_close,
 	.enum_snapshots = smb3_enum_snapshots,
+	.get_dfs_refer = smb2_get_dfs_refer,
+	.select_sectype = smb2_select_sectype,
+#ifdef CONFIG_CIFS_ACL
+	.get_acl = get_smb2_acl,
+	.get_acl_by_fid = get_smb2_acl_by_fid,
+	.set_acl = set_smb2_acl,
+#endif /* CIFS_ACL */
 };
 
 struct smb_version_operations smb30_operations = {
@@ -1727,6 +2690,7 @@ struct smb_version_operations smb30_operations = {
 	.print_stats = smb2_print_stats,
 	.dump_share_caps = smb2_dump_share_caps,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.handle_cancelled_mid = smb2_handle_cancelled_mid,
 	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
@@ -1769,6 +2733,7 @@ struct smb_version_operations smb30_operations = {
 	.close_dir = smb2_close_dir,
 	.calc_smb_size = smb2_calc_size,
 	.is_status_pending = smb2_is_status_pending,
+	.is_session_expired = smb2_is_session_expired,
 	.oplock_response = smb2_oplock_response,
 	.queryfs = smb2_queryfs,
 	.mand_lock = smb2_mand_lock,
@@ -1784,13 +2749,24 @@ struct smb_version_operations smb30_operations = {
 	.set_oplock_level = smb3_set_oplock_level,
 	.create_lease_buf = smb3_create_lease_buf,
 	.parse_lease_buf = smb3_parse_lease_buf,
-	.clone_range = smb2_clone_range,
+	.copychunk_range = smb2_copychunk_range,
 	.duplicate_extents = smb2_duplicate_extents,
 	.validate_negotiate = smb3_validate_negotiate,
 	.wp_retry_size = smb2_wp_retry_size,
 	.dir_needs_close = smb2_dir_needs_close,
 	.fallocate = smb3_fallocate,
 	.enum_snapshots = smb3_enum_snapshots,
+	.init_transform_rq = smb3_init_transform_rq,
+	.free_transform_rq = smb3_free_transform_rq,
+	.is_transform_hdr = smb3_is_transform_hdr,
+	.receive_transform = smb3_receive_transform,
+	.get_dfs_refer = smb2_get_dfs_refer,
+	.select_sectype = smb2_select_sectype,
+#ifdef CONFIG_CIFS_ACL
+	.get_acl = get_smb2_acl,
+	.get_acl_by_fid = get_smb2_acl_by_fid,
+	.set_acl = set_smb2_acl,
+#endif /* CIFS_ACL */
 };
 
 #ifdef CONFIG_CIFS_SMB311
@@ -1815,6 +2791,7 @@ struct smb_version_operations smb311_operations = {
 	.print_stats = smb2_print_stats,
 	.dump_share_caps = smb2_dump_share_caps,
 	.is_oplock_break = smb2_is_valid_oplock_break,
+	.handle_cancelled_mid = smb2_handle_cancelled_mid,
 	.downgrade_oplock = smb2_downgrade_oplock,
 	.need_neg = smb2_need_neg,
 	.negotiate = smb2_negotiate,
@@ -1857,6 +2834,7 @@ struct smb_version_operations smb311_operations = {
 	.close_dir = smb2_close_dir,
 	.calc_smb_size = smb2_calc_size,
 	.is_status_pending = smb2_is_status_pending,
+	.is_session_expired = smb2_is_session_expired,
 	.oplock_response = smb2_oplock_response,
 	.queryfs = smb2_queryfs,
 	.mand_lock = smb2_mand_lock,
@@ -1872,13 +2850,19 @@ struct smb_version_operations smb311_operations = {
 	.set_oplock_level = smb3_set_oplock_level,
 	.create_lease_buf = smb3_create_lease_buf,
 	.parse_lease_buf = smb3_parse_lease_buf,
-	.clone_range = smb2_clone_range,
+	.copychunk_range = smb2_copychunk_range,
 	.duplicate_extents = smb2_duplicate_extents,
 /*	.validate_negotiate = smb3_validate_negotiate, */ /* not used in 3.11 */
 	.wp_retry_size = smb2_wp_retry_size,
 	.dir_needs_close = smb2_dir_needs_close,
 	.fallocate = smb3_fallocate,
 	.enum_snapshots = smb3_enum_snapshots,
+	.init_transform_rq = smb3_init_transform_rq,
+	.free_transform_rq = smb3_free_transform_rq,
+	.is_transform_hdr = smb3_is_transform_hdr,
+	.receive_transform = smb3_receive_transform,
+	.get_dfs_refer = smb2_get_dfs_refer,
+	.select_sectype = smb2_select_sectype,
 };
 #endif /* CIFS_SMB311 */
 
@@ -1966,7 +2950,7 @@ struct smb_version_values smb302_values = {
 struct smb_version_values smb311_values = {
 	.version_string = SMB311_VERSION_STRING,
 	.protocol_id = SMB311_PROT_ID,
-	.req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES,
+	.req_capabilities = SMB2_GLOBAL_CAP_DFS | SMB2_GLOBAL_CAP_LEASING | SMB2_GLOBAL_CAP_LARGE_MTU | SMB2_GLOBAL_CAP_PERSISTENT_HANDLES | SMB2_GLOBAL_CAP_ENCRYPTION,
 	.large_lock_type = 0,
 	.exclusive_lock_type = SMB2_LOCKFLAG_EXCLUSIVE_LOCK,
 	.shared_lock_type = SMB2_LOCKFLAG_SHARED_LOCK,
diff --git a/fs/cifs/smb2pdu.c b/fs/cifs/smb2pdu.c
index 87457227812c..5fb2fc2d0080 100644
--- a/fs/cifs/smb2pdu.c
+++ b/fs/cifs/smb2pdu.c
@@ -33,6 +33,7 @@
 #include <linux/vfs.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/uaccess.h>
+#include <linux/uuid.h>
 #include <linux/pagemap.h>
 #include <linux/xattr.h>
 #include "smb2pdu.h"
@@ -77,45 +78,42 @@ static const int smb2_req_struct_sizes[NUMBER_OF_SMB2_COMMANDS] = {
 	/* SMB2_OPLOCK_BREAK */ 24 /* BB this is 36 for LEASE_BREAK variant */
 };
 
+static int encryption_required(const struct cifs_tcon *tcon)
+{
+	if (!tcon)
+		return 0;
+	if ((tcon->ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA) ||
+	    (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA))
+		return 1;
+	if (tcon->seal &&
+	    (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION))
+		return 1;
+	return 0;
+}
 
 static void
-smb2_hdr_assemble(struct smb2_hdr *hdr, __le16 smb2_cmd /* command */ ,
+smb2_hdr_assemble(struct smb2_sync_hdr *shdr, __le16 smb2_cmd,
 		  const struct cifs_tcon *tcon)
 {
-	struct smb2_pdu *pdu = (struct smb2_pdu *)hdr;
-	char *temp = (char *)hdr;
-	/* lookup word count ie StructureSize from table */
-	__u16 parmsize = smb2_req_struct_sizes[le16_to_cpu(smb2_cmd)];
-
-	/*
-	 * smaller than SMALL_BUFFER_SIZE but bigger than fixed area of
-	 * largest operations (Create)
-	 */
-	memset(temp, 0, 256);
-
-	/* Note this is only network field converted to big endian */
-	hdr->smb2_buf_length = cpu_to_be32(parmsize + sizeof(struct smb2_hdr)
-			- 4 /*  RFC 1001 length field itself not counted */);
-
-	hdr->ProtocolId = SMB2_PROTO_NUMBER;
-	hdr->StructureSize = cpu_to_le16(64);
-	hdr->Command = smb2_cmd;
+	shdr->ProtocolId = SMB2_PROTO_NUMBER;
+	shdr->StructureSize = cpu_to_le16(64);
+	shdr->Command = smb2_cmd;
 	if (tcon && tcon->ses && tcon->ses->server) {
 		struct TCP_Server_Info *server = tcon->ses->server;
 
 		spin_lock(&server->req_lock);
 		/* Request up to 2 credits but don't go over the limit. */
 		if (server->credits >= server->max_credits)
-			hdr->CreditRequest = cpu_to_le16(0);
+			shdr->CreditRequest = cpu_to_le16(0);
 		else
-			hdr->CreditRequest = cpu_to_le16(
+			shdr->CreditRequest = cpu_to_le16(
 				min_t(int, server->max_credits -
 						server->credits, 2));
 		spin_unlock(&server->req_lock);
 	} else {
-		hdr->CreditRequest = cpu_to_le16(2);
+		shdr->CreditRequest = cpu_to_le16(2);
 	}
-	hdr->ProcessId = cpu_to_le32((__u16)current->tgid);
+	shdr->ProcessId = cpu_to_le32((__u16)current->tgid);
 
 	if (!tcon)
 		goto out;
@@ -124,13 +122,13 @@ smb2_hdr_assemble(struct smb2_hdr *hdr, __le16 smb2_cmd /* command */ ,
 	/* See sections 2.2.4 and 3.2.4.1.5 of MS-SMB2 */
 	if ((tcon->ses) && (tcon->ses->server) &&
 	    (tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_LARGE_MTU))
-		hdr->CreditCharge = cpu_to_le16(1);
+		shdr->CreditCharge = cpu_to_le16(1);
 	/* else CreditCharge MBZ */
 
-	hdr->TreeId = tcon->tid;
+	shdr->TreeId = tcon->tid;
 	/* Uid is not converted */
 	if (tcon->ses)
-		hdr->SessionId = tcon->ses->Suid;
+		shdr->SessionId = tcon->ses->Suid;
 
 	/*
 	 * If we would set SMB2_FLAGS_DFS_OPERATIONS on open we also would have
@@ -143,12 +141,12 @@ smb2_hdr_assemble(struct smb2_hdr *hdr, __le16 smb2_cmd /* command */ ,
 	 * but it is safer to net set it for now.
 	 */
 /*	if (tcon->share_flags & SHI1005_FLAGS_DFS)
-		hdr->Flags |= SMB2_FLAGS_DFS_OPERATIONS; */
+		shdr->Flags |= SMB2_FLAGS_DFS_OPERATIONS; */
 
-	if (tcon->ses && tcon->ses->server && tcon->ses->server->sign)
-		hdr->Flags |= SMB2_FLAGS_SIGNED;
+	if (tcon->ses && tcon->ses->server && tcon->ses->server->sign &&
+	    !encryption_required(tcon))
+		shdr->Flags |= SMB2_FLAGS_SIGNED;
 out:
-	pdu->StructureSize2 = cpu_to_le16(parmsize);
 	return;
 }
 
@@ -289,16 +287,74 @@ out:
 	return rc;
 }
 
+static void
+fill_small_buf(__le16 smb2_command, struct cifs_tcon *tcon, void *buf,
+	       unsigned int *total_len)
+{
+	struct smb2_sync_pdu *spdu = (struct smb2_sync_pdu *)buf;
+	/* lookup word count ie StructureSize from table */
+	__u16 parmsize = smb2_req_struct_sizes[le16_to_cpu(smb2_command)];
+
+	/*
+	 * smaller than SMALL_BUFFER_SIZE but bigger than fixed area of
+	 * largest operations (Create)
+	 */
+	memset(buf, 0, 256);
+
+	smb2_hdr_assemble(&spdu->sync_hdr, smb2_command, tcon);
+	spdu->StructureSize2 = cpu_to_le16(parmsize);
+
+	*total_len = parmsize + sizeof(struct smb2_sync_hdr);
+}
+
+/* init request without RFC1001 length at the beginning */
+static int
+smb2_plain_req_init(__le16 smb2_command, struct cifs_tcon *tcon,
+		    void **request_buf, unsigned int *total_len)
+{
+	int rc;
+	struct smb2_sync_hdr *shdr;
+
+	rc = smb2_reconnect(smb2_command, tcon);
+	if (rc)
+		return rc;
+
+	/* BB eventually switch this to SMB2 specific small buf size */
+	*request_buf = cifs_small_buf_get();
+	if (*request_buf == NULL) {
+		/* BB should we add a retry in here if not a writepage? */
+		return -ENOMEM;
+	}
+
+	shdr = (struct smb2_sync_hdr *)(*request_buf);
+
+	fill_small_buf(smb2_command, tcon, shdr, total_len);
+
+	if (tcon != NULL) {
+#ifdef CONFIG_CIFS_STATS2
+		uint16_t com_code = le16_to_cpu(smb2_command);
+
+		cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_sent[com_code]);
+#endif
+		cifs_stats_inc(&tcon->num_smbs_sent);
+	}
+
+	return rc;
+}
+
 /*
  * Allocate and return pointer to an SMB request hdr, and set basic
  * SMB information in the SMB header. If the return code is zero, this
- * function must have filled in request_buf pointer.
+ * function must have filled in request_buf pointer. The returned buffer
+ * has RFC1001 length at the beginning.
  */
 static int
 small_smb2_init(__le16 smb2_command, struct cifs_tcon *tcon,
 		void **request_buf)
 {
-	int rc = 0;
+	int rc;
+	unsigned int total_len;
+	struct smb2_pdu *pdu;
 
 	rc = smb2_reconnect(smb2_command, tcon);
 	if (rc)
@@ -311,7 +367,12 @@ small_smb2_init(__le16 smb2_command, struct cifs_tcon *tcon,
 		return -ENOMEM;
 	}
 
-	smb2_hdr_assemble((struct smb2_hdr *) *request_buf, smb2_command, tcon);
+	pdu = (struct smb2_pdu *)(*request_buf);
+
+	fill_small_buf(smb2_command, tcon, get_sync_hdr(pdu), &total_len);
+
+	/* Note this is only network field converted to big endian */
+	pdu->hdr.smb2_buf_length = cpu_to_be32(total_len);
 
 	if (tcon != NULL) {
 #ifdef CONFIG_CIFS_STATS2
@@ -376,7 +437,6 @@ static void assemble_neg_contexts(struct smb2_negotiate_req *req)
 }
 #endif /* SMB311 */
 
-
 /*
  *
  *	SMB2 Worker functions follow:
@@ -398,6 +458,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	struct smb2_negotiate_req *req;
 	struct smb2_negotiate_rsp *rsp;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 	int rc = 0;
 	int resp_buftype;
 	struct TCP_Server_Info *server = ses->server;
@@ -416,7 +477,7 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	if (rc)
 		return rc;
 
-	req->hdr.SessionId = 0;
+	req->hdr.sync_hdr.SessionId = 0;
 
 	req->Dialects[0] = cpu_to_le16(ses->server->vals->protocol_id);
 
@@ -446,9 +507,9 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	/* 4 for rfc1002 length field */
 	iov[0].iov_len = get_rfc1002_length(req) + 4;
 
-	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, flags);
-
-	rsp = (struct smb2_negotiate_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_negotiate_rsp *)rsp_iov.iov_base;
 	/*
 	 * No tcon so can't do
 	 * cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_fail[SMB2...]);
@@ -502,8 +563,10 @@ SMB2_negotiate(const unsigned int xid, struct cifs_ses *ses)
 	 * but for time being this is our only auth choice so doesn't matter.
 	 * We just found a server which sets blob length to zero expecting raw.
 	 */
-	if (blob_length == 0)
+	if (blob_length == 0) {
 		cifs_dbg(FYI, "missing security blob on negprot\n");
+		server->sec_ntlmssp = true;
+	}
 
 	rc = cifs_enable_signing(server, ses->sign);
 	if (rc)
@@ -560,6 +623,7 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
 
 	rc = SMB2_ioctl(xid, tcon, NO_FILE_ID, NO_FILE_ID,
 		FSCTL_VALIDATE_NEGOTIATE_INFO, true /* is_fsctl */,
+		false /* use_ipc */,
 		(char *)&vneg_inbuf, sizeof(struct validate_negotiate_info_req),
 		(char **)&pneg_rsp, &rsplen);
 
@@ -569,8 +633,12 @@ int smb3_validate_negotiate(const unsigned int xid, struct cifs_tcon *tcon)
 	}
 
 	if (rsplen != sizeof(struct validate_negotiate_info_rsp)) {
-		cifs_dbg(VFS, "invalid size of protocol negotiate response\n");
-		return -EIO;
+		cifs_dbg(VFS, "invalid protocol negotiate response size: %d\n",
+			 rsplen);
+
+		/* relax check since Mac returns max bufsize allowed on ioctl */
+		if (rsplen > CIFSMaxBufSize)
+			return -EIO;
 	}
 
 	/* check validate negotiate info response matches what we got earlier */
@@ -596,6 +664,28 @@ vneg_out:
 	return -EIO;
 }
 
+enum securityEnum
+smb2_select_sectype(struct TCP_Server_Info *server, enum securityEnum requested)
+{
+	switch (requested) {
+	case Kerberos:
+	case RawNTLMSSP:
+		return requested;
+	case NTLMv2:
+		return RawNTLMSSP;
+	case Unspecified:
+		if (server->sec_ntlmssp &&
+			(global_secflags & CIFSSEC_MAY_NTLMSSP))
+			return RawNTLMSSP;
+		if ((server->sec_kerberos || server->sec_mskerberos) &&
+			(global_secflags & CIFSSEC_MAY_KRB5))
+			return Kerberos;
+		/* Fallthrough */
+	default:
+		return Unspecified;
+	}
+}
+
 struct SMB2_sess_data {
 	unsigned int xid;
 	struct cifs_ses *ses;
@@ -627,14 +717,15 @@ SMB2_sess_alloc_buffer(struct SMB2_sess_data *sess_data)
 	if (rc)
 		return rc;
 
-	req->hdr.SessionId = 0; /* First session, not a reauthenticate */
+	/* First session, not a reauthenticate */
+	req->hdr.sync_hdr.SessionId = 0;
 
 	/* if reconnect, we need to send previous sess id, otherwise it is 0 */
 	req->PreviousSessionId = sess_data->previous_session;
 
 	req->Flags = 0; /* MBZ */
 	/* to enable echos and oplocks */
-	req->hdr.CreditRequest = cpu_to_le16(3);
+	req->hdr.sync_hdr.CreditRequest = cpu_to_le16(3);
 
 	/* only one of SMB2 signing flags may be set in SMB2 request */
 	if (server->sign)
@@ -671,6 +762,7 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data)
 {
 	int rc;
 	struct smb2_sess_setup_req *req = sess_data->iov[0].iov_base;
+	struct kvec rsp_iov = { NULL, 0 };
 
 	/* Testing shows that buffer offset must be at location of Buffer[0] */
 	req->SecurityBufferOffset =
@@ -685,7 +777,9 @@ SMB2_sess_sendreceive(struct SMB2_sess_data *sess_data)
 	rc = SendReceive2(sess_data->xid, sess_data->ses,
 				sess_data->iov, 2,
 				&sess_data->buf0_type,
-				CIFS_LOG_ERROR | CIFS_NEG_OP);
+				CIFS_LOG_ERROR | CIFS_NEG_OP, &rsp_iov);
+	cifs_small_buf_release(sess_data->iov[0].iov_base);
+	memcpy(&sess_data->iov[0], &rsp_iov, sizeof(struct kvec));
 
 	return rc;
 }
@@ -697,15 +791,13 @@ SMB2_sess_establish_session(struct SMB2_sess_data *sess_data)
 	struct cifs_ses *ses = sess_data->ses;
 
 	mutex_lock(&ses->server->srv_mutex);
-	if (ses->server->sign && ses->server->ops->generate_signingkey) {
+	if (ses->server->ops->generate_signingkey) {
 		rc = ses->server->ops->generate_signingkey(ses);
-		kfree(ses->auth_key.response);
-		ses->auth_key.response = NULL;
 		if (rc) {
 			cifs_dbg(FYI,
 				"SMB3 session key generation failed\n");
 			mutex_unlock(&ses->server->srv_mutex);
-			goto keygen_exit;
+			return rc;
 		}
 	}
 	if (!ses->server->session_estab) {
@@ -719,12 +811,6 @@ SMB2_sess_establish_session(struct SMB2_sess_data *sess_data)
 	ses->status = CifsGood;
 	ses->need_reconnect = false;
 	spin_unlock(&GlobalMid_Lock);
-
-keygen_exit:
-	if (!ses->server->sign) {
-		kfree(ses->auth_key.response);
-		ses->auth_key.response = NULL;
-	}
 	return rc;
 }
 
@@ -781,11 +867,9 @@ SMB2_auth_kerberos(struct SMB2_sess_data *sess_data)
 		goto out_put_spnego_key;
 
 	rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
-	ses->Suid = rsp->hdr.SessionId;
+	ses->Suid = rsp->hdr.sync_hdr.SessionId;
 
 	ses->session_flags = le16_to_cpu(rsp->SessionFlags);
-	if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
-		cifs_dbg(VFS, "SMB3 encryption not supported yet\n");
 
 	rc = SMB2_sess_establish_session(sess_data);
 out_put_spnego_key:
@@ -859,7 +943,7 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
 
 	/* If true, rc here is expected and not an error */
 	if (sess_data->buf0_type != CIFS_NO_BUFFER &&
-		rsp->hdr.Status == STATUS_MORE_PROCESSING_REQUIRED)
+		rsp->hdr.sync_hdr.Status == STATUS_MORE_PROCESSING_REQUIRED)
 		rc = 0;
 
 	if (rc)
@@ -880,10 +964,8 @@ SMB2_sess_auth_rawntlmssp_negotiate(struct SMB2_sess_data *sess_data)
 	cifs_dbg(FYI, "rawntlmssp session setup challenge phase\n");
 
 
-	ses->Suid = rsp->hdr.SessionId;
+	ses->Suid = rsp->hdr.sync_hdr.SessionId;
 	ses->session_flags = le16_to_cpu(rsp->SessionFlags);
-	if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
-		cifs_dbg(VFS, "SMB3 encryption not supported yet\n");
 
 out:
 	kfree(ntlmssp_blob);
@@ -916,7 +998,7 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data)
 		goto out;
 
 	req = (struct smb2_sess_setup_req *) sess_data->iov[0].iov_base;
-	req->hdr.SessionId = ses->Suid;
+	req->hdr.sync_hdr.SessionId = ses->Suid;
 
 	rc = build_ntlmssp_auth_blob(&ntlmssp_blob, &blob_length, ses,
 					sess_data->nls_cp);
@@ -940,10 +1022,8 @@ SMB2_sess_auth_rawntlmssp_authenticate(struct SMB2_sess_data *sess_data)
 
 	rsp = (struct smb2_sess_setup_rsp *)sess_data->iov[0].iov_base;
 
-	ses->Suid = rsp->hdr.SessionId;
+	ses->Suid = rsp->hdr.sync_hdr.SessionId;
 	ses->session_flags = le16_to_cpu(rsp->SessionFlags);
-	if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
-		cifs_dbg(VFS, "SMB3 encryption not supported yet\n");
 
 	rc = SMB2_sess_establish_session(sess_data);
 out:
@@ -958,10 +1038,17 @@ out:
 static int
 SMB2_select_sec(struct cifs_ses *ses, struct SMB2_sess_data *sess_data)
 {
-	if (ses->sectype != Kerberos && ses->sectype != RawNTLMSSP)
-		ses->sectype = RawNTLMSSP;
+	int type;
 
-	switch (ses->sectype) {
+	type = smb2_select_sectype(ses->server, ses->sectype);
+	cifs_dbg(FYI, "sess setup type %d\n", type);
+	if (type == Unspecified) {
+		cifs_dbg(VFS,
+			"Unable to select appropriate authentication method!");
+		return -EINVAL;
+	}
+
+	switch (type) {
 	case Kerberos:
 		sess_data->func = SMB2_auth_kerberos;
 		break;
@@ -969,7 +1056,7 @@ SMB2_select_sec(struct cifs_ses *ses, struct SMB2_sess_data *sess_data)
 		sess_data->func = SMB2_sess_auth_rawntlmssp_negotiate;
 		break;
 	default:
-		cifs_dbg(VFS, "secType %d not supported!\n", ses->sectype);
+		cifs_dbg(VFS, "secType %d not supported!\n", type);
 		return -EOPNOTSUPP;
 	}
 
@@ -1018,6 +1105,7 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses)
 	struct smb2_logoff_req *req; /* response is also trivial struct */
 	int rc = 0;
 	struct TCP_Server_Info *server;
+	int flags = 0;
 
 	cifs_dbg(FYI, "disconnect session %p\n", ses);
 
@@ -1035,11 +1123,15 @@ SMB2_logoff(const unsigned int xid, struct cifs_ses *ses)
 		return rc;
 
 	 /* since no tcon, smb2_init can not do this, so do here */
-	req->hdr.SessionId = ses->Suid;
-	if (server->sign)
-		req->hdr.Flags |= SMB2_FLAGS_SIGNED;
+	req->hdr.sync_hdr.SessionId = ses->Suid;
+
+	if (ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA)
+		flags |= CIFS_TRANSFORM_REQ;
+	else if (server->sign)
+		req->hdr.sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
 
-	rc = SendReceiveNoRsp(xid, ses, (char *) &req->hdr, 0);
+	rc = SendReceiveNoRsp(xid, ses, (char *) req, flags);
+	cifs_small_buf_release(req);
 	/*
 	 * No tcon so can't do
 	 * cifs_stats_inc(&tcon->stats.smb2_stats.smb2_com_fail[SMB2...]);
@@ -1071,28 +1163,18 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	struct smb2_tree_connect_req *req;
 	struct smb2_tree_connect_rsp *rsp = NULL;
 	struct kvec iov[2];
+	struct kvec rsp_iov;
 	int rc = 0;
 	int resp_buftype;
 	int unc_path_len;
-	struct TCP_Server_Info *server;
 	__le16 *unc_path = NULL;
+	int flags = 0;
 
 	cifs_dbg(FYI, "TCON\n");
 
-	if ((ses->server) && tree)
-		server = ses->server;
-	else
+	if (!(ses->server) || !tree)
 		return -EIO;
 
-	if (tcon && tcon->bad_network_name)
-		return -ENOENT;
-
-	if ((tcon && tcon->seal) &&
-	    ((ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION) == 0)) {
-		cifs_dbg(VFS, "encryption requested but no server support");
-		return -EOPNOTSUPP;
-	}
-
 	unc_path = kmalloc(MAX_SHARENAME_LENGTH * 2, GFP_KERNEL);
 	if (unc_path == NULL)
 		return -ENOMEM;
@@ -1104,6 +1186,10 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 		return -EINVAL;
 	}
 
+	/* SMB2 TREE_CONNECT request must be called with TreeId == 0 */
+	if (tcon)
+		tcon->tid = 0;
+
 	rc = small_smb2_init(SMB2_TREE_CONNECT, tcon, (void **) &req);
 	if (rc) {
 		kfree(unc_path);
@@ -1111,11 +1197,15 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	}
 
 	if (tcon == NULL) {
+		if ((ses->session_flags & SMB2_SESSION_FLAG_ENCRYPT_DATA))
+			flags |= CIFS_TRANSFORM_REQ;
+
 		/* since no tcon, smb2_init can not do this, so do here */
-		req->hdr.SessionId = ses->Suid;
-		/* if (ses->server->sec_mode & SECMODE_SIGN_REQUIRED)
-			req->hdr.Flags |= SMB2_FLAGS_SIGNED; */
-	}
+		req->hdr.sync_hdr.SessionId = ses->Suid;
+		if (ses->server->sign)
+			req->hdr.sync_hdr.Flags |= SMB2_FLAGS_SIGNED;
+	} else if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
 
 	iov[0].iov_base = (char *)req;
 	/* 4 for rfc1002 length field and 1 for pad */
@@ -1130,8 +1220,9 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 
 	inc_rfc1001_len(req, unc_path_len - 1 /* pad */);
 
-	rc = SendReceive2(xid, ses, iov, 2, &resp_buftype, 0);
-	rsp = (struct smb2_tree_connect_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, 2, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_tree_connect_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
 		if (tcon) {
@@ -1142,19 +1233,23 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	}
 
 	if (tcon == NULL) {
-		ses->ipc_tid = rsp->hdr.TreeId;
+		ses->ipc_tid = rsp->hdr.sync_hdr.TreeId;
 		goto tcon_exit;
 	}
 
-	if (rsp->ShareType & SMB2_SHARE_TYPE_DISK)
+	switch (rsp->ShareType) {
+	case SMB2_SHARE_TYPE_DISK:
 		cifs_dbg(FYI, "connection to disk share\n");
-	else if (rsp->ShareType & SMB2_SHARE_TYPE_PIPE) {
+		break;
+	case SMB2_SHARE_TYPE_PIPE:
 		tcon->ipc = true;
 		cifs_dbg(FYI, "connection to pipe share\n");
-	} else if (rsp->ShareType & SMB2_SHARE_TYPE_PRINT) {
-		tcon->print = true;
+		break;
+	case SMB2_SHARE_TYPE_PRINT:
+		tcon->ipc = true;
 		cifs_dbg(FYI, "connection to printer\n");
-	} else {
+		break;
+	default:
 		cifs_dbg(VFS, "unknown share type %d\n", rsp->ShareType);
 		rc = -EOPNOTSUPP;
 		goto tcon_error_exit;
@@ -1165,15 +1260,18 @@ SMB2_tcon(const unsigned int xid, struct cifs_ses *ses, const char *tree,
 	tcon->maximal_access = le32_to_cpu(rsp->MaximalAccess);
 	tcon->tidStatus = CifsGood;
 	tcon->need_reconnect = false;
-	tcon->tid = rsp->hdr.TreeId;
+	tcon->tid = rsp->hdr.sync_hdr.TreeId;
 	strlcpy(tcon->treeName, tree, sizeof(tcon->treeName));
 
 	if ((rsp->Capabilities & SMB2_SHARE_CAP_DFS) &&
 	    ((tcon->share_flags & SHI1005_FLAGS_DFS) == 0))
 		cifs_dbg(VFS, "DFS capability contradicts DFS flag\n");
+
+	if (tcon->seal &&
+	    !(tcon->ses->server->capabilities & SMB2_GLOBAL_CAP_ENCRYPTION))
+		cifs_dbg(VFS, "Encryption is requested but not supported\n");
+
 	init_copy_chunk_defaults(tcon);
-	if (tcon->share_flags & SHI1005_FLAGS_ENCRYPT_DATA)
-		cifs_dbg(VFS, "Encrypted shares not supported");
 	if (tcon->ses->server->ops->validate_negotiate)
 		rc = tcon->ses->server->ops->validate_negotiate(xid, tcon);
 tcon_exit:
@@ -1182,10 +1280,8 @@ tcon_exit:
 	return rc;
 
 tcon_error_exit:
-	if (rsp->hdr.Status == STATUS_BAD_NETWORK_NAME) {
+	if (rsp->hdr.sync_hdr.Status == STATUS_BAD_NETWORK_NAME) {
 		cifs_dbg(VFS, "BAD_NETWORK_NAME: %s\n", tree);
-		if (tcon)
-			tcon->bad_network_name = true;
 	}
 	goto tcon_exit;
 }
@@ -1195,14 +1291,12 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
 {
 	struct smb2_tree_disconnect_req *req; /* response is trivial */
 	int rc = 0;
-	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
+	int flags = 0;
 
 	cifs_dbg(FYI, "Tree Disconnect\n");
 
-	if (ses && (ses->server))
-		server = ses->server;
-	else
+	if (!ses || !(ses->server))
 		return -EIO;
 
 	if ((tcon->need_reconnect) || (tcon->ses->need_reconnect))
@@ -1212,7 +1306,11 @@ SMB2_tdis(const unsigned int xid, struct cifs_tcon *tcon)
 	if (rc)
 		return rc;
 
-	rc = SendReceiveNoRsp(xid, ses, (char *)&req->hdr, 0);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	rc = SendReceiveNoRsp(xid, ses, (char *)req, flags);
+	cifs_small_buf_release(req);
 	if (rc)
 		cifs_stats_fail_inc(tcon, SMB2_TREE_DISCONNECT_HE);
 
@@ -1463,6 +1561,51 @@ add_durable_context(struct kvec *iov, unsigned int *num_iovec,
 	return 0;
 }
 
+static int
+alloc_path_with_tree_prefix(__le16 **out_path, int *out_size, int *out_len,
+			    const char *treename, const __le16 *path)
+{
+	int treename_len, path_len;
+	struct nls_table *cp;
+	const __le16 sep[] = {cpu_to_le16('\\'), cpu_to_le16(0x0000)};
+
+	/*
+	 * skip leading "\\"
+	 */
+	treename_len = strlen(treename);
+	if (treename_len < 2 || !(treename[0] == '\\' && treename[1] == '\\'))
+		return -EINVAL;
+
+	treename += 2;
+	treename_len -= 2;
+
+	path_len = UniStrnlen((wchar_t *)path, PATH_MAX);
+
+	/*
+	 * make room for one path separator between the treename and
+	 * path
+	 */
+	*out_len = treename_len + 1 + path_len;
+
+	/*
+	 * final path needs to be null-terminated UTF16 with a
+	 * size aligned to 8
+	 */
+
+	*out_size = roundup((*out_len+1)*2, 8);
+	*out_path = kzalloc(*out_size, GFP_KERNEL);
+	if (!*out_path)
+		return -ENOMEM;
+
+	cp = load_nls_default();
+	cifs_strtoUTF16(*out_path, treename, treename_len, cp);
+	UniStrcat(*out_path, sep);
+	UniStrcat(*out_path, path);
+	unload_nls(cp);
+
+	return 0;
+}
+
 int
 SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	  __u8 *oplock, struct smb2_file_all_info *buf,
@@ -1474,14 +1617,16 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	struct cifs_tcon *tcon = oparms->tcon;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[4];
+	struct kvec rsp_iov;
 	int resp_buftype;
 	int uni_path_len;
 	__le16 *copy_path = NULL;
 	int copy_size;
 	int rc = 0;
-	unsigned int num_iovecs = 2;
+	unsigned int n_iov = 2;
 	__u32 file_attributes = 0;
 	char *dhc_buf = NULL, *lc_buf = NULL;
+	int flags = 0;
 
 	cifs_dbg(FYI, "create/open\n");
 
@@ -1494,6 +1639,9 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	if (rc)
 		return rc;
 
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	if (oparms->create_options & CREATE_OPTION_READONLY)
 		file_attributes |= ATTR_READONLY;
 	if (oparms->create_options & CREATE_OPTION_SPECIAL)
@@ -1506,30 +1654,49 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	req->ShareAccess = FILE_SHARE_ALL_LE;
 	req->CreateDisposition = cpu_to_le32(oparms->disposition);
 	req->CreateOptions = cpu_to_le32(oparms->create_options & CREATE_OPTIONS_MASK);
-	uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2;
-	/* do not count rfc1001 len field */
-	req->NameOffset = cpu_to_le16(sizeof(struct smb2_create_req) - 4);
 
 	iov[0].iov_base = (char *)req;
 	/* 4 for rfc1002 length field */
 	iov[0].iov_len = get_rfc1002_length(req) + 4;
-
-	/* MUST set path len (NameLength) to 0 opening root of share */
-	req->NameLength = cpu_to_le16(uni_path_len - 2);
 	/* -1 since last byte is buf[0] which is sent below (path) */
 	iov[0].iov_len--;
-	if (uni_path_len % 8 != 0) {
-		copy_size = uni_path_len / 8 * 8;
-		if (copy_size < uni_path_len)
-			copy_size += 8;
-
-		copy_path = kzalloc(copy_size, GFP_KERNEL);
-		if (!copy_path)
-			return -ENOMEM;
-		memcpy((char *)copy_path, (const char *)path,
-			uni_path_len);
+
+	req->NameOffset = cpu_to_le16(sizeof(struct smb2_create_req) - 4);
+
+	/* [MS-SMB2] 2.2.13 NameOffset:
+	 * If SMB2_FLAGS_DFS_OPERATIONS is set in the Flags field of
+	 * the SMB2 header, the file name includes a prefix that will
+	 * be processed during DFS name normalization as specified in
+	 * section 3.3.5.9. Otherwise, the file name is relative to
+	 * the share that is identified by the TreeId in the SMB2
+	 * header.
+	 */
+	if (tcon->share_flags & SHI1005_FLAGS_DFS) {
+		int name_len;
+
+		req->hdr.sync_hdr.Flags |= SMB2_FLAGS_DFS_OPERATIONS;
+		rc = alloc_path_with_tree_prefix(&copy_path, &copy_size,
+						 &name_len,
+						 tcon->treeName, path);
+		if (rc)
+			return rc;
+		req->NameLength = cpu_to_le16(name_len * 2);
 		uni_path_len = copy_size;
 		path = copy_path;
+	} else {
+		uni_path_len = (2 * UniStrnlen((wchar_t *)path, PATH_MAX)) + 2;
+		/* MUST set path len (NameLength) to 0 opening root of share */
+		req->NameLength = cpu_to_le16(uni_path_len - 2);
+		if (uni_path_len % 8 != 0) {
+			copy_size = roundup(uni_path_len, 8);
+			copy_path = kzalloc(copy_size, GFP_KERNEL);
+			if (!copy_path)
+				return -ENOMEM;
+			memcpy((char *)copy_path, (const char *)path,
+			       uni_path_len);
+			uni_path_len = copy_size;
+			path = copy_path;
+		}
 	}
 
 	iov[1].iov_len = uni_path_len;
@@ -1544,25 +1711,25 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 	    *oplock == SMB2_OPLOCK_LEVEL_NONE)
 		req->RequestedOplockLevel = *oplock;
 	else {
-		rc = add_lease_context(server, iov, &num_iovecs, oplock);
+		rc = add_lease_context(server, iov, &n_iov, oplock);
 		if (rc) {
 			cifs_small_buf_release(req);
 			kfree(copy_path);
 			return rc;
 		}
-		lc_buf = iov[num_iovecs-1].iov_base;
+		lc_buf = iov[n_iov-1].iov_base;
 	}
 
 	if (*oplock == SMB2_OPLOCK_LEVEL_BATCH) {
 		/* need to set Next field of lease context if we request it */
 		if (server->capabilities & SMB2_GLOBAL_CAP_LEASING) {
 			struct create_context *ccontext =
-			    (struct create_context *)iov[num_iovecs-1].iov_base;
+			    (struct create_context *)iov[n_iov-1].iov_base;
 			ccontext->Next =
 				cpu_to_le32(server->vals->create_lease_size);
 		}
 
-		rc = add_durable_context(iov, &num_iovecs, oparms,
+		rc = add_durable_context(iov, &n_iov, oparms,
 					tcon->use_persistent);
 		if (rc) {
 			cifs_small_buf_release(req);
@@ -1570,11 +1737,12 @@ SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms, __le16 *path,
 			kfree(lc_buf);
 			return rc;
 		}
-		dhc_buf = iov[num_iovecs-1].iov_base;
+		dhc_buf = iov[n_iov-1].iov_base;
 	}
 
-	rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0);
-	rsp = (struct smb2_create_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, n_iov, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_create_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
 		cifs_stats_fail_inc(tcon, SMB2_CREATE_HE);
@@ -1613,17 +1781,20 @@ creat_exit:
  */
 int
 SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
-	   u64 volatile_fid, u32 opcode, bool is_fsctl, char *in_data,
-	   u32 indatalen, char **out_data, u32 *plen /* returned data len */)
+	   u64 volatile_fid, u32 opcode, bool is_fsctl, bool use_ipc,
+	   char *in_data, u32 indatalen,
+	   char **out_data, u32 *plen /* returned data len */)
 {
 	struct smb2_ioctl_req *req;
 	struct smb2_ioctl_rsp *rsp;
-	struct TCP_Server_Info *server;
+	struct smb2_sync_hdr *shdr;
 	struct cifs_ses *ses;
 	struct kvec iov[2];
+	struct kvec rsp_iov;
 	int resp_buftype;
-	int num_iovecs;
+	int n_iov;
 	int rc = 0;
+	int flags = 0;
 
 	cifs_dbg(FYI, "SMB2 IOCTL\n");
 
@@ -1639,15 +1810,26 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	else
 		return -EIO;
 
-	if (ses && (ses->server))
-		server = ses->server;
-	else
+	if (!ses || !(ses->server))
 		return -EIO;
 
 	rc = small_smb2_init(SMB2_IOCTL, tcon, (void **) &req);
 	if (rc)
 		return rc;
 
+	if (use_ipc) {
+		if (ses->ipc_tid == 0) {
+			cifs_small_buf_release(req);
+			return -ENOTCONN;
+		}
+
+		cifs_dbg(FYI, "replacing tid 0x%x with IPC tid 0x%x\n",
+			 req->hdr.sync_hdr.TreeId, ses->ipc_tid);
+		req->hdr.sync_hdr.TreeId = ses->ipc_tid;
+	}
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	req->CtlCode = cpu_to_le32(opcode);
 	req->PersistentFileId = persistent_fid;
 	req->VolatileFileId = volatile_fid;
@@ -1659,9 +1841,9 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 		       cpu_to_le32(offsetof(struct smb2_ioctl_req, Buffer) - 4);
 		iov[1].iov_base = in_data;
 		iov[1].iov_len = indatalen;
-		num_iovecs = 2;
+		n_iov = 2;
 	} else
-		num_iovecs = 1;
+		n_iov = 1;
 
 	req->OutputOffset = 0;
 	req->OutputCount = 0; /* MBZ */
@@ -1671,8 +1853,12 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	 * than one credit. Windows typically sets this smaller, but for some
 	 * ioctls it may be useful to allow server to send more. No point
 	 * limiting what the server can send as long as fits in one credit
+	 * Unfortunately - we can not handle more than CIFS_MAX_MSG_SIZE
+	 * (by default, note that it can be overridden to make max larger)
+	 * in responses (except for read responses which can be bigger.
+	 * We may want to bump this limit up
 	 */
-	req->MaxOutputResponse = cpu_to_le32(0xFF00); /* < 64K uses 1 credit */
+	req->MaxOutputResponse = cpu_to_le32(CIFSMaxBufSize);
 
 	if (is_fsctl)
 		req->Flags = cpu_to_le32(SMB2_0_IOCTL_IS_FSCTL);
@@ -1698,8 +1884,9 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 		iov[0].iov_len = get_rfc1002_length(req) + 4;
 
 
-	rc = SendReceive2(xid, ses, iov, num_iovecs, &resp_buftype, 0);
-	rsp = (struct smb2_ioctl_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, n_iov, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_ioctl_rsp *)rsp_iov.iov_base;
 
 	if ((rc != 0) && (rc != -EINVAL)) {
 		cifs_stats_fail_inc(tcon, SMB2_IOCTL_HE);
@@ -1742,9 +1929,8 @@ SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 		goto ioctl_exit;
 	}
 
-	memcpy(*out_data,
-	       (char *)&rsp->hdr.ProtocolId + le32_to_cpu(rsp->OutputOffset),
-	       *plen);
+	shdr = get_sync_hdr(rsp);
+	memcpy(*out_data, (char *)shdr + le32_to_cpu(rsp->OutputOffset), *plen);
 ioctl_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
@@ -1767,6 +1953,7 @@ SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 
 	rc = SMB2_ioctl(xid, tcon, persistent_fid, volatile_fid,
 			FSCTL_SET_COMPRESSION, true /* is_fsctl */,
+			false /* use_ipc */,
 			(char *)&fsctl_input /* data input */,
 			2 /* in data len */, &ret_data /* out data */, NULL);
 
@@ -1781,23 +1968,25 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	struct smb2_close_req *req;
 	struct smb2_close_rsp *rsp;
-	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 	int resp_buftype;
 	int rc = 0;
+	int flags = 0;
 
 	cifs_dbg(FYI, "Close\n");
 
-	if (ses && (ses->server))
-		server = ses->server;
-	else
+	if (!ses || !(ses->server))
 		return -EIO;
 
 	rc = small_smb2_init(SMB2_CLOSE, tcon, (void **) &req);
 	if (rc)
 		return rc;
 
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	req->PersistentFileId = persistent_fid;
 	req->VolatileFileId = volatile_fid;
 
@@ -1805,8 +1994,9 @@ SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 	/* 4 for rfc1002 length field */
 	iov[0].iov_len = get_rfc1002_length(req) + 4;
 
-	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, 0);
-	rsp = (struct smb2_close_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_close_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0) {
 		cifs_stats_fail_inc(tcon, SMB2_CLOSE_HE);
@@ -1879,32 +2069,36 @@ validate_and_copy_buf(unsigned int offset, unsigned int buffer_length,
 
 static int
 query_info(const unsigned int xid, struct cifs_tcon *tcon,
-	   u64 persistent_fid, u64 volatile_fid, u8 info_class,
-	   size_t output_len, size_t min_len, void *data)
+	   u64 persistent_fid, u64 volatile_fid, u8 info_class, u8 info_type,
+	   u32 additional_info, size_t output_len, size_t min_len, void **data,
+		u32 *dlen)
 {
 	struct smb2_query_info_req *req;
 	struct smb2_query_info_rsp *rsp = NULL;
 	struct kvec iov[2];
+	struct kvec rsp_iov;
 	int rc = 0;
 	int resp_buftype;
-	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
+	int flags = 0;
 
 	cifs_dbg(FYI, "Query Info\n");
 
-	if (ses && (ses->server))
-		server = ses->server;
-	else
+	if (!ses || !(ses->server))
 		return -EIO;
 
 	rc = small_smb2_init(SMB2_QUERY_INFO, tcon, (void **) &req);
 	if (rc)
 		return rc;
 
-	req->InfoType = SMB2_O_INFO_FILE;
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	req->InfoType = info_type;
 	req->FileInfoClass = info_class;
 	req->PersistentFileId = persistent_fid;
 	req->VolatileFileId = volatile_fid;
+	req->AdditionalInformation = cpu_to_le32(additional_info);
 	/* 4 for rfc1002 length field and 1 for Buffer */
 	req->InputBufferOffset =
 		cpu_to_le16(sizeof(struct smb2_query_info_req) - 1 - 4);
@@ -1914,32 +2108,60 @@ query_info(const unsigned int xid, struct cifs_tcon *tcon,
 	/* 4 for rfc1002 length field */
 	iov[0].iov_len = get_rfc1002_length(req) + 4;
 
-	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, 0);
-	rsp = (struct smb2_query_info_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
 		goto qinf_exit;
 	}
 
+	if (dlen) {
+		*dlen = le32_to_cpu(rsp->OutputBufferLength);
+		if (!*data) {
+			*data = kmalloc(*dlen, GFP_KERNEL);
+			if (!*data) {
+				cifs_dbg(VFS,
+					"Error %d allocating memory for acl\n",
+					rc);
+				*dlen = 0;
+				goto qinf_exit;
+			}
+		}
+	}
+
 	rc = validate_and_copy_buf(le16_to_cpu(rsp->OutputBufferOffset),
 				   le32_to_cpu(rsp->OutputBufferLength),
-				   &rsp->hdr, min_len, data);
+				   &rsp->hdr, min_len, *data);
 
 qinf_exit:
 	free_rsp_buf(resp_buftype, rsp);
 	return rc;
 }
 
+int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
+	u64 persistent_fid, u64 volatile_fid, struct smb2_file_all_info *data)
+{
+	return query_info(xid, tcon, persistent_fid, volatile_fid,
+			  FILE_ALL_INFORMATION, SMB2_O_INFO_FILE, 0,
+			  sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
+			  sizeof(struct smb2_file_all_info), (void **)&data,
+			  NULL);
+}
+
 int
-SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
+SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon,
 		u64 persistent_fid, u64 volatile_fid,
-		struct smb2_file_all_info *data)
+		void **data, u32 *plen)
 {
+	__u32 additional_info = OWNER_SECINFO | GROUP_SECINFO | DACL_SECINFO;
+	*plen = 0;
+
 	return query_info(xid, tcon, persistent_fid, volatile_fid,
-			  FILE_ALL_INFORMATION,
-			  sizeof(struct smb2_file_all_info) + PATH_MAX * 2,
-			  sizeof(struct smb2_file_all_info), data);
+			  0, SMB2_O_INFO_SECURITY, additional_info,
+			  SMB2_MAX_BUFFER_SIZE,
+			  sizeof(struct smb2_file_all_info), data, plen);
 }
 
 int
@@ -1947,9 +2169,10 @@ SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon,
 		 u64 persistent_fid, u64 volatile_fid, __le64 *uniqueid)
 {
 	return query_info(xid, tcon, persistent_fid, volatile_fid,
-			  FILE_INTERNAL_INFORMATION,
+			  FILE_INTERNAL_INFORMATION, SMB2_O_INFO_FILE, 0,
+			  sizeof(struct smb2_file_internal_info),
 			  sizeof(struct smb2_file_internal_info),
-			  sizeof(struct smb2_file_internal_info), uniqueid);
+			  (void **)&uniqueid, NULL);
 }
 
 /*
@@ -1963,15 +2186,13 @@ static void
 smb2_echo_callback(struct mid_q_entry *mid)
 {
 	struct TCP_Server_Info *server = mid->callback_data;
-	struct smb2_echo_rsp *smb2 = (struct smb2_echo_rsp *)mid->resp_buf;
+	struct smb2_echo_rsp *rsp = (struct smb2_echo_rsp *)mid->resp_buf;
 	unsigned int credits_received = 1;
 
 	if (mid->mid_state == MID_RESPONSE_RECEIVED)
-		credits_received = le16_to_cpu(smb2->hdr.CreditRequest);
+		credits_received = le16_to_cpu(rsp->hdr.sync_hdr.CreditRequest);
 
-	mutex_lock(&server->srv_mutex);
 	DeleteMidQEntry(mid);
-	mutex_unlock(&server->srv_mutex);
 	add_credits(server, credits_received, CIFS_ECHO_OP);
 }
 
@@ -1983,6 +2204,9 @@ void smb2_reconnect_server(struct work_struct *work)
 	struct cifs_tcon *tcon, *tcon2;
 	struct list_head tmp_list;
 	int tcon_exist = false;
+	int rc;
+	int resched = false;
+
 
 	/* Prevent simultaneous reconnects that can corrupt tcon->rlist list */
 	mutex_lock(&server->reconnect_mutex);
@@ -2010,13 +2234,18 @@ void smb2_reconnect_server(struct work_struct *work)
 	spin_unlock(&cifs_tcp_ses_lock);
 
 	list_for_each_entry_safe(tcon, tcon2, &tmp_list, rlist) {
-		if (!smb2_reconnect(SMB2_INTERNAL_CMD, tcon))
+		rc = smb2_reconnect(SMB2_INTERNAL_CMD, tcon);
+		if (!rc)
 			cifs_reopen_persistent_handles(tcon);
+		else
+			resched = true;
 		list_del_init(&tcon->rlist);
 		cifs_put_tcon(tcon);
 	}
 
 	cifs_dbg(FYI, "Reconnecting tcons finished\n");
+	if (resched)
+		queue_delayed_work(cifsiod_wq, &server->reconnect, 2 * HZ);
 	mutex_unlock(&server->reconnect_mutex);
 
 	/* now we can safely release srv struct */
@@ -2029,9 +2258,9 @@ SMB2_echo(struct TCP_Server_Info *server)
 {
 	struct smb2_echo_req *req;
 	int rc = 0;
-	struct kvec iov;
-	struct smb_rqst rqst = { .rq_iov = &iov,
-				 .rq_nvec = 1 };
+	struct kvec iov[2];
+	struct smb_rqst rqst = { .rq_iov = iov,
+				 .rq_nvec = 2 };
 
 	cifs_dbg(FYI, "In echo request\n");
 
@@ -2045,14 +2274,16 @@ SMB2_echo(struct TCP_Server_Info *server)
 	if (rc)
 		return rc;
 
-	req->hdr.CreditRequest = cpu_to_le16(1);
+	req->hdr.sync_hdr.CreditRequest = cpu_to_le16(1);
 
-	iov.iov_base = (char *)req;
 	/* 4 for rfc1002 length field */
-	iov.iov_len = get_rfc1002_length(req) + 4;
+	iov[0].iov_len = 4;
+	iov[0].iov_base = (char *)req;
+	iov[1].iov_len = get_rfc1002_length(req);
+	iov[1].iov_base = (char *)req + 4;
 
-	rc = cifs_call_async(server, &rqst, NULL, smb2_echo_callback, server,
-			     CIFS_ECHO_OP);
+	rc = cifs_call_async(server, &rqst, NULL, smb2_echo_callback, NULL,
+			     server, CIFS_ECHO_OP);
 	if (rc)
 		cifs_dbg(FYI, "Echo request failed: %d\n", rc);
 
@@ -2065,23 +2296,25 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	   u64 volatile_fid)
 {
 	struct smb2_flush_req *req;
-	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 	int resp_buftype;
 	int rc = 0;
+	int flags = 0;
 
 	cifs_dbg(FYI, "Flush\n");
 
-	if (ses && (ses->server))
-		server = ses->server;
-	else
+	if (!ses || !(ses->server))
 		return -EIO;
 
 	rc = small_smb2_init(SMB2_FLUSH, tcon, (void **) &req);
 	if (rc)
 		return rc;
 
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	req->PersistentFileId = persistent_fid;
 	req->VolatileFileId = volatile_fid;
 
@@ -2089,12 +2322,13 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 	/* 4 for rfc1002 length field */
 	iov[0].iov_len = get_rfc1002_length(req) + 4;
 
-	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, 0);
+	rc = SendReceive2(xid, ses, iov, 1, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
 
 	if (rc != 0)
 		cifs_stats_fail_inc(tcon, SMB2_FLUSH_HE);
 
-	free_rsp_buf(resp_buftype, iov[0].iov_base);
+	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	return rc;
 }
 
@@ -2103,19 +2337,23 @@ SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
  * have the end_of_chain boolean set to true.
  */
 static int
-smb2_new_read_req(struct kvec *iov, struct cifs_io_parms *io_parms,
-		  unsigned int remaining_bytes, int request_type)
+smb2_new_read_req(void **buf, unsigned int *total_len,
+		  struct cifs_io_parms *io_parms, unsigned int remaining_bytes,
+		  int request_type)
 {
 	int rc = -EACCES;
-	struct smb2_read_req *req = NULL;
+	struct smb2_read_plain_req *req = NULL;
+	struct smb2_sync_hdr *shdr;
 
-	rc = small_smb2_init(SMB2_READ, io_parms->tcon, (void **) &req);
+	rc = smb2_plain_req_init(SMB2_READ, io_parms->tcon, (void **) &req,
+				 total_len);
 	if (rc)
 		return rc;
 	if (io_parms->tcon->ses->server == NULL)
 		return -ECONNABORTED;
 
-	req->hdr.ProcessId = cpu_to_le32(io_parms->pid);
+	shdr = &req->sync_hdr;
+	shdr->ProcessId = cpu_to_le32(io_parms->pid);
 
 	req->PersistentFileId = io_parms->persistent_fid;
 	req->VolatileFileId = io_parms->volatile_fid;
@@ -2128,19 +2366,19 @@ smb2_new_read_req(struct kvec *iov, struct cifs_io_parms *io_parms,
 
 	if (request_type & CHAINED_REQUEST) {
 		if (!(request_type & END_OF_CHAIN)) {
-			/* 4 for rfc1002 length field */
-			req->hdr.NextCommand =
-				cpu_to_le32(get_rfc1002_length(req) + 4);
+			/* next 8-byte aligned request */
+			*total_len = DIV_ROUND_UP(*total_len, 8) * 8;
+			shdr->NextCommand = cpu_to_le32(*total_len);
 		} else /* END_OF_CHAIN */
-			req->hdr.NextCommand = 0;
+			shdr->NextCommand = 0;
 		if (request_type & RELATED_REQUEST) {
-			req->hdr.Flags |= SMB2_FLAGS_RELATED_OPERATIONS;
+			shdr->Flags |= SMB2_FLAGS_RELATED_OPERATIONS;
 			/*
 			 * Related requests use info from previous read request
 			 * in chain.
 			 */
-			req->hdr.SessionId = 0xFFFFFFFF;
-			req->hdr.TreeId = 0xFFFFFFFF;
+			shdr->SessionId = 0xFFFFFFFF;
+			shdr->TreeId = 0xFFFFFFFF;
 			req->PersistentFileId = 0xFFFFFFFF;
 			req->VolatileFileId = 0xFFFFFFFF;
 		}
@@ -2150,9 +2388,7 @@ smb2_new_read_req(struct kvec *iov, struct cifs_io_parms *io_parms,
 	else
 		req->RemainingBytes = 0;
 
-	iov[0].iov_base = (char *)req;
-	/* 4 for rfc1002 length field */
-	iov[0].iov_len = get_rfc1002_length(req) + 4;
+	*buf = req;
 	return rc;
 }
 
@@ -2162,10 +2398,11 @@ smb2_readv_callback(struct mid_q_entry *mid)
 	struct cifs_readdata *rdata = mid->callback_data;
 	struct cifs_tcon *tcon = tlink_tcon(rdata->cfile->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
-	struct smb2_hdr *buf = (struct smb2_hdr *)rdata->iov.iov_base;
+	struct smb2_sync_hdr *shdr =
+				(struct smb2_sync_hdr *)rdata->iov[1].iov_base;
 	unsigned int credits_received = 1;
-	struct smb_rqst rqst = { .rq_iov = &rdata->iov,
-				 .rq_nvec = 1,
+	struct smb_rqst rqst = { .rq_iov = rdata->iov,
+				 .rq_nvec = 2,
 				 .rq_pages = rdata->pages,
 				 .rq_npages = rdata->nr_pages,
 				 .rq_pagesz = rdata->pagesz,
@@ -2177,9 +2414,9 @@ smb2_readv_callback(struct mid_q_entry *mid)
 
 	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
-		credits_received = le16_to_cpu(buf->CreditRequest);
+		credits_received = le16_to_cpu(shdr->CreditRequest);
 		/* result already set, check signature */
-		if (server->sign) {
+		if (server->sign && !mid->decrypted) {
 			int rc;
 
 			rc = smb2_verify_signature(&rqst, server);
@@ -2210,22 +2447,23 @@ smb2_readv_callback(struct mid_q_entry *mid)
 		cifs_stats_fail_inc(tcon, SMB2_READ_HE);
 
 	queue_work(cifsiod_wq, &rdata->work);
-	mutex_lock(&server->srv_mutex);
 	DeleteMidQEntry(mid);
-	mutex_unlock(&server->srv_mutex);
 	add_credits(server, credits_received, 0);
 }
 
-/* smb2_async_readv - send an async write, and set up mid to handle result */
+/* smb2_async_readv - send an async read, and set up mid to handle result */
 int
 smb2_async_readv(struct cifs_readdata *rdata)
 {
 	int rc, flags = 0;
-	struct smb2_hdr *buf;
+	char *buf;
+	struct smb2_sync_hdr *shdr;
 	struct cifs_io_parms io_parms;
-	struct smb_rqst rqst = { .rq_iov = &rdata->iov,
-				 .rq_nvec = 1 };
+	struct smb_rqst rqst = { .rq_iov = rdata->iov,
+				 .rq_nvec = 2 };
 	struct TCP_Server_Info *server;
+	unsigned int total_len;
+	__be32 req_len;
 
 	cifs_dbg(FYI, "%s: offset=%llu bytes=%u\n",
 		 __func__, rdata->offset, rdata->bytes);
@@ -2239,7 +2477,7 @@ smb2_async_readv(struct cifs_readdata *rdata)
 
 	server = io_parms.tcon->ses->server;
 
-	rc = smb2_new_read_req(&rdata->iov, &io_parms, 0, 0);
+	rc = smb2_new_read_req((void **) &buf, &total_len, &io_parms, 0, 0);
 	if (rc) {
 		if (rc == -EAGAIN && rdata->credits) {
 			/* credits was reset by reconnect */
@@ -2252,26 +2490,34 @@ smb2_async_readv(struct cifs_readdata *rdata)
 		return rc;
 	}
 
-	buf = (struct smb2_hdr *)rdata->iov.iov_base;
-	/* 4 for rfc1002 length field */
-	rdata->iov.iov_len = get_rfc1002_length(rdata->iov.iov_base) + 4;
+	if (encryption_required(io_parms.tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	req_len = cpu_to_be32(total_len);
+
+	rdata->iov[0].iov_base = &req_len;
+	rdata->iov[0].iov_len = sizeof(__be32);
+	rdata->iov[1].iov_base = buf;
+	rdata->iov[1].iov_len = total_len;
+
+	shdr = (struct smb2_sync_hdr *)buf;
 
 	if (rdata->credits) {
-		buf->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes,
+		shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(rdata->bytes,
 						SMB2_MAX_BUFFER_SIZE));
-		buf->CreditRequest = buf->CreditCharge;
+		shdr->CreditRequest = shdr->CreditCharge;
 		spin_lock(&server->req_lock);
 		server->credits += rdata->credits -
-						le16_to_cpu(buf->CreditCharge);
+						le16_to_cpu(shdr->CreditCharge);
 		spin_unlock(&server->req_lock);
 		wake_up(&server->request_q);
-		flags = CIFS_HAS_CREDITS;
+		flags |= CIFS_HAS_CREDITS;
 	}
 
 	kref_get(&rdata->refcount);
 	rc = cifs_call_async(io_parms.tcon->ses->server, &rqst,
 			     cifs_readv_receive, smb2_readv_callback,
-			     rdata, flags);
+			     smb3_handle_read_data, rdata, flags);
 	if (rc) {
 		kref_put(&rdata->refcount, cifs_readdata_release);
 		cifs_stats_fail_inc(io_parms.tcon, SMB2_READ_HE);
@@ -2286,21 +2532,41 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 	  unsigned int *nbytes, char **buf, int *buf_type)
 {
 	int resp_buftype, rc = -EACCES;
+	struct smb2_read_plain_req *req = NULL;
 	struct smb2_read_rsp *rsp = NULL;
-	struct kvec iov[1];
+	struct smb2_sync_hdr *shdr;
+	struct kvec iov[2];
+	struct kvec rsp_iov;
+	unsigned int total_len;
+	__be32 req_len;
+	struct smb_rqst rqst = { .rq_iov = iov,
+				 .rq_nvec = 2 };
+	int flags = CIFS_LOG_ERROR;
+	struct cifs_ses *ses = io_parms->tcon->ses;
 
 	*nbytes = 0;
-	rc = smb2_new_read_req(iov, io_parms, 0, 0);
+	rc = smb2_new_read_req((void **)&req, &total_len, io_parms, 0, 0);
 	if (rc)
 		return rc;
 
-	rc = SendReceive2(xid, io_parms->tcon->ses, iov, 1,
-			  &resp_buftype, CIFS_LOG_ERROR);
+	if (encryption_required(io_parms->tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	req_len = cpu_to_be32(total_len);
 
-	rsp = (struct smb2_read_rsp *)iov[0].iov_base;
+	iov[0].iov_base = &req_len;
+	iov[0].iov_len = sizeof(__be32);
+	iov[1].iov_base = req;
+	iov[1].iov_len = total_len;
+
+	rc = cifs_send_recv(xid, ses, &rqst, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
 
-	if (rsp->hdr.Status == STATUS_END_OF_FILE) {
-		free_rsp_buf(resp_buftype, iov[0].iov_base);
+	rsp = (struct smb2_read_rsp *)rsp_iov.iov_base;
+	shdr = get_sync_hdr(rsp);
+
+	if (shdr->Status == STATUS_END_OF_FILE) {
+		free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 		return 0;
 	}
 
@@ -2319,11 +2585,10 @@ SMB2_read(const unsigned int xid, struct cifs_io_parms *io_parms,
 	}
 
 	if (*buf) {
-		memcpy(*buf, (char *)&rsp->hdr.ProtocolId + rsp->DataOffset,
-		       *nbytes);
-		free_rsp_buf(resp_buftype, iov[0].iov_base);
+		memcpy(*buf, (char *)shdr + rsp->DataOffset, *nbytes);
+		free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	} else if (resp_buftype != CIFS_NO_BUFFER) {
-		*buf = iov[0].iov_base;
+		*buf = rsp_iov.iov_base;
 		if (resp_buftype == CIFS_SMALL_BUFFER)
 			*buf_type = CIFS_SMALL_BUFFER;
 		else if (resp_buftype == CIFS_LARGE_BUFFER)
@@ -2341,14 +2606,13 @@ smb2_writev_callback(struct mid_q_entry *mid)
 {
 	struct cifs_writedata *wdata = mid->callback_data;
 	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
-	struct TCP_Server_Info *server = tcon->ses->server;
 	unsigned int written;
 	struct smb2_write_rsp *rsp = (struct smb2_write_rsp *)mid->resp_buf;
 	unsigned int credits_received = 1;
 
 	switch (mid->mid_state) {
 	case MID_RESPONSE_RECEIVED:
-		credits_received = le16_to_cpu(rsp->hdr.CreditRequest);
+		credits_received = le16_to_cpu(rsp->hdr.sync_hdr.CreditRequest);
 		wdata->result = smb2_check_receive(mid, tcon->ses->server, 0);
 		if (wdata->result != 0)
 			break;
@@ -2381,9 +2645,7 @@ smb2_writev_callback(struct mid_q_entry *mid)
 		cifs_stats_fail_inc(tcon, SMB2_WRITE_HE);
 
 	queue_work(cifsiod_wq, &wdata->work);
-	mutex_lock(&server->srv_mutex);
 	DeleteMidQEntry(mid);
-	mutex_unlock(&server->srv_mutex);
 	add_credits(tcon->ses->server, credits_received, 0);
 }
 
@@ -2394,10 +2656,11 @@ smb2_async_writev(struct cifs_writedata *wdata,
 {
 	int rc = -EACCES, flags = 0;
 	struct smb2_write_req *req = NULL;
+	struct smb2_sync_hdr *shdr;
 	struct cifs_tcon *tcon = tlink_tcon(wdata->cfile->tlink);
 	struct TCP_Server_Info *server = tcon->ses->server;
-	struct kvec iov;
-	struct smb_rqst rqst;
+	struct kvec iov[2];
+	struct smb_rqst rqst = { };
 
 	rc = small_smb2_init(SMB2_WRITE, tcon, (void **) &req);
 	if (rc) {
@@ -2412,7 +2675,11 @@ smb2_async_writev(struct cifs_writedata *wdata,
 		goto async_writev_out;
 	}
 
-	req->hdr.ProcessId = cpu_to_le32(wdata->cfile->pid);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	shdr = get_sync_hdr(req);
+	shdr->ProcessId = cpu_to_le32(wdata->cfile->pid);
 
 	req->PersistentFileId = wdata->cfile->fid.persistent_fid;
 	req->VolatileFileId = wdata->cfile->fid.volatile_fid;
@@ -2426,11 +2693,13 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	req->RemainingBytes = 0;
 
 	/* 4 for rfc1002 length field and 1 for Buffer */
-	iov.iov_len = get_rfc1002_length(req) + 4 - 1;
-	iov.iov_base = req;
+	iov[0].iov_len = 4;
+	iov[0].iov_base = req;
+	iov[1].iov_len = get_rfc1002_length(req) - 1;
+	iov[1].iov_base = (char *)req + 4;
 
-	rqst.rq_iov = &iov;
-	rqst.rq_nvec = 1;
+	rqst.rq_iov = iov;
+	rqst.rq_nvec = 2;
 	rqst.rq_pages = wdata->pages;
 	rqst.rq_npages = wdata->nr_pages;
 	rqst.rq_pagesz = wdata->pagesz;
@@ -2444,20 +2713,20 @@ smb2_async_writev(struct cifs_writedata *wdata,
 	inc_rfc1001_len(&req->hdr, wdata->bytes - 1 /* Buffer */);
 
 	if (wdata->credits) {
-		req->hdr.CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes,
+		shdr->CreditCharge = cpu_to_le16(DIV_ROUND_UP(wdata->bytes,
 						    SMB2_MAX_BUFFER_SIZE));
-		req->hdr.CreditRequest = req->hdr.CreditCharge;
+		shdr->CreditRequest = shdr->CreditCharge;
 		spin_lock(&server->req_lock);
 		server->credits += wdata->credits -
-					le16_to_cpu(req->hdr.CreditCharge);
+						le16_to_cpu(shdr->CreditCharge);
 		spin_unlock(&server->req_lock);
 		wake_up(&server->request_q);
-		flags = CIFS_HAS_CREDITS;
+		flags |= CIFS_HAS_CREDITS;
 	}
 
 	kref_get(&wdata->refcount);
-	rc = cifs_call_async(server, &rqst, NULL, smb2_writev_callback, wdata,
-			     flags);
+	rc = cifs_call_async(server, &rqst, NULL, smb2_writev_callback, NULL,
+			     wdata, flags);
 
 	if (rc) {
 		kref_put(&wdata->refcount, release);
@@ -2483,6 +2752,9 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 	struct smb2_write_req *req = NULL;
 	struct smb2_write_rsp *rsp = NULL;
 	int resp_buftype;
+	struct kvec rsp_iov;
+	int flags = 0;
+
 	*nbytes = 0;
 
 	if (n_vec < 1)
@@ -2495,7 +2767,10 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 	if (io_parms->tcon->ses->server == NULL)
 		return -ECONNABORTED;
 
-	req->hdr.ProcessId = cpu_to_le32(io_parms->pid);
+	if (encryption_required(io_parms->tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	req->hdr.sync_hdr.ProcessId = cpu_to_le32(io_parms->pid);
 
 	req->PersistentFileId = io_parms->persistent_fid;
 	req->VolatileFileId = io_parms->volatile_fid;
@@ -2517,8 +2792,9 @@ SMB2_write(const unsigned int xid, struct cifs_io_parms *io_parms,
 	inc_rfc1001_len(req, io_parms->length - 1 /* Buffer */);
 
 	rc = SendReceive2(xid, io_parms->tcon->ses, iov, n_vec + 1,
-			  &resp_buftype, 0);
-	rsp = (struct smb2_write_rsp *)iov[0].iov_base;
+			  &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_write_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
 		cifs_stats_fail_inc(io_parms->tcon, SMB2_WRITE_HE);
@@ -2581,6 +2857,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	struct smb2_query_directory_req *req;
 	struct smb2_query_directory_rsp *rsp = NULL;
 	struct kvec iov[2];
+	struct kvec rsp_iov;
 	int rc = 0;
 	int len;
 	int resp_buftype = CIFS_NO_BUFFER;
@@ -2591,6 +2868,7 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	char *end_of_smb;
 	unsigned int output_size = CIFSMaxBufSize;
 	size_t info_buf_size;
+	int flags = 0;
 
 	if (ses && (ses->server))
 		server = ses->server;
@@ -2601,6 +2879,9 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	switch (srch_inf->info_level) {
 	case SMB_FIND_FILE_DIRECTORY_INFO:
 		req->FileInformationClass = FILE_DIRECTORY_INFORMATION;
@@ -2645,11 +2926,13 @@ SMB2_query_directory(const unsigned int xid, struct cifs_tcon *tcon,
 
 	inc_rfc1001_len(req, len - 1 /* Buffer */);
 
-	rc = SendReceive2(xid, ses, iov, 2, &resp_buftype, 0);
-	rsp = (struct smb2_query_directory_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, 2, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_query_directory_rsp *)rsp_iov.iov_base;
 
 	if (rc) {
-		if (rc == -ENODATA && rsp->hdr.Status == STATUS_NO_MORE_FILES) {
+		if (rc == -ENODATA &&
+		    rsp->hdr.sync_hdr.Status == STATUS_NO_MORE_FILES) {
 			srch_inf->endOfSearch = true;
 			rc = 0;
 		}
@@ -2699,21 +2982,21 @@ qdir_exit:
 
 static int
 send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
-	       u64 persistent_fid, u64 volatile_fid, u32 pid, int info_class,
-	       unsigned int num, void **data, unsigned int *size)
+	       u64 persistent_fid, u64 volatile_fid, u32 pid, u8 info_class,
+	       u8 info_type, u32 additional_info, unsigned int num,
+		void **data, unsigned int *size)
 {
 	struct smb2_set_info_req *req;
 	struct smb2_set_info_rsp *rsp = NULL;
 	struct kvec *iov;
+	struct kvec rsp_iov;
 	int rc = 0;
 	int resp_buftype;
 	unsigned int i;
-	struct TCP_Server_Info *server;
 	struct cifs_ses *ses = tcon->ses;
+	int flags = 0;
 
-	if (ses && (ses->server))
-		server = ses->server;
-	else
+	if (!ses || !(ses->server))
 		return -EIO;
 
 	if (!num)
@@ -2729,12 +3012,16 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 		return rc;
 	}
 
-	req->hdr.ProcessId = cpu_to_le32(pid);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	req->hdr.sync_hdr.ProcessId = cpu_to_le32(pid);
 
-	req->InfoType = SMB2_O_INFO_FILE;
+	req->InfoType = info_type;
 	req->FileInfoClass = info_class;
 	req->PersistentFileId = persistent_fid;
 	req->VolatileFileId = volatile_fid;
+	req->AdditionalInformation = cpu_to_le32(additional_info);
 
 	/* 4 for RFC1001 length and 1 for Buffer */
 	req->BufferOffset =
@@ -2756,8 +3043,9 @@ send_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 		iov[i].iov_len = size[i];
 	}
 
-	rc = SendReceive2(xid, ses, iov, num, &resp_buftype, 0);
-	rsp = (struct smb2_set_info_rsp *)iov[0].iov_base;
+	rc = SendReceive2(xid, ses, iov, num, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(req);
+	rsp = (struct smb2_set_info_rsp *)rsp_iov.iov_base;
 
 	if (rc != 0)
 		cifs_stats_fail_inc(tcon, SMB2_SET_INFO_HE);
@@ -2793,8 +3081,8 @@ SMB2_rename(const unsigned int xid, struct cifs_tcon *tcon,
 	size[1] = len + 2 /* null */;
 
 	rc = send_set_info(xid, tcon, persistent_fid, volatile_fid,
-			   current->tgid, FILE_RENAME_INFORMATION, 2, data,
-			   size);
+		current->tgid, FILE_RENAME_INFORMATION, SMB2_O_INFO_FILE,
+		0, 2, data, size);
 	kfree(data);
 	return rc;
 }
@@ -2811,8 +3099,8 @@ SMB2_rmdir(const unsigned int xid, struct cifs_tcon *tcon,
 	size = 1; /* sizeof __u8 */
 
 	return send_set_info(xid, tcon, persistent_fid, volatile_fid,
-			current->tgid, FILE_DISPOSITION_INFORMATION, 1, &data,
-			&size);
+		current->tgid, FILE_DISPOSITION_INFORMATION, SMB2_O_INFO_FILE,
+		0, 1, &data, &size);
 }
 
 int
@@ -2841,7 +3129,8 @@ SMB2_set_hardlink(const unsigned int xid, struct cifs_tcon *tcon,
 	size[1] = len + 2 /* null */;
 
 	rc = send_set_info(xid, tcon, persistent_fid, volatile_fid,
-			   current->tgid, FILE_LINK_INFORMATION, 2, data, size);
+			current->tgid, FILE_LINK_INFORMATION, SMB2_O_INFO_FILE,
+			0, 2, data, size);
 	kfree(data);
 	return rc;
 }
@@ -2861,10 +3150,12 @@ SMB2_set_eof(const unsigned int xid, struct cifs_tcon *tcon, u64 persistent_fid,
 
 	if (is_falloc)
 		return send_set_info(xid, tcon, persistent_fid, volatile_fid,
-			pid, FILE_ALLOCATION_INFORMATION, 1, &data, &size);
+			pid, FILE_ALLOCATION_INFORMATION, SMB2_O_INFO_FILE,
+			0, 1, &data, &size);
 	else
 		return send_set_info(xid, tcon, persistent_fid, volatile_fid,
-			pid, FILE_END_OF_FILE_INFORMATION, 1, &data, &size);
+			pid, FILE_END_OF_FILE_INFORMATION, SMB2_O_INFO_FILE,
+			0, 1, &data, &size);
 }
 
 int
@@ -2874,8 +3165,18 @@ SMB2_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 	unsigned int size;
 	size = sizeof(FILE_BASIC_INFO);
 	return send_set_info(xid, tcon, persistent_fid, volatile_fid,
-			     current->tgid, FILE_BASIC_INFORMATION, 1,
-			     (void **)&buf, &size);
+		current->tgid, FILE_BASIC_INFORMATION, SMB2_O_INFO_FILE,
+		0, 1, (void **)&buf, &size);
+}
+
+int
+SMB2_set_acl(const unsigned int xid, struct cifs_tcon *tcon,
+		u64 persistent_fid, u64 volatile_fid,
+		struct cifs_ntsd *pnntsd, int pacllen, int aclflag)
+{
+	return send_set_info(xid, tcon, persistent_fid, volatile_fid,
+			current->tgid, 0, SMB2_O_INFO_SECURITY, aclflag,
+			1, (void **)&pnntsd, &pacllen);
 }
 
 int
@@ -2885,20 +3186,23 @@ SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	int rc;
 	struct smb2_oplock_break *req = NULL;
+	int flags = CIFS_OBREAK_OP;
 
 	cifs_dbg(FYI, "SMB2_oplock_break\n");
 	rc = small_smb2_init(SMB2_OPLOCK_BREAK, tcon, (void **) &req);
-
 	if (rc)
 		return rc;
 
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
 	req->VolatileFid = volatile_fid;
 	req->PersistentFid = persistent_fid;
 	req->OplockLevel = oplock_level;
-	req->hdr.CreditRequest = cpu_to_le16(1);
+	req->hdr.sync_hdr.CreditRequest = cpu_to_le16(1);
 
-	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) req, CIFS_OBREAK_OP);
-	/* SMB2 buffer freed by function above */
+	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) req, flags);
+	cifs_small_buf_release(req);
 
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE);
@@ -2958,10 +3262,12 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	struct smb2_query_info_rsp *rsp = NULL;
 	struct kvec iov;
+	struct kvec rsp_iov;
 	int rc = 0;
 	int resp_buftype;
 	struct cifs_ses *ses = tcon->ses;
 	struct smb2_fs_full_size_info *info = NULL;
+	int flags = 0;
 
 	rc = build_qfs_info_req(&iov, tcon, FS_FULL_SIZE_INFORMATION,
 				sizeof(struct smb2_fs_full_size_info),
@@ -2969,12 +3275,16 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	rc = SendReceive2(xid, ses, &iov, 1, &resp_buftype, 0);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	rc = SendReceive2(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(iov.iov_base);
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
 		goto qfsinf_exit;
 	}
-	rsp = (struct smb2_query_info_rsp *)iov.iov_base;
+	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
 
 	info = (struct smb2_fs_full_size_info *)(4 /* RFC1001 len */ +
 		le16_to_cpu(rsp->OutputBufferOffset) + (char *)&rsp->hdr);
@@ -2985,7 +3295,7 @@ SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 		copy_fs_info_to_kstatfs(info, fsdata);
 
 qfsinf_exit:
-	free_rsp_buf(resp_buftype, iov.iov_base);
+	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	return rc;
 }
 
@@ -2995,10 +3305,12 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	struct smb2_query_info_rsp *rsp = NULL;
 	struct kvec iov;
+	struct kvec rsp_iov;
 	int rc = 0;
 	int resp_buftype, max_len, min_len;
 	struct cifs_ses *ses = tcon->ses;
 	unsigned int rsp_len, offset;
+	int flags = 0;
 
 	if (level == FS_DEVICE_INFORMATION) {
 		max_len = sizeof(FILE_SYSTEM_DEVICE_INFO);
@@ -3019,12 +3331,16 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	rc = SendReceive2(xid, ses, &iov, 1, &resp_buftype, 0);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	rc = SendReceive2(xid, ses, &iov, 1, &resp_buftype, flags, &rsp_iov);
+	cifs_small_buf_release(iov.iov_base);
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_QUERY_INFO_HE);
 		goto qfsattr_exit;
 	}
-	rsp = (struct smb2_query_info_rsp *)iov.iov_base;
+	rsp = (struct smb2_query_info_rsp *)rsp_iov.iov_base;
 
 	rsp_len = le32_to_cpu(rsp->OutputBufferLength);
 	offset = le16_to_cpu(rsp->OutputBufferOffset);
@@ -3048,7 +3364,7 @@ SMB2_QFS_attr(const unsigned int xid, struct cifs_tcon *tcon,
 	}
 
 qfsattr_exit:
-	free_rsp_buf(resp_buftype, iov.iov_base);
+	free_rsp_buf(resp_buftype, rsp_iov.iov_base);
 	return rc;
 }
 
@@ -3060,8 +3376,10 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	int rc = 0;
 	struct smb2_lock_req *req = NULL;
 	struct kvec iov[2];
+	struct kvec rsp_iov;
 	int resp_buf_type;
 	unsigned int count;
+	int flags = CIFS_NO_RESP;
 
 	cifs_dbg(FYI, "smb2_lockv num lock %d\n", num_lock);
 
@@ -3069,7 +3387,10 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	if (rc)
 		return rc;
 
-	req->hdr.ProcessId = cpu_to_le32(pid);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	req->hdr.sync_hdr.ProcessId = cpu_to_le32(pid);
 	req->LockCount = cpu_to_le16(num_lock);
 
 	req->PersistentFileId = persist_fid;
@@ -3085,7 +3406,9 @@ smb2_lockv(const unsigned int xid, struct cifs_tcon *tcon,
 	iov[1].iov_len = count;
 
 	cifs_stats_inc(&tcon->stats.cifs_stats.num_locks);
-	rc = SendReceive2(xid, tcon->ses, iov, 2, &resp_buf_type, CIFS_NO_RESP);
+	rc = SendReceive2(xid, tcon->ses, iov, 2, &resp_buf_type, flags,
+			  &rsp_iov);
+	cifs_small_buf_release(req);
 	if (rc) {
 		cifs_dbg(FYI, "Send error in smb2_lockv = %d\n", rc);
 		cifs_stats_fail_inc(tcon, SMB2_LOCK_HE);
@@ -3117,22 +3440,25 @@ SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
 {
 	int rc;
 	struct smb2_lease_ack *req = NULL;
+	int flags = CIFS_OBREAK_OP;
 
 	cifs_dbg(FYI, "SMB2_lease_break\n");
 	rc = small_smb2_init(SMB2_OPLOCK_BREAK, tcon, (void **) &req);
-
 	if (rc)
 		return rc;
 
-	req->hdr.CreditRequest = cpu_to_le16(1);
+	if (encryption_required(tcon))
+		flags |= CIFS_TRANSFORM_REQ;
+
+	req->hdr.sync_hdr.CreditRequest = cpu_to_le16(1);
 	req->StructureSize = cpu_to_le16(36);
 	inc_rfc1001_len(req, 12);
 
 	memcpy(req->LeaseKey, lease_key, 16);
 	req->LeaseState = lease_state;
 
-	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) req, CIFS_OBREAK_OP);
-	/* SMB2 buffer freed by function above */
+	rc = SendReceiveNoRsp(xid, tcon->ses, (char *) req, flags);
+	cifs_small_buf_release(req);
 
 	if (rc) {
 		cifs_stats_fail_inc(tcon, SMB2_OPLOCK_BREAK_HE);
diff --git a/fs/cifs/smb2pdu.h b/fs/cifs/smb2pdu.h
index dc0d141f33e2..18700fd25a0b 100644
--- a/fs/cifs/smb2pdu.h
+++ b/fs/cifs/smb2pdu.h
@@ -101,10 +101,7 @@
 
 #define SMB2_HEADER_STRUCTURE_SIZE cpu_to_le16(64)
 
-struct smb2_hdr {
-	__be32 smb2_buf_length;	/* big endian on wire */
-				/* length is only two or three bytes - with
-				 one or two byte type preceding it that MBZ */
+struct smb2_sync_hdr {
 	__le32 ProtocolId;	/* 0xFE 'S' 'M' 'B' */
 	__le16 StructureSize;	/* 64 */
 	__le16 CreditCharge;	/* MBZ */
@@ -120,16 +117,31 @@ struct smb2_hdr {
 	__u8   Signature[16];
 } __packed;
 
+struct smb2_sync_pdu {
+	struct smb2_sync_hdr sync_hdr;
+	__le16 StructureSize2; /* size of wct area (varies, request specific) */
+} __packed;
+
+struct smb2_hdr {
+	__be32 smb2_buf_length;	/* big endian on wire */
+				/* length is only two or three bytes - with */
+				/* one or two byte type preceding it that MBZ */
+	struct smb2_sync_hdr sync_hdr;
+} __packed;
+
 struct smb2_pdu {
 	struct smb2_hdr hdr;
 	__le16 StructureSize2; /* size of wct area (varies, request specific) */
 } __packed;
 
+#define SMB3_AES128CMM_NONCE 11
+#define SMB3_AES128GCM_NONCE 12
+
 struct smb2_transform_hdr {
 	__be32 smb2_buf_length;	/* big endian on wire */
 				/* length is only two or three bytes - with
 				 one or two byte type preceding it that MBZ */
-	__u8   ProtocolId[4];	/* 0xFD 'S' 'M' 'B' */
+	__le32 ProtocolId;	/* 0xFD 'S' 'M' 'B' */
 	__u8   Signature[16];
 	__u8   Nonce[16];
 	__le32 OriginalMessageSize;
@@ -683,6 +695,14 @@ struct fsctl_get_integrity_information_rsp {
 /* Integrity flags for above */
 #define FSCTL_INTEGRITY_FLAG_CHECKSUM_ENFORCEMENT_OFF	0x00000001
 
+/* See MS-DFSC 2.2.2 */
+struct fsctl_get_dfs_referral_req {
+	__le16 MaxReferralLevel;
+	__u8 RequestFileName[];
+} __packed;
+
+/* DFS response is struct get_dfs_refer_rsp */
+
 /* See MS-SMB2 2.2.31.3 */
 struct network_resiliency_req {
 	__le32 Timeout;
@@ -814,8 +834,9 @@ struct smb2_flush_rsp {
 #define SMB2_CHANNEL_RDMA_V1		0x00000001 /* SMB3 or later */
 #define SMB2_CHANNEL_RDMA_V1_INVALIDATE 0x00000001 /* SMB3.02 or later */
 
-struct smb2_read_req {
-	struct smb2_hdr hdr;
+/* SMB2 read request without RFC1001 length at the beginning */
+struct smb2_read_plain_req {
+	struct smb2_sync_hdr sync_hdr;
 	__le16 StructureSize; /* Must be 49 */
 	__u8   Padding; /* offset from start of SMB2 header to place read */
 	__u8   Flags; /* MBZ unless SMB3.02 or later */
diff --git a/fs/cifs/smb2proto.h b/fs/cifs/smb2proto.h
index f2d511a6971b..1cadaf9f3c58 100644
--- a/fs/cifs/smb2proto.h
+++ b/fs/cifs/smb2proto.h
@@ -48,6 +48,10 @@ extern struct mid_q_entry *smb2_setup_request(struct cifs_ses *ses,
 			      struct smb_rqst *rqst);
 extern struct mid_q_entry *smb2_setup_async_request(
 			struct TCP_Server_Info *server, struct smb_rqst *rqst);
+extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
+					   __u64 ses_id);
+extern struct cifs_tcon *smb2_find_smb_tcon(struct TCP_Server_Info *server,
+						__u64 ses_id, __u32  tid);
 extern int smb2_calc_signature(struct smb_rqst *rqst,
 				struct TCP_Server_Info *server);
 extern int smb3_calc_signature(struct smb_rqst *rqst,
@@ -56,6 +60,10 @@ extern void smb2_echo_request(struct work_struct *work);
 extern __le32 smb2_get_lease_state(struct cifsInodeInfo *cinode);
 extern bool smb2_is_valid_oplock_break(char *buffer,
 				       struct TCP_Server_Info *srv);
+extern struct cifs_ses *smb2_find_smb_ses(struct TCP_Server_Info *server,
+					  __u64 ses_id);
+extern int smb3_handle_read_data(struct TCP_Server_Info *server,
+				 struct mid_q_entry *mid);
 
 extern void move_smb2_info_to_cifs(FILE_ALL_INFO *dst,
 				   struct smb2_file_all_info *src);
@@ -97,6 +105,7 @@ extern int smb2_unlock_range(struct cifsFileInfo *cfile,
 			     struct file_lock *flock, const unsigned int xid);
 extern int smb2_push_mandatory_locks(struct cifsFileInfo *cfile);
 extern void smb2_reconnect_server(struct work_struct *work);
+extern int smb3_crypto_aead_allocate(struct TCP_Server_Info *server);
 
 /*
  * SMB2 Worker functions - most of protocol specific implementation details
@@ -116,7 +125,8 @@ extern int SMB2_open(const unsigned int xid, struct cifs_open_parms *oparms,
 		     struct smb2_err_rsp **err_buf);
 extern int SMB2_ioctl(const unsigned int xid, struct cifs_tcon *tcon,
 		     u64 persistent_fid, u64 volatile_fid, u32 opcode,
-		     bool is_fsctl, char *in_data, u32 indatalen,
+		     bool is_fsctl, bool use_ipc,
+		     char *in_data, u32 indatalen,
 		     char **out_data, u32 *plen /* returned data len */);
 extern int SMB2_close(const unsigned int xid, struct cifs_tcon *tcon,
 		      u64 persistent_file_id, u64 volatile_file_id);
@@ -125,6 +135,9 @@ extern int SMB2_flush(const unsigned int xid, struct cifs_tcon *tcon,
 extern int SMB2_query_info(const unsigned int xid, struct cifs_tcon *tcon,
 			   u64 persistent_file_id, u64 volatile_file_id,
 			   struct smb2_file_all_info *data);
+extern int SMB2_query_acl(const unsigned int xid, struct cifs_tcon *tcon,
+			   u64 persistent_file_id, u64 volatile_file_id,
+			   void **data, unsigned int *plen);
 extern int SMB2_get_srv_num(const unsigned int xid, struct cifs_tcon *tcon,
 			    u64 persistent_fid, u64 volatile_fid,
 			    __le64 *uniqueid);
@@ -153,11 +166,17 @@ extern int SMB2_set_eof(const unsigned int xid, struct cifs_tcon *tcon,
 extern int SMB2_set_info(const unsigned int xid, struct cifs_tcon *tcon,
 			 u64 persistent_fid, u64 volatile_fid,
 			 FILE_BASIC_INFO *buf);
+extern int SMB2_set_acl(const unsigned int xid, struct cifs_tcon *tcon,
+			u64 persistent_fid, u64 volatile_fid,
+			struct cifs_ntsd *pnntsd, int pacllen, int aclflag);
 extern int SMB2_set_compression(const unsigned int xid, struct cifs_tcon *tcon,
 				u64 persistent_fid, u64 volatile_fid);
 extern int SMB2_oplock_break(const unsigned int xid, struct cifs_tcon *tcon,
 			     const u64 persistent_fid, const u64 volatile_fid,
 			     const __u8 oplock_level);
+extern int smb2_handle_cancelled_mid(char *buffer,
+					struct TCP_Server_Info *server);
+void smb2_cancelled_close_fid(struct work_struct *work);
 extern int SMB2_QFS_info(const unsigned int xid, struct cifs_tcon *tcon,
 			 u64 persistent_file_id, u64 volatile_file_id,
 			 struct kstatfs *FSData);
@@ -175,4 +194,6 @@ extern int SMB2_lease_break(const unsigned int xid, struct cifs_tcon *tcon,
 			    __u8 *lease_key, const __le32 lease_state);
 extern int smb3_validate_negotiate(const unsigned int, struct cifs_tcon *);
 
+extern enum securityEnum smb2_select_sectype(struct TCP_Server_Info *,
+					enum securityEnum);
 #endif			/* _SMB2PROTO_H */
diff --git a/fs/cifs/smb2transport.c b/fs/cifs/smb2transport.c
index bc9a7b634643..67367cf1f8cd 100644
--- a/fs/cifs/smb2transport.c
+++ b/fs/cifs/smb2transport.c
@@ -31,6 +31,7 @@
 #include <asm/processor.h>
 #include <linux/mempool.h>
 #include <linux/highmem.h>
+#include <crypto/aead.h>
 #include "smb2pdu.h"
 #include "cifsglob.h"
 #include "cifsproto.h"
@@ -115,22 +116,68 @@ smb3_crypto_shash_allocate(struct TCP_Server_Info *server)
 }
 
 static struct cifs_ses *
-smb2_find_smb_ses(struct smb2_hdr *smb2hdr, struct TCP_Server_Info *server)
+smb2_find_smb_ses_unlocked(struct TCP_Server_Info *server, __u64 ses_id)
 {
 	struct cifs_ses *ses;
 
-	spin_lock(&cifs_tcp_ses_lock);
 	list_for_each_entry(ses, &server->smb_ses_list, smb_ses_list) {
-		if (ses->Suid != smb2hdr->SessionId)
+		if (ses->Suid != ses_id)
 			continue;
-		spin_unlock(&cifs_tcp_ses_lock);
 		return ses;
 	}
+
+	return NULL;
+}
+
+struct cifs_ses *
+smb2_find_smb_ses(struct TCP_Server_Info *server, __u64 ses_id)
+{
+	struct cifs_ses *ses;
+
+	spin_lock(&cifs_tcp_ses_lock);
+	ses = smb2_find_smb_ses_unlocked(server, ses_id);
 	spin_unlock(&cifs_tcp_ses_lock);
 
+	return ses;
+}
+
+static struct cifs_tcon *
+smb2_find_smb_sess_tcon_unlocked(struct cifs_ses *ses, __u32  tid)
+{
+	struct cifs_tcon *tcon;
+
+	list_for_each_entry(tcon, &ses->tcon_list, tcon_list) {
+		if (tcon->tid != tid)
+			continue;
+		++tcon->tc_count;
+		return tcon;
+	}
+
 	return NULL;
 }
 
+/*
+ * Obtain tcon corresponding to the tid in the given
+ * cifs_ses
+ */
+
+struct cifs_tcon *
+smb2_find_smb_tcon(struct TCP_Server_Info *server, __u64 ses_id, __u32  tid)
+{
+	struct cifs_ses *ses;
+	struct cifs_tcon *tcon;
+
+	spin_lock(&cifs_tcp_ses_lock);
+	ses = smb2_find_smb_ses_unlocked(server, ses_id);
+	if (!ses) {
+		spin_unlock(&cifs_tcp_ses_lock);
+		return NULL;
+	}
+	tcon = smb2_find_smb_sess_tcon_unlocked(ses, tid);
+	spin_unlock(&cifs_tcp_ses_lock);
+
+	return tcon;
+}
 
 int
 smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
@@ -139,17 +186,17 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	unsigned char smb2_signature[SMB2_HMACSHA256_SIZE];
 	unsigned char *sigptr = smb2_signature;
 	struct kvec *iov = rqst->rq_iov;
-	struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base;
+	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[1].iov_base;
 	struct cifs_ses *ses;
 
-	ses = smb2_find_smb_ses(smb2_pdu, server);
+	ses = smb2_find_smb_ses(server, shdr->SessionId);
 	if (!ses) {
 		cifs_dbg(VFS, "%s: Could not find session\n", __func__);
 		return 0;
 	}
 
 	memset(smb2_signature, 0x0, SMB2_HMACSHA256_SIZE);
-	memset(smb2_pdu->Signature, 0x0, SMB2_SIGNATURE_SIZE);
+	memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE);
 
 	rc = smb2_crypto_shash_allocate(server);
 	if (rc) {
@@ -174,7 +221,7 @@ smb2_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 		&server->secmech.sdeschmacsha256->shash);
 
 	if (!rc)
-		memcpy(smb2_pdu->Signature, sigptr, SMB2_SIGNATURE_SIZE);
+		memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE);
 
 	return rc;
 }
@@ -288,9 +335,31 @@ generate_smb3signingkey(struct cifs_ses *ses,
 	if (rc)
 		return rc;
 
-	return generate_key(ses, ptriplet->decryption.label,
-			    ptriplet->decryption.context,
-			    ses->smb3decryptionkey, SMB3_SIGN_KEY_SIZE);
+	rc = generate_key(ses, ptriplet->decryption.label,
+			  ptriplet->decryption.context,
+			  ses->smb3decryptionkey, SMB3_SIGN_KEY_SIZE);
+
+	if (rc)
+		return rc;
+
+#ifdef CONFIG_CIFS_DEBUG_DUMP_KEYS
+	cifs_dbg(VFS, "%s: dumping generated AES session keys\n", __func__);
+	/*
+	 * The session id is opaque in terms of endianness, so we can't
+	 * print it as a long long. we dump it as we got it on the wire
+	 */
+	cifs_dbg(VFS, "Session Id    %*ph\n", (int)sizeof(ses->Suid),
+			&ses->Suid);
+	cifs_dbg(VFS, "Session Key   %*ph\n",
+		 SMB2_NTLMV2_SESSKEY_SIZE, ses->auth_key.response);
+	cifs_dbg(VFS, "Signing Key   %*ph\n",
+		 SMB3_SIGN_KEY_SIZE, ses->smb3signingkey);
+	cifs_dbg(VFS, "ServerIn Key  %*ph\n",
+		 SMB3_SIGN_KEY_SIZE, ses->smb3encryptionkey);
+	cifs_dbg(VFS, "ServerOut Key %*ph\n",
+		 SMB3_SIGN_KEY_SIZE, ses->smb3decryptionkey);
+#endif
+	return rc;
 }
 
 int
@@ -356,17 +425,17 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	unsigned char smb3_signature[SMB2_CMACAES_SIZE];
 	unsigned char *sigptr = smb3_signature;
 	struct kvec *iov = rqst->rq_iov;
-	struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)iov[0].iov_base;
+	struct smb2_sync_hdr *shdr = (struct smb2_sync_hdr *)iov[1].iov_base;
 	struct cifs_ses *ses;
 
-	ses = smb2_find_smb_ses(smb2_pdu, server);
+	ses = smb2_find_smb_ses(server, shdr->SessionId);
 	if (!ses) {
 		cifs_dbg(VFS, "%s: Could not find session\n", __func__);
 		return 0;
 	}
 
 	memset(smb3_signature, 0x0, SMB2_CMACAES_SIZE);
-	memset(smb2_pdu->Signature, 0x0, SMB2_SIGNATURE_SIZE);
+	memset(shdr->Signature, 0x0, SMB2_SIGNATURE_SIZE);
 
 	rc = crypto_shash_setkey(server->secmech.cmacaes,
 		ses->smb3signingkey, SMB2_CMACAES_SIZE);
@@ -391,7 +460,7 @@ smb3_calc_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 				   &server->secmech.sdesccmacaes->shash);
 
 	if (!rc)
-		memcpy(smb2_pdu->Signature, sigptr, SMB2_SIGNATURE_SIZE);
+		memcpy(shdr->Signature, sigptr, SMB2_SIGNATURE_SIZE);
 
 	return rc;
 }
@@ -401,14 +470,15 @@ static int
 smb2_sign_rqst(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 {
 	int rc = 0;
-	struct smb2_hdr *smb2_pdu = rqst->rq_iov[0].iov_base;
+	struct smb2_sync_hdr *shdr =
+			(struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
 
-	if (!(smb2_pdu->Flags & SMB2_FLAGS_SIGNED) ||
+	if (!(shdr->Flags & SMB2_FLAGS_SIGNED) ||
 	    server->tcpStatus == CifsNeedNegotiate)
 		return rc;
 
 	if (!server->session_estab) {
-		strncpy(smb2_pdu->Signature, "BSRSPYL", 8);
+		strncpy(shdr->Signature, "BSRSPYL", 8);
 		return rc;
 	}
 
@@ -422,11 +492,12 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 {
 	unsigned int rc;
 	char server_response_sig[16];
-	struct smb2_hdr *smb2_pdu = (struct smb2_hdr *)rqst->rq_iov[0].iov_base;
+	struct smb2_sync_hdr *shdr =
+			(struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
 
-	if ((smb2_pdu->Command == SMB2_NEGOTIATE) ||
-	    (smb2_pdu->Command == SMB2_SESSION_SETUP) ||
-	    (smb2_pdu->Command == SMB2_OPLOCK_BREAK) ||
+	if ((shdr->Command == SMB2_NEGOTIATE) ||
+	    (shdr->Command == SMB2_SESSION_SETUP) ||
+	    (shdr->Command == SMB2_OPLOCK_BREAK) ||
 	    (!server->session_estab))
 		return 0;
 
@@ -436,17 +507,17 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	 */
 
 	/* Do not need to verify session setups with signature "BSRSPYL " */
-	if (memcmp(smb2_pdu->Signature, "BSRSPYL ", 8) == 0)
+	if (memcmp(shdr->Signature, "BSRSPYL ", 8) == 0)
 		cifs_dbg(FYI, "dummy signature received for smb command 0x%x\n",
-			 smb2_pdu->Command);
+			 shdr->Command);
 
 	/*
 	 * Save off the origiginal signature so we can modify the smb and check
 	 * our calculated signature against what the server sent.
 	 */
-	memcpy(server_response_sig, smb2_pdu->Signature, SMB2_SIGNATURE_SIZE);
+	memcpy(server_response_sig, shdr->Signature, SMB2_SIGNATURE_SIZE);
 
-	memset(smb2_pdu->Signature, 0, SMB2_SIGNATURE_SIZE);
+	memset(shdr->Signature, 0, SMB2_SIGNATURE_SIZE);
 
 	mutex_lock(&server->srv_mutex);
 	rc = server->ops->calc_signature(rqst, server);
@@ -455,8 +526,7 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
 	if (rc)
 		return rc;
 
-	if (memcmp(server_response_sig, smb2_pdu->Signature,
-		   SMB2_SIGNATURE_SIZE))
+	if (memcmp(server_response_sig, shdr->Signature, SMB2_SIGNATURE_SIZE))
 		return -EACCES;
 	else
 		return 0;
@@ -467,18 +537,19 @@ smb2_verify_signature(struct smb_rqst *rqst, struct TCP_Server_Info *server)
  * and when srv_mutex is held.
  */
 static inline void
-smb2_seq_num_into_buf(struct TCP_Server_Info *server, struct smb2_hdr *hdr)
+smb2_seq_num_into_buf(struct TCP_Server_Info *server,
+		      struct smb2_sync_hdr *shdr)
 {
-	unsigned int i, num = le16_to_cpu(hdr->CreditCharge);
+	unsigned int i, num = le16_to_cpu(shdr->CreditCharge);
 
-	hdr->MessageId = get_next_mid64(server);
+	shdr->MessageId = get_next_mid64(server);
 	/* skip message numbers according to CreditCharge field */
 	for (i = 1; i < num; i++)
 		get_next_mid(server);
 }
 
 static struct mid_q_entry *
-smb2_mid_entry_alloc(const struct smb2_hdr *smb_buffer,
+smb2_mid_entry_alloc(const struct smb2_sync_hdr *shdr,
 		     struct TCP_Server_Info *server)
 {
 	struct mid_q_entry *temp;
@@ -489,23 +560,19 @@ smb2_mid_entry_alloc(const struct smb2_hdr *smb_buffer,
 	}
 
 	temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
-	if (temp == NULL)
-		return temp;
-	else {
-		memset(temp, 0, sizeof(struct mid_q_entry));
-		temp->mid = le64_to_cpu(smb_buffer->MessageId);
-		temp->pid = current->pid;
-		temp->command = smb_buffer->Command;	/* Always LE */
-		temp->when_alloc = jiffies;
-		temp->server = server;
-
-		/*
-		 * The default is for the mid to be synchronous, so the
-		 * default callback just wakes up the current task.
-		 */
-		temp->callback = cifs_wake_up_task;
-		temp->callback_data = current;
-	}
+	memset(temp, 0, sizeof(struct mid_q_entry));
+	temp->mid = le64_to_cpu(shdr->MessageId);
+	temp->pid = current->pid;
+	temp->command = shdr->Command; /* Always LE */
+	temp->when_alloc = jiffies;
+	temp->server = server;
+
+	/*
+	 * The default is for the mid to be synchronous, so the
+	 * default callback just wakes up the current task.
+	 */
+	temp->callback = cifs_wake_up_task;
+	temp->callback_data = current;
 
 	atomic_inc(&midCount);
 	temp->mid_state = MID_REQUEST_ALLOCATED;
@@ -513,7 +580,7 @@ smb2_mid_entry_alloc(const struct smb2_hdr *smb_buffer,
 }
 
 static int
-smb2_get_mid_entry(struct cifs_ses *ses, struct smb2_hdr *buf,
+smb2_get_mid_entry(struct cifs_ses *ses, struct smb2_sync_hdr *shdr,
 		   struct mid_q_entry **mid)
 {
 	if (ses->server->tcpStatus == CifsExiting)
@@ -525,19 +592,19 @@ smb2_get_mid_entry(struct cifs_ses *ses, struct smb2_hdr *buf,
 	}
 
 	if (ses->status == CifsNew) {
-		if ((buf->Command != SMB2_SESSION_SETUP) &&
-		    (buf->Command != SMB2_NEGOTIATE))
+		if ((shdr->Command != SMB2_SESSION_SETUP) &&
+		    (shdr->Command != SMB2_NEGOTIATE))
 			return -EAGAIN;
 		/* else ok - we are setting up session */
 	}
 
 	if (ses->status == CifsExiting) {
-		if (buf->Command != SMB2_LOGOFF)
+		if (shdr->Command != SMB2_LOGOFF)
 			return -EAGAIN;
 		/* else ok - we are shutting down the session */
 	}
 
-	*mid = smb2_mid_entry_alloc(buf, ses->server);
+	*mid = smb2_mid_entry_alloc(shdr, ses->server);
 	if (*mid == NULL)
 		return -ENOMEM;
 	spin_lock(&GlobalMid_Lock);
@@ -551,16 +618,18 @@ smb2_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server,
 		   bool log_error)
 {
 	unsigned int len = get_rfc1002_length(mid->resp_buf);
-	struct kvec iov;
-	struct smb_rqst rqst = { .rq_iov = &iov,
-				 .rq_nvec = 1 };
+	struct kvec iov[2];
+	struct smb_rqst rqst = { .rq_iov = iov,
+				 .rq_nvec = 2 };
 
-	iov.iov_base = (char *)mid->resp_buf;
-	iov.iov_len = get_rfc1002_length(mid->resp_buf) + 4;
+	iov[0].iov_base = (char *)mid->resp_buf;
+	iov[0].iov_len = 4;
+	iov[1].iov_base = (char *)mid->resp_buf + 4;
+	iov[1].iov_len = len;
 
 	dump_smb(mid->resp_buf, min_t(u32, 80, len));
 	/* convert the length into a more usable form */
-	if (len > 24 && server->sign) {
+	if (len > 24 && server->sign && !mid->decrypted) {
 		int rc;
 
 		rc = smb2_verify_signature(&rqst, server);
@@ -576,12 +645,13 @@ struct mid_q_entry *
 smb2_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
 {
 	int rc;
-	struct smb2_hdr *hdr = (struct smb2_hdr *)rqst->rq_iov[0].iov_base;
+	struct smb2_sync_hdr *shdr =
+			(struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
 	struct mid_q_entry *mid;
 
-	smb2_seq_num_into_buf(ses->server, hdr);
+	smb2_seq_num_into_buf(ses->server, shdr);
 
-	rc = smb2_get_mid_entry(ses, hdr, &mid);
+	rc = smb2_get_mid_entry(ses, shdr, &mid);
 	if (rc)
 		return ERR_PTR(rc);
 	rc = smb2_sign_rqst(rqst, ses->server);
@@ -596,12 +666,13 @@ struct mid_q_entry *
 smb2_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 {
 	int rc;
-	struct smb2_hdr *hdr = (struct smb2_hdr *)rqst->rq_iov[0].iov_base;
+	struct smb2_sync_hdr *shdr =
+			(struct smb2_sync_hdr *)rqst->rq_iov[1].iov_base;
 	struct mid_q_entry *mid;
 
-	smb2_seq_num_into_buf(server, hdr);
+	smb2_seq_num_into_buf(server, shdr);
 
-	mid = smb2_mid_entry_alloc(hdr, server);
+	mid = smb2_mid_entry_alloc(shdr, server);
 	if (mid == NULL)
 		return ERR_PTR(-ENOMEM);
 
@@ -613,3 +684,33 @@ smb2_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 
 	return mid;
 }
+
+int
+smb3_crypto_aead_allocate(struct TCP_Server_Info *server)
+{
+	struct crypto_aead *tfm;
+
+	if (!server->secmech.ccmaesencrypt) {
+		tfm = crypto_alloc_aead("ccm(aes)", 0, 0);
+		if (IS_ERR(tfm)) {
+			cifs_dbg(VFS, "%s: Failed to alloc encrypt aead\n",
+				 __func__);
+			return PTR_ERR(tfm);
+		}
+		server->secmech.ccmaesencrypt = tfm;
+	}
+
+	if (!server->secmech.ccmaesdecrypt) {
+		tfm = crypto_alloc_aead("ccm(aes)", 0, 0);
+		if (IS_ERR(tfm)) {
+			crypto_free_aead(server->secmech.ccmaesencrypt);
+			server->secmech.ccmaesencrypt = NULL;
+			cifs_dbg(VFS, "%s: Failed to alloc decrypt aead\n",
+				 __func__);
+			return PTR_ERR(tfm);
+		}
+		server->secmech.ccmaesdecrypt = tfm;
+	}
+
+	return 0;
+}
diff --git a/fs/cifs/transport.c b/fs/cifs/transport.c
index fbb84c08e3cd..7efbab013957 100644
--- a/fs/cifs/transport.c
+++ b/fs/cifs/transport.c
@@ -55,26 +55,22 @@ AllocMidQEntry(const struct smb_hdr *smb_buffer, struct TCP_Server_Info *server)
 	}
 
 	temp = mempool_alloc(cifs_mid_poolp, GFP_NOFS);
-	if (temp == NULL)
-		return temp;
-	else {
-		memset(temp, 0, sizeof(struct mid_q_entry));
-		temp->mid = get_mid(smb_buffer);
-		temp->pid = current->pid;
-		temp->command = cpu_to_le16(smb_buffer->Command);
-		cifs_dbg(FYI, "For smb_command %d\n", smb_buffer->Command);
+	memset(temp, 0, sizeof(struct mid_q_entry));
+	temp->mid = get_mid(smb_buffer);
+	temp->pid = current->pid;
+	temp->command = cpu_to_le16(smb_buffer->Command);
+	cifs_dbg(FYI, "For smb_command %d\n", smb_buffer->Command);
 	/*	do_gettimeofday(&temp->when_sent);*/ /* easier to use jiffies */
-		/* when mid allocated can be before when sent */
-		temp->when_alloc = jiffies;
-		temp->server = server;
+	/* when mid allocated can be before when sent */
+	temp->when_alloc = jiffies;
+	temp->server = server;
 
-		/*
-		 * The default is for the mid to be synchronous, so the
-		 * default callback just wakes up the current task.
-		 */
-		temp->callback = cifs_wake_up_task;
-		temp->callback_data = current;
-	}
+	/*
+	 * The default is for the mid to be synchronous, so the
+	 * default callback just wakes up the current task.
+	 */
+	temp->callback = cifs_wake_up_task;
+	temp->callback_data = current;
 
 	atomic_inc(&midCount);
 	temp->mid_state = MID_REQUEST_ALLOCATED;
@@ -98,7 +94,7 @@ DeleteMidQEntry(struct mid_q_entry *midEntry)
 	now = jiffies;
 	/* commands taking longer than one second are indications that
 	   something is wrong, unless it is quite a slow link or server */
-	if ((now - midEntry->when_alloc) > HZ) {
+	if (time_after(now, midEntry->when_alloc + HZ)) {
 		if ((cifsFYI & CIFS_TIMER) && (midEntry->command != command)) {
 			pr_debug(" CIFS slow rsp: cmd %d mid %llu",
 			       midEntry->command, midEntry->mid);
@@ -221,7 +217,7 @@ rqst_len(struct smb_rqst *rqst)
 }
 
 static int
-smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
+__smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 {
 	int rc;
 	struct kvec *iov = rqst->rq_iov;
@@ -245,8 +241,12 @@ smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 		return -EIO;
 	}
 
+	if (n_vec < 2)
+		return -EIO;
+
 	cifs_dbg(FYI, "Sending smb: smb_len=%u\n", smb_buf_length);
 	dump_smb(iov[0].iov_base, iov[0].iov_len);
+	dump_smb(iov[1].iov_base, iov[1].iov_len);
 
 	/* cork the socket */
 	kernel_setsockopt(ssocket, SOL_TCP, TCP_CORK,
@@ -309,24 +309,43 @@ uncork:
 }
 
 static int
-smb_sendv(struct TCP_Server_Info *server, struct kvec *iov, int n_vec)
+smb_send_rqst(struct TCP_Server_Info *server, struct smb_rqst *rqst, int flags)
 {
-	struct smb_rqst rqst = { .rq_iov = iov,
-				 .rq_nvec = n_vec };
+	struct smb_rqst cur_rqst;
+	int rc;
+
+	if (!(flags & CIFS_TRANSFORM_REQ))
+		return __smb_send_rqst(server, rqst);
 
-	return smb_send_rqst(server, &rqst);
+	if (!server->ops->init_transform_rq ||
+	    !server->ops->free_transform_rq) {
+		cifs_dbg(VFS, "Encryption requested but transform callbacks are missed\n");
+		return -EIO;
+	}
+
+	rc = server->ops->init_transform_rq(server, &cur_rqst, rqst);
+	if (rc)
+		return rc;
+
+	rc = __smb_send_rqst(server, &cur_rqst);
+	server->ops->free_transform_rq(&cur_rqst);
+	return rc;
 }
 
 int
 smb_send(struct TCP_Server_Info *server, struct smb_hdr *smb_buffer,
 	 unsigned int smb_buf_length)
 {
-	struct kvec iov;
+	struct kvec iov[2];
+	struct smb_rqst rqst = { .rq_iov = iov,
+				 .rq_nvec = 2 };
 
-	iov.iov_base = smb_buffer;
-	iov.iov_len = smb_buf_length + 4;
+	iov[0].iov_base = smb_buffer;
+	iov[0].iov_len = 4;
+	iov[1].iov_base = (char *)smb_buffer + 4;
+	iov[1].iov_len = smb_buf_length;
 
-	return smb_sendv(server, &iov, 1);
+	return __smb_send_rqst(server, &rqst);
 }
 
 static int
@@ -454,6 +473,10 @@ cifs_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 	struct smb_hdr *hdr = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
 	struct mid_q_entry *mid;
 
+	if (rqst->rq_iov[0].iov_len != 4 ||
+	    rqst->rq_iov[0].iov_base + 4 != rqst->rq_iov[1].iov_base)
+		return ERR_PTR(-EIO);
+
 	/* enable signing if server requires it */
 	if (server->sign)
 		hdr->Flags2 |= SMBFLG2_SECURITY_SIGNATURE;
@@ -478,7 +501,7 @@ cifs_setup_async_request(struct TCP_Server_Info *server, struct smb_rqst *rqst)
 int
 cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst,
 		mid_receive_t *receive, mid_callback_t *callback,
-		void *cbdata, const int flags)
+		mid_handle_t *handle, void *cbdata, const int flags)
 {
 	int rc, timeout, optype;
 	struct mid_q_entry *mid;
@@ -505,6 +528,7 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst,
 	mid->receive = receive;
 	mid->callback = callback;
 	mid->callback_data = cbdata;
+	mid->handle = handle;
 	mid->mid_state = MID_REQUEST_SUBMITTED;
 
 	/* put it on the pending_mid_q */
@@ -512,11 +536,14 @@ cifs_call_async(struct TCP_Server_Info *server, struct smb_rqst *rqst,
 	list_add_tail(&mid->qhead, &server->pending_mid_q);
 	spin_unlock(&GlobalMid_Lock);
 
-
+	/*
+	 * Need to store the time in mid before calling I/O. For call_async,
+	 * I/O response may come back and free the mid entry on another thread.
+	 */
+	cifs_save_when_sent(mid);
 	cifs_in_send_inc(server);
-	rc = smb_send_rqst(server, rqst);
+	rc = smb_send_rqst(server, rqst, flags);
 	cifs_in_send_dec(server);
-	cifs_save_when_sent(mid);
 
 	if (rc < 0) {
 		server->sequence_number -= 2;
@@ -547,12 +574,13 @@ SendReceiveNoRsp(const unsigned int xid, struct cifs_ses *ses,
 {
 	int rc;
 	struct kvec iov[1];
+	struct kvec rsp_iov;
 	int resp_buf_type;
 
 	iov[0].iov_base = in_buf;
 	iov[0].iov_len = get_rfc1002_length(in_buf) + 4;
 	flags |= CIFS_NO_RESP;
-	rc = SendReceive2(xid, ses, iov, 1, &resp_buf_type, flags);
+	rc = SendReceive2(xid, ses, iov, 1, &resp_buf_type, flags, &rsp_iov);
 	cifs_dbg(NOISY, "SendRcvNoRsp flags %d rc %d\n", flags, rc);
 
 	return rc;
@@ -588,17 +616,16 @@ cifs_sync_mid_result(struct mid_q_entry *mid, struct TCP_Server_Info *server)
 	}
 	spin_unlock(&GlobalMid_Lock);
 
-	mutex_lock(&server->srv_mutex);
 	DeleteMidQEntry(mid);
-	mutex_unlock(&server->srv_mutex);
 	return rc;
 }
 
 static inline int
-send_cancel(struct TCP_Server_Info *server, void *buf, struct mid_q_entry *mid)
+send_cancel(struct TCP_Server_Info *server, struct smb_rqst *rqst,
+	    struct mid_q_entry *mid)
 {
 	return server->ops->send_cancel ?
-				server->ops->send_cancel(server, buf, mid) : 0;
+				server->ops->send_cancel(server, rqst, mid) : 0;
 }
 
 int
@@ -611,13 +638,15 @@ cifs_check_receive(struct mid_q_entry *mid, struct TCP_Server_Info *server,
 
 	/* convert the length into a more usable form */
 	if (server->sign) {
-		struct kvec iov;
+		struct kvec iov[2];
 		int rc = 0;
-		struct smb_rqst rqst = { .rq_iov = &iov,
-					 .rq_nvec = 1 };
+		struct smb_rqst rqst = { .rq_iov = iov,
+					 .rq_nvec = 2 };
 
-		iov.iov_base = mid->resp_buf;
-		iov.iov_len = len;
+		iov[0].iov_base = mid->resp_buf;
+		iov[0].iov_len = 4;
+		iov[1].iov_base = (char *)mid->resp_buf + 4;
+		iov[1].iov_len = len - 4;
 		/* FIXME: add code to kill session */
 		rc = cifs_verify_signature(&rqst, server,
 					   mid->sequence_number);
@@ -637,6 +666,10 @@ cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
 	struct smb_hdr *hdr = (struct smb_hdr *)rqst->rq_iov[0].iov_base;
 	struct mid_q_entry *mid;
 
+	if (rqst->rq_iov[0].iov_len != 4 ||
+	    rqst->rq_iov[0].iov_base + 4 != rqst->rq_iov[1].iov_base)
+		return ERR_PTR(-EIO);
+
 	rc = allocate_mid(ses, hdr, &mid);
 	if (rc)
 		return ERR_PTR(rc);
@@ -649,17 +682,15 @@ cifs_setup_request(struct cifs_ses *ses, struct smb_rqst *rqst)
 }
 
 int
-SendReceive2(const unsigned int xid, struct cifs_ses *ses,
-	     struct kvec *iov, int n_vec, int *resp_buf_type /* ret */,
-	     const int flags)
+cifs_send_recv(const unsigned int xid, struct cifs_ses *ses,
+	       struct smb_rqst *rqst, int *resp_buf_type, const int flags,
+	       struct kvec *resp_iov)
 {
 	int rc = 0;
 	int timeout, optype;
 	struct mid_q_entry *midQ;
-	char *buf = iov[0].iov_base;
 	unsigned int credits = 1;
-	struct smb_rqst rqst = { .rq_iov = iov,
-				 .rq_nvec = n_vec };
+	char *buf;
 
 	timeout = flags & CIFS_TIMEOUT_MASK;
 	optype = flags & CIFS_OP_MASK;
@@ -667,15 +698,12 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	*resp_buf_type = CIFS_NO_BUFFER;  /* no response buf yet */
 
 	if ((ses == NULL) || (ses->server == NULL)) {
-		cifs_small_buf_release(buf);
 		cifs_dbg(VFS, "Null session\n");
 		return -EIO;
 	}
 
-	if (ses->server->tcpStatus == CifsExiting) {
-		cifs_small_buf_release(buf);
+	if (ses->server->tcpStatus == CifsExiting)
 		return -ENOENT;
-	}
 
 	/*
 	 * Ensure that we do not send more than 50 overlapping requests
@@ -684,10 +712,8 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	 */
 
 	rc = wait_for_free_request(ses->server, timeout, optype);
-	if (rc) {
-		cifs_small_buf_release(buf);
+	if (rc)
 		return rc;
-	}
 
 	/*
 	 * Make sure that we sign in the same order that we send on this socket
@@ -697,10 +723,9 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 
 	mutex_lock(&ses->server->srv_mutex);
 
-	midQ = ses->server->ops->setup_request(ses, &rqst);
+	midQ = ses->server->ops->setup_request(ses, rqst);
 	if (IS_ERR(midQ)) {
 		mutex_unlock(&ses->server->srv_mutex);
-		cifs_small_buf_release(buf);
 		/* Update # of requests on wire to server */
 		add_credits(ses->server, 1, optype);
 		return PTR_ERR(midQ);
@@ -708,7 +733,7 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 
 	midQ->mid_state = MID_REQUEST_SUBMITTED;
 	cifs_in_send_inc(ses->server);
-	rc = smb_sendv(ses->server, iov, n_vec);
+	rc = smb_send_rqst(ses->server, rqst, flags);
 	cifs_in_send_dec(ses->server);
 	cifs_save_when_sent(midQ);
 
@@ -716,32 +741,27 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 		ses->server->sequence_number -= 2;
 	mutex_unlock(&ses->server->srv_mutex);
 
-	if (rc < 0) {
-		cifs_small_buf_release(buf);
+	if (rc < 0)
 		goto out;
-	}
 
-	if (timeout == CIFS_ASYNC_OP) {
-		cifs_small_buf_release(buf);
+	if (timeout == CIFS_ASYNC_OP)
 		goto out;
-	}
 
 	rc = wait_for_response(ses->server, midQ);
 	if (rc != 0) {
-		send_cancel(ses->server, buf, midQ);
+		cifs_dbg(FYI, "Cancelling wait for mid %llu\n",	midQ->mid);
+		send_cancel(ses->server, rqst, midQ);
 		spin_lock(&GlobalMid_Lock);
 		if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
+			midQ->mid_flags |= MID_WAIT_CANCELLED;
 			midQ->callback = DeleteMidQEntry;
 			spin_unlock(&GlobalMid_Lock);
-			cifs_small_buf_release(buf);
 			add_credits(ses->server, 1, optype);
 			return rc;
 		}
 		spin_unlock(&GlobalMid_Lock);
 	}
 
-	cifs_small_buf_release(buf);
-
 	rc = cifs_sync_mid_result(midQ, ses->server);
 	if (rc != 0) {
 		add_credits(ses->server, 1, optype);
@@ -755,8 +775,8 @@ SendReceive2(const unsigned int xid, struct cifs_ses *ses,
 	}
 
 	buf = (char *)midQ->resp_buf;
-	iov[0].iov_base = buf;
-	iov[0].iov_len = get_rfc1002_length(buf) + 4;
+	resp_iov->iov_base = buf;
+	resp_iov->iov_len = get_rfc1002_length(buf) + 4;
 	if (midQ->large_buf)
 		*resp_buf_type = CIFS_LARGE_BUFFER;
 	else
@@ -778,12 +798,45 @@ out:
 }
 
 int
+SendReceive2(const unsigned int xid, struct cifs_ses *ses,
+	     struct kvec *iov, int n_vec, int *resp_buf_type /* ret */,
+	     const int flags, struct kvec *resp_iov)
+{
+	struct smb_rqst rqst;
+	struct kvec *new_iov;
+	int rc;
+
+	new_iov = kmalloc(sizeof(struct kvec) * (n_vec + 1), GFP_KERNEL);
+	if (!new_iov)
+		return -ENOMEM;
+
+	/* 1st iov is a RFC1001 length followed by the rest of the packet */
+	memcpy(new_iov + 1, iov, (sizeof(struct kvec) * n_vec));
+
+	new_iov[0].iov_base = new_iov[1].iov_base;
+	new_iov[0].iov_len = 4;
+	new_iov[1].iov_base += 4;
+	new_iov[1].iov_len -= 4;
+
+	memset(&rqst, 0, sizeof(struct smb_rqst));
+	rqst.rq_iov = new_iov;
+	rqst.rq_nvec = n_vec + 1;
+
+	rc = cifs_send_recv(xid, ses, &rqst, resp_buf_type, flags, resp_iov);
+	kfree(new_iov);
+	return rc;
+}
+
+int
 SendReceive(const unsigned int xid, struct cifs_ses *ses,
 	    struct smb_hdr *in_buf, struct smb_hdr *out_buf,
 	    int *pbytes_returned, const int timeout)
 {
 	int rc = 0;
 	struct mid_q_entry *midQ;
+	unsigned int len = be32_to_cpu(in_buf->smb_buf_length);
+	struct kvec iov = { .iov_base = in_buf, .iov_len = len };
+	struct smb_rqst rqst = { .rq_iov = &iov, .rq_nvec = 1 };
 
 	if (ses == NULL) {
 		cifs_dbg(VFS, "Null smb session\n");
@@ -801,10 +854,9 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
 	   to the same server. We may make this configurable later or
 	   use ses->maxReq */
 
-	if (be32_to_cpu(in_buf->smb_buf_length) > CIFSMaxBufSize +
-			MAX_CIFS_HDR_SIZE - 4) {
+	if (len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) {
 		cifs_dbg(VFS, "Illegal length, greater than maximum frame, %d\n",
-			 be32_to_cpu(in_buf->smb_buf_length));
+			 len);
 		return -EIO;
 	}
 
@@ -835,7 +887,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
 	midQ->mid_state = MID_REQUEST_SUBMITTED;
 
 	cifs_in_send_inc(ses->server);
-	rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
+	rc = smb_send(ses->server, in_buf, len);
 	cifs_in_send_dec(ses->server);
 	cifs_save_when_sent(midQ);
 
@@ -852,7 +904,7 @@ SendReceive(const unsigned int xid, struct cifs_ses *ses,
 
 	rc = wait_for_response(ses->server, midQ);
 	if (rc != 0) {
-		send_cancel(ses->server, in_buf, midQ);
+		send_cancel(ses->server, &rqst, midQ);
 		spin_lock(&GlobalMid_Lock);
 		if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
 			/* no longer considered to be "in-flight" */
@@ -921,6 +973,9 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 	int rstart = 0;
 	struct mid_q_entry *midQ;
 	struct cifs_ses *ses;
+	unsigned int len = be32_to_cpu(in_buf->smb_buf_length);
+	struct kvec iov = { .iov_base = in_buf, .iov_len = len };
+	struct smb_rqst rqst = { .rq_iov = &iov, .rq_nvec = 1 };
 
 	if (tcon == NULL || tcon->ses == NULL) {
 		cifs_dbg(VFS, "Null smb session\n");
@@ -940,10 +995,9 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 	   to the same server. We may make this configurable later or
 	   use ses->maxReq */
 
-	if (be32_to_cpu(in_buf->smb_buf_length) > CIFSMaxBufSize +
-			MAX_CIFS_HDR_SIZE - 4) {
+	if (len > CIFSMaxBufSize + MAX_CIFS_HDR_SIZE - 4) {
 		cifs_dbg(VFS, "Illegal length, greater than maximum frame, %d\n",
-			 be32_to_cpu(in_buf->smb_buf_length));
+			 len);
 		return -EIO;
 	}
 
@@ -972,7 +1026,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 
 	midQ->mid_state = MID_REQUEST_SUBMITTED;
 	cifs_in_send_inc(ses->server);
-	rc = smb_send(ses->server, in_buf, be32_to_cpu(in_buf->smb_buf_length));
+	rc = smb_send(ses->server, in_buf, len);
 	cifs_in_send_dec(ses->server);
 	cifs_save_when_sent(midQ);
 
@@ -1001,7 +1055,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 		if (in_buf->Command == SMB_COM_TRANSACTION2) {
 			/* POSIX lock. We send a NT_CANCEL SMB to cause the
 			   blocking lock to return. */
-			rc = send_cancel(ses->server, in_buf, midQ);
+			rc = send_cancel(ses->server, &rqst, midQ);
 			if (rc) {
 				cifs_delete_mid(midQ);
 				return rc;
@@ -1022,7 +1076,7 @@ SendReceiveBlockingLock(const unsigned int xid, struct cifs_tcon *tcon,
 
 		rc = wait_for_response(ses->server, midQ);
 		if (rc) {
-			send_cancel(ses->server, in_buf, midQ);
+			send_cancel(ses->server, &rqst, midQ);
 			spin_lock(&GlobalMid_Lock);
 			if (midQ->mid_state == MID_REQUEST_SUBMITTED) {
 				/* no longer considered to be "in-flight" */
diff --git a/fs/cifs/xattr.c b/fs/cifs/xattr.c
index 20af5187ba63..de50e749ff05 100644
--- a/fs/cifs/xattr.c
+++ b/fs/cifs/xattr.c
@@ -188,8 +188,6 @@ static int cifs_creation_time_get(struct dentry *dentry, struct inode *inode,
 	pcreatetime = (__u64 *)value;
 	*pcreatetime = CIFS_I(inode)->createtime;
 	return sizeof(__u64);
-
-	return rc;
 }
 
 
@@ -235,8 +233,7 @@ static int cifs_xattr_get(const struct xattr_handler *handler,
 
 		if (pTcon->ses->server->ops->query_all_EAs)
 			rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
-				full_path, name, value, size,
-				cifs_sb->local_nls, cifs_remap(cifs_sb));
+				full_path, name, value, size, cifs_sb);
 		break;
 
 	case XATTR_CIFS_ACL: {
@@ -336,8 +333,7 @@ ssize_t cifs_listxattr(struct dentry *direntry, char *data, size_t buf_size)
 
 	if (pTcon->ses->server->ops->query_all_EAs)
 		rc = pTcon->ses->server->ops->query_all_EAs(xid, pTcon,
-				full_path, NULL, data, buf_size,
-				cifs_sb->local_nls, cifs_remap(cifs_sb));
+				full_path, NULL, data, buf_size, cifs_sb);
 list_ea_exit:
 	kfree(full_path);
 	free_xid(xid);
diff --git a/fs/coda/coda_linux.h b/fs/coda/coda_linux.h
index 5104d84c4f64..d3c361883c28 100644
--- a/fs/coda/coda_linux.h
+++ b/fs/coda/coda_linux.h
@@ -47,7 +47,7 @@ int coda_open(struct inode *i, struct file *f);
 int coda_release(struct inode *i, struct file *f);
 int coda_permission(struct inode *inode, int mask);
 int coda_revalidate_inode(struct inode *);
-int coda_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+int coda_getattr(const struct path *, struct kstat *, u32, unsigned int);
 int coda_setattr(struct dentry *, struct iattr *);
 
 /* this file:  heloers */
diff --git a/fs/coda/file.c b/fs/coda/file.c
index 6e0154eb6fcc..363402fcb3ed 100644
--- a/fs/coda/file.c
+++ b/fs/coda/file.c
@@ -34,7 +34,7 @@ coda_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 	BUG_ON(!cfi || cfi->cfi_magic != CODA_MAGIC);
 
-	return vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos);
+	return vfs_iter_read(cfi->cfi_container, to, &iocb->ki_pos, 0);
 }
 
 static ssize_t
@@ -51,7 +51,7 @@ coda_file_write_iter(struct kiocb *iocb, struct iov_iter *to)
 	host_file = cfi->cfi_container;
 	file_start_write(host_file);
 	inode_lock(coda_inode);
-	ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos);
+	ret = vfs_iter_write(cfi->cfi_container, to, &iocb->ki_pos, 0);
 	coda_inode->i_size = file_inode(host_file)->i_size;
 	coda_inode->i_blocks = (coda_inode->i_size + 511) >> 9;
 	coda_inode->i_mtime = coda_inode->i_ctime = current_time(coda_inode);
@@ -96,7 +96,7 @@ coda_file_mmap(struct file *coda_file, struct vm_area_struct *vma)
 	cfi->cfi_mapcount++;
 	spin_unlock(&cii->c_lock);
 
-	return host_file->f_op->mmap(host_file, vma);
+	return call_mmap(host_file, vma);
 }
 
 int coda_open(struct inode *coda_inode, struct file *coda_file)
diff --git a/fs/coda/inode.c b/fs/coda/inode.c
index 71dbe7e287ce..6058df380cc0 100644
--- a/fs/coda/inode.c
+++ b/fs/coda/inode.c
@@ -183,10 +183,6 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
 		goto unlock_out;
 	}
 
-	error = bdi_setup_and_register(&vc->bdi, "coda");
-	if (error)
-		goto unlock_out;
-
 	vc->vc_sb = sb;
 	mutex_unlock(&vc->vc_mutex);
 
@@ -197,7 +193,10 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_magic = CODA_SUPER_MAGIC;
 	sb->s_op = &coda_super_operations;
 	sb->s_d_op = &coda_dentry_operations;
-	sb->s_bdi = &vc->bdi;
+
+	error = super_setup_bdi(sb);
+	if (error)
+		goto error;
 
 	/* get root fid from Venus: this needs the root inode */
 	error = venus_rootfid(sb, &fid);
@@ -228,7 +227,6 @@ static int coda_fill_super(struct super_block *sb, void *data, int silent)
 
 error:
 	mutex_lock(&vc->vc_mutex);
-	bdi_destroy(&vc->bdi);
 	vc->vc_sb = NULL;
 	sb->s_fs_info = NULL;
 unlock_out:
@@ -240,7 +238,6 @@ static void coda_put_super(struct super_block *sb)
 {
 	struct venus_comm *vcp = coda_vcp(sb);
 	mutex_lock(&vcp->vc_mutex);
-	bdi_destroy(&vcp->bdi);
 	vcp->vc_sb = NULL;
 	sb->s_fs_info = NULL;
 	mutex_unlock(&vcp->vc_mutex);
@@ -255,11 +252,12 @@ static void coda_evict_inode(struct inode *inode)
 	coda_cache_clear_inode(inode);
 }
 
-int coda_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int coda_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
-	int err = coda_revalidate_inode(d_inode(dentry));
+	int err = coda_revalidate_inode(d_inode(path->dentry));
 	if (!err)
-		generic_fillattr(d_inode(dentry), stat);
+		generic_fillattr(d_inode(path->dentry), stat);
 	return err;
 }
 
diff --git a/fs/coda/psdev.c b/fs/coda/psdev.c
index 822629126e89..f40e3953e7fe 100644
--- a/fs/coda/psdev.c
+++ b/fs/coda/psdev.c
@@ -22,7 +22,7 @@
 #include <linux/kernel.h>
 #include <linux/major.h>
 #include <linux/time.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/ioport.h>
 #include <linux/fcntl.h>
diff --git a/fs/coda/upcall.c b/fs/coda/upcall.c
index f6c6c8adbc01..e82357c89979 100644
--- a/fs/coda/upcall.c
+++ b/fs/coda/upcall.c
@@ -15,7 +15,7 @@
  */
 
 #include <linux/signal.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/types.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
diff --git a/fs/compat.c b/fs/compat.c
index e50a2114f474..190b38b39d9e 100644
--- a/fs/compat.c
+++ b/fs/compat.c
@@ -15,554 +15,14 @@
  *  published by the Free Software Foundation.
  */
 
-#include <linux/stddef.h>
-#include <linux/kernel.h>
-#include <linux/linkage.h>
 #include <linux/compat.h>
-#include <linux/errno.h>
-#include <linux/time.h>
-#include <linux/fs.h>
-#include <linux/fcntl.h>
-#include <linux/namei.h>
-#include <linux/file.h>
-#include <linux/fdtable.h>
-#include <linux/vfs.h>
-#include <linux/ioctl.h>
-#include <linux/init.h>
 #include <linux/ncp_mount.h>
 #include <linux/nfs4_mount.h>
 #include <linux/syscalls.h>
-#include <linux/ctype.h>
-#include <linux/dirent.h>
-#include <linux/fsnotify.h>
-#include <linux/highuid.h>
-#include <linux/personality.h>
-#include <linux/rwsem.h>
-#include <linux/tsacct_kern.h>
-#include <linux/security.h>
-#include <linux/highmem.h>
-#include <linux/signal.h>
-#include <linux/poll.h>
-#include <linux/mm.h>
-#include <linux/fs_struct.h>
 #include <linux/slab.h>
-#include <linux/pagemap.h>
-#include <linux/aio.h>
-
 #include <linux/uaccess.h>
-#include <asm/mmu_context.h>
-#include <asm/ioctls.h>
 #include "internal.h"
 
-/*
- * Not all architectures have sys_utime, so implement this in terms
- * of sys_utimes.
- */
-COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename,
-		       struct compat_utimbuf __user *, t)
-{
-	struct timespec tv[2];
-
-	if (t) {
-		if (get_user(tv[0].tv_sec, &t->actime) ||
-		    get_user(tv[1].tv_sec, &t->modtime))
-			return -EFAULT;
-		tv[0].tv_nsec = 0;
-		tv[1].tv_nsec = 0;
-	}
-	return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0);
-}
-
-COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags)
-{
-	struct timespec tv[2];
-
-	if  (t) {
-		if (compat_get_timespec(&tv[0], &t[0]) ||
-		    compat_get_timespec(&tv[1], &t[1]))
-			return -EFAULT;
-
-		if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT)
-			return 0;
-	}
-	return do_utimes(dfd, filename, t ? tv : NULL, flags);
-}
-
-COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t)
-{
-	struct timespec tv[2];
-
-	if (t) {
-		if (get_user(tv[0].tv_sec, &t[0].tv_sec) ||
-		    get_user(tv[0].tv_nsec, &t[0].tv_usec) ||
-		    get_user(tv[1].tv_sec, &t[1].tv_sec) ||
-		    get_user(tv[1].tv_nsec, &t[1].tv_usec))
-			return -EFAULT;
-		if (tv[0].tv_nsec >= 1000000 || tv[0].tv_nsec < 0 ||
-		    tv[1].tv_nsec >= 1000000 || tv[1].tv_nsec < 0)
-			return -EINVAL;
-		tv[0].tv_nsec *= 1000;
-		tv[1].tv_nsec *= 1000;
-	}
-	return do_utimes(dfd, filename, t ? tv : NULL, 0);
-}
-
-COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t)
-{
-	return compat_sys_futimesat(AT_FDCWD, filename, t);
-}
-
-static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
-{
-	struct compat_stat tmp;
-
-	if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev))
-		return -EOVERFLOW;
-
-	memset(&tmp, 0, sizeof(tmp));
-	tmp.st_dev = old_encode_dev(stat->dev);
-	tmp.st_ino = stat->ino;
-	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
-		return -EOVERFLOW;
-	tmp.st_mode = stat->mode;
-	tmp.st_nlink = stat->nlink;
-	if (tmp.st_nlink != stat->nlink)
-		return -EOVERFLOW;
-	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
-	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
-	tmp.st_rdev = old_encode_dev(stat->rdev);
-	if ((u64) stat->size > MAX_NON_LFS)
-		return -EOVERFLOW;
-	tmp.st_size = stat->size;
-	tmp.st_atime = stat->atime.tv_sec;
-	tmp.st_atime_nsec = stat->atime.tv_nsec;
-	tmp.st_mtime = stat->mtime.tv_sec;
-	tmp.st_mtime_nsec = stat->mtime.tv_nsec;
-	tmp.st_ctime = stat->ctime.tv_sec;
-	tmp.st_ctime_nsec = stat->ctime.tv_nsec;
-	tmp.st_blocks = stat->blocks;
-	tmp.st_blksize = stat->blksize;
-	return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0;
-}
-
-COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename,
-		       struct compat_stat __user *, statbuf)
-{
-	struct kstat stat;
-	int error;
-
-	error = vfs_stat(filename, &stat);
-	if (error)
-		return error;
-	return cp_compat_stat(&stat, statbuf);
-}
-
-COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename,
-		       struct compat_stat __user *, statbuf)
-{
-	struct kstat stat;
-	int error;
-
-	error = vfs_lstat(filename, &stat);
-	if (error)
-		return error;
-	return cp_compat_stat(&stat, statbuf);
-}
-
-#ifndef __ARCH_WANT_STAT64
-COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd,
-		       const char __user *, filename,
-		       struct compat_stat __user *, statbuf, int, flag)
-{
-	struct kstat stat;
-	int error;
-
-	error = vfs_fstatat(dfd, filename, &stat, flag);
-	if (error)
-		return error;
-	return cp_compat_stat(&stat, statbuf);
-}
-#endif
-
-COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd,
-		       struct compat_stat __user *, statbuf)
-{
-	struct kstat stat;
-	int error = vfs_fstat(fd, &stat);
-
-	if (!error)
-		error = cp_compat_stat(&stat, statbuf);
-	return error;
-}
-
-static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *kbuf)
-{
-	
-	if (sizeof ubuf->f_blocks == 4) {
-		if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail |
-		     kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
-			return -EOVERFLOW;
-		/* f_files and f_ffree may be -1; it's okay
-		 * to stuff that into 32 bits */
-		if (kbuf->f_files != 0xffffffffffffffffULL
-		 && (kbuf->f_files & 0xffffffff00000000ULL))
-			return -EOVERFLOW;
-		if (kbuf->f_ffree != 0xffffffffffffffffULL
-		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
-			return -EOVERFLOW;
-	}
-	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) ||
-	    __put_user(kbuf->f_type, &ubuf->f_type) ||
-	    __put_user(kbuf->f_bsize, &ubuf->f_bsize) ||
-	    __put_user(kbuf->f_blocks, &ubuf->f_blocks) ||
-	    __put_user(kbuf->f_bfree, &ubuf->f_bfree) ||
-	    __put_user(kbuf->f_bavail, &ubuf->f_bavail) ||
-	    __put_user(kbuf->f_files, &ubuf->f_files) ||
-	    __put_user(kbuf->f_ffree, &ubuf->f_ffree) ||
-	    __put_user(kbuf->f_namelen, &ubuf->f_namelen) ||
-	    __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
-	    __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) ||
-	    __put_user(kbuf->f_frsize, &ubuf->f_frsize) ||
-	    __put_user(kbuf->f_flags, &ubuf->f_flags) ||
-	    __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare)))
-		return -EFAULT;
-	return 0;
-}
-
-/*
- * The following statfs calls are copies of code from fs/statfs.c and
- * should be checked against those from time to time
- */
-COMPAT_SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct compat_statfs __user *, buf)
-{
-	struct kstatfs tmp;
-	int error = user_statfs(pathname, &tmp);
-	if (!error)
-		error = put_compat_statfs(buf, &tmp);
-	return error;
-}
-
-COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, buf)
-{
-	struct kstatfs tmp;
-	int error = fd_statfs(fd, &tmp);
-	if (!error)
-		error = put_compat_statfs(buf, &tmp);
-	return error;
-}
-
-static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf)
-{
-	if (sizeof(ubuf->f_bsize) == 4) {
-		if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen |
-		     kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL)
-			return -EOVERFLOW;
-		/* f_files and f_ffree may be -1; it's okay
-		 * to stuff that into 32 bits */
-		if (kbuf->f_files != 0xffffffffffffffffULL
-		 && (kbuf->f_files & 0xffffffff00000000ULL))
-			return -EOVERFLOW;
-		if (kbuf->f_ffree != 0xffffffffffffffffULL
-		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
-			return -EOVERFLOW;
-	}
-	if (!access_ok(VERIFY_WRITE, ubuf, sizeof(*ubuf)) ||
-	    __put_user(kbuf->f_type, &ubuf->f_type) ||
-	    __put_user(kbuf->f_bsize, &ubuf->f_bsize) ||
-	    __put_user(kbuf->f_blocks, &ubuf->f_blocks) ||
-	    __put_user(kbuf->f_bfree, &ubuf->f_bfree) ||
-	    __put_user(kbuf->f_bavail, &ubuf->f_bavail) ||
-	    __put_user(kbuf->f_files, &ubuf->f_files) ||
-	    __put_user(kbuf->f_ffree, &ubuf->f_ffree) ||
-	    __put_user(kbuf->f_namelen, &ubuf->f_namelen) ||
-	    __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) ||
-	    __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) ||
-	    __put_user(kbuf->f_frsize, &ubuf->f_frsize) ||
-	    __put_user(kbuf->f_flags, &ubuf->f_flags) ||
-	    __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare)))
-		return -EFAULT;
-	return 0;
-}
-
-COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf)
-{
-	struct kstatfs tmp;
-	int error;
-
-	if (sz != sizeof(*buf))
-		return -EINVAL;
-
-	error = user_statfs(pathname, &tmp);
-	if (!error)
-		error = put_compat_statfs64(buf, &tmp);
-	return error;
-}
-
-COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf)
-{
-	struct kstatfs tmp;
-	int error;
-
-	if (sz != sizeof(*buf))
-		return -EINVAL;
-
-	error = fd_statfs(fd, &tmp);
-	if (!error)
-		error = put_compat_statfs64(buf, &tmp);
-	return error;
-}
-
-/*
- * This is a copy of sys_ustat, just dealing with a structure layout.
- * Given how simple this syscall is that apporach is more maintainable
- * than the various conversion hacks.
- */
-COMPAT_SYSCALL_DEFINE2(ustat, unsigned, dev, struct compat_ustat __user *, u)
-{
-	struct compat_ustat tmp;
-	struct kstatfs sbuf;
-	int err = vfs_ustat(new_decode_dev(dev), &sbuf);
-	if (err)
-		return err;
-
-	memset(&tmp, 0, sizeof(struct compat_ustat));
-	tmp.f_tfree = sbuf.f_bfree;
-	tmp.f_tinode = sbuf.f_ffree;
-	if (copy_to_user(u, &tmp, sizeof(struct compat_ustat)))
-		return -EFAULT;
-	return 0;
-}
-
-static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
-{
-	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
-	    __get_user(kfl->l_type, &ufl->l_type) ||
-	    __get_user(kfl->l_whence, &ufl->l_whence) ||
-	    __get_user(kfl->l_start, &ufl->l_start) ||
-	    __get_user(kfl->l_len, &ufl->l_len) ||
-	    __get_user(kfl->l_pid, &ufl->l_pid))
-		return -EFAULT;
-	return 0;
-}
-
-static int put_compat_flock(struct flock *kfl, struct compat_flock __user *ufl)
-{
-	if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) ||
-	    __put_user(kfl->l_type, &ufl->l_type) ||
-	    __put_user(kfl->l_whence, &ufl->l_whence) ||
-	    __put_user(kfl->l_start, &ufl->l_start) ||
-	    __put_user(kfl->l_len, &ufl->l_len) ||
-	    __put_user(kfl->l_pid, &ufl->l_pid))
-		return -EFAULT;
-	return 0;
-}
-
-#ifndef HAVE_ARCH_GET_COMPAT_FLOCK64
-static int get_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl)
-{
-	if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) ||
-	    __get_user(kfl->l_type, &ufl->l_type) ||
-	    __get_user(kfl->l_whence, &ufl->l_whence) ||
-	    __get_user(kfl->l_start, &ufl->l_start) ||
-	    __get_user(kfl->l_len, &ufl->l_len) ||
-	    __get_user(kfl->l_pid, &ufl->l_pid))
-		return -EFAULT;
-	return 0;
-}
-#endif
-
-#ifndef HAVE_ARCH_PUT_COMPAT_FLOCK64
-static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *ufl)
-{
-	if (!access_ok(VERIFY_WRITE, ufl, sizeof(*ufl)) ||
-	    __put_user(kfl->l_type, &ufl->l_type) ||
-	    __put_user(kfl->l_whence, &ufl->l_whence) ||
-	    __put_user(kfl->l_start, &ufl->l_start) ||
-	    __put_user(kfl->l_len, &ufl->l_len) ||
-	    __put_user(kfl->l_pid, &ufl->l_pid))
-		return -EFAULT;
-	return 0;
-}
-#endif
-
-static unsigned int
-convert_fcntl_cmd(unsigned int cmd)
-{
-	switch (cmd) {
-	case F_GETLK64:
-		return F_GETLK;
-	case F_SETLK64:
-		return F_SETLK;
-	case F_SETLKW64:
-		return F_SETLKW;
-	}
-
-	return cmd;
-}
-
-COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
-		       compat_ulong_t, arg)
-{
-	mm_segment_t old_fs;
-	struct flock f;
-	long ret;
-	unsigned int conv_cmd;
-
-	switch (cmd) {
-	case F_GETLK:
-	case F_SETLK:
-	case F_SETLKW:
-		ret = get_compat_flock(&f, compat_ptr(arg));
-		if (ret != 0)
-			break;
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		ret = sys_fcntl(fd, cmd, (unsigned long)&f);
-		set_fs(old_fs);
-		if (cmd == F_GETLK && ret == 0) {
-			/* GETLK was successful and we need to return the data...
-			 * but it needs to fit in the compat structure.
-			 * l_start shouldn't be too big, unless the original
-			 * start + end is greater than COMPAT_OFF_T_MAX, in which
-			 * case the app was asking for trouble, so we return
-			 * -EOVERFLOW in that case.
-			 * l_len could be too big, in which case we just truncate it,
-			 * and only allow the app to see that part of the conflicting
-			 * lock that might make sense to it anyway
-			 */
-
-			if (f.l_start > COMPAT_OFF_T_MAX)
-				ret = -EOVERFLOW;
-			if (f.l_len > COMPAT_OFF_T_MAX)
-				f.l_len = COMPAT_OFF_T_MAX;
-			if (ret == 0)
-				ret = put_compat_flock(&f, compat_ptr(arg));
-		}
-		break;
-
-	case F_GETLK64:
-	case F_SETLK64:
-	case F_SETLKW64:
-	case F_OFD_GETLK:
-	case F_OFD_SETLK:
-	case F_OFD_SETLKW:
-		ret = get_compat_flock64(&f, compat_ptr(arg));
-		if (ret != 0)
-			break;
-		old_fs = get_fs();
-		set_fs(KERNEL_DS);
-		conv_cmd = convert_fcntl_cmd(cmd);
-		ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f);
-		set_fs(old_fs);
-		if ((conv_cmd == F_GETLK || conv_cmd == F_OFD_GETLK) && ret == 0) {
-			/* need to return lock information - see above for commentary */
-			if (f.l_start > COMPAT_LOFF_T_MAX)
-				ret = -EOVERFLOW;
-			if (f.l_len > COMPAT_LOFF_T_MAX)
-				f.l_len = COMPAT_LOFF_T_MAX;
-			if (ret == 0)
-				ret = put_compat_flock64(&f, compat_ptr(arg));
-		}
-		break;
-
-	default:
-		ret = sys_fcntl(fd, cmd, arg);
-		break;
-	}
-	return ret;
-}
-
-COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
-		       compat_ulong_t, arg)
-{
-	switch (cmd) {
-	case F_GETLK64:
-	case F_SETLK64:
-	case F_SETLKW64:
-	case F_OFD_GETLK:
-	case F_OFD_SETLK:
-	case F_OFD_SETLKW:
-		return -EINVAL;
-	}
-	return compat_sys_fcntl64(fd, cmd, arg);
-}
-
-/* A write operation does a read from user space and vice versa */
-#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ)
-
-ssize_t compat_rw_copy_check_uvector(int type,
-		const struct compat_iovec __user *uvector, unsigned long nr_segs,
-		unsigned long fast_segs, struct iovec *fast_pointer,
-		struct iovec **ret_pointer)
-{
-	compat_ssize_t tot_len;
-	struct iovec *iov = *ret_pointer = fast_pointer;
-	ssize_t ret = 0;
-	int seg;
-
-	/*
-	 * SuS says "The readv() function *may* fail if the iovcnt argument
-	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
-	 * traditionally returned zero for zero segments, so...
-	 */
-	if (nr_segs == 0)
-		goto out;
-
-	ret = -EINVAL;
-	if (nr_segs > UIO_MAXIOV)
-		goto out;
-	if (nr_segs > fast_segs) {
-		ret = -ENOMEM;
-		iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
-		if (iov == NULL)
-			goto out;
-	}
-	*ret_pointer = iov;
-
-	ret = -EFAULT;
-	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
-		goto out;
-
-	/*
-	 * Single unix specification:
-	 * We should -EINVAL if an element length is not >= 0 and fitting an
-	 * ssize_t.
-	 *
-	 * In Linux, the total length is limited to MAX_RW_COUNT, there is
-	 * no overflow possibility.
-	 */
-	tot_len = 0;
-	ret = -EINVAL;
-	for (seg = 0; seg < nr_segs; seg++) {
-		compat_uptr_t buf;
-		compat_ssize_t len;
-
-		if (__get_user(len, &uvector->iov_len) ||
-		   __get_user(buf, &uvector->iov_base)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len < 0)	/* size_t not fitting in compat_ssize_t .. */
-			goto out;
-		if (type >= 0 &&
-		    !access_ok(vrfy_dir(type), compat_ptr(buf), len)) {
-			ret = -EFAULT;
-			goto out;
-		}
-		if (len > MAX_RW_COUNT - tot_len)
-			len = MAX_RW_COUNT - tot_len;
-		tot_len += len;
-		iov->iov_base = compat_ptr(buf);
-		iov->iov_len = (compat_size_t) len;
-		uvector++;
-		iov++;
-	}
-	ret = tot_len;
-
-out:
-	return ret;
-}
-
 struct compat_ncp_mount_data {
 	compat_int_t version;
 	compat_uint_t ncp_fd;
@@ -743,653 +203,3 @@ COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name,
  out:
 	return retval;
 }
-
-struct compat_old_linux_dirent {
-	compat_ulong_t	d_ino;
-	compat_ulong_t	d_offset;
-	unsigned short	d_namlen;
-	char		d_name[1];
-};
-
-struct compat_readdir_callback {
-	struct dir_context ctx;
-	struct compat_old_linux_dirent __user *dirent;
-	int result;
-};
-
-static int compat_fillonedir(struct dir_context *ctx, const char *name,
-			     int namlen, loff_t offset, u64 ino,
-			     unsigned int d_type)
-{
-	struct compat_readdir_callback *buf =
-		container_of(ctx, struct compat_readdir_callback, ctx);
-	struct compat_old_linux_dirent __user *dirent;
-	compat_ulong_t d_ino;
-
-	if (buf->result)
-		return -EINVAL;
-	d_ino = ino;
-	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
-		buf->result = -EOVERFLOW;
-		return -EOVERFLOW;
-	}
-	buf->result++;
-	dirent = buf->dirent;
-	if (!access_ok(VERIFY_WRITE, dirent,
-			(unsigned long)(dirent->d_name + namlen + 1) -
-				(unsigned long)dirent))
-		goto efault;
-	if (	__put_user(d_ino, &dirent->d_ino) ||
-		__put_user(offset, &dirent->d_offset) ||
-		__put_user(namlen, &dirent->d_namlen) ||
-		__copy_to_user(dirent->d_name, name, namlen) ||
-		__put_user(0, dirent->d_name + namlen))
-		goto efault;
-	return 0;
-efault:
-	buf->result = -EFAULT;
-	return -EFAULT;
-}
-
-COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
-		struct compat_old_linux_dirent __user *, dirent, unsigned int, count)
-{
-	int error;
-	struct fd f = fdget_pos(fd);
-	struct compat_readdir_callback buf = {
-		.ctx.actor = compat_fillonedir,
-		.dirent = dirent
-	};
-
-	if (!f.file)
-		return -EBADF;
-
-	error = iterate_dir(f.file, &buf.ctx);
-	if (buf.result)
-		error = buf.result;
-
-	fdput_pos(f);
-	return error;
-}
-
-struct compat_linux_dirent {
-	compat_ulong_t	d_ino;
-	compat_ulong_t	d_off;
-	unsigned short	d_reclen;
-	char		d_name[1];
-};
-
-struct compat_getdents_callback {
-	struct dir_context ctx;
-	struct compat_linux_dirent __user *current_dir;
-	struct compat_linux_dirent __user *previous;
-	int count;
-	int error;
-};
-
-static int compat_filldir(struct dir_context *ctx, const char *name, int namlen,
-		loff_t offset, u64 ino, unsigned int d_type)
-{
-	struct compat_linux_dirent __user * dirent;
-	struct compat_getdents_callback *buf =
-		container_of(ctx, struct compat_getdents_callback, ctx);
-	compat_ulong_t d_ino;
-	int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) +
-		namlen + 2, sizeof(compat_long_t));
-
-	buf->error = -EINVAL;	/* only used if we fail.. */
-	if (reclen > buf->count)
-		return -EINVAL;
-	d_ino = ino;
-	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
-		buf->error = -EOVERFLOW;
-		return -EOVERFLOW;
-	}
-	dirent = buf->previous;
-	if (dirent) {
-		if (signal_pending(current))
-			return -EINTR;
-		if (__put_user(offset, &dirent->d_off))
-			goto efault;
-	}
-	dirent = buf->current_dir;
-	if (__put_user(d_ino, &dirent->d_ino))
-		goto efault;
-	if (__put_user(reclen, &dirent->d_reclen))
-		goto efault;
-	if (copy_to_user(dirent->d_name, name, namlen))
-		goto efault;
-	if (__put_user(0, dirent->d_name + namlen))
-		goto efault;
-	if (__put_user(d_type, (char  __user *) dirent + reclen - 1))
-		goto efault;
-	buf->previous = dirent;
-	dirent = (void __user *)dirent + reclen;
-	buf->current_dir = dirent;
-	buf->count -= reclen;
-	return 0;
-efault:
-	buf->error = -EFAULT;
-	return -EFAULT;
-}
-
-COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
-		struct compat_linux_dirent __user *, dirent, unsigned int, count)
-{
-	struct fd f;
-	struct compat_linux_dirent __user * lastdirent;
-	struct compat_getdents_callback buf = {
-		.ctx.actor = compat_filldir,
-		.current_dir = dirent,
-		.count = count
-	};
-	int error;
-
-	if (!access_ok(VERIFY_WRITE, dirent, count))
-		return -EFAULT;
-
-	f = fdget_pos(fd);
-	if (!f.file)
-		return -EBADF;
-
-	error = iterate_dir(f.file, &buf.ctx);
-	if (error >= 0)
-		error = buf.error;
-	lastdirent = buf.previous;
-	if (lastdirent) {
-		if (put_user(buf.ctx.pos, &lastdirent->d_off))
-			error = -EFAULT;
-		else
-			error = count - buf.count;
-	}
-	fdput_pos(f);
-	return error;
-}
-
-#ifdef __ARCH_WANT_COMPAT_SYS_GETDENTS64
-
-struct compat_getdents_callback64 {
-	struct dir_context ctx;
-	struct linux_dirent64 __user *current_dir;
-	struct linux_dirent64 __user *previous;
-	int count;
-	int error;
-};
-
-static int compat_filldir64(struct dir_context *ctx, const char *name,
-			    int namlen, loff_t offset, u64 ino,
-			    unsigned int d_type)
-{
-	struct linux_dirent64 __user *dirent;
-	struct compat_getdents_callback64 *buf =
-		container_of(ctx, struct compat_getdents_callback64, ctx);
-	int reclen = ALIGN(offsetof(struct linux_dirent64, d_name) + namlen + 1,
-		sizeof(u64));
-	u64 off;
-
-	buf->error = -EINVAL;	/* only used if we fail.. */
-	if (reclen > buf->count)
-		return -EINVAL;
-	dirent = buf->previous;
-
-	if (dirent) {
-		if (signal_pending(current))
-			return -EINTR;
-		if (__put_user_unaligned(offset, &dirent->d_off))
-			goto efault;
-	}
-	dirent = buf->current_dir;
-	if (__put_user_unaligned(ino, &dirent->d_ino))
-		goto efault;
-	off = 0;
-	if (__put_user_unaligned(off, &dirent->d_off))
-		goto efault;
-	if (__put_user(reclen, &dirent->d_reclen))
-		goto efault;
-	if (__put_user(d_type, &dirent->d_type))
-		goto efault;
-	if (copy_to_user(dirent->d_name, name, namlen))
-		goto efault;
-	if (__put_user(0, dirent->d_name + namlen))
-		goto efault;
-	buf->previous = dirent;
-	dirent = (void __user *)dirent + reclen;
-	buf->current_dir = dirent;
-	buf->count -= reclen;
-	return 0;
-efault:
-	buf->error = -EFAULT;
-	return -EFAULT;
-}
-
-COMPAT_SYSCALL_DEFINE3(getdents64, unsigned int, fd,
-		struct linux_dirent64 __user *, dirent, unsigned int, count)
-{
-	struct fd f;
-	struct linux_dirent64 __user * lastdirent;
-	struct compat_getdents_callback64 buf = {
-		.ctx.actor = compat_filldir64,
-		.current_dir = dirent,
-		.count = count
-	};
-	int error;
-
-	if (!access_ok(VERIFY_WRITE, dirent, count))
-		return -EFAULT;
-
-	f = fdget_pos(fd);
-	if (!f.file)
-		return -EBADF;
-
-	error = iterate_dir(f.file, &buf.ctx);
-	if (error >= 0)
-		error = buf.error;
-	lastdirent = buf.previous;
-	if (lastdirent) {
-		typeof(lastdirent->d_off) d_off = buf.ctx.pos;
-		if (__put_user_unaligned(d_off, &lastdirent->d_off))
-			error = -EFAULT;
-		else
-			error = count - buf.count;
-	}
-	fdput_pos(f);
-	return error;
-}
-#endif /* __ARCH_WANT_COMPAT_SYS_GETDENTS64 */
-
-/*
- * Exactly like fs/open.c:sys_open(), except that it doesn't set the
- * O_LARGEFILE flag.
- */
-COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
-{
-	return do_sys_open(AT_FDCWD, filename, flags, mode);
-}
-
-/*
- * Exactly like fs/open.c:sys_openat(), except that it doesn't set the
- * O_LARGEFILE flag.
- */
-COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode)
-{
-	return do_sys_open(dfd, filename, flags, mode);
-}
-
-#define __COMPAT_NFDBITS       (8 * sizeof(compat_ulong_t))
-
-static int poll_select_copy_remaining(struct timespec *end_time, void __user *p,
-				      int timeval, int ret)
-{
-	struct timespec ts;
-
-	if (!p)
-		return ret;
-
-	if (current->personality & STICKY_TIMEOUTS)
-		goto sticky;
-
-	/* No update for zero timeout */
-	if (!end_time->tv_sec && !end_time->tv_nsec)
-		return ret;
-
-	ktime_get_ts(&ts);
-	ts = timespec_sub(*end_time, ts);
-	if (ts.tv_sec < 0)
-		ts.tv_sec = ts.tv_nsec = 0;
-
-	if (timeval) {
-		struct compat_timeval rtv;
-
-		rtv.tv_sec = ts.tv_sec;
-		rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
-
-		if (!copy_to_user(p, &rtv, sizeof(rtv)))
-			return ret;
-	} else {
-		struct compat_timespec rts;
-
-		rts.tv_sec = ts.tv_sec;
-		rts.tv_nsec = ts.tv_nsec;
-
-		if (!copy_to_user(p, &rts, sizeof(rts)))
-			return ret;
-	}
-	/*
-	 * If an application puts its timeval in read-only memory, we
-	 * don't want the Linux-specific update to the timeval to
-	 * cause a fault after the select has completed
-	 * successfully. However, because we're not updating the
-	 * timeval, we can't restart the system call.
-	 */
-
-sticky:
-	if (ret == -ERESTARTNOHAND)
-		ret = -EINTR;
-	return ret;
-}
-
-/*
- * Ooo, nasty.  We need here to frob 32-bit unsigned longs to
- * 64-bit unsigned longs.
- */
-static
-int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
-			unsigned long *fdset)
-{
-	nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS);
-	if (ufdset) {
-		unsigned long odd;
-
-		if (!access_ok(VERIFY_WRITE, ufdset, nr*sizeof(compat_ulong_t)))
-			return -EFAULT;
-
-		odd = nr & 1UL;
-		nr &= ~1UL;
-		while (nr) {
-			unsigned long h, l;
-			if (__get_user(l, ufdset) || __get_user(h, ufdset+1))
-				return -EFAULT;
-			ufdset += 2;
-			*fdset++ = h << 32 | l;
-			nr -= 2;
-		}
-		if (odd && __get_user(*fdset, ufdset))
-			return -EFAULT;
-	} else {
-		/* Tricky, must clear full unsigned long in the
-		 * kernel fdset at the end, this makes sure that
-		 * actually happens.
-		 */
-		memset(fdset, 0, ((nr + 1) & ~1)*sizeof(compat_ulong_t));
-	}
-	return 0;
-}
-
-static
-int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
-		      unsigned long *fdset)
-{
-	unsigned long odd;
-	nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS);
-
-	if (!ufdset)
-		return 0;
-
-	odd = nr & 1UL;
-	nr &= ~1UL;
-	while (nr) {
-		unsigned long h, l;
-		l = *fdset++;
-		h = l >> 32;
-		if (__put_user(l, ufdset) || __put_user(h, ufdset+1))
-			return -EFAULT;
-		ufdset += 2;
-		nr -= 2;
-	}
-	if (odd && __put_user(*fdset, ufdset))
-		return -EFAULT;
-	return 0;
-}
-
-
-/*
- * This is a virtual copy of sys_select from fs/select.c and probably
- * should be compared to it from time to time
- */
-
-/*
- * We can actually return ERESTARTSYS instead of EINTR, but I'd
- * like to be certain this leads to no problems. So I return
- * EINTR just for safety.
- *
- * Update: ERESTARTSYS breaks at least the xview clock binary, so
- * I'm trying ERESTARTNOHAND which restart only when you want to.
- */
-int compat_core_sys_select(int n, compat_ulong_t __user *inp,
-	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
-	struct timespec *end_time)
-{
-	fd_set_bits fds;
-	void *bits;
-	int size, max_fds, ret = -EINVAL;
-	struct fdtable *fdt;
-	long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
-
-	if (n < 0)
-		goto out_nofds;
-
-	/* max_fds can increase, so grab it once to avoid race */
-	rcu_read_lock();
-	fdt = files_fdtable(current->files);
-	max_fds = fdt->max_fds;
-	rcu_read_unlock();
-	if (n > max_fds)
-		n = max_fds;
-
-	/*
-	 * We need 6 bitmaps (in/out/ex for both incoming and outgoing),
-	 * since we used fdset we need to allocate memory in units of
-	 * long-words.
-	 */
-	size = FDS_BYTES(n);
-	bits = stack_fds;
-	if (size > sizeof(stack_fds) / 6) {
-		bits = kmalloc(6 * size, GFP_KERNEL);
-		ret = -ENOMEM;
-		if (!bits)
-			goto out_nofds;
-	}
-	fds.in      = (unsigned long *)  bits;
-	fds.out     = (unsigned long *) (bits +   size);
-	fds.ex      = (unsigned long *) (bits + 2*size);
-	fds.res_in  = (unsigned long *) (bits + 3*size);
-	fds.res_out = (unsigned long *) (bits + 4*size);
-	fds.res_ex  = (unsigned long *) (bits + 5*size);
-
-	if ((ret = compat_get_fd_set(n, inp, fds.in)) ||
-	    (ret = compat_get_fd_set(n, outp, fds.out)) ||
-	    (ret = compat_get_fd_set(n, exp, fds.ex)))
-		goto out;
-	zero_fd_set(n, fds.res_in);
-	zero_fd_set(n, fds.res_out);
-	zero_fd_set(n, fds.res_ex);
-
-	ret = do_select(n, &fds, end_time);
-
-	if (ret < 0)
-		goto out;
-	if (!ret) {
-		ret = -ERESTARTNOHAND;
-		if (signal_pending(current))
-			goto out;
-		ret = 0;
-	}
-
-	if (compat_set_fd_set(n, inp, fds.res_in) ||
-	    compat_set_fd_set(n, outp, fds.res_out) ||
-	    compat_set_fd_set(n, exp, fds.res_ex))
-		ret = -EFAULT;
-out:
-	if (bits != stack_fds)
-		kfree(bits);
-out_nofds:
-	return ret;
-}
-
-COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp,
-	compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
-	struct compat_timeval __user *, tvp)
-{
-	struct timespec end_time, *to = NULL;
-	struct compat_timeval tv;
-	int ret;
-
-	if (tvp) {
-		if (copy_from_user(&tv, tvp, sizeof(tv)))
-			return -EFAULT;
-
-		to = &end_time;
-		if (poll_select_set_timeout(to,
-				tv.tv_sec + (tv.tv_usec / USEC_PER_SEC),
-				(tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC))
-			return -EINVAL;
-	}
-
-	ret = compat_core_sys_select(n, inp, outp, exp, to);
-	ret = poll_select_copy_remaining(&end_time, tvp, 1, ret);
-
-	return ret;
-}
-
-struct compat_sel_arg_struct {
-	compat_ulong_t n;
-	compat_uptr_t inp;
-	compat_uptr_t outp;
-	compat_uptr_t exp;
-	compat_uptr_t tvp;
-};
-
-COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg)
-{
-	struct compat_sel_arg_struct a;
-
-	if (copy_from_user(&a, arg, sizeof(a)))
-		return -EFAULT;
-	return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp),
-				 compat_ptr(a.exp), compat_ptr(a.tvp));
-}
-
-static long do_compat_pselect(int n, compat_ulong_t __user *inp,
-	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
-	struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask,
-	compat_size_t sigsetsize)
-{
-	compat_sigset_t ss32;
-	sigset_t ksigmask, sigsaved;
-	struct compat_timespec ts;
-	struct timespec end_time, *to = NULL;
-	int ret;
-
-	if (tsp) {
-		if (copy_from_user(&ts, tsp, sizeof(ts)))
-			return -EFAULT;
-
-		to = &end_time;
-		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
-			return -EINVAL;
-	}
-
-	if (sigmask) {
-		if (sigsetsize != sizeof(compat_sigset_t))
-			return -EINVAL;
-		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
-			return -EFAULT;
-		sigset_from_compat(&ksigmask, &ss32);
-
-		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
-		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
-	}
-
-	ret = compat_core_sys_select(n, inp, outp, exp, to);
-	ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
-
-	if (ret == -ERESTARTNOHAND) {
-		/*
-		 * Don't restore the signal mask yet. Let do_signal() deliver
-		 * the signal on the way back to userspace, before the signal
-		 * mask is restored.
-		 */
-		if (sigmask) {
-			memcpy(&current->saved_sigmask, &sigsaved,
-					sizeof(sigsaved));
-			set_restore_sigmask();
-		}
-	} else if (sigmask)
-		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
-
-	return ret;
-}
-
-COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp,
-	compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
-	struct compat_timespec __user *, tsp, void __user *, sig)
-{
-	compat_size_t sigsetsize = 0;
-	compat_uptr_t up = 0;
-
-	if (sig) {
-		if (!access_ok(VERIFY_READ, sig,
-				sizeof(compat_uptr_t)+sizeof(compat_size_t)) ||
-		    	__get_user(up, (compat_uptr_t __user *)sig) ||
-		    	__get_user(sigsetsize,
-				(compat_size_t __user *)(sig+sizeof(up))))
-			return -EFAULT;
-	}
-	return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(up),
-				 sigsetsize);
-}
-
-COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds,
-	unsigned int,  nfds, struct compat_timespec __user *, tsp,
-	const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize)
-{
-	compat_sigset_t ss32;
-	sigset_t ksigmask, sigsaved;
-	struct compat_timespec ts;
-	struct timespec end_time, *to = NULL;
-	int ret;
-
-	if (tsp) {
-		if (copy_from_user(&ts, tsp, sizeof(ts)))
-			return -EFAULT;
-
-		to = &end_time;
-		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
-			return -EINVAL;
-	}
-
-	if (sigmask) {
-		if (sigsetsize != sizeof(compat_sigset_t))
-			return -EINVAL;
-		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
-			return -EFAULT;
-		sigset_from_compat(&ksigmask, &ss32);
-
-		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
-		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
-	}
-
-	ret = do_sys_poll(ufds, nfds, to);
-
-	/* We can restart this syscall, usually */
-	if (ret == -EINTR) {
-		/*
-		 * Don't restore the signal mask yet. Let do_signal() deliver
-		 * the signal on the way back to userspace, before the signal
-		 * mask is restored.
-		 */
-		if (sigmask) {
-			memcpy(&current->saved_sigmask, &sigsaved,
-				sizeof(sigsaved));
-			set_restore_sigmask();
-		}
-		ret = -ERESTARTNOHAND;
-	} else if (sigmask)
-		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
-
-	ret = poll_select_copy_remaining(&end_time, tsp, 0, ret);
-
-	return ret;
-}
-
-#ifdef CONFIG_FHANDLE
-/*
- * Exactly like fs/open.c:sys_open_by_handle_at(), except that it
- * doesn't set the O_LARGEFILE flag.
- */
-COMPAT_SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
-			     struct file_handle __user *, handle, int, flags)
-{
-	return do_handle_open(mountdirfd, handle, flags);
-}
-#endif
diff --git a/fs/compat_binfmt_elf.c b/fs/compat_binfmt_elf.c
index 4d24d17bcfc1..504b3c3539dc 100644
--- a/fs/compat_binfmt_elf.c
+++ b/fs/compat_binfmt_elf.c
@@ -51,22 +51,8 @@
 #define elf_prstatus	compat_elf_prstatus
 #define elf_prpsinfo	compat_elf_prpsinfo
 
-/*
- * Compat version of cputime_to_compat_timeval, perhaps this
- * should be an inline in <linux/compat.h>.
- */
-static void cputime_to_compat_timeval(const cputime_t cputime,
-				      struct compat_timeval *value)
-{
-	struct timeval tv;
-	cputime_to_timeval(cputime, &tv);
-	value->tv_sec = tv.tv_sec;
-	value->tv_usec = tv.tv_usec;
-}
-
-#undef cputime_to_timeval
-#define cputime_to_timeval cputime_to_compat_timeval
-
+#undef ns_to_timeval
+#define ns_to_timeval ns_to_compat_timeval
 
 /*
  * To use this file, asm/elf.h must define compat_elf_check_arch.
diff --git a/fs/compat_ioctl.c b/fs/compat_ioctl.c
index 11d087b2b28e..2dd4a7af7dd7 100644
--- a/fs/compat_ioctl.c
+++ b/fs/compat_ioctl.c
@@ -739,23 +739,22 @@ static int do_i2c_smbus_ioctl(struct file *file,
 		unsigned int cmd, struct i2c_smbus_ioctl_data32   __user *udata)
 {
 	struct i2c_smbus_ioctl_data	__user *tdata;
-	compat_caddr_t			datap;
+	union {
+		/* beginnings of those have identical layouts */
+		struct i2c_smbus_ioctl_data32	data32;
+		struct i2c_smbus_ioctl_data	data;
+	} v;
 
 	tdata = compat_alloc_user_space(sizeof(*tdata));
 	if (tdata == NULL)
 		return -ENOMEM;
-	if (!access_ok(VERIFY_WRITE, tdata, sizeof(*tdata)))
-		return -EFAULT;
 
-	if (!access_ok(VERIFY_READ, udata, sizeof(*udata)))
+	memset(&v, 0, sizeof(v));
+	if (copy_from_user(&v.data32, udata, sizeof(v.data32)))
 		return -EFAULT;
+	v.data.data = compat_ptr(v.data32.data);
 
-	if (__copy_in_user(&tdata->read_write, &udata->read_write, 2 * sizeof(u8)))
-		return -EFAULT;
-	if (__copy_in_user(&tdata->size, &udata->size, 2 * sizeof(u32)))
-		return -EFAULT;
-	if (__get_user(datap, &udata->data) ||
-	    __put_user(compat_ptr(datap), &tdata->data))
+	if (copy_to_user(tdata, &v.data, sizeof(v.data)))
 		return -EFAULT;
 
 	return do_ioctl(file, cmd, (unsigned long)tdata);
@@ -833,7 +832,7 @@ static int compat_ioctl_preallocate(struct file *file,
  */
 #define XFORM(i) (((i) ^ ((i) << 27) ^ ((i) << 17)) & 0xffffffff)
 
-#define COMPATIBLE_IOCTL(cmd) XFORM(cmd),
+#define COMPATIBLE_IOCTL(cmd) XFORM((u32)cmd),
 /* ioctl should not be warned about even if it's not implemented.
    Valid reasons to use this:
    - It is implemented with ->compat_ioctl on some device, but programs
@@ -866,8 +865,6 @@ COMPATIBLE_IOCTL(TIOCGDEV)
 COMPATIBLE_IOCTL(TIOCCBRK)
 COMPATIBLE_IOCTL(TIOCGSID)
 COMPATIBLE_IOCTL(TIOCGICOUNT)
-COMPATIBLE_IOCTL(TIOCGPKT)
-COMPATIBLE_IOCTL(TIOCGPTLCK)
 COMPATIBLE_IOCTL(TIOCGEXCL)
 /* Little t */
 COMPATIBLE_IOCTL(TIOCGETD)
@@ -883,16 +880,12 @@ COMPATIBLE_IOCTL(TIOCMGET)
 COMPATIBLE_IOCTL(TIOCMBIC)
 COMPATIBLE_IOCTL(TIOCMBIS)
 COMPATIBLE_IOCTL(TIOCMSET)
-COMPATIBLE_IOCTL(TIOCPKT)
 COMPATIBLE_IOCTL(TIOCNOTTY)
 COMPATIBLE_IOCTL(TIOCSTI)
 COMPATIBLE_IOCTL(TIOCOUTQ)
 COMPATIBLE_IOCTL(TIOCSPGRP)
 COMPATIBLE_IOCTL(TIOCGPGRP)
-COMPATIBLE_IOCTL(TIOCGPTN)
-COMPATIBLE_IOCTL(TIOCSPTLCK)
 COMPATIBLE_IOCTL(TIOCSERGETLSR)
-COMPATIBLE_IOCTL(TIOCSIG)
 #ifdef TIOCSRS485
 COMPATIBLE_IOCTL(TIOCSRS485)
 #endif
diff --git a/fs/configfs/item.c b/fs/configfs/item.c
index 8b2a994042dd..a66f6624d899 100644
--- a/fs/configfs/item.c
+++ b/fs/configfs/item.c
@@ -138,6 +138,14 @@ struct config_item *config_item_get(struct config_item *item)
 }
 EXPORT_SYMBOL(config_item_get);
 
+struct config_item *config_item_get_unless_zero(struct config_item *item)
+{
+	if (item && kref_get_unless_zero(&item->ci_kref))
+		return item;
+	return NULL;
+}
+EXPORT_SYMBOL(config_item_get_unless_zero);
+
 static void config_item_cleanup(struct config_item *item)
 {
 	struct config_item_type *t = item->ci_type;
diff --git a/fs/configfs/symlink.c b/fs/configfs/symlink.c
index a6ab012a2c6a..c8aabba502f6 100644
--- a/fs/configfs/symlink.c
+++ b/fs/configfs/symlink.c
@@ -83,14 +83,13 @@ static int create_link(struct config_item *parent_item,
 	ret = -ENOMEM;
 	sl = kmalloc(sizeof(struct configfs_symlink), GFP_KERNEL);
 	if (sl) {
-		sl->sl_target = config_item_get(item);
 		spin_lock(&configfs_dirent_lock);
 		if (target_sd->s_type & CONFIGFS_USET_DROPPING) {
 			spin_unlock(&configfs_dirent_lock);
-			config_item_put(item);
 			kfree(sl);
 			return -ENOENT;
 		}
+		sl->sl_target = config_item_get(item);
 		list_add(&sl->sl_list, &target_sd->s_links);
 		spin_unlock(&configfs_dirent_lock);
 		ret = configfs_create_link(sl, parent_item->ci_dentry,
diff --git a/fs/coredump.c b/fs/coredump.c
index ae6b05629ca1..592683711c64 100644
--- a/fs/coredump.c
+++ b/fs/coredump.c
@@ -16,6 +16,9 @@
 #include <linux/personality.h>
 #include <linux/binfmts.h>
 #include <linux/coredump.h>
+#include <linux/sched/coredump.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task_stack.h>
 #include <linux/utsname.h>
 #include <linux/pid_namespace.h>
 #include <linux/module.h>
@@ -33,7 +36,6 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/oom.h>
 #include <linux/compat.h>
-#include <linux/sched.h>
 #include <linux/fs.h>
 #include <linux/path.h>
 #include <linux/timekeeping.h>
diff --git a/fs/crypto/Kconfig b/fs/crypto/Kconfig
index f514978f6688..02b7d91c9231 100644
--- a/fs/crypto/Kconfig
+++ b/fs/crypto/Kconfig
@@ -1,6 +1,5 @@
 config FS_ENCRYPTION
 	tristate "FS Encryption (Per-file encryption)"
-	depends on BLOCK
 	select CRYPTO
 	select CRYPTO_AES
 	select CRYPTO_CBC
@@ -8,6 +7,7 @@ config FS_ENCRYPTION
 	select CRYPTO_XTS
 	select CRYPTO_CTS
 	select CRYPTO_CTR
+	select CRYPTO_SHA256
 	select KEYS
 	help
 	  Enable encryption of files and directories.  This
diff --git a/fs/crypto/Makefile b/fs/crypto/Makefile
index f17684c48739..9f6607f17b53 100644
--- a/fs/crypto/Makefile
+++ b/fs/crypto/Makefile
@@ -1,3 +1,4 @@
 obj-$(CONFIG_FS_ENCRYPTION)	+= fscrypto.o
 
 fscrypto-y := crypto.o fname.o policy.o keyinfo.o
+fscrypto-$(CONFIG_BLOCK) += bio.o
diff --git a/fs/crypto/bio.c b/fs/crypto/bio.c
new file mode 100644
index 000000000000..6181e9526860
--- /dev/null
+++ b/fs/crypto/bio.c
@@ -0,0 +1,145 @@
+/*
+ * This contains encryption functions for per-file encryption.
+ *
+ * Copyright (C) 2015, Google, Inc.
+ * Copyright (C) 2015, Motorola Mobility
+ *
+ * Written by Michael Halcrow, 2014.
+ *
+ * Filename encryption additions
+ *	Uday Savagaonkar, 2014
+ * Encryption policy handling additions
+ *	Ildar Muslukhov, 2014
+ * Add fscrypt_pullback_bio_page()
+ *	Jaegeuk Kim, 2015.
+ *
+ * This has not yet undergone a rigorous security audit.
+ *
+ * The usage of AES-XTS should conform to recommendations in NIST
+ * Special Publication 800-38E and IEEE P1619/D16.
+ */
+
+#include <linux/pagemap.h>
+#include <linux/module.h>
+#include <linux/bio.h>
+#include <linux/namei.h>
+#include "fscrypt_private.h"
+
+/*
+ * Call fscrypt_decrypt_page on every single page, reusing the encryption
+ * context.
+ */
+static void completion_pages(struct work_struct *work)
+{
+	struct fscrypt_ctx *ctx =
+		container_of(work, struct fscrypt_ctx, r.work);
+	struct bio *bio = ctx->r.bio;
+	struct bio_vec *bv;
+	int i;
+
+	bio_for_each_segment_all(bv, bio, i) {
+		struct page *page = bv->bv_page;
+		int ret = fscrypt_decrypt_page(page->mapping->host, page,
+				PAGE_SIZE, 0, page->index);
+
+		if (ret) {
+			WARN_ON_ONCE(1);
+			SetPageError(page);
+		} else {
+			SetPageUptodate(page);
+		}
+		unlock_page(page);
+	}
+	fscrypt_release_ctx(ctx);
+	bio_put(bio);
+}
+
+void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio)
+{
+	INIT_WORK(&ctx->r.work, completion_pages);
+	ctx->r.bio = bio;
+	queue_work(fscrypt_read_workqueue, &ctx->r.work);
+}
+EXPORT_SYMBOL(fscrypt_decrypt_bio_pages);
+
+void fscrypt_pullback_bio_page(struct page **page, bool restore)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *bounce_page;
+
+	/* The bounce data pages are unmapped. */
+	if ((*page)->mapping)
+		return;
+
+	/* The bounce data page is unmapped. */
+	bounce_page = *page;
+	ctx = (struct fscrypt_ctx *)page_private(bounce_page);
+
+	/* restore control page */
+	*page = ctx->w.control_page;
+
+	if (restore)
+		fscrypt_restore_control_page(bounce_page);
+}
+EXPORT_SYMBOL(fscrypt_pullback_bio_page);
+
+int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
+				sector_t pblk, unsigned int len)
+{
+	struct fscrypt_ctx *ctx;
+	struct page *ciphertext_page = NULL;
+	struct bio *bio;
+	int ret, err = 0;
+
+	BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
+
+	ctx = fscrypt_get_ctx(inode, GFP_NOFS);
+	if (IS_ERR(ctx))
+		return PTR_ERR(ctx);
+
+	ciphertext_page = fscrypt_alloc_bounce_page(ctx, GFP_NOWAIT);
+	if (IS_ERR(ciphertext_page)) {
+		err = PTR_ERR(ciphertext_page);
+		goto errout;
+	}
+
+	while (len--) {
+		err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk,
+					     ZERO_PAGE(0), ciphertext_page,
+					     PAGE_SIZE, 0, GFP_NOFS);
+		if (err)
+			goto errout;
+
+		bio = bio_alloc(GFP_NOWAIT, 1);
+		if (!bio) {
+			err = -ENOMEM;
+			goto errout;
+		}
+		bio->bi_bdev = inode->i_sb->s_bdev;
+		bio->bi_iter.bi_sector =
+			pblk << (inode->i_sb->s_blocksize_bits - 9);
+		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
+		ret = bio_add_page(bio, ciphertext_page,
+					inode->i_sb->s_blocksize, 0);
+		if (ret != inode->i_sb->s_blocksize) {
+			/* should never happen! */
+			WARN_ON(1);
+			bio_put(bio);
+			err = -EIO;
+			goto errout;
+		}
+		err = submit_bio_wait(bio);
+		if (err == 0 && bio->bi_status)
+			err = -EIO;
+		bio_put(bio);
+		if (err)
+			goto errout;
+		lblk++;
+		pblk++;
+	}
+	err = 0;
+errout:
+	fscrypt_release_ctx(ctx);
+	return err;
+}
+EXPORT_SYMBOL(fscrypt_zeroout_range);
diff --git a/fs/crypto/crypto.c b/fs/crypto/crypto.c
index ac8e4f6a3773..c7835df7e7b8 100644
--- a/fs/crypto/crypto.c
+++ b/fs/crypto/crypto.c
@@ -24,9 +24,9 @@
 #include <linux/module.h>
 #include <linux/scatterlist.h>
 #include <linux/ratelimit.h>
-#include <linux/bio.h>
 #include <linux/dcache.h>
 #include <linux/namei.h>
+#include <crypto/aes.h>
 #include "fscrypt_private.h"
 
 static unsigned int num_prealloc_crypto_pages = 32;
@@ -44,7 +44,7 @@ static mempool_t *fscrypt_bounce_page_pool = NULL;
 static LIST_HEAD(fscrypt_free_ctxs);
 static DEFINE_SPINLOCK(fscrypt_ctx_lock);
 
-static struct workqueue_struct *fscrypt_read_workqueue;
+struct workqueue_struct *fscrypt_read_workqueue;
 static DEFINE_MUTEX(fscrypt_init_mutex);
 
 static struct kmem_cache *fscrypt_ctx_cachep;
@@ -141,21 +141,15 @@ static void page_crypt_complete(struct crypto_async_request *req, int res)
 	complete(&ecr->completion);
 }
 
-typedef enum {
-	FS_DECRYPT = 0,
-	FS_ENCRYPT,
-} fscrypt_direction_t;
-
-static int do_page_crypto(const struct inode *inode,
-			fscrypt_direction_t rw, u64 lblk_num,
-			struct page *src_page, struct page *dest_page,
-			unsigned int len, unsigned int offs,
-			gfp_t gfp_flags)
+int fscrypt_do_page_crypto(const struct inode *inode, fscrypt_direction_t rw,
+			   u64 lblk_num, struct page *src_page,
+			   struct page *dest_page, unsigned int len,
+			   unsigned int offs, gfp_t gfp_flags)
 {
 	struct {
 		__le64 index;
-		u8 padding[FS_XTS_TWEAK_SIZE - sizeof(__le64)];
-	} xts_tweak;
+		u8 padding[FS_IV_SIZE - sizeof(__le64)];
+	} iv;
 	struct skcipher_request *req = NULL;
 	DECLARE_FS_COMPLETION_RESULT(ecr);
 	struct scatterlist dst, src;
@@ -165,6 +159,16 @@ static int do_page_crypto(const struct inode *inode,
 
 	BUG_ON(len == 0);
 
+	BUILD_BUG_ON(sizeof(iv) != FS_IV_SIZE);
+	BUILD_BUG_ON(AES_BLOCK_SIZE != FS_IV_SIZE);
+	iv.index = cpu_to_le64(lblk_num);
+	memset(iv.padding, 0, sizeof(iv.padding));
+
+	if (ci->ci_essiv_tfm != NULL) {
+		crypto_cipher_encrypt_one(ci->ci_essiv_tfm, (u8 *)&iv,
+					  (u8 *)&iv);
+	}
+
 	req = skcipher_request_alloc(tfm, gfp_flags);
 	if (!req) {
 		printk_ratelimited(KERN_ERR
@@ -177,15 +181,11 @@ static int do_page_crypto(const struct inode *inode,
 		req, CRYPTO_TFM_REQ_MAY_BACKLOG | CRYPTO_TFM_REQ_MAY_SLEEP,
 		page_crypt_complete, &ecr);
 
-	BUILD_BUG_ON(sizeof(xts_tweak) != FS_XTS_TWEAK_SIZE);
-	xts_tweak.index = cpu_to_le64(lblk_num);
-	memset(xts_tweak.padding, 0, sizeof(xts_tweak.padding));
-
 	sg_init_table(&dst, 1);
 	sg_set_page(&dst, dest_page, len, offs);
 	sg_init_table(&src, 1);
 	sg_set_page(&src, src_page, len, offs);
-	skcipher_request_set_crypt(req, &src, &dst, len, &xts_tweak);
+	skcipher_request_set_crypt(req, &src, &dst, len, &iv);
 	if (rw == FS_DECRYPT)
 		res = crypto_skcipher_decrypt(req);
 	else
@@ -205,7 +205,8 @@ static int do_page_crypto(const struct inode *inode,
 	return 0;
 }
 
-static struct page *alloc_bounce_page(struct fscrypt_ctx *ctx, gfp_t gfp_flags)
+struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx,
+				       gfp_t gfp_flags)
 {
 	ctx->w.bounce_page = mempool_alloc(fscrypt_bounce_page_pool, gfp_flags);
 	if (ctx->w.bounce_page == NULL)
@@ -260,9 +261,9 @@ struct page *fscrypt_encrypt_page(const struct inode *inode,
 
 	if (inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES) {
 		/* with inplace-encryption we just encrypt the page */
-		err = do_page_crypto(inode, FS_ENCRYPT, lblk_num,
-					page, ciphertext_page,
-					len, offs, gfp_flags);
+		err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk_num, page,
+					     ciphertext_page, len, offs,
+					     gfp_flags);
 		if (err)
 			return ERR_PTR(err);
 
@@ -276,14 +277,14 @@ struct page *fscrypt_encrypt_page(const struct inode *inode,
 		return (struct page *)ctx;
 
 	/* The encryption operation will require a bounce page. */
-	ciphertext_page = alloc_bounce_page(ctx, gfp_flags);
+	ciphertext_page = fscrypt_alloc_bounce_page(ctx, gfp_flags);
 	if (IS_ERR(ciphertext_page))
 		goto errout;
 
 	ctx->w.control_page = page;
-	err = do_page_crypto(inode, FS_ENCRYPT, lblk_num,
-					page, ciphertext_page,
-					len, offs, gfp_flags);
+	err = fscrypt_do_page_crypto(inode, FS_ENCRYPT, lblk_num,
+				     page, ciphertext_page, len, offs,
+				     gfp_flags);
 	if (err) {
 		ciphertext_page = ERR_PTR(err);
 		goto errout;
@@ -320,72 +321,11 @@ int fscrypt_decrypt_page(const struct inode *inode, struct page *page,
 	if (!(inode->i_sb->s_cop->flags & FS_CFLG_OWN_PAGES))
 		BUG_ON(!PageLocked(page));
 
-	return do_page_crypto(inode, FS_DECRYPT, lblk_num, page, page, len,
-			offs, GFP_NOFS);
+	return fscrypt_do_page_crypto(inode, FS_DECRYPT, lblk_num, page, page,
+				      len, offs, GFP_NOFS);
 }
 EXPORT_SYMBOL(fscrypt_decrypt_page);
 
-int fscrypt_zeroout_range(const struct inode *inode, pgoff_t lblk,
-				sector_t pblk, unsigned int len)
-{
-	struct fscrypt_ctx *ctx;
-	struct page *ciphertext_page = NULL;
-	struct bio *bio;
-	int ret, err = 0;
-
-	BUG_ON(inode->i_sb->s_blocksize != PAGE_SIZE);
-
-	ctx = fscrypt_get_ctx(inode, GFP_NOFS);
-	if (IS_ERR(ctx))
-		return PTR_ERR(ctx);
-
-	ciphertext_page = alloc_bounce_page(ctx, GFP_NOWAIT);
-	if (IS_ERR(ciphertext_page)) {
-		err = PTR_ERR(ciphertext_page);
-		goto errout;
-	}
-
-	while (len--) {
-		err = do_page_crypto(inode, FS_ENCRYPT, lblk,
-					ZERO_PAGE(0), ciphertext_page,
-					PAGE_SIZE, 0, GFP_NOFS);
-		if (err)
-			goto errout;
-
-		bio = bio_alloc(GFP_NOWAIT, 1);
-		if (!bio) {
-			err = -ENOMEM;
-			goto errout;
-		}
-		bio->bi_bdev = inode->i_sb->s_bdev;
-		bio->bi_iter.bi_sector =
-			pblk << (inode->i_sb->s_blocksize_bits - 9);
-		bio_set_op_attrs(bio, REQ_OP_WRITE, 0);
-		ret = bio_add_page(bio, ciphertext_page,
-					inode->i_sb->s_blocksize, 0);
-		if (ret != inode->i_sb->s_blocksize) {
-			/* should never happen! */
-			WARN_ON(1);
-			bio_put(bio);
-			err = -EIO;
-			goto errout;
-		}
-		err = submit_bio_wait(bio);
-		if ((err == 0) && bio->bi_error)
-			err = -EIO;
-		bio_put(bio);
-		if (err)
-			goto errout;
-		lblk++;
-		pblk++;
-	}
-	err = 0;
-errout:
-	fscrypt_release_ctx(ctx);
-	return err;
-}
-EXPORT_SYMBOL(fscrypt_zeroout_range);
-
 /*
  * Validate dentries for encrypted directories to make sure we aren't
  * potentially caching stale data after a key has been added or
@@ -394,7 +334,6 @@ EXPORT_SYMBOL(fscrypt_zeroout_range);
 static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct dentry *dir;
-	struct fscrypt_info *ci;
 	int dir_has_key, cached_with_key;
 
 	if (flags & LOOKUP_RCU)
@@ -406,18 +345,11 @@ static int fscrypt_d_revalidate(struct dentry *dentry, unsigned int flags)
 		return 0;
 	}
 
-	ci = d_inode(dir)->i_crypt_info;
-	if (ci && ci->ci_keyring_key &&
-	    (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					  (1 << KEY_FLAG_REVOKED) |
-					  (1 << KEY_FLAG_DEAD))))
-		ci = NULL;
-
 	/* this should eventually be an flag in d_flags */
 	spin_lock(&dentry->d_lock);
 	cached_with_key = dentry->d_flags & DCACHE_ENCRYPTED_WITH_KEY;
 	spin_unlock(&dentry->d_lock);
-	dir_has_key = (ci != NULL);
+	dir_has_key = (d_inode(dir)->i_crypt_info != NULL);
 	dput(dir);
 
 	/*
@@ -442,64 +374,6 @@ const struct dentry_operations fscrypt_d_ops = {
 };
 EXPORT_SYMBOL(fscrypt_d_ops);
 
-/*
- * Call fscrypt_decrypt_page on every single page, reusing the encryption
- * context.
- */
-static void completion_pages(struct work_struct *work)
-{
-	struct fscrypt_ctx *ctx =
-		container_of(work, struct fscrypt_ctx, r.work);
-	struct bio *bio = ctx->r.bio;
-	struct bio_vec *bv;
-	int i;
-
-	bio_for_each_segment_all(bv, bio, i) {
-		struct page *page = bv->bv_page;
-		int ret = fscrypt_decrypt_page(page->mapping->host, page,
-				PAGE_SIZE, 0, page->index);
-
-		if (ret) {
-			WARN_ON_ONCE(1);
-			SetPageError(page);
-		} else {
-			SetPageUptodate(page);
-		}
-		unlock_page(page);
-	}
-	fscrypt_release_ctx(ctx);
-	bio_put(bio);
-}
-
-void fscrypt_decrypt_bio_pages(struct fscrypt_ctx *ctx, struct bio *bio)
-{
-	INIT_WORK(&ctx->r.work, completion_pages);
-	ctx->r.bio = bio;
-	queue_work(fscrypt_read_workqueue, &ctx->r.work);
-}
-EXPORT_SYMBOL(fscrypt_decrypt_bio_pages);
-
-void fscrypt_pullback_bio_page(struct page **page, bool restore)
-{
-	struct fscrypt_ctx *ctx;
-	struct page *bounce_page;
-
-	/* The bounce data pages are unmapped. */
-	if ((*page)->mapping)
-		return;
-
-	/* The bounce data page is unmapped. */
-	bounce_page = *page;
-	ctx = (struct fscrypt_ctx *)page_private(bounce_page);
-
-	/* restore control page */
-	*page = ctx->w.control_page;
-
-	if (restore)
-		fscrypt_restore_control_page(bounce_page);
-}
-EXPORT_SYMBOL(fscrypt_pullback_bio_page);
-
 void fscrypt_restore_control_page(struct page *page)
 {
 	struct fscrypt_ctx *ctx;
@@ -610,6 +484,8 @@ static void __exit fscrypt_exit(void)
 		destroy_workqueue(fscrypt_read_workqueue);
 	kmem_cache_destroy(fscrypt_ctx_cachep);
 	kmem_cache_destroy(fscrypt_info_cachep);
+
+	fscrypt_essiv_cleanup();
 }
 module_exit(fscrypt_exit);
 
diff --git a/fs/crypto/fname.c b/fs/crypto/fname.c
index 56ad9d195f18..ad9f814fdead 100644
--- a/fs/crypto/fname.c
+++ b/fs/crypto/fname.c
@@ -159,6 +159,8 @@ static int fname_decrypt(struct inode *inode,
 static const char *lookup_table =
 	"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789+,";
 
+#define BASE64_CHARS(nbytes)	DIV_ROUND_UP((nbytes) * 4, 3)
+
 /**
  * digest_encode() -
  *
@@ -230,11 +232,14 @@ EXPORT_SYMBOL(fscrypt_fname_encrypted_size);
 int fscrypt_fname_alloc_buffer(const struct inode *inode,
 				u32 ilen, struct fscrypt_str *crypto_str)
 {
-	unsigned int olen = fscrypt_fname_encrypted_size(inode, ilen);
+	u32 olen = fscrypt_fname_encrypted_size(inode, ilen);
+	const u32 max_encoded_len =
+		max_t(u32, BASE64_CHARS(FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE),
+		      1 + BASE64_CHARS(sizeof(struct fscrypt_digested_name)));
 
 	crypto_str->len = olen;
-	if (olen < FS_FNAME_CRYPTO_DIGEST_SIZE * 2)
-		olen = FS_FNAME_CRYPTO_DIGEST_SIZE * 2;
+	olen = max(olen, max_encoded_len);
+
 	/*
 	 * Allocated buffer can hold one more character to null-terminate the
 	 * string
@@ -266,6 +271,10 @@ EXPORT_SYMBOL(fscrypt_fname_free_buffer);
  *
  * The caller must have allocated sufficient memory for the @oname string.
  *
+ * If the key is available, we'll decrypt the disk name; otherwise, we'll encode
+ * it for presentation.  Short names are directly base64-encoded, while long
+ * names are encoded in fscrypt_digested_name format.
+ *
  * Return: 0 on success, -errno on failure
  */
 int fscrypt_fname_disk_to_usr(struct inode *inode,
@@ -274,7 +283,7 @@ int fscrypt_fname_disk_to_usr(struct inode *inode,
 			struct fscrypt_str *oname)
 {
 	const struct qstr qname = FSTR_TO_QSTR(iname);
-	char buf[24];
+	struct fscrypt_digested_name digested_name;
 
 	if (fscrypt_is_dot_dotdot(&qname)) {
 		oname->name[0] = '.';
@@ -289,20 +298,24 @@ int fscrypt_fname_disk_to_usr(struct inode *inode,
 	if (inode->i_crypt_info)
 		return fname_decrypt(inode, iname, oname);
 
-	if (iname->len <= FS_FNAME_CRYPTO_DIGEST_SIZE) {
+	if (iname->len <= FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE) {
 		oname->len = digest_encode(iname->name, iname->len,
 					   oname->name);
 		return 0;
 	}
 	if (hash) {
-		memcpy(buf, &hash, 4);
-		memcpy(buf + 4, &minor_hash, 4);
+		digested_name.hash = hash;
+		digested_name.minor_hash = minor_hash;
 	} else {
-		memset(buf, 0, 8);
+		digested_name.hash = 0;
+		digested_name.minor_hash = 0;
 	}
-	memcpy(buf + 8, iname->name + iname->len - 16, 16);
+	memcpy(digested_name.digest,
+	       FSCRYPT_FNAME_DIGEST(iname->name, iname->len),
+	       FSCRYPT_FNAME_DIGEST_SIZE);
 	oname->name[0] = '_';
-	oname->len = 1 + digest_encode(buf, 24, oname->name + 1);
+	oname->len = 1 + digest_encode((const char *)&digested_name,
+				       sizeof(digested_name), oname->name + 1);
 	return 0;
 }
 EXPORT_SYMBOL(fscrypt_fname_disk_to_usr);
@@ -332,14 +345,39 @@ int fscrypt_fname_usr_to_disk(struct inode *inode,
 	 * in a directory. Consequently, a user space name cannot be mapped to
 	 * a disk-space name
 	 */
-	return -EACCES;
+	return -ENOKEY;
 }
 EXPORT_SYMBOL(fscrypt_fname_usr_to_disk);
 
+/**
+ * fscrypt_setup_filename() - prepare to search a possibly encrypted directory
+ * @dir: the directory that will be searched
+ * @iname: the user-provided filename being searched for
+ * @lookup: 1 if we're allowed to proceed without the key because it's
+ *	->lookup() or we're finding the dir_entry for deletion; 0 if we cannot
+ *	proceed without the key because we're going to create the dir_entry.
+ * @fname: the filename information to be filled in
+ *
+ * Given a user-provided filename @iname, this function sets @fname->disk_name
+ * to the name that would be stored in the on-disk directory entry, if possible.
+ * If the directory is unencrypted this is simply @iname.  Else, if we have the
+ * directory's encryption key, then @iname is the plaintext, so we encrypt it to
+ * get the disk_name.
+ *
+ * Else, for keyless @lookup operations, @iname is the presented ciphertext, so
+ * we decode it to get either the ciphertext disk_name (for short names) or the
+ * fscrypt_digested_name (for long names).  Non-@lookup operations will be
+ * impossible in this case, so we fail them with ENOKEY.
+ *
+ * If successful, fscrypt_free_filename() must be called later to clean up.
+ *
+ * Return: 0 on success, -errno on failure
+ */
 int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 			      int lookup, struct fscrypt_name *fname)
 {
-	int ret = 0, bigname = 0;
+	int ret;
+	int digested;
 
 	memset(fname, 0, sizeof(struct fscrypt_name));
 	fname->usr_fname = iname;
@@ -350,7 +388,7 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 		fname->disk_name.len = iname->len;
 		return 0;
 	}
-	ret = fscrypt_get_crypt_info(dir);
+	ret = fscrypt_get_encryption_info(dir);
 	if (ret && ret != -EOPNOTSUPP)
 		return ret;
 
@@ -367,31 +405,43 @@ int fscrypt_setup_filename(struct inode *dir, const struct qstr *iname,
 		return 0;
 	}
 	if (!lookup)
-		return -EACCES;
+		return -ENOKEY;
 
 	/*
 	 * We don't have the key and we are doing a lookup; decode the
 	 * user-supplied name
 	 */
-	if (iname->name[0] == '_')
-		bigname = 1;
-	if ((bigname && (iname->len != 33)) || (!bigname && (iname->len > 43)))
-		return -ENOENT;
+	if (iname->name[0] == '_') {
+		if (iname->len !=
+		    1 + BASE64_CHARS(sizeof(struct fscrypt_digested_name)))
+			return -ENOENT;
+		digested = 1;
+	} else {
+		if (iname->len >
+		    BASE64_CHARS(FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE))
+			return -ENOENT;
+		digested = 0;
+	}
 
-	fname->crypto_buf.name = kmalloc(32, GFP_KERNEL);
+	fname->crypto_buf.name =
+		kmalloc(max_t(size_t, FSCRYPT_FNAME_MAX_UNDIGESTED_SIZE,
+			      sizeof(struct fscrypt_digested_name)),
+			GFP_KERNEL);
 	if (fname->crypto_buf.name == NULL)
 		return -ENOMEM;
 
-	ret = digest_decode(iname->name + bigname, iname->len - bigname,
+	ret = digest_decode(iname->name + digested, iname->len - digested,
 				fname->crypto_buf.name);
 	if (ret < 0) {
 		ret = -ENOENT;
 		goto errout;
 	}
 	fname->crypto_buf.len = ret;
-	if (bigname) {
-		memcpy(&fname->hash, fname->crypto_buf.name, 4);
-		memcpy(&fname->minor_hash, fname->crypto_buf.name + 4, 4);
+	if (digested) {
+		const struct fscrypt_digested_name *n =
+			(const void *)fname->crypto_buf.name;
+		fname->hash = n->hash;
+		fname->minor_hash = n->minor_hash;
 	} else {
 		fname->disk_name.name = fname->crypto_buf.name;
 		fname->disk_name.len = fname->crypto_buf.len;
@@ -403,12 +453,3 @@ errout:
 	return ret;
 }
 EXPORT_SYMBOL(fscrypt_setup_filename);
-
-void fscrypt_free_filename(struct fscrypt_name *fname)
-{
-	kfree(fname->crypto_buf.name);
-	fname->crypto_buf.name = NULL;
-	fname->usr_fname = NULL;
-	fname->disk_name.name = NULL;
-}
-EXPORT_SYMBOL(fscrypt_free_filename);
diff --git a/fs/crypto/fscrypt_private.h b/fs/crypto/fscrypt_private.h
index aeab032d7d35..a1d5021c31ef 100644
--- a/fs/crypto/fscrypt_private.h
+++ b/fs/crypto/fscrypt_private.h
@@ -11,21 +11,18 @@
 #ifndef _FSCRYPT_PRIVATE_H
 #define _FSCRYPT_PRIVATE_H
 
-#include <linux/fscrypto.h>
-
-#define FS_FNAME_CRYPTO_DIGEST_SIZE	32
+#include <linux/fscrypt_supp.h>
+#include <crypto/hash.h>
 
 /* Encryption parameters */
-#define FS_XTS_TWEAK_SIZE		16
+#define FS_IV_SIZE			16
 #define FS_AES_128_ECB_KEY_SIZE		16
+#define FS_AES_128_CBC_KEY_SIZE		16
+#define FS_AES_128_CTS_KEY_SIZE		16
 #define FS_AES_256_GCM_KEY_SIZE		32
 #define FS_AES_256_CBC_KEY_SIZE		32
 #define FS_AES_256_CTS_KEY_SIZE		32
 #define FS_AES_256_XTS_KEY_SIZE		64
-#define FS_MAX_KEY_SIZE			64
-
-#define FS_KEY_DESC_PREFIX		"fscrypt:"
-#define FS_KEY_DESC_PREFIX_SIZE		8
 
 #define FS_KEY_DERIVATION_NONCE_SIZE		16
 
@@ -51,13 +48,6 @@ struct fscrypt_context {
 
 #define FS_ENCRYPTION_CONTEXT_FORMAT_V1		1
 
-/* This is passed in from userspace into the kernel keyring */
-struct fscrypt_key {
-	u32 mode;
-	u8 raw[FS_MAX_KEY_SIZE];
-	u32 size;
-} __packed;
-
 /*
  * A pointer to this structure is stored in the file system's in-core
  * representation of an inode.
@@ -67,10 +57,15 @@ struct fscrypt_info {
 	u8 ci_filename_mode;
 	u8 ci_flags;
 	struct crypto_skcipher *ci_ctfm;
-	struct key *ci_keyring_key;
+	struct crypto_cipher *ci_essiv_tfm;
 	u8 ci_master_key[FS_KEY_DESCRIPTOR_SIZE];
 };
 
+typedef enum {
+	FS_DECRYPT = 0,
+	FS_ENCRYPT,
+} fscrypt_direction_t;
+
 #define FS_CTX_REQUIRES_FREE_ENCRYPT_FL		0x00000001
 #define FS_CTX_HAS_BOUNCE_BUFFER_FL		0x00000002
 
@@ -81,13 +76,22 @@ struct fscrypt_completion_result {
 
 #define DECLARE_FS_COMPLETION_RESULT(ecr) \
 	struct fscrypt_completion_result ecr = { \
-		COMPLETION_INITIALIZER((ecr).completion), 0 }
+		COMPLETION_INITIALIZER_ONSTACK((ecr).completion), 0 }
 
 
 /* crypto.c */
-int fscrypt_initialize(unsigned int cop_flags);
+extern int fscrypt_initialize(unsigned int cop_flags);
+extern struct workqueue_struct *fscrypt_read_workqueue;
+extern int fscrypt_do_page_crypto(const struct inode *inode,
+				  fscrypt_direction_t rw, u64 lblk_num,
+				  struct page *src_page,
+				  struct page *dest_page,
+				  unsigned int len, unsigned int offs,
+				  gfp_t gfp_flags);
+extern struct page *fscrypt_alloc_bounce_page(struct fscrypt_ctx *ctx,
+					      gfp_t gfp_flags);
 
 /* keyinfo.c */
-extern int fscrypt_get_crypt_info(struct inode *);
+extern void __exit fscrypt_essiv_cleanup(void);
 
 #endif /* _FSCRYPT_PRIVATE_H */
diff --git a/fs/crypto/keyinfo.c b/fs/crypto/keyinfo.c
index 95cd4c3b06c3..018c588c7ac3 100644
--- a/fs/crypto/keyinfo.c
+++ b/fs/crypto/keyinfo.c
@@ -10,8 +10,13 @@
 
 #include <keys/user-type.h>
 #include <linux/scatterlist.h>
+#include <linux/ratelimit.h>
+#include <crypto/aes.h>
+#include <crypto/sha.h>
 #include "fscrypt_private.h"
 
+static struct crypto_shash *essiv_hash_tfm;
+
 static void derive_crypt_complete(struct crypto_async_request *req, int rc)
 {
 	struct fscrypt_completion_result *ecr = req->data;
@@ -27,13 +32,13 @@ static void derive_crypt_complete(struct crypto_async_request *req, int rc)
  * derive_key_aes() - Derive a key using AES-128-ECB
  * @deriving_key: Encryption key used for derivation.
  * @source_key:   Source key to which to apply derivation.
- * @derived_key:  Derived key.
+ * @derived_raw_key:  Derived raw key.
  *
  * Return: Zero on success; non-zero otherwise.
  */
 static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
-				u8 source_key[FS_AES_256_XTS_KEY_SIZE],
-				u8 derived_key[FS_AES_256_XTS_KEY_SIZE])
+				const struct fscrypt_key *source_key,
+				u8 derived_raw_key[FS_MAX_KEY_SIZE])
 {
 	int res = 0;
 	struct skcipher_request *req = NULL;
@@ -60,10 +65,10 @@ static int derive_key_aes(u8 deriving_key[FS_AES_128_ECB_KEY_SIZE],
 	if (res < 0)
 		goto out;
 
-	sg_init_one(&src_sg, source_key, FS_AES_256_XTS_KEY_SIZE);
-	sg_init_one(&dst_sg, derived_key, FS_AES_256_XTS_KEY_SIZE);
-	skcipher_request_set_crypt(req, &src_sg, &dst_sg,
-					FS_AES_256_XTS_KEY_SIZE, NULL);
+	sg_init_one(&src_sg, source_key->raw, source_key->size);
+	sg_init_one(&dst_sg, derived_raw_key, source_key->size);
+	skcipher_request_set_crypt(req, &src_sg, &dst_sg, source_key->size,
+				   NULL);
 	res = crypto_skcipher_encrypt(req);
 	if (res == -EINPROGRESS || res == -EBUSY) {
 		wait_for_completion(&ecr.completion);
@@ -77,28 +82,25 @@ out:
 
 static int validate_user_key(struct fscrypt_info *crypt_info,
 			struct fscrypt_context *ctx, u8 *raw_key,
-			u8 *prefix, int prefix_size)
+			const char *prefix, int min_keysize)
 {
-	u8 *full_key_descriptor;
+	char *description;
 	struct key *keyring_key;
 	struct fscrypt_key *master_key;
 	const struct user_key_payload *ukp;
-	int full_key_len = prefix_size + (FS_KEY_DESCRIPTOR_SIZE * 2) + 1;
 	int res;
 
-	full_key_descriptor = kmalloc(full_key_len, GFP_NOFS);
-	if (!full_key_descriptor)
+	description = kasprintf(GFP_NOFS, "%s%*phN", prefix,
+				FS_KEY_DESCRIPTOR_SIZE,
+				ctx->master_key_descriptor);
+	if (!description)
 		return -ENOMEM;
 
-	memcpy(full_key_descriptor, prefix, prefix_size);
-	sprintf(full_key_descriptor + prefix_size,
-			"%*phN", FS_KEY_DESCRIPTOR_SIZE,
-			ctx->master_key_descriptor);
-	full_key_descriptor[full_key_len - 1] = '\0';
-	keyring_key = request_key(&key_type_logon, full_key_descriptor, NULL);
-	kfree(full_key_descriptor);
+	keyring_key = request_key(&key_type_logon, description, NULL);
+	kfree(description);
 	if (IS_ERR(keyring_key))
 		return PTR_ERR(keyring_key);
+	down_read(&keyring_key->sem);
 
 	if (keyring_key->type != &key_type_logon) {
 		printk_once(KERN_WARNING
@@ -106,66 +108,68 @@ static int validate_user_key(struct fscrypt_info *crypt_info,
 		res = -ENOKEY;
 		goto out;
 	}
-	down_read(&keyring_key->sem);
-	ukp = user_key_payload(keyring_key);
+	ukp = user_key_payload_locked(keyring_key);
 	if (ukp->datalen != sizeof(struct fscrypt_key)) {
 		res = -EINVAL;
-		up_read(&keyring_key->sem);
 		goto out;
 	}
 	master_key = (struct fscrypt_key *)ukp->data;
 	BUILD_BUG_ON(FS_AES_128_ECB_KEY_SIZE != FS_KEY_DERIVATION_NONCE_SIZE);
 
-	if (master_key->size != FS_AES_256_XTS_KEY_SIZE) {
+	if (master_key->size < min_keysize || master_key->size > FS_MAX_KEY_SIZE
+	    || master_key->size % AES_BLOCK_SIZE != 0) {
 		printk_once(KERN_WARNING
 				"%s: key size incorrect: %d\n",
 				__func__, master_key->size);
 		res = -ENOKEY;
-		up_read(&keyring_key->sem);
 		goto out;
 	}
-	res = derive_key_aes(ctx->nonce, master_key->raw, raw_key);
-	up_read(&keyring_key->sem);
-	if (res)
-		goto out;
-
-	crypt_info->ci_keyring_key = keyring_key;
-	return 0;
+	res = derive_key_aes(ctx->nonce, master_key, raw_key);
 out:
+	up_read(&keyring_key->sem);
 	key_put(keyring_key);
 	return res;
 }
 
+static const struct {
+	const char *cipher_str;
+	int keysize;
+} available_modes[] = {
+	[FS_ENCRYPTION_MODE_AES_256_XTS] = { "xts(aes)",
+					     FS_AES_256_XTS_KEY_SIZE },
+	[FS_ENCRYPTION_MODE_AES_256_CTS] = { "cts(cbc(aes))",
+					     FS_AES_256_CTS_KEY_SIZE },
+	[FS_ENCRYPTION_MODE_AES_128_CBC] = { "cbc(aes)",
+					     FS_AES_128_CBC_KEY_SIZE },
+	[FS_ENCRYPTION_MODE_AES_128_CTS] = { "cts(cbc(aes))",
+					     FS_AES_128_CTS_KEY_SIZE },
+};
+
 static int determine_cipher_type(struct fscrypt_info *ci, struct inode *inode,
 				 const char **cipher_str_ret, int *keysize_ret)
 {
-	if (S_ISREG(inode->i_mode)) {
-		if (ci->ci_data_mode == FS_ENCRYPTION_MODE_AES_256_XTS) {
-			*cipher_str_ret = "xts(aes)";
-			*keysize_ret = FS_AES_256_XTS_KEY_SIZE;
-			return 0;
-		}
-		pr_warn_once("fscrypto: unsupported contents encryption mode "
-			     "%d for inode %lu\n",
-			     ci->ci_data_mode, inode->i_ino);
-		return -ENOKEY;
+	u32 mode;
+
+	if (!fscrypt_valid_enc_modes(ci->ci_data_mode, ci->ci_filename_mode)) {
+		pr_warn_ratelimited("fscrypt: inode %lu uses unsupported encryption modes (contents mode %d, filenames mode %d)\n",
+				    inode->i_ino,
+				    ci->ci_data_mode, ci->ci_filename_mode);
+		return -EINVAL;
 	}
 
-	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
-		if (ci->ci_filename_mode == FS_ENCRYPTION_MODE_AES_256_CTS) {
-			*cipher_str_ret = "cts(cbc(aes))";
-			*keysize_ret = FS_AES_256_CTS_KEY_SIZE;
-			return 0;
-		}
-		pr_warn_once("fscrypto: unsupported filenames encryption mode "
-			     "%d for inode %lu\n",
-			     ci->ci_filename_mode, inode->i_ino);
-		return -ENOKEY;
+	if (S_ISREG(inode->i_mode)) {
+		mode = ci->ci_data_mode;
+	} else if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) {
+		mode = ci->ci_filename_mode;
+	} else {
+		WARN_ONCE(1, "fscrypt: filesystem tried to load encryption info for inode %lu, which is not encryptable (file type %d)\n",
+			  inode->i_ino, (inode->i_mode & S_IFMT));
+		return -EINVAL;
 	}
 
-	pr_warn_once("fscrypto: unsupported file type %d for inode %lu\n",
-		     (inode->i_mode & S_IFMT), inode->i_ino);
-	return -ENOKEY;
+	*cipher_str_ret = available_modes[mode].cipher_str;
+	*keysize_ret = available_modes[mode].keysize;
+	return 0;
 }
 
 static void put_crypt_info(struct fscrypt_info *ci)
@@ -173,12 +177,78 @@ static void put_crypt_info(struct fscrypt_info *ci)
 	if (!ci)
 		return;
 
-	key_put(ci->ci_keyring_key);
 	crypto_free_skcipher(ci->ci_ctfm);
+	crypto_free_cipher(ci->ci_essiv_tfm);
 	kmem_cache_free(fscrypt_info_cachep, ci);
 }
 
-int fscrypt_get_crypt_info(struct inode *inode)
+static int derive_essiv_salt(const u8 *key, int keysize, u8 *salt)
+{
+	struct crypto_shash *tfm = READ_ONCE(essiv_hash_tfm);
+
+	/* init hash transform on demand */
+	if (unlikely(!tfm)) {
+		struct crypto_shash *prev_tfm;
+
+		tfm = crypto_alloc_shash("sha256", 0, 0);
+		if (IS_ERR(tfm)) {
+			pr_warn_ratelimited("fscrypt: error allocating SHA-256 transform: %ld\n",
+					    PTR_ERR(tfm));
+			return PTR_ERR(tfm);
+		}
+		prev_tfm = cmpxchg(&essiv_hash_tfm, NULL, tfm);
+		if (prev_tfm) {
+			crypto_free_shash(tfm);
+			tfm = prev_tfm;
+		}
+	}
+
+	{
+		SHASH_DESC_ON_STACK(desc, tfm);
+		desc->tfm = tfm;
+		desc->flags = 0;
+
+		return crypto_shash_digest(desc, key, keysize, salt);
+	}
+}
+
+static int init_essiv_generator(struct fscrypt_info *ci, const u8 *raw_key,
+				int keysize)
+{
+	int err;
+	struct crypto_cipher *essiv_tfm;
+	u8 salt[SHA256_DIGEST_SIZE];
+
+	essiv_tfm = crypto_alloc_cipher("aes", 0, 0);
+	if (IS_ERR(essiv_tfm))
+		return PTR_ERR(essiv_tfm);
+
+	ci->ci_essiv_tfm = essiv_tfm;
+
+	err = derive_essiv_salt(raw_key, keysize, salt);
+	if (err)
+		goto out;
+
+	/*
+	 * Using SHA256 to derive the salt/key will result in AES-256 being
+	 * used for IV generation. File contents encryption will still use the
+	 * configured keysize (AES-128) nevertheless.
+	 */
+	err = crypto_cipher_setkey(essiv_tfm, salt, sizeof(salt));
+	if (err)
+		goto out;
+
+out:
+	memzero_explicit(salt, sizeof(salt));
+	return err;
+}
+
+void __exit fscrypt_essiv_cleanup(void)
+{
+	crypto_free_shash(essiv_hash_tfm);
+}
+
+int fscrypt_get_encryption_info(struct inode *inode)
 {
 	struct fscrypt_info *crypt_info;
 	struct fscrypt_context ctx;
@@ -188,30 +258,24 @@ int fscrypt_get_crypt_info(struct inode *inode)
 	u8 *raw_key = NULL;
 	int res;
 
+	if (inode->i_crypt_info)
+		return 0;
+
 	res = fscrypt_initialize(inode->i_sb->s_cop->flags);
 	if (res)
 		return res;
 
-	if (!inode->i_sb->s_cop->get_context)
-		return -EOPNOTSUPP;
-retry:
-	crypt_info = ACCESS_ONCE(inode->i_crypt_info);
-	if (crypt_info) {
-		if (!crypt_info->ci_keyring_key ||
-				key_validate(crypt_info->ci_keyring_key) == 0)
-			return 0;
-		fscrypt_put_encryption_info(inode, crypt_info);
-		goto retry;
-	}
-
 	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
 	if (res < 0) {
-		if (!fscrypt_dummy_context_enabled(inode))
+		if (!fscrypt_dummy_context_enabled(inode) ||
+		    inode->i_sb->s_cop->is_encrypted(inode))
 			return res;
+		/* Fake up a context for an unencrypted directory */
+		memset(&ctx, 0, sizeof(ctx));
 		ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
 		ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
 		ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
-		ctx.flags = 0;
+		memset(ctx.master_key_descriptor, 0x42, FS_KEY_DESCRIPTOR_SIZE);
 	} else if (res != sizeof(ctx)) {
 		return -EINVAL;
 	}
@@ -230,7 +294,7 @@ retry:
 	crypt_info->ci_data_mode = ctx.contents_encryption_mode;
 	crypt_info->ci_filename_mode = ctx.filenames_encryption_mode;
 	crypt_info->ci_ctfm = NULL;
-	crypt_info->ci_keyring_key = NULL;
+	crypt_info->ci_essiv_tfm = NULL;
 	memcpy(crypt_info->ci_master_key, ctx.master_key_descriptor,
 				sizeof(crypt_info->ci_master_key));
 
@@ -247,21 +311,12 @@ retry:
 	if (!raw_key)
 		goto out;
 
-	if (fscrypt_dummy_context_enabled(inode)) {
-		memset(raw_key, 0x42, keysize/2);
-		memset(raw_key+keysize/2, 0x24, keysize - (keysize/2));
-		goto got_key;
-	}
-
-	res = validate_user_key(crypt_info, &ctx, raw_key,
-			FS_KEY_DESC_PREFIX, FS_KEY_DESC_PREFIX_SIZE);
+	res = validate_user_key(crypt_info, &ctx, raw_key, FS_KEY_DESC_PREFIX,
+				keysize);
 	if (res && inode->i_sb->s_cop->key_prefix) {
-		u8 *prefix = NULL;
-		int prefix_size, res2;
-
-		prefix_size = inode->i_sb->s_cop->key_prefix(inode, &prefix);
-		res2 = validate_user_key(crypt_info, &ctx, raw_key,
-							prefix, prefix_size);
+		int res2 = validate_user_key(crypt_info, &ctx, raw_key,
+					     inode->i_sb->s_cop->key_prefix,
+					     keysize);
 		if (res2) {
 			if (res2 == -ENOKEY)
 				res = -ENOKEY;
@@ -270,30 +325,35 @@ retry:
 	} else if (res) {
 		goto out;
 	}
-got_key:
 	ctfm = crypto_alloc_skcipher(cipher_str, 0, 0);
 	if (!ctfm || IS_ERR(ctfm)) {
 		res = ctfm ? PTR_ERR(ctfm) : -ENOMEM;
-		printk(KERN_DEBUG
-		       "%s: error %d (inode %u) allocating crypto tfm\n",
-		       __func__, res, (unsigned) inode->i_ino);
+		pr_debug("%s: error %d (inode %lu) allocating crypto tfm\n",
+			 __func__, res, inode->i_ino);
 		goto out;
 	}
 	crypt_info->ci_ctfm = ctfm;
 	crypto_skcipher_clear_flags(ctfm, ~0);
 	crypto_skcipher_set_flags(ctfm, CRYPTO_TFM_REQ_WEAK_KEY);
+	/*
+	 * if the provided key is longer than keysize, we use the first
+	 * keysize bytes of the derived key only
+	 */
 	res = crypto_skcipher_setkey(ctfm, raw_key, keysize);
 	if (res)
 		goto out;
 
-	kzfree(raw_key);
-	raw_key = NULL;
-	if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) != NULL) {
-		put_crypt_info(crypt_info);
-		goto retry;
+	if (S_ISREG(inode->i_mode) &&
+	    crypt_info->ci_data_mode == FS_ENCRYPTION_MODE_AES_128_CBC) {
+		res = init_essiv_generator(crypt_info, raw_key, keysize);
+		if (res) {
+			pr_debug("%s: error %d (inode %lu) allocating essiv tfm\n",
+				 __func__, res, inode->i_ino);
+			goto out;
+		}
 	}
-	return 0;
-
+	if (cmpxchg(&inode->i_crypt_info, NULL, crypt_info) == NULL)
+		crypt_info = NULL;
 out:
 	if (res == -ENOKEY)
 		res = 0;
@@ -301,6 +361,7 @@ out:
 	kzfree(raw_key);
 	return res;
 }
+EXPORT_SYMBOL(fscrypt_get_encryption_info);
 
 void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci)
 {
@@ -318,17 +379,3 @@ void fscrypt_put_encryption_info(struct inode *inode, struct fscrypt_info *ci)
 	put_crypt_info(ci);
 }
 EXPORT_SYMBOL(fscrypt_put_encryption_info);
-
-int fscrypt_get_encryption_info(struct inode *inode)
-{
-	struct fscrypt_info *ci = inode->i_crypt_info;
-
-	if (!ci ||
-		(ci->ci_keyring_key &&
-		 (ci->ci_keyring_key->flags & ((1 << KEY_FLAG_INVALIDATED) |
-					       (1 << KEY_FLAG_REVOKED) |
-					       (1 << KEY_FLAG_DEAD)))))
-		return fscrypt_get_crypt_info(inode);
-	return 0;
-}
-EXPORT_SYMBOL(fscrypt_get_encryption_info);
diff --git a/fs/crypto/policy.c b/fs/crypto/policy.c
index d6cd7ea4851d..ce07a86200f3 100644
--- a/fs/crypto/policy.c
+++ b/fs/crypto/policy.c
@@ -13,73 +13,34 @@
 #include <linux/mount.h>
 #include "fscrypt_private.h"
 
-static int inode_has_encryption_context(struct inode *inode)
-{
-	if (!inode->i_sb->s_cop->get_context)
-		return 0;
-	return (inode->i_sb->s_cop->get_context(inode, NULL, 0L) > 0);
-}
-
 /*
- * check whether the policy is consistent with the encryption context
- * for the inode
+ * check whether an encryption policy is consistent with an encryption context
  */
-static int is_encryption_context_consistent_with_policy(struct inode *inode,
+static bool is_encryption_context_consistent_with_policy(
+				const struct fscrypt_context *ctx,
 				const struct fscrypt_policy *policy)
 {
-	struct fscrypt_context ctx;
-	int res;
-
-	if (!inode->i_sb->s_cop->get_context)
-		return 0;
-
-	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
-	if (res != sizeof(ctx))
-		return 0;
-
-	return (memcmp(ctx.master_key_descriptor, policy->master_key_descriptor,
-			FS_KEY_DESCRIPTOR_SIZE) == 0 &&
-			(ctx.flags == policy->flags) &&
-			(ctx.contents_encryption_mode ==
-			 policy->contents_encryption_mode) &&
-			(ctx.filenames_encryption_mode ==
-			 policy->filenames_encryption_mode));
+	return memcmp(ctx->master_key_descriptor, policy->master_key_descriptor,
+		      FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+		(ctx->flags == policy->flags) &&
+		(ctx->contents_encryption_mode ==
+		 policy->contents_encryption_mode) &&
+		(ctx->filenames_encryption_mode ==
+		 policy->filenames_encryption_mode);
 }
 
 static int create_encryption_context_from_policy(struct inode *inode,
 				const struct fscrypt_policy *policy)
 {
 	struct fscrypt_context ctx;
-	int res;
-
-	if (!inode->i_sb->s_cop->set_context)
-		return -EOPNOTSUPP;
-
-	if (inode->i_sb->s_cop->prepare_context) {
-		res = inode->i_sb->s_cop->prepare_context(inode);
-		if (res)
-			return res;
-	}
 
 	ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
 	memcpy(ctx.master_key_descriptor, policy->master_key_descriptor,
 					FS_KEY_DESCRIPTOR_SIZE);
 
-	if (!fscrypt_valid_contents_enc_mode(
-				policy->contents_encryption_mode)) {
-		printk(KERN_WARNING
-		       "%s: Invalid contents encryption mode %d\n", __func__,
-			policy->contents_encryption_mode);
+	if (!fscrypt_valid_enc_modes(policy->contents_encryption_mode,
+				     policy->filenames_encryption_mode))
 		return -EINVAL;
-	}
-
-	if (!fscrypt_valid_filenames_enc_mode(
-				policy->filenames_encryption_mode)) {
-		printk(KERN_WARNING
-			"%s: Invalid filenames encryption mode %d\n", __func__,
-			policy->filenames_encryption_mode);
-		return -EINVAL;
-	}
 
 	if (policy->flags & ~FS_POLICY_FLAGS_VALID)
 		return -EINVAL;
@@ -98,6 +59,7 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg)
 	struct fscrypt_policy policy;
 	struct inode *inode = file_inode(filp);
 	int ret;
+	struct fscrypt_context ctx;
 
 	if (copy_from_user(&policy, arg, sizeof(policy)))
 		return -EFAULT;
@@ -114,22 +76,23 @@ int fscrypt_ioctl_set_policy(struct file *filp, const void __user *arg)
 
 	inode_lock(inode);
 
-	if (!inode_has_encryption_context(inode)) {
+	ret = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (ret == -ENODATA) {
 		if (!S_ISDIR(inode->i_mode))
-			ret = -EINVAL;
-		else if (!inode->i_sb->s_cop->empty_dir)
-			ret = -EOPNOTSUPP;
+			ret = -ENOTDIR;
 		else if (!inode->i_sb->s_cop->empty_dir(inode))
 			ret = -ENOTEMPTY;
 		else
 			ret = create_encryption_context_from_policy(inode,
 								    &policy);
-	} else if (!is_encryption_context_consistent_with_policy(inode,
-								 &policy)) {
-		printk(KERN_WARNING
-		       "%s: Policy inconsistent with encryption context\n",
-		       __func__);
-		ret = -EINVAL;
+	} else if (ret == sizeof(ctx) &&
+		   is_encryption_context_consistent_with_policy(&ctx,
+								&policy)) {
+		/* The file already uses the same encryption policy. */
+		ret = 0;
+	} else if (ret >= 0 || ret == -ERANGE) {
+		/* The file already uses a different encryption policy. */
+		ret = -EEXIST;
 	}
 
 	inode_unlock(inode);
@@ -146,13 +109,14 @@ int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
 	struct fscrypt_policy policy;
 	int res;
 
-	if (!inode->i_sb->s_cop->get_context ||
-			!inode->i_sb->s_cop->is_encrypted(inode))
+	if (!inode->i_sb->s_cop->is_encrypted(inode))
 		return -ENODATA;
 
 	res = inode->i_sb->s_cop->get_context(inode, &ctx, sizeof(ctx));
+	if (res < 0 && res != -ERANGE)
+		return res;
 	if (res != sizeof(ctx))
-		return -ENODATA;
+		return -EINVAL;
 	if (ctx.format != FS_ENCRYPTION_CONTEXT_FORMAT_V1)
 		return -EINVAL;
 
@@ -169,27 +133,61 @@ int fscrypt_ioctl_get_policy(struct file *filp, void __user *arg)
 }
 EXPORT_SYMBOL(fscrypt_ioctl_get_policy);
 
+/**
+ * fscrypt_has_permitted_context() - is a file's encryption policy permitted
+ *				     within its directory?
+ *
+ * @parent: inode for parent directory
+ * @child: inode for file being looked up, opened, or linked into @parent
+ *
+ * Filesystems must call this before permitting access to an inode in a
+ * situation where the parent directory is encrypted (either before allowing
+ * ->lookup() to succeed, or for a regular file before allowing it to be opened)
+ * and before any operation that involves linking an inode into an encrypted
+ * directory, including link, rename, and cross rename.  It enforces the
+ * constraint that within a given encrypted directory tree, all files use the
+ * same encryption policy.  The pre-access check is needed to detect potentially
+ * malicious offline violations of this constraint, while the link and rename
+ * checks are needed to prevent online violations of this constraint.
+ *
+ * Return: 1 if permitted, 0 if forbidden.  If forbidden, the caller must fail
+ * the filesystem operation with EPERM.
+ */
 int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
 {
-	struct fscrypt_info *parent_ci, *child_ci;
+	const struct fscrypt_operations *cops = parent->i_sb->s_cop;
+	const struct fscrypt_info *parent_ci, *child_ci;
+	struct fscrypt_context parent_ctx, child_ctx;
 	int res;
 
-	if ((parent == NULL) || (child == NULL)) {
-		printk(KERN_ERR	"parent %p child %p\n", parent, child);
-		BUG_ON(1);
-	}
-
 	/* No restrictions on file types which are never encrypted */
 	if (!S_ISREG(child->i_mode) && !S_ISDIR(child->i_mode) &&
 	    !S_ISLNK(child->i_mode))
 		return 1;
 
-	/* no restrictions if the parent directory is not encrypted */
-	if (!parent->i_sb->s_cop->is_encrypted(parent))
+	/* No restrictions if the parent directory is unencrypted */
+	if (!cops->is_encrypted(parent))
 		return 1;
-	/* if the child directory is not encrypted, this is always a problem */
-	if (!parent->i_sb->s_cop->is_encrypted(child))
+
+	/* Encrypted directories must not contain unencrypted files */
+	if (!cops->is_encrypted(child))
 		return 0;
+
+	/*
+	 * Both parent and child are encrypted, so verify they use the same
+	 * encryption policy.  Compare the fscrypt_info structs if the keys are
+	 * available, otherwise retrieve and compare the fscrypt_contexts.
+	 *
+	 * Note that the fscrypt_context retrieval will be required frequently
+	 * when accessing an encrypted directory tree without the key.
+	 * Performance-wise this is not a big deal because we already don't
+	 * really optimize for file access without the key (to the extent that
+	 * such access is even possible), given that any attempted access
+	 * already causes a fscrypt_context retrieval and keyring search.
+	 *
+	 * In any case, if an unexpected error occurs, fall back to "forbidden".
+	 */
+
 	res = fscrypt_get_encryption_info(parent);
 	if (res)
 		return 0;
@@ -198,17 +196,32 @@ int fscrypt_has_permitted_context(struct inode *parent, struct inode *child)
 		return 0;
 	parent_ci = parent->i_crypt_info;
 	child_ci = child->i_crypt_info;
-	if (!parent_ci && !child_ci)
-		return 1;
-	if (!parent_ci || !child_ci)
+
+	if (parent_ci && child_ci) {
+		return memcmp(parent_ci->ci_master_key, child_ci->ci_master_key,
+			      FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+			(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
+			(parent_ci->ci_filename_mode ==
+			 child_ci->ci_filename_mode) &&
+			(parent_ci->ci_flags == child_ci->ci_flags);
+	}
+
+	res = cops->get_context(parent, &parent_ctx, sizeof(parent_ctx));
+	if (res != sizeof(parent_ctx))
 		return 0;
 
-	return (memcmp(parent_ci->ci_master_key,
-			child_ci->ci_master_key,
-			FS_KEY_DESCRIPTOR_SIZE) == 0 &&
-		(parent_ci->ci_data_mode == child_ci->ci_data_mode) &&
-		(parent_ci->ci_filename_mode == child_ci->ci_filename_mode) &&
-		(parent_ci->ci_flags == child_ci->ci_flags));
+	res = cops->get_context(child, &child_ctx, sizeof(child_ctx));
+	if (res != sizeof(child_ctx))
+		return 0;
+
+	return memcmp(parent_ctx.master_key_descriptor,
+		      child_ctx.master_key_descriptor,
+		      FS_KEY_DESCRIPTOR_SIZE) == 0 &&
+		(parent_ctx.contents_encryption_mode ==
+		 child_ctx.contents_encryption_mode) &&
+		(parent_ctx.filenames_encryption_mode ==
+		 child_ctx.filenames_encryption_mode) &&
+		(parent_ctx.flags == child_ctx.flags);
 }
 EXPORT_SYMBOL(fscrypt_has_permitted_context);
 
@@ -217,9 +230,9 @@ EXPORT_SYMBOL(fscrypt_has_permitted_context);
  * @parent: Parent inode from which the context is inherited.
  * @child:  Child inode that inherits the context from @parent.
  * @fs_data:  private data given by FS.
- * @preload:  preload child i_crypt_info
+ * @preload:  preload child i_crypt_info if true
  *
- * Return: Zero on success, non-zero otherwise
+ * Return: 0 on success, -errno on failure
  */
 int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 						void *fs_data, bool preload)
@@ -228,9 +241,6 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 	struct fscrypt_info *ci;
 	int res;
 
-	if (!parent->i_sb->s_cop->set_context)
-		return -EOPNOTSUPP;
-
 	res = fscrypt_get_encryption_info(parent);
 	if (res < 0)
 		return res;
@@ -240,20 +250,13 @@ int fscrypt_inherit_context(struct inode *parent, struct inode *child,
 		return -ENOKEY;
 
 	ctx.format = FS_ENCRYPTION_CONTEXT_FORMAT_V1;
-	if (fscrypt_dummy_context_enabled(parent)) {
-		ctx.contents_encryption_mode = FS_ENCRYPTION_MODE_AES_256_XTS;
-		ctx.filenames_encryption_mode = FS_ENCRYPTION_MODE_AES_256_CTS;
-		ctx.flags = 0;
-		memset(ctx.master_key_descriptor, 0x42, FS_KEY_DESCRIPTOR_SIZE);
-		res = 0;
-	} else {
-		ctx.contents_encryption_mode = ci->ci_data_mode;
-		ctx.filenames_encryption_mode = ci->ci_filename_mode;
-		ctx.flags = ci->ci_flags;
-		memcpy(ctx.master_key_descriptor, ci->ci_master_key,
-				FS_KEY_DESCRIPTOR_SIZE);
-	}
+	ctx.contents_encryption_mode = ci->ci_data_mode;
+	ctx.filenames_encryption_mode = ci->ci_filename_mode;
+	ctx.flags = ci->ci_flags;
+	memcpy(ctx.master_key_descriptor, ci->ci_master_key,
+	       FS_KEY_DESCRIPTOR_SIZE);
 	get_random_bytes(ctx.nonce, FS_KEY_DERIVATION_NONCE_SIZE);
+	BUILD_BUG_ON(sizeof(ctx) != FSCRYPT_SET_CONTEXT_MAX_SIZE);
 	res = parent->i_sb->s_cop->set_context(child, &ctx,
 						sizeof(ctx), fs_data);
 	if (res)
diff --git a/fs/dax.c b/fs/dax.c
index c45598b912e1..306c2b603fb8 100644
--- a/fs/dax.c
+++ b/fs/dax.c
@@ -25,8 +25,8 @@
 #include <linux/mm.h>
 #include <linux/mutex.h>
 #include <linux/pagevec.h>
-#include <linux/pmem.h>
 #include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/uio.h>
 #include <linux/vmstat.h>
 #include <linux/pfn_t.h>
@@ -35,6 +35,9 @@
 #include <linux/iomap.h>
 #include "internal.h"
 
+#define CREATE_TRACE_POINTS
+#include <trace/events/fs_dax.h>
+
 /* We choose 4096 entries - same as per-zone page wait tables */
 #define DAX_WAIT_TABLE_BITS 12
 #define DAX_WAIT_TABLE_ENTRIES (1 << DAX_WAIT_TABLE_BITS)
@@ -51,32 +54,6 @@ static int __init init_dax_wait_table(void)
 }
 fs_initcall(init_dax_wait_table);
 
-static long dax_map_atomic(struct block_device *bdev, struct blk_dax_ctl *dax)
-{
-	struct request_queue *q = bdev->bd_queue;
-	long rc = -EIO;
-
-	dax->addr = ERR_PTR(-EIO);
-	if (blk_queue_enter(q, true) != 0)
-		return rc;
-
-	rc = bdev_direct_access(bdev, dax);
-	if (rc < 0) {
-		dax->addr = ERR_PTR(rc);
-		blk_queue_exit(q);
-		return rc;
-	}
-	return rc;
-}
-
-static void dax_unmap_atomic(struct block_device *bdev,
-		const struct blk_dax_ctl *dax)
-{
-	if (IS_ERR(dax->addr))
-		return;
-	blk_queue_exit(bdev->bd_queue);
-}
-
 static int dax_is_pmd_entry(void *entry)
 {
 	return (unsigned long)entry & RADIX_DAX_PMD;
@@ -97,26 +74,6 @@ static int dax_is_empty_entry(void *entry)
 	return (unsigned long)entry & RADIX_DAX_EMPTY;
 }
 
-struct page *read_dax_sector(struct block_device *bdev, sector_t n)
-{
-	struct page *page = alloc_pages(GFP_KERNEL, 0);
-	struct blk_dax_ctl dax = {
-		.size = PAGE_SIZE,
-		.sector = n & ~((((int) PAGE_SIZE) / 512) - 1),
-	};
-	long rc;
-
-	if (!page)
-		return ERR_PTR(-ENOMEM);
-
-	rc = dax_map_atomic(bdev, &dax);
-	if (rc < 0)
-		return ERR_PTR(rc);
-	memcpy_from_pmem(page_address(page), dax.addr, PAGE_SIZE);
-	dax_unmap_atomic(bdev, &dax);
-	return page;
-}
-
 /*
  * DAX radix tree locking
  */
@@ -126,7 +83,7 @@ struct exceptional_entry_key {
 };
 
 struct wait_exceptional_entry_queue {
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	struct exceptional_entry_key key;
 };
 
@@ -150,7 +107,7 @@ static wait_queue_head_t *dax_entry_waitqueue(struct address_space *mapping,
 	return wait_table + hash;
 }
 
-static int wake_exceptional_entry_func(wait_queue_t *wait, unsigned int mode,
+static int wake_exceptional_entry_func(wait_queue_entry_t *wait, unsigned int mode,
 				       int sync, void *keyp)
 {
 	struct exceptional_entry_key *key = keyp;
@@ -369,6 +326,22 @@ restart:
 		}
 		spin_lock_irq(&mapping->tree_lock);
 
+		if (!entry) {
+			/*
+			 * We needed to drop the page_tree lock while calling
+			 * radix_tree_preload() and we didn't have an entry to
+			 * lock.  See if another thread inserted an entry at
+			 * our index during this time.
+			 */
+			entry = __radix_tree_lookup(&mapping->page_tree, index,
+					NULL, &slot);
+			if (entry) {
+				radix_tree_preload_end();
+				spin_unlock_irq(&mapping->tree_lock);
+				goto restart;
+			}
+		}
+
 		if (pmd_downgrade) {
 			radix_tree_delete(&mapping->page_tree, index);
 			mapping->nrexceptional--;
@@ -384,19 +357,12 @@ restart:
 		if (err) {
 			spin_unlock_irq(&mapping->tree_lock);
 			/*
-			 * Someone already created the entry?  This is a
-			 * normal failure when inserting PMDs in a range
-			 * that already contains PTEs.  In that case we want
-			 * to return -EEXIST immediately.
-			 */
-			if (err == -EEXIST && !(size_flag & RADIX_DAX_PMD))
-				goto restart;
-			/*
-			 * Our insertion of a DAX PMD entry failed, most
-			 * likely because it collided with a PTE sized entry
-			 * at a different index in the PMD range.  We haven't
-			 * inserted anything into the radix tree and have no
-			 * waiters to wake.
+			 * Our insertion of a DAX entry failed, most likely
+			 * because we were inserting a PMD entry and it
+			 * collided with a PTE sized entry at a different
+			 * index in the PMD range.  We haven't inserted
+			 * anything into the radix tree and have no waiters to
+			 * wake.
 			 */
 			return ERR_PTR(err);
 		}
@@ -494,35 +460,6 @@ int dax_delete_mapping_entry(struct address_space *mapping, pgoff_t index)
 }
 
 /*
- * Invalidate exceptional DAX entry if easily possible. This handles DAX
- * entries for invalidate_inode_pages() so we evict the entry only if we can
- * do so without blocking.
- */
-int dax_invalidate_mapping_entry(struct address_space *mapping, pgoff_t index)
-{
-	int ret = 0;
-	void *entry, **slot;
-	struct radix_tree_root *page_tree = &mapping->page_tree;
-
-	spin_lock_irq(&mapping->tree_lock);
-	entry = __radix_tree_lookup(page_tree, index, NULL, &slot);
-	if (!entry || !radix_tree_exceptional_entry(entry) ||
-	    slot_locked(mapping, slot))
-		goto out;
-	if (radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_DIRTY) ||
-	    radix_tree_tag_get(page_tree, index, PAGECACHE_TAG_TOWRITE))
-		goto out;
-	radix_tree_delete(page_tree, index);
-	mapping->nrexceptional--;
-	ret = 1;
-out:
-	spin_unlock_irq(&mapping->tree_lock);
-	if (ret)
-		dax_wake_mapping_entry_waiter(mapping, index, entry, true);
-	return ret;
-}
-
-/*
  * Invalidate exceptional DAX entry if it is clean.
  */
 int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
@@ -542,21 +479,25 @@ int dax_invalidate_mapping_entry_sync(struct address_space *mapping,
 static int dax_load_hole(struct address_space *mapping, void **entry,
 			 struct vm_fault *vmf)
 {
+	struct inode *inode = mapping->host;
 	struct page *page;
 	int ret;
 
 	/* Hole page already exists? Return it...  */
 	if (!radix_tree_exceptional_entry(*entry)) {
 		page = *entry;
-		goto out;
+		goto finish_fault;
 	}
 
 	/* This will replace locked radix tree entry with a hole page */
 	page = find_or_create_page(mapping, vmf->pgoff,
 				   vmf->gfp_mask | __GFP_ZERO);
-	if (!page)
-		return VM_FAULT_OOM;
- out:
+	if (!page) {
+		ret = VM_FAULT_OOM;
+		goto out;
+	}
+
+finish_fault:
 	vmf->page = page;
 	ret = finish_fault(vmf);
 	vmf->page = NULL;
@@ -564,26 +505,37 @@ static int dax_load_hole(struct address_space *mapping, void **entry,
 	if (!ret) {
 		/* Grab reference for PTE that is now referencing the page */
 		get_page(page);
-		return VM_FAULT_NOPAGE;
+		ret = VM_FAULT_NOPAGE;
 	}
+out:
+	trace_dax_load_hole(inode, vmf, ret);
 	return ret;
 }
 
-static int copy_user_dax(struct block_device *bdev, sector_t sector, size_t size,
-		struct page *to, unsigned long vaddr)
+static int copy_user_dax(struct block_device *bdev, struct dax_device *dax_dev,
+		sector_t sector, size_t size, struct page *to,
+		unsigned long vaddr)
 {
-	struct blk_dax_ctl dax = {
-		.sector = sector,
-		.size = size,
-	};
-	void *vto;
-
-	if (dax_map_atomic(bdev, &dax) < 0)
-		return PTR_ERR(dax.addr);
+	void *vto, *kaddr;
+	pgoff_t pgoff;
+	pfn_t pfn;
+	long rc;
+	int id;
+
+	rc = bdev_dax_pgoff(bdev, sector, size, &pgoff);
+	if (rc)
+		return rc;
+
+	id = dax_read_lock();
+	rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, &pfn);
+	if (rc < 0) {
+		dax_read_unlock(id);
+		return rc;
+	}
 	vto = kmap_atomic(to);
-	copy_user_page(vto, (void __force *)dax.addr, vaddr, to);
+	copy_user_page(vto, (void __force *)kaddr, vaddr, to);
 	kunmap_atomic(vto);
-	dax_unmap_atomic(bdev, &dax);
+	dax_read_unlock(id);
 	return 0;
 }
 
@@ -751,12 +703,16 @@ unlock_pte:
 }
 
 static int dax_writeback_one(struct block_device *bdev,
-		struct address_space *mapping, pgoff_t index, void *entry)
+		struct dax_device *dax_dev, struct address_space *mapping,
+		pgoff_t index, void *entry)
 {
 	struct radix_tree_root *page_tree = &mapping->page_tree;
-	struct blk_dax_ctl dax;
-	void *entry2, **slot;
-	int ret = 0;
+	void *entry2, **slot, *kaddr;
+	long ret = 0, id;
+	sector_t sector;
+	pgoff_t pgoff;
+	size_t size;
+	pfn_t pfn;
 
 	/*
 	 * A page got tagged dirty in DAX mapping? Something is seriously
@@ -805,26 +761,29 @@ static int dax_writeback_one(struct block_device *bdev,
 	 * 'entry'.  This allows us to flush for PMD_SIZE and not have to
 	 * worry about partial PMD writebacks.
 	 */
-	dax.sector = dax_radix_sector(entry);
-	dax.size = PAGE_SIZE << dax_radix_order(entry);
+	sector = dax_radix_sector(entry);
+	size = PAGE_SIZE << dax_radix_order(entry);
+
+	id = dax_read_lock();
+	ret = bdev_dax_pgoff(bdev, sector, size, &pgoff);
+	if (ret)
+		goto dax_unlock;
 
 	/*
-	 * We cannot hold tree_lock while calling dax_map_atomic() because it
-	 * eventually calls cond_resched().
+	 * dax_direct_access() may sleep, so cannot hold tree_lock over
+	 * its invocation.
 	 */
-	ret = dax_map_atomic(bdev, &dax);
-	if (ret < 0) {
-		put_locked_mapping_entry(mapping, index, entry);
-		return ret;
-	}
+	ret = dax_direct_access(dax_dev, pgoff, size / PAGE_SIZE, &kaddr, &pfn);
+	if (ret < 0)
+		goto dax_unlock;
 
-	if (WARN_ON_ONCE(ret < dax.size)) {
+	if (WARN_ON_ONCE(ret < size / PAGE_SIZE)) {
 		ret = -EIO;
-		goto unmap;
+		goto dax_unlock;
 	}
 
-	dax_mapping_entry_mkclean(mapping, index, pfn_t_to_pfn(dax.pfn));
-	wb_cache_pmem(dax.addr, dax.size);
+	dax_mapping_entry_mkclean(mapping, index, pfn_t_to_pfn(pfn));
+	dax_flush(dax_dev, pgoff, kaddr, size);
 	/*
 	 * After we have flushed the cache, we can clear the dirty tag. There
 	 * cannot be new dirty data in the pfn after the flush has completed as
@@ -834,8 +793,9 @@ static int dax_writeback_one(struct block_device *bdev,
 	spin_lock_irq(&mapping->tree_lock);
 	radix_tree_tag_clear(page_tree, index, PAGECACHE_TAG_DIRTY);
 	spin_unlock_irq(&mapping->tree_lock);
- unmap:
-	dax_unmap_atomic(bdev, &dax);
+	trace_dax_writeback_one(mapping->host, index, size >> PAGE_SHIFT);
+ dax_unlock:
+	dax_read_unlock(id);
 	put_locked_mapping_entry(mapping, index, entry);
 	return ret;
 
@@ -856,6 +816,7 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	pgoff_t start_index, end_index;
 	pgoff_t indices[PAGEVEC_SIZE];
+	struct dax_device *dax_dev;
 	struct pagevec pvec;
 	bool done = false;
 	int i, ret = 0;
@@ -866,9 +827,15 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 	if (!mapping->nrexceptional || wbc->sync_mode != WB_SYNC_ALL)
 		return 0;
 
+	dax_dev = dax_get_by_host(bdev->bd_disk->disk_name);
+	if (!dax_dev)
+		return -EIO;
+
 	start_index = wbc->range_start >> PAGE_SHIFT;
 	end_index = wbc->range_end >> PAGE_SHIFT;
 
+	trace_dax_writeback_range(inode, start_index, end_index);
+
 	tag_pages_for_writeback(mapping, start_index, end_index);
 
 	pagevec_init(&pvec, 0);
@@ -886,49 +853,64 @@ int dax_writeback_mapping_range(struct address_space *mapping,
 				break;
 			}
 
-			ret = dax_writeback_one(bdev, mapping, indices[i],
-					pvec.pages[i]);
-			if (ret < 0)
-				return ret;
+			ret = dax_writeback_one(bdev, dax_dev, mapping,
+					indices[i], pvec.pages[i]);
+			if (ret < 0) {
+				mapping_set_error(mapping, ret);
+				goto out;
+			}
 		}
+		start_index = indices[pvec.nr - 1] + 1;
 	}
-	return 0;
+out:
+	put_dax(dax_dev);
+	trace_dax_writeback_range_done(inode, start_index, end_index);
+	return (ret < 0 ? ret : 0);
 }
 EXPORT_SYMBOL_GPL(dax_writeback_mapping_range);
 
 static int dax_insert_mapping(struct address_space *mapping,
-		struct block_device *bdev, sector_t sector, size_t size,
-		void **entryp, struct vm_area_struct *vma, struct vm_fault *vmf)
+		struct block_device *bdev, struct dax_device *dax_dev,
+		sector_t sector, size_t size, void **entryp,
+		struct vm_area_struct *vma, struct vm_fault *vmf)
 {
 	unsigned long vaddr = vmf->address;
-	struct blk_dax_ctl dax = {
-		.sector = sector,
-		.size = size,
-	};
-	void *ret;
 	void *entry = *entryp;
+	void *ret, *kaddr;
+	pgoff_t pgoff;
+	int id, rc;
+	pfn_t pfn;
+
+	rc = bdev_dax_pgoff(bdev, sector, size, &pgoff);
+	if (rc)
+		return rc;
 
-	if (dax_map_atomic(bdev, &dax) < 0)
-		return PTR_ERR(dax.addr);
-	dax_unmap_atomic(bdev, &dax);
+	id = dax_read_lock();
+	rc = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, &pfn);
+	if (rc < 0) {
+		dax_read_unlock(id);
+		return rc;
+	}
+	dax_read_unlock(id);
 
-	ret = dax_insert_mapping_entry(mapping, vmf, entry, dax.sector, 0);
+	ret = dax_insert_mapping_entry(mapping, vmf, entry, sector, 0);
 	if (IS_ERR(ret))
 		return PTR_ERR(ret);
 	*entryp = ret;
 
-	return vm_insert_mixed(vma, vaddr, dax.pfn);
+	trace_dax_insert_mapping(mapping->host, vmf, ret);
+	return vm_insert_mixed(vma, vaddr, pfn);
 }
 
 /**
  * dax_pfn_mkwrite - handle first write to DAX page
- * @vma: The virtual memory area where the fault occurred
  * @vmf: The description of the fault
  */
-int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+int dax_pfn_mkwrite(struct vm_fault *vmf)
 {
-	struct file *file = vma->vm_file;
+	struct file *file = vmf->vma->vm_file;
 	struct address_space *mapping = file->f_mapping;
+	struct inode *inode = mapping->host;
 	void *entry, **slot;
 	pgoff_t index = vmf->pgoff;
 
@@ -938,6 +920,7 @@ int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 		if (entry)
 			put_unlocked_mapping_entry(mapping, index, entry);
 		spin_unlock_irq(&mapping->tree_lock);
+		trace_dax_pfn_mkwrite_no_entry(inode, vmf, VM_FAULT_NOPAGE);
 		return VM_FAULT_NOPAGE;
 	}
 	radix_tree_tag_set(&mapping->page_tree, index, PAGECACHE_TAG_DIRTY);
@@ -950,6 +933,7 @@ int dax_pfn_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	 */
 	finish_mkwrite_fault(vmf);
 	put_locked_mapping_entry(mapping, index, entry);
+	trace_dax_pfn_mkwrite(inode, vmf, VM_FAULT_NOPAGE);
 	return VM_FAULT_NOPAGE;
 }
 EXPORT_SYMBOL_GPL(dax_pfn_mkwrite);
@@ -967,24 +951,35 @@ static bool dax_range_is_aligned(struct block_device *bdev,
 	return true;
 }
 
-int __dax_zero_page_range(struct block_device *bdev, sector_t sector,
-		unsigned int offset, unsigned int length)
+int __dax_zero_page_range(struct block_device *bdev,
+		struct dax_device *dax_dev, sector_t sector,
+		unsigned int offset, unsigned int size)
 {
-	struct blk_dax_ctl dax = {
-		.sector		= sector,
-		.size		= PAGE_SIZE,
-	};
-
-	if (dax_range_is_aligned(bdev, offset, length)) {
-		sector_t start_sector = dax.sector + (offset >> 9);
+	if (dax_range_is_aligned(bdev, offset, size)) {
+		sector_t start_sector = sector + (offset >> 9);
 
 		return blkdev_issue_zeroout(bdev, start_sector,
-				length >> 9, GFP_NOFS, true);
+				size >> 9, GFP_NOFS, 0);
 	} else {
-		if (dax_map_atomic(bdev, &dax) < 0)
-			return PTR_ERR(dax.addr);
-		clear_pmem(dax.addr + offset, length);
-		dax_unmap_atomic(bdev, &dax);
+		pgoff_t pgoff;
+		long rc, id;
+		void *kaddr;
+		pfn_t pfn;
+
+		rc = bdev_dax_pgoff(bdev, sector, PAGE_SIZE, &pgoff);
+		if (rc)
+			return rc;
+
+		id = dax_read_lock();
+		rc = dax_direct_access(dax_dev, pgoff, 1, &kaddr,
+				&pfn);
+		if (rc < 0) {
+			dax_read_unlock(id);
+			return rc;
+		}
+		memset(kaddr + offset, 0, size);
+		dax_flush(dax_dev, pgoff, kaddr + offset, size);
+		dax_read_unlock(id);
 	}
 	return 0;
 }
@@ -999,9 +994,12 @@ static loff_t
 dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		struct iomap *iomap)
 {
+	struct block_device *bdev = iomap->bdev;
+	struct dax_device *dax_dev = iomap->dax_dev;
 	struct iov_iter *iter = data;
 	loff_t end = pos + length, done = 0;
 	ssize_t ret = 0;
+	int id;
 
 	if (iov_iter_rw(iter) == READ) {
 		end = min(end, i_size_read(inode));
@@ -1020,40 +1018,49 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	 * into page tables. We have to tear down these mappings so that data
 	 * written by write(2) is visible in mmap.
 	 */
-	if ((iomap->flags & IOMAP_F_NEW) && inode->i_mapping->nrpages) {
+	if (iomap->flags & IOMAP_F_NEW) {
 		invalidate_inode_pages2_range(inode->i_mapping,
 					      pos >> PAGE_SHIFT,
 					      (end - 1) >> PAGE_SHIFT);
 	}
 
+	id = dax_read_lock();
 	while (pos < end) {
 		unsigned offset = pos & (PAGE_SIZE - 1);
-		struct blk_dax_ctl dax = { 0 };
+		const size_t size = ALIGN(length + offset, PAGE_SIZE);
+		const sector_t sector = dax_iomap_sector(iomap, pos);
 		ssize_t map_len;
+		pgoff_t pgoff;
+		void *kaddr;
+		pfn_t pfn;
 
 		if (fatal_signal_pending(current)) {
 			ret = -EINTR;
 			break;
 		}
 
-		dax.sector = dax_iomap_sector(iomap, pos);
-		dax.size = (length + offset + PAGE_SIZE - 1) & PAGE_MASK;
-		map_len = dax_map_atomic(iomap->bdev, &dax);
+		ret = bdev_dax_pgoff(bdev, sector, size, &pgoff);
+		if (ret)
+			break;
+
+		map_len = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size),
+				&kaddr, &pfn);
 		if (map_len < 0) {
 			ret = map_len;
 			break;
 		}
 
-		dax.addr += offset;
+		map_len = PFN_PHYS(map_len);
+		kaddr += offset;
 		map_len -= offset;
 		if (map_len > end - pos)
 			map_len = end - pos;
 
 		if (iov_iter_rw(iter) == WRITE)
-			map_len = copy_from_iter_pmem(dax.addr, map_len, iter);
+			map_len = dax_copy_from_iter(dax_dev, pgoff, kaddr,
+					map_len, iter);
 		else
-			map_len = copy_to_iter(dax.addr, map_len, iter);
-		dax_unmap_atomic(iomap->bdev, &dax);
+			map_len = copy_to_iter(kaddr, map_len, iter);
 		if (map_len <= 0) {
 			ret = map_len ? map_len : -EFAULT;
 			break;
@@ -1063,6 +1070,7 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 		length -= map_len;
 		done += map_len;
 	}
+	dax_read_unlock(id);
 
 	return done ? done : ret;
 }
@@ -1079,15 +1087,19 @@ dax_iomap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
  */
 ssize_t
 dax_iomap_rw(struct kiocb *iocb, struct iov_iter *iter,
-		struct iomap_ops *ops)
+		const struct iomap_ops *ops)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = mapping->host;
 	loff_t pos = iocb->ki_pos, ret = 0, done = 0;
 	unsigned flags = 0;
 
-	if (iov_iter_rw(iter) == WRITE)
+	if (iov_iter_rw(iter) == WRITE) {
+		lockdep_assert_held_exclusive(&inode->i_rwsem);
 		flags |= IOMAP_WRITE;
+	} else {
+		lockdep_assert_held(&inode->i_rwsem);
+	}
 
 	while (iov_iter_count(iter)) {
 		ret = iomap_apply(inode, pos, iov_iter_count(iter), flags, ops,
@@ -1112,20 +1124,10 @@ static int dax_fault_return(int error)
 	return VM_FAULT_SIGBUS;
 }
 
-/**
- * dax_iomap_fault - handle a page fault on a DAX file
- * @vma: The virtual memory area where the fault occurred
- * @vmf: The description of the fault
- * @ops: iomap ops passed from the file system
- *
- * When a page fault occurs, filesystems may call this helper in their fault
- * or mkwrite handler for DAX files. Assumes the caller has done all the
- * necessary locking for the page fault to proceed successfully.
- */
-int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
-			struct iomap_ops *ops)
+static int dax_iomap_pte_fault(struct vm_fault *vmf,
+			       const struct iomap_ops *ops)
 {
-	struct address_space *mapping = vma->vm_file->f_mapping;
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	struct inode *inode = mapping->host;
 	unsigned long vaddr = vmf->address;
 	loff_t pos = (loff_t)vmf->pgoff << PAGE_SHIFT;
@@ -1136,34 +1138,50 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	int vmf_ret = 0;
 	void *entry;
 
+	trace_dax_pte_fault(inode, vmf, vmf_ret);
 	/*
 	 * Check whether offset isn't beyond end of file now. Caller is supposed
 	 * to hold locks serializing us with truncate / punch hole so this is
 	 * a reliable test.
 	 */
-	if (pos >= i_size_read(inode))
-		return VM_FAULT_SIGBUS;
+	if (pos >= i_size_read(inode)) {
+		vmf_ret = VM_FAULT_SIGBUS;
+		goto out;
+	}
 
 	if ((vmf->flags & FAULT_FLAG_WRITE) && !vmf->cow_page)
 		flags |= IOMAP_WRITE;
 
+	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
+	if (IS_ERR(entry)) {
+		vmf_ret = dax_fault_return(PTR_ERR(entry));
+		goto out;
+	}
+
+	/*
+	 * It is possible, particularly with mixed reads & writes to private
+	 * mappings, that we have raced with a PMD fault that overlaps with
+	 * the PTE we need to set up.  If so just return and the fault will be
+	 * retried.
+	 */
+	if (pmd_trans_huge(*vmf->pmd) || pmd_devmap(*vmf->pmd)) {
+		vmf_ret = VM_FAULT_NOPAGE;
+		goto unlock_entry;
+	}
+
 	/*
 	 * Note that we don't bother to use iomap_apply here: DAX required
 	 * the file system block size to be equal the page size, which means
 	 * that we never have to deal with more than a single extent here.
 	 */
 	error = ops->iomap_begin(inode, pos, PAGE_SIZE, flags, &iomap);
-	if (error)
-		return dax_fault_return(error);
-	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
-		vmf_ret = dax_fault_return(-EIO);	/* fs corruption? */
-		goto finish_iomap;
+	if (error) {
+		vmf_ret = dax_fault_return(error);
+		goto unlock_entry;
 	}
-
-	entry = grab_mapping_entry(mapping, vmf->pgoff, 0);
-	if (IS_ERR(entry)) {
-		vmf_ret = dax_fault_return(PTR_ERR(entry));
-		goto finish_iomap;
+	if (WARN_ON_ONCE(iomap.offset + iomap.length < pos + PAGE_SIZE)) {
+		error = -EIO;	/* fs corruption? */
+		goto error_finish_iomap;
 	}
 
 	sector = dax_iomap_sector(&iomap, pos);
@@ -1175,8 +1193,8 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 			clear_user_highpage(vmf->cow_page, vaddr);
 			break;
 		case IOMAP_MAPPED:
-			error = copy_user_dax(iomap.bdev, sector, PAGE_SIZE,
-					vmf->cow_page, vaddr);
+			error = copy_user_dax(iomap.bdev, iomap.dax_dev,
+					sector, PAGE_SIZE, vmf->cow_page, vaddr);
 			break;
 		default:
 			WARN_ON_ONCE(1);
@@ -1185,24 +1203,24 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		}
 
 		if (error)
-			goto error_unlock_entry;
+			goto error_finish_iomap;
 
 		__SetPageUptodate(vmf->cow_page);
 		vmf_ret = finish_fault(vmf);
 		if (!vmf_ret)
 			vmf_ret = VM_FAULT_DONE_COW;
-		goto unlock_entry;
+		goto finish_iomap;
 	}
 
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
 		if (iomap.flags & IOMAP_F_NEW) {
 			count_vm_event(PGMAJFAULT);
-			mem_cgroup_count_vm_event(vma->vm_mm, PGMAJFAULT);
+			count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
 			major = VM_FAULT_MAJOR;
 		}
-		error = dax_insert_mapping(mapping, iomap.bdev, sector,
-				PAGE_SIZE, &entry, vma, vmf);
+		error = dax_insert_mapping(mapping, iomap.bdev, iomap.dax_dev,
+				sector, PAGE_SIZE, &entry, vmf->vma, vmf);
 		/* -EBUSY is fine, somebody else faulted on the same PTE */
 		if (error == -EBUSY)
 			error = 0;
@@ -1211,7 +1229,7 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 	case IOMAP_HOLE:
 		if (!(vmf->flags & FAULT_FLAG_WRITE)) {
 			vmf_ret = dax_load_hole(mapping, &entry, vmf);
-			goto unlock_entry;
+			goto finish_iomap;
 		}
 		/*FALLTHRU*/
 	default:
@@ -1220,10 +1238,8 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		break;
 	}
 
- error_unlock_entry:
+ error_finish_iomap:
 	vmf_ret = dax_fault_return(error) | major;
- unlock_entry:
-	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
 		int copied = PAGE_SIZE;
@@ -1238,9 +1254,12 @@ int dax_iomap_fault(struct vm_area_struct *vma, struct vm_fault *vmf,
 		 */
 		ops->iomap_end(inode, pos, PAGE_SIZE, copied, flags, &iomap);
 	}
+ unlock_entry:
+	put_locked_mapping_entry(mapping, vmf->pgoff, entry);
+ out:
+	trace_dax_pte_fault_done(inode, vmf, vmf_ret);
 	return vmf_ret;
 }
-EXPORT_SYMBOL_GPL(dax_iomap_fault);
 
 #ifdef CONFIG_FS_DAX_PMD
 /*
@@ -1249,94 +1268,121 @@ EXPORT_SYMBOL_GPL(dax_iomap_fault);
  */
 #define PG_PMD_COLOUR	((PMD_SIZE >> PAGE_SHIFT) - 1)
 
-static int dax_pmd_insert_mapping(struct vm_area_struct *vma, pmd_t *pmd,
-		struct vm_fault *vmf, unsigned long address,
-		struct iomap *iomap, loff_t pos, bool write, void **entryp)
+static int dax_pmd_insert_mapping(struct vm_fault *vmf, struct iomap *iomap,
+		loff_t pos, void **entryp)
 {
-	struct address_space *mapping = vma->vm_file->f_mapping;
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
+	const sector_t sector = dax_iomap_sector(iomap, pos);
+	struct dax_device *dax_dev = iomap->dax_dev;
 	struct block_device *bdev = iomap->bdev;
-	struct blk_dax_ctl dax = {
-		.sector = dax_iomap_sector(iomap, pos),
-		.size = PMD_SIZE,
-	};
-	long length = dax_map_atomic(bdev, &dax);
-	void *ret;
-
-	if (length < 0) /* dax_map_atomic() failed */
-		return VM_FAULT_FALLBACK;
-	if (length < PMD_SIZE)
-		goto unmap_fallback;
-	if (pfn_t_to_pfn(dax.pfn) & PG_PMD_COLOUR)
-		goto unmap_fallback;
-	if (!pfn_t_devmap(dax.pfn))
-		goto unmap_fallback;
-
-	dax_unmap_atomic(bdev, &dax);
+	struct inode *inode = mapping->host;
+	const size_t size = PMD_SIZE;
+	void *ret = NULL, *kaddr;
+	long length = 0;
+	pgoff_t pgoff;
+	pfn_t pfn;
+	int id;
+
+	if (bdev_dax_pgoff(bdev, sector, size, &pgoff) != 0)
+		goto fallback;
 
-	ret = dax_insert_mapping_entry(mapping, vmf, *entryp, dax.sector,
+	id = dax_read_lock();
+	length = dax_direct_access(dax_dev, pgoff, PHYS_PFN(size), &kaddr, &pfn);
+	if (length < 0)
+		goto unlock_fallback;
+	length = PFN_PHYS(length);
+
+	if (length < size)
+		goto unlock_fallback;
+	if (pfn_t_to_pfn(pfn) & PG_PMD_COLOUR)
+		goto unlock_fallback;
+	if (!pfn_t_devmap(pfn))
+		goto unlock_fallback;
+	dax_read_unlock(id);
+
+	ret = dax_insert_mapping_entry(mapping, vmf, *entryp, sector,
 			RADIX_DAX_PMD);
 	if (IS_ERR(ret))
-		return VM_FAULT_FALLBACK;
+		goto fallback;
 	*entryp = ret;
 
-	return vmf_insert_pfn_pmd(vma, address, pmd, dax.pfn, write);
+	trace_dax_pmd_insert_mapping(inode, vmf, length, pfn, ret);
+	return vmf_insert_pfn_pmd(vmf->vma, vmf->address, vmf->pmd,
+			pfn, vmf->flags & FAULT_FLAG_WRITE);
 
- unmap_fallback:
-	dax_unmap_atomic(bdev, &dax);
+unlock_fallback:
+	dax_read_unlock(id);
+fallback:
+	trace_dax_pmd_insert_mapping_fallback(inode, vmf, length, pfn, ret);
 	return VM_FAULT_FALLBACK;
 }
 
-static int dax_pmd_load_hole(struct vm_area_struct *vma, pmd_t *pmd,
-		struct vm_fault *vmf, unsigned long address,
-		struct iomap *iomap, void **entryp)
+static int dax_pmd_load_hole(struct vm_fault *vmf, struct iomap *iomap,
+		void **entryp)
 {
-	struct address_space *mapping = vma->vm_file->f_mapping;
-	unsigned long pmd_addr = address & PMD_MASK;
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
+	unsigned long pmd_addr = vmf->address & PMD_MASK;
+	struct inode *inode = mapping->host;
 	struct page *zero_page;
+	void *ret = NULL;
 	spinlock_t *ptl;
 	pmd_t pmd_entry;
-	void *ret;
 
-	zero_page = mm_get_huge_zero_page(vma->vm_mm);
+	zero_page = mm_get_huge_zero_page(vmf->vma->vm_mm);
 
 	if (unlikely(!zero_page))
-		return VM_FAULT_FALLBACK;
+		goto fallback;
 
 	ret = dax_insert_mapping_entry(mapping, vmf, *entryp, 0,
 			RADIX_DAX_PMD | RADIX_DAX_HZP);
 	if (IS_ERR(ret))
-		return VM_FAULT_FALLBACK;
+		goto fallback;
 	*entryp = ret;
 
-	ptl = pmd_lock(vma->vm_mm, pmd);
-	if (!pmd_none(*pmd)) {
+	ptl = pmd_lock(vmf->vma->vm_mm, vmf->pmd);
+	if (!pmd_none(*(vmf->pmd))) {
 		spin_unlock(ptl);
-		return VM_FAULT_FALLBACK;
+		goto fallback;
 	}
 
-	pmd_entry = mk_pmd(zero_page, vma->vm_page_prot);
+	pmd_entry = mk_pmd(zero_page, vmf->vma->vm_page_prot);
 	pmd_entry = pmd_mkhuge(pmd_entry);
-	set_pmd_at(vma->vm_mm, pmd_addr, pmd, pmd_entry);
+	set_pmd_at(vmf->vma->vm_mm, pmd_addr, vmf->pmd, pmd_entry);
 	spin_unlock(ptl);
+	trace_dax_pmd_load_hole(inode, vmf, zero_page, ret);
 	return VM_FAULT_NOPAGE;
+
+fallback:
+	trace_dax_pmd_load_hole_fallback(inode, vmf, zero_page, ret);
+	return VM_FAULT_FALLBACK;
 }
 
-int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
-		pmd_t *pmd, unsigned int flags, struct iomap_ops *ops)
+static int dax_iomap_pmd_fault(struct vm_fault *vmf,
+			       const struct iomap_ops *ops)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct address_space *mapping = vma->vm_file->f_mapping;
-	unsigned long pmd_addr = address & PMD_MASK;
-	bool write = flags & FAULT_FLAG_WRITE;
+	unsigned long pmd_addr = vmf->address & PMD_MASK;
+	bool write = vmf->flags & FAULT_FLAG_WRITE;
 	unsigned int iomap_flags = (write ? IOMAP_WRITE : 0) | IOMAP_FAULT;
 	struct inode *inode = mapping->host;
 	int result = VM_FAULT_FALLBACK;
 	struct iomap iomap = { 0 };
 	pgoff_t max_pgoff, pgoff;
-	struct vm_fault vmf;
 	void *entry;
 	loff_t pos;
 	int error;
 
+	/*
+	 * Check whether offset isn't beyond end of file now. Caller is
+	 * supposed to hold locks serializing us with truncate / punch hole so
+	 * this is a reliable test.
+	 */
+	pgoff = linear_page_index(vma, pmd_addr);
+	max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT;
+
+	trace_dax_pmd_fault(inode, vmf, max_pgoff, 0);
+
 	/* Fall back to PTEs if we're going to COW */
 	if (write && !(vma->vm_flags & VM_SHARED))
 		goto fallback;
@@ -1347,22 +1393,38 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	if ((pmd_addr + PMD_SIZE) > vma->vm_end)
 		goto fallback;
 
-	/*
-	 * Check whether offset isn't beyond end of file now. Caller is
-	 * supposed to hold locks serializing us with truncate / punch hole so
-	 * this is a reliable test.
-	 */
-	pgoff = linear_page_index(vma, pmd_addr);
-	max_pgoff = (i_size_read(inode) - 1) >> PAGE_SHIFT;
-
-	if (pgoff > max_pgoff)
-		return VM_FAULT_SIGBUS;
+	if (pgoff > max_pgoff) {
+		result = VM_FAULT_SIGBUS;
+		goto out;
+	}
 
 	/* If the PMD would extend beyond the file size */
 	if ((pgoff | PG_PMD_COLOUR) > max_pgoff)
 		goto fallback;
 
 	/*
+	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
+	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
+	 * the tree, for instance), it will return -EEXIST and we just fall
+	 * back to 4k entries.
+	 */
+	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
+	if (IS_ERR(entry))
+		goto fallback;
+
+	/*
+	 * It is possible, particularly with mixed reads & writes to private
+	 * mappings, that we have raced with a PTE fault that overlaps with
+	 * the PMD we need to set up.  If so just return and the fault will be
+	 * retried.
+	 */
+	if (!pmd_none(*vmf->pmd) && !pmd_trans_huge(*vmf->pmd) &&
+			!pmd_devmap(*vmf->pmd)) {
+		result = 0;
+		goto unlock_entry;
+	}
+
+	/*
 	 * Note that we don't use iomap_apply here.  We aren't doing I/O, only
 	 * setting up a mapping, so really we're using iomap_begin() as a way
 	 * to look up our filesystem block.
@@ -1370,44 +1432,26 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 	pos = (loff_t)pgoff << PAGE_SHIFT;
 	error = ops->iomap_begin(inode, pos, PMD_SIZE, iomap_flags, &iomap);
 	if (error)
-		goto fallback;
+		goto unlock_entry;
 
 	if (iomap.offset + iomap.length < pos + PMD_SIZE)
 		goto finish_iomap;
 
-	/*
-	 * grab_mapping_entry() will make sure we get a 2M empty entry, a DAX
-	 * PMD or a HZP entry.  If it can't (because a 4k page is already in
-	 * the tree, for instance), it will return -EEXIST and we just fall
-	 * back to 4k entries.
-	 */
-	entry = grab_mapping_entry(mapping, pgoff, RADIX_DAX_PMD);
-	if (IS_ERR(entry))
-		goto finish_iomap;
-
-	vmf.pgoff = pgoff;
-	vmf.flags = flags;
-	vmf.gfp_mask = mapping_gfp_mask(mapping) | __GFP_IO;
-
 	switch (iomap.type) {
 	case IOMAP_MAPPED:
-		result = dax_pmd_insert_mapping(vma, pmd, &vmf, address,
-				&iomap, pos, write, &entry);
+		result = dax_pmd_insert_mapping(vmf, &iomap, pos, &entry);
 		break;
 	case IOMAP_UNWRITTEN:
 	case IOMAP_HOLE:
 		if (WARN_ON_ONCE(write))
-			goto unlock_entry;
-		result = dax_pmd_load_hole(vma, pmd, &vmf, address, &iomap,
-				&entry);
+			break;
+		result = dax_pmd_load_hole(vmf, &iomap, &entry);
 		break;
 	default:
 		WARN_ON_ONCE(1);
 		break;
 	}
 
- unlock_entry:
-	put_locked_mapping_entry(mapping, pgoff, entry);
  finish_iomap:
 	if (ops->iomap_end) {
 		int copied = PMD_SIZE;
@@ -1423,12 +1467,45 @@ int dax_iomap_pmd_fault(struct vm_area_struct *vma, unsigned long address,
 		ops->iomap_end(inode, pos, PMD_SIZE, copied, iomap_flags,
 				&iomap);
 	}
+ unlock_entry:
+	put_locked_mapping_entry(mapping, pgoff, entry);
  fallback:
 	if (result == VM_FAULT_FALLBACK) {
-		split_huge_pmd(vma, pmd, address);
+		split_huge_pmd(vma, vmf->pmd, vmf->address);
 		count_vm_event(THP_FAULT_FALLBACK);
 	}
+out:
+	trace_dax_pmd_fault_done(inode, vmf, max_pgoff, result);
 	return result;
 }
-EXPORT_SYMBOL_GPL(dax_iomap_pmd_fault);
+#else
+static int dax_iomap_pmd_fault(struct vm_fault *vmf,
+			       const struct iomap_ops *ops)
+{
+	return VM_FAULT_FALLBACK;
+}
 #endif /* CONFIG_FS_DAX_PMD */
+
+/**
+ * dax_iomap_fault - handle a page fault on a DAX file
+ * @vmf: The description of the fault
+ * @ops: iomap ops passed from the file system
+ *
+ * When a page fault occurs, filesystems may call this helper in
+ * their fault handler for DAX files. dax_iomap_fault() assumes the caller
+ * has done all the necessary locking for page fault to proceed
+ * successfully.
+ */
+int dax_iomap_fault(struct vm_fault *vmf, enum page_entry_size pe_size,
+		    const struct iomap_ops *ops)
+{
+	switch (pe_size) {
+	case PE_SIZE_PTE:
+		return dax_iomap_pte_fault(vmf, ops);
+	case PE_SIZE_PMD:
+		return dax_iomap_pmd_fault(vmf, ops);
+	default:
+		return VM_FAULT_FALLBACK;
+	}
+}
+EXPORT_SYMBOL_GPL(dax_iomap_fault);
diff --git a/fs/dcache.c b/fs/dcache.c
index 95d71eda8142..f90141387f01 100644
--- a/fs/dcache.c
+++ b/fs/dcache.c
@@ -90,6 +90,11 @@ EXPORT_SYMBOL(rename_lock);
 
 static struct kmem_cache *dentry_cache __read_mostly;
 
+const struct qstr empty_name = QSTR_INIT("", 0);
+EXPORT_SYMBOL(empty_name);
+const struct qstr slash_name = QSTR_INIT("/", 1);
+EXPORT_SYMBOL(slash_name);
+
 /*
  * This is the single most critical data structure when it comes
  * to the dcache: the hashtable for lookups. Somebody should try
@@ -277,6 +282,33 @@ static inline int dname_external(const struct dentry *dentry)
 	return dentry->d_name.name != dentry->d_iname;
 }
 
+void take_dentry_name_snapshot(struct name_snapshot *name, struct dentry *dentry)
+{
+	spin_lock(&dentry->d_lock);
+	if (unlikely(dname_external(dentry))) {
+		struct external_name *p = external_name(dentry);
+		atomic_inc(&p->u.count);
+		spin_unlock(&dentry->d_lock);
+		name->name = p->name;
+	} else {
+		memcpy(name->inline_name, dentry->d_iname, DNAME_INLINE_LEN);
+		spin_unlock(&dentry->d_lock);
+		name->name = name->inline_name;
+	}
+}
+EXPORT_SYMBOL(take_dentry_name_snapshot);
+
+void release_dentry_name_snapshot(struct name_snapshot *name)
+{
+	if (unlikely(name->name != name->inline_name)) {
+		struct external_name *p;
+		p = container_of(name->name, struct external_name, name[0]);
+		if (unlikely(atomic_dec_and_test(&p->u.count)))
+			kfree_rcu(p, u.head);
+	}
+}
+EXPORT_SYMBOL(release_dentry_name_snapshot);
+
 static inline void __d_set_inode_and_type(struct dentry *dentry,
 					  struct inode *inode,
 					  unsigned type_flags)
@@ -419,6 +451,8 @@ static void dentry_lru_add(struct dentry *dentry)
 {
 	if (unlikely(!(dentry->d_flags & DCACHE_LRU_LIST)))
 		d_lru_add(dentry);
+	else if (unlikely(!(dentry->d_flags & DCACHE_REFERENCED)))
+		dentry->d_flags |= DCACHE_REFERENCED;
 }
 
 /**
@@ -779,8 +813,6 @@ repeat:
 			goto kill_it;
 	}
 
-	if (!(dentry->d_flags & DCACHE_REFERENCED))
-		dentry->d_flags |= DCACHE_REFERENCED;
 	dentry_lru_add(dentry);
 
 	dentry->d_lockref.count--;
@@ -1133,11 +1165,12 @@ void shrink_dcache_sb(struct super_block *sb)
 		LIST_HEAD(dispose);
 
 		freed = list_lru_walk(&sb->s_dentry_lru,
-			dentry_lru_isolate_shrink, &dispose, UINT_MAX);
+			dentry_lru_isolate_shrink, &dispose, 1024);
 
 		this_cpu_sub(nr_dentry_unused, freed);
 		shrink_dentry_list(&dispose);
-	} while (freed > 0);
+		cond_resched();
+	} while (list_lru_count(&sb->s_dentry_lru) > 0);
 }
 EXPORT_SYMBOL(shrink_dcache_sb);
 
@@ -1494,7 +1527,7 @@ static void check_and_drop(void *_data)
 {
 	struct detach_data *data = _data;
 
-	if (!data->mountpoint && !data->select.found)
+	if (!data->mountpoint && list_empty(&data->select.dispose))
 		__d_drop(data->select.start);
 }
 
@@ -1536,17 +1569,15 @@ void d_invalidate(struct dentry *dentry)
 
 		d_walk(dentry, &data, detach_and_collect, check_and_drop);
 
-		if (data.select.found)
+		if (!list_empty(&data.select.dispose))
 			shrink_dentry_list(&data.select.dispose);
+		else if (!data.mountpoint)
+			return;
 
 		if (data.mountpoint) {
 			detach_mounts(data.mountpoint);
 			dput(data.mountpoint);
 		}
-
-		if (!data.mountpoint && !data.select.found)
-			break;
-
 		cond_resched();
 	}
 }
@@ -1580,8 +1611,7 @@ struct dentry *__d_alloc(struct super_block *sb, const struct qstr *name)
 	 */
 	dentry->d_iname[DNAME_INLINE_LEN-1] = 0;
 	if (unlikely(!name)) {
-		static const struct qstr anon = QSTR_INIT("/", 1);
-		name = &anon;
+		name = &slash_name;
 		dname = dentry->d_iname;
 	} else if (name->len > DNAME_INLINE_LEN-1) {
 		size_t size = offsetof(struct external_name, name[1]);
@@ -3548,8 +3578,6 @@ __setup("dhash_entries=", set_dhash_entries);
 
 static void __init dcache_init_early(void)
 {
-	unsigned int loop;
-
 	/* If hashes are distributed across NUMA nodes, defer
 	 * hash allocation until vmalloc space is available.
 	 */
@@ -3561,24 +3589,19 @@ static void __init dcache_init_early(void)
 					sizeof(struct hlist_bl_head),
 					dhash_entries,
 					13,
-					HASH_EARLY,
+					HASH_EARLY | HASH_ZERO,
 					&d_hash_shift,
 					&d_hash_mask,
 					0,
 					0);
-
-	for (loop = 0; loop < (1U << d_hash_shift); loop++)
-		INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
 }
 
 static void __init dcache_init(void)
 {
-	unsigned int loop;
-
-	/* 
+	/*
 	 * A constructor could be added for stable state like the lists,
 	 * but it is probably not worth it because of the cache nature
-	 * of the dcache. 
+	 * of the dcache.
 	 */
 	dentry_cache = KMEM_CACHE(dentry,
 		SLAB_RECLAIM_ACCOUNT|SLAB_PANIC|SLAB_MEM_SPREAD|SLAB_ACCOUNT);
@@ -3592,14 +3615,11 @@ static void __init dcache_init(void)
 					sizeof(struct hlist_bl_head),
 					dhash_entries,
 					13,
-					0,
+					HASH_ZERO,
 					&d_hash_shift,
 					&d_hash_mask,
 					0,
 					0);
-
-	for (loop = 0; loop < (1U << d_hash_shift); loop++)
-		INIT_HLIST_BL_HEAD(dentry_hashtable + loop);
 }
 
 /* SLAB cache for __getname() consumers */
@@ -3610,6 +3630,11 @@ EXPORT_SYMBOL(d_genocide);
 
 void __init vfs_caches_init_early(void)
 {
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(in_lookup_hashtable); i++)
+		INIT_HLIST_BL_HEAD(&in_lookup_hashtable[i]);
+
 	dcache_init_early();
 	inode_init_early();
 }
diff --git a/fs/debugfs/file.c b/fs/debugfs/file.c
index 354e2ab62031..6dabc4a10396 100644
--- a/fs/debugfs/file.c
+++ b/fs/debugfs/file.c
@@ -9,7 +9,7 @@
  *	2 as published by the Free Software Foundation.
  *
  *  debugfs is for people to use instead of /proc or /sys.
- *  See Documentation/DocBook/filesystems for more details.
+ *  See Documentation/filesystems/ for more details.
  *
  */
 
diff --git a/fs/debugfs/inode.c b/fs/debugfs/inode.c
index f17fcf89e18e..c59f015f386e 100644
--- a/fs/debugfs/inode.c
+++ b/fs/debugfs/inode.c
@@ -9,7 +9,7 @@
  *	2 as published by the Free Software Foundation.
  *
  *  debugfs is for people to use instead of /proc or /sys.
- *  See Documentation/DocBook/kernel-api for more details.
+ *  See ./Documentation/core-api/kernel-api.rst for more details.
  *
  */
 
@@ -187,9 +187,9 @@ static const struct super_operations debugfs_super_operations = {
 
 static struct vfsmount *debugfs_automount(struct path *path)
 {
-	struct vfsmount *(*f)(void *);
-	f = (struct vfsmount *(*)(void *))path->dentry->d_fsdata;
-	return f(d_inode(path->dentry)->i_private);
+	debugfs_automount_t f;
+	f = (debugfs_automount_t)path->dentry->d_fsdata;
+	return f(path->dentry, d_inode(path->dentry)->i_private);
 }
 
 static const struct dentry_operations debugfs_dops = {
@@ -199,12 +199,10 @@ static const struct dentry_operations debugfs_dops = {
 
 static int debug_fill_super(struct super_block *sb, void *data, int silent)
 {
-	static struct tree_descr debug_files[] = {{""}};
+	static const struct tree_descr debug_files[] = {{""}};
 	struct debugfs_fs_info *fsi;
 	int err;
 
-	save_mount_options(sb, data);
-
 	fsi = kzalloc(sizeof(struct debugfs_fs_info), GFP_KERNEL);
 	sb->s_fs_info = fsi;
 	if (!fsi) {
@@ -248,6 +246,42 @@ static struct file_system_type debug_fs_type = {
 };
 MODULE_ALIAS_FS("debugfs");
 
+/**
+ * debugfs_lookup() - look up an existing debugfs file
+ * @name: a pointer to a string containing the name of the file to look up.
+ * @parent: a pointer to the parent dentry of the file.
+ *
+ * This function will return a pointer to a dentry if it succeeds.  If the file
+ * doesn't exist or an error occurs, %NULL will be returned.  The returned
+ * dentry must be passed to dput() when it is no longer needed.
+ *
+ * If debugfs is not enabled in the kernel, the value -%ENODEV will be
+ * returned.
+ */
+struct dentry *debugfs_lookup(const char *name, struct dentry *parent)
+{
+	struct dentry *dentry;
+
+	if (IS_ERR(parent))
+		return NULL;
+
+	if (!parent)
+		parent = debugfs_mount->mnt_root;
+
+	inode_lock(d_inode(parent));
+	dentry = lookup_one_len(name, parent, strlen(name));
+	inode_unlock(d_inode(parent));
+
+	if (IS_ERR(dentry))
+		return NULL;
+	if (!d_really_is_positive(dentry)) {
+		dput(dentry);
+		return NULL;
+	}
+	return dentry;
+}
+EXPORT_SYMBOL_GPL(debugfs_lookup);
+
 static struct dentry *start_creating(const char *name, struct dentry *parent)
 {
 	struct dentry *dentry;
@@ -504,7 +538,7 @@ EXPORT_SYMBOL_GPL(debugfs_create_dir);
  */
 struct dentry *debugfs_create_automount(const char *name,
 					struct dentry *parent,
-					struct vfsmount *(*f)(void *),
+					debugfs_automount_t f,
 					void *data)
 {
 	struct dentry *dentry = start_creating(name, parent);
@@ -730,7 +764,7 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
 {
 	int error;
 	struct dentry *dentry = NULL, *trap;
-	const char *old_name;
+	struct name_snapshot old_name;
 
 	trap = lock_rename(new_dir, old_dir);
 	/* Source or destination directories don't exist? */
@@ -745,19 +779,19 @@ struct dentry *debugfs_rename(struct dentry *old_dir, struct dentry *old_dentry,
 	if (IS_ERR(dentry) || dentry == trap || d_really_is_positive(dentry))
 		goto exit;
 
-	old_name = fsnotify_oldname_init(old_dentry->d_name.name);
+	take_dentry_name_snapshot(&old_name, old_dentry);
 
 	error = simple_rename(d_inode(old_dir), old_dentry, d_inode(new_dir),
 			      dentry, 0);
 	if (error) {
-		fsnotify_oldname_free(old_name);
+		release_dentry_name_snapshot(&old_name);
 		goto exit;
 	}
 	d_move(old_dentry, dentry);
-	fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name,
+	fsnotify_move(d_inode(old_dir), d_inode(new_dir), old_name.name,
 		d_is_dir(old_dentry),
 		NULL, old_dentry);
-	fsnotify_oldname_free(old_name);
+	release_dentry_name_snapshot(&old_name);
 	unlock_rename(new_dir, old_dir);
 	dput(dentry);
 	return old_dentry;
diff --git a/fs/direct-io.c b/fs/direct-io.c
index c87bae4376b8..08cf27811e5a 100644
--- a/fs/direct-io.c
+++ b/fs/direct-io.c
@@ -294,7 +294,7 @@ static void dio_aio_complete_work(struct work_struct *work)
 	dio_complete(dio, 0, true);
 }
 
-static int dio_bio_complete(struct dio *dio, struct bio *bio);
+static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio);
 
 /*
  * Asynchronous IO callback. 
@@ -348,13 +348,12 @@ static void dio_bio_end_io(struct bio *bio)
 /**
  * dio_end_io - handle the end io action for the given bio
  * @bio: The direct io bio thats being completed
- * @error: Error if there was one
  *
  * This is meant to be called by any filesystem that uses their own dio_submit_t
  * so that the DIO specific endio actions are dealt with after the filesystem
  * has done it's completion work.
  */
-void dio_end_io(struct bio *bio, int error)
+void dio_end_io(struct bio *bio)
 {
 	struct dio *dio = bio->bi_private;
 
@@ -386,6 +385,8 @@ dio_bio_alloc(struct dio *dio, struct dio_submit *sdio,
 	else
 		bio->bi_end_io = dio_bio_end_io;
 
+	bio->bi_write_hint = dio->iocb->ki_hint;
+
 	sdio->bio = bio;
 	sdio->logical_offset_in_bio = sdio->cur_page_fs_offset;
 }
@@ -474,17 +475,20 @@ static struct bio *dio_await_one(struct dio *dio)
 /*
  * Process one completed BIO.  No locks are held.
  */
-static int dio_bio_complete(struct dio *dio, struct bio *bio)
+static blk_status_t dio_bio_complete(struct dio *dio, struct bio *bio)
 {
 	struct bio_vec *bvec;
 	unsigned i;
-	int err;
+	blk_status_t err = bio->bi_status;
 
-	if (bio->bi_error)
-		dio->io_error = -EIO;
+	if (err) {
+		if (err == BLK_STS_AGAIN && (bio->bi_opf & REQ_NOWAIT))
+			dio->io_error = -EAGAIN;
+		else
+			dio->io_error = -EIO;
+	}
 
 	if (dio->is_async && dio->op == REQ_OP_READ && dio->should_dirty) {
-		err = bio->bi_error;
 		bio_check_pages_dirty(bio);	/* transfers ownership */
 	} else {
 		bio_for_each_segment_all(bvec, bio, i) {
@@ -495,7 +499,6 @@ static int dio_bio_complete(struct dio *dio, struct bio *bio)
 				set_page_dirty_lock(page);
 			put_page(page);
 		}
-		err = bio->bi_error;
 		bio_put(bio);
 	}
 	return err;
@@ -539,7 +542,7 @@ static inline int dio_bio_reap(struct dio *dio, struct dio_submit *sdio)
 			bio = dio->bio_list;
 			dio->bio_list = bio->bi_private;
 			spin_unlock_irqrestore(&dio->bio_lock, flags);
-			ret2 = dio_bio_complete(dio, bio);
+			ret2 = blk_status_to_errno(dio_bio_complete(dio, bio));
 			if (ret == 0)
 				ret = ret2;
 		}
@@ -587,7 +590,7 @@ static int dio_set_defer_completion(struct dio *dio)
 /*
  * Call into the fs to map some more disk blocks.  We record the current number
  * of available blocks at sdio->blocks_available.  These are in units of the
- * fs blocksize, (1 << inode->i_blkbits).
+ * fs blocksize, i_blocksize(inode).
  *
  * The fs is allowed to map lots of blocks at once.  If it wants to do that,
  * it uses the passed inode-relative block number as the file offset, as usual.
@@ -1197,6 +1200,8 @@ do_blockdev_direct_IO(struct kiocb *iocb, struct inode *inode,
 	if (iov_iter_rw(iter) == WRITE) {
 		dio->op = REQ_OP_WRITE;
 		dio->op_flags = REQ_SYNC | REQ_IDLE;
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			dio->op_flags |= REQ_NOWAIT;
 	} else {
 		dio->op = REQ_OP_READ;
 	}
diff --git a/fs/dlm/lowcomms.c b/fs/dlm/lowcomms.c
index 7d398d300e97..9382db998ec9 100644
--- a/fs/dlm/lowcomms.c
+++ b/fs/dlm/lowcomms.c
@@ -743,7 +743,7 @@ static int tcp_accept_from_sock(struct connection *con)
 	newsock->type = con->sock->type;
 	newsock->ops = con->sock->ops;
 
-	result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK);
+	result = con->sock->ops->accept(con->sock, newsock, O_NONBLOCK, true);
 	if (result < 0)
 		goto accept_err;
 
diff --git a/fs/dlm/user.c b/fs/dlm/user.c
index 1ce908c2232c..23488f559cf9 100644
--- a/fs/dlm/user.c
+++ b/fs/dlm/user.c
@@ -17,6 +17,7 @@
 #include <linux/dlm.h>
 #include <linux/dlm_device.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
 
 #include "dlm_internal.h"
 #include "lockspace.h"
diff --git a/fs/ecryptfs/ecryptfs_kernel.h b/fs/ecryptfs/ecryptfs_kernel.h
index 599a29237cfe..9c351bf757b2 100644
--- a/fs/ecryptfs/ecryptfs_kernel.h
+++ b/fs/ecryptfs/ecryptfs_kernel.h
@@ -117,7 +117,7 @@ ecryptfs_get_key_payload_data(struct key *key)
 
 	auth_tok = ecryptfs_get_encrypted_key_payload_data(key);
 	if (!auth_tok)
-		return (struct ecryptfs_auth_tok *)user_key_payload(key)->data;
+		return (struct ecryptfs_auth_tok *)user_key_payload_locked(key)->data;
 	else
 		return auth_tok;
 }
@@ -349,7 +349,6 @@ struct ecryptfs_mount_crypt_stat {
 struct ecryptfs_sb_info {
 	struct super_block *wsi_sb;
 	struct ecryptfs_mount_crypt_stat mount_crypt_stat;
-	struct backing_dev_info bdi;
 };
 
 /* file private data. */
diff --git a/fs/ecryptfs/inode.c b/fs/ecryptfs/inode.c
index e7413f82d27b..efc2db42d175 100644
--- a/fs/ecryptfs/inode.c
+++ b/fs/ecryptfs/inode.c
@@ -959,9 +959,10 @@ out:
 	return rc;
 }
 
-static int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
-				 struct kstat *stat)
+static int ecryptfs_getattr_link(const struct path *path, struct kstat *stat,
+				 u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	struct ecryptfs_mount_crypt_stat *mount_crypt_stat;
 	int rc = 0;
 
@@ -983,13 +984,15 @@ static int ecryptfs_getattr_link(struct vfsmount *mnt, struct dentry *dentry,
 	return rc;
 }
 
-static int ecryptfs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			    struct kstat *stat)
+static int ecryptfs_getattr(const struct path *path, struct kstat *stat,
+			    u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
 	struct kstat lower_stat;
 	int rc;
 
-	rc = vfs_getattr(ecryptfs_dentry_to_lower_path(dentry), &lower_stat);
+	rc = vfs_getattr(ecryptfs_dentry_to_lower_path(dentry), &lower_stat,
+			 request_mask, flags);
 	if (!rc) {
 		fsstack_copy_attr_all(d_inode(dentry),
 				      ecryptfs_inode_to_lower(d_inode(dentry)));
diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
index 866bb18efefe..e00d45af84ea 100644
--- a/fs/ecryptfs/kthread.c
+++ b/fs/ecryptfs/kthread.c
@@ -123,7 +123,7 @@ void ecryptfs_destroy_kthread(void)
  * @lower_dentry: Lower dentry for file to open
  * @lower_mnt: Lower vfsmount for file to open
  *
- * This function gets a r/w file opened againt the lower dentry.
+ * This function gets a r/w file opened against the lower dentry.
  *
  * Returns zero on success; non-zero otherwise
  */
diff --git a/fs/ecryptfs/main.c b/fs/ecryptfs/main.c
index 151872dcc1f4..9014479d0160 100644
--- a/fs/ecryptfs/main.c
+++ b/fs/ecryptfs/main.c
@@ -519,12 +519,11 @@ static struct dentry *ecryptfs_mount(struct file_system_type *fs_type, int flags
 		goto out;
 	}
 
-	rc = bdi_setup_and_register(&sbi->bdi, "ecryptfs");
+	rc = super_setup_bdi(s);
 	if (rc)
 		goto out1;
 
 	ecryptfs_set_superblock_private(s, sbi);
-	s->s_bdi = &sbi->bdi;
 
 	/* ->kill_sb() will take care of sbi after that point */
 	sbi = NULL;
@@ -633,7 +632,6 @@ static void ecryptfs_kill_block_super(struct super_block *sb)
 	if (!sb_info)
 		return;
 	ecryptfs_destroy_mount_crypt_stat(&sb_info->mount_crypt_stat);
-	bdi_destroy(&sb_info->bdi);
 	kmem_cache_free(ecryptfs_sb_info_cache, sb_info);
 }
 
diff --git a/fs/ecryptfs/read_write.c b/fs/ecryptfs/read_write.c
index 158a3a39f82d..039e627194a9 100644
--- a/fs/ecryptfs/read_write.c
+++ b/fs/ecryptfs/read_write.c
@@ -22,6 +22,8 @@
 
 #include <linux/fs.h>
 #include <linux/pagemap.h>
+#include <linux/sched/signal.h>
+
 #include "ecryptfs_kernel.h"
 
 /**
diff --git a/fs/efivarfs/super.c b/fs/efivarfs/super.c
index d7a7c53803c1..5b68e4294faa 100644
--- a/fs/efivarfs/super.c
+++ b/fs/efivarfs/super.c
@@ -29,7 +29,6 @@ static const struct super_operations efivarfs_ops = {
 	.statfs = simple_statfs,
 	.drop_inode = generic_delete_inode,
 	.evict_inode = efivarfs_evict_inode,
-	.show_options = generic_show_options,
 };
 
 static struct super_block *efivarfs_sb;
diff --git a/fs/eventfd.c b/fs/eventfd.c
index 1231cd1999d8..2fb4eadaa118 100644
--- a/fs/eventfd.c
+++ b/fs/eventfd.c
@@ -9,7 +9,7 @@
 #include <linux/poll.h>
 #include <linux/init.h>
 #include <linux/fs.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/kernel.h>
 #include <linux/slab.h>
 #include <linux/list.h>
@@ -191,7 +191,7 @@ static void eventfd_ctx_do_read(struct eventfd_ctx *ctx, __u64 *cnt)
  * This is used to atomically remove a wait queue entry from the eventfd wait
  * queue head, and read/reset the counter value.
  */
-int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_t *wait,
+int eventfd_ctx_remove_wait_queue(struct eventfd_ctx *ctx, wait_queue_entry_t *wait,
 				  __u64 *cnt)
 {
 	unsigned long flags;
@@ -215,8 +215,8 @@ EXPORT_SYMBOL_GPL(eventfd_ctx_remove_wait_queue);
  *
  * Returns %0 if successful, or the following error codes:
  *
- * -EAGAIN      : The operation would have blocked but @no_wait was non-zero.
- * -ERESTARTSYS : A signal interrupted the wait operation.
+ *  - -EAGAIN      : The operation would have blocked but @no_wait was non-zero.
+ *  - -ERESTARTSYS : A signal interrupted the wait operation.
  *
  * If @no_wait is zero, the function might sleep until the eventfd internal
  * counter becomes greater than zero.
diff --git a/fs/eventpoll.c b/fs/eventpoll.c
index bcb68fcc8445..e767e4389cb1 100644
--- a/fs/eventpoll.c
+++ b/fs/eventpoll.c
@@ -13,7 +13,7 @@
 
 #include <linux/init.h>
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/signal.h>
@@ -42,6 +42,7 @@
 #include <linux/seq_file.h>
 #include <linux/compat.h>
 #include <linux/rculist.h>
+#include <net/busy_poll.h>
 
 /*
  * LOCKING:
@@ -224,6 +225,11 @@ struct eventpoll {
 	/* used to optimize loop detection check */
 	int visited;
 	struct list_head visited_list_link;
+
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	/* used to track busy poll napi_id */
+	unsigned int napi_id;
+#endif
 };
 
 /* Wait structure used by the poll hooks */
@@ -238,7 +244,7 @@ struct eppoll_entry {
 	 * Wait queue item that will be linked to the target file wait
 	 * queue head.
 	 */
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	/* The wait queue head that linked the "wait" wait queue item */
 	wait_queue_head_t *whead;
@@ -341,13 +347,13 @@ static inline int ep_is_linked(struct list_head *p)
 	return !list_empty(p);
 }
 
-static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_t *p)
+static inline struct eppoll_entry *ep_pwq_from_wait(wait_queue_entry_t *p)
 {
 	return container_of(p, struct eppoll_entry, wait);
 }
 
 /* Get the "struct epitem" from a wait queue pointer */
-static inline struct epitem *ep_item_from_wait(wait_queue_t *p)
+static inline struct epitem *ep_item_from_wait(wait_queue_entry_t *p)
 {
 	return container_of(p, struct eppoll_entry, wait)->base;
 }
@@ -384,6 +390,77 @@ static inline int ep_events_available(struct eventpoll *ep)
 	return !list_empty(&ep->rdllist) || ep->ovflist != EP_UNACTIVE_PTR;
 }
 
+#ifdef CONFIG_NET_RX_BUSY_POLL
+static bool ep_busy_loop_end(void *p, unsigned long start_time)
+{
+	struct eventpoll *ep = p;
+
+	return ep_events_available(ep) || busy_loop_timeout(start_time);
+}
+#endif /* CONFIG_NET_RX_BUSY_POLL */
+
+/*
+ * Busy poll if globally on and supporting sockets found && no events,
+ * busy loop will return if need_resched or ep_events_available.
+ *
+ * we must do our busy polling with irqs enabled
+ */
+static void ep_busy_loop(struct eventpoll *ep, int nonblock)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	unsigned int napi_id = READ_ONCE(ep->napi_id);
+
+	if ((napi_id >= MIN_NAPI_ID) && net_busy_loop_on())
+		napi_busy_loop(napi_id, nonblock ? NULL : ep_busy_loop_end, ep);
+#endif
+}
+
+static inline void ep_reset_busy_poll_napi_id(struct eventpoll *ep)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	if (ep->napi_id)
+		ep->napi_id = 0;
+#endif
+}
+
+/*
+ * Set epoll busy poll NAPI ID from sk.
+ */
+static inline void ep_set_busy_poll_napi_id(struct epitem *epi)
+{
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	struct eventpoll *ep;
+	unsigned int napi_id;
+	struct socket *sock;
+	struct sock *sk;
+	int err;
+
+	if (!net_busy_loop_on())
+		return;
+
+	sock = sock_from_file(epi->ffd.file, &err);
+	if (!sock)
+		return;
+
+	sk = sock->sk;
+	if (!sk)
+		return;
+
+	napi_id = READ_ONCE(sk->sk_napi_id);
+	ep = epi->ep;
+
+	/* Non-NAPI IDs can be rejected
+	 *	or
+	 * Nothing to do if we already have this ID
+	 */
+	if (napi_id < MIN_NAPI_ID || napi_id == ep->napi_id)
+		return;
+
+	/* record NAPI ID for use in next busy poll */
+	ep->napi_id = napi_id;
+#endif
+}
+
 /**
  * ep_call_nested - Perform a bound (possibly) nested call, by checking
  *                  that the recursion limit is not exceeded, and that
@@ -883,10 +960,14 @@ static void ep_show_fdinfo(struct seq_file *m, struct file *f)
 	mutex_lock(&ep->mtx);
 	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
 		struct epitem *epi = rb_entry(rbp, struct epitem, rbn);
+		struct inode *inode = file_inode(epi->ffd.file);
 
-		seq_printf(m, "tfd: %8d events: %8x data: %16llx\n",
+		seq_printf(m, "tfd: %8d events: %8x data: %16llx "
+			   " pos:%lli ino:%lx sdev:%x\n",
 			   epi->ffd.fd, epi->event.events,
-			   (long long)epi->event.data);
+			   (long long)epi->event.data,
+			   (long long)epi->ffd.file->f_pos,
+			   inode->i_ino, inode->i_sb->s_dev);
 		if (seq_has_overflowed(m))
 			break;
 	}
@@ -996,12 +1077,56 @@ static struct epitem *ep_find(struct eventpoll *ep, struct file *file, int fd)
 	return epir;
 }
 
+#ifdef CONFIG_CHECKPOINT_RESTORE
+static struct epitem *ep_find_tfd(struct eventpoll *ep, int tfd, unsigned long toff)
+{
+	struct rb_node *rbp;
+	struct epitem *epi;
+
+	for (rbp = rb_first(&ep->rbr); rbp; rbp = rb_next(rbp)) {
+		epi = rb_entry(rbp, struct epitem, rbn);
+		if (epi->ffd.fd == tfd) {
+			if (toff == 0)
+				return epi;
+			else
+				toff--;
+		}
+		cond_resched();
+	}
+
+	return NULL;
+}
+
+struct file *get_epoll_tfile_raw_ptr(struct file *file, int tfd,
+				     unsigned long toff)
+{
+	struct file *file_raw;
+	struct eventpoll *ep;
+	struct epitem *epi;
+
+	if (!is_file_epoll(file))
+		return ERR_PTR(-EINVAL);
+
+	ep = file->private_data;
+
+	mutex_lock(&ep->mtx);
+	epi = ep_find_tfd(ep, tfd, toff);
+	if (epi)
+		file_raw = epi->ffd.file;
+	else
+		file_raw = ERR_PTR(-ENOENT);
+	mutex_unlock(&ep->mtx);
+
+	return file_raw;
+}
+#endif /* CONFIG_CHECKPOINT_RESTORE */
+
 /*
  * This is the callback that is passed to the wait queue wakeup
  * mechanism. It is called by the stored file descriptors when they
  * have events to report.
  */
-static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int ep_poll_callback(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	int pwake = 0;
 	unsigned long flags;
@@ -1017,11 +1142,13 @@ static int ep_poll_callback(wait_queue_t *wait, unsigned mode, int sync, void *k
 		 * can't use __remove_wait_queue(). whead->lock is held by
 		 * the caller.
 		 */
-		list_del_init(&wait->task_list);
+		list_del_init(&wait->entry);
 	}
 
 	spin_lock_irqsave(&ep->lock, flags);
 
+	ep_set_busy_poll_napi_id(epi);
+
 	/*
 	 * If the event mask does not contain any poll(2) event, we consider the
 	 * descriptor to be disabled. This condition is likely the effect of the
@@ -1363,6 +1490,9 @@ static int ep_insert(struct eventpoll *ep, struct epoll_event *event,
 	/* We have to drop the new item inside our item list to keep track of it */
 	spin_lock_irqsave(&ep->lock, flags);
 
+	/* record NAPI ID of new item if present */
+	ep_set_busy_poll_napi_id(epi);
+
 	/* If the file is already "ready" we drop it inside the ready list */
 	if ((revents & event->events) && !ep_is_linked(&epi->rdllink)) {
 		list_add_tail(&epi->rdllink, &ep->rdllist);
@@ -1617,7 +1747,7 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	int res = 0, eavail, timed_out = 0;
 	unsigned long flags;
 	u64 slack = 0;
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	ktime_t expires, *to = NULL;
 
 	if (timeout > 0) {
@@ -1637,10 +1767,21 @@ static int ep_poll(struct eventpoll *ep, struct epoll_event __user *events,
 	}
 
 fetch_events:
+
+	if (!ep_events_available(ep))
+		ep_busy_loop(ep, timed_out);
+
 	spin_lock_irqsave(&ep->lock, flags);
 
 	if (!ep_events_available(ep)) {
 		/*
+		 * Busy poll timed out.  Drop NAPI ID for now, we can add
+		 * it back in when we have moved a socket with a valid NAPI
+		 * ID onto the ready list.
+		 */
+		ep_reset_busy_poll_napi_id(ep);
+
+		/*
 		 * We don't have any available event to return to the caller.
 		 * We need to sleep here, and we will be wake up by
 		 * ep_poll_callback() when events will become available.
@@ -1655,6 +1796,16 @@ fetch_events:
 			 * to TASK_INTERRUPTIBLE before doing the checks.
 			 */
 			set_current_state(TASK_INTERRUPTIBLE);
+			/*
+			 * Always short-circuit for fatal signals to allow
+			 * threads to make a timely exit without the chance of
+			 * finding more events available and fetching
+			 * repeatedly.
+			 */
+			if (fatal_signal_pending(current)) {
+				res = -EINTR;
+				break;
+			}
 			if (ep_events_available(ep) || timed_out)
 				break;
 			if (signal_pending(current)) {
@@ -1895,7 +2046,7 @@ SYSCALL_DEFINE4(epoll_ctl, int, epfd, int, op, int, fd,
 	 * so EPOLLEXCLUSIVE is not allowed for a EPOLL_CTL_MOD operation.
 	 * Also, we do not currently supported nested exclusive wakeups.
 	 */
-	if (epds.events & EPOLLEXCLUSIVE) {
+	if (ep_op_has_event(op) && (epds.events & EPOLLEXCLUSIVE)) {
 		if (op == EPOLL_CTL_MOD)
 			goto error_tgt_fput;
 		if (op == EPOLL_CTL_ADD && (is_file_epoll(tf.file) ||
diff --git a/fs/exec.c b/fs/exec.c
index e57946610733..62175cbcc801 100644
--- a/fs/exec.c
+++ b/fs/exec.c
@@ -32,6 +32,11 @@
 #include <linux/swap.h>
 #include <linux/string.h>
 #include <linux/init.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/numa_balancing.h>
+#include <linux/sched/task.h>
 #include <linux/pagemap.h>
 #include <linux/perf_event.h>
 #include <linux/highmem.h>
@@ -215,7 +220,24 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 
 	if (write) {
 		unsigned long size = bprm->vma->vm_end - bprm->vma->vm_start;
-		struct rlimit *rlim;
+		unsigned long ptr_size, limit;
+
+		/*
+		 * Since the stack will hold pointers to the strings, we
+		 * must account for them as well.
+		 *
+		 * The size calculation is the entire vma while each arg page is
+		 * built, so each time we get here it's calculating how far it
+		 * is currently (rather than each call being just the newly
+		 * added size from the arg page).  As a result, we need to
+		 * always add the entire size of the pointers, so that on the
+		 * last call to get_arg_page() we'll actually have the entire
+		 * correct size.
+		 */
+		ptr_size = (bprm->argc + bprm->envc) * sizeof(void *);
+		if (ptr_size > ULONG_MAX - size)
+			goto fail;
+		size += ptr_size;
 
 		acct_arg_size(bprm, size / PAGE_SIZE);
 
@@ -227,20 +249,24 @@ static struct page *get_arg_page(struct linux_binprm *bprm, unsigned long pos,
 			return page;
 
 		/*
-		 * Limit to 1/4-th the stack size for the argv+env strings.
+		 * Limit to 1/4 of the max stack size or 3/4 of _STK_LIM
+		 * (whichever is smaller) for the argv+env strings.
 		 * This ensures that:
 		 *  - the remaining binfmt code will not run out of stack space,
 		 *  - the program will have a reasonable amount of stack left
 		 *    to work from.
 		 */
-		rlim = current->signal->rlim;
-		if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur) / 4) {
-			put_page(page);
-			return NULL;
-		}
+		limit = _STK_LIM / 4 * 3;
+		limit = min(limit, rlimit(RLIMIT_STACK) / 4);
+		if (size > limit)
+			goto fail;
 	}
 
 	return page;
+
+fail:
+	put_page(page);
+	return NULL;
 }
 
 static void put_arg_page(struct page *page)
@@ -1088,7 +1114,7 @@ static int de_thread(struct task_struct *tsk)
 		struct task_struct *leader = tsk->group_leader;
 
 		for (;;) {
-			threadgroup_change_begin(tsk);
+			cgroup_threadgroup_change_begin(tsk);
 			write_lock_irq(&tasklist_lock);
 			/*
 			 * Do this under tasklist_lock to ensure that
@@ -1099,7 +1125,7 @@ static int de_thread(struct task_struct *tsk)
 				break;
 			__set_current_state(TASK_KILLABLE);
 			write_unlock_irq(&tasklist_lock);
-			threadgroup_change_end(tsk);
+			cgroup_threadgroup_change_end(tsk);
 			schedule();
 			if (unlikely(__fatal_signal_pending(tsk)))
 				goto killed;
@@ -1157,7 +1183,7 @@ static int de_thread(struct task_struct *tsk)
 		if (unlikely(leader->ptrace))
 			__wake_up_parent(leader, leader->parent);
 		write_unlock_irq(&tasklist_lock);
-		threadgroup_change_end(tsk);
+		cgroup_threadgroup_change_end(tsk);
 
 		release_task(leader);
 	}
@@ -1315,6 +1341,7 @@ void setup_new_exec(struct linux_binprm * bprm)
 	else
 		set_dumpable(current->mm, suid_dumpable);
 
+	arch_setup_new_exec();
 	perf_event_exec();
 	__set_task_comm(current, kbasename(bprm->filename), true);
 
@@ -1426,12 +1453,8 @@ static void check_unsafe_exec(struct linux_binprm *bprm)
 	struct task_struct *p = current, *t;
 	unsigned n_fs;
 
-	if (p->ptrace) {
-		if (ptracer_capable(p, current_user_ns()))
-			bprm->unsafe |= LSM_UNSAFE_PTRACE_CAP;
-		else
-			bprm->unsafe |= LSM_UNSAFE_PTRACE;
-	}
+	if (p->ptrace)
+		bprm->unsafe |= LSM_UNSAFE_PTRACE;
 
 	/*
 	 * This isn't strictly necessary, but it makes it harder for LSMs to
@@ -1479,7 +1502,7 @@ static void bprm_fill_uid(struct linux_binprm *bprm)
 	if (task_no_new_privs(current))
 		return;
 
-	inode = file_inode(bprm->file);
+	inode = bprm->file->f_path.dentry->d_inode;
 	mode = READ_ONCE(inode->i_mode);
 	if (!(mode & (S_ISUID|S_ISGID)))
 		return;
diff --git a/fs/exofs/dir.c b/fs/exofs/dir.c
index 42f9a0a0c4ca..98233a97b7b8 100644
--- a/fs/exofs/dir.c
+++ b/fs/exofs/dir.c
@@ -72,7 +72,7 @@ static int exofs_commit_chunk(struct page *page, loff_t pos, unsigned len)
 	set_page_dirty(page);
 
 	if (IS_DIRSYNC(dir))
-		err = write_one_page(page, 1);
+		err = write_one_page(page);
 	else
 		unlock_page(page);
 
@@ -405,8 +405,7 @@ int exofs_set_link(struct inode *dir, struct exofs_dir_entry *de,
 	int err;
 
 	lock_page(page);
-	err = exofs_write_begin(NULL, page->mapping, pos, len,
-				AOP_FLAG_UNINTERRUPTIBLE, &page, NULL);
+	err = exofs_write_begin(NULL, page->mapping, pos, len, 0, &page, NULL);
 	if (err)
 		EXOFS_ERR("exofs_set_link: exofs_write_begin FAILED => %d\n",
 			  err);
diff --git a/fs/exofs/exofs.h b/fs/exofs/exofs.h
index 2e86086bc940..5dc392404559 100644
--- a/fs/exofs/exofs.h
+++ b/fs/exofs/exofs.h
@@ -64,7 +64,6 @@ struct exofs_dev {
  * our extension to the in-memory superblock
  */
 struct exofs_sb_info {
-	struct backing_dev_info bdi;		/* register our bdi with VFS  */
 	struct exofs_sb_stats s_ess;		/* Written often, pre-allocate*/
 	int		s_timeout;		/* timeout for OSD operations */
 	uint64_t	s_nextid;		/* highest object ID used     */
diff --git a/fs/exofs/super.c b/fs/exofs/super.c
index 1076a4233b39..819624cfc8da 100644
--- a/fs/exofs/super.c
+++ b/fs/exofs/super.c
@@ -464,7 +464,6 @@ static void exofs_put_super(struct super_block *sb)
 			    sbi->one_comp.obj.partition);
 
 	exofs_sysfs_sb_del(sbi);
-	bdi_destroy(&sbi->bdi);
 	exofs_free_sbi(sbi);
 	sb->s_fs_info = NULL;
 }
@@ -809,8 +808,12 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
 	__sbi_read_stats(sbi);
 
 	/* set up operation vectors */
-	sbi->bdi.ra_pages = __ra_pages(&sbi->layout);
-	sb->s_bdi = &sbi->bdi;
+	ret = super_setup_bdi(sb);
+	if (ret) {
+		EXOFS_DBGMSG("Failed to super_setup_bdi\n");
+		goto free_sbi;
+	}
+	sb->s_bdi->ra_pages = __ra_pages(&sbi->layout);
 	sb->s_fs_info = sbi;
 	sb->s_op = &exofs_sops;
 	sb->s_export_op = &exofs_export_ops;
@@ -836,14 +839,6 @@ static int exofs_fill_super(struct super_block *sb, void *data, int silent)
 		goto free_sbi;
 	}
 
-	ret = bdi_setup_and_register(&sbi->bdi, "exofs");
-	if (ret) {
-		EXOFS_DBGMSG("Failed to bdi_setup_and_register\n");
-		dput(sb->s_root);
-		sb->s_root = NULL;
-		goto free_sbi;
-	}
-
 	exofs_sysfs_dbg_print();
 	_exofs_print_device("Mounting", opts->dev_name,
 			    ore_comp_dev(&sbi->oc, 0),
diff --git a/fs/exofs/sys.c b/fs/exofs/sys.c
index 5e6a2c0a1f0b..1f7d5e46cdda 100644
--- a/fs/exofs/sys.c
+++ b/fs/exofs/sys.c
@@ -122,7 +122,7 @@ void exofs_sysfs_dbg_print(void)
 	list_for_each_entry_safe(k_name, k_tmp, &exofs_kset->list, entry) {
 		printk(KERN_INFO "%s: name %s ref %d\n",
 			__func__, kobject_name(k_name),
-			(int)atomic_read(&k_name->kref.refcount));
+			(int)kref_read(&k_name->kref));
 	}
 #endif
 }
diff --git a/fs/exportfs/expfs.c b/fs/exportfs/expfs.c
index a4b531be9168..329a5d103846 100644
--- a/fs/exportfs/expfs.c
+++ b/fs/exportfs/expfs.c
@@ -15,6 +15,7 @@
 #include <linux/mount.h>
 #include <linux/namei.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 
 #define dprintk(fmt, args...) do{}while(0)
 
@@ -299,7 +300,8 @@ static int get_name(const struct path *path, char *name, struct dentry *child)
 	 * filesystem supports 64-bit inode numbers.  So we need to
 	 * actually call ->getattr, not just read i_ino:
 	 */
-	error = vfs_getattr_nosec(&child_path, &stat);
+	error = vfs_getattr_nosec(&child_path, &stat,
+				  STATX_INO, AT_STATX_SYNC_AS_STAT);
 	if (error)
 		return error;
 	buffer.ino = stat.ino;
diff --git a/fs/ext2/acl.c b/fs/ext2/acl.c
index 79dafa71effd..51f0aea70cb4 100644
--- a/fs/ext2/acl.c
+++ b/fs/ext2/acl.c
@@ -175,11 +175,8 @@ ext2_get_acl(struct inode *inode, int type)
 	return acl;
 }
 
-/*
- * inode->i_mutex: down
- */
-int
-ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+static int
+__ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	int name_index;
 	void *value = NULL;
@@ -189,13 +186,6 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	switch(type) {
 		case ACL_TYPE_ACCESS:
 			name_index = EXT2_XATTR_INDEX_POSIX_ACL_ACCESS;
-			if (acl) {
-				error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
-				if (error)
-					return error;
-				inode->i_ctime = current_time(inode);
-				mark_inode_dirty(inode);
-			}
 			break;
 
 		case ACL_TYPE_DEFAULT:
@@ -222,6 +212,31 @@ ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 }
 
 /*
+ * inode->i_mutex: down
+ */
+int
+ext2_set_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+	int error;
+	int update_mode = 0;
+	umode_t mode = inode->i_mode;
+
+	if (type == ACL_TYPE_ACCESS && acl) {
+		error = posix_acl_update_mode(inode, &mode, &acl);
+		if (error)
+			return error;
+		update_mode = 1;
+	}
+	error = __ext2_set_acl(inode, acl, type);
+	if (!error && update_mode) {
+		inode->i_mode = mode;
+		inode->i_ctime = current_time(inode);
+		mark_inode_dirty(inode);
+	}
+	return error;
+}
+
+/*
  * Initialize the ACLs of a new inode. Called from ext2_new_inode.
  *
  * dir->i_mutex: down
@@ -238,12 +253,12 @@ ext2_init_acl(struct inode *inode, struct inode *dir)
 		return error;
 
 	if (default_acl) {
-		error = ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+		error = __ext2_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
 		posix_acl_release(default_acl);
 	}
 	if (acl) {
 		if (!error)
-			error = ext2_set_acl(inode, acl, ACL_TYPE_ACCESS);
+			error = __ext2_set_acl(inode, acl, ACL_TYPE_ACCESS);
 		posix_acl_release(acl);
 	}
 	return error;
diff --git a/fs/ext2/balloc.c b/fs/ext2/balloc.c
index 4c40c0786e16..d0bdb74f0e15 100644
--- a/fs/ext2/balloc.c
+++ b/fs/ext2/balloc.c
@@ -15,6 +15,7 @@
 #include <linux/quotaops.h>
 #include <linux/slab.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/buffer_head.h>
 #include <linux/capability.h>
 
diff --git a/fs/ext2/dir.c b/fs/ext2/dir.c
index d9650c9508e4..e2709695b177 100644
--- a/fs/ext2/dir.c
+++ b/fs/ext2/dir.c
@@ -100,7 +100,7 @@ static int ext2_commit_chunk(struct page *page, loff_t pos, unsigned len)
 	}
 
 	if (IS_DIRSYNC(dir)) {
-		err = write_one_page(page, 1);
+		err = write_one_page(page);
 		if (!err)
 			err = sync_inode_metadata(dir, 1);
 	} else {
diff --git a/fs/ext2/ext2.h b/fs/ext2/ext2.h
index 37e2be784ac7..23ebb92484c6 100644
--- a/fs/ext2/ext2.h
+++ b/fs/ext2/ext2.h
@@ -113,7 +113,7 @@ struct ext2_sb_info {
 	 * of the mount options.
 	 */
 	spinlock_t s_lock;
-	struct mb_cache *s_mb_cache;
+	struct mb_cache *s_ea_block_cache;
 };
 
 static inline spinlock_t *
@@ -779,7 +779,6 @@ extern void ext2_evict_inode(struct inode *);
 extern int ext2_get_block(struct inode *, sector_t, struct buffer_head *, int);
 extern int ext2_setattr (struct dentry *, struct iattr *);
 extern void ext2_set_inode_flags(struct inode *inode);
-extern void ext2_get_inode_flags(struct ext2_inode_info *);
 extern int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
 		       u64 start, u64 len);
 
@@ -796,7 +795,8 @@ void ext2_error(struct super_block *, const char *, const char *, ...);
 extern __printf(3, 4)
 void ext2_msg(struct super_block *, const char *, const char *, ...);
 extern void ext2_update_dynamic_rev (struct super_block *sb);
-extern void ext2_write_super (struct super_block *);
+extern void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es,
+			    int wait);
 
 /*
  * Inodes and files operations
@@ -814,7 +814,7 @@ extern const struct file_operations ext2_file_operations;
 /* inode.c */
 extern const struct address_space_operations ext2_aops;
 extern const struct address_space_operations ext2_nobh_aops;
-extern struct iomap_ops ext2_iomap_ops;
+extern const struct iomap_ops ext2_iomap_ops;
 
 /* namei.c */
 extern const struct inode_operations ext2_dir_inode_operations;
diff --git a/fs/ext2/file.c b/fs/ext2/file.c
index b0f241528a30..d34d32bdc944 100644
--- a/fs/ext2/file.c
+++ b/fs/ext2/file.c
@@ -87,19 +87,19 @@ out_unlock:
  * The default page_lock and i_size verification done by non-DAX fault paths
  * is sufficient because ext2 doesn't support hole punching.
  */
-static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int ext2_dax_fault(struct vm_fault *vmf)
 {
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	int ret;
 
 	if (vmf->flags & FAULT_FLAG_WRITE) {
 		sb_start_pagefault(inode->i_sb);
-		file_update_time(vma->vm_file);
+		file_update_time(vmf->vma->vm_file);
 	}
 	down_read(&ei->dax_sem);
 
-	ret = dax_iomap_fault(vma, vmf, &ext2_iomap_ops);
+	ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &ext2_iomap_ops);
 
 	up_read(&ei->dax_sem);
 	if (vmf->flags & FAULT_FLAG_WRITE)
@@ -107,16 +107,15 @@ static int ext2_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 	return ret;
 }
 
-static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
-		struct vm_fault *vmf)
+static int ext2_dax_pfn_mkwrite(struct vm_fault *vmf)
 {
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct ext2_inode_info *ei = EXT2_I(inode);
 	loff_t size;
 	int ret;
 
 	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
+	file_update_time(vmf->vma->vm_file);
 	down_read(&ei->dax_sem);
 
 	/* check that the faulting page hasn't raced with truncate */
@@ -124,7 +123,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 	if (vmf->pgoff >= size)
 		ret = VM_FAULT_SIGBUS;
 	else
-		ret = dax_pfn_mkwrite(vma, vmf);
+		ret = dax_pfn_mkwrite(vmf);
 
 	up_read(&ei->dax_sem);
 	sb_end_pagefault(inode->i_sb);
@@ -134,7 +133,7 @@ static int ext2_dax_pfn_mkwrite(struct vm_area_struct *vma,
 static const struct vm_operations_struct ext2_dax_vm_ops = {
 	.fault		= ext2_dax_fault,
 	/*
-	 * .pmd_fault is not supported for DAX because allocation in ext2
+	 * .huge_fault is not supported for DAX because allocation in ext2
 	 * cannot be reliably aligned to huge page sizes and so pmd faults
 	 * will always fail and fail back to regular faults.
 	 */
@@ -175,15 +174,12 @@ int ext2_fsync(struct file *file, loff_t start, loff_t end, int datasync)
 {
 	int ret;
 	struct super_block *sb = file->f_mapping->host->i_sb;
-	struct address_space *mapping = sb->s_bdev->bd_inode->i_mapping;
 
 	ret = generic_file_fsync(file, start, end, datasync);
-	if (ret == -EIO || test_and_clear_bit(AS_EIO, &mapping->flags)) {
+	if (ret == -EIO)
 		/* We don't really know where the IO error happened... */
 		ext2_error(sb, __func__,
 			   "detected IO error when writing metadata buffers");
-		ret = -EIO;
-	}
 	return ret;
 }
 
diff --git a/fs/ext2/inode.c b/fs/ext2/inode.c
index f073bfca694b..30163d007b2f 100644
--- a/fs/ext2/inode.c
+++ b/fs/ext2/inode.c
@@ -659,6 +659,7 @@ static int ext2_get_blocks(struct inode *inode,
 				 */
 				err = -EAGAIN;
 				count = 0;
+				partial = chain + depth - 1;
 				break;
 			}
 			blk = le32_to_cpu(*(chain[depth-1].p + count));
@@ -799,6 +800,7 @@ int ext2_get_block(struct inode *inode, sector_t iblock,
 static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		unsigned flags, struct iomap *iomap)
 {
+	struct block_device *bdev;
 	unsigned int blkbits = inode->i_blkbits;
 	unsigned long first_block = offset >> blkbits;
 	unsigned long max_blocks = (length + (1 << blkbits) - 1) >> blkbits;
@@ -812,8 +814,13 @@ static int ext2_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 		return ret;
 
 	iomap->flags = 0;
-	iomap->bdev = inode->i_sb->s_bdev;
+	bdev = inode->i_sb->s_bdev;
+	iomap->bdev = bdev;
 	iomap->offset = (u64)first_block << blkbits;
+	if (blk_queue_dax(bdev->bd_queue))
+		iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
+	else
+		iomap->dax_dev = NULL;
 
 	if (ret == 0) {
 		iomap->type = IOMAP_HOLE;
@@ -835,6 +842,7 @@ static int
 ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 		ssize_t written, unsigned flags, struct iomap *iomap)
 {
+	fs_put_dax(iomap->dax_dev);
 	if (iomap->type == IOMAP_MAPPED &&
 	    written < length &&
 	    (flags & IOMAP_WRITE))
@@ -842,13 +850,13 @@ ext2_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 	return 0;
 }
 
-struct iomap_ops ext2_iomap_ops = {
+const struct iomap_ops ext2_iomap_ops = {
 	.iomap_begin		= ext2_iomap_begin,
 	.iomap_end		= ext2_iomap_end,
 };
 #else
 /* Define empty ops for !CONFIG_FS_DAX case to avoid ugly ifdefs */
-struct iomap_ops ext2_iomap_ops;
+const struct iomap_ops ext2_iomap_ops;
 #endif /* CONFIG_FS_DAX */
 
 int ext2_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
@@ -1384,25 +1392,6 @@ void ext2_set_inode_flags(struct inode *inode)
 		inode->i_flags |= S_DAX;
 }
 
-/* Propagate flags from i_flags to EXT2_I(inode)->i_flags */
-void ext2_get_inode_flags(struct ext2_inode_info *ei)
-{
-	unsigned int flags = ei->vfs_inode.i_flags;
-
-	ei->i_flags &= ~(EXT2_SYNC_FL|EXT2_APPEND_FL|
-			EXT2_IMMUTABLE_FL|EXT2_NOATIME_FL|EXT2_DIRSYNC_FL);
-	if (flags & S_SYNC)
-		ei->i_flags |= EXT2_SYNC_FL;
-	if (flags & S_APPEND)
-		ei->i_flags |= EXT2_APPEND_FL;
-	if (flags & S_IMMUTABLE)
-		ei->i_flags |= EXT2_IMMUTABLE_FL;
-	if (flags & S_NOATIME)
-		ei->i_flags |= EXT2_NOATIME_FL;
-	if (flags & S_DIRSYNC)
-		ei->i_flags |= EXT2_DIRSYNC_FL;
-}
-
 struct inode *ext2_iget (struct super_block *sb, unsigned long ino)
 {
 	struct ext2_inode_info *ei;
@@ -1563,7 +1552,6 @@ static int __ext2_write_inode(struct inode *inode, int do_sync)
 	if (ei->i_state & EXT2_STATE_NEW)
 		memset(raw_inode, 0, EXT2_SB(sb)->s_inode_size);
 
-	ext2_get_inode_flags(ei);
 	raw_inode->i_mode = cpu_to_le16(inode->i_mode);
 	if (!(test_opt(sb, NO_UID32))) {
 		raw_inode->i_uid_low = cpu_to_le16(low_16_bits(uid));
@@ -1615,7 +1603,7 @@ static int __ext2_write_inode(struct inode *inode, int do_sync)
 				EXT2_SET_RO_COMPAT_FEATURE(sb,
 					EXT2_FEATURE_RO_COMPAT_LARGE_FILE);
 				spin_unlock(&EXT2_SB(sb)->s_lock);
-				ext2_write_super(sb);
+				ext2_sync_super(sb, EXT2_SB(sb)->s_es, 1);
 			}
 		}
 	}
diff --git a/fs/ext2/ioctl.c b/fs/ext2/ioctl.c
index 191e02b28ce8..087f122cca42 100644
--- a/fs/ext2/ioctl.c
+++ b/fs/ext2/ioctl.c
@@ -29,7 +29,6 @@ long ext2_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 	switch (cmd) {
 	case EXT2_IOC_GETFLAGS:
-		ext2_get_inode_flags(ei);
 		flags = ei->i_flags & EXT2_FL_USER_VISIBLE;
 		return put_user(flags, (int __user *) arg);
 	case EXT2_IOC_SETFLAGS: {
diff --git a/fs/ext2/super.c b/fs/ext2/super.c
index 9e25a71fe1a2..7b1bc9059863 100644
--- a/fs/ext2/super.c
+++ b/fs/ext2/super.c
@@ -32,12 +32,12 @@
 #include <linux/log2.h>
 #include <linux/quotaops.h>
 #include <linux/uaccess.h>
+#include <linux/dax.h>
 #include "ext2.h"
 #include "xattr.h"
 #include "acl.h"
 
-static void ext2_sync_super(struct super_block *sb,
-			    struct ext2_super_block *es, int wait);
+static void ext2_write_super(struct super_block *sb);
 static int ext2_remount (struct super_block * sb, int * flags, char * data);
 static int ext2_statfs (struct dentry * dentry, struct kstatfs * buf);
 static int ext2_sync_fs(struct super_block *sb, int wait);
@@ -123,17 +123,33 @@ void ext2_update_dynamic_rev(struct super_block *sb)
 	 */
 }
 
+#ifdef CONFIG_QUOTA
+static int ext2_quota_off(struct super_block *sb, int type);
+
+static void ext2_quota_off_umount(struct super_block *sb)
+{
+	int type;
+
+	for (type = 0; type < MAXQUOTAS; type++)
+		ext2_quota_off(sb, type);
+}
+#else
+static inline void ext2_quota_off_umount(struct super_block *sb)
+{
+}
+#endif
+
 static void ext2_put_super (struct super_block * sb)
 {
 	int db_count;
 	int i;
 	struct ext2_sb_info *sbi = EXT2_SB(sb);
 
-	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
+	ext2_quota_off_umount(sb);
 
-	if (sbi->s_mb_cache) {
-		ext2_xattr_destroy_cache(sbi->s_mb_cache);
-		sbi->s_mb_cache = NULL;
+	if (sbi->s_ea_block_cache) {
+		ext2_xattr_destroy_cache(sbi->s_ea_block_cache);
+		sbi->s_ea_block_cache = NULL;
 	}
 	if (!(sb->s_flags & MS_RDONLY)) {
 		struct ext2_super_block *es = sbi->s_es;
@@ -314,10 +330,23 @@ static int ext2_show_options(struct seq_file *seq, struct dentry *root)
 #ifdef CONFIG_QUOTA
 static ssize_t ext2_quota_read(struct super_block *sb, int type, char *data, size_t len, loff_t off);
 static ssize_t ext2_quota_write(struct super_block *sb, int type, const char *data, size_t len, loff_t off);
+static int ext2_quota_on(struct super_block *sb, int type, int format_id,
+			 const struct path *path);
 static struct dquot **ext2_get_dquots(struct inode *inode)
 {
 	return EXT2_I(inode)->i_dquot;
 }
+
+static const struct quotactl_ops ext2_quotactl_ops = {
+	.quota_on	= ext2_quota_on,
+	.quota_off	= ext2_quota_off,
+	.quota_sync	= dquot_quota_sync,
+	.get_state	= dquot_get_state,
+	.set_info	= dquot_set_dqinfo,
+	.get_dqblk	= dquot_get_dqblk,
+	.set_dqblk	= dquot_set_dqblk,
+	.get_nextdqblk	= dquot_get_next_dqblk,
+};
 #endif
 
 static const struct super_operations ext2_sops = {
@@ -1102,9 +1131,9 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 #ifdef CONFIG_EXT2_FS_XATTR
-	sbi->s_mb_cache = ext2_xattr_create_cache();
-	if (!sbi->s_mb_cache) {
-		ext2_msg(sb, KERN_ERR, "Failed to create an mb_cache");
+	sbi->s_ea_block_cache = ext2_xattr_create_cache();
+	if (!sbi->s_ea_block_cache) {
+		ext2_msg(sb, KERN_ERR, "Failed to create ea_block_cache");
 		goto failed_mount3;
 	}
 #endif
@@ -1117,7 +1146,7 @@ static int ext2_fill_super(struct super_block *sb, void *data, int silent)
 
 #ifdef CONFIG_QUOTA
 	sb->dq_op = &dquot_operations;
-	sb->s_qcop = &dquot_quotactl_ops;
+	sb->s_qcop = &ext2_quotactl_ops;
 	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
 #endif
 
@@ -1153,8 +1182,8 @@ cantfind_ext2:
 			sb->s_id);
 	goto failed_mount;
 failed_mount3:
-	if (sbi->s_mb_cache)
-		ext2_xattr_destroy_cache(sbi->s_mb_cache);
+	if (sbi->s_ea_block_cache)
+		ext2_xattr_destroy_cache(sbi->s_ea_block_cache);
 	percpu_counter_destroy(&sbi->s_freeblocks_counter);
 	percpu_counter_destroy(&sbi->s_freeinodes_counter);
 	percpu_counter_destroy(&sbi->s_dirs_counter);
@@ -1194,8 +1223,8 @@ static void ext2_clear_super_error(struct super_block *sb)
 	}
 }
 
-static void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es,
-			    int wait)
+void ext2_sync_super(struct super_block *sb, struct ext2_super_block *es,
+		     int wait)
 {
 	ext2_clear_super_error(sb);
 	spin_lock(&EXT2_SB(sb)->s_lock);
@@ -1270,7 +1299,7 @@ static int ext2_unfreeze(struct super_block *sb)
 	return 0;
 }
 
-void ext2_write_super(struct super_block *sb)
+static void ext2_write_super(struct super_block *sb)
 {
 	if (!(sb->s_flags & MS_RDONLY))
 		ext2_sync_fs(sb, 1);
@@ -1548,6 +1577,51 @@ out:
 	return len - towrite;
 }
 
+static int ext2_quota_on(struct super_block *sb, int type, int format_id,
+			 const struct path *path)
+{
+	int err;
+	struct inode *inode;
+
+	err = dquot_quota_on(sb, type, format_id, path);
+	if (err)
+		return err;
+
+	inode = d_inode(path->dentry);
+	inode_lock(inode);
+	EXT2_I(inode)->i_flags |= EXT2_NOATIME_FL | EXT2_IMMUTABLE_FL;
+	inode_set_flags(inode, S_NOATIME | S_IMMUTABLE,
+			S_NOATIME | S_IMMUTABLE);
+	inode_unlock(inode);
+	mark_inode_dirty(inode);
+
+	return 0;
+}
+
+static int ext2_quota_off(struct super_block *sb, int type)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	int err;
+
+	if (!inode || !igrab(inode))
+		goto out;
+
+	err = dquot_quota_off(sb, type);
+	if (err)
+		goto out_put;
+
+	inode_lock(inode);
+	EXT2_I(inode)->i_flags &= ~(EXT2_NOATIME_FL | EXT2_IMMUTABLE_FL);
+	inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE);
+	inode_unlock(inode);
+	mark_inode_dirty(inode);
+out_put:
+	iput(inode);
+	return err;
+out:
+	return dquot_quota_off(sb, type);
+}
+
 #endif
 
 static struct file_system_type ext2_fs_type = {
diff --git a/fs/ext2/xattr.c b/fs/ext2/xattr.c
index fbdb8f171893..1b9b1268d418 100644
--- a/fs/ext2/xattr.c
+++ b/fs/ext2/xattr.c
@@ -121,6 +121,8 @@ const struct xattr_handler *ext2_xattr_handlers[] = {
 	NULL
 };
 
+#define EA_BLOCK_CACHE(inode)	(EXT2_SB(inode->i_sb)->s_ea_block_cache)
+
 static inline const struct xattr_handler *
 ext2_xattr_handler(int name_index)
 {
@@ -150,7 +152,7 @@ ext2_xattr_get(struct inode *inode, int name_index, const char *name,
 	size_t name_len, size;
 	char *end;
 	int error;
-	struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
+	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
 
 	ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
 		  name_index, name, buffer, (long)buffer_size);
@@ -195,7 +197,7 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_get",
 			goto found;
 		entry = next;
 	}
-	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
+	if (ext2_xattr_cache_insert(ea_block_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 	error = -ENODATA;
 	goto cleanup;
@@ -208,7 +210,7 @@ found:
 	    le16_to_cpu(entry->e_value_offs) + size > inode->i_sb->s_blocksize)
 		goto bad_block;
 
-	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
+	if (ext2_xattr_cache_insert(ea_block_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 	if (buffer) {
 		error = -ERANGE;
@@ -246,7 +248,7 @@ ext2_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 	char *end;
 	size_t rest = buffer_size;
 	int error;
-	struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
+	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
 
 	ea_idebug(inode, "buffer=%p, buffer_size=%ld",
 		  buffer, (long)buffer_size);
@@ -281,7 +283,7 @@ bad_block:	ext2_error(inode->i_sb, "ext2_xattr_list",
 			goto bad_block;
 		entry = next;
 	}
-	if (ext2_xattr_cache_insert(ext2_mb_cache, bh))
+	if (ext2_xattr_cache_insert(ea_block_cache, bh))
 		ea_idebug(inode, "cache insert failed");
 
 	/* list the attribute names */
@@ -493,8 +495,8 @@ bad_block:		ext2_error(sb, "ext2_xattr_set",
 			 * This must happen under buffer lock for
 			 * ext2_xattr_set2() to reliably detect modified block
 			 */
-			mb_cache_entry_delete_block(EXT2_SB(sb)->s_mb_cache,
-						    hash, bh->b_blocknr);
+			mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash,
+					      bh->b_blocknr);
 
 			/* keep the buffer locked while modifying it. */
 		} else {
@@ -627,7 +629,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *new_bh = NULL;
 	int error;
-	struct mb_cache *ext2_mb_cache = EXT2_SB(sb)->s_mb_cache;
+	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
 
 	if (header) {
 		new_bh = ext2_xattr_cache_find(inode, header);
@@ -655,7 +657,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			   don't need to change the reference count. */
 			new_bh = old_bh;
 			get_bh(new_bh);
-			ext2_xattr_cache_insert(ext2_mb_cache, new_bh);
+			ext2_xattr_cache_insert(ea_block_cache, new_bh);
 		} else {
 			/* We need to allocate a new block */
 			ext2_fsblk_t goal = ext2_group_first_block_no(sb,
@@ -676,7 +678,7 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			memcpy(new_bh->b_data, header, new_bh->b_size);
 			set_buffer_uptodate(new_bh);
 			unlock_buffer(new_bh);
-			ext2_xattr_cache_insert(ext2_mb_cache, new_bh);
+			ext2_xattr_cache_insert(ea_block_cache, new_bh);
 			
 			ext2_xattr_update_super_block(sb);
 		}
@@ -721,8 +723,8 @@ ext2_xattr_set2(struct inode *inode, struct buffer_head *old_bh,
 			 * This must happen under buffer lock for
 			 * ext2_xattr_set2() to reliably detect freed block
 			 */
-			mb_cache_entry_delete_block(ext2_mb_cache,
-						    hash, old_bh->b_blocknr);
+			mb_cache_entry_delete(ea_block_cache, hash,
+					      old_bh->b_blocknr);
 			/* Free the old block. */
 			ea_bdebug(old_bh, "freeing");
 			ext2_free_blocks(inode, old_bh->b_blocknr, 1);
@@ -795,8 +797,8 @@ ext2_xattr_delete_inode(struct inode *inode)
 		 * This must happen under buffer lock for ext2_xattr_set2() to
 		 * reliably detect freed block
 		 */
-		mb_cache_entry_delete_block(EXT2_SB(inode->i_sb)->s_mb_cache,
-					    hash, bh->b_blocknr);
+		mb_cache_entry_delete(EA_BLOCK_CACHE(inode), hash,
+				      bh->b_blocknr);
 		ext2_free_blocks(inode, EXT2_I(inode)->i_file_acl, 1);
 		get_bh(bh);
 		bforget(bh);
@@ -897,21 +899,21 @@ ext2_xattr_cache_find(struct inode *inode, struct ext2_xattr_header *header)
 {
 	__u32 hash = le32_to_cpu(header->h_hash);
 	struct mb_cache_entry *ce;
-	struct mb_cache *ext2_mb_cache = EXT2_SB(inode->i_sb)->s_mb_cache;
+	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
 
 	if (!header->h_hash)
 		return NULL;  /* never share */
 	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
 again:
-	ce = mb_cache_entry_find_first(ext2_mb_cache, hash);
+	ce = mb_cache_entry_find_first(ea_block_cache, hash);
 	while (ce) {
 		struct buffer_head *bh;
 
-		bh = sb_bread(inode->i_sb, ce->e_block);
+		bh = sb_bread(inode->i_sb, ce->e_value);
 		if (!bh) {
 			ext2_error(inode->i_sb, "ext2_xattr_cache_find",
 				"inode %ld: block %ld read error",
-				inode->i_ino, (unsigned long) ce->e_block);
+				inode->i_ino, (unsigned long) ce->e_value);
 		} else {
 			lock_buffer(bh);
 			/*
@@ -924,27 +926,27 @@ again:
 			 * entry is still hashed is reliable.
 			 */
 			if (hlist_bl_unhashed(&ce->e_hash_list)) {
-				mb_cache_entry_put(ext2_mb_cache, ce);
+				mb_cache_entry_put(ea_block_cache, ce);
 				unlock_buffer(bh);
 				brelse(bh);
 				goto again;
 			} else if (le32_to_cpu(HDR(bh)->h_refcount) >
 				   EXT2_XATTR_REFCOUNT_MAX) {
 				ea_idebug(inode, "block %ld refcount %d>%d",
-					  (unsigned long) ce->e_block,
+					  (unsigned long) ce->e_value,
 					  le32_to_cpu(HDR(bh)->h_refcount),
 					  EXT2_XATTR_REFCOUNT_MAX);
 			} else if (!ext2_xattr_cmp(header, HDR(bh))) {
 				ea_bdebug(bh, "b_count=%d",
 					  atomic_read(&(bh->b_count)));
-				mb_cache_entry_touch(ext2_mb_cache, ce);
-				mb_cache_entry_put(ext2_mb_cache, ce);
+				mb_cache_entry_touch(ea_block_cache, ce);
+				mb_cache_entry_put(ea_block_cache, ce);
 				return bh;
 			}
 			unlock_buffer(bh);
 			brelse(bh);
 		}
-		ce = mb_cache_entry_find_next(ext2_mb_cache, ce);
+		ce = mb_cache_entry_find_next(ea_block_cache, ce);
 	}
 	return NULL;
 }
diff --git a/fs/ext4/Makefile b/fs/ext4/Makefile
index 354103f3490c..d9beca1653c5 100644
--- a/fs/ext4/Makefile
+++ b/fs/ext4/Makefile
@@ -4,11 +4,11 @@
 
 obj-$(CONFIG_EXT4_FS) += ext4.o
 
-ext4-y	:= balloc.o bitmap.o dir.o file.o fsync.o ialloc.o inode.o page-io.o \
-		ioctl.o namei.o super.o symlink.o hash.o resize.o extents.o \
-		ext4_jbd2.o migrate.o mballoc.o block_validity.o move_extent.o \
-		mmp.o indirect.o extents_status.o xattr.o xattr_user.o \
-		xattr_trusted.o inline.o readpage.o sysfs.o
+ext4-y	:= balloc.o bitmap.o block_validity.o dir.o ext4_jbd2.o extents.o \
+		extents_status.o file.o fsmap.o fsync.o hash.o ialloc.o \
+		indirect.o inline.o inode.o ioctl.o mballoc.o migrate.o \
+		mmp.o move_extent.o namei.o page-io.o readpage.o resize.o \
+		super.o symlink.o sysfs.o xattr.o xattr_trusted.o xattr_user.o
 
 ext4-$(CONFIG_EXT4_FS_POSIX_ACL)	+= acl.o
 ext4-$(CONFIG_EXT4_FS_SECURITY)		+= xattr_security.o
diff --git a/fs/ext4/acl.c b/fs/ext4/acl.c
index fd389935ecd1..09441ae07a5b 100644
--- a/fs/ext4/acl.c
+++ b/fs/ext4/acl.c
@@ -4,6 +4,7 @@
  * Copyright (C) 2001-2003 Andreas Gruenbacher, <agruen@suse.de>
  */
 
+#include <linux/quotaops.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
 #include "xattr.h"
@@ -182,7 +183,7 @@ ext4_get_acl(struct inode *inode, int type)
  */
 static int
 __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
-	     struct posix_acl *acl)
+	     struct posix_acl *acl, int xattr_flags)
 {
 	int name_index;
 	void *value = NULL;
@@ -217,7 +218,7 @@ __ext4_set_acl(handle_t *handle, struct inode *inode, int type,
 	}
 
 	error = ext4_xattr_set_handle(handle, inode, name_index, "",
-				      value, size, 0);
+				      value, size, xattr_flags);
 
 	kfree(value);
 	if (!error)
@@ -230,15 +231,23 @@ int
 ext4_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	handle_t *handle;
-	int error, retries = 0;
+	int error, credits, retries = 0;
+	size_t acl_size = acl ? ext4_acl_size(acl->a_count) : 0;
 
+	error = dquot_initialize(inode);
+	if (error)
+		return error;
 retry:
-	handle = ext4_journal_start(inode, EXT4_HT_XATTR,
-				    ext4_jbd2_credits_xattr(inode));
+	error = ext4_xattr_set_credits(inode, acl_size, false /* is_create */,
+				       &credits);
+	if (error)
+		return error;
+
+	handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
-	error = __ext4_set_acl(handle, inode, type, acl);
+	error = __ext4_set_acl(handle, inode, type, acl, 0 /* xattr_flags */);
 	ext4_journal_stop(handle);
 	if (error == -ENOSPC && ext4_should_retry_alloc(inode->i_sb, &retries))
 		goto retry;
@@ -263,13 +272,13 @@ ext4_init_acl(handle_t *handle, struct inode *inode, struct inode *dir)
 
 	if (default_acl) {
 		error = __ext4_set_acl(handle, inode, ACL_TYPE_DEFAULT,
-				       default_acl);
+				       default_acl, XATTR_CREATE);
 		posix_acl_release(default_acl);
 	}
 	if (acl) {
 		if (!error)
 			error = __ext4_set_acl(handle, inode, ACL_TYPE_ACCESS,
-					       acl);
+					       acl, XATTR_CREATE);
 		posix_acl_release(acl);
 	}
 	return error;
diff --git a/fs/ext4/ext4.h b/fs/ext4/ext4.h
index 2163c1e69f2a..9ebde0cd632e 100644
--- a/fs/ext4/ext4.h
+++ b/fs/ext4/ext4.h
@@ -28,11 +28,16 @@
 #include <linux/timer.h>
 #include <linux/version.h>
 #include <linux/wait.h>
+#include <linux/sched/signal.h>
 #include <linux/blockgroup_lock.h>
 #include <linux/percpu_counter.h>
 #include <linux/ratelimit.h>
 #include <crypto/hash.h>
-#include <linux/fscrypto.h>
+#ifdef CONFIG_EXT4_FS_ENCRYPTION
+#include <linux/fscrypt_supp.h>
+#else
+#include <linux/fscrypt_notsupp.h>
+#endif
 #include <linux/falloc.h>
 #include <linux/percpu-rwsem.h>
 #ifdef __KERNEL__
@@ -679,6 +684,16 @@ struct fsxattr {
 #define EXT4_IOC_FSGETXATTR		FS_IOC_FSGETXATTR
 #define EXT4_IOC_FSSETXATTR		FS_IOC_FSSETXATTR
 
+#define EXT4_IOC_SHUTDOWN _IOR ('X', 125, __u32)
+
+/*
+ * Flags for going down operation
+ */
+#define EXT4_GOING_FLAGS_DEFAULT		0x0	/* going down */
+#define EXT4_GOING_FLAGS_LOGFLUSH		0x1	/* flush log but not data */
+#define EXT4_GOING_FLAGS_NOLOGFLUSH		0x2	/* don't flush log nor data */
+
+
 #if defined(__KERNEL__) && defined(CONFIG_COMPAT)
 /*
  * ioctl commands in 32 bit emulation
@@ -1099,6 +1114,7 @@ struct ext4_inode_info {
 /*
  * Mount flags set via mount options or defaults
  */
+#define EXT4_MOUNT_NO_MBCACHE		0x00001 /* Do not use mbcache */
 #define EXT4_MOUNT_GRPID		0x00004	/* Create files with directory's group */
 #define EXT4_MOUNT_DEBUG		0x00008	/* Some debugging messages */
 #define EXT4_MOUNT_ERRORS_CONT		0x00010	/* Continue on errors */
@@ -1343,11 +1359,6 @@ struct ext4_super_block {
 /* Number of quota types we support */
 #define EXT4_MAXQUOTAS 3
 
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-#define EXT4_KEY_DESC_PREFIX "ext4:"
-#define EXT4_KEY_DESC_PREFIX_SIZE 5
-#endif
-
 /*
  * fourth extended-fs super-block data in memory
  */
@@ -1404,8 +1415,7 @@ struct ext4_sb_info {
 	struct journal_s *s_journal;
 	struct list_head s_orphan;
 	struct mutex s_orphan_lock;
-	unsigned long s_resize_flags;		/* Flags indicating if there
-						   is a resizer */
+	unsigned long s_ext4_flags;		/* Ext4 superblock flags */
 	unsigned long s_commit_interval;
 	u32 s_max_batch_time;
 	u32 s_min_batch_time;
@@ -1435,6 +1445,8 @@ struct ext4_sb_info {
 	unsigned int *s_mb_maxs;
 	unsigned int s_group_info_size;
 	unsigned int s_mb_free_pending;
+	struct list_head s_freed_data_list;	/* List of blocks to be freed
+						   after commit completed */
 
 	/* tunables */
 	unsigned long s_stripe;
@@ -1507,7 +1519,8 @@ struct ext4_sb_info {
 	struct list_head s_es_list;	/* List of inodes with reclaimable extents */
 	long s_es_nr_inode;
 	struct ext4_es_stats s_es_stats;
-	struct mb_cache *s_mb_cache;
+	struct mb_cache *s_ea_block_cache;
+	struct mb_cache *s_ea_inode_cache;
 	spinlock_t s_es_lock ____cacheline_aligned_in_smp;
 
 	/* Ratelimit ext4 messages. */
@@ -1517,12 +1530,6 @@ struct ext4_sb_info {
 
 	/* Barrier between changing inodes' journal flags and writepages ops. */
 	struct percpu_rw_semaphore s_journal_flag_rwsem;
-
-	/* Encryption support */
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	u8 key_prefix[EXT4_KEY_DESC_PREFIX_SIZE];
-	u8 key_prefix_size;
-#endif
 };
 
 static inline struct ext4_sb_info *EXT4_SB(struct super_block *sb)
@@ -1794,10 +1801,12 @@ EXT4_FEATURE_INCOMPAT_FUNCS(encrypt,		ENCRYPT)
 					 EXT4_FEATURE_INCOMPAT_EXTENTS| \
 					 EXT4_FEATURE_INCOMPAT_64BIT| \
 					 EXT4_FEATURE_INCOMPAT_FLEX_BG| \
+					 EXT4_FEATURE_INCOMPAT_EA_INODE| \
 					 EXT4_FEATURE_INCOMPAT_MMP | \
 					 EXT4_FEATURE_INCOMPAT_INLINE_DATA | \
 					 EXT4_FEATURE_INCOMPAT_ENCRYPT | \
-					 EXT4_FEATURE_INCOMPAT_CSUM_SEED)
+					 EXT4_FEATURE_INCOMPAT_CSUM_SEED | \
+					 EXT4_FEATURE_INCOMPAT_LARGEDIR)
 #define EXT4_FEATURE_RO_COMPAT_SUPP	(EXT4_FEATURE_RO_COMPAT_SPARSE_SUPER| \
 					 EXT4_FEATURE_RO_COMPAT_LARGE_FILE| \
 					 EXT4_FEATURE_RO_COMPAT_GDT_CSUM| \
@@ -1845,6 +1854,18 @@ static inline bool ext4_has_incompat_features(struct super_block *sb)
 }
 
 /*
+ * Superblock flags
+ */
+#define EXT4_FLAGS_RESIZING	0
+#define EXT4_FLAGS_SHUTDOWN	1
+
+static inline int ext4_forced_shutdown(struct ext4_sb_info *sbi)
+{
+	return test_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+}
+
+
+/*
  * Default values for user and/or group using reserved blocks
  */
 #define	EXT4_DEF_RESUID		0
@@ -2083,6 +2104,12 @@ static inline struct ext4_inode *ext4_raw_inode(struct ext4_iloc *iloc)
 	return (struct ext4_inode *) (iloc->bh->b_data + iloc->offset);
 }
 
+static inline bool ext4_is_quota_file(struct inode *inode)
+{
+	return IS_NOQUOTA(inode) &&
+	       !(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL);
+}
+
 /*
  * This structure is stuffed into the struct file's private_data field
  * for directories.  It is where we put information so that we can do
@@ -2111,6 +2138,16 @@ ext4_group_first_block_no(struct super_block *sb, ext4_group_t group_no)
  */
 #define ERR_BAD_DX_DIR	(-(MAX_ERRNO - 1))
 
+/* htree levels for ext4 */
+#define	EXT4_HTREE_LEVEL_COMPAT	2
+#define	EXT4_HTREE_LEVEL	3
+
+static inline int ext4_dir_htree_level(struct super_block *sb)
+{
+	return ext4_has_feature_largedir(sb) ?
+		EXT4_HTREE_LEVEL : EXT4_HTREE_LEVEL_COMPAT;
+}
+
 /*
  * Timeout and state flag for lazy initialization inode thread.
  */
@@ -2320,28 +2357,6 @@ static inline int ext4_fname_setup_filename(struct inode *dir,
 }
 static inline void ext4_fname_free_filename(struct ext4_filename *fname) { }
 
-#define fscrypt_set_d_op(i)
-#define fscrypt_get_ctx			fscrypt_notsupp_get_ctx
-#define fscrypt_release_ctx		fscrypt_notsupp_release_ctx
-#define fscrypt_encrypt_page		fscrypt_notsupp_encrypt_page
-#define fscrypt_decrypt_page		fscrypt_notsupp_decrypt_page
-#define fscrypt_decrypt_bio_pages	fscrypt_notsupp_decrypt_bio_pages
-#define fscrypt_pullback_bio_page	fscrypt_notsupp_pullback_bio_page
-#define fscrypt_restore_control_page	fscrypt_notsupp_restore_control_page
-#define fscrypt_zeroout_range		fscrypt_notsupp_zeroout_range
-#define fscrypt_ioctl_set_policy	fscrypt_notsupp_ioctl_set_policy
-#define fscrypt_ioctl_get_policy	fscrypt_notsupp_ioctl_get_policy
-#define fscrypt_has_permitted_context	fscrypt_notsupp_has_permitted_context
-#define fscrypt_inherit_context		fscrypt_notsupp_inherit_context
-#define fscrypt_get_encryption_info	fscrypt_notsupp_get_encryption_info
-#define fscrypt_put_encryption_info	fscrypt_notsupp_put_encryption_info
-#define fscrypt_setup_filename		fscrypt_notsupp_setup_filename
-#define fscrypt_free_filename		fscrypt_notsupp_free_filename
-#define fscrypt_fname_encrypted_size	fscrypt_notsupp_fname_encrypted_size
-#define fscrypt_fname_alloc_buffer	fscrypt_notsupp_fname_alloc_buffer
-#define fscrypt_fname_free_buffer	fscrypt_notsupp_fname_free_buffer
-#define fscrypt_fname_disk_to_usr	fscrypt_notsupp_fname_disk_to_usr
-#define fscrypt_fname_usr_to_disk	fscrypt_notsupp_fname_usr_to_disk
 #endif
 
 /* dir.c */
@@ -2363,17 +2378,16 @@ extern int ext4_find_dest_de(struct inode *dir, struct inode *inode,
 			     void *buf, int buf_size,
 			     struct ext4_filename *fname,
 			     struct ext4_dir_entry_2 **dest_de);
-int ext4_insert_dentry(struct inode *dir,
-		       struct inode *inode,
-		       struct ext4_dir_entry_2 *de,
-		       int buf_size,
-		       struct ext4_filename *fname);
+void ext4_insert_dentry(struct inode *inode,
+			struct ext4_dir_entry_2 *de,
+			int buf_size,
+			struct ext4_filename *fname);
 static inline void ext4_update_dx_flag(struct inode *inode)
 {
 	if (!ext4_has_feature_dir_index(inode->i_sb))
 		ext4_clear_inode_flag(inode, EXT4_INODE_INDEX);
 }
-static unsigned char ext4_filetype_table[] = {
+static const unsigned char ext4_filetype_table[] = {
 	DT_UNKNOWN, DT_REG, DT_DIR, DT_CHR, DT_BLK, DT_FIFO, DT_SOCK, DT_LNK
 };
 
@@ -2397,16 +2411,17 @@ extern int ext4fs_dirhash(const char *name, int len, struct
 /* ialloc.c */
 extern struct inode *__ext4_new_inode(handle_t *, struct inode *, umode_t,
 				      const struct qstr *qstr, __u32 goal,
-				      uid_t *owner, int handle_type,
-				      unsigned int line_no, int nblocks);
+				      uid_t *owner, __u32 i_flags,
+				      int handle_type, unsigned int line_no,
+				      int nblocks);
 
-#define ext4_new_inode(handle, dir, mode, qstr, goal, owner) \
+#define ext4_new_inode(handle, dir, mode, qstr, goal, owner, i_flags) \
 	__ext4_new_inode((handle), (dir), (mode), (qstr), (goal), (owner), \
-			 0, 0, 0)
+			 i_flags, 0, 0, 0)
 #define ext4_new_inode_start_handle(dir, mode, qstr, goal, owner, \
 				    type, nblocks)		    \
 	__ext4_new_inode(NULL, (dir), (mode), (qstr), (goal), (owner), \
-			 (type), __LINE__, (nblocks))
+			 0, (type), __LINE__, (nblocks))
 
 
 extern void ext4_free_inode(handle_t *, struct inode *);
@@ -2441,6 +2456,7 @@ extern int ext4_mb_add_groupinfo(struct super_block *sb,
 extern int ext4_group_add_blocks(handle_t *handle, struct super_block *sb,
 				ext4_fsblk_t block, unsigned long count);
 extern int ext4_trim_fs(struct super_block *, struct fstrim_range *);
+extern void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid);
 
 /* inode.c */
 int ext4_inode_is_fast_symlink(struct inode *inode);
@@ -2470,10 +2486,10 @@ extern struct inode *ext4_iget(struct super_block *, unsigned long);
 extern struct inode *ext4_iget_normal(struct super_block *, unsigned long);
 extern int  ext4_write_inode(struct inode *, struct writeback_control *);
 extern int  ext4_setattr(struct dentry *, struct iattr *);
-extern int  ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
-				struct kstat *stat);
+extern int  ext4_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern void ext4_evict_inode(struct inode *);
 extern void ext4_clear_inode(struct inode *);
+extern int  ext4_file_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int  ext4_sync_inode(handle_t *, struct inode *);
 extern void ext4_dirty_inode(struct inode *, int);
 extern int ext4_change_inode_journal_flag(struct inode *, int);
@@ -2484,15 +2500,14 @@ extern int ext4_truncate(struct inode *);
 extern int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length);
 extern int ext4_truncate_restart_trans(handle_t *, struct inode *, int nblocks);
 extern void ext4_set_inode_flags(struct inode *);
-extern void ext4_get_inode_flags(struct ext4_inode_info *);
 extern int ext4_alloc_da_blocks(struct inode *inode);
 extern void ext4_set_aops(struct inode *inode);
 extern int ext4_writepage_trans_blocks(struct inode *);
 extern int ext4_chunk_trans_blocks(struct inode *, int nrblocks);
 extern int ext4_zero_partial_blocks(handle_t *handle, struct inode *inode,
 			     loff_t lstart, loff_t lend);
-extern int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf);
-extern int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf);
+extern int ext4_page_mkwrite(struct vm_fault *vmf);
+extern int ext4_filemap_fault(struct vm_fault *vmf);
 extern qsize_t *ext4_get_reserved_space(struct inode *inode);
 extern int ext4_get_projid(struct inode *inode, kprojid_t *projid);
 extern void ext4_da_update_reserve_space(struct inode *inode,
@@ -2532,7 +2547,6 @@ extern int ext4_search_dir(struct buffer_head *bh,
 			   int buf_size,
 			   struct inode *dir,
 			   struct ext4_filename *fname,
-			   const struct qstr *d_name,
 			   unsigned int offset,
 			   struct ext4_dir_entry_2 **res_dir);
 extern int ext4_generic_delete_entry(handle_t *handle,
@@ -2714,19 +2728,20 @@ extern void ext4_group_desc_csum_set(struct super_block *sb, __u32 group,
 extern int ext4_register_li_request(struct super_block *sb,
 				    ext4_group_t first_not_zeroed);
 
-static inline int ext4_has_group_desc_csum(struct super_block *sb)
-{
-	return ext4_has_feature_gdt_csum(sb) ||
-	       EXT4_SB(sb)->s_chksum_driver != NULL;
-}
-
 static inline int ext4_has_metadata_csum(struct super_block *sb)
 {
 	WARN_ON_ONCE(ext4_has_feature_metadata_csum(sb) &&
 		     !EXT4_SB(sb)->s_chksum_driver);
 
-	return (EXT4_SB(sb)->s_chksum_driver != NULL);
+	return ext4_has_feature_metadata_csum(sb) &&
+	       (EXT4_SB(sb)->s_chksum_driver != NULL);
 }
+
+static inline int ext4_has_group_desc_csum(struct super_block *sb)
+{
+	return ext4_has_feature_gdt_csum(sb) || ext4_has_metadata_csum(sb);
+}
+
 static inline ext4_fsblk_t ext4_blocks_count(struct ext4_super_block *es)
 {
 	return ((ext4_fsblk_t)le32_to_cpu(es->s_blocks_count_hi) << 32) |
@@ -2766,13 +2781,15 @@ static inline void ext4_r_blocks_count_set(struct ext4_super_block *es,
 	es->s_r_blocks_count_hi = cpu_to_le32(blk >> 32);
 }
 
-static inline loff_t ext4_isize(struct ext4_inode *raw_inode)
+static inline loff_t ext4_isize(struct super_block *sb,
+				struct ext4_inode *raw_inode)
 {
-	if (S_ISREG(le16_to_cpu(raw_inode->i_mode)))
+	if (ext4_has_feature_largedir(sb) ||
+	    S_ISREG(le16_to_cpu(raw_inode->i_mode)))
 		return ((loff_t)le32_to_cpu(raw_inode->i_size_high) << 32) |
 			le32_to_cpu(raw_inode->i_size_lo);
-	else
-		return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
+
+	return (loff_t) le32_to_cpu(raw_inode->i_size_lo);
 }
 
 static inline void ext4_isize_set(struct ext4_inode *raw_inode, loff_t i_size)
@@ -3016,7 +3033,6 @@ extern int htree_inlinedir_to_tree(struct file *dir_file,
 				   int *has_inline_data);
 extern struct buffer_head *ext4_find_inline_entry(struct inode *dir,
 					struct ext4_filename *fname,
-					const struct qstr *d_name,
 					struct ext4_dir_entry_2 **res_dir,
 					int *has_inline_data);
 extern int ext4_delete_inline_entry(handle_t *handle,
@@ -3034,7 +3050,7 @@ extern int ext4_inline_data_fiemap(struct inode *inode,
 extern int ext4_try_to_evict_inline_data(handle_t *handle,
 					 struct inode *inode,
 					 int needed);
-extern void ext4_inline_data_truncate(struct inode *inode, int *has_inline);
+extern int ext4_inline_data_truncate(struct inode *inode, int *has_inline);
 
 extern int ext4_convert_inline_data(struct inode *inode);
 
@@ -3058,7 +3074,7 @@ extern int ext4_handle_dirty_dirent_node(handle_t *handle,
 					 struct inode *inode,
 					 struct buffer_head *bh);
 #define S_SHIFT 12
-static unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = {
+static const unsigned char ext4_type_by_mode[S_IFMT >> S_SHIFT] = {
 	[S_IFREG >> S_SHIFT]	= EXT4_FT_REG_FILE,
 	[S_IFDIR >> S_SHIFT]	= EXT4_FT_DIR,
 	[S_IFCHR >> S_SHIFT]	= EXT4_FT_CHRDEV,
@@ -3228,7 +3244,6 @@ static inline void ext4_inode_resume_unlocked_dio(struct inode *inode)
 					    EXT4_WQ_HASH_SZ])
 extern wait_queue_head_t ext4__ioend_wq[EXT4_WQ_HASH_SZ];
 
-#define EXT4_RESIZING	0
 extern int ext4_resize_begin(struct super_block *sb);
 extern void ext4_resize_end(struct super_block *sb);
 
@@ -3253,7 +3268,7 @@ static inline void ext4_clear_io_unwritten_flag(ext4_io_end_t *io_end)
 	}
 }
 
-extern struct iomap_ops ext4_iomap_ops;
+extern const struct iomap_ops ext4_iomap_ops;
 
 #endif	/* __KERNEL__ */
 
diff --git a/fs/ext4/ext4_jbd2.c b/fs/ext4/ext4_jbd2.c
index e770c1ee4613..dd106b1d5d89 100644
--- a/fs/ext4/ext4_jbd2.c
+++ b/fs/ext4/ext4_jbd2.c
@@ -43,6 +43,10 @@ static int ext4_journal_check_start(struct super_block *sb)
 	journal_t *journal;
 
 	might_sleep();
+
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return -EIO;
+
 	if (sb->s_flags & MS_RDONLY)
 		return -EROFS;
 	WARN_ON(sb->s_writers.frozen == SB_FREEZE_COMPLETE);
@@ -161,6 +165,13 @@ int __ext4_journal_get_write_access(const char *where, unsigned int line,
 	might_sleep();
 
 	if (ext4_handle_valid(handle)) {
+		struct super_block *sb;
+
+		sb = handle->h_transaction->t_journal->j_private;
+		if (unlikely(ext4_forced_shutdown(EXT4_SB(sb)))) {
+			jbd2_journal_abort_handle(handle);
+			return -EIO;
+		}
 		err = jbd2_journal_get_write_access(handle, bh);
 		if (err)
 			ext4_journal_abort_handle(where, line, __func__, bh,
diff --git a/fs/ext4/ext4_jbd2.h b/fs/ext4/ext4_jbd2.h
index f97611171023..dabad1bc8617 100644
--- a/fs/ext4/ext4_jbd2.h
+++ b/fs/ext4/ext4_jbd2.h
@@ -77,7 +77,14 @@
 
 #define EXT4_RESERVE_TRANS_BLOCKS	12U
 
-#define EXT4_INDEX_EXTRA_TRANS_BLOCKS	8
+/*
+ * Number of credits needed if we need to insert an entry into a
+ * directory.  For each new index block, we need 4 blocks (old index
+ * block, new index block, bitmap block, bg summary).  For normal
+ * htree directories there are 2 levels; if the largedir feature
+ * enabled it's 3 levels.
+ */
+#define EXT4_INDEX_EXTRA_TRANS_BLOCKS	12U
 
 #ifdef CONFIG_QUOTA
 /* Amount of blocks needed for quota update - we know that the structure was
@@ -104,20 +111,6 @@
 #define EXT4_MAXQUOTAS_INIT_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_INIT_BLOCKS(sb))
 #define EXT4_MAXQUOTAS_DEL_BLOCKS(sb) (EXT4_MAXQUOTAS*EXT4_QUOTA_DEL_BLOCKS(sb))
 
-static inline int ext4_jbd2_credits_xattr(struct inode *inode)
-{
-	int credits = EXT4_DATA_TRANS_BLOCKS(inode->i_sb);
-
-	/*
-	 * In case of inline data, we may push out the data to a block,
-	 * so we need to reserve credits for this eventuality
-	 */
-	if (ext4_has_inline_data(inode))
-		credits += ext4_writepage_trans_blocks(inode) + 1;
-	return credits;
-}
-
-
 /*
  * Ext4 handle operation types -- for logging purposes
  */
diff --git a/fs/ext4/extents.c b/fs/ext4/extents.c
index 3e295d3350a9..e0a8425ff74d 100644
--- a/fs/ext4/extents.c
+++ b/fs/ext4/extents.c
@@ -2488,7 +2488,8 @@ int ext4_ext_index_trans_blocks(struct inode *inode, int extents)
 
 static inline int get_default_free_blocks_flags(struct inode *inode)
 {
-	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) ||
+	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE))
 		return EXT4_FREE_BLOCKS_METADATA | EXT4_FREE_BLOCKS_FORGET;
 	else if (ext4_should_journal_data(inode))
 		return EXT4_FREE_BLOCKS_FORGET;
@@ -3413,13 +3414,13 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	struct ext4_sb_info *sbi;
 	struct ext4_extent_header *eh;
 	struct ext4_map_blocks split_map;
-	struct ext4_extent zero_ex;
+	struct ext4_extent zero_ex1, zero_ex2;
 	struct ext4_extent *ex, *abut_ex;
 	ext4_lblk_t ee_block, eof_block;
 	unsigned int ee_len, depth, map_len = map->m_len;
 	int allocated = 0, max_zeroout = 0;
 	int err = 0;
-	int split_flag = 0;
+	int split_flag = EXT4_EXT_DATA_VALID2;
 
 	ext_debug("ext4_ext_convert_to_initialized: inode %lu, logical"
 		"block %llu, max_blocks %u\n", inode->i_ino,
@@ -3436,7 +3437,8 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	ex = path[depth].p_ext;
 	ee_block = le32_to_cpu(ex->ee_block);
 	ee_len = ext4_ext_get_actual_len(ex);
-	zero_ex.ee_len = 0;
+	zero_ex1.ee_len = 0;
+	zero_ex2.ee_len = 0;
 
 	trace_ext4_ext_convert_to_initialized_enter(inode, map, ex);
 
@@ -3576,62 +3578,52 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 	if (ext4_encrypted_inode(inode))
 		max_zeroout = 0;
 
-	/* If extent is less than s_max_zeroout_kb, zeroout directly */
-	if (max_zeroout && (ee_len <= max_zeroout)) {
-		err = ext4_ext_zeroout(inode, ex);
-		if (err)
-			goto out;
-		zero_ex.ee_block = ex->ee_block;
-		zero_ex.ee_len = cpu_to_le16(ext4_ext_get_actual_len(ex));
-		ext4_ext_store_pblock(&zero_ex, ext4_ext_pblock(ex));
-
-		err = ext4_ext_get_access(handle, inode, path + depth);
-		if (err)
-			goto out;
-		ext4_ext_mark_initialized(ex);
-		ext4_ext_try_to_merge(handle, inode, path, ex);
-		err = ext4_ext_dirty(handle, inode, path + path->p_depth);
-		goto out;
-	}
-
 	/*
-	 * four cases:
+	 * five cases:
 	 * 1. split the extent into three extents.
-	 * 2. split the extent into two extents, zeroout the first half.
-	 * 3. split the extent into two extents, zeroout the second half.
+	 * 2. split the extent into two extents, zeroout the head of the first
+	 *    extent.
+	 * 3. split the extent into two extents, zeroout the tail of the second
+	 *    extent.
 	 * 4. split the extent into two extents with out zeroout.
+	 * 5. no splitting needed, just possibly zeroout the head and / or the
+	 *    tail of the extent.
 	 */
 	split_map.m_lblk = map->m_lblk;
 	split_map.m_len = map->m_len;
 
-	if (max_zeroout && (allocated > map->m_len)) {
+	if (max_zeroout && (allocated > split_map.m_len)) {
 		if (allocated <= max_zeroout) {
-			/* case 3 */
-			zero_ex.ee_block =
-					 cpu_to_le32(map->m_lblk);
-			zero_ex.ee_len = cpu_to_le16(allocated);
-			ext4_ext_store_pblock(&zero_ex,
-				ext4_ext_pblock(ex) + map->m_lblk - ee_block);
-			err = ext4_ext_zeroout(inode, &zero_ex);
+			/* case 3 or 5 */
+			zero_ex1.ee_block =
+				 cpu_to_le32(split_map.m_lblk +
+					     split_map.m_len);
+			zero_ex1.ee_len =
+				cpu_to_le16(allocated - split_map.m_len);
+			ext4_ext_store_pblock(&zero_ex1,
+				ext4_ext_pblock(ex) + split_map.m_lblk +
+				split_map.m_len - ee_block);
+			err = ext4_ext_zeroout(inode, &zero_ex1);
 			if (err)
 				goto out;
-			split_map.m_lblk = map->m_lblk;
 			split_map.m_len = allocated;
-		} else if (map->m_lblk - ee_block + map->m_len < max_zeroout) {
-			/* case 2 */
-			if (map->m_lblk != ee_block) {
-				zero_ex.ee_block = ex->ee_block;
-				zero_ex.ee_len = cpu_to_le16(map->m_lblk -
+		}
+		if (split_map.m_lblk - ee_block + split_map.m_len <
+								max_zeroout) {
+			/* case 2 or 5 */
+			if (split_map.m_lblk != ee_block) {
+				zero_ex2.ee_block = ex->ee_block;
+				zero_ex2.ee_len = cpu_to_le16(split_map.m_lblk -
 							ee_block);
-				ext4_ext_store_pblock(&zero_ex,
+				ext4_ext_store_pblock(&zero_ex2,
 						      ext4_ext_pblock(ex));
-				err = ext4_ext_zeroout(inode, &zero_ex);
+				err = ext4_ext_zeroout(inode, &zero_ex2);
 				if (err)
 					goto out;
 			}
 
+			split_map.m_len += split_map.m_lblk - ee_block;
 			split_map.m_lblk = ee_block;
-			split_map.m_len = map->m_lblk - ee_block + map->m_len;
 			allocated = map->m_len;
 		}
 	}
@@ -3642,8 +3634,11 @@ static int ext4_ext_convert_to_initialized(handle_t *handle,
 		err = 0;
 out:
 	/* If we have gotten a failure, don't zero out status tree */
-	if (!err)
-		err = ext4_zeroout_es(inode, &zero_ex);
+	if (!err) {
+		err = ext4_zeroout_es(inode, &zero_ex1);
+		if (!err)
+			err = ext4_zeroout_es(inode, &zero_ex2);
+	}
 	return err ? err : allocated;
 }
 
@@ -4883,6 +4878,8 @@ static long ext4_zero_range(struct file *file, loff_t offset,
 
 	/* Zero out partial block at the edges of the range */
 	ret = ext4_zero_partial_blocks(handle, inode, offset, len);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 
 	if (file->f_flags & O_SYNC)
 		ext4_handle_sync(handle);
@@ -5334,7 +5331,8 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	ext4_lblk_t stop, *iterator, ex_start, ex_end;
 
 	/* Let path point to the last extent */
-	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL, 0);
+	path = ext4_find_extent(inode, EXT_MAX_BLOCKS - 1, NULL,
+				EXT4_EX_NOCACHE);
 	if (IS_ERR(path))
 		return PTR_ERR(path);
 
@@ -5343,15 +5341,15 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	if (!extent)
 		goto out;
 
-	stop = le32_to_cpu(extent->ee_block) +
-			ext4_ext_get_actual_len(extent);
+	stop = le32_to_cpu(extent->ee_block);
 
        /*
 	 * In case of left shift, Don't start shifting extents until we make
 	 * sure the hole is big enough to accommodate the shift.
 	*/
 	if (SHIFT == SHIFT_LEFT) {
-		path = ext4_find_extent(inode, start - 1, &path, 0);
+		path = ext4_find_extent(inode, start - 1, &path,
+					EXT4_EX_NOCACHE);
 		if (IS_ERR(path))
 			return PTR_ERR(path);
 		depth = path->p_depth;
@@ -5383,9 +5381,14 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 	else
 		iterator = &stop;
 
-	/* Its safe to start updating extents */
-	while (start < stop) {
-		path = ext4_find_extent(inode, *iterator, &path, 0);
+	/*
+	 * Its safe to start updating extents.  Start and stop are unsigned, so
+	 * in case of right shift if extent with 0 block is reached, iterator
+	 * becomes NULL to indicate the end of the loop.
+	 */
+	while (iterator && start <= stop) {
+		path = ext4_find_extent(inode, *iterator, &path,
+					EXT4_EX_NOCACHE);
 		if (IS_ERR(path))
 			return PTR_ERR(path);
 		depth = path->p_depth;
@@ -5412,8 +5415,11 @@ ext4_ext_shift_extents(struct inode *inode, handle_t *handle,
 					ext4_ext_get_actual_len(extent);
 		} else {
 			extent = EXT_FIRST_EXTENT(path[depth].p_hdr);
-			*iterator =  le32_to_cpu(extent->ee_block) > 0 ?
-				le32_to_cpu(extent->ee_block) - 1 : 0;
+			if (le32_to_cpu(extent->ee_block) > 0)
+				*iterator = le32_to_cpu(extent->ee_block) - 1;
+			else
+				/* Beginning is reached, end of the loop */
+				iterator = NULL;
 			/* Update path extent in case we need to stop */
 			while (le32_to_cpu(extent->ee_block) < start)
 				extent++;
@@ -5560,6 +5566,7 @@ int ext4_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 		ext4_handle_sync(handle);
 	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+	ext4_update_inode_fsync_trans(handle, inode, 1);
 
 out_stop:
 	ext4_journal_stop(handle);
@@ -5733,6 +5740,8 @@ int ext4_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	up_write(&EXT4_I(inode)->i_data_sem);
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 
 out_stop:
 	ext4_journal_stop(handle);
diff --git a/fs/ext4/extents_status.c b/fs/ext4/extents_status.c
index 37e059202cd2..e7f12a204cbc 100644
--- a/fs/ext4/extents_status.c
+++ b/fs/ext4/extents_status.c
@@ -84,7 +84,7 @@
  *   --	writeout
  *	Writeout looks up whole page cache to see if a buffer is
  *	mapped, If there are not very many delayed buffers, then it is
- *	time comsuming.
+ *	time consuming.
  *
  * With extent status tree implementation, FIEMAP, SEEK_HOLE/DATA,
  * bigalloc and writeout can figure out if a block or a range of
diff --git a/fs/ext4/file.c b/fs/ext4/file.c
index d663d3d7c81c..58294c9a7e1d 100644
--- a/fs/ext4/file.c
+++ b/fs/ext4/file.c
@@ -37,7 +37,11 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
 
-	inode_lock_shared(inode);
+	if (!inode_trylock_shared(inode)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_lock_shared(inode);
+	}
 	/*
 	 * Recheck under inode lock - at this point we are sure it cannot
 	 * change anymore
@@ -57,6 +61,9 @@ static ssize_t ext4_dax_read_iter(struct kiocb *iocb, struct iov_iter *to)
 
 static ssize_t ext4_file_read_iter(struct kiocb *iocb, struct iov_iter *to)
 {
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(file_inode(iocb->ki_filp)->i_sb))))
+		return -EIO;
+
 	if (!iov_iter_count(to))
 		return 0; /* skip atime */
 
@@ -175,9 +182,12 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 {
 	struct inode *inode = file_inode(iocb->ki_filp);
 	ssize_t ret;
-	bool overwrite = false;
 
-	inode_lock(inode);
+	if (!inode_trylock(inode)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_lock(inode);
+	}
 	ret = ext4_write_checks(iocb, from);
 	if (ret <= 0)
 		goto out;
@@ -188,16 +198,9 @@ ext4_dax_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	if (ret)
 		goto out;
 
-	if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
-		overwrite = true;
-		downgrade_write(&inode->i_rwsem);
-	}
 	ret = dax_iomap_rw(iocb, from, &ext4_iomap_ops);
 out:
-	if (!overwrite)
-		inode_unlock(inode);
-	else
-		inode_unlock_shared(inode);
+	inode_unlock(inode);
 	if (ret > 0)
 		ret = generic_write_sync(iocb, ret);
 	return ret;
@@ -213,12 +216,20 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	int overwrite = 0;
 	ssize_t ret;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 #ifdef CONFIG_FS_DAX
 	if (IS_DAX(inode))
 		return ext4_dax_write_iter(iocb, from);
 #endif
 
-	inode_lock(inode);
+	if (!inode_trylock(inode)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		inode_lock(inode);
+	}
+
 	ret = ext4_write_checks(iocb, from);
 	if (ret <= 0)
 		goto out;
@@ -237,9 +248,15 @@ ext4_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 
 	iocb->private = &overwrite;
 	/* Check whether we do a DIO overwrite or not */
-	if (o_direct && ext4_should_dioread_nolock(inode) && !unaligned_aio &&
-	    ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from)))
-		overwrite = 1;
+	if (o_direct && !unaligned_aio) {
+		if (ext4_overwrite_io(inode, iocb->ki_pos, iov_iter_count(from))) {
+			if (ext4_should_dioread_nolock(inode))
+				overwrite = 1;
+		} else if (iocb->ki_flags & IOCB_NOWAIT) {
+			ret = -EAGAIN;
+			goto out;
+		}
+	}
 
 	ret = __generic_file_write_iter(iocb, from);
 	inode_unlock(inode);
@@ -255,46 +272,43 @@ out:
 }
 
 #ifdef CONFIG_FS_DAX
-static int ext4_dax_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int ext4_dax_huge_fault(struct vm_fault *vmf,
+		enum page_entry_size pe_size)
 {
 	int result;
-	struct inode *inode = file_inode(vma->vm_file);
+	handle_t *handle = NULL;
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	bool write = vmf->flags & FAULT_FLAG_WRITE;
 
 	if (write) {
 		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
+		file_update_time(vmf->vma->vm_file);
+		down_read(&EXT4_I(inode)->i_mmap_sem);
+		handle = ext4_journal_start_sb(sb, EXT4_HT_WRITE_PAGE,
+					       EXT4_DATA_TRANS_BLOCKS(sb));
+	} else {
+		down_read(&EXT4_I(inode)->i_mmap_sem);
 	}
-	down_read(&EXT4_I(inode)->i_mmap_sem);
-	result = dax_iomap_fault(vma, vmf, &ext4_iomap_ops);
-	up_read(&EXT4_I(inode)->i_mmap_sem);
-	if (write)
+	if (!IS_ERR(handle))
+		result = dax_iomap_fault(vmf, pe_size, &ext4_iomap_ops);
+	else
+		result = VM_FAULT_SIGBUS;
+	if (write) {
+		if (!IS_ERR(handle))
+			ext4_journal_stop(handle);
+		up_read(&EXT4_I(inode)->i_mmap_sem);
 		sb_end_pagefault(sb);
+	} else {
+		up_read(&EXT4_I(inode)->i_mmap_sem);
+	}
 
 	return result;
 }
 
-static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
-						pmd_t *pmd, unsigned int flags)
+static int ext4_dax_fault(struct vm_fault *vmf)
 {
-	int result;
-	struct inode *inode = file_inode(vma->vm_file);
-	struct super_block *sb = inode->i_sb;
-	bool write = flags & FAULT_FLAG_WRITE;
-
-	if (write) {
-		sb_start_pagefault(sb);
-		file_update_time(vma->vm_file);
-	}
-	down_read(&EXT4_I(inode)->i_mmap_sem);
-	result = dax_iomap_pmd_fault(vma, addr, pmd, flags,
-				     &ext4_iomap_ops);
-	up_read(&EXT4_I(inode)->i_mmap_sem);
-	if (write)
-		sb_end_pagefault(sb);
-
-	return result;
+	return ext4_dax_huge_fault(vmf, PE_SIZE_PTE);
 }
 
 /*
@@ -306,22 +320,21 @@ static int ext4_dax_pmd_fault(struct vm_area_struct *vma, unsigned long addr,
  * wp_pfn_shared() fails. Thus fault gets retried and things work out as
  * desired.
  */
-static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
-				struct vm_fault *vmf)
+static int ext4_dax_pfn_mkwrite(struct vm_fault *vmf)
 {
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct super_block *sb = inode->i_sb;
 	loff_t size;
 	int ret;
 
 	sb_start_pagefault(sb);
-	file_update_time(vma->vm_file);
+	file_update_time(vmf->vma->vm_file);
 	down_read(&EXT4_I(inode)->i_mmap_sem);
 	size = (i_size_read(inode) + PAGE_SIZE - 1) >> PAGE_SHIFT;
 	if (vmf->pgoff >= size)
 		ret = VM_FAULT_SIGBUS;
 	else
-		ret = dax_pfn_mkwrite(vma, vmf);
+		ret = dax_pfn_mkwrite(vmf);
 	up_read(&EXT4_I(inode)->i_mmap_sem);
 	sb_end_pagefault(sb);
 
@@ -330,7 +343,7 @@ static int ext4_dax_pfn_mkwrite(struct vm_area_struct *vma,
 
 static const struct vm_operations_struct ext4_dax_vm_ops = {
 	.fault		= ext4_dax_fault,
-	.pmd_fault	= ext4_dax_pmd_fault,
+	.huge_fault	= ext4_dax_huge_fault,
 	.page_mkwrite	= ext4_dax_fault,
 	.pfn_mkwrite	= ext4_dax_pfn_mkwrite,
 };
@@ -348,13 +361,9 @@ static int ext4_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	struct inode *inode = file->f_mapping->host;
 
-	if (ext4_encrypted_inode(inode)) {
-		int err = fscrypt_get_encryption_info(inode);
-		if (err)
-			return 0;
-		if (!fscrypt_has_encryption_key(inode))
-			return -ENOKEY;
-	}
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	file_accessed(file);
 	if (IS_DAX(file_inode(file))) {
 		vma->vm_ops = &ext4_dax_vm_ops;
@@ -375,6 +384,9 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 	char buf[64], *cp;
 	int ret;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	if (unlikely(!(sbi->s_mount_flags & EXT4_MF_MNTDIR_SAMPLED) &&
 		     !(sb->s_flags & MS_RDONLY))) {
 		sbi->s_mount_flags |= EXT4_MF_MNTDIR_SAMPLED;
@@ -435,6 +447,10 @@ static int ext4_file_open(struct inode * inode, struct file * filp)
 		if (ret < 0)
 			return ret;
 	}
+
+	/* Set the flags to support nowait AIO */
+	filp->f_mode |= FMODE_AIO_NOWAIT;
+
 	return dquot_file_open(inode, filp);
 }
 
@@ -474,57 +490,37 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 	endoff = (loff_t)end_blk << blkbits;
 
 	index = startoff >> PAGE_SHIFT;
-	end = endoff >> PAGE_SHIFT;
+	end = (endoff - 1) >> PAGE_SHIFT;
 
 	pagevec_init(&pvec, 0);
 	do {
 		int i, num;
 		unsigned long nr_pages;
 
-		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
+		num = min_t(pgoff_t, end - index, PAGEVEC_SIZE - 1) + 1;
 		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
 					  (pgoff_t)num);
-		if (nr_pages == 0) {
-			if (whence == SEEK_DATA)
-				break;
-
-			BUG_ON(whence != SEEK_HOLE);
-			/*
-			 * If this is the first time to go into the loop and
-			 * offset is not beyond the end offset, it will be a
-			 * hole at this offset
-			 */
-			if (lastoff == startoff || lastoff < endoff)
-				found = 1;
-			break;
-		}
-
-		/*
-		 * If this is the first time to go into the loop and
-		 * offset is smaller than the first page offset, it will be a
-		 * hole at this offset.
-		 */
-		if (lastoff == startoff && whence == SEEK_HOLE &&
-		    lastoff < page_offset(pvec.pages[0])) {
-			found = 1;
+		if (nr_pages == 0)
 			break;
-		}
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
 			struct buffer_head *bh, *head;
 
 			/*
-			 * If the current offset is not beyond the end of given
-			 * range, it will be a hole.
+			 * If current offset is smaller than the page offset,
+			 * there is a hole at this offset.
 			 */
-			if (lastoff < endoff && whence == SEEK_HOLE &&
-			    page->index > end) {
+			if (whence == SEEK_HOLE && lastoff < endoff &&
+			    lastoff < page_offset(pvec.pages[i])) {
 				found = 1;
 				*offset = lastoff;
 				goto out;
 			}
 
+			if (page->index > end)
+				goto out;
+
 			lock_page(page);
 
 			if (unlikely(page->mapping != inode->i_mapping)) {
@@ -564,20 +560,18 @@ static int ext4_find_unwritten_pgoff(struct inode *inode,
 			unlock_page(page);
 		}
 
-		/*
-		 * The no. of pages is less than our desired, that would be a
-		 * hole in there.
-		 */
-		if (nr_pages < num && whence == SEEK_HOLE) {
-			found = 1;
-			*offset = lastoff;
+		/* The no. of pages is less than our desired, we are done. */
+		if (nr_pages < num)
 			break;
-		}
 
 		index = pvec.pages[i - 1]->index + 1;
 		pagevec_release(&pvec);
 	} while (index <= end);
 
+	if (whence == SEEK_HOLE && lastoff < endoff) {
+		found = 1;
+		*offset = lastoff;
+	}
 out:
 	pagevec_release(&pvec);
 	return found;
@@ -757,7 +751,7 @@ const struct file_operations ext4_file_operations = {
 
 const struct inode_operations ext4_file_inode_operations = {
 	.setattr	= ext4_setattr,
-	.getattr	= ext4_getattr,
+	.getattr	= ext4_file_getattr,
 	.listxattr	= ext4_listxattr,
 	.get_acl	= ext4_get_acl,
 	.set_acl	= ext4_set_acl,
diff --git a/fs/ext4/fsmap.c b/fs/ext4/fsmap.c
new file mode 100644
index 000000000000..7ec340898598
--- /dev/null
+++ b/fs/ext4/fsmap.c
@@ -0,0 +1,726 @@
+/*
+ * Copyright (C) 2017 Oracle.  All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+#include "ext4.h"
+#include <linux/fsmap.h>
+#include "fsmap.h"
+#include "mballoc.h"
+#include <linux/sort.h>
+#include <linux/list_sort.h>
+#include <trace/events/ext4.h>
+
+/* Convert an ext4_fsmap to an fsmap. */
+void ext4_fsmap_from_internal(struct super_block *sb, struct fsmap *dest,
+			      struct ext4_fsmap *src)
+{
+	dest->fmr_device = src->fmr_device;
+	dest->fmr_flags = src->fmr_flags;
+	dest->fmr_physical = src->fmr_physical << sb->s_blocksize_bits;
+	dest->fmr_owner = src->fmr_owner;
+	dest->fmr_offset = 0;
+	dest->fmr_length = src->fmr_length << sb->s_blocksize_bits;
+	dest->fmr_reserved[0] = 0;
+	dest->fmr_reserved[1] = 0;
+	dest->fmr_reserved[2] = 0;
+}
+
+/* Convert an fsmap to an ext4_fsmap. */
+void ext4_fsmap_to_internal(struct super_block *sb, struct ext4_fsmap *dest,
+			    struct fsmap *src)
+{
+	dest->fmr_device = src->fmr_device;
+	dest->fmr_flags = src->fmr_flags;
+	dest->fmr_physical = src->fmr_physical >> sb->s_blocksize_bits;
+	dest->fmr_owner = src->fmr_owner;
+	dest->fmr_length = src->fmr_length >> sb->s_blocksize_bits;
+}
+
+/* getfsmap query state */
+struct ext4_getfsmap_info {
+	struct ext4_fsmap_head	*gfi_head;
+	ext4_fsmap_format_t	gfi_formatter;	/* formatting fn */
+	void			*gfi_format_arg;/* format buffer */
+	ext4_fsblk_t		gfi_next_fsblk;	/* next fsblock we expect */
+	u32			gfi_dev;	/* device id */
+	ext4_group_t		gfi_agno;	/* bg number, if applicable */
+	struct ext4_fsmap	gfi_low;	/* low rmap key */
+	struct ext4_fsmap	gfi_high;	/* high rmap key */
+	struct ext4_fsmap	gfi_lastfree;	/* free ext at end of last bg */
+	struct list_head	gfi_meta_list;	/* fixed metadata list */
+	bool			gfi_last;	/* last extent? */
+};
+
+/* Associate a device with a getfsmap handler. */
+struct ext4_getfsmap_dev {
+	int			(*gfd_fn)(struct super_block *sb,
+				      struct ext4_fsmap *keys,
+				      struct ext4_getfsmap_info *info);
+	u32			gfd_dev;
+};
+
+/* Compare two getfsmap device handlers. */
+static int ext4_getfsmap_dev_compare(const void *p1, const void *p2)
+{
+	const struct ext4_getfsmap_dev *d1 = p1;
+	const struct ext4_getfsmap_dev *d2 = p2;
+
+	return d1->gfd_dev - d2->gfd_dev;
+}
+
+/* Compare a record against our starting point */
+static bool ext4_getfsmap_rec_before_low_key(struct ext4_getfsmap_info *info,
+					     struct ext4_fsmap *rec)
+{
+	return rec->fmr_physical < info->gfi_low.fmr_physical;
+}
+
+/*
+ * Format a reverse mapping for getfsmap, having translated rm_startblock
+ * into the appropriate daddr units.
+ */
+static int ext4_getfsmap_helper(struct super_block *sb,
+				struct ext4_getfsmap_info *info,
+				struct ext4_fsmap *rec)
+{
+	struct ext4_fsmap fmr;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t rec_fsblk = rec->fmr_physical;
+	ext4_group_t agno;
+	ext4_grpblk_t cno;
+	int error;
+
+	if (fatal_signal_pending(current))
+		return -EINTR;
+
+	/*
+	 * Filter out records that start before our startpoint, if the
+	 * caller requested that.
+	 */
+	if (ext4_getfsmap_rec_before_low_key(info, rec)) {
+		rec_fsblk += rec->fmr_length;
+		if (info->gfi_next_fsblk < rec_fsblk)
+			info->gfi_next_fsblk = rec_fsblk;
+		return EXT4_QUERY_RANGE_CONTINUE;
+	}
+
+	/* Are we just counting mappings? */
+	if (info->gfi_head->fmh_count == 0) {
+		if (rec_fsblk > info->gfi_next_fsblk)
+			info->gfi_head->fmh_entries++;
+
+		if (info->gfi_last)
+			return EXT4_QUERY_RANGE_CONTINUE;
+
+		info->gfi_head->fmh_entries++;
+
+		rec_fsblk += rec->fmr_length;
+		if (info->gfi_next_fsblk < rec_fsblk)
+			info->gfi_next_fsblk = rec_fsblk;
+		return EXT4_QUERY_RANGE_CONTINUE;
+	}
+
+	/*
+	 * If the record starts past the last physical block we saw,
+	 * then we've found a gap.  Report the gap as being owned by
+	 * whatever the caller specified is the missing owner.
+	 */
+	if (rec_fsblk > info->gfi_next_fsblk) {
+		if (info->gfi_head->fmh_entries >= info->gfi_head->fmh_count)
+			return EXT4_QUERY_RANGE_ABORT;
+
+		ext4_get_group_no_and_offset(sb, info->gfi_next_fsblk,
+				&agno, &cno);
+		trace_ext4_fsmap_mapping(sb, info->gfi_dev, agno,
+				EXT4_C2B(sbi, cno),
+				rec_fsblk - info->gfi_next_fsblk,
+				EXT4_FMR_OWN_UNKNOWN);
+
+		fmr.fmr_device = info->gfi_dev;
+		fmr.fmr_physical = info->gfi_next_fsblk;
+		fmr.fmr_owner = EXT4_FMR_OWN_UNKNOWN;
+		fmr.fmr_length = rec_fsblk - info->gfi_next_fsblk;
+		fmr.fmr_flags = FMR_OF_SPECIAL_OWNER;
+		error = info->gfi_formatter(&fmr, info->gfi_format_arg);
+		if (error)
+			return error;
+		info->gfi_head->fmh_entries++;
+	}
+
+	if (info->gfi_last)
+		goto out;
+
+	/* Fill out the extent we found */
+	if (info->gfi_head->fmh_entries >= info->gfi_head->fmh_count)
+		return EXT4_QUERY_RANGE_ABORT;
+
+	ext4_get_group_no_and_offset(sb, rec_fsblk, &agno, &cno);
+	trace_ext4_fsmap_mapping(sb, info->gfi_dev, agno, EXT4_C2B(sbi, cno),
+			rec->fmr_length, rec->fmr_owner);
+
+	fmr.fmr_device = info->gfi_dev;
+	fmr.fmr_physical = rec_fsblk;
+	fmr.fmr_owner = rec->fmr_owner;
+	fmr.fmr_flags = FMR_OF_SPECIAL_OWNER;
+	fmr.fmr_length = rec->fmr_length;
+	error = info->gfi_formatter(&fmr, info->gfi_format_arg);
+	if (error)
+		return error;
+	info->gfi_head->fmh_entries++;
+
+out:
+	rec_fsblk += rec->fmr_length;
+	if (info->gfi_next_fsblk < rec_fsblk)
+		info->gfi_next_fsblk = rec_fsblk;
+	return EXT4_QUERY_RANGE_CONTINUE;
+}
+
+static inline ext4_fsblk_t ext4_fsmap_next_pblk(struct ext4_fsmap *fmr)
+{
+	return fmr->fmr_physical + fmr->fmr_length;
+}
+
+/* Transform a blockgroup's free record into a fsmap */
+static int ext4_getfsmap_datadev_helper(struct super_block *sb,
+					ext4_group_t agno, ext4_grpblk_t start,
+					ext4_grpblk_t len, void *priv)
+{
+	struct ext4_fsmap irec;
+	struct ext4_getfsmap_info *info = priv;
+	struct ext4_fsmap *p;
+	struct ext4_fsmap *tmp;
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t fsb;
+	ext4_fsblk_t fslen;
+	int error;
+
+	fsb = (EXT4_C2B(sbi, start) + ext4_group_first_block_no(sb, agno));
+	fslen = EXT4_C2B(sbi, len);
+
+	/* If the retained free extent record is set... */
+	if (info->gfi_lastfree.fmr_owner) {
+		/* ...and abuts this one, lengthen it and return. */
+		if (ext4_fsmap_next_pblk(&info->gfi_lastfree) == fsb) {
+			info->gfi_lastfree.fmr_length += fslen;
+			return 0;
+		}
+
+		/*
+		 * There's a gap between the two free extents; emit the
+		 * retained extent prior to merging the meta_list.
+		 */
+		error = ext4_getfsmap_helper(sb, info, &info->gfi_lastfree);
+		if (error)
+			return error;
+		info->gfi_lastfree.fmr_owner = 0;
+	}
+
+	/* Merge in any relevant extents from the meta_list */
+	list_for_each_entry_safe(p, tmp, &info->gfi_meta_list, fmr_list) {
+		if (p->fmr_physical + p->fmr_length <= info->gfi_next_fsblk) {
+			list_del(&p->fmr_list);
+			kfree(p);
+		} else if (p->fmr_physical < fsb) {
+			error = ext4_getfsmap_helper(sb, info, p);
+			if (error)
+				return error;
+
+			list_del(&p->fmr_list);
+			kfree(p);
+		}
+	}
+
+	irec.fmr_device = 0;
+	irec.fmr_physical = fsb;
+	irec.fmr_length = fslen;
+	irec.fmr_owner = EXT4_FMR_OWN_FREE;
+	irec.fmr_flags = 0;
+
+	/* If this is a free extent at the end of a bg, buffer it. */
+	if (ext4_fsmap_next_pblk(&irec) ==
+			ext4_group_first_block_no(sb, agno + 1)) {
+		info->gfi_lastfree = irec;
+		return 0;
+	}
+
+	/* Otherwise, emit it */
+	return ext4_getfsmap_helper(sb, info, &irec);
+}
+
+/* Execute a getfsmap query against the log device. */
+static int ext4_getfsmap_logdev(struct super_block *sb, struct ext4_fsmap *keys,
+				struct ext4_getfsmap_info *info)
+{
+	journal_t *journal = EXT4_SB(sb)->s_journal;
+	struct ext4_fsmap irec;
+
+	/* Set up search keys */
+	info->gfi_low = keys[0];
+	info->gfi_low.fmr_length = 0;
+
+	memset(&info->gfi_high, 0xFF, sizeof(info->gfi_high));
+
+	trace_ext4_fsmap_low_key(sb, info->gfi_dev, 0,
+			info->gfi_low.fmr_physical,
+			info->gfi_low.fmr_length,
+			info->gfi_low.fmr_owner);
+
+	trace_ext4_fsmap_high_key(sb, info->gfi_dev, 0,
+			info->gfi_high.fmr_physical,
+			info->gfi_high.fmr_length,
+			info->gfi_high.fmr_owner);
+
+	if (keys[0].fmr_physical > 0)
+		return 0;
+
+	/* Fabricate an rmap entry for the external log device. */
+	irec.fmr_physical = journal->j_blk_offset;
+	irec.fmr_length = journal->j_maxlen;
+	irec.fmr_owner = EXT4_FMR_OWN_LOG;
+	irec.fmr_flags = 0;
+
+	return ext4_getfsmap_helper(sb, info, &irec);
+}
+
+/* Helper to fill out an ext4_fsmap. */
+static inline int ext4_getfsmap_fill(struct list_head *meta_list,
+				     ext4_fsblk_t fsb, ext4_fsblk_t len,
+				     uint64_t owner)
+{
+	struct ext4_fsmap *fsm;
+
+	fsm = kmalloc(sizeof(*fsm), GFP_NOFS);
+	if (!fsm)
+		return -ENOMEM;
+	fsm->fmr_device = 0;
+	fsm->fmr_flags = 0;
+	fsm->fmr_physical = fsb;
+	fsm->fmr_owner = owner;
+	fsm->fmr_length = len;
+	list_add_tail(&fsm->fmr_list, meta_list);
+
+	return 0;
+}
+
+/*
+ * This function returns the number of file system metadata blocks at
+ * the beginning of a block group, including the reserved gdt blocks.
+ */
+static unsigned int ext4_getfsmap_find_sb(struct super_block *sb,
+					  ext4_group_t agno,
+					  struct list_head *meta_list)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t fsb = ext4_group_first_block_no(sb, agno);
+	ext4_fsblk_t len;
+	unsigned long first_meta_bg = le32_to_cpu(sbi->s_es->s_first_meta_bg);
+	unsigned long metagroup = agno / EXT4_DESC_PER_BLOCK(sb);
+	int error;
+
+	/* Record the superblock. */
+	if (ext4_bg_has_super(sb, agno)) {
+		error = ext4_getfsmap_fill(meta_list, fsb, 1, EXT4_FMR_OWN_FS);
+		if (error)
+			return error;
+		fsb++;
+	}
+
+	/* Record the group descriptors. */
+	len = ext4_bg_num_gdb(sb, agno);
+	if (!len)
+		return 0;
+	error = ext4_getfsmap_fill(meta_list, fsb, len,
+				   EXT4_FMR_OWN_GDT);
+	if (error)
+		return error;
+	fsb += len;
+
+	/* Reserved GDT blocks */
+	if (!ext4_has_feature_meta_bg(sb) || metagroup < first_meta_bg) {
+		len = le16_to_cpu(sbi->s_es->s_reserved_gdt_blocks);
+		error = ext4_getfsmap_fill(meta_list, fsb, len,
+					   EXT4_FMR_OWN_RESV_GDT);
+		if (error)
+			return error;
+	}
+
+	return 0;
+}
+
+/* Compare two fsmap items. */
+static int ext4_getfsmap_compare(void *priv,
+				 struct list_head *a,
+				 struct list_head *b)
+{
+	struct ext4_fsmap *fa;
+	struct ext4_fsmap *fb;
+
+	fa = container_of(a, struct ext4_fsmap, fmr_list);
+	fb = container_of(b, struct ext4_fsmap, fmr_list);
+	if (fa->fmr_physical < fb->fmr_physical)
+		return -1;
+	else if (fa->fmr_physical > fb->fmr_physical)
+		return 1;
+	return 0;
+}
+
+/* Merge adjacent extents of fixed metadata. */
+static void ext4_getfsmap_merge_fixed_metadata(struct list_head *meta_list)
+{
+	struct ext4_fsmap *p;
+	struct ext4_fsmap *prev = NULL;
+	struct ext4_fsmap *tmp;
+
+	list_for_each_entry_safe(p, tmp, meta_list, fmr_list) {
+		if (!prev) {
+			prev = p;
+			continue;
+		}
+
+		if (prev->fmr_owner == p->fmr_owner &&
+		    prev->fmr_physical + prev->fmr_length == p->fmr_physical) {
+			prev->fmr_length += p->fmr_length;
+			list_del(&p->fmr_list);
+			kfree(p);
+		} else
+			prev = p;
+	}
+}
+
+/* Free a list of fixed metadata. */
+static void ext4_getfsmap_free_fixed_metadata(struct list_head *meta_list)
+{
+	struct ext4_fsmap *p;
+	struct ext4_fsmap *tmp;
+
+	list_for_each_entry_safe(p, tmp, meta_list, fmr_list) {
+		list_del(&p->fmr_list);
+		kfree(p);
+	}
+}
+
+/* Find all the fixed metadata in the filesystem. */
+int ext4_getfsmap_find_fixed_metadata(struct super_block *sb,
+				      struct list_head *meta_list)
+{
+	struct ext4_group_desc *gdp;
+	ext4_group_t agno;
+	int error;
+
+	INIT_LIST_HEAD(meta_list);
+
+	/* Collect everything. */
+	for (agno = 0; agno < EXT4_SB(sb)->s_groups_count; agno++) {
+		gdp = ext4_get_group_desc(sb, agno, NULL);
+		if (!gdp) {
+			error = -EFSCORRUPTED;
+			goto err;
+		}
+
+		/* Superblock & GDT */
+		error = ext4_getfsmap_find_sb(sb, agno, meta_list);
+		if (error)
+			goto err;
+
+		/* Block bitmap */
+		error = ext4_getfsmap_fill(meta_list,
+					   ext4_block_bitmap(sb, gdp), 1,
+					   EXT4_FMR_OWN_BLKBM);
+		if (error)
+			goto err;
+
+		/* Inode bitmap */
+		error = ext4_getfsmap_fill(meta_list,
+					   ext4_inode_bitmap(sb, gdp), 1,
+					   EXT4_FMR_OWN_INOBM);
+		if (error)
+			goto err;
+
+		/* Inodes */
+		error = ext4_getfsmap_fill(meta_list,
+					   ext4_inode_table(sb, gdp),
+					   EXT4_SB(sb)->s_itb_per_group,
+					   EXT4_FMR_OWN_INODES);
+		if (error)
+			goto err;
+	}
+
+	/* Sort the list */
+	list_sort(NULL, meta_list, ext4_getfsmap_compare);
+
+	/* Merge adjacent extents */
+	ext4_getfsmap_merge_fixed_metadata(meta_list);
+
+	return 0;
+err:
+	ext4_getfsmap_free_fixed_metadata(meta_list);
+	return error;
+}
+
+/* Execute a getfsmap query against the buddy bitmaps */
+static int ext4_getfsmap_datadev(struct super_block *sb,
+				 struct ext4_fsmap *keys,
+				 struct ext4_getfsmap_info *info)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	ext4_fsblk_t start_fsb;
+	ext4_fsblk_t end_fsb;
+	ext4_fsblk_t bofs;
+	ext4_fsblk_t eofs;
+	ext4_group_t start_ag;
+	ext4_group_t end_ag;
+	ext4_grpblk_t first_cluster;
+	ext4_grpblk_t last_cluster;
+	int error = 0;
+
+	bofs = le32_to_cpu(sbi->s_es->s_first_data_block);
+	eofs = ext4_blocks_count(sbi->s_es);
+	if (keys[0].fmr_physical >= eofs)
+		return 0;
+	else if (keys[0].fmr_physical < bofs)
+		keys[0].fmr_physical = bofs;
+	if (keys[1].fmr_physical >= eofs)
+		keys[1].fmr_physical = eofs - 1;
+	start_fsb = keys[0].fmr_physical;
+	end_fsb = keys[1].fmr_physical;
+
+	/* Determine first and last group to examine based on start and end */
+	ext4_get_group_no_and_offset(sb, start_fsb, &start_ag, &first_cluster);
+	ext4_get_group_no_and_offset(sb, end_fsb, &end_ag, &last_cluster);
+
+	/*
+	 * Convert the fsmap low/high keys to bg based keys.  Initialize
+	 * low to the fsmap low key and max out the high key to the end
+	 * of the bg.
+	 */
+	info->gfi_low = keys[0];
+	info->gfi_low.fmr_physical = EXT4_C2B(sbi, first_cluster);
+	info->gfi_low.fmr_length = 0;
+
+	memset(&info->gfi_high, 0xFF, sizeof(info->gfi_high));
+
+	/* Assemble a list of all the fixed-location metadata. */
+	error = ext4_getfsmap_find_fixed_metadata(sb, &info->gfi_meta_list);
+	if (error)
+		goto err;
+
+	/* Query each bg */
+	for (info->gfi_agno = start_ag;
+	     info->gfi_agno <= end_ag;
+	     info->gfi_agno++) {
+		/*
+		 * Set the bg high key from the fsmap high key if this
+		 * is the last bg that we're querying.
+		 */
+		if (info->gfi_agno == end_ag) {
+			info->gfi_high = keys[1];
+			info->gfi_high.fmr_physical = EXT4_C2B(sbi,
+					last_cluster);
+			info->gfi_high.fmr_length = 0;
+		}
+
+		trace_ext4_fsmap_low_key(sb, info->gfi_dev, info->gfi_agno,
+				info->gfi_low.fmr_physical,
+				info->gfi_low.fmr_length,
+				info->gfi_low.fmr_owner);
+
+		trace_ext4_fsmap_high_key(sb, info->gfi_dev, info->gfi_agno,
+				info->gfi_high.fmr_physical,
+				info->gfi_high.fmr_length,
+				info->gfi_high.fmr_owner);
+
+		error = ext4_mballoc_query_range(sb, info->gfi_agno,
+				EXT4_B2C(sbi, info->gfi_low.fmr_physical),
+				EXT4_B2C(sbi, info->gfi_high.fmr_physical),
+				ext4_getfsmap_datadev_helper, info);
+		if (error)
+			goto err;
+
+		/*
+		 * Set the bg low key to the start of the bg prior to
+		 * moving on to the next bg.
+		 */
+		if (info->gfi_agno == start_ag)
+			memset(&info->gfi_low, 0, sizeof(info->gfi_low));
+	}
+
+	/* Do we have a retained free extent? */
+	if (info->gfi_lastfree.fmr_owner) {
+		error = ext4_getfsmap_helper(sb, info, &info->gfi_lastfree);
+		if (error)
+			goto err;
+	}
+
+	/* Report any gaps at the end of the bg */
+	info->gfi_last = true;
+	error = ext4_getfsmap_datadev_helper(sb, end_ag, last_cluster, 0, info);
+	if (error)
+		goto err;
+
+err:
+	ext4_getfsmap_free_fixed_metadata(&info->gfi_meta_list);
+	return error;
+}
+
+/* Do we recognize the device? */
+static bool ext4_getfsmap_is_valid_device(struct super_block *sb,
+					  struct ext4_fsmap *fm)
+{
+	if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX ||
+	    fm->fmr_device == new_encode_dev(sb->s_bdev->bd_dev))
+		return true;
+	if (EXT4_SB(sb)->journal_bdev &&
+	    fm->fmr_device == new_encode_dev(EXT4_SB(sb)->journal_bdev->bd_dev))
+		return true;
+	return false;
+}
+
+/* Ensure that the low key is less than the high key. */
+static bool ext4_getfsmap_check_keys(struct ext4_fsmap *low_key,
+				     struct ext4_fsmap *high_key)
+{
+	if (low_key->fmr_device > high_key->fmr_device)
+		return false;
+	if (low_key->fmr_device < high_key->fmr_device)
+		return true;
+
+	if (low_key->fmr_physical > high_key->fmr_physical)
+		return false;
+	if (low_key->fmr_physical < high_key->fmr_physical)
+		return true;
+
+	if (low_key->fmr_owner > high_key->fmr_owner)
+		return false;
+	if (low_key->fmr_owner < high_key->fmr_owner)
+		return true;
+
+	return false;
+}
+
+#define EXT4_GETFSMAP_DEVS	2
+/*
+ * Get filesystem's extents as described in head, and format for
+ * output.  Calls formatter to fill the user's buffer until all
+ * extents are mapped, until the passed-in head->fmh_count slots have
+ * been filled, or until the formatter short-circuits the loop, if it
+ * is tracking filled-in extents on its own.
+ *
+ * Key to Confusion
+ * ----------------
+ * There are multiple levels of keys and counters at work here:
+ * _fsmap_head.fmh_keys		-- low and high fsmap keys passed in;
+ * 				   these reflect fs-wide block addrs.
+ * dkeys			-- fmh_keys used to query each device;
+ * 				   these are fmh_keys but w/ the low key
+ * 				   bumped up by fmr_length.
+ * _getfsmap_info.gfi_next_fsblk-- next fs block we expect to see; this
+ *				   is how we detect gaps in the fsmap
+ *				   records and report them.
+ * _getfsmap_info.gfi_low/high	-- per-bg low/high keys computed from
+ * 				   dkeys; used to query the free space.
+ */
+int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head,
+		  ext4_fsmap_format_t formatter, void *arg)
+{
+	struct ext4_fsmap dkeys[2];	/* per-dev keys */
+	struct ext4_getfsmap_dev handlers[EXT4_GETFSMAP_DEVS];
+	struct ext4_getfsmap_info info = {0};
+	int i;
+	int error = 0;
+
+	if (head->fmh_iflags & ~FMH_IF_VALID)
+		return -EINVAL;
+	if (!ext4_getfsmap_is_valid_device(sb, &head->fmh_keys[0]) ||
+	    !ext4_getfsmap_is_valid_device(sb, &head->fmh_keys[1]))
+		return -EINVAL;
+
+	head->fmh_entries = 0;
+
+	/* Set up our device handlers. */
+	memset(handlers, 0, sizeof(handlers));
+	handlers[0].gfd_dev = new_encode_dev(sb->s_bdev->bd_dev);
+	handlers[0].gfd_fn = ext4_getfsmap_datadev;
+	if (EXT4_SB(sb)->journal_bdev) {
+		handlers[1].gfd_dev = new_encode_dev(
+				EXT4_SB(sb)->journal_bdev->bd_dev);
+		handlers[1].gfd_fn = ext4_getfsmap_logdev;
+	}
+
+	sort(handlers, EXT4_GETFSMAP_DEVS, sizeof(struct ext4_getfsmap_dev),
+			ext4_getfsmap_dev_compare, NULL);
+
+	/*
+	 * To continue where we left off, we allow userspace to use the
+	 * last mapping from a previous call as the low key of the next.
+	 * This is identified by a non-zero length in the low key. We
+	 * have to increment the low key in this scenario to ensure we
+	 * don't return the same mapping again, and instead return the
+	 * very next mapping.
+	 *
+	 * Bump the physical offset as there can be no other mapping for
+	 * the same physical block range.
+	 */
+	dkeys[0] = head->fmh_keys[0];
+	dkeys[0].fmr_physical += dkeys[0].fmr_length;
+	dkeys[0].fmr_owner = 0;
+	dkeys[0].fmr_length = 0;
+	memset(&dkeys[1], 0xFF, sizeof(struct ext4_fsmap));
+
+	if (!ext4_getfsmap_check_keys(dkeys, &head->fmh_keys[1]))
+		return -EINVAL;
+
+	info.gfi_next_fsblk = head->fmh_keys[0].fmr_physical +
+			  head->fmh_keys[0].fmr_length;
+	info.gfi_formatter = formatter;
+	info.gfi_format_arg = arg;
+	info.gfi_head = head;
+
+	/* For each device we support... */
+	for (i = 0; i < EXT4_GETFSMAP_DEVS; i++) {
+		/* Is this device within the range the user asked for? */
+		if (!handlers[i].gfd_fn)
+			continue;
+		if (head->fmh_keys[0].fmr_device > handlers[i].gfd_dev)
+			continue;
+		if (head->fmh_keys[1].fmr_device < handlers[i].gfd_dev)
+			break;
+
+		/*
+		 * If this device number matches the high key, we have
+		 * to pass the high key to the handler to limit the
+		 * query results.  If the device number exceeds the
+		 * low key, zero out the low key so that we get
+		 * everything from the beginning.
+		 */
+		if (handlers[i].gfd_dev == head->fmh_keys[1].fmr_device)
+			dkeys[1] = head->fmh_keys[1];
+		if (handlers[i].gfd_dev > head->fmh_keys[0].fmr_device)
+			memset(&dkeys[0], 0, sizeof(struct ext4_fsmap));
+
+		info.gfi_dev = handlers[i].gfd_dev;
+		info.gfi_last = false;
+		info.gfi_agno = -1;
+		error = handlers[i].gfd_fn(sb, dkeys, &info);
+		if (error)
+			break;
+		info.gfi_next_fsblk = 0;
+	}
+
+	head->fmh_oflags = FMH_OF_DEV_T;
+	return error;
+}
diff --git a/fs/ext4/fsmap.h b/fs/ext4/fsmap.h
new file mode 100644
index 000000000000..9a2cd367cc66
--- /dev/null
+++ b/fs/ext4/fsmap.h
@@ -0,0 +1,69 @@
+/*
+ * Copyright (C) 2017 Oracle.  All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+#ifndef __EXT4_FSMAP_H__
+#define	__EXT4_FSMAP_H__
+
+struct fsmap;
+
+/* internal fsmap representation */
+struct ext4_fsmap {
+	struct list_head	fmr_list;
+	dev_t		fmr_device;	/* device id */
+	uint32_t	fmr_flags;	/* mapping flags */
+	uint64_t	fmr_physical;	/* device offset of segment */
+	uint64_t	fmr_owner;	/* owner id */
+	uint64_t	fmr_length;	/* length of segment, blocks */
+};
+
+struct ext4_fsmap_head {
+	uint32_t	fmh_iflags;	/* control flags */
+	uint32_t	fmh_oflags;	/* output flags */
+	unsigned int	fmh_count;	/* # of entries in array incl. input */
+	unsigned int	fmh_entries;	/* # of entries filled in (output). */
+
+	struct ext4_fsmap fmh_keys[2];	/* low and high keys */
+};
+
+void ext4_fsmap_from_internal(struct super_block *sb, struct fsmap *dest,
+		struct ext4_fsmap *src);
+void ext4_fsmap_to_internal(struct super_block *sb, struct ext4_fsmap *dest,
+		struct fsmap *src);
+
+/* fsmap to userspace formatter - copy to user & advance pointer */
+typedef int (*ext4_fsmap_format_t)(struct ext4_fsmap *, void *);
+
+int ext4_getfsmap(struct super_block *sb, struct ext4_fsmap_head *head,
+		ext4_fsmap_format_t formatter, void *arg);
+
+#define EXT4_QUERY_RANGE_ABORT		1
+#define EXT4_QUERY_RANGE_CONTINUE	0
+
+/*	fmr_owner special values for FS_IOC_GETFSMAP; some share w/ XFS */
+#define EXT4_FMR_OWN_FREE	FMR_OWN_FREE      /* free space */
+#define EXT4_FMR_OWN_UNKNOWN	FMR_OWN_UNKNOWN   /* unknown owner */
+#define EXT4_FMR_OWN_FS		FMR_OWNER('X', 1) /* static fs metadata */
+#define EXT4_FMR_OWN_LOG	FMR_OWNER('X', 2) /* journalling log */
+#define EXT4_FMR_OWN_INODES	FMR_OWNER('X', 5) /* inodes */
+#define EXT4_FMR_OWN_GDT	FMR_OWNER('f', 1) /* group descriptors */
+#define EXT4_FMR_OWN_RESV_GDT	FMR_OWNER('f', 2) /* reserved gdt blocks */
+#define EXT4_FMR_OWN_BLKBM	FMR_OWNER('f', 3) /* inode bitmap */
+#define EXT4_FMR_OWN_INOBM	FMR_OWNER('f', 4) /* block bitmap */
+
+#endif /* __EXT4_FSMAP_H__ */
diff --git a/fs/ext4/fsync.c b/fs/ext4/fsync.c
index 88effb1053c7..aae2c3971cef 100644
--- a/fs/ext4/fsync.c
+++ b/fs/ext4/fsync.c
@@ -100,6 +100,9 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	tid_t commit_tid;
 	bool needs_barrier = false;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	J_ASSERT(ext4_journal_current_handle() == NULL);
 
 	trace_ext4_sync_file_enter(file, datasync);
@@ -121,7 +124,7 @@ int ext4_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 		goto out;
 	}
 
-	ret = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	ret = file_write_and_wait_range(file, start, end);
 	if (ret)
 		return ret;
 	/*
diff --git a/fs/ext4/hash.c b/fs/ext4/hash.c
index e026aa941fd5..38b8a96eb97c 100644
--- a/fs/ext4/hash.c
+++ b/fs/ext4/hash.c
@@ -10,7 +10,8 @@
  */
 
 #include <linux/fs.h>
-#include <linux/cryptohash.h>
+#include <linux/compiler.h>
+#include <linux/bitops.h>
 #include "ext4.h"
 
 #define DELTA 0x9E3779B9
@@ -32,6 +33,74 @@ static void TEA_transform(__u32 buf[4], __u32 const in[])
 	buf[1] += b1;
 }
 
+/* F, G and H are basic MD4 functions: selection, majority, parity */
+#define F(x, y, z) ((z) ^ ((x) & ((y) ^ (z))))
+#define G(x, y, z) (((x) & (y)) + (((x) ^ (y)) & (z)))
+#define H(x, y, z) ((x) ^ (y) ^ (z))
+
+/*
+ * The generic round function.  The application is so specific that
+ * we don't bother protecting all the arguments with parens, as is generally
+ * good macro practice, in favor of extra legibility.
+ * Rotation is separate from addition to prevent recomputation
+ */
+#define ROUND(f, a, b, c, d, x, s)	\
+	(a += f(b, c, d) + x, a = rol32(a, s))
+#define K1 0
+#define K2 013240474631UL
+#define K3 015666365641UL
+
+/*
+ * Basic cut-down MD4 transform.  Returns only 32 bits of result.
+ */
+static __u32 half_md4_transform(__u32 buf[4], __u32 const in[8])
+{
+	__u32 a = buf[0], b = buf[1], c = buf[2], d = buf[3];
+
+	/* Round 1 */
+	ROUND(F, a, b, c, d, in[0] + K1,  3);
+	ROUND(F, d, a, b, c, in[1] + K1,  7);
+	ROUND(F, c, d, a, b, in[2] + K1, 11);
+	ROUND(F, b, c, d, a, in[3] + K1, 19);
+	ROUND(F, a, b, c, d, in[4] + K1,  3);
+	ROUND(F, d, a, b, c, in[5] + K1,  7);
+	ROUND(F, c, d, a, b, in[6] + K1, 11);
+	ROUND(F, b, c, d, a, in[7] + K1, 19);
+
+	/* Round 2 */
+	ROUND(G, a, b, c, d, in[1] + K2,  3);
+	ROUND(G, d, a, b, c, in[3] + K2,  5);
+	ROUND(G, c, d, a, b, in[5] + K2,  9);
+	ROUND(G, b, c, d, a, in[7] + K2, 13);
+	ROUND(G, a, b, c, d, in[0] + K2,  3);
+	ROUND(G, d, a, b, c, in[2] + K2,  5);
+	ROUND(G, c, d, a, b, in[4] + K2,  9);
+	ROUND(G, b, c, d, a, in[6] + K2, 13);
+
+	/* Round 3 */
+	ROUND(H, a, b, c, d, in[3] + K3,  3);
+	ROUND(H, d, a, b, c, in[7] + K3,  9);
+	ROUND(H, c, d, a, b, in[2] + K3, 11);
+	ROUND(H, b, c, d, a, in[6] + K3, 15);
+	ROUND(H, a, b, c, d, in[1] + K3,  3);
+	ROUND(H, d, a, b, c, in[5] + K3,  9);
+	ROUND(H, c, d, a, b, in[0] + K3, 11);
+	ROUND(H, b, c, d, a, in[4] + K3, 15);
+
+	buf[0] += a;
+	buf[1] += b;
+	buf[2] += c;
+	buf[3] += d;
+
+	return buf[1]; /* "most hashed" word */
+}
+#undef ROUND
+#undef K1
+#undef K2
+#undef K3
+#undef F
+#undef G
+#undef H
 
 /* The old legacy hash */
 static __u32 dx_hack_hash_unsigned(const char *name, int len)
diff --git a/fs/ext4/ialloc.c b/fs/ext4/ialloc.c
index e57e8d90ea54..507bfb3344d4 100644
--- a/fs/ext4/ialloc.c
+++ b/fs/ext4/ialloc.c
@@ -21,6 +21,8 @@
 #include <linux/random.h>
 #include <linux/bitops.h>
 #include <linux/blkdev.h>
+#include <linux/cred.h>
+
 #include <asm/byteorder.h>
 
 #include "ext4.h"
@@ -292,7 +294,6 @@ void ext4_free_inode(handle_t *handle, struct inode *inode)
 	 * as writing the quota to disk may need the lock as well.
 	 */
 	dquot_initialize(inode);
-	ext4_xattr_delete_inode(handle, inode);
 	dquot_free_inode(inode);
 	dquot_drop(inode);
 
@@ -741,8 +742,9 @@ out:
  */
 struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 			       umode_t mode, const struct qstr *qstr,
-			       __u32 goal, uid_t *owner, int handle_type,
-			       unsigned int line_no, int nblocks)
+			       __u32 goal, uid_t *owner, __u32 i_flags,
+			       int handle_type, unsigned int line_no,
+			       int nblocks)
 {
 	struct super_block *sb;
 	struct buffer_head *inode_bitmap_bh = NULL;
@@ -764,27 +766,69 @@ struct inode *__ext4_new_inode(handle_t *handle, struct inode *dir,
 	if (!dir || !dir->i_nlink)
 		return ERR_PTR(-EPERM);
 
-	if ((ext4_encrypted_inode(dir) ||
-	     DUMMY_ENCRYPTION_ENABLED(EXT4_SB(dir->i_sb))) &&
-	    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode))) {
+	sb = dir->i_sb;
+	sbi = EXT4_SB(sb);
+
+	if (unlikely(ext4_forced_shutdown(sbi)))
+		return ERR_PTR(-EIO);
+
+	if ((ext4_encrypted_inode(dir) || DUMMY_ENCRYPTION_ENABLED(sbi)) &&
+	    (S_ISREG(mode) || S_ISDIR(mode) || S_ISLNK(mode)) &&
+	    !(i_flags & EXT4_EA_INODE_FL)) {
 		err = fscrypt_get_encryption_info(dir);
 		if (err)
 			return ERR_PTR(err);
 		if (!fscrypt_has_encryption_key(dir))
-			return ERR_PTR(-EPERM);
-		if (!handle)
-			nblocks += EXT4_DATA_TRANS_BLOCKS(dir->i_sb);
+			return ERR_PTR(-ENOKEY);
 		encrypt = 1;
 	}
 
-	sb = dir->i_sb;
+	if (!handle && sbi->s_journal && !(i_flags & EXT4_EA_INODE_FL)) {
+#ifdef CONFIG_EXT4_FS_POSIX_ACL
+		struct posix_acl *p = get_acl(dir, ACL_TYPE_DEFAULT);
+
+		if (p) {
+			int acl_size = p->a_count * sizeof(ext4_acl_entry);
+
+			nblocks += (S_ISDIR(mode) ? 2 : 1) *
+				__ext4_xattr_set_credits(sb, NULL /* inode */,
+					NULL /* block_bh */, acl_size,
+					true /* is_create */);
+			posix_acl_release(p);
+		}
+#endif
+
+#ifdef CONFIG_SECURITY
+		{
+			int num_security_xattrs = 1;
+
+#ifdef CONFIG_INTEGRITY
+			num_security_xattrs++;
+#endif
+			/*
+			 * We assume that security xattrs are never
+			 * more than 1k.  In practice they are under
+			 * 128 bytes.
+			 */
+			nblocks += num_security_xattrs *
+				__ext4_xattr_set_credits(sb, NULL /* inode */,
+					NULL /* block_bh */, 1024,
+					true /* is_create */);
+		}
+#endif
+		if (encrypt)
+			nblocks += __ext4_xattr_set_credits(sb,
+					NULL /* inode */, NULL /* block_bh */,
+					FSCRYPT_SET_CONTEXT_MAX_SIZE,
+					true /* is_create */);
+	}
+
 	ngroups = ext4_get_groups_count(sb);
 	trace_ext4_request_inode(dir, mode);
 	inode = new_inode(sb);
 	if (!inode)
 		return ERR_PTR(-ENOMEM);
 	ei = EXT4_I(inode);
-	sbi = EXT4_SB(sb);
 
 	/*
 	 * Initialize owners and quota early so that we don't have to account
@@ -1048,6 +1092,7 @@ got:
 	/* Don't inherit extent flag from directory, amongst others. */
 	ei->i_flags =
 		ext4_mask_flags(mode, EXT4_I(dir)->i_flags & EXT4_FL_INHERITED);
+	ei->i_flags |= i_flags;
 	ei->i_file_acl = 0;
 	ei->i_dtime = 0;
 	ei->i_block_group = group;
@@ -1093,13 +1138,26 @@ got:
 	if (err)
 		goto fail_drop;
 
-	err = ext4_init_acl(handle, inode, dir);
-	if (err)
-		goto fail_free_drop;
+	/*
+	 * Since the encryption xattr will always be unique, create it first so
+	 * that it's less likely to end up in an external xattr block and
+	 * prevent its deduplication.
+	 */
+	if (encrypt) {
+		err = fscrypt_inherit_context(dir, inode, handle, true);
+		if (err)
+			goto fail_free_drop;
+	}
 
-	err = ext4_init_security(handle, inode, dir, qstr);
-	if (err)
-		goto fail_free_drop;
+	if (!(ei->i_flags & EXT4_EA_INODE_FL)) {
+		err = ext4_init_acl(handle, inode, dir);
+		if (err)
+			goto fail_free_drop;
+
+		err = ext4_init_security(handle, inode, dir, qstr);
+		if (err)
+			goto fail_free_drop;
+	}
 
 	if (ext4_has_feature_extents(sb)) {
 		/* set extent flag only for directory, file and normal symlink*/
@@ -1114,12 +1172,6 @@ got:
 		ei->i_datasync_tid = handle->h_transaction->t_tid;
 	}
 
-	if (encrypt) {
-		err = fscrypt_inherit_context(dir, inode, handle, true);
-		if (err)
-			goto fail_free_drop;
-	}
-
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err) {
 		ext4_std_error(sb, err);
diff --git a/fs/ext4/indirect.c b/fs/ext4/indirect.c
index bc15c2c17633..7ffa290cbb8e 100644
--- a/fs/ext4/indirect.c
+++ b/fs/ext4/indirect.c
@@ -829,7 +829,8 @@ static int ext4_clear_blocks(handle_t *handle, struct inode *inode,
 	int	flags = EXT4_FREE_BLOCKS_VALIDATED;
 	int	err;
 
-	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode))
+	if (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode) ||
+	    ext4_test_inode_flag(inode, EXT4_INODE_EA_INODE))
 		flags |= EXT4_FREE_BLOCKS_FORGET | EXT4_FREE_BLOCKS_METADATA;
 	else if (ext4_should_journal_data(inode))
 		flags |= EXT4_FREE_BLOCKS_FORGET;
diff --git a/fs/ext4/inline.c b/fs/ext4/inline.c
index 437df6a1a841..28c5c3abddb3 100644
--- a/fs/ext4/inline.c
+++ b/fs/ext4/inline.c
@@ -61,7 +61,7 @@ static int get_max_inline_xattr_value_size(struct inode *inode,
 
 	/* Compute min_offs. */
 	for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry)) {
-		if (!entry->e_value_block && entry->e_value_size) {
+		if (!entry->e_value_inum && entry->e_value_size) {
 			size_t offs = le16_to_cpu(entry->e_value_offs);
 			if (offs < min_offs)
 				min_offs = offs;
@@ -215,6 +215,9 @@ static void ext4_write_inline_data(struct inode *inode, struct ext4_iloc *iloc,
 	struct ext4_inode *raw_inode;
 	int cp_len = 0;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return;
+
 	BUG_ON(!EXT4_I(inode)->i_inline_off);
 	BUG_ON(pos + len > EXT4_I(inode)->i_inline_size);
 
@@ -381,7 +384,7 @@ out:
 static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
 				    unsigned int len)
 {
-	int ret, size;
+	int ret, size, no_expand;
 	struct ext4_inode_info *ei = EXT4_I(inode);
 
 	if (!ext4_test_inode_state(inode, EXT4_STATE_MAY_INLINE_DATA))
@@ -391,15 +394,14 @@ static int ext4_prepare_inline_data(handle_t *handle, struct inode *inode,
 	if (size < len)
 		return -ENOSPC;
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 
 	if (ei->i_inline_off)
 		ret = ext4_update_inline_data(handle, inode, len);
 	else
 		ret = ext4_create_inline_data(handle, inode, len);
 
-	up_write(&EXT4_I(inode)->xattr_sem);
-
+	ext4_write_unlock_xattr(inode, &no_expand);
 	return ret;
 }
 
@@ -533,7 +535,7 @@ static int ext4_convert_inline_data_to_extent(struct address_space *mapping,
 					      struct inode *inode,
 					      unsigned flags)
 {
-	int ret, needed_blocks;
+	int ret, needed_blocks, no_expand;
 	handle_t *handle = NULL;
 	int retries = 0, sem_held = 0;
 	struct page *page = NULL;
@@ -573,7 +575,7 @@ retry:
 		goto out;
 	}
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	sem_held = 1;
 	/* If some one has already done this for us, just exit. */
 	if (!ext4_has_inline_data(inode)) {
@@ -610,7 +612,7 @@ retry:
 		put_page(page);
 		page = NULL;
 		ext4_orphan_add(handle, inode);
-		up_write(&EXT4_I(inode)->xattr_sem);
+		ext4_write_unlock_xattr(inode, &no_expand);
 		sem_held = 0;
 		ext4_journal_stop(handle);
 		handle = NULL;
@@ -636,7 +638,7 @@ out:
 		put_page(page);
 	}
 	if (sem_held)
-		up_write(&EXT4_I(inode)->xattr_sem);
+		ext4_write_unlock_xattr(inode, &no_expand);
 	if (handle)
 		ext4_journal_stop(handle);
 	brelse(iloc.bh);
@@ -729,7 +731,7 @@ convert:
 int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 			       unsigned copied, struct page *page)
 {
-	int ret;
+	int ret, no_expand;
 	void *kaddr;
 	struct ext4_iloc iloc;
 
@@ -747,7 +749,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 		goto out;
 	}
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	BUG_ON(!ext4_has_inline_data(inode));
 
 	kaddr = kmap_atomic(page);
@@ -757,7 +759,7 @@ int ext4_write_inline_data_end(struct inode *inode, loff_t pos, unsigned len,
 	/* clear page dirty so that writepages wouldn't work for us. */
 	ClearPageDirty(page);
 
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 	brelse(iloc.bh);
 out:
 	return copied;
@@ -768,7 +770,7 @@ ext4_journalled_write_inline_data(struct inode *inode,
 				  unsigned len,
 				  struct page *page)
 {
-	int ret;
+	int ret, no_expand;
 	void *kaddr;
 	struct ext4_iloc iloc;
 
@@ -778,11 +780,11 @@ ext4_journalled_write_inline_data(struct inode *inode,
 		return NULL;
 	}
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	kaddr = kmap_atomic(page);
 	ext4_write_inline_data(inode, &iloc, kaddr, 0, len);
 	kunmap_atomic(kaddr);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 
 	return iloc.bh;
 }
@@ -944,8 +946,15 @@ int ext4_da_write_inline_data_end(struct inode *inode, loff_t pos,
 				  struct page *page)
 {
 	int i_size_changed = 0;
+	int ret;
 
-	copied = ext4_write_inline_data_end(inode, pos, len, copied, page);
+	ret = ext4_write_inline_data_end(inode, pos, len, copied, page);
+	if (ret < 0) {
+		unlock_page(page);
+		put_page(page);
+		return ret;
+	}
+	copied = ret;
 
 	/*
 	 * No need to use i_size_read() here, the i_size
@@ -1025,7 +1034,7 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
 	err = ext4_journal_get_write_access(handle, iloc->bh);
 	if (err)
 		return err;
-	ext4_insert_dentry(dir, inode, de, inline_size, fname);
+	ext4_insert_dentry(inode, de, inline_size, fname);
 
 	ext4_show_inline_dir(dir, iloc->bh, inline_start, inline_size);
 
@@ -1043,7 +1052,6 @@ static int ext4_add_dirent_to_inline(handle_t *handle,
 	dir->i_mtime = dir->i_ctime = current_time(dir);
 	ext4_update_dx_flag(dir);
 	dir->i_version++;
-	ext4_mark_inode_dirty(handle, dir);
 	return 1;
 }
 
@@ -1161,10 +1169,9 @@ static int ext4_finish_convert_inline_dir(handle_t *handle,
 	set_buffer_uptodate(dir_block);
 	err = ext4_handle_dirty_dirent_node(handle, inode, dir_block);
 	if (err)
-		goto out;
+		return err;
 	set_buffer_verified(dir_block);
-out:
-	return err;
+	return ext4_mark_inode_dirty(handle, inode);
 }
 
 static int ext4_convert_inline_data_nolock(handle_t *handle,
@@ -1259,7 +1266,7 @@ out:
 int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
 			      struct inode *dir, struct inode *inode)
 {
-	int ret, inline_size;
+	int ret, inline_size, no_expand;
 	void *inline_start;
 	struct ext4_iloc iloc;
 
@@ -1267,7 +1274,7 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
 	if (ret)
 		return ret;
 
-	down_write(&EXT4_I(dir)->xattr_sem);
+	ext4_write_lock_xattr(dir, &no_expand);
 	if (!ext4_has_inline_data(dir))
 		goto out;
 
@@ -1312,8 +1319,8 @@ int ext4_try_add_inline_entry(handle_t *handle, struct ext4_filename *fname,
 	ret = ext4_convert_inline_data_nolock(handle, dir, &iloc);
 
 out:
+	ext4_write_unlock_xattr(dir, &no_expand);
 	ext4_mark_inode_dirty(handle, dir);
-	up_write(&EXT4_I(dir)->xattr_sem);
 	brelse(iloc.bh);
 	return ret;
 }
@@ -1620,7 +1627,6 @@ out:
 
 struct buffer_head *ext4_find_inline_entry(struct inode *dir,
 					struct ext4_filename *fname,
-					const struct qstr *d_name,
 					struct ext4_dir_entry_2 **res_dir,
 					int *has_inline_data)
 {
@@ -1642,7 +1648,7 @@ struct buffer_head *ext4_find_inline_entry(struct inode *dir,
 						EXT4_INLINE_DOTDOT_SIZE;
 	inline_size = EXT4_MIN_INLINE_DATA_SIZE - EXT4_INLINE_DOTDOT_SIZE;
 	ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
-			      dir, fname, d_name, 0, res_dir);
+			      dir, fname, 0, res_dir);
 	if (ret == 1)
 		goto out_find;
 	if (ret < 0)
@@ -1655,7 +1661,7 @@ struct buffer_head *ext4_find_inline_entry(struct inode *dir,
 	inline_size = ext4_get_inline_size(dir) - EXT4_MIN_INLINE_DATA_SIZE;
 
 	ret = ext4_search_dir(iloc.bh, inline_start, inline_size,
-			      dir, fname, d_name, 0, res_dir);
+			      dir, fname, 0, res_dir);
 	if (ret == 1)
 		goto out_find;
 
@@ -1673,7 +1679,7 @@ int ext4_delete_inline_entry(handle_t *handle,
 			     struct buffer_head *bh,
 			     int *has_inline_data)
 {
-	int err, inline_size;
+	int err, inline_size, no_expand;
 	struct ext4_iloc iloc;
 	void *inline_start;
 
@@ -1681,7 +1687,7 @@ int ext4_delete_inline_entry(handle_t *handle,
 	if (err)
 		return err;
 
-	down_write(&EXT4_I(dir)->xattr_sem);
+	ext4_write_lock_xattr(dir, &no_expand);
 	if (!ext4_has_inline_data(dir)) {
 		*has_inline_data = 0;
 		goto out;
@@ -1709,13 +1715,11 @@ int ext4_delete_inline_entry(handle_t *handle,
 	if (err)
 		goto out;
 
-	err = ext4_mark_inode_dirty(handle, dir);
-	if (unlikely(err))
-		goto out;
-
 	ext4_show_inline_dir(dir, iloc.bh, inline_start, inline_size);
 out:
-	up_write(&EXT4_I(dir)->xattr_sem);
+	ext4_write_unlock_xattr(dir, &no_expand);
+	if (likely(err == 0))
+		err = ext4_mark_inode_dirty(handle, dir);
 	brelse(iloc.bh);
 	if (err != -ENOENT)
 		ext4_std_error(dir->i_sb, err);
@@ -1814,11 +1818,11 @@ out:
 
 int ext4_destroy_inline_data(handle_t *handle, struct inode *inode)
 {
-	int ret;
+	int ret, no_expand;
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	ret = ext4_destroy_inline_data_nolock(handle, inode);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 
 	return ret;
 }
@@ -1900,10 +1904,10 @@ out:
 	return error;
 }
 
-void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
+int ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 {
 	handle_t *handle;
-	int inline_size, value_len, needed_blocks;
+	int inline_size, value_len, needed_blocks, no_expand, err = 0;
 	size_t i_size;
 	void *value = NULL;
 	struct ext4_xattr_ibody_find is = {
@@ -1918,19 +1922,19 @@ void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 	needed_blocks = ext4_writepage_trans_blocks(inode);
 	handle = ext4_journal_start(inode, EXT4_HT_INODE, needed_blocks);
 	if (IS_ERR(handle))
-		return;
+		return PTR_ERR(handle);
 
-	down_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_lock_xattr(inode, &no_expand);
 	if (!ext4_has_inline_data(inode)) {
 		*has_inline = 0;
 		ext4_journal_stop(handle);
-		return;
+		return 0;
 	}
 
-	if (ext4_orphan_add(handle, inode))
+	if ((err = ext4_orphan_add(handle, inode)) != 0)
 		goto out;
 
-	if (ext4_get_inode_loc(inode, &is.iloc))
+	if ((err = ext4_get_inode_loc(inode, &is.iloc)) != 0)
 		goto out;
 
 	down_write(&EXT4_I(inode)->i_data_sem);
@@ -1941,24 +1945,29 @@ void ext4_inline_data_truncate(struct inode *inode, int *has_inline)
 	if (i_size < inline_size) {
 		/* Clear the content in the xattr space. */
 		if (inline_size > EXT4_MIN_INLINE_DATA_SIZE) {
-			if (ext4_xattr_ibody_find(inode, &i, &is))
+			if ((err = ext4_xattr_ibody_find(inode, &i, &is)) != 0)
 				goto out_error;
 
 			BUG_ON(is.s.not_found);
 
 			value_len = le32_to_cpu(is.s.here->e_value_size);
 			value = kmalloc(value_len, GFP_NOFS);
-			if (!value)
+			if (!value) {
+				err = -ENOMEM;
 				goto out_error;
+			}
 
-			if (ext4_xattr_ibody_get(inode, i.name_index, i.name,
-						value, value_len))
+			err = ext4_xattr_ibody_get(inode, i.name_index,
+						   i.name, value, value_len);
+			if (err <= 0)
 				goto out_error;
 
 			i.value = value;
 			i.value_len = i_size > EXT4_MIN_INLINE_DATA_SIZE ?
 					i_size - EXT4_MIN_INLINE_DATA_SIZE : 0;
-			if (ext4_xattr_ibody_inline_set(handle, inode, &i, &is))
+			err = ext4_xattr_ibody_inline_set(handle, inode,
+							  &i, &is);
+			if (err)
 				goto out_error;
 		}
 
@@ -1978,23 +1987,24 @@ out_error:
 	up_write(&EXT4_I(inode)->i_data_sem);
 out:
 	brelse(is.iloc.bh);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 	kfree(value);
 	if (inode->i_nlink)
 		ext4_orphan_del(handle, inode);
 
-	inode->i_mtime = inode->i_ctime = current_time(inode);
-	ext4_mark_inode_dirty(handle, inode);
-	if (IS_SYNC(inode))
-		ext4_handle_sync(handle);
-
+	if (err == 0) {
+		inode->i_mtime = inode->i_ctime = current_time(inode);
+		err = ext4_mark_inode_dirty(handle, inode);
+		if (IS_SYNC(inode))
+			ext4_handle_sync(handle);
+	}
 	ext4_journal_stop(handle);
-	return;
+	return err;
 }
 
 int ext4_convert_inline_data(struct inode *inode)
 {
-	int error, needed_blocks;
+	int error, needed_blocks, no_expand;
 	handle_t *handle;
 	struct ext4_iloc iloc;
 
@@ -2016,15 +2026,10 @@ int ext4_convert_inline_data(struct inode *inode)
 		goto out_free;
 	}
 
-	down_write(&EXT4_I(inode)->xattr_sem);
-	if (!ext4_has_inline_data(inode)) {
-		up_write(&EXT4_I(inode)->xattr_sem);
-		goto out;
-	}
-
-	error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
-	up_write(&EXT4_I(inode)->xattr_sem);
-out:
+	ext4_write_lock_xattr(inode, &no_expand);
+	if (ext4_has_inline_data(inode))
+		error = ext4_convert_inline_data_nolock(handle, inode, &iloc);
+	ext4_write_unlock_xattr(inode, &no_expand);
 	ext4_journal_stop(handle);
 out_free:
 	brelse(iloc.bh);
diff --git a/fs/ext4/inode.c b/fs/ext4/inode.c
index 88d57af1b516..3c600f02673f 100644
--- a/fs/ext4/inode.c
+++ b/fs/ext4/inode.c
@@ -144,16 +144,12 @@ static int ext4_meta_trans_blocks(struct inode *inode, int lblocks,
 
 /*
  * Test whether an inode is a fast symlink.
+ * A fast symlink has its symlink data stored in ext4_inode_info->i_data.
  */
 int ext4_inode_is_fast_symlink(struct inode *inode)
 {
-        int ea_blocks = EXT4_I(inode)->i_file_acl ?
-		EXT4_CLUSTER_SIZE(inode->i_sb) >> 9 : 0;
-
-	if (ext4_has_inline_data(inode))
-		return 0;
-
-	return (S_ISLNK(inode->i_mode) && inode->i_blocks - ea_blocks == 0);
+	return S_ISLNK(inode->i_mode) && inode->i_size &&
+	       (inode->i_size < EXT4_N_BLOCKS * 4);
 }
 
 /*
@@ -189,6 +185,8 @@ void ext4_evict_inode(struct inode *inode)
 {
 	handle_t *handle;
 	int err;
+	int extra_credits = 3;
+	struct ext4_xattr_inode_array *ea_inode_array = NULL;
 
 	trace_ext4_evict_inode(inode);
 
@@ -213,7 +211,8 @@ void ext4_evict_inode(struct inode *inode)
 		 */
 		if (inode->i_ino != EXT4_JOURNAL_INO &&
 		    ext4_should_journal_data(inode) &&
-		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode))) {
+		    (S_ISLNK(inode->i_mode) || S_ISREG(inode->i_mode)) &&
+		    inode->i_data.nrpages) {
 			journal_t *journal = EXT4_SB(inode->i_sb)->s_journal;
 			tid_t commit_tid = EXT4_I(inode)->i_datasync_tid;
 
@@ -238,8 +237,12 @@ void ext4_evict_inode(struct inode *inode)
 	 * protection against it
 	 */
 	sb_start_intwrite(inode->i_sb);
+
+	if (!IS_NOQUOTA(inode))
+		extra_credits += EXT4_MAXQUOTAS_DEL_BLOCKS(inode->i_sb);
+
 	handle = ext4_journal_start(inode, EXT4_HT_TRUNCATE,
-				    ext4_blocks_for_truncate(inode)+3);
+				 ext4_blocks_for_truncate(inode)+extra_credits);
 	if (IS_ERR(handle)) {
 		ext4_std_error(inode->i_sb, PTR_ERR(handle));
 		/*
@@ -254,6 +257,16 @@ void ext4_evict_inode(struct inode *inode)
 
 	if (IS_SYNC(inode))
 		ext4_handle_sync(handle);
+
+	/*
+	 * Set inode->i_size to 0 before calling ext4_truncate(). We need
+	 * special handling of symlinks here because i_size is used to
+	 * determine whether ext4_inode_info->i_data contains symlink data or
+	 * block mappings. Setting i_size to 0 will remove its fast symlink
+	 * status. Erase i_data so that it becomes a valid empty block map.
+	 */
+	if (ext4_inode_is_fast_symlink(inode))
+		memset(EXT4_I(inode)->i_data, 0, sizeof(EXT4_I(inode)->i_data));
 	inode->i_size = 0;
 	err = ext4_mark_inode_dirty(handle, inode);
 	if (err) {
@@ -271,25 +284,17 @@ void ext4_evict_inode(struct inode *inode)
 		}
 	}
 
-	/*
-	 * ext4_ext_truncate() doesn't reserve any slop when it
-	 * restarts journal transactions; therefore there may not be
-	 * enough credits left in the handle to remove the inode from
-	 * the orphan list and set the dtime field.
-	 */
-	if (!ext4_handle_has_enough_credits(handle, 3)) {
-		err = ext4_journal_extend(handle, 3);
-		if (err > 0)
-			err = ext4_journal_restart(handle, 3);
-		if (err != 0) {
-			ext4_warning(inode->i_sb,
-				     "couldn't extend journal (err %d)", err);
-		stop_handle:
-			ext4_journal_stop(handle);
-			ext4_orphan_del(NULL, inode);
-			sb_end_intwrite(inode->i_sb);
-			goto no_delete;
-		}
+	/* Remove xattr references. */
+	err = ext4_xattr_delete_inode(handle, inode, &ea_inode_array,
+				      extra_credits);
+	if (err) {
+		ext4_warning(inode->i_sb, "xattr delete (err %d)", err);
+stop_handle:
+		ext4_journal_stop(handle);
+		ext4_orphan_del(NULL, inode);
+		sb_end_intwrite(inode->i_sb);
+		ext4_xattr_inode_array_free(ea_inode_array);
+		goto no_delete;
 	}
 
 	/*
@@ -317,6 +322,7 @@ void ext4_evict_inode(struct inode *inode)
 		ext4_free_inode(handle, inode);
 	ext4_journal_stop(handle);
 	sb_end_intwrite(inode->i_sb);
+	ext4_xattr_inode_array_free(ea_inode_array);
 	return;
 no_delete:
 	ext4_clear_inode(inode);	/* We must guarantee clearing of inode... */
@@ -710,7 +716,7 @@ out_sem:
 		if (map->m_flags & EXT4_MAP_NEW &&
 		    !(map->m_flags & EXT4_MAP_UNWRITTEN) &&
 		    !(flags & EXT4_GET_BLOCKS_ZERO) &&
-		    !IS_NOQUOTA(inode) &&
+		    !ext4_is_quota_file(inode) &&
 		    ext4_should_order_data(inode)) {
 			if (flags & EXT4_GET_BLOCKS_IO_SUBMIT)
 				ret = ext4_jbd2_inode_add_wait(handle, inode);
@@ -1189,6 +1195,9 @@ static int ext4_write_begin(struct file *file, struct address_space *mapping,
 	pgoff_t index;
 	unsigned from, to;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	trace_ext4_write_begin(inode, pos, len, flags);
 	/*
 	 * Reserve one block more for addition to orphan list in case
@@ -1330,8 +1339,11 @@ static int ext4_write_end(struct file *file,
 	if (ext4_has_inline_data(inode)) {
 		ret = ext4_write_inline_data_end(inode, pos, len,
 						 copied, page);
-		if (ret < 0)
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
 			goto errout;
+		}
 		copied = ret;
 	} else
 		copied = block_write_end(file, mapping, pos,
@@ -1385,7 +1397,9 @@ errout:
  * set the buffer to be dirty, since in data=journalled mode we need
  * to call ext4_handle_dirty_metadata() instead.
  */
-static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
+static void ext4_journalled_zero_new_buffers(handle_t *handle,
+					    struct page *page,
+					    unsigned from, unsigned to)
 {
 	unsigned int block_start = 0, block_end;
 	struct buffer_head *head, *bh;
@@ -1402,7 +1416,7 @@ static void zero_new_buffers(struct page *page, unsigned from, unsigned to)
 					size = min(to, block_end) - start;
 
 					zero_user(page, start, size);
-					set_buffer_uptodate(bh);
+					write_end_fn(handle, bh);
 				}
 				clear_buffer_new(bh);
 			}
@@ -1431,18 +1445,25 @@ static int ext4_journalled_write_end(struct file *file,
 
 	BUG_ON(!ext4_handle_valid(handle));
 
-	if (ext4_has_inline_data(inode))
-		copied = ext4_write_inline_data_end(inode, pos, len,
-						    copied, page);
-	else {
-		if (copied < len) {
-			if (!PageUptodate(page))
-				copied = 0;
-			zero_new_buffers(page, from+copied, to);
+	if (ext4_has_inline_data(inode)) {
+		ret = ext4_write_inline_data_end(inode, pos, len,
+						 copied, page);
+		if (ret < 0) {
+			unlock_page(page);
+			put_page(page);
+			goto errout;
 		}
-
+		copied = ret;
+	} else if (unlikely(copied < len) && !PageUptodate(page)) {
+		copied = 0;
+		ext4_journalled_zero_new_buffers(handle, page, from, to);
+	} else {
+		if (unlikely(copied < len))
+			ext4_journalled_zero_new_buffers(handle, page,
+							 from + copied, to);
 		ret = ext4_walk_page_buffers(handle, page_buffers(page), from,
-					     to, &partial, write_end_fn);
+					     from + copied, &partial,
+					     write_end_fn);
 		if (!partial)
 			SetPageUptodate(page);
 	}
@@ -1468,6 +1489,7 @@ static int ext4_journalled_write_end(struct file *file,
 		 */
 		ext4_orphan_add(handle, inode);
 
+errout:
 	ret2 = ext4_journal_stop(handle);
 	if (!ret)
 		ret = ret2;
@@ -1627,6 +1649,7 @@ struct mpage_da_data {
 	 */
 	struct ext4_map_blocks map;
 	struct ext4_io_submit io_submit;	/* IO submission data */
+	unsigned int do_map:1;
 };
 
 static void mpage_release_unused_pages(struct mpage_da_data *mpd,
@@ -2034,6 +2057,12 @@ static int ext4_writepage(struct page *page,
 	struct ext4_io_submit io_submit;
 	bool keep_towrite = false;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb)))) {
+		ext4_invalidatepage(page, 0, PAGE_SIZE);
+		unlock_page(page);
+		return -EIO;
+	}
+
 	trace_ext4_writepage(page);
 	size = i_size_read(inode);
 	if (page->index == size >> PAGE_SHIFT)
@@ -2101,15 +2130,29 @@ static int ext4_writepage(struct page *page,
 static int mpage_submit_page(struct mpage_da_data *mpd, struct page *page)
 {
 	int len;
-	loff_t size = i_size_read(mpd->inode);
+	loff_t size;
 	int err;
 
 	BUG_ON(page->index != mpd->first_page);
+	clear_page_dirty_for_io(page);
+	/*
+	 * We have to be very careful here!  Nothing protects writeback path
+	 * against i_size changes and the page can be writeably mapped into
+	 * page tables. So an application can be growing i_size and writing
+	 * data through mmap while writeback runs. clear_page_dirty_for_io()
+	 * write-protects our page in page tables and the page cannot get
+	 * written to again until we release page lock. So only after
+	 * clear_page_dirty_for_io() we are safe to sample i_size for
+	 * ext4_bio_write_page() to zero-out tail of the written page. We rely
+	 * on the barrier provided by TestClearPageDirty in
+	 * clear_page_dirty_for_io() to make sure i_size is really sampled only
+	 * after page tables are updated.
+	 */
+	size = i_size_read(mpd->inode);
 	if (page->index == size >> PAGE_SHIFT)
 		len = size & ~PAGE_MASK;
 	else
 		len = PAGE_SIZE;
-	clear_page_dirty_for_io(page);
 	err = ext4_bio_write_page(&mpd->io_submit, page, len, mpd->wbc, false);
 	if (!err)
 		mpd->wbc->nr_to_write--;
@@ -2157,6 +2200,9 @@ static bool mpage_add_bh_to_extent(struct mpage_da_data *mpd, ext4_lblk_t lblk,
 
 	/* First block in the extent? */
 	if (map->m_len == 0) {
+		/* We cannot map unless handle is started... */
+		if (!mpd->do_map)
+			return false;
 		map->m_lblk = lblk;
 		map->m_len = 1;
 		map->m_flags = bh->b_state & BH_FLAGS;
@@ -2199,7 +2245,7 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 {
 	struct inode *inode = mpd->inode;
 	int err;
-	ext4_lblk_t blocks = (i_size_read(inode) + (1 << inode->i_blkbits) - 1)
+	ext4_lblk_t blocks = (i_size_read(inode) + i_blocksize(inode) - 1)
 							>> inode->i_blkbits;
 
 	do {
@@ -2209,6 +2255,9 @@ static int mpage_process_page_bufs(struct mpage_da_data *mpd,
 			/* Found extent to map? */
 			if (mpd->map.m_len)
 				return 0;
+			/* Buffer needs mapping and handle is not started? */
+			if (!mpd->do_map)
+				return 0;
 			/* Everything mapped so far and we hit EOF */
 			break;
 		}
@@ -2409,7 +2458,8 @@ static int mpage_map_and_submit_extent(handle_t *handle,
 		if (err < 0) {
 			struct super_block *sb = inode->i_sb;
 
-			if (EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
+			if (ext4_forced_shutdown(EXT4_SB(sb)) ||
+			    EXT4_SB(sb)->s_mount_flags & EXT4_MF_FS_ABORTED)
 				goto invalidate_dirty_pages;
 			/*
 			 * Let the uper layers retry transient errors.
@@ -2464,8 +2514,8 @@ update_disksize:
 			disksize = i_size;
 		if (disksize > EXT4_I(inode)->i_disksize)
 			EXT4_I(inode)->i_disksize = disksize;
-		err2 = ext4_mark_inode_dirty(handle, inode);
 		up_write(&EXT4_I(inode)->i_data_sem);
+		err2 = ext4_mark_inode_dirty(handle, inode);
 		if (err2)
 			ext4_error(inode->i_sb,
 				   "Failed to mark inode %lu dirty",
@@ -2631,6 +2681,9 @@ static int ext4_writepages(struct address_space *mapping,
 	struct blk_plug plug;
 	bool give_up_on_write = false;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	percpu_down_read(&sbi->s_journal_flag_rwsem);
 	trace_ext4_writepages(inode, wbc);
 
@@ -2667,7 +2720,8 @@ static int ext4_writepages(struct address_space *mapping,
 	 * *never* be called, so if that ever happens, we would want
 	 * the stack trace.
 	 */
-	if (unlikely(sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(mapping->host->i_sb)) ||
+		     sbi->s_mount_flags & EXT4_MF_FS_ABORTED)) {
 		ret = -EROFS;
 		goto out_writepages;
 	}
@@ -2720,6 +2774,29 @@ retry:
 		tag_pages_for_writeback(mapping, mpd.first_page, mpd.last_page);
 	done = false;
 	blk_start_plug(&plug);
+
+	/*
+	 * First writeback pages that don't need mapping - we can avoid
+	 * starting a transaction unnecessarily and also avoid being blocked
+	 * in the block layer on device congestion while having transaction
+	 * started.
+	 */
+	mpd.do_map = 0;
+	mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
+	if (!mpd.io_submit.io_end) {
+		ret = -ENOMEM;
+		goto unplug;
+	}
+	ret = mpage_prepare_extent_to_map(&mpd);
+	/* Submit prepared bio */
+	ext4_io_submit(&mpd.io_submit);
+	ext4_put_io_end_defer(mpd.io_submit.io_end);
+	mpd.io_submit.io_end = NULL;
+	/* Unlock pages we didn't use */
+	mpage_release_unused_pages(&mpd, false);
+	if (ret < 0)
+		goto unplug;
+
 	while (!done && mpd.first_page <= mpd.last_page) {
 		/* For each extent of pages we use new io_end */
 		mpd.io_submit.io_end = ext4_init_io_end(inode, GFP_KERNEL);
@@ -2748,8 +2825,10 @@ retry:
 				wbc->nr_to_write, inode->i_ino, ret);
 			/* Release allocated io_end */
 			ext4_put_io_end(mpd.io_submit.io_end);
+			mpd.io_submit.io_end = NULL;
 			break;
 		}
+		mpd.do_map = 1;
 
 		trace_ext4_da_write_pages(inode, mpd.first_page, mpd.wbc);
 		ret = mpage_prepare_extent_to_map(&mpd);
@@ -2780,6 +2859,7 @@ retry:
 		if (!ext4_handle_valid(handle) || handle->h_sync == 0) {
 			ext4_journal_stop(handle);
 			handle = NULL;
+			mpd.do_map = 0;
 		}
 		/* Submit prepared bio */
 		ext4_io_submit(&mpd.io_submit);
@@ -2797,6 +2877,7 @@ retry:
 			ext4_journal_stop(handle);
 		} else
 			ext4_put_io_end(mpd.io_submit.io_end);
+		mpd.io_submit.io_end = NULL;
 
 		if (ret == -ENOSPC && sbi->s_journal) {
 			/*
@@ -2812,6 +2893,7 @@ retry:
 		if (ret)
 			break;
 	}
+unplug:
 	blk_finish_plug(&plug);
 	if (!ret && !cycled && wbc->nr_to_write > 0) {
 		cycled = 1;
@@ -2892,6 +2974,9 @@ static int ext4_da_write_begin(struct file *file, struct address_space *mapping,
 	struct inode *inode = mapping->host;
 	handle_t *handle;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	index = pos >> PAGE_SHIFT;
 
 	if (ext4_nonda_switch(inode->i_sb) ||
@@ -3275,6 +3360,7 @@ static int ext4_releasepage(struct page *page, gfp_t wait)
 static int ext4_iomap_begin(struct inode *inode, loff_t offset, loff_t length,
 			    unsigned flags, struct iomap *iomap)
 {
+	struct block_device *bdev;
 	unsigned int blkbits = inode->i_blkbits;
 	unsigned long first_block = offset >> blkbits;
 	unsigned long last_block = (offset + length - 1) >> blkbits;
@@ -3343,7 +3429,12 @@ retry:
 	}
 
 	iomap->flags = 0;
-	iomap->bdev = inode->i_sb->s_bdev;
+	bdev = inode->i_sb->s_bdev;
+	iomap->bdev = bdev;
+	if (blk_queue_dax(bdev->bd_queue))
+		iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
+	else
+		iomap->dax_dev = NULL;
 	iomap->offset = first_block << blkbits;
 
 	if (ret == 0) {
@@ -3376,6 +3467,7 @@ static int ext4_iomap_end(struct inode *inode, loff_t offset, loff_t length,
 	int blkbits = inode->i_blkbits;
 	bool truncate = false;
 
+	fs_put_dax(iomap->dax_dev);
 	if (!(flags & IOMAP_WRITE) || (flags & IOMAP_FAULT))
 		return 0;
 
@@ -3420,7 +3512,7 @@ orphan_del:
 	return ret;
 }
 
-struct iomap_ops ext4_iomap_ops = {
+const struct iomap_ops ext4_iomap_ops = {
 	.iomap_begin		= ext4_iomap_begin,
 	.iomap_end		= ext4_iomap_end,
 };
@@ -3547,7 +3639,7 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
 	if (overwrite)
 		get_block_func = ext4_dio_get_block_overwrite;
 	else if (!ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS) ||
-		   round_down(offset, 1 << inode->i_blkbits) >= inode->i_size) {
+		   round_down(offset, i_blocksize(inode)) >= inode->i_size) {
 		get_block_func = ext4_dio_get_block;
 		dio_flags = DIO_LOCKING | DIO_SKIP_HOLES;
 	} else if (is_sync_kiocb(iocb)) {
@@ -3557,9 +3649,6 @@ static ssize_t ext4_direct_IO_write(struct kiocb *iocb, struct iov_iter *iter)
 		get_block_func = ext4_dio_get_block_unwritten_async;
 		dio_flags = DIO_LOCKING;
 	}
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	BUG_ON(ext4_encrypted_inode(inode) && S_ISREG(inode->i_mode));
-#endif
 	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev, iter,
 				   get_block_func, ext4_end_io_dio, NULL,
 				   dio_flags);
@@ -3641,7 +3730,7 @@ static ssize_t ext4_direct_IO_read(struct kiocb *iocb, struct iov_iter *iter)
 	 */
 	inode_lock_shared(inode);
 	ret = filemap_write_and_wait_range(mapping, iocb->ki_pos,
-					   iocb->ki_pos + count);
+					   iocb->ki_pos + count - 1);
 	if (ret)
 		goto out_unlock;
 	ret = __blockdev_direct_IO(iocb, inode, inode->i_sb->s_bdev,
@@ -3914,6 +4003,10 @@ static int ext4_block_truncate_page(handle_t *handle,
 	unsigned blocksize;
 	struct inode *inode = mapping->host;
 
+	/* If we are processing an encrypted inode during orphan list handling */
+	if (ext4_encrypted_inode(inode) && !fscrypt_has_encryption_key(inode))
+		return 0;
+
 	blocksize = inode->i_sb->s_blocksize;
 	length = blocksize - (offset & (blocksize - 1));
 
@@ -4131,6 +4224,8 @@ int ext4_punch_hole(struct inode *inode, loff_t offset, loff_t length)
 
 	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
+	if (ret >= 0)
+		ext4_update_inode_fsync_trans(handle, inode, 1);
 out_stop:
 	ext4_journal_stop(handle);
 out_dio:
@@ -4222,7 +4317,9 @@ int ext4_truncate(struct inode *inode)
 	if (ext4_has_inline_data(inode)) {
 		int has_inline = 1;
 
-		ext4_inline_data_truncate(inode, &has_inline);
+		err = ext4_inline_data_truncate(inode, &has_inline);
+		if (err)
+			return err;
 		if (has_inline)
 			return 0;
 	}
@@ -4466,31 +4563,6 @@ void ext4_set_inode_flags(struct inode *inode)
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC|S_DAX);
 }
 
-/* Propagate flags from i_flags to EXT4_I(inode)->i_flags */
-void ext4_get_inode_flags(struct ext4_inode_info *ei)
-{
-	unsigned int vfs_fl;
-	unsigned long old_fl, new_fl;
-
-	do {
-		vfs_fl = ei->vfs_inode.i_flags;
-		old_fl = ei->i_flags;
-		new_fl = old_fl & ~(EXT4_SYNC_FL|EXT4_APPEND_FL|
-				EXT4_IMMUTABLE_FL|EXT4_NOATIME_FL|
-				EXT4_DIRSYNC_FL);
-		if (vfs_fl & S_SYNC)
-			new_fl |= EXT4_SYNC_FL;
-		if (vfs_fl & S_APPEND)
-			new_fl |= EXT4_APPEND_FL;
-		if (vfs_fl & S_IMMUTABLE)
-			new_fl |= EXT4_IMMUTABLE_FL;
-		if (vfs_fl & S_NOATIME)
-			new_fl |= EXT4_NOATIME_FL;
-		if (vfs_fl & S_DIRSYNC)
-			new_fl |= EXT4_DIRSYNC_FL;
-	} while (cmpxchg(&ei->i_flags, old_fl, new_fl) != old_fl);
-}
-
 static blkcnt_t ext4_inode_blocks(struct ext4_inode *raw_inode,
 				  struct ext4_inode_info *ei)
 {
@@ -4646,7 +4718,7 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	if (ext4_has_feature_64bit(sb))
 		ei->i_file_acl |=
 			((__u64)le16_to_cpu(raw_inode->i_file_acl_high)) << 32;
-	inode->i_size = ext4_isize(raw_inode);
+	inode->i_size = ext4_isize(sb, raw_inode);
 	if ((size = i_size_read(inode)) < 0) {
 		EXT4_ERROR_INODE(inode, "bad i_size value: %lld", size);
 		ret = -EFSCORRUPTED;
@@ -4780,6 +4852,15 @@ struct inode *ext4_iget(struct super_block *sb, unsigned long ino)
 	}
 	brelse(iloc.bh);
 	ext4_set_inode_flags(inode);
+
+	if (ei->i_flags & EXT4_EA_INODE_FL) {
+		ext4_xattr_inode_set_class(inode);
+
+		inode_lock(inode);
+		inode->i_flags |= S_NOQUOTA;
+		inode_unlock(inode);
+	}
+
 	unlock_new_inode(inode);
 	return inode;
 
@@ -4927,7 +5008,6 @@ static int ext4_do_update_inode(handle_t *handle,
 	if (ext4_test_inode_state(inode, EXT4_STATE_NEW))
 		memset(raw_inode, 0, EXT4_SB(inode->i_sb)->s_inode_size);
 
-	ext4_get_inode_flags(ei);
 	raw_inode->i_mode = cpu_to_le16(inode->i_mode);
 	i_uid = i_uid_read(inode);
 	i_gid = i_gid_read(inode);
@@ -4972,7 +5052,7 @@ static int ext4_do_update_inode(handle_t *handle,
 		raw_inode->i_file_acl_high =
 			cpu_to_le16(ei->i_file_acl >> 32);
 	raw_inode->i_file_acl_lo = cpu_to_le32(ei->i_file_acl);
-	if (ei->i_disksize != ext4_isize(raw_inode)) {
+	if (ei->i_disksize != ext4_isize(inode->i_sb, raw_inode)) {
 		ext4_isize_set(raw_inode, ei->i_disksize);
 		need_datasync = 1;
 	}
@@ -5143,7 +5223,7 @@ static void ext4_wait_for_tail_page_commit(struct inode *inode)
 	 * do. We do the check mainly to optimize the common PAGE_SIZE ==
 	 * blocksize case
 	 */
-	if (offset > PAGE_SIZE - (1 << inode->i_blkbits))
+	if (offset > PAGE_SIZE - i_blocksize(inode))
 		return;
 	while (1) {
 		page = find_lock_page(inode->i_mapping,
@@ -5197,6 +5277,9 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 	int orphan = 0;
 	const unsigned int ia_valid = attr->ia_valid;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	error = setattr_prepare(dentry, attr);
 	if (error)
 		return error;
@@ -5219,7 +5302,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 			error = PTR_ERR(handle);
 			goto err_out;
 		}
+
+		/* dquot_transfer() calls back ext4_get_inode_usage() which
+		 * counts xattr inode references.
+		 */
+		down_read(&EXT4_I(inode)->xattr_sem);
 		error = dquot_transfer(inode, attr);
+		up_read(&EXT4_I(inode)->xattr_sem);
+
 		if (error) {
 			ext4_journal_stop(handle);
 			return error;
@@ -5239,6 +5329,14 @@ int ext4_setattr(struct dentry *dentry, struct iattr *attr)
 		loff_t oldsize = inode->i_size;
 		int shrink = (attr->ia_size <= inode->i_size);
 
+		if (ext4_encrypted_inode(inode)) {
+			error = fscrypt_get_encryption_info(inode);
+			if (error)
+				return error;
+			if (!fscrypt_has_encryption_key(inode))
+				return -ENOKEY;
+		}
+
 		if (!(ext4_test_inode_flag(inode, EXT4_INODE_EXTENTS))) {
 			struct ext4_sb_info *sbi = EXT4_SB(inode->i_sb);
 
@@ -5348,20 +5446,55 @@ err_out:
 	return error;
 }
 
-int ext4_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		 struct kstat *stat)
+int ext4_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode;
-	unsigned long long delalloc_blocks;
+	struct inode *inode = d_inode(path->dentry);
+	struct ext4_inode *raw_inode;
+	struct ext4_inode_info *ei = EXT4_I(inode);
+	unsigned int flags;
+
+	if (EXT4_FITS_IN_INODE(raw_inode, ei, i_crtime)) {
+		stat->result_mask |= STATX_BTIME;
+		stat->btime.tv_sec = ei->i_crtime.tv_sec;
+		stat->btime.tv_nsec = ei->i_crtime.tv_nsec;
+	}
+
+	flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
+	if (flags & EXT4_APPEND_FL)
+		stat->attributes |= STATX_ATTR_APPEND;
+	if (flags & EXT4_COMPR_FL)
+		stat->attributes |= STATX_ATTR_COMPRESSED;
+	if (flags & EXT4_ENCRYPT_FL)
+		stat->attributes |= STATX_ATTR_ENCRYPTED;
+	if (flags & EXT4_IMMUTABLE_FL)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+	if (flags & EXT4_NODUMP_FL)
+		stat->attributes |= STATX_ATTR_NODUMP;
+
+	stat->attributes_mask |= (STATX_ATTR_APPEND |
+				  STATX_ATTR_COMPRESSED |
+				  STATX_ATTR_ENCRYPTED |
+				  STATX_ATTR_IMMUTABLE |
+				  STATX_ATTR_NODUMP);
 
-	inode = d_inode(dentry);
 	generic_fillattr(inode, stat);
+	return 0;
+}
+
+int ext4_file_getattr(const struct path *path, struct kstat *stat,
+		      u32 request_mask, unsigned int query_flags)
+{
+	struct inode *inode = d_inode(path->dentry);
+	u64 delalloc_blocks;
+
+	ext4_getattr(path, stat, request_mask, query_flags);
 
 	/*
 	 * If there is inline data in the inode, the inode will normally not
 	 * have data blocks allocated (it may have an external xattr block).
 	 * Report at least one sector for such files, so tools like tar, rsync,
-	 * others doen't incorrectly think the file is completely sparse.
+	 * others don't incorrectly think the file is completely sparse.
 	 */
 	if (unlikely(ext4_has_inline_data(inode)))
 		stat->blocks += (stat->size + 511) >> 9;
@@ -5483,6 +5616,9 @@ int ext4_mark_iloc_dirty(handle_t *handle,
 {
 	int err = 0;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	if (IS_I_VERSION(inode))
 		inode_inc_iversion(inode);
 
@@ -5506,6 +5642,9 @@ ext4_reserve_inode_write(handle_t *handle, struct inode *inode,
 {
 	int err;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	err = ext4_get_inode_loc(inode, iloc);
 	if (!err) {
 		BUFFER_TRACE(iloc->bh, "get_write_access");
@@ -5541,8 +5680,9 @@ static int ext4_expand_extra_isize(struct inode *inode,
 	/* No extended attributes present */
 	if (!ext4_test_inode_state(inode, EXT4_STATE_XATTR) ||
 	    header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)) {
-		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE, 0,
-			new_extra_isize);
+		memset((void *)raw_inode + EXT4_GOOD_OLD_INODE_SIZE +
+		       EXT4_I(inode)->i_extra_isize, 0,
+		       new_extra_isize - EXT4_I(inode)->i_extra_isize);
 		EXT4_I(inode)->i_extra_isize = new_extra_isize;
 		return 0;
 	}
@@ -5776,8 +5916,9 @@ static int ext4_bh_unmapped(handle_t *handle, struct buffer_head *bh)
 	return !buffer_mapped(bh);
 }
 
-int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+int ext4_page_mkwrite(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct page *page = vmf->page;
 	loff_t size;
 	unsigned long len;
@@ -5793,6 +5934,11 @@ int ext4_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	file_update_time(vma->vm_file);
 
 	down_read(&EXT4_I(inode)->i_mmap_sem);
+
+	ret = ext4_convert_inline_data(inode);
+	if (ret)
+		goto out_ret;
+
 	/* Delalloc case is easy... */
 	if (test_opt(inode->i_sb, DELALLOC) &&
 	    !ext4_should_journal_data(inode) &&
@@ -5867,13 +6013,13 @@ out:
 	return ret;
 }
 
-int ext4_filemap_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+int ext4_filemap_fault(struct vm_fault *vmf)
 {
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	int err;
 
 	down_read(&EXT4_I(inode)->i_mmap_sem);
-	err = filemap_fault(vma, vmf);
+	err = filemap_fault(vmf);
 	up_read(&EXT4_I(inode)->i_mmap_sem);
 
 	return err;
diff --git a/fs/ext4/ioctl.c b/fs/ext4/ioctl.c
index d534399cf607..42b3a73143cf 100644
--- a/fs/ext4/ioctl.c
+++ b/fs/ext4/ioctl.c
@@ -16,8 +16,12 @@
 #include <linux/quotaops.h>
 #include <linux/uuid.h>
 #include <linux/uaccess.h>
+#include <linux/delay.h>
 #include "ext4_jbd2.h"
 #include "ext4.h"
+#include <linux/fsmap.h>
+#include "fsmap.h"
+#include <trace/events/ext4.h>
 
 /**
  * Swap memory between @a and @b for @len bytes.
@@ -214,7 +218,7 @@ static int ext4_ioctl_setflags(struct inode *inode,
 	unsigned int jflag;
 
 	/* Is it quota file? Do not allow user to mess with it */
-	if (IS_NOQUOTA(inode))
+	if (ext4_is_quota_file(inode))
 		goto flags_out;
 
 	oldflags = ei->i_flags;
@@ -338,7 +342,7 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
 	err = -EPERM;
 	inode_lock(inode);
 	/* Is it quota file? Do not allow user to mess with it */
-	if (IS_NOQUOTA(inode))
+	if (ext4_is_quota_file(inode))
 		goto out_unlock;
 
 	err = ext4_get_inode_loc(inode, &iloc);
@@ -369,7 +373,13 @@ static int ext4_ioctl_setproject(struct file *filp, __u32 projid)
 
 	transfer_to[PRJQUOTA] = dqget(sb, make_kqid_projid(kprojid));
 	if (!IS_ERR(transfer_to[PRJQUOTA])) {
+
+		/* __dquot_transfer() calls back ext4_get_inode_usage() which
+		 * counts xattr inode references.
+		 */
+		down_read(&EXT4_I(inode)->xattr_sem);
 		err = __dquot_transfer(inode, transfer_to);
+		up_read(&EXT4_I(inode)->xattr_sem);
 		dqput(transfer_to[PRJQUOTA]);
 		if (err)
 			goto out_dirty;
@@ -442,6 +452,136 @@ static inline unsigned long ext4_xflags_to_iflags(__u32 xflags)
 	return iflags;
 }
 
+static int ext4_shutdown(struct super_block *sb, unsigned long arg)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	__u32 flags;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (get_user(flags, (__u32 __user *)arg))
+		return -EFAULT;
+
+	if (flags > EXT4_GOING_FLAGS_NOLOGFLUSH)
+		return -EINVAL;
+
+	if (ext4_forced_shutdown(sbi))
+		return 0;
+
+	ext4_msg(sb, KERN_ALERT, "shut down requested (%d)", flags);
+
+	switch (flags) {
+	case EXT4_GOING_FLAGS_DEFAULT:
+		freeze_bdev(sb->s_bdev);
+		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+		thaw_bdev(sb->s_bdev, sb);
+		break;
+	case EXT4_GOING_FLAGS_LOGFLUSH:
+		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+		if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
+			(void) ext4_force_commit(sb);
+			jbd2_journal_abort(sbi->s_journal, 0);
+		}
+		break;
+	case EXT4_GOING_FLAGS_NOLOGFLUSH:
+		set_bit(EXT4_FLAGS_SHUTDOWN, &sbi->s_ext4_flags);
+		if (sbi->s_journal && !is_journal_aborted(sbi->s_journal)) {
+			msleep(100);
+			jbd2_journal_abort(sbi->s_journal, 0);
+		}
+		break;
+	default:
+		return -EINVAL;
+	}
+	clear_opt(sb, DISCARD);
+	return 0;
+}
+
+struct getfsmap_info {
+	struct super_block	*gi_sb;
+	struct fsmap_head __user *gi_data;
+	unsigned int		gi_idx;
+	__u32			gi_last_flags;
+};
+
+static int ext4_getfsmap_format(struct ext4_fsmap *xfm, void *priv)
+{
+	struct getfsmap_info *info = priv;
+	struct fsmap fm;
+
+	trace_ext4_getfsmap_mapping(info->gi_sb, xfm);
+
+	info->gi_last_flags = xfm->fmr_flags;
+	ext4_fsmap_from_internal(info->gi_sb, &fm, xfm);
+	if (copy_to_user(&info->gi_data->fmh_recs[info->gi_idx++], &fm,
+			sizeof(struct fsmap)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static int ext4_ioc_getfsmap(struct super_block *sb,
+			     struct fsmap_head __user *arg)
+{
+	struct getfsmap_info info = {0};
+	struct ext4_fsmap_head xhead = {0};
+	struct fsmap_head head;
+	bool aborted = false;
+	int error;
+
+	if (copy_from_user(&head, arg, sizeof(struct fsmap_head)))
+		return -EFAULT;
+	if (memchr_inv(head.fmh_reserved, 0, sizeof(head.fmh_reserved)) ||
+	    memchr_inv(head.fmh_keys[0].fmr_reserved, 0,
+		       sizeof(head.fmh_keys[0].fmr_reserved)) ||
+	    memchr_inv(head.fmh_keys[1].fmr_reserved, 0,
+		       sizeof(head.fmh_keys[1].fmr_reserved)))
+		return -EINVAL;
+	/*
+	 * ext4 doesn't report file extents at all, so the only valid
+	 * file offsets are the magic ones (all zeroes or all ones).
+	 */
+	if (head.fmh_keys[0].fmr_offset ||
+	    (head.fmh_keys[1].fmr_offset != 0 &&
+	     head.fmh_keys[1].fmr_offset != -1ULL))
+		return -EINVAL;
+
+	xhead.fmh_iflags = head.fmh_iflags;
+	xhead.fmh_count = head.fmh_count;
+	ext4_fsmap_to_internal(sb, &xhead.fmh_keys[0], &head.fmh_keys[0]);
+	ext4_fsmap_to_internal(sb, &xhead.fmh_keys[1], &head.fmh_keys[1]);
+
+	trace_ext4_getfsmap_low_key(sb, &xhead.fmh_keys[0]);
+	trace_ext4_getfsmap_high_key(sb, &xhead.fmh_keys[1]);
+
+	info.gi_sb = sb;
+	info.gi_data = arg;
+	error = ext4_getfsmap(sb, &xhead, ext4_getfsmap_format, &info);
+	if (error == EXT4_QUERY_RANGE_ABORT) {
+		error = 0;
+		aborted = true;
+	} else if (error)
+		return error;
+
+	/* If we didn't abort, set the "last" flag in the last fmx */
+	if (!aborted && info.gi_idx) {
+		info.gi_last_flags |= FMR_OF_LAST;
+		if (copy_to_user(&info.gi_data->fmh_recs[info.gi_idx - 1].fmr_flags,
+				 &info.gi_last_flags,
+				 sizeof(info.gi_last_flags)))
+			return -EFAULT;
+	}
+
+	/* copy back header */
+	head.fmh_entries = xhead.fmh_entries;
+	head.fmh_oflags = xhead.fmh_oflags;
+	if (copy_to_user(arg, &head, sizeof(struct fsmap_head)))
+		return -EFAULT;
+
+	return 0;
+}
+
 long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
@@ -452,8 +592,9 @@ long ext4_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 	ext4_debug("cmd = %u, arg = %lu\n", cmd, arg);
 
 	switch (cmd) {
+	case FS_IOC_GETFSMAP:
+		return ext4_ioc_getfsmap(sb, (void __user *)arg);
 	case EXT4_IOC_GETFLAGS:
-		ext4_get_inode_flags(ei);
 		flags = ei->i_flags & EXT4_FL_USER_VISIBLE;
 		return put_user(flags, (int __user *) arg);
 	case EXT4_IOC_SETFLAGS: {
@@ -841,7 +982,6 @@ resizefs_out:
 		struct fsxattr fa;
 
 		memset(&fa, 0, sizeof(struct fsxattr));
-		ext4_get_inode_flags(ei);
 		fa.fsx_xflags = ext4_iflags_to_xflags(ei->i_flags & EXT4_FL_USER_VISIBLE);
 
 		if (ext4_has_feature_project(inode->i_sb)) {
@@ -893,6 +1033,8 @@ resizefs_out:
 
 		return 0;
 	}
+	case EXT4_IOC_SHUTDOWN:
+		return ext4_shutdown(sb, arg);
 	default:
 		return -ENOTTY;
 	}
@@ -959,6 +1101,8 @@ long ext4_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case EXT4_IOC_SET_ENCRYPTION_POLICY:
 	case EXT4_IOC_GET_ENCRYPTION_PWSALT:
 	case EXT4_IOC_GET_ENCRYPTION_POLICY:
+	case EXT4_IOC_SHUTDOWN:
+	case FS_IOC_GETFSMAP:
 		break;
 	default:
 		return -ENOIOCTLCMD;
diff --git a/fs/ext4/mballoc.c b/fs/ext4/mballoc.c
index 7ae43c59bc79..581e357e8406 100644
--- a/fs/ext4/mballoc.c
+++ b/fs/ext4/mballoc.c
@@ -357,7 +357,7 @@ static struct kmem_cache *ext4_free_data_cachep;
 #define NR_GRPINFO_CACHES 8
 static struct kmem_cache *ext4_groupinfo_caches[NR_GRPINFO_CACHES];
 
-static const char *ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = {
+static const char * const ext4_groupinfo_slab_names[NR_GRPINFO_CACHES] = {
 	"ext4_groupinfo_1k", "ext4_groupinfo_2k", "ext4_groupinfo_4k",
 	"ext4_groupinfo_8k", "ext4_groupinfo_16k", "ext4_groupinfo_32k",
 	"ext4_groupinfo_64k", "ext4_groupinfo_128k"
@@ -367,8 +367,6 @@ static void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 					ext4_group_t group);
 static void ext4_mb_generate_from_freelist(struct super_block *sb, void *bitmap,
 						ext4_group_t group);
-static void ext4_free_data_callback(struct super_block *sb,
-				struct ext4_journal_cb_entry *jce, int rc);
 
 static inline void *mb_correct_addr_and_bit(int *bit, void *addr)
 {
@@ -838,7 +836,7 @@ static int ext4_mb_init_cache(struct page *page, char *incore, gfp_t gfp)
 	inode = page->mapping->host;
 	sb = inode->i_sb;
 	ngroups = ext4_get_groups_count(sb);
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	blocks_per_page = PAGE_SIZE / blocksize;
 
 	groups_per_page = blocks_per_page >> 1;
@@ -1556,7 +1554,17 @@ static int mb_find_extent(struct ext4_buddy *e4b, int block,
 		ex->fe_len += 1 << order;
 	}
 
-	BUG_ON(ex->fe_start + ex->fe_len > (1 << (e4b->bd_blkbits + 3)));
+	if (ex->fe_start + ex->fe_len > (1 << (e4b->bd_blkbits + 3))) {
+		/* Should never happen! (but apparently sometimes does?!?) */
+		WARN_ON(1);
+		ext4_error(e4b->bd_sb, "corruption or bug in mb_find_extent "
+			   "block=%d, order=%d needed=%d ex=%u/%d/%d@%u",
+			   block, order, needed, ex->fe_group, ex->fe_start,
+			   ex->fe_len, ex->fe_logical);
+		ex->fe_len = 0;
+		ex->fe_start = 0;
+		ex->fe_group = 0;
+	}
 	return ex->fe_len;
 }
 
@@ -2136,8 +2144,10 @@ ext4_mb_regular_allocator(struct ext4_allocation_context *ac)
 	 * We search using buddy data only if the order of the request
 	 * is greater than equal to the sbi_s_mb_order2_reqs
 	 * You can tune it via /sys/fs/ext4/<partition>/mb_order2_req
+	 * We also support searching for power-of-two requests only for
+	 * requests upto maximum buddy size we have constructed.
 	 */
-	if (i >= sbi->s_mb_order2_reqs) {
+	if (i >= sbi->s_mb_order2_reqs && i <= sb->s_blocksize_bits + 2) {
 		/*
 		 * This should tell if fe_len is exactly power of 2
 		 */
@@ -2207,7 +2217,7 @@ repeat:
 			}
 
 			ac->ac_groups_scanned++;
-			if (cr == 0 && ac->ac_2order < sb->s_blocksize_bits+2)
+			if (cr == 0)
 				ext4_mb_simple_scan_group(ac, &e4b);
 			else if (cr == 1 && sbi->s_stripe &&
 					!(ac->ac_g_ex.fe_len % sbi->s_stripe))
@@ -2381,7 +2391,7 @@ int ext4_mb_alloc_groupinfo(struct super_block *sb, ext4_group_t ngroups)
 		return 0;
 
 	size = roundup_pow_of_two(sizeof(*sbi->s_group_info) * size);
-	new_groupinfo = ext4_kvzalloc(size, GFP_KERNEL);
+	new_groupinfo = kvzalloc(size, GFP_KERNEL);
 	if (!new_groupinfo) {
 		ext4_msg(sb, KERN_ERR, "can't allocate buddy meta group");
 		return -ENOMEM;
@@ -2627,6 +2637,7 @@ int ext4_mb_init(struct super_block *sb)
 	spin_lock_init(&sbi->s_md_lock);
 	spin_lock_init(&sbi->s_bal_lock);
 	sbi->s_mb_free_pending = 0;
+	INIT_LIST_HEAD(&sbi->s_freed_data_list);
 
 	sbi->s_mb_max_to_scan = MB_DEFAULT_MAX_TO_SCAN;
 	sbi->s_mb_min_to_scan = MB_DEFAULT_MIN_TO_SCAN;
@@ -2770,7 +2781,8 @@ int ext4_mb_release(struct super_block *sb)
 }
 
 static inline int ext4_issue_discard(struct super_block *sb,
-		ext4_group_t block_group, ext4_grpblk_t cluster, int count)
+		ext4_group_t block_group, ext4_grpblk_t cluster, int count,
+		struct bio **biop)
 {
 	ext4_fsblk_t discard_block;
 
@@ -2779,18 +2791,18 @@ static inline int ext4_issue_discard(struct super_block *sb,
 	count = EXT4_C2B(EXT4_SB(sb), count);
 	trace_ext4_discard_blocks(sb,
 			(unsigned long long) discard_block, count);
-	return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
+	if (biop) {
+		return __blkdev_issue_discard(sb->s_bdev,
+			(sector_t)discard_block << (sb->s_blocksize_bits - 9),
+			(sector_t)count << (sb->s_blocksize_bits - 9),
+			GFP_NOFS, 0, biop);
+	} else
+		return sb_issue_discard(sb, discard_block, count, GFP_NOFS, 0);
 }
 
-/*
- * This function is called by the jbd2 layer once the commit has finished,
- * so we know we can free the blocks that were released with that commit.
- */
-static void ext4_free_data_callback(struct super_block *sb,
-				    struct ext4_journal_cb_entry *jce,
-				    int rc)
+static void ext4_free_data_in_buddy(struct super_block *sb,
+				    struct ext4_free_data *entry)
 {
-	struct ext4_free_data *entry = (struct ext4_free_data *)jce;
 	struct ext4_buddy e4b;
 	struct ext4_group_info *db;
 	int err, count = 0, count2 = 0;
@@ -2798,18 +2810,6 @@ static void ext4_free_data_callback(struct super_block *sb,
 	mb_debug(1, "gonna free %u blocks in group %u (0x%p):",
 		 entry->efd_count, entry->efd_group, entry);
 
-	if (test_opt(sb, DISCARD)) {
-		err = ext4_issue_discard(sb, entry->efd_group,
-					 entry->efd_start_cluster,
-					 entry->efd_count);
-		if (err && err != -EOPNOTSUPP)
-			ext4_msg(sb, KERN_WARNING, "discard request in"
-				 " group:%d block:%d count:%d failed"
-				 " with %d", entry->efd_group,
-				 entry->efd_start_cluster,
-				 entry->efd_count, err);
-	}
-
 	err = ext4_mb_load_buddy(sb, entry->efd_group, &e4b);
 	/* we expect to find existing buddy because it's pinned */
 	BUG_ON(err != 0);
@@ -2850,6 +2850,56 @@ static void ext4_free_data_callback(struct super_block *sb,
 	mb_debug(1, "freed %u blocks in %u structures\n", count, count2);
 }
 
+/*
+ * This function is called by the jbd2 layer once the commit has finished,
+ * so we know we can free the blocks that were released with that commit.
+ */
+void ext4_process_freed_data(struct super_block *sb, tid_t commit_tid)
+{
+	struct ext4_sb_info *sbi = EXT4_SB(sb);
+	struct ext4_free_data *entry, *tmp;
+	struct bio *discard_bio = NULL;
+	struct list_head freed_data_list;
+	struct list_head *cut_pos = NULL;
+	int err;
+
+	INIT_LIST_HEAD(&freed_data_list);
+
+	spin_lock(&sbi->s_md_lock);
+	list_for_each_entry(entry, &sbi->s_freed_data_list, efd_list) {
+		if (entry->efd_tid != commit_tid)
+			break;
+		cut_pos = &entry->efd_list;
+	}
+	if (cut_pos)
+		list_cut_position(&freed_data_list, &sbi->s_freed_data_list,
+				  cut_pos);
+	spin_unlock(&sbi->s_md_lock);
+
+	if (test_opt(sb, DISCARD)) {
+		list_for_each_entry(entry, &freed_data_list, efd_list) {
+			err = ext4_issue_discard(sb, entry->efd_group,
+						 entry->efd_start_cluster,
+						 entry->efd_count,
+						 &discard_bio);
+			if (err && err != -EOPNOTSUPP) {
+				ext4_msg(sb, KERN_WARNING, "discard request in"
+					 " group:%d block:%d count:%d failed"
+					 " with %d", entry->efd_group,
+					 entry->efd_start_cluster,
+					 entry->efd_count, err);
+			} else if (err == -EOPNOTSUPP)
+				break;
+		}
+
+		if (discard_bio)
+			submit_bio_wait(discard_bio);
+	}
+
+	list_for_each_entry_safe(entry, tmp, &freed_data_list, efd_list)
+		ext4_free_data_in_buddy(sb, entry);
+}
+
 int __init ext4_init_mballoc(void)
 {
 	ext4_pspace_cachep = KMEM_CACHE(ext4_prealloc_space,
@@ -3123,6 +3173,13 @@ ext4_mb_normalize_request(struct ext4_allocation_context *ac,
 	if (ar->pright && start + size - 1 >= ar->lright)
 		size -= start + size - ar->lright;
 
+	/*
+	 * Trim allocation request for filesystems with artificially small
+	 * groups.
+	 */
+	if (size > EXT4_BLOCKS_PER_GROUP(ac->ac_sb))
+		size = EXT4_BLOCKS_PER_GROUP(ac->ac_sb);
+
 	end = start + size;
 
 	/* check we don't cross already preallocated blocks */
@@ -3510,7 +3567,7 @@ void ext4_mb_generate_from_pa(struct super_block *sb, void *bitmap,
 		ext4_set_bits(bitmap, start, len);
 		preallocated += len;
 	}
-	mb_debug(1, "prellocated %u for group %u\n", preallocated, group);
+	mb_debug(1, "preallocated %u for group %u\n", preallocated, group);
 }
 
 static void ext4_mb_pa_callback(struct rcu_head *head)
@@ -3868,7 +3925,8 @@ ext4_mb_discard_group_preallocations(struct super_block *sb,
 
 	err = ext4_mb_load_buddy(sb, group, &e4b);
 	if (err) {
-		ext4_error(sb, "Error loading buddy information for %u", group);
+		ext4_warning(sb, "Error %d loading buddy information for %u",
+			     err, group);
 		put_bh(bitmap_bh);
 		return 0;
 	}
@@ -4025,10 +4083,11 @@ repeat:
 		BUG_ON(pa->pa_type != MB_INODE_PA);
 		group = ext4_get_group_number(sb, pa->pa_pstart);
 
-		err = ext4_mb_load_buddy(sb, group, &e4b);
+		err = ext4_mb_load_buddy_gfp(sb, group, &e4b,
+					     GFP_NOFS|__GFP_NOFAIL);
 		if (err) {
-			ext4_error(sb, "Error loading buddy information for %u",
-					group);
+			ext4_error(sb, "Error %d loading buddy information for %u",
+				   err, group);
 			continue;
 		}
 
@@ -4284,11 +4343,14 @@ ext4_mb_discard_lg_preallocations(struct super_block *sb,
 	spin_unlock(&lg->lg_prealloc_lock);
 
 	list_for_each_entry_safe(pa, tmp, &discard_list, u.pa_tmp_list) {
+		int err;
 
 		group = ext4_get_group_number(sb, pa->pa_pstart);
-		if (ext4_mb_load_buddy(sb, group, &e4b)) {
-			ext4_error(sb, "Error loading buddy information for %u",
-					group);
+		err = ext4_mb_load_buddy_gfp(sb, group, &e4b,
+					     GFP_NOFS|__GFP_NOFAIL);
+		if (err) {
+			ext4_error(sb, "Error %d loading buddy information for %u",
+				   err, group);
 			continue;
 		}
 		ext4_lock_group(sb, group);
@@ -4440,7 +4502,7 @@ ext4_fsblk_t ext4_mb_new_blocks(handle_t *handle,
 	trace_ext4_request_blocks(ar);
 
 	/* Allow to use superuser reservation for quota file */
-	if (IS_NOQUOTA(ar->inode))
+	if (ext4_is_quota_file(ar->inode))
 		ar->flags |= EXT4_MB_USE_ROOT_BLOCKS;
 
 	if ((ar->flags & EXT4_MB_DELALLOC_RESERVED) == 0) {
@@ -4559,14 +4621,28 @@ out:
  * are contiguous, AND the extents were freed by the same transaction,
  * AND the blocks are associated with the same group.
  */
-static int can_merge(struct ext4_free_data *entry1,
-			struct ext4_free_data *entry2)
+static void ext4_try_merge_freed_extent(struct ext4_sb_info *sbi,
+					struct ext4_free_data *entry,
+					struct ext4_free_data *new_entry,
+					struct rb_root *entry_rb_root)
 {
-	if ((entry1->efd_tid == entry2->efd_tid) &&
-	    (entry1->efd_group == entry2->efd_group) &&
-	    ((entry1->efd_start_cluster + entry1->efd_count) == entry2->efd_start_cluster))
-		return 1;
-	return 0;
+	if ((entry->efd_tid != new_entry->efd_tid) ||
+	    (entry->efd_group != new_entry->efd_group))
+		return;
+	if (entry->efd_start_cluster + entry->efd_count ==
+	    new_entry->efd_start_cluster) {
+		new_entry->efd_start_cluster = entry->efd_start_cluster;
+		new_entry->efd_count += entry->efd_count;
+	} else if (new_entry->efd_start_cluster + new_entry->efd_count ==
+		   entry->efd_start_cluster) {
+		new_entry->efd_count += entry->efd_count;
+	} else
+		return;
+	spin_lock(&sbi->s_md_lock);
+	list_del(&entry->efd_list);
+	spin_unlock(&sbi->s_md_lock);
+	rb_erase(&entry->efd_node, entry_rb_root);
+	kmem_cache_free(ext4_free_data_cachep, entry);
 }
 
 static noinline_for_stack int
@@ -4622,29 +4698,19 @@ ext4_mb_free_metadata(handle_t *handle, struct ext4_buddy *e4b,
 	node = rb_prev(new_node);
 	if (node) {
 		entry = rb_entry(node, struct ext4_free_data, efd_node);
-		if (can_merge(entry, new_entry) &&
-		    ext4_journal_callback_try_del(handle, &entry->efd_jce)) {
-			new_entry->efd_start_cluster = entry->efd_start_cluster;
-			new_entry->efd_count += entry->efd_count;
-			rb_erase(node, &(db->bb_free_root));
-			kmem_cache_free(ext4_free_data_cachep, entry);
-		}
+		ext4_try_merge_freed_extent(sbi, entry, new_entry,
+					    &(db->bb_free_root));
 	}
 
 	node = rb_next(new_node);
 	if (node) {
 		entry = rb_entry(node, struct ext4_free_data, efd_node);
-		if (can_merge(new_entry, entry) &&
-		    ext4_journal_callback_try_del(handle, &entry->efd_jce)) {
-			new_entry->efd_count += entry->efd_count;
-			rb_erase(node, &(db->bb_free_root));
-			kmem_cache_free(ext4_free_data_cachep, entry);
-		}
+		ext4_try_merge_freed_extent(sbi, entry, new_entry,
+					    &(db->bb_free_root));
 	}
-	/* Add the extent to transaction's private list */
-	new_entry->efd_jce.jce_func = ext4_free_data_callback;
+
 	spin_lock(&sbi->s_md_lock);
-	_ext4_journal_callback_add(handle, &new_entry->efd_jce);
+	list_add_tail(&new_entry->efd_list, &sbi->s_freed_data_list);
 	sbi->s_mb_free_pending += clusters;
 	spin_unlock(&sbi->s_md_lock);
 	return 0;
@@ -4847,7 +4913,8 @@ do_more:
 		 * them with group lock_held
 		 */
 		if (test_opt(sb, DISCARD)) {
-			err = ext4_issue_discard(sb, block_group, bit, count);
+			err = ext4_issue_discard(sb, block_group, bit, count,
+						 NULL);
 			if (err && err != -EOPNOTSUPP)
 				ext4_msg(sb, KERN_WARNING, "discard request in"
 					 " group:%d block:%d count:%lu failed"
@@ -5070,7 +5137,7 @@ __acquires(bitlock)
 	 */
 	mb_mark_used(e4b, &ex);
 	ext4_unlock_group(sb, group);
-	ret = ext4_issue_discard(sb, group, start, count);
+	ret = ext4_issue_discard(sb, group, start, count, NULL);
 	ext4_lock_group(sb, group);
 	mb_free_blocks(NULL, e4b, start, ex.fe_len);
 	return ret;
@@ -5108,8 +5175,8 @@ ext4_trim_all_free(struct super_block *sb, ext4_group_t group,
 
 	ret = ext4_mb_load_buddy(sb, group, &e4b);
 	if (ret) {
-		ext4_error(sb, "Error in loading buddy "
-				"information for %u", group);
+		ext4_warning(sb, "Error %d loading buddy information for %u",
+			     ret, group);
 		return ret;
 	}
 	bitmap = e4b.bd_bitmap;
@@ -5258,3 +5325,52 @@ out:
 	range->len = EXT4_C2B(EXT4_SB(sb), trimmed) << sb->s_blocksize_bits;
 	return ret;
 }
+
+/* Iterate all the free extents in the group. */
+int
+ext4_mballoc_query_range(
+	struct super_block		*sb,
+	ext4_group_t			group,
+	ext4_grpblk_t			start,
+	ext4_grpblk_t			end,
+	ext4_mballoc_query_range_fn	formatter,
+	void				*priv)
+{
+	void				*bitmap;
+	ext4_grpblk_t			next;
+	struct ext4_buddy		e4b;
+	int				error;
+
+	error = ext4_mb_load_buddy(sb, group, &e4b);
+	if (error)
+		return error;
+	bitmap = e4b.bd_bitmap;
+
+	ext4_lock_group(sb, group);
+
+	start = (e4b.bd_info->bb_first_free > start) ?
+		e4b.bd_info->bb_first_free : start;
+	if (end >= EXT4_CLUSTERS_PER_GROUP(sb))
+		end = EXT4_CLUSTERS_PER_GROUP(sb) - 1;
+
+	while (start <= end) {
+		start = mb_find_next_zero_bit(bitmap, end + 1, start);
+		if (start > end)
+			break;
+		next = mb_find_next_bit(bitmap, end + 1, start);
+
+		ext4_unlock_group(sb, group);
+		error = formatter(sb, group, start, next - start, priv);
+		if (error)
+			goto out_unload;
+		ext4_lock_group(sb, group);
+
+		start = next + 1;
+	}
+
+	ext4_unlock_group(sb, group);
+out_unload:
+	ext4_mb_unload_buddy(&e4b);
+
+	return error;
+}
diff --git a/fs/ext4/mballoc.h b/fs/ext4/mballoc.h
index 1aba469f8220..009300ee1561 100644
--- a/fs/ext4/mballoc.h
+++ b/fs/ext4/mballoc.h
@@ -78,10 +78,8 @@ do {									\
 
 
 struct ext4_free_data {
-	/* MUST be the first member */
-	struct ext4_journal_cb_entry	efd_jce;
-
-	/* ext4_free_data private data starts from here */
+	/* this links the free block information from sb_info */
+	struct list_head		efd_list;
 
 	/* this links the free block information from group_info */
 	struct rb_node			efd_node;
@@ -199,4 +197,21 @@ static inline ext4_fsblk_t ext4_grp_offs_to_block(struct super_block *sb,
 	return ext4_group_first_block_no(sb, fex->fe_group) +
 		(fex->fe_start << EXT4_SB(sb)->s_cluster_bits);
 }
+
+typedef int (*ext4_mballoc_query_range_fn)(
+	struct super_block		*sb,
+	ext4_group_t			agno,
+	ext4_grpblk_t			start,
+	ext4_grpblk_t			len,
+	void				*priv);
+
+int
+ext4_mballoc_query_range(
+	struct super_block		*sb,
+	ext4_group_t			agno,
+	ext4_grpblk_t			start,
+	ext4_grpblk_t			end,
+	ext4_mballoc_query_range_fn	formatter,
+	void				*priv);
+
 #endif
diff --git a/fs/ext4/migrate.c b/fs/ext4/migrate.c
index 364ea4d4a943..cf5181b62df1 100644
--- a/fs/ext4/migrate.c
+++ b/fs/ext4/migrate.c
@@ -475,7 +475,7 @@ int ext4_ext_migrate(struct inode *inode)
 	owner[0] = i_uid_read(inode);
 	owner[1] = i_gid_read(inode);
 	tmp_inode = ext4_new_inode(handle, d_inode(inode->i_sb->s_root),
-				   S_IFREG, NULL, goal, owner);
+				   S_IFREG, NULL, goal, owner, 0);
 	if (IS_ERR(tmp_inode)) {
 		retval = PTR_ERR(tmp_inode);
 		ext4_journal_stop(handle);
diff --git a/fs/ext4/move_extent.c b/fs/ext4/move_extent.c
index 6fc14def0c70..9bb36909ec92 100644
--- a/fs/ext4/move_extent.c
+++ b/fs/ext4/move_extent.c
@@ -187,7 +187,7 @@ mext_page_mkuptodate(struct page *page, unsigned from, unsigned to)
 	if (PageUptodate(page))
 		return 0;
 
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, blocksize, 0);
 
@@ -484,7 +484,7 @@ mext_check_arguments(struct inode *orig_inode,
 		return -EBUSY;
 	}
 
-	if (IS_NOQUOTA(orig_inode) || IS_NOQUOTA(donor_inode)) {
+	if (ext4_is_quota_file(orig_inode) && ext4_is_quota_file(donor_inode)) {
 		ext4_debug("ext4 move extent: The argument files should "
 			"not be quota files [ino:orig %lu, donor %lu]\n",
 			orig_inode->i_ino, donor_inode->i_ino);
@@ -511,7 +511,7 @@ mext_check_arguments(struct inode *orig_inode,
 	if ((orig_start & ~(PAGE_MASK >> orig_inode->i_blkbits)) !=
 	    (donor_start & ~(PAGE_MASK >> orig_inode->i_blkbits))) {
 		ext4_debug("ext4 move extent: orig and donor's start "
-			"offset are not alligned [ino:orig %lu, donor %lu]\n",
+			"offsets are not aligned [ino:orig %lu, donor %lu]\n",
 			orig_inode->i_ino, donor_inode->i_ino);
 		return -EINVAL;
 	}
diff --git a/fs/ext4/namei.c b/fs/ext4/namei.c
index eadba919f26b..13f0cadb1238 100644
--- a/fs/ext4/namei.c
+++ b/fs/ext4/namei.c
@@ -513,7 +513,7 @@ ext4_next_entry(struct ext4_dir_entry_2 *p, unsigned long blocksize)
 
 static inline ext4_lblk_t dx_get_block(struct dx_entry *entry)
 {
-	return le32_to_cpu(entry->block) & 0x00ffffff;
+	return le32_to_cpu(entry->block) & 0x0fffffff;
 }
 
 static inline void dx_set_block(struct dx_entry *entry, ext4_lblk_t value)
@@ -739,6 +739,7 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
 	struct dx_frame *ret_err = ERR_PTR(ERR_BAD_DX_DIR);
 	u32 hash;
 
+	memset(frame_in, 0, EXT4_HTREE_LEVEL * sizeof(frame_in[0]));
 	frame->bh = ext4_read_dirblock(dir, 0, INDEX);
 	if (IS_ERR(frame->bh))
 		return (struct dx_frame *) frame->bh;
@@ -768,9 +769,15 @@ dx_probe(struct ext4_filename *fname, struct inode *dir,
 	}
 
 	indirect = root->info.indirect_levels;
-	if (indirect > 1) {
-		ext4_warning_inode(dir, "Unimplemented hash depth: %#06x",
-				   root->info.indirect_levels);
+	if (indirect >= ext4_dir_htree_level(dir->i_sb)) {
+		ext4_warning(dir->i_sb,
+			     "Directory (ino: %lu) htree depth %#06x exceed"
+			     "supported value", dir->i_ino,
+			     ext4_dir_htree_level(dir->i_sb));
+		if (ext4_dir_htree_level(dir->i_sb) < EXT4_HTREE_LEVEL) {
+			ext4_warning(dir->i_sb, "Enable large directory "
+						"feature to access it");
+		}
 		goto fail;
 	}
 
@@ -859,12 +866,19 @@ fail:
 
 static void dx_release(struct dx_frame *frames)
 {
+	struct dx_root_info *info;
+	int i;
+
 	if (frames[0].bh == NULL)
 		return;
 
-	if (((struct dx_root *)frames[0].bh->b_data)->info.indirect_levels)
-		brelse(frames[1].bh);
-	brelse(frames[0].bh);
+	info = &((struct dx_root *)frames[0].bh->b_data)->info;
+	for (i = 0; i <= info->indirect_levels; i++) {
+		if (frames[i].bh == NULL)
+			break;
+		brelse(frames[i].bh);
+		frames[i].bh = NULL;
+	}
 }
 
 /*
@@ -1050,7 +1064,7 @@ int ext4_htree_fill_tree(struct file *dir_file, __u32 start_hash,
 {
 	struct dx_hash_info hinfo;
 	struct ext4_dir_entry_2 *de;
-	struct dx_frame frames[2], *frame;
+	struct dx_frame frames[EXT4_HTREE_LEVEL], *frame;
 	struct inode *dir;
 	ext4_lblk_t block;
 	int count = 0;
@@ -1155,12 +1169,11 @@ errout:
 static inline int search_dirblock(struct buffer_head *bh,
 				  struct inode *dir,
 				  struct ext4_filename *fname,
-				  const struct qstr *d_name,
 				  unsigned int offset,
 				  struct ext4_dir_entry_2 **res_dir)
 {
 	return ext4_search_dir(bh, bh->b_data, dir->i_sb->s_blocksize, dir,
-			       fname, d_name, offset, res_dir);
+			       fname, offset, res_dir);
 }
 
 /*
@@ -1237,37 +1250,24 @@ static void dx_insert_block(struct dx_frame *frame, u32 hash, ext4_lblk_t block)
 }
 
 /*
- * NOTE! unlike strncmp, ext4_match returns 1 for success, 0 for failure.
+ * Test whether a directory entry matches the filename being searched for.
  *
- * `len <= EXT4_NAME_LEN' is guaranteed by caller.
- * `de != NULL' is guaranteed by caller.
+ * Return: %true if the directory entry matches, otherwise %false.
  */
-static inline int ext4_match(struct ext4_filename *fname,
-			     struct ext4_dir_entry_2 *de)
+static inline bool ext4_match(const struct ext4_filename *fname,
+			      const struct ext4_dir_entry_2 *de)
 {
-	const void *name = fname_name(fname);
-	u32 len = fname_len(fname);
+	struct fscrypt_name f;
 
 	if (!de->inode)
-		return 0;
+		return false;
 
+	f.usr_fname = fname->usr_fname;
+	f.disk_name = fname->disk_name;
 #ifdef CONFIG_EXT4_FS_ENCRYPTION
-	if (unlikely(!name)) {
-		if (fname->usr_fname->name[0] == '_') {
-			int ret;
-			if (de->name_len < 16)
-				return 0;
-			ret = memcmp(de->name + de->name_len - 16,
-				     fname->crypto_buf.name + 8, 16);
-			return (ret == 0) ? 1 : 0;
-		}
-		name = fname->crypto_buf.name;
-		len = fname->crypto_buf.len;
-	}
+	f.crypto_buf = fname->crypto_buf;
 #endif
-	if (de->name_len != len)
-		return 0;
-	return (memcmp(de->name, name, len) == 0) ? 1 : 0;
+	return fscrypt_match_name(&f, de->name, de->name_len);
 }
 
 /*
@@ -1275,54 +1275,36 @@ static inline int ext4_match(struct ext4_filename *fname,
  */
 int ext4_search_dir(struct buffer_head *bh, char *search_buf, int buf_size,
 		    struct inode *dir, struct ext4_filename *fname,
-		    const struct qstr *d_name,
 		    unsigned int offset, struct ext4_dir_entry_2 **res_dir)
 {
 	struct ext4_dir_entry_2 * de;
 	char * dlimit;
 	int de_len;
-	int res;
 
 	de = (struct ext4_dir_entry_2 *)search_buf;
 	dlimit = search_buf + buf_size;
 	while ((char *) de < dlimit) {
 		/* this code is executed quadratically often */
 		/* do minimal checking `by hand' */
-		if ((char *) de + de->name_len <= dlimit) {
-			res = ext4_match(fname, de);
-			if (res < 0) {
-				res = -1;
-				goto return_result;
-			}
-			if (res > 0) {
-				/* found a match - just to be sure, do
-				 * a full check */
-				if (ext4_check_dir_entry(dir, NULL, de, bh,
-						bh->b_data,
-						 bh->b_size, offset)) {
-					res = -1;
-					goto return_result;
-				}
-				*res_dir = de;
-				res = 1;
-				goto return_result;
-			}
-
+		if ((char *) de + de->name_len <= dlimit &&
+		    ext4_match(fname, de)) {
+			/* found a match - just to be sure, do
+			 * a full check */
+			if (ext4_check_dir_entry(dir, NULL, de, bh, bh->b_data,
+						 bh->b_size, offset))
+				return -1;
+			*res_dir = de;
+			return 1;
 		}
 		/* prevent looping on a bad block */
 		de_len = ext4_rec_len_from_disk(de->rec_len,
 						dir->i_sb->s_blocksize);
-		if (de_len <= 0) {
-			res = -1;
-			goto return_result;
-		}
+		if (de_len <= 0)
+			return -1;
 		offset += de_len;
 		de = (struct ext4_dir_entry_2 *) ((char *) de + de_len);
 	}
-
-	res = 0;
-return_result:
-	return res;
+	return 0;
 }
 
 static int is_dx_internal_node(struct inode *dir, ext4_lblk_t block,
@@ -1378,12 +1360,14 @@ static struct buffer_head * ext4_find_entry (struct inode *dir,
 		return NULL;
 
 	retval = ext4_fname_setup_filename(dir, d_name, 1, &fname);
+	if (retval == -ENOENT)
+		return NULL;
 	if (retval)
 		return ERR_PTR(retval);
 
 	if (ext4_has_inline_data(dir)) {
 		int has_inline_data = 1;
-		ret = ext4_find_inline_entry(dir, &fname, d_name, res_dir,
+		ret = ext4_find_inline_entry(dir, &fname, res_dir,
 					     &has_inline_data);
 		if (has_inline_data) {
 			if (inlined)
@@ -1458,11 +1442,11 @@ restart:
 			goto next;
 		wait_on_buffer(bh);
 		if (!buffer_uptodate(bh)) {
-			/* read error, skip block & hope for the best */
 			EXT4_ERROR_INODE(dir, "reading directory lblock %lu",
 					 (unsigned long) block);
 			brelse(bh);
-			goto next;
+			ret = ERR_PTR(-EIO);
+			goto cleanup_and_exit;
 		}
 		if (!buffer_verified(bh) &&
 		    !is_dx_internal_node(dir, block,
@@ -1472,10 +1456,11 @@ restart:
 			EXT4_ERROR_INODE(dir, "checksumming directory "
 					 "block %lu", (unsigned long)block);
 			brelse(bh);
-			goto next;
+			ret = ERR_PTR(-EFSBADCRC);
+			goto cleanup_and_exit;
 		}
 		set_buffer_verified(bh);
-		i = search_dirblock(bh, dir, &fname, d_name,
+		i = search_dirblock(bh, dir, &fname,
 			    block << EXT4_BLOCK_SIZE_BITS(sb), res_dir);
 		if (i == 1) {
 			EXT4_I(dir)->i_dir_start_lookup = block;
@@ -1515,8 +1500,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
 			struct ext4_dir_entry_2 **res_dir)
 {
 	struct super_block * sb = dir->i_sb;
-	struct dx_frame frames[2], *frame;
-	const struct qstr *d_name = fname->usr_fname;
+	struct dx_frame frames[EXT4_HTREE_LEVEL], *frame;
 	struct buffer_head *bh;
 	ext4_lblk_t block;
 	int retval;
@@ -1533,7 +1517,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
 		if (IS_ERR(bh))
 			goto errout;
 
-		retval = search_dirblock(bh, dir, fname, d_name,
+		retval = search_dirblock(bh, dir, fname,
 					 block << EXT4_BLOCK_SIZE_BITS(sb),
 					 res_dir);
 		if (retval == 1)
@@ -1558,7 +1542,7 @@ static struct buffer_head * ext4_dx_find_entry(struct inode *dir,
 
 	bh = NULL;
 errout:
-	dxtrace(printk(KERN_DEBUG "%s not found\n", d_name->name));
+	dxtrace(printk(KERN_DEBUG "%s not found\n", fname->usr_fname->name));
 success:
 	dx_release(frames);
 	return bh;
@@ -1614,15 +1598,10 @@ static struct dentry *ext4_lookup(struct inode *dir, struct dentry *dentry, unsi
 		if (!IS_ERR(inode) && ext4_encrypted_inode(dir) &&
 		    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
 		    !fscrypt_has_permitted_context(dir, inode)) {
-			int nokey = ext4_encrypted_inode(inode) &&
-				!fscrypt_has_encryption_key(inode);
-			iput(inode);
-			if (nokey)
-				return ERR_PTR(-ENOKEY);
 			ext4_warning(inode->i_sb,
 				     "Inconsistent encryption contexts: %lu/%lu",
-				     (unsigned long) dir->i_ino,
-				     (unsigned long) inode->i_ino);
+				     dir->i_ino, inode->i_ino);
+			iput(inode);
 			return ERR_PTR(-EPERM);
 		}
 	}
@@ -1829,24 +1808,15 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode,
 	int nlen, rlen;
 	unsigned int offset = 0;
 	char *top;
-	int res;
 
 	de = (struct ext4_dir_entry_2 *)buf;
 	top = buf + buf_size - reclen;
 	while ((char *) de <= top) {
 		if (ext4_check_dir_entry(dir, NULL, de, bh,
-					 buf, buf_size, offset)) {
-			res = -EFSCORRUPTED;
-			goto return_result;
-		}
-		/* Provide crypto context and crypto buffer to ext4 match */
-		res = ext4_match(fname, de);
-		if (res < 0)
-			goto return_result;
-		if (res > 0) {
-			res = -EEXIST;
-			goto return_result;
-		}
+					 buf, buf_size, offset))
+			return -EFSCORRUPTED;
+		if (ext4_match(fname, de))
+			return -EEXIST;
 		nlen = EXT4_DIR_REC_LEN(de->name_len);
 		rlen = ext4_rec_len_from_disk(de->rec_len, buf_size);
 		if ((de->inode ? rlen - nlen : rlen) >= reclen)
@@ -1854,22 +1824,17 @@ int ext4_find_dest_de(struct inode *dir, struct inode *inode,
 		de = (struct ext4_dir_entry_2 *)((char *)de + rlen);
 		offset += rlen;
 	}
-
 	if ((char *) de > top)
-		res = -ENOSPC;
-	else {
-		*dest_de = de;
-		res = 0;
-	}
-return_result:
-	return res;
+		return -ENOSPC;
+
+	*dest_de = de;
+	return 0;
 }
 
-int ext4_insert_dentry(struct inode *dir,
-		       struct inode *inode,
-		       struct ext4_dir_entry_2 *de,
-		       int buf_size,
-		       struct ext4_filename *fname)
+void ext4_insert_dentry(struct inode *inode,
+			struct ext4_dir_entry_2 *de,
+			int buf_size,
+			struct ext4_filename *fname)
 {
 
 	int nlen, rlen;
@@ -1888,7 +1853,6 @@ int ext4_insert_dentry(struct inode *dir,
 	ext4_set_de_type(inode->i_sb, de, inode->i_mode);
 	de->name_len = fname_len(fname);
 	memcpy(de->name, fname_name(fname), fname_len(fname));
-	return 0;
 }
 
 /*
@@ -1924,11 +1888,8 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
 		return err;
 	}
 
-	/* By now the buffer is marked for journaling. Due to crypto operations,
-	 * the following function call may fail */
-	err = ext4_insert_dentry(dir, inode, de, blocksize, fname);
-	if (err < 0)
-		return err;
+	/* By now the buffer is marked for journaling */
+	ext4_insert_dentry(inode, de, blocksize, fname);
 
 	/*
 	 * XXX shouldn't update any times until successful
@@ -1943,7 +1904,7 @@ static int add_dirent_to_buf(handle_t *handle, struct ext4_filename *fname,
 	 */
 	dir->i_mtime = dir->i_ctime = current_time(dir);
 	ext4_update_dx_flag(dir);
-	dir->i_version++;
+	inode_inc_iversion(dir);
 	ext4_mark_inode_dirty(handle, dir);
 	BUFFER_TRACE(bh, "call ext4_handle_dirty_metadata");
 	err = ext4_handle_dirty_dirent_node(handle, dir, bh);
@@ -1962,7 +1923,7 @@ static int make_indexed_dir(handle_t *handle, struct ext4_filename *fname,
 {
 	struct buffer_head *bh2;
 	struct dx_root	*root;
-	struct dx_frame	frames[2], *frame;
+	struct dx_frame	frames[EXT4_HTREE_LEVEL], *frame;
 	struct dx_entry *entries;
 	struct ext4_dir_entry_2	*de, *de2;
 	struct ext4_dir_entry_tail *t;
@@ -2181,13 +2142,16 @@ out:
 static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 			     struct inode *dir, struct inode *inode)
 {
-	struct dx_frame frames[2], *frame;
+	struct dx_frame frames[EXT4_HTREE_LEVEL], *frame;
 	struct dx_entry *entries, *at;
 	struct buffer_head *bh;
 	struct super_block *sb = dir->i_sb;
 	struct ext4_dir_entry_2 *de;
+	int restart;
 	int err;
 
+again:
+	restart = 0;
 	frame = dx_probe(fname, dir, NULL, frames);
 	if (IS_ERR(frame))
 		return PTR_ERR(frame);
@@ -2209,24 +2173,44 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 	if (err != -ENOSPC)
 		goto cleanup;
 
+	err = 0;
 	/* Block full, should compress but for now just split */
 	dxtrace(printk(KERN_DEBUG "using %u of %u node entries\n",
 		       dx_get_count(entries), dx_get_limit(entries)));
 	/* Need to split index? */
 	if (dx_get_count(entries) == dx_get_limit(entries)) {
 		ext4_lblk_t newblock;
-		unsigned icount = dx_get_count(entries);
-		int levels = frame - frames;
+		int levels = frame - frames + 1;
+		unsigned int icount;
+		int add_level = 1;
 		struct dx_entry *entries2;
 		struct dx_node *node2;
 		struct buffer_head *bh2;
 
-		if (levels && (dx_get_count(frames->entries) ==
-			       dx_get_limit(frames->entries))) {
-			ext4_warning_inode(dir, "Directory index full!");
+		while (frame > frames) {
+			if (dx_get_count((frame - 1)->entries) <
+			    dx_get_limit((frame - 1)->entries)) {
+				add_level = 0;
+				break;
+			}
+			frame--; /* split higher index block */
+			at = frame->at;
+			entries = frame->entries;
+			restart = 1;
+		}
+		if (add_level && levels == ext4_dir_htree_level(sb)) {
+			ext4_warning(sb, "Directory (ino: %lu) index full, "
+					 "reach max htree level :%d",
+					 dir->i_ino, levels);
+			if (ext4_dir_htree_level(sb) < EXT4_HTREE_LEVEL) {
+				ext4_warning(sb, "Large directory feature is "
+						 "not enabled on this "
+						 "filesystem");
+			}
 			err = -ENOSPC;
 			goto cleanup;
 		}
+		icount = dx_get_count(entries);
 		bh2 = ext4_append(handle, dir, &newblock);
 		if (IS_ERR(bh2)) {
 			err = PTR_ERR(bh2);
@@ -2241,7 +2225,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 		err = ext4_journal_get_write_access(handle, frame->bh);
 		if (err)
 			goto journal_error;
-		if (levels) {
+		if (!add_level) {
 			unsigned icount1 = icount/2, icount2 = icount - icount1;
 			unsigned hash2 = dx_get_hash(entries + icount1);
 			dxtrace(printk(KERN_DEBUG "Split index %i/%i\n",
@@ -2249,7 +2233,7 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 
 			BUFFER_TRACE(frame->bh, "get_write_access"); /* index root */
 			err = ext4_journal_get_write_access(handle,
-							     frames[0].bh);
+							     (frame - 1)->bh);
 			if (err)
 				goto journal_error;
 
@@ -2265,17 +2249,25 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 				frame->entries = entries = entries2;
 				swap(frame->bh, bh2);
 			}
-			dx_insert_block(frames + 0, hash2, newblock);
-			dxtrace(dx_show_index("node", frames[1].entries));
+			dx_insert_block((frame - 1), hash2, newblock);
+			dxtrace(dx_show_index("node", frame->entries));
 			dxtrace(dx_show_index("node",
 			       ((struct dx_node *) bh2->b_data)->entries));
 			err = ext4_handle_dirty_dx_node(handle, dir, bh2);
 			if (err)
 				goto journal_error;
 			brelse (bh2);
+			err = ext4_handle_dirty_dx_node(handle, dir,
+						   (frame - 1)->bh);
+			if (err)
+				goto journal_error;
+			if (restart) {
+				err = ext4_handle_dirty_dx_node(handle, dir,
+							   frame->bh);
+				goto journal_error;
+			}
 		} else {
-			dxtrace(printk(KERN_DEBUG
-				       "Creating second level index...\n"));
+			struct dx_root *dxroot;
 			memcpy((char *) entries2, (char *) entries,
 			       icount * sizeof(struct dx_entry));
 			dx_set_limit(entries2, dx_node_limit(dir));
@@ -2283,22 +2275,18 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 			/* Set up root */
 			dx_set_count(entries, 1);
 			dx_set_block(entries + 0, newblock);
-			((struct dx_root *) frames[0].bh->b_data)->info.indirect_levels = 1;
-
-			/* Add new access path frame */
-			frame = frames + 1;
-			frame->at = at = at - entries + entries2;
-			frame->entries = entries = entries2;
-			frame->bh = bh2;
-			err = ext4_journal_get_write_access(handle,
-							     frame->bh);
+			dxroot = (struct dx_root *)frames[0].bh->b_data;
+			dxroot->info.indirect_levels += 1;
+			dxtrace(printk(KERN_DEBUG
+				       "Creating %d level index...\n",
+				       info->indirect_levels));
+			err = ext4_handle_dirty_dx_node(handle, dir, frame->bh);
 			if (err)
 				goto journal_error;
-		}
-		err = ext4_handle_dirty_dx_node(handle, dir, frames[0].bh);
-		if (err) {
-			ext4_std_error(inode->i_sb, err);
-			goto cleanup;
+			err = ext4_handle_dirty_dx_node(handle, dir, bh2);
+			brelse(bh2);
+			restart = 1;
+			goto journal_error;
 		}
 	}
 	de = do_split(handle, dir, &bh, frame, &fname->hinfo);
@@ -2310,10 +2298,15 @@ static int ext4_dx_add_entry(handle_t *handle, struct ext4_filename *fname,
 	goto cleanup;
 
 journal_error:
-	ext4_std_error(dir->i_sb, err);
+	ext4_std_error(dir->i_sb, err); /* this is a no-op if err == 0 */
 cleanup:
 	brelse(bh);
 	dx_release(frames);
+	/* @restart is true means htree-path has been changed, we need to
+	 * repeat dx_probe() to find out valid htree-path
+	 */
+	if (restart && err == 0)
+		goto again;
 	return err;
 }
 
@@ -2350,7 +2343,7 @@ int ext4_generic_delete_entry(handle_t *handle,
 					blocksize);
 			else
 				de->inode = 0;
-			dir->i_version++;
+			inode_inc_iversion(dir);
 			return 0;
 		}
 		i += ext4_rec_len_from_disk(de->rec_len, blocksize);
@@ -2935,6 +2928,9 @@ static int ext4_rmdir(struct inode *dir, struct dentry *dentry)
 	struct ext4_dir_entry_2 *de;
 	handle_t *handle = NULL;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+		return -EIO;
+
 	/* Initialize quotas before so that eventual writes go in
 	 * separate transaction */
 	retval = dquot_initialize(dir);
@@ -3008,6 +3004,9 @@ static int ext4_unlink(struct inode *dir, struct dentry *dentry)
 	struct ext4_dir_entry_2 *de;
 	handle_t *handle = NULL;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+		return -EIO;
+
 	trace_ext4_unlink_enter(dir, dentry);
 	/* Initialize quotas before so that eventual writes go
 	 * in separate transaction */
@@ -3078,6 +3077,9 @@ static int ext4_symlink(struct inode *dir,
 	struct fscrypt_str disk_link;
 	struct fscrypt_symlink_data *sd = NULL;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(dir->i_sb))))
+		return -EIO;
+
 	disk_link.len = len + 1;
 	disk_link.name = (char *) symname;
 
@@ -3088,7 +3090,7 @@ static int ext4_symlink(struct inode *dir,
 		if (err)
 			return err;
 		if (!fscrypt_has_encryption_key(dir))
-			return -EPERM;
+			return -ENOKEY;
 		disk_link.len = (fscrypt_fname_encrypted_size(dir, len) +
 				 sizeof(struct fscrypt_symlink_data));
 		sd = kzalloc(disk_link.len, GFP_KERNEL);
@@ -3525,6 +3527,12 @@ static int ext4_rename(struct inode *old_dir, struct dentry *old_dentry,
 			EXT4_I(old_dentry->d_inode)->i_projid)))
 		return -EXDEV;
 
+	if ((ext4_encrypted_inode(old_dir) &&
+	     !fscrypt_has_encryption_key(old_dir)) ||
+	    (ext4_encrypted_inode(new_dir) &&
+	     !fscrypt_has_encryption_key(new_dir)))
+		return -ENOKEY;
+
 	retval = dquot_initialize(old.dir);
 	if (retval)
 		return retval;
@@ -3725,6 +3733,12 @@ static int ext4_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int retval;
 	struct timespec ctime;
 
+	if ((ext4_encrypted_inode(old_dir) &&
+	     !fscrypt_has_encryption_key(old_dir)) ||
+	    (ext4_encrypted_inode(new_dir) &&
+	     !fscrypt_has_encryption_key(new_dir)))
+		return -ENOKEY;
+
 	if ((ext4_encrypted_inode(old_dir) ||
 	     ext4_encrypted_inode(new_dir)) &&
 	    (old_dir != new_dir) &&
@@ -3858,6 +3872,9 @@ static int ext4_rename2(struct inode *old_dir, struct dentry *old_dentry,
 			struct inode *new_dir, struct dentry *new_dentry,
 			unsigned int flags)
 {
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(old_dir->i_sb))))
+		return -EIO;
+
 	if (flags & ~(RENAME_NOREPLACE | RENAME_EXCHANGE | RENAME_WHITEOUT))
 		return -EINVAL;
 
@@ -3884,6 +3901,7 @@ const struct inode_operations ext4_dir_inode_operations = {
 	.tmpfile	= ext4_tmpfile,
 	.rename		= ext4_rename2,
 	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
 	.listxattr	= ext4_listxattr,
 	.get_acl	= ext4_get_acl,
 	.set_acl	= ext4_set_acl,
@@ -3892,6 +3910,7 @@ const struct inode_operations ext4_dir_inode_operations = {
 
 const struct inode_operations ext4_special_inode_operations = {
 	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
 	.listxattr	= ext4_listxattr,
 	.get_acl	= ext4_get_acl,
 	.set_acl	= ext4_set_acl,
diff --git a/fs/ext4/page-io.c b/fs/ext4/page-io.c
index d83b0f3c5fe9..c2fce4478cca 100644
--- a/fs/ext4/page-io.c
+++ b/fs/ext4/page-io.c
@@ -24,7 +24,6 @@
 #include <linux/slab.h>
 #include <linux/mm.h>
 #include <linux/backing-dev.h>
-#include <linux/fscrypto.h>
 
 #include "ext4_jbd2.h"
 #include "xattr.h"
@@ -86,7 +85,7 @@ static void ext4_finish_bio(struct bio *bio)
 		}
 #endif
 
-		if (bio->bi_error) {
+		if (bio->bi_status) {
 			SetPageError(page);
 			mapping_set_error(page->mapping, -EIO);
 		}
@@ -105,7 +104,7 @@ static void ext4_finish_bio(struct bio *bio)
 				continue;
 			}
 			clear_buffer_async_write(bh);
-			if (bio->bi_error)
+			if (bio->bi_status)
 				buffer_io_error(bh);
 		} while ((bh = bh->b_this_page) != head);
 		bit_spin_unlock(BH_Uptodate_Lock, &head->b_state);
@@ -158,7 +157,7 @@ static int ext4_end_io(ext4_io_end_t *io)
 
 	io->handle = NULL;	/* Following call will use up the handle */
 	ret = ext4_convert_unwritten_extents(handle, inode, offset, size);
-	if (ret < 0) {
+	if (ret < 0 && !ext4_forced_shutdown(EXT4_SB(inode->i_sb))) {
 		ext4_msg(inode->i_sb, KERN_EMERG,
 			 "failed to convert unwritten extents to written "
 			 "extents -- potential data loss!  "
@@ -298,21 +297,31 @@ static void ext4_end_bio(struct bio *bio)
 {
 	ext4_io_end_t *io_end = bio->bi_private;
 	sector_t bi_sector = bio->bi_iter.bi_sector;
+	char b[BDEVNAME_SIZE];
 
-	BUG_ON(!io_end);
+	if (WARN_ONCE(!io_end, "io_end is NULL: %s: sector %Lu len %u err %d\n",
+		      bdevname(bio->bi_bdev, b),
+		      (long long) bio->bi_iter.bi_sector,
+		      (unsigned) bio_sectors(bio),
+		      bio->bi_status)) {
+		ext4_finish_bio(bio);
+		bio_put(bio);
+		return;
+	}
 	bio->bi_end_io = NULL;
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		struct inode *inode = io_end->inode;
 
 		ext4_warning(inode->i_sb, "I/O error %d writing to inode %lu "
 			     "(offset %llu size %ld starting block %llu)",
-			     bio->bi_error, inode->i_ino,
+			     bio->bi_status, inode->i_ino,
 			     (unsigned long long) io_end->offset,
 			     (long) io_end->size,
 			     (unsigned long long)
 			     bi_sector >> (inode->i_blkbits - 9));
-		mapping_set_error(inode->i_mapping, bio->bi_error);
+		mapping_set_error(inode->i_mapping,
+				blk_status_to_errno(bio->bi_status));
 	}
 
 	if (io_end->flag & EXT4_IO_END_UNWRITTEN) {
@@ -341,6 +350,7 @@ void ext4_io_submit(struct ext4_io_submit *io)
 	if (bio) {
 		int io_op_flags = io->io_wbc->sync_mode == WB_SYNC_ALL ?
 				  REQ_SYNC : 0;
+		io->io_bio->bi_write_hint = io->io_end->inode->i_write_hint;
 		bio_set_op_attrs(io->io_bio, REQ_OP_WRITE, io_op_flags);
 		submit_bio(io->io_bio);
 	}
@@ -388,6 +398,7 @@ submit_and_retry:
 		ret = io_submit_init_bio(io, bh);
 		if (ret)
 			return ret;
+		io->io_bio->bi_write_hint = inode->i_write_hint;
 	}
 	ret = bio_add_page(io->io_bio, page, bh->b_size, bh_offset(bh));
 	if (ret != bh->b_size)
diff --git a/fs/ext4/readpage.c b/fs/ext4/readpage.c
index a81b829d56de..40a5497b0f60 100644
--- a/fs/ext4/readpage.c
+++ b/fs/ext4/readpage.c
@@ -73,7 +73,7 @@ static void mpage_end_io(struct bio *bio)
 	int i;
 
 	if (ext4_bio_encrypted(bio)) {
-		if (bio->bi_error) {
+		if (bio->bi_status) {
 			fscrypt_release_ctx(bio->bi_private);
 		} else {
 			fscrypt_decrypt_bio_pages(bio->bi_private, bio);
@@ -83,7 +83,7 @@ static void mpage_end_io(struct bio *bio)
 	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
 
-		if (!bio->bi_error) {
+		if (!bio->bi_status) {
 			SetPageUptodate(page);
 		} else {
 			ClearPageUptodate(page);
diff --git a/fs/ext4/resize.c b/fs/ext4/resize.c
index cf681004b196..c3ed9021b781 100644
--- a/fs/ext4/resize.c
+++ b/fs/ext4/resize.c
@@ -45,7 +45,8 @@ int ext4_resize_begin(struct super_block *sb)
 		return -EPERM;
 	}
 
-	if (test_and_set_bit_lock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags))
+	if (test_and_set_bit_lock(EXT4_FLAGS_RESIZING,
+				  &EXT4_SB(sb)->s_ext4_flags))
 		ret = -EBUSY;
 
 	return ret;
@@ -53,7 +54,7 @@ int ext4_resize_begin(struct super_block *sb)
 
 void ext4_resize_end(struct super_block *sb)
 {
-	clear_bit_unlock(EXT4_RESIZING, &EXT4_SB(sb)->s_resize_flags);
+	clear_bit_unlock(EXT4_FLAGS_RESIZING, &EXT4_SB(sb)->s_ext4_flags);
 	smp_mb__after_atomic();
 }
 
diff --git a/fs/ext4/super.c b/fs/ext4/super.c
index 66845a08a87a..0886fe82e9c4 100644
--- a/fs/ext4/super.c
+++ b/fs/ext4/super.c
@@ -37,6 +37,7 @@
 #include <linux/ctype.h>
 #include <linux/log2.h>
 #include <linux/crc16.h>
+#include <linux/dax.h>
 #include <linux/cleancache.h>
 #include <linux/uaccess.h>
 
@@ -49,6 +50,7 @@
 #include "xattr.h"
 #include "acl.h"
 #include "mballoc.h"
+#include "fsmap.h"
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/ext4.h>
@@ -371,6 +373,9 @@ static void ext4_journal_commit_callback(journal_t *journal, transaction_t *txn)
 	struct ext4_journal_cb_entry	*jce;
 
 	BUG_ON(txn->t_state == T_FINISHED);
+
+	ext4_process_freed_data(sb, txn->t_tid);
+
 	spin_lock(&sbi->s_md_lock);
 	while (!list_empty(&txn->t_private_list)) {
 		jce = list_entry(txn->t_private_list.next,
@@ -438,6 +443,9 @@ void __ext4_error(struct super_block *sb, const char *function,
 	struct va_format vaf;
 	va_list args;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return;
+
 	if (ext4_error_ratelimit(sb)) {
 		va_start(args, fmt);
 		vaf.fmt = fmt;
@@ -459,6 +467,9 @@ void __ext4_error_inode(struct inode *inode, const char *function,
 	struct va_format vaf;
 	struct ext4_super_block *es = EXT4_SB(inode->i_sb)->s_es;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return;
+
 	es->s_last_error_ino = cpu_to_le32(inode->i_ino);
 	es->s_last_error_block = cpu_to_le64(block);
 	if (ext4_error_ratelimit(inode->i_sb)) {
@@ -491,6 +502,9 @@ void __ext4_error_file(struct file *file, const char *function,
 	struct inode *inode = file_inode(file);
 	char pathname[80], *path;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return;
+
 	es = EXT4_SB(inode->i_sb)->s_es;
 	es->s_last_error_ino = cpu_to_le32(inode->i_ino);
 	if (ext4_error_ratelimit(inode->i_sb)) {
@@ -567,6 +581,9 @@ void __ext4_std_error(struct super_block *sb, const char *function,
 	char nbuf[16];
 	const char *errstr;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return;
+
 	/* Special case: if the error is EROFS, and we're not already
 	 * inside a transaction, then there's really no point in logging
 	 * an error. */
@@ -600,6 +617,9 @@ void __ext4_abort(struct super_block *sb, const char *function,
 	struct va_format vaf;
 	va_list args;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return;
+
 	save_error_info(sb, function, line);
 	va_start(args, fmt);
 	vaf.fmt = fmt;
@@ -695,6 +715,9 @@ __acquires(bitlock)
 	va_list args;
 	struct ext4_super_block *es = EXT4_SB(sb)->s_es;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return;
+
 	es->s_last_error_ino = cpu_to_le32(ino);
 	es->s_last_error_block = cpu_to_le64(block);
 	__save_error_info(sb, function, line);
@@ -821,22 +844,41 @@ static void dump_orphan_list(struct super_block *sb, struct ext4_sb_info *sbi)
 	}
 }
 
+#ifdef CONFIG_QUOTA
+static int ext4_quota_off(struct super_block *sb, int type);
+
+static inline void ext4_quota_off_umount(struct super_block *sb)
+{
+	int type;
+
+	/* Use our quota_off function to clear inode flags etc. */
+	for (type = 0; type < EXT4_MAXQUOTAS; type++)
+		ext4_quota_off(sb, type);
+}
+#else
+static inline void ext4_quota_off_umount(struct super_block *sb)
+{
+}
+#endif
+
 static void ext4_put_super(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 	struct ext4_super_block *es = sbi->s_es;
+	int aborted = 0;
 	int i, err;
 
 	ext4_unregister_li_request(sb);
-	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
+	ext4_quota_off_umount(sb);
 
 	flush_workqueue(sbi->rsv_conversion_wq);
 	destroy_workqueue(sbi->rsv_conversion_wq);
 
 	if (sbi->s_journal) {
+		aborted = is_journal_aborted(sbi->s_journal);
 		err = jbd2_journal_destroy(sbi->s_journal);
 		sbi->s_journal = NULL;
-		if (err < 0)
+		if ((err < 0) && !aborted)
 			ext4_abort(sb, "Couldn't clean up the journal");
 	}
 
@@ -847,7 +889,7 @@ static void ext4_put_super(struct super_block *sb)
 	ext4_mb_release(sb);
 	ext4_ext_release(sb);
 
-	if (!(sb->s_flags & MS_RDONLY)) {
+	if (!(sb->s_flags & MS_RDONLY) && !aborted) {
 		ext4_clear_feature_journal_needs_recovery(sb);
 		es->s_state = cpu_to_le16(sbi->s_mount_state);
 	}
@@ -888,9 +930,13 @@ static void ext4_put_super(struct super_block *sb)
 		invalidate_bdev(sbi->journal_bdev);
 		ext4_blkdev_remove(sbi);
 	}
-	if (sbi->s_mb_cache) {
-		ext4_xattr_destroy_cache(sbi->s_mb_cache);
-		sbi->s_mb_cache = NULL;
+	if (sbi->s_ea_inode_cache) {
+		ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
+		sbi->s_ea_inode_cache = NULL;
+	}
+	if (sbi->s_ea_block_cache) {
+		ext4_xattr_destroy_cache(sbi->s_ea_block_cache);
+		sbi->s_ea_block_cache = NULL;
 	}
 	if (sbi->s_mmp_tsk)
 		kthread_stop(sbi->s_mmp_tsk);
@@ -1100,22 +1146,24 @@ static int ext4_get_context(struct inode *inode, void *ctx, size_t len)
 				 EXT4_XATTR_NAME_ENCRYPTION_CONTEXT, ctx, len);
 }
 
-static int ext4_key_prefix(struct inode *inode, u8 **key)
-{
-	*key = EXT4_SB(inode->i_sb)->key_prefix;
-	return EXT4_SB(inode->i_sb)->key_prefix_size;
-}
-
-static int ext4_prepare_context(struct inode *inode)
-{
-	return ext4_convert_inline_data(inode);
-}
-
 static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 							void *fs_data)
 {
 	handle_t *handle = fs_data;
-	int res, res2, retries = 0;
+	int res, res2, credits, retries = 0;
+
+	/*
+	 * Encrypting the root directory is not allowed because e2fsck expects
+	 * lost+found to exist and be unencrypted, and encrypting the root
+	 * directory would imply encrypting the lost+found directory as well as
+	 * the filename "lost+found" itself.
+	 */
+	if (inode->i_ino == EXT4_ROOT_INO)
+		return -EPERM;
+
+	res = ext4_convert_inline_data(inode);
+	if (res)
+		return res;
 
 	/*
 	 * If a journal handle was specified, then the encryption context is
@@ -1142,9 +1190,16 @@ static int ext4_set_context(struct inode *inode, const void *ctx, size_t len,
 		return res;
 	}
 
+	res = dquot_initialize(inode);
+	if (res)
+		return res;
 retry:
-	handle = ext4_journal_start(inode, EXT4_HT_MISC,
-			ext4_jbd2_credits_xattr(inode));
+	res = ext4_xattr_set_credits(inode, len, false /* is_create */,
+				     &credits);
+	if (res)
+		return res;
+
+	handle = ext4_journal_start(inode, EXT4_HT_MISC, credits);
 	if (IS_ERR(handle))
 		return PTR_ERR(handle);
 
@@ -1168,7 +1223,7 @@ retry:
 	return res;
 }
 
-static int ext4_dummy_context(struct inode *inode)
+static bool ext4_dummy_context(struct inode *inode)
 {
 	return DUMMY_ENCRYPTION_ENABLED(EXT4_SB(inode->i_sb));
 }
@@ -1179,10 +1234,9 @@ static unsigned ext4_max_namelen(struct inode *inode)
 		EXT4_NAME_LEN;
 }
 
-static struct fscrypt_operations ext4_cryptops = {
+static const struct fscrypt_operations ext4_cryptops = {
+	.key_prefix		= "ext4:",
 	.get_context		= ext4_get_context,
-	.key_prefix		= ext4_key_prefix,
-	.prepare_context	= ext4_prepare_context,
 	.set_context		= ext4_set_context,
 	.dummy_context		= ext4_dummy_context,
 	.is_encrypted		= ext4_encrypted_inode,
@@ -1190,13 +1244,13 @@ static struct fscrypt_operations ext4_cryptops = {
 	.max_namelen		= ext4_max_namelen,
 };
 #else
-static struct fscrypt_operations ext4_cryptops = {
+static const struct fscrypt_operations ext4_cryptops = {
 	.is_encrypted		= ext4_encrypted_inode,
 };
 #endif
 
 #ifdef CONFIG_QUOTA
-static char *quotatypes[] = INITQFNAMES;
+static const char * const quotatypes[] = INITQFNAMES;
 #define QTYPE2NAME(t) (quotatypes[t])
 
 static int ext4_write_dquot(struct dquot *dquot);
@@ -1206,7 +1260,6 @@ static int ext4_mark_dquot_dirty(struct dquot *dquot);
 static int ext4_write_info(struct super_block *sb, int type);
 static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 			 const struct path *path);
-static int ext4_quota_off(struct super_block *sb, int type);
 static int ext4_quota_on_mount(struct super_block *sb, int type);
 static ssize_t ext4_quota_read(struct super_block *sb, int type, char *data,
 			       size_t len, loff_t off);
@@ -1223,16 +1276,17 @@ static struct dquot **ext4_get_dquots(struct inode *inode)
 }
 
 static const struct dquot_operations ext4_quota_operations = {
-	.get_reserved_space = ext4_get_reserved_space,
-	.write_dquot	= ext4_write_dquot,
-	.acquire_dquot	= ext4_acquire_dquot,
-	.release_dquot	= ext4_release_dquot,
-	.mark_dirty	= ext4_mark_dquot_dirty,
-	.write_info	= ext4_write_info,
-	.alloc_dquot	= dquot_alloc,
-	.destroy_dquot	= dquot_destroy,
-	.get_projid	= ext4_get_projid,
-	.get_next_id	= ext4_get_next_id,
+	.get_reserved_space	= ext4_get_reserved_space,
+	.write_dquot		= ext4_write_dquot,
+	.acquire_dquot		= ext4_acquire_dquot,
+	.release_dquot		= ext4_release_dquot,
+	.mark_dirty		= ext4_mark_dquot_dirty,
+	.write_info		= ext4_write_info,
+	.alloc_dquot		= dquot_alloc,
+	.destroy_dquot		= dquot_destroy,
+	.get_projid		= ext4_get_projid,
+	.get_inode_usage	= ext4_get_inode_usage,
+	.get_next_id		= ext4_get_next_id,
 };
 
 static const struct quotactl_ops ext4_qctl_operations = {
@@ -1290,12 +1344,12 @@ enum {
 	Opt_noquota, Opt_barrier, Opt_nobarrier, Opt_err,
 	Opt_usrquota, Opt_grpquota, Opt_prjquota, Opt_i_version, Opt_dax,
 	Opt_stripe, Opt_delalloc, Opt_nodelalloc, Opt_mblk_io_submit,
-	Opt_lazytime, Opt_nolazytime,
+	Opt_lazytime, Opt_nolazytime, Opt_debug_want_extra_isize,
 	Opt_nomblk_io_submit, Opt_block_validity, Opt_noblock_validity,
 	Opt_inode_readahead_blks, Opt_journal_ioprio,
 	Opt_dioread_nolock, Opt_dioread_lock,
 	Opt_discard, Opt_nodiscard, Opt_init_itable, Opt_noinit_itable,
-	Opt_max_dir_size_kb, Opt_nojournal_checksum,
+	Opt_max_dir_size_kb, Opt_nojournal_checksum, Opt_nombcache,
 };
 
 static const match_table_t tokens = {
@@ -1358,6 +1412,7 @@ static const match_table_t tokens = {
 	{Opt_delalloc, "delalloc"},
 	{Opt_lazytime, "lazytime"},
 	{Opt_nolazytime, "nolazytime"},
+	{Opt_debug_want_extra_isize, "debug_want_extra_isize=%u"},
 	{Opt_nodelalloc, "nodelalloc"},
 	{Opt_removed, "mblk_io_submit"},
 	{Opt_removed, "nomblk_io_submit"},
@@ -1377,6 +1432,8 @@ static const match_table_t tokens = {
 	{Opt_noinit_itable, "noinit_itable"},
 	{Opt_max_dir_size_kb, "max_dir_size_kb=%u"},
 	{Opt_test_dummy_encryption, "test_dummy_encryption"},
+	{Opt_nombcache, "nombcache"},
+	{Opt_nombcache, "no_mbcache"},	/* for backward compatibility */
 	{Opt_removed, "check=none"},	/* mount option from ext2/3 */
 	{Opt_removed, "nocheck"},	/* mount option from ext2/3 */
 	{Opt_removed, "reservation"},	/* mount option from ext2/3 */
@@ -1409,7 +1466,8 @@ static ext4_fsblk_t get_sb_block(void **data)
 }
 
 #define DEFAULT_JOURNAL_IOPRIO (IOPRIO_PRIO_VALUE(IOPRIO_CLASS_BE, 3))
-static char deprecated_msg[] = "Mount option \"%s\" will be removed by %s\n"
+static const char deprecated_msg[] =
+	"Mount option \"%s\" will be removed by %s\n"
 	"Contact linux-ext4@vger.kernel.org if you think we should keep it.\n";
 
 #ifdef CONFIG_QUOTA
@@ -1563,6 +1621,7 @@ static const struct mount_opts {
 #endif
 	{Opt_nouid32, EXT4_MOUNT_NO_UID32, MOPT_SET},
 	{Opt_debug, EXT4_MOUNT_DEBUG, MOPT_SET},
+	{Opt_debug_want_extra_isize, 0, MOPT_GTE0},
 	{Opt_quota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA, MOPT_SET | MOPT_Q},
 	{Opt_usrquota, EXT4_MOUNT_QUOTA | EXT4_MOUNT_USRQUOTA,
 							MOPT_SET | MOPT_Q},
@@ -1582,6 +1641,7 @@ static const struct mount_opts {
 	{Opt_jqfmt_vfsv1, QFMT_VFS_V1, MOPT_QFMT},
 	{Opt_max_dir_size_kb, 0, MOPT_GTE0},
 	{Opt_test_dummy_encryption, 0, MOPT_GTE0},
+	{Opt_nombcache, EXT4_MOUNT_NO_MBCACHE, MOPT_SET},
 	{Opt_err, 0, 0}
 };
 
@@ -1676,6 +1736,8 @@ static int handle_mount_opt(struct super_block *sb, char *opt, int token,
 		if (arg == 0)
 			arg = JBD2_DEFAULT_MAX_COMMIT_AGE;
 		sbi->s_commit_interval = HZ * arg;
+	} else if (token == Opt_debug_want_extra_isize) {
+		sbi->s_want_extra_isize = arg;
 	} else if (token == Opt_max_batch_time) {
 		sbi->s_max_batch_time = arg;
 	} else if (token == Opt_min_batch_time) {
@@ -2116,7 +2178,7 @@ int ext4_alloc_flex_bg_array(struct super_block *sb, ext4_group_t ngroup)
 		return 0;
 
 	size = roundup_pow_of_two(size * sizeof(struct flex_groups));
-	new_groups = ext4_kvzalloc(size, GFP_KERNEL);
+	new_groups = kvzalloc(size, GFP_KERNEL);
 	if (!new_groups) {
 		ext4_msg(sb, KERN_ERR, "not enough memory for %d flex groups",
 			 size / (int) sizeof(struct flex_groups));
@@ -2619,9 +2681,9 @@ static unsigned long ext4_get_stripe_size(struct ext4_sb_info *sbi)
 
 	if (sbi->s_stripe && sbi->s_stripe <= sbi->s_blocks_per_group)
 		ret = sbi->s_stripe;
-	else if (stripe_width <= sbi->s_blocks_per_group)
+	else if (stripe_width && stripe_width <= sbi->s_blocks_per_group)
 		ret = stripe_width;
-	else if (stride <= sbi->s_blocks_per_group)
+	else if (stride && stride <= sbi->s_blocks_per_group)
 		ret = stride;
 	else
 		ret = 0;
@@ -3407,7 +3469,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	}
 
 	/* Load the checksum driver */
-	if (ext4_has_feature_metadata_csum(sb)) {
+	if (ext4_has_feature_metadata_csum(sb) ||
+	    ext4_has_feature_ea_inode(sb)) {
 		sbi->s_chksum_driver = crypto_alloc_shash("crc32c", 0, 0);
 		if (IS_ERR(sbi->s_chksum_driver)) {
 			ext4_msg(sb, KERN_ERR, "Cannot load crc32c driver.");
@@ -3429,7 +3492,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	/* Precompute checksum seed for all metadata */
 	if (ext4_has_feature_csum_seed(sb))
 		sbi->s_csum_seed = le32_to_cpu(es->s_checksum_seed);
-	else if (ext4_has_metadata_csum(sb))
+	else if (ext4_has_metadata_csum(sb) || ext4_has_feature_ea_inode(sb))
 		sbi->s_csum_seed = ext4_chksum(sbi, ~0, es->s_uuid,
 					       sizeof(es->s_uuid));
 
@@ -3559,6 +3622,16 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 				 "The Hurd can't support 64-bit file systems");
 			goto failed_mount;
 		}
+
+		/*
+		 * ea_inode feature uses l_i_version field which is not
+		 * available in HURD_COMPAT mode.
+		 */
+		if (ext4_has_feature_ea_inode(sb)) {
+			ext4_msg(sb, KERN_ERR,
+				 "ea_inode feature is not supported for Hurd");
+			goto failed_mount;
+		}
 	}
 
 	if (IS_EXT2_SB(sb)) {
@@ -3842,7 +3915,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	db_count = (sbi->s_groups_count + EXT4_DESC_PER_BLOCK(sb) - 1) /
 		   EXT4_DESC_PER_BLOCK(sb);
 	if (ext4_has_feature_meta_bg(sb)) {
-		if (le32_to_cpu(es->s_first_meta_bg) >= db_count) {
+		if (le32_to_cpu(es->s_first_meta_bg) > db_count) {
 			ext4_msg(sb, KERN_WARNING,
 				 "first meta block group too large: %u "
 				 "(group descriptor block count %u)",
@@ -3850,7 +3923,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 			goto failed_mount;
 		}
 	}
-	sbi->s_group_desc = ext4_kvmalloc(db_count *
+	sbi->s_group_desc = kvmalloc(db_count *
 					  sizeof(struct buffer_head *),
 					  GFP_KERNEL);
 	if (sbi->s_group_desc == NULL) {
@@ -3861,6 +3934,12 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 
 	bgl_lock_init(sbi->s_blockgroup_lock);
 
+	/* Pre-read the descriptors into the buffer cache */
+	for (i = 0; i < db_count; i++) {
+		block = descriptor_loc(sb, logical_sb_block, i);
+		sb_breadahead(sb, block);
+	}
+
 	for (i = 0; i < db_count; i++) {
 		block = descriptor_loc(sb, logical_sb_block, i);
 		sbi->s_group_desc[i] = sb_bread_unmovable(sb, block);
@@ -3906,7 +3985,7 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 		sb->s_qcop = &ext4_qctl_operations;
 	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP | QTYPE_MASK_PRJ;
 #endif
-	memcpy(sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
+	memcpy(&sb->s_uuid, es->s_uuid, sizeof(es->s_uuid));
 
 	INIT_LIST_HEAD(&sbi->s_orphan); /* unlinked but open files */
 	mutex_init(&sbi->s_orphan_lock);
@@ -3925,7 +4004,8 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	 * root first: it may be modified in the journal!
 	 */
 	if (!test_opt(sb, NOLOAD) && ext4_has_feature_journal(sb)) {
-		if (ext4_load_journal(sb, es, journal_devnum))
+		err = ext4_load_journal(sb, es, journal_devnum);
+		if (err)
 			goto failed_mount3a;
 	} else if (test_opt(sb, NOLOAD) && !(sb->s_flags & MS_RDONLY) &&
 		   ext4_has_feature_journal_needs_recovery(sb)) {
@@ -4016,10 +4096,22 @@ static int ext4_fill_super(struct super_block *sb, void *data, int silent)
 	sbi->s_journal->j_commit_callback = ext4_journal_commit_callback;
 
 no_journal:
-	sbi->s_mb_cache = ext4_xattr_create_cache();
-	if (!sbi->s_mb_cache) {
-		ext4_msg(sb, KERN_ERR, "Failed to create an mb_cache");
-		goto failed_mount_wq;
+	if (!test_opt(sb, NO_MBCACHE)) {
+		sbi->s_ea_block_cache = ext4_xattr_create_cache();
+		if (!sbi->s_ea_block_cache) {
+			ext4_msg(sb, KERN_ERR,
+				 "Failed to create ea_block_cache");
+			goto failed_mount_wq;
+		}
+
+		if (ext4_has_feature_ea_inode(sb)) {
+			sbi->s_ea_inode_cache = ext4_xattr_create_cache();
+			if (!sbi->s_ea_inode_cache) {
+				ext4_msg(sb, KERN_ERR,
+					 "Failed to create ea_inode_cache");
+				goto failed_mount_wq;
+			}
+		}
 	}
 
 	if ((DUMMY_ENCRYPTION_ENABLED(sbi) || ext4_has_feature_encrypt(sb)) &&
@@ -4087,7 +4179,8 @@ no_journal:
 		sb->s_flags |= MS_RDONLY;
 
 	/* determine the minimum size of new large inodes, if present */
-	if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE) {
+	if (sbi->s_inode_size > EXT4_GOOD_OLD_INODE_SIZE &&
+	    sbi->s_want_extra_isize == 0) {
 		sbi->s_want_extra_isize = sizeof(struct ext4_inode) -
 						     EXT4_GOOD_OLD_INODE_SIZE;
 		if (ext4_has_feature_extra_isize(sb)) {
@@ -4218,11 +4311,6 @@ no_journal:
 	ratelimit_state_init(&sbi->s_msg_ratelimit_state, 5 * HZ, 10);
 
 	kfree(orig_data);
-#ifdef CONFIG_EXT4_FS_ENCRYPTION
-	memcpy(sbi->key_prefix, EXT4_KEY_DESC_PREFIX,
-				EXT4_KEY_DESC_PREFIX_SIZE);
-	sbi->key_prefix_size = EXT4_KEY_DESC_PREFIX_SIZE;
-#endif
 	return 0;
 
 cantfind_ext4:
@@ -4255,9 +4343,13 @@ failed_mount4:
 	if (EXT4_SB(sb)->rsv_conversion_wq)
 		destroy_workqueue(EXT4_SB(sb)->rsv_conversion_wq);
 failed_mount_wq:
-	if (sbi->s_mb_cache) {
-		ext4_xattr_destroy_cache(sbi->s_mb_cache);
-		sbi->s_mb_cache = NULL;
+	if (sbi->s_ea_inode_cache) {
+		ext4_xattr_destroy_cache(sbi->s_ea_inode_cache);
+		sbi->s_ea_inode_cache = NULL;
+	}
+	if (sbi->s_ea_block_cache) {
+		ext4_xattr_destroy_cache(sbi->s_ea_block_cache);
+		sbi->s_ea_block_cache = NULL;
 	}
 	if (sbi->s_journal) {
 		jbd2_journal_destroy(sbi->s_journal);
@@ -4616,7 +4708,7 @@ static int ext4_commit_super(struct super_block *sb, int sync)
 	if (sync) {
 		unlock_buffer(sbh);
 		error = __sync_dirty_buffer(sbh,
-			test_opt(sb, BARRIER) ? REQ_FUA : REQ_SYNC);
+			REQ_SYNC | (test_opt(sb, BARRIER) ? REQ_FUA : 0));
 		if (error)
 			return error;
 
@@ -4720,6 +4812,9 @@ static int ext4_sync_fs(struct super_block *sb, int wait)
 	bool needs_barrier = false;
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(sb))))
+		return 0;
+
 	trace_ext4_sync_fs(sb, wait);
 	flush_workqueue(sbi->rsv_conversion_wq);
 	/*
@@ -4803,7 +4898,7 @@ out:
  */
 static int ext4_unfreeze(struct super_block *sb)
 {
-	if (sb->s_flags & MS_RDONLY)
+	if ((sb->s_flags & MS_RDONLY) || ext4_forced_shutdown(EXT4_SB(sb)))
 		return 0;
 
 	if (EXT4_SB(sb)->s_journal) {
@@ -4913,6 +5008,12 @@ static int ext4_remount(struct super_block *sb, int *flags, char *data)
 		}
 	}
 
+	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_NO_MBCACHE) {
+		ext4_msg(sb, KERN_ERR, "can't enable nombcache during remount");
+		err = -EINVAL;
+		goto restore_opts;
+	}
+
 	if ((sbi->s_mount_opt ^ old_opts.s_mount_opt) & EXT4_MOUNT_DAX) {
 		ext4_msg(sb, KERN_WARNING, "warning: refusing change of "
 			"dax flag with busy inodes while remounting");
@@ -5328,11 +5429,33 @@ static int ext4_quota_on(struct super_block *sb, int type, int format_id,
 		if (err)
 			return err;
 	}
+
 	lockdep_set_quota_inode(path->dentry->d_inode, I_DATA_SEM_QUOTA);
 	err = dquot_quota_on(sb, type, format_id, path);
-	if (err)
+	if (err) {
 		lockdep_set_quota_inode(path->dentry->d_inode,
 					     I_DATA_SEM_NORMAL);
+	} else {
+		struct inode *inode = d_inode(path->dentry);
+		handle_t *handle;
+
+		/*
+		 * Set inode flags to prevent userspace from messing with quota
+		 * files. If this fails, we return success anyway since quotas
+		 * are already enabled and this is not a hard failure.
+		 */
+		inode_lock(inode);
+		handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1);
+		if (IS_ERR(handle))
+			goto unlock_inode;
+		EXT4_I(inode)->i_flags |= EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL;
+		inode_set_flags(inode, S_NOATIME | S_IMMUTABLE,
+				S_NOATIME | S_IMMUTABLE);
+		ext4_mark_inode_dirty(handle, inode);
+		ext4_journal_stop(handle);
+	unlock_inode:
+		inode_unlock(inode);
+	}
 	return err;
 }
 
@@ -5406,24 +5529,40 @@ static int ext4_quota_off(struct super_block *sb, int type)
 {
 	struct inode *inode = sb_dqopt(sb)->files[type];
 	handle_t *handle;
+	int err;
 
 	/* Force all delayed allocation blocks to be allocated.
 	 * Caller already holds s_umount sem */
 	if (test_opt(sb, DELALLOC))
 		sync_filesystem(sb);
 
-	if (!inode)
+	if (!inode || !igrab(inode))
 		goto out;
 
-	/* Update modification times of quota files when userspace can
-	 * start looking at them */
+	err = dquot_quota_off(sb, type);
+	if (err || ext4_has_feature_quota(sb))
+		goto out_put;
+
+	inode_lock(inode);
+	/*
+	 * Update modification times of quota files when userspace can
+	 * start looking at them. If we fail, we return success anyway since
+	 * this is not a hard failure and quotas are already disabled.
+	 */
 	handle = ext4_journal_start(inode, EXT4_HT_QUOTA, 1);
 	if (IS_ERR(handle))
-		goto out;
+		goto out_unlock;
+	EXT4_I(inode)->i_flags &= ~(EXT4_NOATIME_FL | EXT4_IMMUTABLE_FL);
+	inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE);
 	inode->i_mtime = inode->i_ctime = current_time(inode);
 	ext4_mark_inode_dirty(handle, inode);
 	ext4_journal_stop(handle);
-
+out_unlock:
+	inode_unlock(inode);
+out_put:
+	lockdep_set_quota_inode(inode, I_DATA_SEM_NORMAL);
+	iput(inode);
+	return err;
 out:
 	return dquot_quota_off(sb, type);
 }
diff --git a/fs/ext4/symlink.c b/fs/ext4/symlink.c
index 73b184d161fc..5c8fc53cb0e5 100644
--- a/fs/ext4/symlink.c
+++ b/fs/ext4/symlink.c
@@ -85,17 +85,20 @@ errout:
 const struct inode_operations ext4_encrypted_symlink_inode_operations = {
 	.get_link	= ext4_encrypted_get_link,
 	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
 	.listxattr	= ext4_listxattr,
 };
 
 const struct inode_operations ext4_symlink_inode_operations = {
 	.get_link	= page_get_link,
 	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
 	.listxattr	= ext4_listxattr,
 };
 
 const struct inode_operations ext4_fast_symlink_inode_operations = {
 	.get_link	= simple_get_link,
 	.setattr	= ext4_setattr,
+	.getattr	= ext4_getattr,
 	.listxattr	= ext4_listxattr,
 };
diff --git a/fs/ext4/sysfs.c b/fs/ext4/sysfs.c
index 42145be5c6b4..48c7a7d55ed3 100644
--- a/fs/ext4/sysfs.c
+++ b/fs/ext4/sysfs.c
@@ -34,7 +34,7 @@ typedef enum {
 	ptr_ext4_super_block_offset,
 } attr_ptr_t;
 
-static const char *proc_dirname = "fs/ext4";
+static const char proc_dirname[] = "fs/ext4";
 static struct proc_dir_entry *ext4_proc_root;
 
 struct ext4_attr {
@@ -100,7 +100,7 @@ static ssize_t reserved_clusters_store(struct ext4_attr *a,
 	int ret;
 
 	ret = kstrtoull(skip_spaces(buf), 0, &val);
-	if (!ret || val >= clusters)
+	if (ret || val >= clusters)
 		return -EINVAL;
 
 	atomic64_set(&sbi->s_resv_clusters, val);
@@ -375,7 +375,7 @@ static const struct file_operations ext4_seq_##name##_fops = { \
 PROC_FILE_SHOW_DEFN(es_shrinker_info);
 PROC_FILE_SHOW_DEFN(options);
 
-static struct ext4_proc_files {
+static const struct ext4_proc_files {
 	const char *name;
 	const struct file_operations *fops;
 } proc_files[] = {
@@ -388,7 +388,7 @@ static struct ext4_proc_files {
 int ext4_register_sysfs(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_proc_files *p;
+	const struct ext4_proc_files *p;
 	int err;
 
 	sbi->s_kobj.kset = &ext4_kset;
@@ -412,7 +412,7 @@ int ext4_register_sysfs(struct super_block *sb)
 void ext4_unregister_sysfs(struct super_block *sb)
 {
 	struct ext4_sb_info *sbi = EXT4_SB(sb);
-	struct ext4_proc_files *p;
+	const struct ext4_proc_files *p;
 
 	if (sbi->s_proc) {
 		for (p = proc_files; p->name; p++)
diff --git a/fs/ext4/xattr.c b/fs/ext4/xattr.c
index 5a94fa52b74f..cff4f41ced61 100644
--- a/fs/ext4/xattr.c
+++ b/fs/ext4/xattr.c
@@ -72,16 +72,16 @@
 # define ea_bdebug(bh, fmt, ...)	no_printk(fmt, ##__VA_ARGS__)
 #endif
 
-static void ext4_xattr_cache_insert(struct mb_cache *, struct buffer_head *);
-static struct buffer_head *ext4_xattr_cache_find(struct inode *,
-						 struct ext4_xattr_header *,
-						 struct mb_cache_entry **);
-static void ext4_xattr_rehash(struct ext4_xattr_header *,
-			      struct ext4_xattr_entry *);
-static int ext4_xattr_list(struct dentry *dentry, char *buffer,
-			   size_t buffer_size);
-
-static const struct xattr_handler *ext4_xattr_handler_map[] = {
+static void ext4_xattr_block_cache_insert(struct mb_cache *,
+					  struct buffer_head *);
+static struct buffer_head *
+ext4_xattr_block_cache_find(struct inode *, struct ext4_xattr_header *,
+			    struct mb_cache_entry **);
+static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value,
+				    size_t value_count);
+static void ext4_xattr_rehash(struct ext4_xattr_header *);
+
+static const struct xattr_handler * const ext4_xattr_handler_map[] = {
 	[EXT4_XATTR_INDEX_USER]		     = &ext4_xattr_user_handler,
 #ifdef CONFIG_EXT4_FS_POSIX_ACL
 	[EXT4_XATTR_INDEX_POSIX_ACL_ACCESS]  = &posix_acl_access_xattr_handler,
@@ -106,8 +106,22 @@ const struct xattr_handler *ext4_xattr_handlers[] = {
 	NULL
 };
 
-#define EXT4_GET_MB_CACHE(inode)	(((struct ext4_sb_info *) \
-				inode->i_sb->s_fs_info)->s_mb_cache)
+#define EA_BLOCK_CACHE(inode)	(((struct ext4_sb_info *) \
+				inode->i_sb->s_fs_info)->s_ea_block_cache)
+
+#define EA_INODE_CACHE(inode)	(((struct ext4_sb_info *) \
+				inode->i_sb->s_fs_info)->s_ea_inode_cache)
+
+static int
+ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array,
+			struct inode *inode);
+
+#ifdef CONFIG_LOCKDEP
+void ext4_xattr_inode_set_class(struct inode *ea_inode)
+{
+	lockdep_set_subclass(&ea_inode->i_rwsem, 1);
+}
+#endif
 
 static __le32 ext4_xattr_block_csum(struct inode *inode,
 				    sector_t block_nr,
@@ -131,31 +145,26 @@ static __le32 ext4_xattr_block_csum(struct inode *inode,
 }
 
 static int ext4_xattr_block_csum_verify(struct inode *inode,
-					sector_t block_nr,
-					struct ext4_xattr_header *hdr)
+					struct buffer_head *bh)
 {
-	if (ext4_has_metadata_csum(inode->i_sb) &&
-	    (hdr->h_checksum != ext4_xattr_block_csum(inode, block_nr, hdr)))
-		return 0;
-	return 1;
-}
+	struct ext4_xattr_header *hdr = BHDR(bh);
+	int ret = 1;
 
-static void ext4_xattr_block_csum_set(struct inode *inode,
-				      sector_t block_nr,
-				      struct ext4_xattr_header *hdr)
-{
-	if (!ext4_has_metadata_csum(inode->i_sb))
-		return;
-
-	hdr->h_checksum = ext4_xattr_block_csum(inode, block_nr, hdr);
+	if (ext4_has_metadata_csum(inode->i_sb)) {
+		lock_buffer(bh);
+		ret = (hdr->h_checksum == ext4_xattr_block_csum(inode,
+							bh->b_blocknr, hdr));
+		unlock_buffer(bh);
+	}
+	return ret;
 }
 
-static inline int ext4_handle_dirty_xattr_block(handle_t *handle,
-						struct inode *inode,
-						struct buffer_head *bh)
+static void ext4_xattr_block_csum_set(struct inode *inode,
+				      struct buffer_head *bh)
 {
-	ext4_xattr_block_csum_set(inode, bh->b_blocknr, BHDR(bh));
-	return ext4_handle_dirty_metadata(handle, inode, bh);
+	if (ext4_has_metadata_csum(inode->i_sb))
+		BHDR(bh)->h_checksum = ext4_xattr_block_csum(inode,
+						bh->b_blocknr, BHDR(bh));
 }
 
 static inline const struct xattr_handler *
@@ -168,20 +177,9 @@ ext4_xattr_handler(int name_index)
 	return handler;
 }
 
-/*
- * Inode operation listxattr()
- *
- * d_inode(dentry)->i_mutex: don't care
- */
-ssize_t
-ext4_listxattr(struct dentry *dentry, char *buffer, size_t size)
-{
-	return ext4_xattr_list(dentry, buffer, size);
-}
-
 static int
-ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end,
-		       void *value_start)
+ext4_xattr_check_entries(struct ext4_xattr_entry *entry, void *end,
+			 void *value_start)
 {
 	struct ext4_xattr_entry *e = entry;
 
@@ -195,9 +193,8 @@ ext4_xattr_check_names(struct ext4_xattr_entry *entry, void *end,
 
 	/* Check the values */
 	while (!IS_LAST_ENTRY(entry)) {
-		if (entry->e_value_block != 0)
-			return -EFSCORRUPTED;
-		if (entry->e_value_size != 0) {
+		if (entry->e_value_size != 0 &&
+		    entry->e_value_inum == 0) {
 			u16 offs = le16_to_cpu(entry->e_value_offs);
 			u32 size = le32_to_cpu(entry->e_value_size);
 			void *value;
@@ -233,10 +230,10 @@ ext4_xattr_check_block(struct inode *inode, struct buffer_head *bh)
 	if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
 	    BHDR(bh)->h_blocks != cpu_to_le32(1))
 		return -EFSCORRUPTED;
-	if (!ext4_xattr_block_csum_verify(inode, bh->b_blocknr, BHDR(bh)))
+	if (!ext4_xattr_block_csum_verify(inode, bh))
 		return -EFSBADCRC;
-	error = ext4_xattr_check_names(BFIRST(bh), bh->b_data + bh->b_size,
-				       bh->b_data);
+	error = ext4_xattr_check_entries(BFIRST(bh), bh->b_data + bh->b_size,
+					 bh->b_data);
 	if (!error)
 		set_buffer_verified(bh);
 	return error;
@@ -251,7 +248,7 @@ __xattr_check_inode(struct inode *inode, struct ext4_xattr_ibody_header *header,
 	if (end - (void *)header < sizeof(*header) + sizeof(u32) ||
 	    (header->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC)))
 		goto errout;
-	error = ext4_xattr_check_names(IFIRST(header), end, IFIRST(header));
+	error = ext4_xattr_check_entries(IFIRST(header), end, IFIRST(header));
 errout:
 	if (error)
 		__ext4_error_inode(inode, function, line, 0,
@@ -262,20 +259,9 @@ errout:
 #define xattr_check_inode(inode, header, end) \
 	__xattr_check_inode((inode), (header), (end), __func__, __LINE__)
 
-static inline int
-ext4_xattr_check_entry(struct ext4_xattr_entry *entry, size_t size)
-{
-	size_t value_size = le32_to_cpu(entry->e_value_size);
-
-	if (entry->e_value_block != 0 || value_size > size ||
-	    le16_to_cpu(entry->e_value_offs) + value_size > size)
-		return -EFSCORRUPTED;
-	return 0;
-}
-
 static int
 ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index,
-		      const char *name, size_t size, int sorted)
+		      const char *name, int sorted)
 {
 	struct ext4_xattr_entry *entry;
 	size_t name_len;
@@ -295,11 +281,188 @@ ext4_xattr_find_entry(struct ext4_xattr_entry **pentry, int name_index,
 			break;
 	}
 	*pentry = entry;
-	if (!cmp && ext4_xattr_check_entry(entry, size))
-		return -EFSCORRUPTED;
 	return cmp ? -ENODATA : 0;
 }
 
+static u32
+ext4_xattr_inode_hash(struct ext4_sb_info *sbi, const void *buffer, size_t size)
+{
+	return ext4_chksum(sbi, sbi->s_csum_seed, buffer, size);
+}
+
+static u64 ext4_xattr_inode_get_ref(struct inode *ea_inode)
+{
+	return ((u64)ea_inode->i_ctime.tv_sec << 32) |
+	       ((u32)ea_inode->i_version);
+}
+
+static void ext4_xattr_inode_set_ref(struct inode *ea_inode, u64 ref_count)
+{
+	ea_inode->i_ctime.tv_sec = (u32)(ref_count >> 32);
+	ea_inode->i_version = (u32)ref_count;
+}
+
+static u32 ext4_xattr_inode_get_hash(struct inode *ea_inode)
+{
+	return (u32)ea_inode->i_atime.tv_sec;
+}
+
+static void ext4_xattr_inode_set_hash(struct inode *ea_inode, u32 hash)
+{
+	ea_inode->i_atime.tv_sec = hash;
+}
+
+/*
+ * Read the EA value from an inode.
+ */
+static int ext4_xattr_inode_read(struct inode *ea_inode, void *buf, size_t size)
+{
+	unsigned long block = 0;
+	struct buffer_head *bh;
+	int blocksize = ea_inode->i_sb->s_blocksize;
+	size_t csize, copied = 0;
+	void *copy_pos = buf;
+
+	while (copied < size) {
+		csize = (size - copied) > blocksize ? blocksize : size - copied;
+		bh = ext4_bread(NULL, ea_inode, block, 0);
+		if (IS_ERR(bh))
+			return PTR_ERR(bh);
+		if (!bh)
+			return -EFSCORRUPTED;
+
+		memcpy(copy_pos, bh->b_data, csize);
+		brelse(bh);
+
+		copy_pos += csize;
+		block += 1;
+		copied += csize;
+	}
+	return 0;
+}
+
+static int ext4_xattr_inode_iget(struct inode *parent, unsigned long ea_ino,
+				 struct inode **ea_inode)
+{
+	struct inode *inode;
+	int err;
+
+	inode = ext4_iget(parent->i_sb, ea_ino);
+	if (IS_ERR(inode)) {
+		err = PTR_ERR(inode);
+		ext4_error(parent->i_sb,
+			   "error while reading EA inode %lu err=%d", ea_ino,
+			   err);
+		return err;
+	}
+
+	if (is_bad_inode(inode)) {
+		ext4_error(parent->i_sb,
+			   "error while reading EA inode %lu is_bad_inode",
+			   ea_ino);
+		err = -EIO;
+		goto error;
+	}
+
+	if (!(EXT4_I(inode)->i_flags & EXT4_EA_INODE_FL)) {
+		ext4_error(parent->i_sb,
+			   "EA inode %lu does not have EXT4_EA_INODE_FL flag",
+			    ea_ino);
+		err = -EINVAL;
+		goto error;
+	}
+
+	*ea_inode = inode;
+	return 0;
+error:
+	iput(inode);
+	return err;
+}
+
+static int
+ext4_xattr_inode_verify_hashes(struct inode *ea_inode,
+			       struct ext4_xattr_entry *entry, void *buffer,
+			       size_t size)
+{
+	u32 hash;
+
+	/* Verify stored hash matches calculated hash. */
+	hash = ext4_xattr_inode_hash(EXT4_SB(ea_inode->i_sb), buffer, size);
+	if (hash != ext4_xattr_inode_get_hash(ea_inode))
+		return -EFSCORRUPTED;
+
+	if (entry) {
+		__le32 e_hash, tmp_data;
+
+		/* Verify entry hash. */
+		tmp_data = cpu_to_le32(hash);
+		e_hash = ext4_xattr_hash_entry(entry->e_name, entry->e_name_len,
+					       &tmp_data, 1);
+		if (e_hash != entry->e_hash)
+			return -EFSCORRUPTED;
+	}
+	return 0;
+}
+
+#define EXT4_XATTR_INODE_GET_PARENT(inode) ((__u32)(inode)->i_mtime.tv_sec)
+
+/*
+ * Read xattr value from the EA inode.
+ */
+static int
+ext4_xattr_inode_get(struct inode *inode, struct ext4_xattr_entry *entry,
+		     void *buffer, size_t size)
+{
+	struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode);
+	struct inode *ea_inode;
+	int err;
+
+	err = ext4_xattr_inode_iget(inode, le32_to_cpu(entry->e_value_inum),
+				    &ea_inode);
+	if (err) {
+		ea_inode = NULL;
+		goto out;
+	}
+
+	if (i_size_read(ea_inode) != size) {
+		ext4_warning_inode(ea_inode,
+				   "ea_inode file size=%llu entry size=%zu",
+				   i_size_read(ea_inode), size);
+		err = -EFSCORRUPTED;
+		goto out;
+	}
+
+	err = ext4_xattr_inode_read(ea_inode, buffer, size);
+	if (err)
+		goto out;
+
+	err = ext4_xattr_inode_verify_hashes(ea_inode, entry, buffer, size);
+	/*
+	 * Compatibility check for old Lustre ea_inode implementation. Old
+	 * version does not have hash validation, but it has a backpointer
+	 * from ea_inode to the parent inode.
+	 */
+	if (err == -EFSCORRUPTED) {
+		if (EXT4_XATTR_INODE_GET_PARENT(ea_inode) != inode->i_ino ||
+		    ea_inode->i_generation != inode->i_generation) {
+			ext4_warning_inode(ea_inode,
+					   "EA inode hash validation failed");
+			goto out;
+		}
+		/* Do not add ea_inode to the cache. */
+		ea_inode_cache = NULL;
+	} else if (err)
+		goto out;
+
+	if (ea_inode_cache)
+		mb_cache_entry_create(ea_inode_cache, GFP_NOFS,
+				      ext4_xattr_inode_get_hash(ea_inode),
+				      ea_inode->i_ino, true /* reusable */);
+out:
+	iput(ea_inode);
+	return err;
+}
+
 static int
 ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
 		     void *buffer, size_t buffer_size)
@@ -308,7 +471,7 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
 	struct ext4_xattr_entry *entry;
 	size_t size;
 	int error;
-	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
 
 	ea_idebug(inode, "name=%d.%s, buffer=%p, buffer_size=%ld",
 		  name_index, name, buffer, (long)buffer_size);
@@ -324,17 +487,14 @@ ext4_xattr_block_get(struct inode *inode, int name_index, const char *name,
 	ea_bdebug(bh, "b_count=%d, refcount=%d",
 		atomic_read(&(bh->b_count)), le32_to_cpu(BHDR(bh)->h_refcount));
 	if (ext4_xattr_check_block(inode, bh)) {
-bad_block:
 		EXT4_ERROR_INODE(inode, "bad block %llu",
 				 EXT4_I(inode)->i_file_acl);
 		error = -EFSCORRUPTED;
 		goto cleanup;
 	}
-	ext4_xattr_cache_insert(ext4_mb_cache, bh);
+	ext4_xattr_block_cache_insert(ea_block_cache, bh);
 	entry = BFIRST(bh);
-	error = ext4_xattr_find_entry(&entry, name_index, name, bh->b_size, 1);
-	if (error == -EFSCORRUPTED)
-		goto bad_block;
+	error = ext4_xattr_find_entry(&entry, name_index, name, 1);
 	if (error)
 		goto cleanup;
 	size = le32_to_cpu(entry->e_value_size);
@@ -342,8 +502,15 @@ bad_block:
 		error = -ERANGE;
 		if (size > buffer_size)
 			goto cleanup;
-		memcpy(buffer, bh->b_data + le16_to_cpu(entry->e_value_offs),
-		       size);
+		if (entry->e_value_inum) {
+			error = ext4_xattr_inode_get(inode, entry, buffer,
+						     size);
+			if (error)
+				goto cleanup;
+		} else {
+			memcpy(buffer, bh->b_data +
+			       le16_to_cpu(entry->e_value_offs), size);
+		}
 	}
 	error = size;
 
@@ -371,13 +538,12 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
 		return error;
 	raw_inode = ext4_raw_inode(&iloc);
 	header = IHDR(inode, raw_inode);
-	entry = IFIRST(header);
 	end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
 	error = xattr_check_inode(inode, header, end);
 	if (error)
 		goto cleanup;
-	error = ext4_xattr_find_entry(&entry, name_index, name,
-				      end - (void *)entry, 0);
+	entry = IFIRST(header);
+	error = ext4_xattr_find_entry(&entry, name_index, name, 0);
 	if (error)
 		goto cleanup;
 	size = le32_to_cpu(entry->e_value_size);
@@ -385,8 +551,15 @@ ext4_xattr_ibody_get(struct inode *inode, int name_index, const char *name,
 		error = -ERANGE;
 		if (size > buffer_size)
 			goto cleanup;
-		memcpy(buffer, (void *)IFIRST(header) +
-		       le16_to_cpu(entry->e_value_offs), size);
+		if (entry->e_value_inum) {
+			error = ext4_xattr_inode_get(inode, entry, buffer,
+						     size);
+			if (error)
+				goto cleanup;
+		} else {
+			memcpy(buffer, (void *)IFIRST(header) +
+			       le16_to_cpu(entry->e_value_offs), size);
+		}
 	}
 	error = size;
 
@@ -411,6 +584,9 @@ ext4_xattr_get(struct inode *inode, int name_index, const char *name,
 {
 	int error;
 
+	if (unlikely(ext4_forced_shutdown(EXT4_SB(inode->i_sb))))
+		return -EIO;
+
 	if (strlen(name) > 255)
 		return -ERANGE;
 
@@ -460,7 +636,6 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 	struct inode *inode = d_inode(dentry);
 	struct buffer_head *bh = NULL;
 	int error;
-	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
 
 	ea_idebug(inode, "buffer=%p, buffer_size=%ld",
 		  buffer, (long)buffer_size);
@@ -482,7 +657,7 @@ ext4_xattr_block_list(struct dentry *dentry, char *buffer, size_t buffer_size)
 		error = -EFSCORRUPTED;
 		goto cleanup;
 	}
-	ext4_xattr_cache_insert(ext4_mb_cache, bh);
+	ext4_xattr_block_cache_insert(EA_BLOCK_CACHE(inode), bh);
 	error = ext4_xattr_list_entries(dentry, BFIRST(bh), buffer, buffer_size);
 
 cleanup:
@@ -521,7 +696,9 @@ cleanup:
 }
 
 /*
- * ext4_xattr_list()
+ * Inode operation listxattr()
+ *
+ * d_inode(dentry)->i_rwsem: don't care
  *
  * Copy a list of attribute names into the buffer
  * provided, or compute the buffer size required.
@@ -530,8 +707,8 @@ cleanup:
  * Returns a negative error number on failure, or the number of bytes
  * used / required on success.
  */
-static int
-ext4_xattr_list(struct dentry *dentry, char *buffer, size_t buffer_size)
+ssize_t
+ext4_listxattr(struct dentry *dentry, char *buffer, size_t buffer_size)
 {
 	int ret, ret2;
 
@@ -569,15 +746,445 @@ static void ext4_xattr_update_super_block(handle_t *handle,
 	}
 }
 
+int ext4_get_inode_usage(struct inode *inode, qsize_t *usage)
+{
+	struct ext4_iloc iloc = { .bh = NULL };
+	struct buffer_head *bh = NULL;
+	struct ext4_inode *raw_inode;
+	struct ext4_xattr_ibody_header *header;
+	struct ext4_xattr_entry *entry;
+	qsize_t ea_inode_refs = 0;
+	void *end;
+	int ret;
+
+	lockdep_assert_held_read(&EXT4_I(inode)->xattr_sem);
+
+	if (ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
+		ret = ext4_get_inode_loc(inode, &iloc);
+		if (ret)
+			goto out;
+		raw_inode = ext4_raw_inode(&iloc);
+		header = IHDR(inode, raw_inode);
+		end = (void *)raw_inode + EXT4_SB(inode->i_sb)->s_inode_size;
+		ret = xattr_check_inode(inode, header, end);
+		if (ret)
+			goto out;
+
+		for (entry = IFIRST(header); !IS_LAST_ENTRY(entry);
+		     entry = EXT4_XATTR_NEXT(entry))
+			if (entry->e_value_inum)
+				ea_inode_refs++;
+	}
+
+	if (EXT4_I(inode)->i_file_acl) {
+		bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+		if (!bh) {
+			ret = -EIO;
+			goto out;
+		}
+
+		if (ext4_xattr_check_block(inode, bh)) {
+			ret = -EFSCORRUPTED;
+			goto out;
+		}
+
+		for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry);
+		     entry = EXT4_XATTR_NEXT(entry))
+			if (entry->e_value_inum)
+				ea_inode_refs++;
+	}
+	*usage = ea_inode_refs + 1;
+	ret = 0;
+out:
+	brelse(iloc.bh);
+	brelse(bh);
+	return ret;
+}
+
+static inline size_t round_up_cluster(struct inode *inode, size_t length)
+{
+	struct super_block *sb = inode->i_sb;
+	size_t cluster_size = 1 << (EXT4_SB(sb)->s_cluster_bits +
+				    inode->i_blkbits);
+	size_t mask = ~(cluster_size - 1);
+
+	return (length + cluster_size - 1) & mask;
+}
+
+static int ext4_xattr_inode_alloc_quota(struct inode *inode, size_t len)
+{
+	int err;
+
+	err = dquot_alloc_inode(inode);
+	if (err)
+		return err;
+	err = dquot_alloc_space_nodirty(inode, round_up_cluster(inode, len));
+	if (err)
+		dquot_free_inode(inode);
+	return err;
+}
+
+static void ext4_xattr_inode_free_quota(struct inode *inode, size_t len)
+{
+	dquot_free_space_nodirty(inode, round_up_cluster(inode, len));
+	dquot_free_inode(inode);
+}
+
+int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode,
+			     struct buffer_head *block_bh, size_t value_len,
+			     bool is_create)
+{
+	int credits;
+	int blocks;
+
+	/*
+	 * 1) Owner inode update
+	 * 2) Ref count update on old xattr block
+	 * 3) new xattr block
+	 * 4) block bitmap update for new xattr block
+	 * 5) group descriptor for new xattr block
+	 * 6) block bitmap update for old xattr block
+	 * 7) group descriptor for old block
+	 *
+	 * 6 & 7 can happen if we have two racing threads T_a and T_b
+	 * which are each trying to set an xattr on inodes I_a and I_b
+	 * which were both initially sharing an xattr block.
+	 */
+	credits = 7;
+
+	/* Quota updates. */
+	credits += EXT4_MAXQUOTAS_TRANS_BLOCKS(sb);
+
+	/*
+	 * In case of inline data, we may push out the data to a block,
+	 * so we need to reserve credits for this eventuality
+	 */
+	if (inode && ext4_has_inline_data(inode))
+		credits += ext4_writepage_trans_blocks(inode) + 1;
+
+	/* We are done if ea_inode feature is not enabled. */
+	if (!ext4_has_feature_ea_inode(sb))
+		return credits;
+
+	/* New ea_inode, inode map, block bitmap, group descriptor. */
+	credits += 4;
+
+	/* Data blocks. */
+	blocks = (value_len + sb->s_blocksize - 1) >> sb->s_blocksize_bits;
+
+	/* Indirection block or one level of extent tree. */
+	blocks += 1;
+
+	/* Block bitmap and group descriptor updates for each block. */
+	credits += blocks * 2;
+
+	/* Blocks themselves. */
+	credits += blocks;
+
+	if (!is_create) {
+		/* Dereference ea_inode holding old xattr value.
+		 * Old ea_inode, inode map, block bitmap, group descriptor.
+		 */
+		credits += 4;
+
+		/* Data blocks for old ea_inode. */
+		blocks = XATTR_SIZE_MAX >> sb->s_blocksize_bits;
+
+		/* Indirection block or one level of extent tree for old
+		 * ea_inode.
+		 */
+		blocks += 1;
+
+		/* Block bitmap and group descriptor updates for each block. */
+		credits += blocks * 2;
+	}
+
+	/* We may need to clone the existing xattr block in which case we need
+	 * to increment ref counts for existing ea_inodes referenced by it.
+	 */
+	if (block_bh) {
+		struct ext4_xattr_entry *entry = BFIRST(block_bh);
+
+		for (; !IS_LAST_ENTRY(entry); entry = EXT4_XATTR_NEXT(entry))
+			if (entry->e_value_inum)
+				/* Ref count update on ea_inode. */
+				credits += 1;
+	}
+	return credits;
+}
+
+static int ext4_xattr_ensure_credits(handle_t *handle, struct inode *inode,
+				     int credits, struct buffer_head *bh,
+				     bool dirty, bool block_csum)
+{
+	int error;
+
+	if (!ext4_handle_valid(handle))
+		return 0;
+
+	if (handle->h_buffer_credits >= credits)
+		return 0;
+
+	error = ext4_journal_extend(handle, credits - handle->h_buffer_credits);
+	if (!error)
+		return 0;
+	if (error < 0) {
+		ext4_warning(inode->i_sb, "Extend journal (error %d)", error);
+		return error;
+	}
+
+	if (bh && dirty) {
+		if (block_csum)
+			ext4_xattr_block_csum_set(inode, bh);
+		error = ext4_handle_dirty_metadata(handle, NULL, bh);
+		if (error) {
+			ext4_warning(inode->i_sb, "Handle metadata (error %d)",
+				     error);
+			return error;
+		}
+	}
+
+	error = ext4_journal_restart(handle, credits);
+	if (error) {
+		ext4_warning(inode->i_sb, "Restart journal (error %d)", error);
+		return error;
+	}
+
+	if (bh) {
+		error = ext4_journal_get_write_access(handle, bh);
+		if (error) {
+			ext4_warning(inode->i_sb,
+				     "Get write access failed (error %d)",
+				     error);
+			return error;
+		}
+	}
+	return 0;
+}
+
+static int ext4_xattr_inode_update_ref(handle_t *handle, struct inode *ea_inode,
+				       int ref_change)
+{
+	struct mb_cache *ea_inode_cache = EA_INODE_CACHE(ea_inode);
+	struct ext4_iloc iloc;
+	s64 ref_count;
+	u32 hash;
+	int ret;
+
+	inode_lock(ea_inode);
+
+	ret = ext4_reserve_inode_write(handle, ea_inode, &iloc);
+	if (ret) {
+		iloc.bh = NULL;
+		goto out;
+	}
+
+	ref_count = ext4_xattr_inode_get_ref(ea_inode);
+	ref_count += ref_change;
+	ext4_xattr_inode_set_ref(ea_inode, ref_count);
+
+	if (ref_change > 0) {
+		WARN_ONCE(ref_count <= 0, "EA inode %lu ref_count=%lld",
+			  ea_inode->i_ino, ref_count);
+
+		if (ref_count == 1) {
+			WARN_ONCE(ea_inode->i_nlink, "EA inode %lu i_nlink=%u",
+				  ea_inode->i_ino, ea_inode->i_nlink);
+
+			set_nlink(ea_inode, 1);
+			ext4_orphan_del(handle, ea_inode);
+
+			if (ea_inode_cache) {
+				hash = ext4_xattr_inode_get_hash(ea_inode);
+				mb_cache_entry_create(ea_inode_cache,
+						      GFP_NOFS, hash,
+						      ea_inode->i_ino,
+						      true /* reusable */);
+			}
+		}
+	} else {
+		WARN_ONCE(ref_count < 0, "EA inode %lu ref_count=%lld",
+			  ea_inode->i_ino, ref_count);
+
+		if (ref_count == 0) {
+			WARN_ONCE(ea_inode->i_nlink != 1,
+				  "EA inode %lu i_nlink=%u",
+				  ea_inode->i_ino, ea_inode->i_nlink);
+
+			clear_nlink(ea_inode);
+			ext4_orphan_add(handle, ea_inode);
+
+			if (ea_inode_cache) {
+				hash = ext4_xattr_inode_get_hash(ea_inode);
+				mb_cache_entry_delete(ea_inode_cache, hash,
+						      ea_inode->i_ino);
+			}
+		}
+	}
+
+	ret = ext4_mark_iloc_dirty(handle, ea_inode, &iloc);
+	iloc.bh = NULL;
+	if (ret)
+		ext4_warning_inode(ea_inode,
+				   "ext4_mark_iloc_dirty() failed ret=%d", ret);
+out:
+	brelse(iloc.bh);
+	inode_unlock(ea_inode);
+	return ret;
+}
+
+static int ext4_xattr_inode_inc_ref(handle_t *handle, struct inode *ea_inode)
+{
+	return ext4_xattr_inode_update_ref(handle, ea_inode, 1);
+}
+
+static int ext4_xattr_inode_dec_ref(handle_t *handle, struct inode *ea_inode)
+{
+	return ext4_xattr_inode_update_ref(handle, ea_inode, -1);
+}
+
+static int ext4_xattr_inode_inc_ref_all(handle_t *handle, struct inode *parent,
+					struct ext4_xattr_entry *first)
+{
+	struct inode *ea_inode;
+	struct ext4_xattr_entry *entry;
+	struct ext4_xattr_entry *failed_entry;
+	unsigned int ea_ino;
+	int err, saved_err;
+
+	for (entry = first; !IS_LAST_ENTRY(entry);
+	     entry = EXT4_XATTR_NEXT(entry)) {
+		if (!entry->e_value_inum)
+			continue;
+		ea_ino = le32_to_cpu(entry->e_value_inum);
+		err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode);
+		if (err)
+			goto cleanup;
+		err = ext4_xattr_inode_inc_ref(handle, ea_inode);
+		if (err) {
+			ext4_warning_inode(ea_inode, "inc ref error %d", err);
+			iput(ea_inode);
+			goto cleanup;
+		}
+		iput(ea_inode);
+	}
+	return 0;
+
+cleanup:
+	saved_err = err;
+	failed_entry = entry;
+
+	for (entry = first; entry != failed_entry;
+	     entry = EXT4_XATTR_NEXT(entry)) {
+		if (!entry->e_value_inum)
+			continue;
+		ea_ino = le32_to_cpu(entry->e_value_inum);
+		err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode);
+		if (err) {
+			ext4_warning(parent->i_sb,
+				     "cleanup ea_ino %u iget error %d", ea_ino,
+				     err);
+			continue;
+		}
+		err = ext4_xattr_inode_dec_ref(handle, ea_inode);
+		if (err)
+			ext4_warning_inode(ea_inode, "cleanup dec ref error %d",
+					   err);
+		iput(ea_inode);
+	}
+	return saved_err;
+}
+
+static void
+ext4_xattr_inode_dec_ref_all(handle_t *handle, struct inode *parent,
+			     struct buffer_head *bh,
+			     struct ext4_xattr_entry *first, bool block_csum,
+			     struct ext4_xattr_inode_array **ea_inode_array,
+			     int extra_credits, bool skip_quota)
+{
+	struct inode *ea_inode;
+	struct ext4_xattr_entry *entry;
+	bool dirty = false;
+	unsigned int ea_ino;
+	int err;
+	int credits;
+
+	/* One credit for dec ref on ea_inode, one for orphan list addition, */
+	credits = 2 + extra_credits;
+
+	for (entry = first; !IS_LAST_ENTRY(entry);
+	     entry = EXT4_XATTR_NEXT(entry)) {
+		if (!entry->e_value_inum)
+			continue;
+		ea_ino = le32_to_cpu(entry->e_value_inum);
+		err = ext4_xattr_inode_iget(parent, ea_ino, &ea_inode);
+		if (err)
+			continue;
+
+		err = ext4_expand_inode_array(ea_inode_array, ea_inode);
+		if (err) {
+			ext4_warning_inode(ea_inode,
+					   "Expand inode array err=%d", err);
+			iput(ea_inode);
+			continue;
+		}
+
+		err = ext4_xattr_ensure_credits(handle, parent, credits, bh,
+						dirty, block_csum);
+		if (err) {
+			ext4_warning_inode(ea_inode, "Ensure credits err=%d",
+					   err);
+			continue;
+		}
+
+		err = ext4_xattr_inode_dec_ref(handle, ea_inode);
+		if (err) {
+			ext4_warning_inode(ea_inode, "ea_inode dec ref err=%d",
+					   err);
+			continue;
+		}
+
+		if (!skip_quota)
+			ext4_xattr_inode_free_quota(parent,
+					      le32_to_cpu(entry->e_value_size));
+
+		/*
+		 * Forget about ea_inode within the same transaction that
+		 * decrements the ref count. This avoids duplicate decrements in
+		 * case the rest of the work spills over to subsequent
+		 * transactions.
+		 */
+		entry->e_value_inum = 0;
+		entry->e_value_size = 0;
+
+		dirty = true;
+	}
+
+	if (dirty) {
+		/*
+		 * Note that we are deliberately skipping csum calculation for
+		 * the final update because we do not expect any journal
+		 * restarts until xattr block is freed.
+		 */
+
+		err = ext4_handle_dirty_metadata(handle, NULL, bh);
+		if (err)
+			ext4_warning_inode(parent,
+					   "handle dirty metadata err=%d", err);
+	}
+}
+
 /*
  * Release the xattr block BH: If the reference count is > 1, decrement it;
  * otherwise free the block.
  */
 static void
 ext4_xattr_release_block(handle_t *handle, struct inode *inode,
-			 struct buffer_head *bh)
+			 struct buffer_head *bh,
+			 struct ext4_xattr_inode_array **ea_inode_array,
+			 int extra_credits)
 {
-	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
 	u32 hash, ref;
 	int error = 0;
 
@@ -595,9 +1202,19 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 		 * This must happen under buffer lock for
 		 * ext4_xattr_block_set() to reliably detect freed block
 		 */
-		mb_cache_entry_delete_block(ext4_mb_cache, hash, bh->b_blocknr);
+		if (ea_block_cache)
+			mb_cache_entry_delete(ea_block_cache, hash,
+					      bh->b_blocknr);
 		get_bh(bh);
 		unlock_buffer(bh);
+
+		if (ext4_has_feature_ea_inode(inode->i_sb))
+			ext4_xattr_inode_dec_ref_all(handle, inode, bh,
+						     BFIRST(bh),
+						     true /* block_csum */,
+						     ea_inode_array,
+						     extra_credits,
+						     true /* skip_quota */);
 		ext4_free_blocks(handle, inode, bh, 0, 1,
 				 EXT4_FREE_BLOCKS_METADATA |
 				 EXT4_FREE_BLOCKS_FORGET);
@@ -607,31 +1224,32 @@ ext4_xattr_release_block(handle_t *handle, struct inode *inode,
 		if (ref == EXT4_XATTR_REFCOUNT_MAX - 1) {
 			struct mb_cache_entry *ce;
 
-			ce = mb_cache_entry_get(ext4_mb_cache, hash,
-						bh->b_blocknr);
-			if (ce) {
-				ce->e_reusable = 1;
-				mb_cache_entry_put(ext4_mb_cache, ce);
+			if (ea_block_cache) {
+				ce = mb_cache_entry_get(ea_block_cache, hash,
+							bh->b_blocknr);
+				if (ce) {
+					ce->e_reusable = 1;
+					mb_cache_entry_put(ea_block_cache, ce);
+				}
 			}
 		}
 
+		ext4_xattr_block_csum_set(inode, bh);
 		/*
 		 * Beware of this ugliness: Releasing of xattr block references
 		 * from different inodes can race and so we have to protect
 		 * from a race where someone else frees the block (and releases
 		 * its journal_head) before we are done dirtying the buffer. In
 		 * nojournal mode this race is harmless and we actually cannot
-		 * call ext4_handle_dirty_xattr_block() with locked buffer as
+		 * call ext4_handle_dirty_metadata() with locked buffer as
 		 * that function can call sync_dirty_buffer() so for that case
 		 * we handle the dirtying after unlocking the buffer.
 		 */
 		if (ext4_handle_valid(handle))
-			error = ext4_handle_dirty_xattr_block(handle, inode,
-							      bh);
+			error = ext4_handle_dirty_metadata(handle, inode, bh);
 		unlock_buffer(bh);
 		if (!ext4_handle_valid(handle))
-			error = ext4_handle_dirty_xattr_block(handle, inode,
-							      bh);
+			error = ext4_handle_dirty_metadata(handle, inode, bh);
 		if (IS_SYNC(inode))
 			ext4_handle_sync(handle);
 		dquot_free_block(inode, EXT4_C2B(EXT4_SB(inode->i_sb), 1));
@@ -651,7 +1269,7 @@ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last,
 				    size_t *min_offs, void *base, int *total)
 {
 	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
-		if (last->e_value_size) {
+		if (!last->e_value_inum && last->e_value_size) {
 			size_t offs = le16_to_cpu(last->e_value_offs);
 			if (offs < *min_offs)
 				*min_offs = offs;
@@ -662,113 +1280,454 @@ static size_t ext4_xattr_free_space(struct ext4_xattr_entry *last,
 	return (*min_offs - ((void *)last - base) - sizeof(__u32));
 }
 
-static int
-ext4_xattr_set_entry(struct ext4_xattr_info *i, struct ext4_xattr_search *s)
+/*
+ * Write the value of the EA in an inode.
+ */
+static int ext4_xattr_inode_write(handle_t *handle, struct inode *ea_inode,
+				  const void *buf, int bufsize)
+{
+	struct buffer_head *bh = NULL;
+	unsigned long block = 0;
+	int blocksize = ea_inode->i_sb->s_blocksize;
+	int max_blocks = (bufsize + blocksize - 1) >> ea_inode->i_blkbits;
+	int csize, wsize = 0;
+	int ret = 0;
+	int retries = 0;
+
+retry:
+	while (ret >= 0 && ret < max_blocks) {
+		struct ext4_map_blocks map;
+		map.m_lblk = block += ret;
+		map.m_len = max_blocks -= ret;
+
+		ret = ext4_map_blocks(handle, ea_inode, &map,
+				      EXT4_GET_BLOCKS_CREATE);
+		if (ret <= 0) {
+			ext4_mark_inode_dirty(handle, ea_inode);
+			if (ret == -ENOSPC &&
+			    ext4_should_retry_alloc(ea_inode->i_sb, &retries)) {
+				ret = 0;
+				goto retry;
+			}
+			break;
+		}
+	}
+
+	if (ret < 0)
+		return ret;
+
+	block = 0;
+	while (wsize < bufsize) {
+		if (bh != NULL)
+			brelse(bh);
+		csize = (bufsize - wsize) > blocksize ? blocksize :
+								bufsize - wsize;
+		bh = ext4_getblk(handle, ea_inode, block, 0);
+		if (IS_ERR(bh))
+			return PTR_ERR(bh);
+		ret = ext4_journal_get_write_access(handle, bh);
+		if (ret)
+			goto out;
+
+		memcpy(bh->b_data, buf, csize);
+		set_buffer_uptodate(bh);
+		ext4_handle_dirty_metadata(handle, ea_inode, bh);
+
+		buf += csize;
+		wsize += csize;
+		block += 1;
+	}
+
+	inode_lock(ea_inode);
+	i_size_write(ea_inode, wsize);
+	ext4_update_i_disksize(ea_inode, wsize);
+	inode_unlock(ea_inode);
+
+	ext4_mark_inode_dirty(handle, ea_inode);
+
+out:
+	brelse(bh);
+
+	return ret;
+}
+
+/*
+ * Create an inode to store the value of a large EA.
+ */
+static struct inode *ext4_xattr_inode_create(handle_t *handle,
+					     struct inode *inode, u32 hash)
+{
+	struct inode *ea_inode = NULL;
+	uid_t owner[2] = { i_uid_read(inode), i_gid_read(inode) };
+	int err;
+
+	/*
+	 * Let the next inode be the goal, so we try and allocate the EA inode
+	 * in the same group, or nearby one.
+	 */
+	ea_inode = ext4_new_inode(handle, inode->i_sb->s_root->d_inode,
+				  S_IFREG | 0600, NULL, inode->i_ino + 1, owner,
+				  EXT4_EA_INODE_FL);
+	if (!IS_ERR(ea_inode)) {
+		ea_inode->i_op = &ext4_file_inode_operations;
+		ea_inode->i_fop = &ext4_file_operations;
+		ext4_set_aops(ea_inode);
+		ext4_xattr_inode_set_class(ea_inode);
+		unlock_new_inode(ea_inode);
+		ext4_xattr_inode_set_ref(ea_inode, 1);
+		ext4_xattr_inode_set_hash(ea_inode, hash);
+		err = ext4_mark_inode_dirty(handle, ea_inode);
+		if (!err)
+			err = ext4_inode_attach_jinode(ea_inode);
+		if (err) {
+			iput(ea_inode);
+			return ERR_PTR(err);
+		}
+
+		/*
+		 * Xattr inodes are shared therefore quota charging is performed
+		 * at a higher level.
+		 */
+		dquot_free_inode(ea_inode);
+		dquot_drop(ea_inode);
+		inode_lock(ea_inode);
+		ea_inode->i_flags |= S_NOQUOTA;
+		inode_unlock(ea_inode);
+	}
+
+	return ea_inode;
+}
+
+static struct inode *
+ext4_xattr_inode_cache_find(struct inode *inode, const void *value,
+			    size_t value_len, u32 hash)
+{
+	struct inode *ea_inode;
+	struct mb_cache_entry *ce;
+	struct mb_cache *ea_inode_cache = EA_INODE_CACHE(inode);
+	void *ea_data;
+
+	if (!ea_inode_cache)
+		return NULL;
+
+	ce = mb_cache_entry_find_first(ea_inode_cache, hash);
+	if (!ce)
+		return NULL;
+
+	ea_data = ext4_kvmalloc(value_len, GFP_NOFS);
+	if (!ea_data) {
+		mb_cache_entry_put(ea_inode_cache, ce);
+		return NULL;
+	}
+
+	while (ce) {
+		ea_inode = ext4_iget(inode->i_sb, ce->e_value);
+		if (!IS_ERR(ea_inode) &&
+		    !is_bad_inode(ea_inode) &&
+		    (EXT4_I(ea_inode)->i_flags & EXT4_EA_INODE_FL) &&
+		    i_size_read(ea_inode) == value_len &&
+		    !ext4_xattr_inode_read(ea_inode, ea_data, value_len) &&
+		    !ext4_xattr_inode_verify_hashes(ea_inode, NULL, ea_data,
+						    value_len) &&
+		    !memcmp(value, ea_data, value_len)) {
+			mb_cache_entry_touch(ea_inode_cache, ce);
+			mb_cache_entry_put(ea_inode_cache, ce);
+			kvfree(ea_data);
+			return ea_inode;
+		}
+
+		if (!IS_ERR(ea_inode))
+			iput(ea_inode);
+		ce = mb_cache_entry_find_next(ea_inode_cache, ce);
+	}
+	kvfree(ea_data);
+	return NULL;
+}
+
+/*
+ * Add value of the EA in an inode.
+ */
+static int ext4_xattr_inode_lookup_create(handle_t *handle, struct inode *inode,
+					  const void *value, size_t value_len,
+					  struct inode **ret_inode)
+{
+	struct inode *ea_inode;
+	u32 hash;
+	int err;
+
+	hash = ext4_xattr_inode_hash(EXT4_SB(inode->i_sb), value, value_len);
+	ea_inode = ext4_xattr_inode_cache_find(inode, value, value_len, hash);
+	if (ea_inode) {
+		err = ext4_xattr_inode_inc_ref(handle, ea_inode);
+		if (err) {
+			iput(ea_inode);
+			return err;
+		}
+
+		*ret_inode = ea_inode;
+		return 0;
+	}
+
+	/* Create an inode for the EA value */
+	ea_inode = ext4_xattr_inode_create(handle, inode, hash);
+	if (IS_ERR(ea_inode))
+		return PTR_ERR(ea_inode);
+
+	err = ext4_xattr_inode_write(handle, ea_inode, value, value_len);
+	if (err) {
+		ext4_xattr_inode_dec_ref(handle, ea_inode);
+		iput(ea_inode);
+		return err;
+	}
+
+	if (EA_INODE_CACHE(inode))
+		mb_cache_entry_create(EA_INODE_CACHE(inode), GFP_NOFS, hash,
+				      ea_inode->i_ino, true /* reusable */);
+
+	*ret_inode = ea_inode;
+	return 0;
+}
+
+/*
+ * Reserve min(block_size/8, 1024) bytes for xattr entries/names if ea_inode
+ * feature is enabled.
+ */
+#define EXT4_XATTR_BLOCK_RESERVE(inode)	min(i_blocksize(inode)/8, 1024U)
+
+static int ext4_xattr_set_entry(struct ext4_xattr_info *i,
+				struct ext4_xattr_search *s,
+				handle_t *handle, struct inode *inode,
+				bool is_block)
 {
 	struct ext4_xattr_entry *last;
-	size_t free, min_offs = s->end - s->base, name_len = strlen(i->name);
+	struct ext4_xattr_entry *here = s->here;
+	size_t min_offs = s->end - s->base, name_len = strlen(i->name);
+	int in_inode = i->in_inode;
+	struct inode *old_ea_inode = NULL;
+	struct inode *new_ea_inode = NULL;
+	size_t old_size, new_size;
+	int ret;
+
+	/* Space used by old and new values. */
+	old_size = (!s->not_found && !here->e_value_inum) ?
+			EXT4_XATTR_SIZE(le32_to_cpu(here->e_value_size)) : 0;
+	new_size = (i->value && !in_inode) ? EXT4_XATTR_SIZE(i->value_len) : 0;
+
+	/*
+	 * Optimization for the simple case when old and new values have the
+	 * same padded sizes. Not applicable if external inodes are involved.
+	 */
+	if (new_size && new_size == old_size) {
+		size_t offs = le16_to_cpu(here->e_value_offs);
+		void *val = s->base + offs;
+
+		here->e_value_size = cpu_to_le32(i->value_len);
+		if (i->value == EXT4_ZERO_XATTR_VALUE) {
+			memset(val, 0, new_size);
+		} else {
+			memcpy(val, i->value, i->value_len);
+			/* Clear padding bytes. */
+			memset(val + i->value_len, 0, new_size - i->value_len);
+		}
+		return 0;
+	}
 
 	/* Compute min_offs and last. */
 	last = s->first;
 	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
-		if (last->e_value_size) {
+		if (!last->e_value_inum && last->e_value_size) {
 			size_t offs = le16_to_cpu(last->e_value_offs);
 			if (offs < min_offs)
 				min_offs = offs;
 		}
 	}
-	free = min_offs - ((void *)last - s->base) - sizeof(__u32);
-	if (!s->not_found) {
-		if (s->here->e_value_size) {
-			size_t size = le32_to_cpu(s->here->e_value_size);
-			free += EXT4_XATTR_SIZE(size);
-		}
-		free += EXT4_XATTR_LEN(name_len);
-	}
+
+	/* Check whether we have enough space. */
 	if (i->value) {
-		if (free < EXT4_XATTR_LEN(name_len) +
-			   EXT4_XATTR_SIZE(i->value_len))
-			return -ENOSPC;
+		size_t free;
+
+		free = min_offs - ((void *)last - s->base) - sizeof(__u32);
+		if (!s->not_found)
+			free += EXT4_XATTR_LEN(name_len) + old_size;
+
+		if (free < EXT4_XATTR_LEN(name_len) + new_size) {
+			ret = -ENOSPC;
+			goto out;
+		}
+
+		/*
+		 * If storing the value in an external inode is an option,
+		 * reserve space for xattr entries/names in the external
+		 * attribute block so that a long value does not occupy the
+		 * whole space and prevent futher entries being added.
+		 */
+		if (ext4_has_feature_ea_inode(inode->i_sb) &&
+		    new_size && is_block &&
+		    (min_offs + old_size - new_size) <
+					EXT4_XATTR_BLOCK_RESERVE(inode)) {
+			ret = -ENOSPC;
+			goto out;
+		}
 	}
 
-	if (i->value && s->not_found) {
-		/* Insert the new name. */
-		size_t size = EXT4_XATTR_LEN(name_len);
-		size_t rest = (void *)last - (void *)s->here + sizeof(__u32);
-		memmove((void *)s->here + size, s->here, rest);
-		memset(s->here, 0, size);
-		s->here->e_name_index = i->name_index;
-		s->here->e_name_len = name_len;
-		memcpy(s->here->e_name, i->name, name_len);
-	} else {
-		if (s->here->e_value_size) {
-			void *first_val = s->base + min_offs;
-			size_t offs = le16_to_cpu(s->here->e_value_offs);
-			void *val = s->base + offs;
-			size_t size = EXT4_XATTR_SIZE(
-				le32_to_cpu(s->here->e_value_size));
-
-			if (i->value && size == EXT4_XATTR_SIZE(i->value_len)) {
-				/* The old and the new value have the same
-				   size. Just replace. */
-				s->here->e_value_size =
-					cpu_to_le32(i->value_len);
-				if (i->value == EXT4_ZERO_XATTR_VALUE) {
-					memset(val, 0, size);
-				} else {
-					/* Clear pad bytes first. */
-					memset(val + size - EXT4_XATTR_PAD, 0,
-					       EXT4_XATTR_PAD);
-					memcpy(val, i->value, i->value_len);
-				}
-				return 0;
-			}
+	/*
+	 * Getting access to old and new ea inodes is subject to failures.
+	 * Finish that work before doing any modifications to the xattr data.
+	 */
+	if (!s->not_found && here->e_value_inum) {
+		ret = ext4_xattr_inode_iget(inode,
+					    le32_to_cpu(here->e_value_inum),
+					    &old_ea_inode);
+		if (ret) {
+			old_ea_inode = NULL;
+			goto out;
+		}
+	}
+	if (i->value && in_inode) {
+		WARN_ON_ONCE(!i->value_len);
+
+		ret = ext4_xattr_inode_alloc_quota(inode, i->value_len);
+		if (ret)
+			goto out;
+
+		ret = ext4_xattr_inode_lookup_create(handle, inode, i->value,
+						     i->value_len,
+						     &new_ea_inode);
+		if (ret) {
+			new_ea_inode = NULL;
+			ext4_xattr_inode_free_quota(inode, i->value_len);
+			goto out;
+		}
+	}
 
-			/* Remove the old value. */
-			memmove(first_val + size, first_val, val - first_val);
-			memset(first_val, 0, size);
-			s->here->e_value_size = 0;
-			s->here->e_value_offs = 0;
-			min_offs += size;
-
-			/* Adjust all value offsets. */
-			last = s->first;
-			while (!IS_LAST_ENTRY(last)) {
-				size_t o = le16_to_cpu(last->e_value_offs);
-				if (last->e_value_size && o < offs)
-					last->e_value_offs =
-						cpu_to_le16(o + size);
-				last = EXT4_XATTR_NEXT(last);
+	if (old_ea_inode) {
+		/* We are ready to release ref count on the old_ea_inode. */
+		ret = ext4_xattr_inode_dec_ref(handle, old_ea_inode);
+		if (ret) {
+			/* Release newly required ref count on new_ea_inode. */
+			if (new_ea_inode) {
+				int err;
+
+				err = ext4_xattr_inode_dec_ref(handle,
+							       new_ea_inode);
+				if (err)
+					ext4_warning_inode(new_ea_inode,
+						  "dec ref new_ea_inode err=%d",
+						  err);
+				ext4_xattr_inode_free_quota(inode,
+							    i->value_len);
 			}
+			goto out;
 		}
-		if (!i->value) {
-			/* Remove the old name. */
-			size_t size = EXT4_XATTR_LEN(name_len);
-			last = ENTRY((void *)last - size);
-			memmove(s->here, (void *)s->here + size,
-				(void *)last - (void *)s->here + sizeof(__u32));
-			memset(last, 0, size);
+
+		ext4_xattr_inode_free_quota(inode,
+					    le32_to_cpu(here->e_value_size));
+	}
+
+	/* No failures allowed past this point. */
+
+	if (!s->not_found && here->e_value_offs) {
+		/* Remove the old value. */
+		void *first_val = s->base + min_offs;
+		size_t offs = le16_to_cpu(here->e_value_offs);
+		void *val = s->base + offs;
+
+		memmove(first_val + old_size, first_val, val - first_val);
+		memset(first_val, 0, old_size);
+		min_offs += old_size;
+
+		/* Adjust all value offsets. */
+		last = s->first;
+		while (!IS_LAST_ENTRY(last)) {
+			size_t o = le16_to_cpu(last->e_value_offs);
+
+			if (!last->e_value_inum &&
+			    last->e_value_size && o < offs)
+				last->e_value_offs = cpu_to_le16(o + old_size);
+			last = EXT4_XATTR_NEXT(last);
 		}
 	}
 
+	if (!i->value) {
+		/* Remove old name. */
+		size_t size = EXT4_XATTR_LEN(name_len);
+
+		last = ENTRY((void *)last - size);
+		memmove(here, (void *)here + size,
+			(void *)last - (void *)here + sizeof(__u32));
+		memset(last, 0, size);
+	} else if (s->not_found) {
+		/* Insert new name. */
+		size_t size = EXT4_XATTR_LEN(name_len);
+		size_t rest = (void *)last - (void *)here + sizeof(__u32);
+
+		memmove((void *)here + size, here, rest);
+		memset(here, 0, size);
+		here->e_name_index = i->name_index;
+		here->e_name_len = name_len;
+		memcpy(here->e_name, i->name, name_len);
+	} else {
+		/* This is an update, reset value info. */
+		here->e_value_inum = 0;
+		here->e_value_offs = 0;
+		here->e_value_size = 0;
+	}
+
 	if (i->value) {
-		/* Insert the new value. */
-		s->here->e_value_size = cpu_to_le32(i->value_len);
-		if (i->value_len) {
-			size_t size = EXT4_XATTR_SIZE(i->value_len);
-			void *val = s->base + min_offs - size;
-			s->here->e_value_offs = cpu_to_le16(min_offs - size);
+		/* Insert new value. */
+		if (in_inode) {
+			here->e_value_inum = cpu_to_le32(new_ea_inode->i_ino);
+		} else if (i->value_len) {
+			void *val = s->base + min_offs - new_size;
+
+			here->e_value_offs = cpu_to_le16(min_offs - new_size);
 			if (i->value == EXT4_ZERO_XATTR_VALUE) {
-				memset(val, 0, size);
+				memset(val, 0, new_size);
 			} else {
-				/* Clear the pad bytes first. */
-				memset(val + size - EXT4_XATTR_PAD, 0,
-				       EXT4_XATTR_PAD);
 				memcpy(val, i->value, i->value_len);
+				/* Clear padding bytes. */
+				memset(val + i->value_len, 0,
+				       new_size - i->value_len);
 			}
 		}
+		here->e_value_size = cpu_to_le32(i->value_len);
 	}
-	return 0;
+
+	if (i->value) {
+		__le32 hash = 0;
+
+		/* Entry hash calculation. */
+		if (in_inode) {
+			__le32 crc32c_hash;
+
+			/*
+			 * Feed crc32c hash instead of the raw value for entry
+			 * hash calculation. This is to avoid walking
+			 * potentially long value buffer again.
+			 */
+			crc32c_hash = cpu_to_le32(
+				       ext4_xattr_inode_get_hash(new_ea_inode));
+			hash = ext4_xattr_hash_entry(here->e_name,
+						     here->e_name_len,
+						     &crc32c_hash, 1);
+		} else if (is_block) {
+			__le32 *value = s->base + min_offs - new_size;
+
+			hash = ext4_xattr_hash_entry(here->e_name,
+						     here->e_name_len, value,
+						     new_size >> 2);
+		}
+		here->e_hash = hash;
+	}
+
+	if (is_block)
+		ext4_xattr_rehash((struct ext4_xattr_header *)s->base);
+
+	ret = 0;
+out:
+	iput(old_ea_inode);
+	iput(new_ea_inode);
+	return ret;
 }
 
 struct ext4_xattr_block_find {
@@ -807,7 +1766,7 @@ ext4_xattr_block_find(struct inode *inode, struct ext4_xattr_info *i,
 		bs->s.end = bs->bh->b_data + bs->bh->b_size;
 		bs->s.here = bs->s.first;
 		error = ext4_xattr_find_entry(&bs->s.here, i->name_index,
-					      i->name, bs->bh->b_size, 1);
+					      i->name, 1);
 		if (error && error != -ENODATA)
 			goto cleanup;
 		bs->s.not_found = error;
@@ -825,15 +1784,16 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 {
 	struct super_block *sb = inode->i_sb;
 	struct buffer_head *new_bh = NULL;
-	struct ext4_xattr_search *s = &bs->s;
+	struct ext4_xattr_search s_copy = bs->s;
+	struct ext4_xattr_search *s = &s_copy;
 	struct mb_cache_entry *ce = NULL;
 	int error = 0;
-	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
+	struct inode *ea_inode = NULL;
+	size_t old_ea_inode_size = 0;
 
 #define header(x) ((struct ext4_xattr_header *)(x))
 
-	if (i->value && i->value_len > sb->s_blocksize)
-		return -ENOSPC;
 	if (s->base) {
 		BUFFER_TRACE(bs->bh, "get_write_access");
 		error = ext4_journal_get_write_access(handle, bs->bh);
@@ -849,24 +1809,23 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			 * ext4_xattr_block_set() to reliably detect modified
 			 * block
 			 */
-			mb_cache_entry_delete_block(ext4_mb_cache, hash,
-						    bs->bh->b_blocknr);
+			if (ea_block_cache)
+				mb_cache_entry_delete(ea_block_cache, hash,
+						      bs->bh->b_blocknr);
 			ea_bdebug(bs->bh, "modifying in-place");
-			error = ext4_xattr_set_entry(i, s);
-			if (!error) {
-				if (!IS_LAST_ENTRY(s->first))
-					ext4_xattr_rehash(header(s->base),
-							  s->here);
-				ext4_xattr_cache_insert(ext4_mb_cache,
-					bs->bh);
-			}
+			error = ext4_xattr_set_entry(i, s, handle, inode,
+						     true /* is_block */);
+			if (!error)
+				ext4_xattr_block_cache_insert(ea_block_cache,
+							      bs->bh);
+			ext4_xattr_block_csum_set(inode, bs->bh);
 			unlock_buffer(bs->bh);
 			if (error == -EFSCORRUPTED)
 				goto bad_block;
 			if (!error)
-				error = ext4_handle_dirty_xattr_block(handle,
-								      inode,
-								      bs->bh);
+				error = ext4_handle_dirty_metadata(handle,
+								   inode,
+								   bs->bh);
 			if (error)
 				goto cleanup;
 			goto inserted;
@@ -884,6 +1843,24 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 			header(s->base)->h_refcount = cpu_to_le32(1);
 			s->here = ENTRY(s->base + offset);
 			s->end = s->base + bs->bh->b_size;
+
+			/*
+			 * If existing entry points to an xattr inode, we need
+			 * to prevent ext4_xattr_set_entry() from decrementing
+			 * ref count on it because the reference belongs to the
+			 * original block. In this case, make the entry look
+			 * like it has an empty value.
+			 */
+			if (!s->not_found && s->here->e_value_inum) {
+				/*
+				 * Defer quota free call for previous inode
+				 * until success is guaranteed.
+				 */
+				old_ea_inode_size = le32_to_cpu(
+							s->here->e_value_size);
+				s->here->e_value_inum = 0;
+				s->here->e_value_size = 0;
+			}
 		}
 	} else {
 		/* Allocate a buffer where we construct the new block. */
@@ -900,17 +1877,33 @@ ext4_xattr_block_set(handle_t *handle, struct inode *inode,
 		s->end = s->base + sb->s_blocksize;
 	}
 
-	error = ext4_xattr_set_entry(i, s);
+	error = ext4_xattr_set_entry(i, s, handle, inode, true /* is_block */);
 	if (error == -EFSCORRUPTED)
 		goto bad_block;
 	if (error)
 		goto cleanup;
-	if (!IS_LAST_ENTRY(s->first))
-		ext4_xattr_rehash(header(s->base), s->here);
+
+	if (i->value && s->here->e_value_inum) {
+		unsigned int ea_ino;
+
+		/*
+		 * A ref count on ea_inode has been taken as part of the call to
+		 * ext4_xattr_set_entry() above. We would like to drop this
+		 * extra ref but we have to wait until the xattr block is
+		 * initialized and has its own ref count on the ea_inode.
+		 */
+		ea_ino = le32_to_cpu(s->here->e_value_inum);
+		error = ext4_xattr_inode_iget(inode, ea_ino, &ea_inode);
+		if (error) {
+			ea_inode = NULL;
+			goto cleanup;
+		}
+	}
 
 inserted:
 	if (!IS_LAST_ENTRY(s->first)) {
-		new_bh = ext4_xattr_cache_find(inode, header(s->base), &ce);
+		new_bh = ext4_xattr_block_cache_find(inode, header(s->base),
+						     &ce);
 		if (new_bh) {
 			/* We found an identical block in the cache. */
 			if (new_bh == bs->bh)
@@ -918,6 +1911,8 @@ inserted:
 			else {
 				u32 ref;
 
+				WARN_ON_ONCE(dquot_initialize_needed(inode));
+
 				/* The old block is released after updating
 				   the inode. */
 				error = dquot_alloc_block(inode,
@@ -953,7 +1948,7 @@ inserted:
 							 EXT4_C2B(EXT4_SB(sb),
 								  1));
 					brelse(new_bh);
-					mb_cache_entry_put(ext4_mb_cache, ce);
+					mb_cache_entry_put(ea_block_cache, ce);
 					ce = NULL;
 					new_bh = NULL;
 					goto inserted;
@@ -964,15 +1959,16 @@ inserted:
 					ce->e_reusable = 0;
 				ea_bdebug(new_bh, "reusing; refcount now=%d",
 					  ref);
+				ext4_xattr_block_csum_set(inode, new_bh);
 				unlock_buffer(new_bh);
-				error = ext4_handle_dirty_xattr_block(handle,
-								      inode,
-								      new_bh);
+				error = ext4_handle_dirty_metadata(handle,
+								   inode,
+								   new_bh);
 				if (error)
 					goto cleanup_dquot;
 			}
-			mb_cache_entry_touch(ext4_mb_cache, ce);
-			mb_cache_entry_put(ext4_mb_cache, ce);
+			mb_cache_entry_touch(ea_block_cache, ce);
+			mb_cache_entry_put(ea_block_cache, ce);
 			ce = NULL;
 		} else if (bs->bh && s->base == bs->bh->b_data) {
 			/* We were modifying this block in-place. */
@@ -983,6 +1979,8 @@ inserted:
 			/* We need to allocate a new block */
 			ext4_fsblk_t goal, block;
 
+			WARN_ON_ONCE(dquot_initialize_needed(inode));
+
 			goal = ext4_group_first_block_no(sb,
 						EXT4_I(inode)->i_block_group);
 
@@ -1009,6 +2007,22 @@ getblk_failed:
 						 EXT4_FREE_BLOCKS_METADATA);
 				goto cleanup;
 			}
+			error = ext4_xattr_inode_inc_ref_all(handle, inode,
+						      ENTRY(header(s->base)+1));
+			if (error)
+				goto getblk_failed;
+			if (ea_inode) {
+				/* Drop the extra ref on ea_inode. */
+				error = ext4_xattr_inode_dec_ref(handle,
+								 ea_inode);
+				if (error)
+					ext4_warning_inode(ea_inode,
+							   "dec ref error=%d",
+							   error);
+				iput(ea_inode);
+				ea_inode = NULL;
+			}
+
 			lock_buffer(new_bh);
 			error = ext4_journal_get_create_access(handle, new_bh);
 			if (error) {
@@ -1017,27 +2031,51 @@ getblk_failed:
 				goto getblk_failed;
 			}
 			memcpy(new_bh->b_data, s->base, new_bh->b_size);
+			ext4_xattr_block_csum_set(inode, new_bh);
 			set_buffer_uptodate(new_bh);
 			unlock_buffer(new_bh);
-			ext4_xattr_cache_insert(ext4_mb_cache, new_bh);
-			error = ext4_handle_dirty_xattr_block(handle,
-							      inode, new_bh);
+			ext4_xattr_block_cache_insert(ea_block_cache, new_bh);
+			error = ext4_handle_dirty_metadata(handle, inode,
+							   new_bh);
 			if (error)
 				goto cleanup;
 		}
 	}
 
+	if (old_ea_inode_size)
+		ext4_xattr_inode_free_quota(inode, old_ea_inode_size);
+
 	/* Update the inode. */
 	EXT4_I(inode)->i_file_acl = new_bh ? new_bh->b_blocknr : 0;
 
 	/* Drop the previous xattr block. */
-	if (bs->bh && bs->bh != new_bh)
-		ext4_xattr_release_block(handle, inode, bs->bh);
+	if (bs->bh && bs->bh != new_bh) {
+		struct ext4_xattr_inode_array *ea_inode_array = NULL;
+
+		ext4_xattr_release_block(handle, inode, bs->bh,
+					 &ea_inode_array,
+					 0 /* extra_credits */);
+		ext4_xattr_inode_array_free(ea_inode_array);
+	}
 	error = 0;
 
 cleanup:
+	if (ea_inode) {
+		int error2;
+
+		error2 = ext4_xattr_inode_dec_ref(handle, ea_inode);
+		if (error2)
+			ext4_warning_inode(ea_inode, "dec ref error=%d",
+					   error2);
+
+		/* If there was an error, revert the quota charge. */
+		if (error)
+			ext4_xattr_inode_free_quota(inode,
+						    i_size_read(ea_inode));
+		iput(ea_inode);
+	}
 	if (ce)
-		mb_cache_entry_put(ext4_mb_cache, ce);
+		mb_cache_entry_put(ea_block_cache, ce);
 	brelse(new_bh);
 	if (!(bs->bh && s->base == bs->bh->b_data))
 		kfree(s->base);
@@ -1076,8 +2114,7 @@ int ext4_xattr_ibody_find(struct inode *inode, struct ext4_xattr_info *i,
 			return error;
 		/* Find the named attribute. */
 		error = ext4_xattr_find_entry(&is->s.here, i->name_index,
-					      i->name, is->s.end -
-					      (void *)is->s.base, 0);
+					      i->name, 0);
 		if (error && error != -ENODATA)
 			return error;
 		is->s.not_found = error;
@@ -1095,7 +2132,7 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
 
 	if (EXT4_I(inode)->i_extra_isize == 0)
 		return -ENOSPC;
-	error = ext4_xattr_set_entry(i, s);
+	error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
 	if (error) {
 		if (error == -ENOSPC &&
 		    ext4_has_inline_data(inode)) {
@@ -1107,7 +2144,8 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
 			error = ext4_xattr_ibody_find(inode, i, is);
 			if (error)
 				return error;
-			error = ext4_xattr_set_entry(i, s);
+			error = ext4_xattr_set_entry(i, s, handle, inode,
+						     false /* is_block */);
 		}
 		if (error)
 			return error;
@@ -1123,7 +2161,7 @@ int ext4_xattr_ibody_inline_set(handle_t *handle, struct inode *inode,
 	return 0;
 }
 
-static int ext4_xattr_ibody_set(struct inode *inode,
+static int ext4_xattr_ibody_set(handle_t *handle, struct inode *inode,
 				struct ext4_xattr_info *i,
 				struct ext4_xattr_ibody_find *is)
 {
@@ -1133,7 +2171,7 @@ static int ext4_xattr_ibody_set(struct inode *inode,
 
 	if (EXT4_I(inode)->i_extra_isize == 0)
 		return -ENOSPC;
-	error = ext4_xattr_set_entry(i, s);
+	error = ext4_xattr_set_entry(i, s, handle, inode, false /* is_block */);
 	if (error)
 		return error;
 	header = IHDR(inode, ext4_raw_inode(&is->iloc));
@@ -1152,12 +2190,31 @@ static int ext4_xattr_value_same(struct ext4_xattr_search *s,
 {
 	void *value;
 
+	/* When e_value_inum is set the value is stored externally. */
+	if (s->here->e_value_inum)
+		return 0;
 	if (le32_to_cpu(s->here->e_value_size) != i->value_len)
 		return 0;
 	value = ((void *)s->base) + le16_to_cpu(s->here->e_value_offs);
 	return !memcmp(value, i->value, i->value_len);
 }
 
+static struct buffer_head *ext4_xattr_get_block(struct inode *inode)
+{
+	struct buffer_head *bh;
+	int error;
+
+	if (!EXT4_I(inode)->i_file_acl)
+		return NULL;
+	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+	if (!bh)
+		return ERR_PTR(-EIO);
+	error = ext4_xattr_check_block(inode, bh);
+	if (error)
+		return ERR_PTR(error);
+	return bh;
+}
+
 /*
  * ext4_xattr_set_handle()
  *
@@ -1180,7 +2237,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		.name = name,
 		.value = value,
 		.value_len = value_len,
-
+		.in_inode = 0,
 	};
 	struct ext4_xattr_ibody_find is = {
 		.s = { .not_found = -ENODATA, },
@@ -1188,16 +2245,37 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 	struct ext4_xattr_block_find bs = {
 		.s = { .not_found = -ENODATA, },
 	};
-	unsigned long no_expand;
+	int no_expand;
 	int error;
 
 	if (!name)
 		return -EINVAL;
 	if (strlen(name) > 255)
 		return -ERANGE;
-	down_write(&EXT4_I(inode)->xattr_sem);
-	no_expand = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
-	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+
+	ext4_write_lock_xattr(inode, &no_expand);
+
+	/* Check journal credits under write lock. */
+	if (ext4_handle_valid(handle)) {
+		struct buffer_head *bh;
+		int credits;
+
+		bh = ext4_xattr_get_block(inode);
+		if (IS_ERR(bh)) {
+			error = PTR_ERR(bh);
+			goto cleanup;
+		}
+
+		credits = __ext4_xattr_set_credits(inode->i_sb, inode, bh,
+						   value_len,
+						   flags & XATTR_CREATE);
+		brelse(bh);
+
+		if (!ext4_handle_has_enough_credits(handle, credits)) {
+			error = -ENOSPC;
+			goto cleanup;
+		}
+	}
 
 	error = ext4_reserve_inode_write(handle, inode, &is.iloc);
 	if (error)
@@ -1228,9 +2306,10 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		if (flags & XATTR_CREATE)
 			goto cleanup;
 	}
+
 	if (!value) {
 		if (!is.s.not_found)
-			error = ext4_xattr_ibody_set(inode, &i, &is);
+			error = ext4_xattr_ibody_set(handle, inode, &i, &is);
 		else if (!bs.s.not_found)
 			error = ext4_xattr_block_set(handle, inode, &i, &bs);
 	} else {
@@ -1241,7 +2320,12 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		if (!bs.s.not_found && ext4_xattr_value_same(&bs.s, &i))
 			goto cleanup;
 
-		error = ext4_xattr_ibody_set(inode, &i, &is);
+		if (ext4_has_feature_ea_inode(inode->i_sb) &&
+		    (EXT4_XATTR_SIZE(i.value_len) >
+			EXT4_XATTR_MIN_LARGE_EA_SIZE(inode->i_sb->s_blocksize)))
+			i.in_inode = 1;
+retry_inode:
+		error = ext4_xattr_ibody_set(handle, inode, &i, &is);
 		if (!error && !bs.s.not_found) {
 			i.value = NULL;
 			error = ext4_xattr_block_set(handle, inode, &i, &bs);
@@ -1252,11 +2336,20 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 					goto cleanup;
 			}
 			error = ext4_xattr_block_set(handle, inode, &i, &bs);
-			if (error)
-				goto cleanup;
-			if (!is.s.not_found) {
+			if (!error && !is.s.not_found) {
 				i.value = NULL;
-				error = ext4_xattr_ibody_set(inode, &i, &is);
+				error = ext4_xattr_ibody_set(handle, inode, &i,
+							     &is);
+			} else if (error == -ENOSPC) {
+				/*
+				 * Xattr does not fit in the block, store at
+				 * external inode if possible.
+				 */
+				if (ext4_has_feature_ea_inode(inode->i_sb) &&
+				    !i.in_inode) {
+					i.in_inode = 1;
+					goto retry_inode;
+				}
 			}
 		}
 	}
@@ -1264,7 +2357,7 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 		ext4_xattr_update_super_block(handle, inode->i_sb);
 		inode->i_ctime = current_time(inode);
 		if (!value)
-			ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
+			no_expand = 0;
 		error = ext4_mark_iloc_dirty(handle, inode, &is.iloc);
 		/*
 		 * The bh is consumed by ext4_mark_iloc_dirty, even with
@@ -1278,12 +2371,37 @@ ext4_xattr_set_handle(handle_t *handle, struct inode *inode, int name_index,
 cleanup:
 	brelse(is.iloc.bh);
 	brelse(bs.bh);
-	if (no_expand == 0)
-		ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 	return error;
 }
 
+int ext4_xattr_set_credits(struct inode *inode, size_t value_len,
+			   bool is_create, int *credits)
+{
+	struct buffer_head *bh;
+	int err;
+
+	*credits = 0;
+
+	if (!EXT4_SB(inode->i_sb)->s_journal)
+		return 0;
+
+	down_read(&EXT4_I(inode)->xattr_sem);
+
+	bh = ext4_xattr_get_block(inode);
+	if (IS_ERR(bh)) {
+		err = PTR_ERR(bh);
+	} else {
+		*credits = __ext4_xattr_set_credits(inode->i_sb, inode, bh,
+						    value_len, is_create);
+		brelse(bh);
+		err = 0;
+	}
+
+	up_read(&EXT4_I(inode)->xattr_sem);
+	return err;
+}
+
 /*
  * ext4_xattr_set()
  *
@@ -1297,10 +2415,20 @@ ext4_xattr_set(struct inode *inode, int name_index, const char *name,
 	       const void *value, size_t value_len, int flags)
 {
 	handle_t *handle;
+	struct super_block *sb = inode->i_sb;
 	int error, retries = 0;
-	int credits = ext4_jbd2_credits_xattr(inode);
+	int credits;
+
+	error = dquot_initialize(inode);
+	if (error)
+		return error;
 
 retry:
+	error = ext4_xattr_set_credits(inode, value_len, flags & XATTR_CREATE,
+				       &credits);
+	if (error)
+		return error;
+
 	handle = ext4_journal_start(inode, EXT4_HT_XATTR, credits);
 	if (IS_ERR(handle)) {
 		error = PTR_ERR(handle);
@@ -1311,7 +2439,7 @@ retry:
 					      value, value_len, flags);
 		error2 = ext4_journal_stop(handle);
 		if (error == -ENOSPC &&
-		    ext4_should_retry_alloc(inode->i_sb, &retries))
+		    ext4_should_retry_alloc(sb, &retries))
 			goto retry;
 		if (error == 0)
 			error = error2;
@@ -1336,7 +2464,7 @@ static void ext4_xattr_shift_entries(struct ext4_xattr_entry *entry,
 
 	/* Adjust the value offsets of the entries */
 	for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
-		if (last->e_value_size) {
+		if (!last->e_value_inum && last->e_value_size) {
 			new_offs = le16_to_cpu(last->e_value_offs) +
 							value_offs_shift;
 			last->e_value_offs = cpu_to_le16(new_offs);
@@ -1356,18 +2484,16 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 	struct ext4_xattr_ibody_find *is = NULL;
 	struct ext4_xattr_block_find *bs = NULL;
 	char *buffer = NULL, *b_entry_name = NULL;
-	size_t value_offs, value_size;
+	size_t value_size = le32_to_cpu(entry->e_value_size);
 	struct ext4_xattr_info i = {
 		.value = NULL,
 		.value_len = 0,
 		.name_index = entry->e_name_index,
+		.in_inode = !!entry->e_value_inum,
 	};
 	struct ext4_xattr_ibody_header *header = IHDR(inode, raw_inode);
 	int error;
 
-	value_offs = le16_to_cpu(entry->e_value_offs);
-	value_size = le32_to_cpu(entry->e_value_size);
-
 	is = kzalloc(sizeof(struct ext4_xattr_ibody_find), GFP_NOFS);
 	bs = kzalloc(sizeof(struct ext4_xattr_block_find), GFP_NOFS);
 	buffer = kmalloc(value_size, GFP_NOFS);
@@ -1383,7 +2509,15 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 	bs->bh = NULL;
 
 	/* Save the entry name and the entry value */
-	memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size);
+	if (entry->e_value_inum) {
+		error = ext4_xattr_inode_get(inode, entry, buffer, value_size);
+		if (error)
+			goto out;
+	} else {
+		size_t value_offs = le16_to_cpu(entry->e_value_offs);
+		memcpy(buffer, (void *)IFIRST(header) + value_offs, value_size);
+	}
+
 	memcpy(b_entry_name, entry->e_name, entry->e_name_len);
 	b_entry_name[entry->e_name_len] = '\0';
 	i.name = b_entry_name;
@@ -1397,11 +2531,10 @@ static int ext4_xattr_move_to_block(handle_t *handle, struct inode *inode,
 		goto out;
 
 	/* Remove the chosen entry from the inode */
-	error = ext4_xattr_ibody_set(inode, &i, is);
+	error = ext4_xattr_ibody_set(handle, inode, &i, is);
 	if (error)
 		goto out;
 
-	i.name = b_entry_name;
 	i.value = buffer;
 	i.value_len = value_size;
 	error = ext4_xattr_block_find(inode, &i, bs);
@@ -1445,9 +2578,10 @@ static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode,
 		last = IFIRST(header);
 		/* Find the entry best suited to be pushed into EA block */
 		for (; !IS_LAST_ENTRY(last); last = EXT4_XATTR_NEXT(last)) {
-			total_size =
-			EXT4_XATTR_SIZE(le32_to_cpu(last->e_value_size)) +
-					EXT4_XATTR_LEN(last->e_name_len);
+			total_size = EXT4_XATTR_LEN(last->e_name_len);
+			if (!last->e_value_inum)
+				total_size += EXT4_XATTR_SIZE(
+					       le32_to_cpu(last->e_value_size));
 			if (total_size <= bfree &&
 			    total_size < min_total_size) {
 				if (total_size + ifree < isize_diff) {
@@ -1466,8 +2600,10 @@ static int ext4_xattr_make_inode_space(handle_t *handle, struct inode *inode,
 		}
 
 		entry_size = EXT4_XATTR_LEN(entry->e_name_len);
-		total_size = entry_size +
-			EXT4_XATTR_SIZE(le32_to_cpu(entry->e_value_size));
+		total_size = entry_size;
+		if (!entry->e_value_inum)
+			total_size += EXT4_XATTR_SIZE(
+					      le32_to_cpu(entry->e_value_size));
 		error = ext4_xattr_move_to_block(handle, inode, raw_inode,
 						 entry);
 		if (error)
@@ -1497,12 +2633,11 @@ int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 	int error = 0, tried_min_extra_isize = 0;
 	int s_min_extra_isize = le16_to_cpu(EXT4_SB(inode->i_sb)->s_es->s_min_extra_isize);
 	int isize_diff;	/* How much do we need to grow i_extra_isize */
+	int no_expand;
+
+	if (ext4_write_trylock_xattr(inode, &no_expand) == 0)
+		return 0;
 
-	down_write(&EXT4_I(inode)->xattr_sem);
-	/*
-	 * Set EXT4_STATE_NO_EXPAND to avoid recursion when marking inode dirty
-	 */
-	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
 retry:
 	isize_diff = new_extra_isize - EXT4_I(inode)->i_extra_isize;
 	if (EXT4_I(inode)->i_extra_isize >= new_extra_isize)
@@ -1584,65 +2719,185 @@ shift:
 	EXT4_I(inode)->i_extra_isize = new_extra_isize;
 	brelse(bh);
 out:
-	ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
-	up_write(&EXT4_I(inode)->xattr_sem);
+	ext4_write_unlock_xattr(inode, &no_expand);
 	return 0;
 
 cleanup:
 	brelse(bh);
 	/*
-	 * We deliberately leave EXT4_STATE_NO_EXPAND set here since inode
-	 * size expansion failed.
+	 * Inode size expansion failed; don't try again
 	 */
-	up_write(&EXT4_I(inode)->xattr_sem);
+	no_expand = 1;
+	ext4_write_unlock_xattr(inode, &no_expand);
 	return error;
 }
 
+#define EIA_INCR 16 /* must be 2^n */
+#define EIA_MASK (EIA_INCR - 1)
 
+/* Add the large xattr @inode into @ea_inode_array for deferred iput().
+ * If @ea_inode_array is new or full it will be grown and the old
+ * contents copied over.
+ */
+static int
+ext4_expand_inode_array(struct ext4_xattr_inode_array **ea_inode_array,
+			struct inode *inode)
+{
+	if (*ea_inode_array == NULL) {
+		/*
+		 * Start with 15 inodes, so it fits into a power-of-two size.
+		 * If *ea_inode_array is NULL, this is essentially offsetof()
+		 */
+		(*ea_inode_array) =
+			kmalloc(offsetof(struct ext4_xattr_inode_array,
+					 inodes[EIA_MASK]),
+				GFP_NOFS);
+		if (*ea_inode_array == NULL)
+			return -ENOMEM;
+		(*ea_inode_array)->count = 0;
+	} else if (((*ea_inode_array)->count & EIA_MASK) == EIA_MASK) {
+		/* expand the array once all 15 + n * 16 slots are full */
+		struct ext4_xattr_inode_array *new_array = NULL;
+		int count = (*ea_inode_array)->count;
+
+		/* if new_array is NULL, this is essentially offsetof() */
+		new_array = kmalloc(
+				offsetof(struct ext4_xattr_inode_array,
+					 inodes[count + EIA_INCR]),
+				GFP_NOFS);
+		if (new_array == NULL)
+			return -ENOMEM;
+		memcpy(new_array, *ea_inode_array,
+		       offsetof(struct ext4_xattr_inode_array, inodes[count]));
+		kfree(*ea_inode_array);
+		*ea_inode_array = new_array;
+	}
+	(*ea_inode_array)->inodes[(*ea_inode_array)->count++] = inode;
+	return 0;
+}
 
 /*
  * ext4_xattr_delete_inode()
  *
- * Free extended attribute resources associated with this inode. This
- * is called immediately before an inode is freed. We have exclusive
- * access to the inode.
+ * Free extended attribute resources associated with this inode. Traverse
+ * all entries and decrement reference on any xattr inodes associated with this
+ * inode. This is called immediately before an inode is freed. We have exclusive
+ * access to the inode. If an orphan inode is deleted it will also release its
+ * references on xattr block and xattr inodes.
  */
-void
-ext4_xattr_delete_inode(handle_t *handle, struct inode *inode)
+int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
+			    struct ext4_xattr_inode_array **ea_inode_array,
+			    int extra_credits)
 {
 	struct buffer_head *bh = NULL;
+	struct ext4_xattr_ibody_header *header;
+	struct ext4_iloc iloc = { .bh = NULL };
+	struct ext4_xattr_entry *entry;
+	int error;
 
-	if (!EXT4_I(inode)->i_file_acl)
-		goto cleanup;
-	bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
-	if (!bh) {
-		EXT4_ERROR_INODE(inode, "block %llu read error",
-				 EXT4_I(inode)->i_file_acl);
+	error = ext4_xattr_ensure_credits(handle, inode, extra_credits,
+					  NULL /* bh */,
+					  false /* dirty */,
+					  false /* block_csum */);
+	if (error) {
+		EXT4_ERROR_INODE(inode, "ensure credits (error %d)", error);
 		goto cleanup;
 	}
-	if (BHDR(bh)->h_magic != cpu_to_le32(EXT4_XATTR_MAGIC) ||
-	    BHDR(bh)->h_blocks != cpu_to_le32(1)) {
-		EXT4_ERROR_INODE(inode, "bad block %llu",
-				 EXT4_I(inode)->i_file_acl);
-		goto cleanup;
+
+	if (ext4_has_feature_ea_inode(inode->i_sb) &&
+	    ext4_test_inode_state(inode, EXT4_STATE_XATTR)) {
+
+		error = ext4_get_inode_loc(inode, &iloc);
+		if (error) {
+			EXT4_ERROR_INODE(inode, "inode loc (error %d)", error);
+			goto cleanup;
+		}
+
+		error = ext4_journal_get_write_access(handle, iloc.bh);
+		if (error) {
+			EXT4_ERROR_INODE(inode, "write access (error %d)",
+					 error);
+			goto cleanup;
+		}
+
+		header = IHDR(inode, ext4_raw_inode(&iloc));
+		if (header->h_magic == cpu_to_le32(EXT4_XATTR_MAGIC))
+			ext4_xattr_inode_dec_ref_all(handle, inode, iloc.bh,
+						     IFIRST(header),
+						     false /* block_csum */,
+						     ea_inode_array,
+						     extra_credits,
+						     false /* skip_quota */);
 	}
-	ext4_xattr_release_block(handle, inode, bh);
-	EXT4_I(inode)->i_file_acl = 0;
 
+	if (EXT4_I(inode)->i_file_acl) {
+		bh = sb_bread(inode->i_sb, EXT4_I(inode)->i_file_acl);
+		if (!bh) {
+			EXT4_ERROR_INODE(inode, "block %llu read error",
+					 EXT4_I(inode)->i_file_acl);
+			error = -EIO;
+			goto cleanup;
+		}
+		error = ext4_xattr_check_block(inode, bh);
+		if (error) {
+			EXT4_ERROR_INODE(inode, "bad block %llu (error %d)",
+					 EXT4_I(inode)->i_file_acl, error);
+			goto cleanup;
+		}
+
+		if (ext4_has_feature_ea_inode(inode->i_sb)) {
+			for (entry = BFIRST(bh); !IS_LAST_ENTRY(entry);
+			     entry = EXT4_XATTR_NEXT(entry))
+				if (entry->e_value_inum)
+					ext4_xattr_inode_free_quota(inode,
+					      le32_to_cpu(entry->e_value_size));
+
+		}
+
+		ext4_xattr_release_block(handle, inode, bh, ea_inode_array,
+					 extra_credits);
+		/*
+		 * Update i_file_acl value in the same transaction that releases
+		 * block.
+		 */
+		EXT4_I(inode)->i_file_acl = 0;
+		error = ext4_mark_inode_dirty(handle, inode);
+		if (error) {
+			EXT4_ERROR_INODE(inode, "mark inode dirty (error %d)",
+					 error);
+			goto cleanup;
+		}
+	}
+	error = 0;
 cleanup:
+	brelse(iloc.bh);
 	brelse(bh);
+	return error;
+}
+
+void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *ea_inode_array)
+{
+	int idx;
+
+	if (ea_inode_array == NULL)
+		return;
+
+	for (idx = 0; idx < ea_inode_array->count; ++idx)
+		iput(ea_inode_array->inodes[idx]);
+	kfree(ea_inode_array);
 }
 
 /*
- * ext4_xattr_cache_insert()
+ * ext4_xattr_block_cache_insert()
  *
- * Create a new entry in the extended attribute cache, and insert
+ * Create a new entry in the extended attribute block cache, and insert
  * it unless such an entry is already in the cache.
  *
  * Returns 0, or a negative error number on failure.
  */
 static void
-ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh)
+ext4_xattr_block_cache_insert(struct mb_cache *ea_block_cache,
+			      struct buffer_head *bh)
 {
 	struct ext4_xattr_header *header = BHDR(bh);
 	__u32 hash = le32_to_cpu(header->h_hash);
@@ -1650,7 +2905,9 @@ ext4_xattr_cache_insert(struct mb_cache *ext4_mb_cache, struct buffer_head *bh)
 		       EXT4_XATTR_REFCOUNT_MAX;
 	int error;
 
-	error = mb_cache_entry_create(ext4_mb_cache, GFP_NOFS, hash,
+	if (!ea_block_cache)
+		return;
+	error = mb_cache_entry_create(ea_block_cache, GFP_NOFS, hash,
 				      bh->b_blocknr, reusable);
 	if (error) {
 		if (error == -EBUSY)
@@ -1682,11 +2939,11 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1,
 		    entry1->e_name_index != entry2->e_name_index ||
 		    entry1->e_name_len != entry2->e_name_len ||
 		    entry1->e_value_size != entry2->e_value_size ||
+		    entry1->e_value_inum != entry2->e_value_inum ||
 		    memcmp(entry1->e_name, entry2->e_name, entry1->e_name_len))
 			return 1;
-		if (entry1->e_value_block != 0 || entry2->e_value_block != 0)
-			return -EFSCORRUPTED;
-		if (memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs),
+		if (!entry1->e_value_inum &&
+		    memcmp((char *)header1 + le16_to_cpu(entry1->e_value_offs),
 			   (char *)header2 + le16_to_cpu(entry2->e_value_offs),
 			   le32_to_cpu(entry1->e_value_size)))
 			return 1;
@@ -1700,7 +2957,7 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1,
 }
 
 /*
- * ext4_xattr_cache_find()
+ * ext4_xattr_block_cache_find()
  *
  * Find an identical extended attribute block.
  *
@@ -1708,30 +2965,33 @@ ext4_xattr_cmp(struct ext4_xattr_header *header1,
  * not found or an error occurred.
  */
 static struct buffer_head *
-ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
-		      struct mb_cache_entry **pce)
+ext4_xattr_block_cache_find(struct inode *inode,
+			    struct ext4_xattr_header *header,
+			    struct mb_cache_entry **pce)
 {
 	__u32 hash = le32_to_cpu(header->h_hash);
 	struct mb_cache_entry *ce;
-	struct mb_cache *ext4_mb_cache = EXT4_GET_MB_CACHE(inode);
+	struct mb_cache *ea_block_cache = EA_BLOCK_CACHE(inode);
 
+	if (!ea_block_cache)
+		return NULL;
 	if (!header->h_hash)
 		return NULL;  /* never share */
 	ea_idebug(inode, "looking for cached blocks [%x]", (int)hash);
-	ce = mb_cache_entry_find_first(ext4_mb_cache, hash);
+	ce = mb_cache_entry_find_first(ea_block_cache, hash);
 	while (ce) {
 		struct buffer_head *bh;
 
-		bh = sb_bread(inode->i_sb, ce->e_block);
+		bh = sb_bread(inode->i_sb, ce->e_value);
 		if (!bh) {
 			EXT4_ERROR_INODE(inode, "block %lu read error",
-					 (unsigned long) ce->e_block);
+					 (unsigned long)ce->e_value);
 		} else if (ext4_xattr_cmp(header, BHDR(bh)) == 0) {
 			*pce = ce;
 			return bh;
 		}
 		brelse(bh);
-		ce = mb_cache_entry_find_next(ext4_mb_cache, ce);
+		ce = mb_cache_entry_find_next(ea_block_cache, ce);
 	}
 	return NULL;
 }
@@ -1744,30 +3004,22 @@ ext4_xattr_cache_find(struct inode *inode, struct ext4_xattr_header *header,
  *
  * Compute the hash of an extended attribute.
  */
-static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header,
-					 struct ext4_xattr_entry *entry)
+static __le32 ext4_xattr_hash_entry(char *name, size_t name_len, __le32 *value,
+				    size_t value_count)
 {
 	__u32 hash = 0;
-	char *name = entry->e_name;
-	int n;
 
-	for (n = 0; n < entry->e_name_len; n++) {
+	while (name_len--) {
 		hash = (hash << NAME_HASH_SHIFT) ^
 		       (hash >> (8*sizeof(hash) - NAME_HASH_SHIFT)) ^
 		       *name++;
 	}
-
-	if (entry->e_value_size != 0) {
-		__le32 *value = (__le32 *)((char *)header +
-			le16_to_cpu(entry->e_value_offs));
-		for (n = (le32_to_cpu(entry->e_value_size) +
-		     EXT4_XATTR_ROUND) >> EXT4_XATTR_PAD_BITS; n; n--) {
-			hash = (hash << VALUE_HASH_SHIFT) ^
-			       (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^
-			       le32_to_cpu(*value++);
-		}
+	while (value_count--) {
+		hash = (hash << VALUE_HASH_SHIFT) ^
+		       (hash >> (8*sizeof(hash) - VALUE_HASH_SHIFT)) ^
+		       le32_to_cpu(*value++);
 	}
-	entry->e_hash = cpu_to_le32(hash);
+	return cpu_to_le32(hash);
 }
 
 #undef NAME_HASH_SHIFT
@@ -1780,13 +3032,11 @@ static inline void ext4_xattr_hash_entry(struct ext4_xattr_header *header,
  *
  * Re-compute the extended attribute hash value after an entry has changed.
  */
-static void ext4_xattr_rehash(struct ext4_xattr_header *header,
-			      struct ext4_xattr_entry *entry)
+static void ext4_xattr_rehash(struct ext4_xattr_header *header)
 {
 	struct ext4_xattr_entry *here;
 	__u32 hash = 0;
 
-	ext4_xattr_hash_entry(header, entry);
 	here = ENTRY(header+1);
 	while (!IS_LAST_ENTRY(here)) {
 		if (!here->e_hash) {
diff --git a/fs/ext4/xattr.h b/fs/ext4/xattr.h
index a92e783fa057..0d2dde1fa87a 100644
--- a/fs/ext4/xattr.h
+++ b/fs/ext4/xattr.h
@@ -44,7 +44,7 @@ struct ext4_xattr_entry {
 	__u8	e_name_len;	/* length of name */
 	__u8	e_name_index;	/* attribute name index */
 	__le16	e_value_offs;	/* offset in disk block of value */
-	__le32	e_value_block;	/* disk block attribute is stored on (n/i) */
+	__le32	e_value_inum;	/* inode in which the value is stored */
 	__le32	e_value_size;	/* size of attribute value */
 	__le32	e_hash;		/* hash value of name and value */
 	char	e_name[0];	/* attribute name */
@@ -69,6 +69,13 @@ struct ext4_xattr_entry {
 		EXT4_I(inode)->i_extra_isize))
 #define IFIRST(hdr) ((struct ext4_xattr_entry *)((hdr)+1))
 
+/*
+ * The minimum size of EA value when you start storing it in an external inode
+ * size of block - size of header - size of 1 entry - 4 null bytes
+*/
+#define EXT4_XATTR_MIN_LARGE_EA_SIZE(b)					\
+	((b) - EXT4_XATTR_LEN(3) - sizeof(struct ext4_xattr_header) - 4)
+
 #define BHDR(bh) ((struct ext4_xattr_header *)((bh)->b_data))
 #define ENTRY(ptr) ((struct ext4_xattr_entry *)(ptr))
 #define BFIRST(bh) ENTRY(BHDR(bh)+1)
@@ -77,10 +84,11 @@ struct ext4_xattr_entry {
 #define EXT4_ZERO_XATTR_VALUE ((void *)-1)
 
 struct ext4_xattr_info {
-	int name_index;
 	const char *name;
 	const void *value;
 	size_t value_len;
+	int name_index;
+	int in_inode;
 };
 
 struct ext4_xattr_search {
@@ -96,19 +104,64 @@ struct ext4_xattr_ibody_find {
 	struct ext4_iloc iloc;
 };
 
+struct ext4_xattr_inode_array {
+	unsigned int count;		/* # of used items in the array */
+	struct inode *inodes[0];
+};
+
 extern const struct xattr_handler ext4_xattr_user_handler;
 extern const struct xattr_handler ext4_xattr_trusted_handler;
 extern const struct xattr_handler ext4_xattr_security_handler;
 
 #define EXT4_XATTR_NAME_ENCRYPTION_CONTEXT "c"
 
+/*
+ * The EXT4_STATE_NO_EXPAND is overloaded and used for two purposes.
+ * The first is to signal that there the inline xattrs and data are
+ * taking up so much space that we might as well not keep trying to
+ * expand it.  The second is that xattr_sem is taken for writing, so
+ * we shouldn't try to recurse into the inode expansion.  For this
+ * second case, we need to make sure that we take save and restore the
+ * NO_EXPAND state flag appropriately.
+ */
+static inline void ext4_write_lock_xattr(struct inode *inode, int *save)
+{
+	down_write(&EXT4_I(inode)->xattr_sem);
+	*save = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+}
+
+static inline int ext4_write_trylock_xattr(struct inode *inode, int *save)
+{
+	if (down_write_trylock(&EXT4_I(inode)->xattr_sem) == 0)
+		return 0;
+	*save = ext4_test_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	ext4_set_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	return 1;
+}
+
+static inline void ext4_write_unlock_xattr(struct inode *inode, int *save)
+{
+	if (*save == 0)
+		ext4_clear_inode_state(inode, EXT4_STATE_NO_EXPAND);
+	up_write(&EXT4_I(inode)->xattr_sem);
+}
+
 extern ssize_t ext4_listxattr(struct dentry *, char *, size_t);
 
 extern int ext4_xattr_get(struct inode *, int, const char *, void *, size_t);
 extern int ext4_xattr_set(struct inode *, int, const char *, const void *, size_t, int);
 extern int ext4_xattr_set_handle(handle_t *, struct inode *, int, const char *, const void *, size_t, int);
+extern int ext4_xattr_set_credits(struct inode *inode, size_t value_len,
+				  bool is_create, int *credits);
+extern int __ext4_xattr_set_credits(struct super_block *sb, struct inode *inode,
+				struct buffer_head *block_bh, size_t value_len,
+				bool is_create);
 
-extern void ext4_xattr_delete_inode(handle_t *, struct inode *);
+extern int ext4_xattr_delete_inode(handle_t *handle, struct inode *inode,
+				   struct ext4_xattr_inode_array **array,
+				   int extra_credits);
+extern void ext4_xattr_inode_array_free(struct ext4_xattr_inode_array *array);
 
 extern int ext4_expand_extra_isize_ea(struct inode *inode, int new_extra_isize,
 			    struct ext4_inode *raw_inode, handle_t *handle);
@@ -137,3 +190,11 @@ static inline int ext4_init_security(handle_t *handle, struct inode *inode,
 	return 0;
 }
 #endif
+
+#ifdef CONFIG_LOCKDEP
+extern void ext4_xattr_inode_set_class(struct inode *ea_inode);
+#else
+static inline void ext4_xattr_inode_set_class(struct inode *ea_inode) { }
+#endif
+
+extern int ext4_get_inode_usage(struct inode *inode, qsize_t *usage);
diff --git a/fs/f2fs/Makefile b/fs/f2fs/Makefile
index ca949ea7c02f..a0dc559b1b47 100644
--- a/fs/f2fs/Makefile
+++ b/fs/f2fs/Makefile
@@ -2,7 +2,7 @@ obj-$(CONFIG_F2FS_FS) += f2fs.o
 
 f2fs-y		:= dir.o file.o inode.o namei.o hash.o super.o inline.o
 f2fs-y		+= checkpoint.o gc.o data.o node.o segment.o recovery.o
-f2fs-y		+= shrinker.o extent_cache.o
+f2fs-y		+= shrinker.o extent_cache.o sysfs.o
 f2fs-$(CONFIG_F2FS_STAT_FS) += debug.o
 f2fs-$(CONFIG_F2FS_FS_XATTR) += xattr.o
 f2fs-$(CONFIG_F2FS_FS_POSIX_ACL) += acl.o
diff --git a/fs/f2fs/acl.c b/fs/f2fs/acl.c
index 8f487692c21f..b4b8438c42ef 100644
--- a/fs/f2fs/acl.c
+++ b/fs/f2fs/acl.c
@@ -211,7 +211,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name_index = F2FS_XATTR_INDEX_POSIX_ACL_ACCESS;
-		if (acl) {
+		if (acl && !ipage) {
 			error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
 			if (error)
 				return error;
@@ -233,7 +233,7 @@ static int __f2fs_set_acl(struct inode *inode, int type,
 		value = f2fs_acl_to_disk(F2FS_I_SB(inode), acl, &size);
 		if (IS_ERR(value)) {
 			clear_inode_flag(inode, FI_ACL_MODE);
-			return (int)PTR_ERR(value);
+			return PTR_ERR(value);
 		}
 	}
 
diff --git a/fs/f2fs/checkpoint.c b/fs/f2fs/checkpoint.c
index f73ee9534d83..5b876f6d3f6b 100644
--- a/fs/f2fs/checkpoint.c
+++ b/fs/f2fs/checkpoint.c
@@ -31,7 +31,7 @@ void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io)
 	set_ckpt_flags(sbi, CP_ERROR_FLAG);
 	sbi->sb->s_flags |= MS_RDONLY;
 	if (!end_io)
-		f2fs_flush_merged_bios(sbi);
+		f2fs_flush_merged_writes(sbi);
 }
 
 /*
@@ -162,6 +162,7 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		.op = REQ_OP_READ,
 		.op_flags = sync ? (REQ_META | REQ_PRIO) : REQ_RAHEAD,
 		.encrypted_page = NULL,
+		.in_list = false,
 	};
 	struct blk_plug plug;
 
@@ -207,12 +208,10 @@ int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
 		}
 
 		fio.page = page;
-		fio.old_blkaddr = fio.new_blkaddr;
-		f2fs_submit_page_mbio(&fio);
+		f2fs_submit_page_bio(&fio);
 		f2fs_put_page(page, 0);
 	}
 out:
-	f2fs_submit_merged_bio(sbi, META, READ);
 	blk_finish_plug(&plug);
 	return blkno - start;
 }
@@ -249,12 +248,13 @@ static int f2fs_write_meta_page(struct page *page,
 	dec_page_count(sbi, F2FS_DIRTY_META);
 
 	if (wbc->for_reclaim)
-		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, META, WRITE);
+		f2fs_submit_merged_write_cond(sbi, page->mapping->host,
+						0, page->index, META);
 
 	unlock_page(page);
 
 	if (unlikely(f2fs_cp_error(sbi)))
-		f2fs_submit_merged_bio(sbi, META, WRITE);
+		f2fs_submit_merged_write(sbi, META);
 
 	return 0;
 
@@ -269,15 +269,19 @@ static int f2fs_write_meta_pages(struct address_space *mapping,
 	struct f2fs_sb_info *sbi = F2FS_M_SB(mapping);
 	long diff, written;
 
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto skip_write;
+
 	/* collect a number of dirty meta pages and write together */
 	if (wbc->for_kupdate ||
 		get_pages(sbi, F2FS_DIRTY_META) < nr_pages_to_skip(sbi, META))
 		goto skip_write;
 
-	trace_f2fs_writepages(mapping->host, wbc, META);
+	/* if locked failed, cp will flush dirty pages instead */
+	if (!mutex_trylock(&sbi->cp_mutex))
+		goto skip_write;
 
-	/* if mounting is failed, skip writing node pages */
-	mutex_lock(&sbi->cp_mutex);
+	trace_f2fs_writepages(mapping->host, wbc, META);
 	diff = nr_pages_to_write(sbi, META, wbc);
 	written = sync_meta_pages(sbi, META, wbc->nr_to_write);
 	mutex_unlock(&sbi->cp_mutex);
@@ -356,7 +360,7 @@ continue_unlock:
 	}
 stop:
 	if (nwritten)
-		f2fs_submit_merged_bio(sbi, type, WRITE);
+		f2fs_submit_merged_write(sbi, type);
 
 	blk_finish_plug(&plug);
 
@@ -493,6 +497,7 @@ int acquire_orphan_inode(struct f2fs_sb_info *sbi)
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	if (time_to_inject(sbi, FAULT_ORPHAN)) {
 		spin_unlock(&im->ino_lock);
+		f2fs_show_injection_info(FAULT_ORPHAN);
 		return -ENOSPC;
 	}
 #endif
@@ -565,7 +570,7 @@ static int recover_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino)
 	if (ni.blk_addr != NULL_ADDR) {
 		set_sbi_flag(sbi, SBI_NEED_FSCK);
 		f2fs_msg(sbi->sb, KERN_WARNING,
-			"%s: orphan failed (ino=%x), run fsck to fix.",
+			"%s: orphan failed (ino=%x) by kernel, retry mount.",
 				__func__, ino);
 		return -EIO;
 	}
@@ -675,14 +680,13 @@ static int get_checkpoint_version(struct f2fs_sb_info *sbi, block_t cp_addr,
 	*cp_block = (struct f2fs_checkpoint *)page_address(*cp_page);
 
 	crc_offset = le32_to_cpu((*cp_block)->checksum_offset);
-	if (crc_offset >= blk_size) {
+	if (crc_offset > (blk_size - sizeof(__le32))) {
 		f2fs_msg(sbi->sb, KERN_WARNING,
 			"invalid crc_offset: %zu", crc_offset);
 		return -EINVAL;
 	}
 
-	crc = le32_to_cpu(*((__le32 *)((unsigned char *)*cp_block
-							+ crc_offset)));
+	crc = cur_cp_crc(*cp_block);
 	if (!f2fs_crc_valid(sbi, crc, *cp_block, crc_offset)) {
 		f2fs_msg(sbi->sb, KERN_WARNING, "invalid crc value");
 		return -EINVAL;
@@ -815,7 +819,9 @@ static void __add_dirty_inode(struct inode *inode, enum inode_type type)
 		return;
 
 	set_inode_flag(inode, flag);
-	list_add_tail(&F2FS_I(inode)->dirty_list, &sbi->inode_list[type]);
+	if (!f2fs_is_volatile_file(inode))
+		list_add_tail(&F2FS_I(inode)->dirty_list,
+						&sbi->inode_list[type]);
 	stat_inc_dirty_inode(sbi, type);
 }
 
@@ -873,6 +879,7 @@ int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type)
 	struct inode *inode;
 	struct f2fs_inode_info *fi;
 	bool is_dir = (type == DIR_INODE);
+	unsigned long ino = 0;
 
 	trace_f2fs_sync_dirty_inodes_enter(sbi->sb, is_dir,
 				get_pages(sbi, is_dir ?
@@ -891,18 +898,27 @@ retry:
 				F2FS_DIRTY_DENTS : F2FS_DIRTY_DATA));
 		return 0;
 	}
-	fi = list_entry(head->next, struct f2fs_inode_info, dirty_list);
+	fi = list_first_entry(head, struct f2fs_inode_info, dirty_list);
 	inode = igrab(&fi->vfs_inode);
 	spin_unlock(&sbi->inode_lock[type]);
 	if (inode) {
+		unsigned long cur_ino = inode->i_ino;
+
 		filemap_fdatawrite(inode->i_mapping);
 		iput(inode);
+		/* We need to give cpu to another writers. */
+		if (ino == cur_ino) {
+			congestion_wait(BLK_RW_ASYNC, HZ/50);
+			cond_resched();
+		} else {
+			ino = cur_ino;
+		}
 	} else {
 		/*
 		 * We should submit bio, since it exists several
 		 * wribacking dentry pages in the freeing inode.
 		 */
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
+		f2fs_submit_merged_write(sbi, DATA);
 		cond_resched();
 	}
 	goto retry;
@@ -924,7 +940,7 @@ int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
 			spin_unlock(&sbi->inode_lock[DIRTY_META]);
 			return 0;
 		}
-		fi = list_entry(head->next, struct f2fs_inode_info,
+		fi = list_first_entry(head, struct f2fs_inode_info,
 							gdirty_list);
 		inode = igrab(&fi->vfs_inode);
 		spin_unlock(&sbi->inode_lock[DIRTY_META]);
@@ -940,6 +956,19 @@ int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi)
 	return 0;
 }
 
+static void __prepare_cp_block(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	nid_t last_nid = nm_i->next_scan_nid;
+
+	next_free_nid(sbi, &last_nid);
+	ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi));
+	ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
+	ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
+	ckpt->next_free_nid = cpu_to_le32(last_nid);
+}
+
 /*
  * Freeze all the FS-operations for checkpoint.
  */
@@ -963,21 +992,26 @@ retry_flush_dents:
 		err = sync_dirty_inodes(sbi, DIR_INODE);
 		if (err)
 			goto out;
+		cond_resched();
 		goto retry_flush_dents;
 	}
 
+	/*
+	 * POR: we should ensure that there are no dirty node pages
+	 * until finishing nat/sit flush. inode->i_blocks can be updated.
+	 */
+	down_write(&sbi->node_change);
+
 	if (get_pages(sbi, F2FS_DIRTY_IMETA)) {
+		up_write(&sbi->node_change);
 		f2fs_unlock_all(sbi);
 		err = f2fs_sync_inode_meta(sbi);
 		if (err)
 			goto out;
+		cond_resched();
 		goto retry_flush_dents;
 	}
 
-	/*
-	 * POR: we should ensure that there are no dirty node pages
-	 * until finishing nat/sit flush.
-	 */
 retry_flush_nodes:
 	down_write(&sbi->node_write);
 
@@ -985,11 +1019,20 @@ retry_flush_nodes:
 		up_write(&sbi->node_write);
 		err = sync_node_pages(sbi, &wbc);
 		if (err) {
+			up_write(&sbi->node_change);
 			f2fs_unlock_all(sbi);
 			goto out;
 		}
+		cond_resched();
 		goto retry_flush_nodes;
 	}
+
+	/*
+	 * sbi->node_change is used only for AIO write_begin path which produces
+	 * dirty node blocks and some checkpoint values by block allocation.
+	 */
+	__prepare_cp_block(sbi);
+	up_write(&sbi->node_change);
 out:
 	blk_finish_plug(&plug);
 	return err;
@@ -998,8 +1041,6 @@ out:
 static void unblock_operations(struct f2fs_sb_info *sbi)
 {
 	up_write(&sbi->node_write);
-
-	build_free_nids(sbi, false);
 	f2fs_unlock_all(sbi);
 }
 
@@ -1022,15 +1063,24 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->cp_lock, flags);
 
-	spin_lock(&sbi->cp_lock);
+	if ((cpc->reason & CP_UMOUNT) &&
+			le32_to_cpu(ckpt->cp_pack_total_block_count) >
+			sbi->blocks_per_seg - NM_I(sbi)->nat_bits_blocks)
+		disable_nat_bits(sbi, false);
 
-	if (cpc->reason == CP_UMOUNT)
+	if (cpc->reason & CP_TRIMMED)
+		__set_ckpt_flags(ckpt, CP_TRIMMED_FLAG);
+
+	if (cpc->reason & CP_UMOUNT)
 		__set_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
 	else
 		__clear_ckpt_flags(ckpt, CP_UMOUNT_FLAG);
 
-	if (cpc->reason == CP_FASTBOOT)
+	if (cpc->reason & CP_FASTBOOT)
 		__set_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
 	else
 		__clear_ckpt_flags(ckpt, CP_FASTBOOT_FLAG);
@@ -1046,15 +1096,14 @@ static void update_ckpt_flags(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	/* set this flag to activate crc|cp_ver for recovery */
 	__set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG);
 
-	spin_unlock(&sbi->cp_lock);
+	spin_unlock_irqrestore(&sbi->cp_lock, flags);
 }
 
 static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num;
-	nid_t last_nid = nm_i->next_scan_nid;
+	unsigned long orphan_num = sbi->im[ORPHAN_INO].ino_num, flags;
 	block_t start_blk;
 	unsigned int data_sum_blocks, orphan_blocks;
 	__u32 crc32 = 0;
@@ -1071,14 +1120,11 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			return -EIO;
 	}
 
-	next_free_nid(sbi, &last_nid);
-
 	/*
 	 * modify checkpoint
 	 * version number is already updated
 	 */
 	ckpt->elapsed_time = cpu_to_le64(get_mtime(sbi));
-	ckpt->valid_block_count = cpu_to_le64(valid_user_blocks(sbi));
 	ckpt->free_segment_count = cpu_to_le32(free_segments(sbi));
 	for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
 		ckpt->cur_node_segno[i] =
@@ -1097,18 +1143,14 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 				curseg_alloc_type(sbi, i + CURSEG_HOT_DATA);
 	}
 
-	ckpt->valid_node_count = cpu_to_le32(valid_node_count(sbi));
-	ckpt->valid_inode_count = cpu_to_le32(valid_inode_count(sbi));
-	ckpt->next_free_nid = cpu_to_le32(last_nid);
-
 	/* 2 cp  + n data seg summary + orphan inode blocks */
 	data_sum_blocks = npages_for_summary_flush(sbi, false);
-	spin_lock(&sbi->cp_lock);
+	spin_lock_irqsave(&sbi->cp_lock, flags);
 	if (data_sum_blocks < NR_CURSEG_DATA_TYPE)
 		__set_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
 	else
 		__clear_ckpt_flags(ckpt, CP_COMPACT_SUM_FLAG);
-	spin_unlock(&sbi->cp_lock);
+	spin_unlock_irqrestore(&sbi->cp_lock, flags);
 
 	orphan_blocks = GET_ORPHAN_BLOCKS(orphan_num);
 	ckpt->cp_pack_start_sum = cpu_to_le32(1 + cp_payload_blks +
@@ -1137,6 +1179,27 @@ static int do_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	start_blk = __start_cp_next_addr(sbi);
 
+	/* write nat bits */
+	if (enabled_nat_bits(sbi, cpc)) {
+		__u64 cp_ver = cur_cp_version(ckpt);
+		block_t blk;
+
+		cp_ver |= ((__u64)crc32 << 32);
+		*(__le64 *)nm_i->nat_bits = cpu_to_le64(cp_ver);
+
+		blk = start_blk + sbi->blocks_per_seg - nm_i->nat_bits_blocks;
+		for (i = 0; i < nm_i->nat_bits_blocks; i++)
+			update_meta_page(sbi, nm_i->nat_bits +
+					(i << F2FS_BLKSIZE_BITS), blk + i);
+
+		/* Flush all the NAT BITS pages */
+		while (get_pages(sbi, F2FS_DIRTY_META)) {
+			sync_meta_pages(sbi, META, LONG_MAX);
+			if (unlikely(f2fs_cp_error(sbi)))
+				return -EIO;
+		}
+	}
+
 	/* need to wait for end_io results */
 	wait_on_all_pages_writeback(sbi);
 	if (unlikely(f2fs_cp_error(sbi)))
@@ -1225,8 +1288,8 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	mutex_lock(&sbi->cp_mutex);
 
 	if (!is_sbi_flag_set(sbi, SBI_IS_DIRTY) &&
-		(cpc->reason == CP_FASTBOOT || cpc->reason == CP_SYNC ||
-		(cpc->reason == CP_DISCARD && !sbi->discard_blks)))
+		((cpc->reason & CP_FASTBOOT) || (cpc->reason & CP_SYNC) ||
+		((cpc->reason & CP_DISCARD) && !sbi->discard_blks)))
 		goto out;
 	if (unlikely(f2fs_cp_error(sbi))) {
 		err = -EIO;
@@ -1245,18 +1308,23 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 	trace_f2fs_write_checkpoint(sbi->sb, cpc->reason, "finish block_ops");
 
-	f2fs_flush_merged_bios(sbi);
+	f2fs_flush_merged_writes(sbi);
 
 	/* this is the case of multiple fstrims without any changes */
-	if (cpc->reason == CP_DISCARD && !is_sbi_flag_set(sbi, SBI_IS_DIRTY)) {
-		f2fs_bug_on(sbi, NM_I(sbi)->dirty_nat_cnt);
-		f2fs_bug_on(sbi, SIT_I(sbi)->dirty_sentries);
-		f2fs_bug_on(sbi, prefree_segments(sbi));
-		flush_sit_entries(sbi, cpc);
-		clear_prefree_segments(sbi, cpc);
-		f2fs_wait_all_discard_bio(sbi);
-		unblock_operations(sbi);
-		goto out;
+	if (cpc->reason & CP_DISCARD) {
+		if (!exist_trim_candidates(sbi, cpc)) {
+			unblock_operations(sbi);
+			goto out;
+		}
+
+		if (NM_I(sbi)->dirty_nat_cnt == 0 &&
+				SIT_I(sbi)->dirty_sentries == 0 &&
+				prefree_segments(sbi) == 0) {
+			flush_sit_entries(sbi, cpc);
+			clear_prefree_segments(sbi, cpc);
+			unblock_operations(sbi);
+			goto out;
+		}
 	}
 
 	/*
@@ -1268,22 +1336,20 @@ int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	ckpt->checkpoint_ver = cpu_to_le64(++ckpt_ver);
 
 	/* write cached NAT/SIT entries to NAT/SIT area */
-	flush_nat_entries(sbi);
+	flush_nat_entries(sbi, cpc);
 	flush_sit_entries(sbi, cpc);
 
 	/* unlock all the fs_lock[] in do_checkpoint() */
 	err = do_checkpoint(sbi, cpc);
-	if (err) {
+	if (err)
 		release_discard_addrs(sbi);
-	} else {
+	else
 		clear_prefree_segments(sbi, cpc);
-		f2fs_wait_all_discard_bio(sbi);
-	}
 
 	unblock_operations(sbi);
 	stat_inc_cp_count(sbi->stat_info);
 
-	if (cpc->reason == CP_RECOVERY)
+	if (cpc->reason & CP_RECOVERY)
 		f2fs_msg(sbi->sb, KERN_NOTICE,
 			"checkpoint: version = %llx", ckpt_ver);
 
diff --git a/fs/f2fs/data.c b/fs/f2fs/data.c
index 9ac262564fa6..87c1f4150c64 100644
--- a/fs/f2fs/data.c
+++ b/fs/f2fs/data.c
@@ -22,6 +22,7 @@
 #include <linux/mm.h>
 #include <linux/memcontrol.h>
 #include <linux/cleancache.h>
+#include <linux/sched/signal.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -55,12 +56,14 @@ static void f2fs_read_end_io(struct bio *bio)
 	int i;
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO))
-		bio->bi_error = -EIO;
+	if (time_to_inject(F2FS_P_SB(bio->bi_io_vec->bv_page), FAULT_IO)) {
+		f2fs_show_injection_info(FAULT_IO);
+		bio->bi_status = BLK_STS_IOERR;
+	}
 #endif
 
 	if (f2fs_bio_encrypted(bio)) {
-		if (bio->bi_error) {
+		if (bio->bi_status) {
 			fscrypt_release_ctx(bio->bi_private);
 		} else {
 			fscrypt_decrypt_bio_pages(bio->bi_private, bio);
@@ -71,7 +74,7 @@ static void f2fs_read_end_io(struct bio *bio)
 	bio_for_each_segment_all(bvec, bio, i) {
 		struct page *page = bvec->bv_page;
 
-		if (!bio->bi_error) {
+		if (!bio->bi_status) {
 			if (!PageUptodate(page))
 				SetPageUptodate(page);
 		} else {
@@ -93,9 +96,20 @@ static void f2fs_write_end_io(struct bio *bio)
 		struct page *page = bvec->bv_page;
 		enum count_type type = WB_DATA_TYPE(page);
 
+		if (IS_DUMMY_WRITTEN_PAGE(page)) {
+			set_page_private(page, (unsigned long)NULL);
+			ClearPagePrivate(page);
+			unlock_page(page);
+			mempool_free(page, sbi->write_io_dummy);
+
+			if (unlikely(bio->bi_status))
+				f2fs_stop_checkpoint(sbi, true);
+			continue;
+		}
+
 		fscrypt_pullback_bio_page(&page, true);
 
-		if (unlikely(bio->bi_error)) {
+		if (unlikely(bio->bi_status)) {
 			mapping_set_error(page->mapping, -EIO);
 			f2fs_stop_checkpoint(sbi, true);
 		}
@@ -171,10 +185,46 @@ static inline void __submit_bio(struct f2fs_sb_info *sbi,
 				struct bio *bio, enum page_type type)
 {
 	if (!is_read_io(bio_op(bio))) {
+		unsigned int start;
+
 		if (f2fs_sb_mounted_blkzoned(sbi->sb) &&
 			current->plug && (type == DATA || type == NODE))
 			blk_finish_plug(current->plug);
+
+		if (type != DATA && type != NODE)
+			goto submit_io;
+
+		start = bio->bi_iter.bi_size >> F2FS_BLKSIZE_BITS;
+		start %= F2FS_IO_SIZE(sbi);
+
+		if (start == 0)
+			goto submit_io;
+
+		/* fill dummy pages */
+		for (; start < F2FS_IO_SIZE(sbi); start++) {
+			struct page *page =
+				mempool_alloc(sbi->write_io_dummy,
+					GFP_NOIO | __GFP_ZERO | __GFP_NOFAIL);
+			f2fs_bug_on(sbi, !page);
+
+			SetPagePrivate(page);
+			set_page_private(page, (unsigned long)DUMMY_WRITTEN_PAGE);
+			lock_page(page);
+			if (bio_add_page(bio, page, PAGE_SIZE, 0) < PAGE_SIZE)
+				f2fs_bug_on(sbi, 1);
+		}
+		/*
+		 * In the NODE case, we lose next block address chain. So, we
+		 * need to do checkpoint in f2fs_sync_file.
+		 */
+		if (type == NODE)
+			set_sbi_flag(sbi, SBI_NEED_CP);
 	}
+submit_io:
+	if (is_read_io(bio_op(bio)))
+		trace_f2fs_submit_read_bio(sbi->sb, type, bio);
+	else
+		trace_f2fs_submit_write_bio(sbi->sb, type, bio);
 	submit_bio(bio);
 }
 
@@ -185,19 +235,19 @@ static void __submit_merged_bio(struct f2fs_bio_info *io)
 	if (!io->bio)
 		return;
 
+	bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
+
 	if (is_read_io(fio->op))
-		trace_f2fs_submit_read_bio(io->sbi->sb, fio, io->bio);
+		trace_f2fs_prepare_read_bio(io->sbi->sb, fio->type, io->bio);
 	else
-		trace_f2fs_submit_write_bio(io->sbi->sb, fio, io->bio);
-
-	bio_set_op_attrs(io->bio, fio->op, fio->op_flags);
+		trace_f2fs_prepare_write_bio(io->sbi->sb, fio->type, io->bio);
 
 	__submit_bio(io->sbi, io->bio, fio->type);
 	io->bio = NULL;
 }
 
-static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
-						struct page *page, nid_t ino)
+static bool __has_merged_page(struct f2fs_bio_info *io,
+				struct inode *inode, nid_t ino, pgoff_t idx)
 {
 	struct bio_vec *bvec;
 	struct page *target;
@@ -206,7 +256,7 @@ static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
 	if (!io->bio)
 		return false;
 
-	if (!inode && !page && !ino)
+	if (!inode && !ino)
 		return true;
 
 	bio_for_each_segment_all(bvec, io->bio, i) {
@@ -216,10 +266,11 @@ static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
 		else
 			target = fscrypt_control_page(bvec->bv_page);
 
+		if (idx != target->index)
+			continue;
+
 		if (inode && inode == target->mapping->host)
 			return true;
-		if (page && page == target)
-			return true;
 		if (ino && ino == ino_of_node(target))
 			return true;
 	}
@@ -228,70 +279,88 @@ static bool __has_merged_page(struct f2fs_bio_info *io, struct inode *inode,
 }
 
 static bool has_merged_page(struct f2fs_sb_info *sbi, struct inode *inode,
-						struct page *page, nid_t ino,
-						enum page_type type)
+				nid_t ino, pgoff_t idx, enum page_type type)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
-	struct f2fs_bio_info *io = &sbi->write_io[btype];
-	bool ret;
+	enum temp_type temp;
+	struct f2fs_bio_info *io;
+	bool ret = false;
 
-	down_read(&io->io_rwsem);
-	ret = __has_merged_page(io, inode, page, ino);
-	up_read(&io->io_rwsem);
+	for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
+		io = sbi->write_io[btype] + temp;
+
+		down_read(&io->io_rwsem);
+		ret = __has_merged_page(io, inode, ino, idx);
+		up_read(&io->io_rwsem);
+
+		/* TODO: use HOT temp only for meta pages now. */
+		if (ret || btype == META)
+			break;
+	}
 	return ret;
 }
 
-static void __f2fs_submit_merged_bio(struct f2fs_sb_info *sbi,
-				struct inode *inode, struct page *page,
-				nid_t ino, enum page_type type, int rw)
+static void __f2fs_submit_merged_write(struct f2fs_sb_info *sbi,
+				enum page_type type, enum temp_type temp)
 {
 	enum page_type btype = PAGE_TYPE_OF_BIO(type);
-	struct f2fs_bio_info *io;
-
-	io = is_read_io(rw) ? &sbi->read_io : &sbi->write_io[btype];
+	struct f2fs_bio_info *io = sbi->write_io[btype] + temp;
 
 	down_write(&io->io_rwsem);
 
-	if (!__has_merged_page(io, inode, page, ino))
-		goto out;
-
 	/* change META to META_FLUSH in the checkpoint procedure */
 	if (type >= META_FLUSH) {
 		io->fio.type = META_FLUSH;
 		io->fio.op = REQ_OP_WRITE;
-		io->fio.op_flags = REQ_PREFLUSH | REQ_META | REQ_PRIO;
+		io->fio.op_flags = REQ_META | REQ_PRIO | REQ_SYNC;
 		if (!test_opt(sbi, NOBARRIER))
-			io->fio.op_flags |= REQ_FUA;
+			io->fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
 	}
 	__submit_merged_bio(io);
-out:
 	up_write(&io->io_rwsem);
 }
 
-void f2fs_submit_merged_bio(struct f2fs_sb_info *sbi, enum page_type type,
-									int rw)
+static void __submit_merged_write_cond(struct f2fs_sb_info *sbi,
+				struct inode *inode, nid_t ino, pgoff_t idx,
+				enum page_type type, bool force)
+{
+	enum temp_type temp;
+
+	if (!force && !has_merged_page(sbi, inode, ino, idx, type))
+		return;
+
+	for (temp = HOT; temp < NR_TEMP_TYPE; temp++) {
+
+		__f2fs_submit_merged_write(sbi, type, temp);
+
+		/* TODO: use HOT temp only for meta pages now. */
+		if (type >= META)
+			break;
+	}
+}
+
+void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type)
 {
-	__f2fs_submit_merged_bio(sbi, NULL, NULL, 0, type, rw);
+	__submit_merged_write_cond(sbi, NULL, 0, 0, type, true);
 }
 
-void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *sbi,
-				struct inode *inode, struct page *page,
-				nid_t ino, enum page_type type, int rw)
+void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
+				struct inode *inode, nid_t ino, pgoff_t idx,
+				enum page_type type)
 {
-	if (has_merged_page(sbi, inode, page, ino, type))
-		__f2fs_submit_merged_bio(sbi, inode, page, ino, type, rw);
+	__submit_merged_write_cond(sbi, inode, ino, idx, type, false);
 }
 
-void f2fs_flush_merged_bios(struct f2fs_sb_info *sbi)
+void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi)
 {
-	f2fs_submit_merged_bio(sbi, DATA, WRITE);
-	f2fs_submit_merged_bio(sbi, NODE, WRITE);
-	f2fs_submit_merged_bio(sbi, META, WRITE);
+	f2fs_submit_merged_write(sbi, DATA);
+	f2fs_submit_merged_write(sbi, NODE);
+	f2fs_submit_merged_write(sbi, META);
 }
 
 /*
  * Fill the locked page with data located in the block address.
- * Return unlocked page.
+ * A caller needs to unlock the page on failure.
  */
 int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 {
@@ -312,18 +381,35 @@ int f2fs_submit_page_bio(struct f2fs_io_info *fio)
 	bio_set_op_attrs(bio, fio->op, fio->op_flags);
 
 	__submit_bio(fio->sbi, bio, fio->type);
+
+	if (!is_read_io(fio->op))
+		inc_page_count(fio->sbi, WB_DATA_TYPE(fio->page));
 	return 0;
 }
 
-void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
+int f2fs_submit_page_write(struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = fio->sbi;
 	enum page_type btype = PAGE_TYPE_OF_BIO(fio->type);
-	struct f2fs_bio_info *io;
-	bool is_read = is_read_io(fio->op);
+	struct f2fs_bio_info *io = sbi->write_io[btype] + fio->temp;
 	struct page *bio_page;
+	int err = 0;
 
-	io = is_read ? &sbi->read_io : &sbi->write_io[btype];
+	f2fs_bug_on(sbi, is_read_io(fio->op));
+
+	down_write(&io->io_rwsem);
+next:
+	if (fio->in_list) {
+		spin_lock(&io->io_lock);
+		if (list_empty(&io->io_list)) {
+			spin_unlock(&io->io_lock);
+			goto out_fail;
+		}
+		fio = list_first_entry(&io->io_list,
+						struct f2fs_io_info, list);
+		list_del(&fio->list);
+		spin_unlock(&io->io_lock);
+	}
 
 	if (fio->old_blkaddr != NEW_ADDR)
 		verify_block_addr(sbi, fio->old_blkaddr);
@@ -331,10 +417,10 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 
 	bio_page = fio->encrypted_page ? fio->encrypted_page : fio->page;
 
-	if (!is_read)
-		inc_page_count(sbi, WB_DATA_TYPE(bio_page));
+	/* set submitted = 1 as a return value */
+	fio->submitted = 1;
 
-	down_write(&io->io_rwsem);
+	inc_page_count(sbi, WB_DATA_TYPE(bio_page));
 
 	if (io->bio && (io->last_block_in_bio != fio->new_blkaddr - 1 ||
 	    (io->fio.op != fio->op || io->fio.op_flags != fio->op_flags) ||
@@ -342,13 +428,18 @@ void f2fs_submit_page_mbio(struct f2fs_io_info *fio)
 		__submit_merged_bio(io);
 alloc_new:
 	if (io->bio == NULL) {
+		if ((fio->type == DATA || fio->type == NODE) &&
+				fio->new_blkaddr & F2FS_IO_SIZE_MASK(sbi)) {
+			err = -EAGAIN;
+			dec_page_count(sbi, WB_DATA_TYPE(bio_page));
+			goto out_fail;
+		}
 		io->bio = __bio_alloc(sbi, fio->new_blkaddr,
-						BIO_MAX_PAGES, is_read);
+						BIO_MAX_PAGES, false);
 		io->fio = *fio;
 	}
 
-	if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) <
-							PAGE_SIZE) {
+	if (bio_add_page(io->bio, bio_page, PAGE_SIZE, 0) < PAGE_SIZE) {
 		__submit_merged_bio(io);
 		goto alloc_new;
 	}
@@ -356,8 +447,13 @@ alloc_new:
 	io->last_block_in_bio = fio->new_blkaddr;
 	f2fs_trace_ios(fio, 0);
 
+	trace_f2fs_submit_page_write(fio->page, fio);
+
+	if (fio->in_list)
+		goto next;
+out_fail:
 	up_write(&io->io_rwsem);
-	trace_f2fs_submit_page_mbio(fio->page, fio);
+	return err;
 }
 
 static void __set_data_blkaddr(struct dnode_of_data *dn)
@@ -395,14 +491,15 @@ void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr)
 int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
+	int err;
 
 	if (!count)
 		return 0;
 
 	if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
 		return -EPERM;
-	if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
-		return -ENOSPC;
+	if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
+		return err;
 
 	trace_f2fs_reserve_new_blocks(dn->inode, dn->nid,
 						dn->ofs_in_node, count);
@@ -453,7 +550,7 @@ int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index)
 
 int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index)
 {
-	struct extent_info ei;
+	struct extent_info ei  = {0,0,0};
 	struct inode *inode = dn->inode;
 
 	if (f2fs_lookup_extent_cache(inode, index, &ei)) {
@@ -470,7 +567,7 @@ struct page *get_read_data_page(struct inode *inode, pgoff_t index,
 	struct address_space *mapping = inode->i_mapping;
 	struct dnode_of_data dn;
 	struct page *page;
-	struct extent_info ei;
+	struct extent_info ei = {0,0,0};
 	int err;
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(inode),
@@ -653,6 +750,7 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	struct node_info ni;
 	pgoff_t fofs;
 	blkcnt_t count = 1;
+	int err;
 
 	if (unlikely(is_inode_flag_set(dn->inode, FI_NO_ALLOC)))
 		return -EPERM;
@@ -661,15 +759,15 @@ static int __allocate_data_block(struct dnode_of_data *dn)
 	if (dn->data_blkaddr == NEW_ADDR)
 		goto alloc;
 
-	if (unlikely(!inc_valid_block_count(sbi, dn->inode, &count)))
-		return -ENOSPC;
+	if (unlikely((err = inc_valid_block_count(sbi, dn->inode, &count))))
+		return err;
 
 alloc:
 	get_node_info(sbi, dn->nid, &ni);
 	set_summary(&sum, dn->nid, dn->ofs_in_node, ni.version);
 
 	allocate_data_block(sbi, NULL, dn->data_blkaddr, &dn->data_blkaddr,
-						&sum, CURSEG_WARM_DATA);
+					&sum, CURSEG_WARM_DATA, NULL, false);
 	set_data_blkaddr(dn);
 
 	/* update i_size */
@@ -694,6 +792,9 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 	struct f2fs_map_blocks map;
 	int err = 0;
 
+	if (is_inode_flag_set(inode, FI_NO_PREALLOC))
+		return 0;
+
 	map.m_lblk = F2FS_BLK_ALIGN(iocb->ki_pos);
 	map.m_len = F2FS_BYTES_TO_BLK(iocb->ki_pos + iov_iter_count(from));
 	if (map.m_len > map.m_lblk)
@@ -722,6 +823,21 @@ int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from)
 	return err;
 }
 
+static inline void __do_map_lock(struct f2fs_sb_info *sbi, int flag, bool lock)
+{
+	if (flag == F2FS_GET_BLOCK_PRE_AIO) {
+		if (lock)
+			down_read(&sbi->node_change);
+		else
+			up_read(&sbi->node_change);
+	} else {
+		if (lock)
+			f2fs_lock_op(sbi);
+		else
+			f2fs_unlock_op(sbi);
+	}
+}
+
 /*
  * f2fs_map_blocks() now supported readahead/bmap/rw direct_IO with
  * f2fs_map_blocks structure.
@@ -742,7 +858,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 	int err = 0, ofs = 1;
 	unsigned int ofs_in_node, last_ofs_in_node;
 	blkcnt_t prealloc;
-	struct extent_info ei;
+	struct extent_info ei = {0,0,0};
 	block_t blkaddr;
 
 	if (!maxblocks)
@@ -764,7 +880,7 @@ int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
 
 next_dnode:
 	if (create)
-		f2fs_lock_op(sbi);
+		__do_map_lock(sbi, flag, true);
 
 	/* When reading holes, we need its node page */
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
@@ -806,7 +922,7 @@ next_block:
 			}
 			if (err)
 				goto sync_out;
-			map->m_flags = F2FS_MAP_NEW;
+			map->m_flags |= F2FS_MAP_NEW;
 			blkaddr = dn.data_blkaddr;
 		} else {
 			if (flag == F2FS_GET_BLOCK_BMAP) {
@@ -874,7 +990,7 @@ skip:
 	f2fs_put_dnode(&dn);
 
 	if (create) {
-		f2fs_unlock_op(sbi);
+		__do_map_lock(sbi, flag, false);
 		f2fs_balance_fs(sbi, dn.node_changed);
 	}
 	goto next_dnode;
@@ -883,7 +999,7 @@ sync_out:
 	f2fs_put_dnode(&dn);
 unlock_out:
 	if (create) {
-		f2fs_unlock_op(sbi);
+		__do_map_lock(sbi, flag, false);
 		f2fs_balance_fs(sbi, dn.node_changed);
 	}
 out:
@@ -906,7 +1022,7 @@ static int __get_data_block(struct inode *inode, sector_t iblock,
 	if (!err) {
 		map_bh(bh, inode->i_sb, map.m_pblk);
 		bh->b_state = (bh->b_state & ~F2FS_MAP_FLAGS) | map.m_flags;
-		bh->b_size = map.m_len << inode->i_blkbits;
+		bh->b_size = (u64)map.m_len << inode->i_blkbits;
 	}
 	return err;
 }
@@ -1086,9 +1202,10 @@ static int f2fs_mpage_readpages(struct address_space *mapping,
 
 	for (page_idx = 0; nr_pages; page_idx++, nr_pages--) {
 
-		prefetchw(&page->flags);
 		if (pages) {
-			page = list_entry(pages->prev, struct page, lru);
+			page = list_last_entry(pages, struct page, lru);
+
+			prefetchw(&page->flags);
 			list_del(&page->lru);
 			if (add_to_page_cache_lru(page, mapping,
 						  page->index,
@@ -1207,7 +1324,7 @@ static int f2fs_read_data_pages(struct file *file,
 			struct list_head *pages, unsigned nr_pages)
 {
 	struct inode *inode = file->f_mapping->host;
-	struct page *page = list_entry(pages->prev, struct page, lru);
+	struct page *page = list_last_entry(pages, struct page, lru);
 
 	trace_f2fs_readpages(inode, page, nr_pages);
 
@@ -1218,17 +1335,84 @@ static int f2fs_read_data_pages(struct file *file,
 	return f2fs_mpage_readpages(mapping, pages, NULL, nr_pages);
 }
 
+static int encrypt_one_page(struct f2fs_io_info *fio)
+{
+	struct inode *inode = fio->page->mapping->host;
+	gfp_t gfp_flags = GFP_NOFS;
+
+	if (!f2fs_encrypted_inode(inode) || !S_ISREG(inode->i_mode))
+		return 0;
+
+	/* wait for GCed encrypted page writeback */
+	f2fs_wait_on_encrypted_page_writeback(fio->sbi, fio->old_blkaddr);
+
+retry_encrypt:
+	fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page,
+			PAGE_SIZE, 0, fio->page->index, gfp_flags);
+	if (!IS_ERR(fio->encrypted_page))
+		return 0;
+
+	/* flush pending IOs and wait for a while in the ENOMEM case */
+	if (PTR_ERR(fio->encrypted_page) == -ENOMEM) {
+		f2fs_flush_merged_writes(fio->sbi);
+		congestion_wait(BLK_RW_ASYNC, HZ/50);
+		gfp_flags |= __GFP_NOFAIL;
+		goto retry_encrypt;
+	}
+	return PTR_ERR(fio->encrypted_page);
+}
+
+static inline bool need_inplace_update(struct f2fs_io_info *fio)
+{
+	struct inode *inode = fio->page->mapping->host;
+
+	if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
+		return false;
+	if (is_cold_data(fio->page))
+		return false;
+	if (IS_ATOMIC_WRITTEN_PAGE(fio->page))
+		return false;
+
+	return need_inplace_update_policy(inode, fio);
+}
+
+static inline bool valid_ipu_blkaddr(struct f2fs_io_info *fio)
+{
+	if (fio->old_blkaddr == NEW_ADDR)
+		return false;
+	if (fio->old_blkaddr == NULL_ADDR)
+		return false;
+	return true;
+}
+
 int do_write_data_page(struct f2fs_io_info *fio)
 {
 	struct page *page = fio->page;
 	struct inode *inode = page->mapping->host;
 	struct dnode_of_data dn;
+	struct extent_info ei = {0,0,0};
+	bool ipu_force = false;
 	int err = 0;
 
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
+	if (need_inplace_update(fio) &&
+			f2fs_lookup_extent_cache(inode, page->index, &ei)) {
+		fio->old_blkaddr = ei.blk + page->index - ei.fofs;
+
+		if (valid_ipu_blkaddr(fio)) {
+			ipu_force = true;
+			fio->need_lock = LOCK_DONE;
+			goto got_it;
+		}
+	}
+
+	/* Deadlock due to between page->lock and f2fs_lock_op */
+	if (fio->need_lock == LOCK_REQ && !f2fs_trylock_op(fio->sbi))
+		return -EAGAIN;
+
 	err = get_dnode_of_data(&dn, page->index, LOOKUP_NODE);
 	if (err)
-		return err;
+		goto out;
 
 	fio->old_blkaddr = dn.data_blkaddr;
 
@@ -1237,59 +1421,56 @@ int do_write_data_page(struct f2fs_io_info *fio)
 		ClearPageUptodate(page);
 		goto out_writepage;
 	}
+got_it:
+	/*
+	 * If current allocation needs SSR,
+	 * it had better in-place writes for updated data.
+	 */
+	if (ipu_force || (valid_ipu_blkaddr(fio) && need_inplace_update(fio))) {
+		err = encrypt_one_page(fio);
+		if (err)
+			goto out_writepage;
 
-	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode)) {
-		gfp_t gfp_flags = GFP_NOFS;
+		set_page_writeback(page);
+		f2fs_put_dnode(&dn);
+		if (fio->need_lock == LOCK_REQ)
+			f2fs_unlock_op(fio->sbi);
+		err = rewrite_data_page(fio);
+		trace_f2fs_do_write_data_page(fio->page, IPU);
+		set_inode_flag(inode, FI_UPDATE_WRITE);
+		return err;
+	}
 
-		/* wait for GCed encrypted page writeback */
-		f2fs_wait_on_encrypted_page_writeback(F2FS_I_SB(inode),
-							fio->old_blkaddr);
-retry_encrypt:
-		fio->encrypted_page = fscrypt_encrypt_page(inode, fio->page,
-							PAGE_SIZE, 0,
-							fio->page->index,
-							gfp_flags);
-		if (IS_ERR(fio->encrypted_page)) {
-			err = PTR_ERR(fio->encrypted_page);
-			if (err == -ENOMEM) {
-				/* flush pending ios and wait for a while */
-				f2fs_flush_merged_bios(F2FS_I_SB(inode));
-				congestion_wait(BLK_RW_ASYNC, HZ/50);
-				gfp_flags |= __GFP_NOFAIL;
-				err = 0;
-				goto retry_encrypt;
-			}
+	if (fio->need_lock == LOCK_RETRY) {
+		if (!f2fs_trylock_op(fio->sbi)) {
+			err = -EAGAIN;
 			goto out_writepage;
 		}
+		fio->need_lock = LOCK_REQ;
 	}
 
+	err = encrypt_one_page(fio);
+	if (err)
+		goto out_writepage;
+
 	set_page_writeback(page);
 
-	/*
-	 * If current allocation needs SSR,
-	 * it had better in-place writes for updated data.
-	 */
-	if (unlikely(fio->old_blkaddr != NEW_ADDR &&
-			!is_cold_data(page) &&
-			!IS_ATOMIC_WRITTEN_PAGE(page) &&
-			need_inplace_update(inode))) {
-		rewrite_data_page(fio);
-		set_inode_flag(inode, FI_UPDATE_WRITE);
-		trace_f2fs_do_write_data_page(page, IPU);
-	} else {
-		write_data_page(&dn, fio);
-		trace_f2fs_do_write_data_page(page, OPU);
-		set_inode_flag(inode, FI_APPEND_WRITE);
-		if (page->index == 0)
-			set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
-	}
+	/* LFS mode write path */
+	write_data_page(&dn, fio);
+	trace_f2fs_do_write_data_page(page, OPU);
+	set_inode_flag(inode, FI_APPEND_WRITE);
+	if (page->index == 0)
+		set_inode_flag(inode, FI_FIRST_BLOCK_WRITTEN);
 out_writepage:
 	f2fs_put_dnode(&dn);
+out:
+	if (fio->need_lock == LOCK_REQ)
+		f2fs_unlock_op(fio->sbi);
 	return err;
 }
 
-static int f2fs_write_data_page(struct page *page,
-					struct writeback_control *wbc)
+static int __write_data_page(struct page *page, bool *submitted,
+				struct writeback_control *wbc)
 {
 	struct inode *inode = page->mapping->host;
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -1305,12 +1486,18 @@ static int f2fs_write_data_page(struct page *page,
 		.type = DATA,
 		.op = REQ_OP_WRITE,
 		.op_flags = wbc_to_write_flags(wbc),
+		.old_blkaddr = NULL_ADDR,
 		.page = page,
 		.encrypted_page = NULL,
+		.submitted = false,
+		.need_lock = LOCK_RETRY,
 	};
 
 	trace_f2fs_writepage(page, DATA);
 
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto redirty_out;
+
 	if (page->index < end_index)
 		goto write;
 
@@ -1324,8 +1511,6 @@ static int f2fs_write_data_page(struct page *page,
 
 	zero_user_segment(page, offset, PAGE_SIZE);
 write:
-	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
-		goto redirty_out;
 	if (f2fs_is_drop_cache(inode))
 		goto out;
 	/* we should not write 0'th page having journal header */
@@ -1342,6 +1527,7 @@ write:
 
 	/* Dentry blocks are controlled by checkpoint */
 	if (S_ISDIR(inode->i_mode)) {
+		fio.need_lock = LOCK_DONE;
 		err = do_write_data_page(&fio);
 		goto done;
 	}
@@ -1350,16 +1536,26 @@ write:
 		need_balance_fs = true;
 	else if (has_not_enough_free_secs(sbi, 0, 0))
 		goto redirty_out;
+	else
+		set_inode_flag(inode, FI_HOT_DATA);
 
 	err = -EAGAIN;
-	f2fs_lock_op(sbi);
-	if (f2fs_has_inline_data(inode))
+	if (f2fs_has_inline_data(inode)) {
 		err = f2fs_write_inline_data(inode, page);
-	if (err == -EAGAIN)
+		if (!err)
+			goto out;
+	}
+
+	if (err == -EAGAIN) {
 		err = do_write_data_page(&fio);
+		if (err == -EAGAIN) {
+			fio.need_lock = LOCK_REQ;
+			err = do_write_data_page(&fio);
+		}
+	}
 	if (F2FS_I(inode)->last_disk_size < psize)
 		F2FS_I(inode)->last_disk_size = psize;
-	f2fs_unlock_op(sbi);
+
 done:
 	if (err && err != -ENOENT)
 		goto redirty_out;
@@ -1370,15 +1566,23 @@ out:
 		ClearPageUptodate(page);
 
 	if (wbc->for_reclaim) {
-		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, DATA, WRITE);
+		f2fs_submit_merged_write_cond(sbi, inode, 0, page->index, DATA);
+		clear_inode_flag(inode, FI_HOT_DATA);
 		remove_dirty_inode(inode);
+		submitted = NULL;
 	}
 
 	unlock_page(page);
-	f2fs_balance_fs(sbi, need_balance_fs);
+	if (!S_ISDIR(inode->i_mode))
+		f2fs_balance_fs(sbi, need_balance_fs);
+
+	if (unlikely(f2fs_cp_error(sbi))) {
+		f2fs_submit_merged_write(sbi, DATA);
+		submitted = NULL;
+	}
 
-	if (unlikely(f2fs_cp_error(sbi)))
-		f2fs_submit_merged_bio(sbi, DATA, WRITE);
+	if (submitted)
+		*submitted = fio.submitted;
 
 	return 0;
 
@@ -1390,6 +1594,12 @@ redirty_out:
 	return err;
 }
 
+static int f2fs_write_data_page(struct page *page,
+					struct writeback_control *wbc)
+{
+	return __write_data_page(page, NULL, wbc);
+}
+
 /*
  * This function was copied from write_cche_pages from mm/page-writeback.c.
  * The major change is making write step of cold data page separately from
@@ -1406,13 +1616,19 @@ static int f2fs_write_cache_pages(struct address_space *mapping,
 	pgoff_t index;
 	pgoff_t end;		/* Inclusive */
 	pgoff_t done_index;
+	pgoff_t last_idx = ULONG_MAX;
 	int cycled;
 	int range_whole = 0;
 	int tag;
-	int nwritten = 0;
 
 	pagevec_init(&pvec, 0);
 
+	if (get_dirty_pages(mapping->host) <=
+				SM_I(F2FS_M_SB(mapping))->min_hot_blocks)
+		set_inode_flag(mapping->host, FI_HOT_DATA);
+	else
+		clear_inode_flag(mapping->host, FI_HOT_DATA);
+
 	if (wbc->range_cyclic) {
 		writeback_index = mapping->writeback_index; /* prev offset */
 		index = writeback_index;
@@ -1446,6 +1662,7 @@ retry:
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
+			bool submitted = false;
 
 			if (page->index > end) {
 				done = 1;
@@ -1453,7 +1670,7 @@ retry:
 			}
 
 			done_index = page->index;
-
+retry_write:
 			lock_page(page);
 
 			if (unlikely(page->mapping != mapping)) {
@@ -1479,7 +1696,7 @@ continue_unlock:
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
-			ret = mapping->a_ops->writepage(page, wbc);
+			ret = __write_data_page(page, &submitted, wbc);
 			if (unlikely(ret)) {
 				/*
 				 * keep nr_to_write, since vfs uses this to
@@ -1489,16 +1706,27 @@ continue_unlock:
 					unlock_page(page);
 					ret = 0;
 					continue;
+				} else if (ret == -EAGAIN) {
+					ret = 0;
+					if (wbc->sync_mode == WB_SYNC_ALL) {
+						cond_resched();
+						congestion_wait(BLK_RW_ASYNC,
+									HZ/50);
+						goto retry_write;
+					}
+					continue;
 				}
 				done_index = page->index + 1;
 				done = 1;
 				break;
-			} else {
-				nwritten++;
+			} else if (submitted) {
+				last_idx = page->index;
 			}
 
-			if (--wbc->nr_to_write <= 0 &&
-			    wbc->sync_mode == WB_SYNC_NONE) {
+			/* give a priority to WB_SYNC threads */
+			if ((atomic_read(&F2FS_M_SB(mapping)->wb_sync_req) ||
+					--wbc->nr_to_write <= 0) &&
+					wbc->sync_mode == WB_SYNC_NONE) {
 				done = 1;
 				break;
 			}
@@ -1516,9 +1744,9 @@ continue_unlock:
 	if (wbc->range_cyclic || (range_whole && wbc->nr_to_write > 0))
 		mapping->writeback_index = done_index;
 
-	if (nwritten)
-		f2fs_submit_merged_bio_cond(F2FS_M_SB(mapping), mapping->host,
-							NULL, 0, DATA, WRITE);
+	if (last_idx != ULONG_MAX)
+		f2fs_submit_merged_write_cond(F2FS_M_SB(mapping), mapping->host,
+						0, last_idx, DATA);
 
 	return ret;
 }
@@ -1539,6 +1767,10 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 	if (!get_dirty_pages(inode) && wbc->sync_mode == WB_SYNC_NONE)
 		return 0;
 
+	/* during POR, we don't need to trigger writepage at all. */
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto skip_write;
+
 	if (S_ISDIR(inode->i_mode) && wbc->sync_mode == WB_SYNC_NONE &&
 			get_dirty_pages(inode) < nr_pages_to_skip(sbi, DATA) &&
 			available_free_memory(sbi, DIRTY_DENTS))
@@ -1548,15 +1780,20 @@ static int f2fs_write_data_pages(struct address_space *mapping,
 	if (is_inode_flag_set(inode, FI_DO_DEFRAG))
 		goto skip_write;
 
-	/* during POR, we don't need to trigger writepage at all. */
-	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
-		goto skip_write;
-
 	trace_f2fs_writepages(mapping->host, wbc, DATA);
 
+	/* to avoid spliting IOs due to mixed WB_SYNC_ALL and WB_SYNC_NONE */
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		atomic_inc(&sbi->wb_sync_req);
+	else if (atomic_read(&sbi->wb_sync_req))
+		goto skip_write;
+
 	blk_start_plug(&plug);
 	ret = f2fs_write_cache_pages(mapping, wbc);
 	blk_finish_plug(&plug);
+
+	if (wbc->sync_mode == WB_SYNC_ALL)
+		atomic_dec(&sbi->wb_sync_req);
 	/*
 	 * if some pages were truncated, we cannot guarantee its mapping->host
 	 * to detect pending bios.
@@ -1577,8 +1814,10 @@ static void f2fs_write_failed(struct address_space *mapping, loff_t to)
 	loff_t i_size = i_size_read(inode);
 
 	if (to > i_size) {
+		down_write(&F2FS_I(inode)->i_mmap_sem);
 		truncate_pagecache(inode, i_size);
 		truncate_blocks(inode, i_size, true);
+		up_write(&F2FS_I(inode)->i_mmap_sem);
 	}
 }
 
@@ -1591,19 +1830,20 @@ static int prepare_write_begin(struct f2fs_sb_info *sbi,
 	struct dnode_of_data dn;
 	struct page *ipage;
 	bool locked = false;
-	struct extent_info ei;
+	struct extent_info ei = {0,0,0};
 	int err = 0;
 
 	/*
 	 * we already allocated all the blocks, so we don't need to get
 	 * the block addresses when there is no need to fill the page.
 	 */
-	if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE)
+	if (!f2fs_has_inline_data(inode) && len == PAGE_SIZE &&
+			!is_inode_flag_set(inode, FI_NO_PREALLOC))
 		return 0;
 
 	if (f2fs_has_inline_data(inode) ||
 			(pos & PAGE_MASK) >= i_size_read(inode)) {
-		f2fs_lock_op(sbi);
+		__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, true);
 		locked = true;
 	}
 restart:
@@ -1639,7 +1879,8 @@ restart:
 			err = get_dnode_of_data(&dn, index, LOOKUP_NODE);
 			if (err || dn.data_blkaddr == NULL_ADDR) {
 				f2fs_put_dnode(&dn);
-				f2fs_lock_op(sbi);
+				__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO,
+								true);
 				locked = true;
 				goto restart;
 			}
@@ -1653,7 +1894,7 @@ out:
 	f2fs_put_dnode(&dn);
 unlock_out:
 	if (locked)
-		f2fs_unlock_op(sbi);
+		__do_map_lock(sbi, F2FS_GET_BLOCK_PRE_AIO, false);
 	return err;
 }
 
@@ -1682,7 +1923,12 @@ static int f2fs_write_begin(struct file *file, struct address_space *mapping,
 			goto fail;
 	}
 repeat:
-	page = grab_cache_page_write_begin(mapping, index, flags);
+	/*
+	 * Do not use grab_cache_page_write_begin() to avoid deadlock due to
+	 * wait_for_stable_page. Will wait that below with our IO control.
+	 */
+	page = pagecache_get_page(mapping, index,
+				FGP_LOCK | FGP_WRITE | FGP_CREAT, GFP_NOFS);
 	if (!page) {
 		err = -ENOMEM;
 		goto fail;
@@ -1715,6 +1961,11 @@ repeat:
 	if (len == PAGE_SIZE || PageUptodate(page))
 		return 0;
 
+	if (!(pos & (PAGE_SIZE - 1)) && (pos + len) >= i_size_read(inode)) {
+		zero_user_segment(page, len, PAGE_SIZE);
+		return 0;
+	}
+
 	if (blkaddr == NEW_ADDR) {
 		zero_user_segment(page, 0, PAGE_SIZE);
 		SetPageUptodate(page);
@@ -1768,7 +2019,7 @@ static int f2fs_write_end(struct file *file,
 	 * let generic_perform_write() try to copy data again through copied=0.
 	 */
 	if (!PageUptodate(page)) {
-		if (unlikely(copied != PAGE_SIZE))
+		if (unlikely(copied != len))
 			copied = 0;
 		else
 			SetPageUptodate(page);
@@ -1857,7 +2108,7 @@ void f2fs_invalidate_page(struct page *page, unsigned int offset,
 
 	/* This is atomic written page, keep Private */
 	if (IS_ATOMIC_WRITTEN_PAGE(page))
-		return;
+		return drop_inmem_page(inode, page);
 
 	set_page_private(page, 0);
 	ClearPagePrivate(page);
@@ -1917,7 +2168,7 @@ static int f2fs_set_data_page_dirty(struct page *page)
 	if (!PageUptodate(page))
 		SetPageUptodate(page);
 
-	if (f2fs_is_atomic_file(inode)) {
+	if (f2fs_is_atomic_file(inode) && !f2fs_is_commit_atomic_write(inode)) {
 		if (!IS_ATOMIC_WRITTEN_PAGE(page)) {
 			register_inmem_page(inode, page);
 			return 1;
@@ -1964,8 +2215,12 @@ int f2fs_migrate_page(struct address_space *mapping,
 	BUG_ON(PageWriteback(page));
 
 	/* migrating an atomic written page is safe with the inmem_lock hold */
-	if (atomic_written && !mutex_trylock(&fi->inmem_lock))
-		return -EAGAIN;
+	if (atomic_written) {
+		if (mode != MIGRATE_SYNC)
+			return -EBUSY;
+		if (!mutex_trylock(&fi->inmem_lock))
+			return -EAGAIN;
+	}
 
 	/*
 	 * A reference is expected if PagePrivate set when move mapping,
diff --git a/fs/f2fs/debug.c b/fs/f2fs/debug.c
index fbd5184140d0..87f449845f5f 100644
--- a/fs/f2fs/debug.c
+++ b/fs/f2fs/debug.c
@@ -50,8 +50,27 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->ndirty_files = sbi->ndirty_inode[FILE_INODE];
 	si->ndirty_all = sbi->ndirty_inode[DIRTY_META];
 	si->inmem_pages = get_pages(sbi, F2FS_INMEM_PAGES);
+	si->aw_cnt = atomic_read(&sbi->aw_cnt);
+	si->vw_cnt = atomic_read(&sbi->vw_cnt);
+	si->max_aw_cnt = atomic_read(&sbi->max_aw_cnt);
+	si->max_vw_cnt = atomic_read(&sbi->max_vw_cnt);
 	si->nr_wb_cp_data = get_pages(sbi, F2FS_WB_CP_DATA);
 	si->nr_wb_data = get_pages(sbi, F2FS_WB_DATA);
+	if (SM_I(sbi) && SM_I(sbi)->fcc_info) {
+		si->nr_flushed =
+			atomic_read(&SM_I(sbi)->fcc_info->issued_flush);
+		si->nr_flushing =
+			atomic_read(&SM_I(sbi)->fcc_info->issing_flush);
+	}
+	if (SM_I(sbi) && SM_I(sbi)->dcc_info) {
+		si->nr_discarded =
+			atomic_read(&SM_I(sbi)->dcc_info->issued_discard);
+		si->nr_discarding =
+			atomic_read(&SM_I(sbi)->dcc_info->issing_discard);
+		si->nr_discard_cmd =
+			atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt);
+		si->undiscard_blks = SM_I(sbi)->dcc_info->undiscard_blks;
+	}
 	si->total_count = (int)sbi->user_block_count / sbi->blocks_per_seg;
 	si->rsvd_segs = reserved_segments(sbi);
 	si->overp_segs = overprovision_segments(sbi);
@@ -62,6 +81,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->inline_xattr = atomic_read(&sbi->inline_xattr);
 	si->inline_inode = atomic_read(&sbi->inline_inode);
 	si->inline_dir = atomic_read(&sbi->inline_dir);
+	si->append = sbi->im[APPEND_INO].ino_num;
+	si->update = sbi->im[UPDATE_INO].ino_num;
 	si->orphans = sbi->im[ORPHAN_INO].ino_num;
 	si->utilization = utilization(sbi);
 
@@ -76,6 +97,7 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	si->sits = MAIN_SEGS(sbi);
 	si->dirty_sits = SIT_I(sbi)->dirty_sentries;
 	si->free_nids = NM_I(sbi)->nid_cnt[FREE_NID_LIST];
+	si->avail_nids = NM_I(sbi)->available_nids;
 	si->alloc_nids = NM_I(sbi)->nid_cnt[ALLOC_NID_LIST];
 	si->bg_gc = sbi->bg_gc;
 	si->util_free = (int)(free_user_blocks(sbi) >> sbi->log_blocks_per_seg)
@@ -89,8 +111,8 @@ static void update_general_status(struct f2fs_sb_info *sbi)
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_NODE; i++) {
 		struct curseg_info *curseg = CURSEG_I(sbi, i);
 		si->curseg[i] = curseg->segno;
-		si->cursec[i] = curseg->segno / sbi->segs_per_sec;
-		si->curzone[i] = si->cursec[i] / sbi->secs_per_zone;
+		si->cursec[i] = GET_SEC_FROM_SEG(sbi, curseg->segno);
+		si->curzone[i] = GET_ZONE_FROM_SEC(sbi, si->cursec[i]);
 	}
 
 	for (i = 0; i < 2; i++) {
@@ -114,10 +136,10 @@ static void update_sit_info(struct f2fs_sb_info *sbi)
 
 	bimodal = 0;
 	total_vblocks = 0;
-	blks_per_sec = sbi->segs_per_sec * sbi->blocks_per_seg;
+	blks_per_sec = BLKS_PER_SEC(sbi);
 	hblks_per_sec = blks_per_sec / 2;
 	for (segno = 0; segno < MAIN_SEGS(sbi); segno += sbi->segs_per_sec) {
-		vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+		vblocks = get_valid_blocks(sbi, segno, true);
 		dist = abs(vblocks - hblks_per_sec);
 		bimodal += dist * dist;
 
@@ -146,7 +168,11 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	if (si->base_mem)
 		goto get_cache;
 
-	si->base_mem = sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize;
+	/* build stat */
+	si->base_mem = sizeof(struct f2fs_stat_info);
+
+	/* build superblock */
+	si->base_mem += sizeof(struct f2fs_sb_info) + sbi->sb->s_blocksize;
 	si->base_mem += 2 * sizeof(struct f2fs_inode_info);
 	si->base_mem += sizeof(*sbi->ckpt);
 	si->base_mem += sizeof(struct percpu_counter) * NR_COUNT_TYPE;
@@ -183,6 +209,10 @@ static void update_mem_info(struct f2fs_sb_info *sbi)
 	/* build nm */
 	si->base_mem += sizeof(struct f2fs_nm_info);
 	si->base_mem += __bitmap_size(sbi, NAT_BITMAP);
+	si->base_mem += (NM_I(sbi)->nat_bits_blocks << F2FS_BLKSIZE_BITS);
+	si->base_mem += NM_I(sbi)->nat_blocks * NAT_ENTRY_BITMAP_SIZE;
+	si->base_mem += NM_I(sbi)->nat_blocks / 8;
+	si->base_mem += NM_I(sbi)->nat_blocks * sizeof(unsigned short);
 
 get_cache:
 	si->cache_mem = 0;
@@ -192,8 +222,13 @@ get_cache:
 		si->cache_mem += sizeof(struct f2fs_gc_kthread);
 
 	/* build merge flush thread */
-	if (SM_I(sbi)->cmd_control_info)
+	if (SM_I(sbi)->fcc_info)
 		si->cache_mem += sizeof(struct flush_cmd_control);
+	if (SM_I(sbi)->dcc_info) {
+		si->cache_mem += sizeof(struct discard_cmd_control);
+		si->cache_mem += sizeof(struct discard_cmd) *
+			atomic_read(&SM_I(sbi)->dcc_info->discard_cmd_cnt);
+	}
 
 	/* free nids */
 	si->cache_mem += (NM_I(sbi)->nid_cnt[FREE_NID_LIST] +
@@ -254,8 +289,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->inline_inode);
 		seq_printf(s, "  - Inline_dentry Inode: %u\n",
 			   si->inline_dir);
-		seq_printf(s, "  - Orphan Inode: %u\n",
-			   si->orphans);
+		seq_printf(s, "  - Orphan/Append/Update Inode: %u, %u, %u\n",
+			   si->orphans, si->append, si->update);
 		seq_printf(s, "\nMain area: %d segs, %d secs %d zones\n",
 			   si->main_area_segs, si->main_area_sections,
 			   si->main_area_zones);
@@ -314,8 +349,16 @@ static int stat_show(struct seq_file *s, void *v)
 		seq_printf(s, "  - Inner Struct Count: tree: %d(%d), node: %d\n",
 				si->ext_tree, si->zombie_tree, si->ext_node);
 		seq_puts(s, "\nBalancing F2FS Async:\n");
-		seq_printf(s, "  - inmem: %4d, wb_cp_data: %4d, wb_data: %4d\n",
-			   si->inmem_pages, si->nr_wb_cp_data, si->nr_wb_data);
+		seq_printf(s, "  - IO (CP: %4d, Data: %4d, Flush: (%4d %4d), "
+			"Discard: (%4d %4d)) cmd: %4d undiscard:%4u\n",
+			   si->nr_wb_cp_data, si->nr_wb_data,
+			   si->nr_flushing, si->nr_flushed,
+			   si->nr_discarding, si->nr_discarded,
+			   si->nr_discard_cmd, si->undiscard_blks);
+		seq_printf(s, "  - inmem: %4d, atomic IO: %4d (Max. %4d), "
+			"volatile IO: %4d (Max. %4d)\n",
+			   si->inmem_pages, si->aw_cnt, si->max_aw_cnt,
+			   si->vw_cnt, si->max_vw_cnt);
 		seq_printf(s, "  - nodes: %4d in %4d\n",
 			   si->ndirty_node, si->node_pages);
 		seq_printf(s, "  - dents: %4d in dirs:%4d (%4d)\n",
@@ -328,8 +371,8 @@ static int stat_show(struct seq_file *s, void *v)
 			   si->ndirty_imeta);
 		seq_printf(s, "  - NATs: %9d/%9d\n  - SITs: %9d/%9d\n",
 			   si->dirty_nats, si->nats, si->dirty_sits, si->sits);
-		seq_printf(s, "  - free_nids: %9d, alloc_nids: %9d\n",
-			   si->free_nids, si->alloc_nids);
+		seq_printf(s, "  - free_nids: %9d/%9d\n  - alloc_nids: %9d\n",
+			   si->free_nids, si->avail_nids, si->alloc_nids);
 		seq_puts(s, "\nDistribution of User Blocks:");
 		seq_puts(s, " [ valid | invalid | free ]\n");
 		seq_puts(s, "  [");
@@ -414,6 +457,11 @@ int f2fs_build_stats(struct f2fs_sb_info *sbi)
 	atomic_set(&sbi->inline_dir, 0);
 	atomic_set(&sbi->inplace_count, 0);
 
+	atomic_set(&sbi->aw_cnt, 0);
+	atomic_set(&sbi->vw_cnt, 0);
+	atomic_set(&sbi->max_aw_cnt, 0);
+	atomic_set(&sbi->max_vw_cnt, 0);
+
 	mutex_lock(&f2fs_stat_mutex);
 	list_add_tail(&si->stat_list, &f2fs_stat_list);
 	mutex_unlock(&f2fs_stat_mutex);
diff --git a/fs/f2fs/dir.c b/fs/f2fs/dir.c
index 827c5daef4fc..37f9c7f55605 100644
--- a/fs/f2fs/dir.c
+++ b/fs/f2fs/dir.c
@@ -94,7 +94,7 @@ static struct f2fs_dir_entry *find_in_block(struct page *dentry_page,
 
 	dentry_blk = (struct f2fs_dentry_block *)kmap(dentry_page);
 
-	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
+	make_dentry_ptr_block(NULL, &d, dentry_blk);
 	de = find_target_dentry(fname, namehash, max_slots, &d);
 	if (de)
 		*res_page = dentry_page;
@@ -111,8 +111,6 @@ struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
 	struct f2fs_dir_entry *de;
 	unsigned long bit_pos = 0;
 	int max_len = 0;
-	struct fscrypt_str de_name = FSTR_INIT(NULL, 0);
-	struct fscrypt_str *name = &fname->disk_name;
 
 	if (max_slots)
 		*max_slots = 0;
@@ -130,17 +128,9 @@ struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
 			continue;
 		}
 
-		/* encrypted case */
-		de_name.name = d->filename[bit_pos];
-		de_name.len = le16_to_cpu(de->name_len);
-
-		/* show encrypted name */
-		if (fname->hash) {
-			if (de->hash_code == cpu_to_le32(fname->hash))
-				goto found;
-		} else if (de_name.len == name->len &&
-			de->hash_code == namehash &&
-			!memcmp(de_name.name, name->name, name->len))
+		if (de->hash_code == namehash &&
+		    fscrypt_match_name(fname, d->filename[bit_pos],
+				       le16_to_cpu(de->name_len)))
 			goto found;
 
 		if (max_slots && max_len > *max_slots)
@@ -170,12 +160,7 @@ static struct f2fs_dir_entry *find_in_level(struct inode *dir,
 	struct f2fs_dir_entry *de = NULL;
 	bool room = false;
 	int max_slots;
-	f2fs_hash_t namehash;
-
-	if(fname->hash)
-		namehash = cpu_to_le32(fname->hash);
-	else
-		namehash = f2fs_dentry_hash(&name);
+	f2fs_hash_t namehash = f2fs_dentry_hash(&name, fname);
 
 	nbucket = dir_buckets(level, F2FS_I(dir)->i_dir_level);
 	nblock = bucket_blocks(level);
@@ -250,6 +235,9 @@ struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
 			break;
 	}
 out:
+	/* This is to increase the speed of f2fs_create */
+	if (!de)
+		F2FS_I(dir)->task = current;
 	return de;
 }
 
@@ -268,7 +256,10 @@ struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
 
 	err = fscrypt_setup_filename(dir, child, 1, &fname);
 	if (err) {
-		*res_page = ERR_PTR(err);
+		if (err == -ENOENT)
+			*res_page = NULL;
+		else
+			*res_page = ERR_PTR(err);
 		return NULL;
 	}
 
@@ -330,24 +321,6 @@ static void init_dent_inode(const struct qstr *name, struct page *ipage)
 	set_page_dirty(ipage);
 }
 
-int update_dent_inode(struct inode *inode, struct inode *to,
-					const struct qstr *name)
-{
-	struct page *page;
-
-	if (file_enc_name(to))
-		return 0;
-
-	page = get_node_page(F2FS_I_SB(inode), inode->i_ino);
-	if (IS_ERR(page))
-		return PTR_ERR(page);
-
-	init_dent_inode(name, page);
-	f2fs_put_page(page, 1);
-
-	return 0;
-}
-
 void do_make_empty_dir(struct inode *inode, struct inode *parent,
 					struct f2fs_dentry_ptr *d)
 {
@@ -377,7 +350,7 @@ static int make_empty_dir(struct inode *inode,
 
 	dentry_blk = kmap_atomic(dentry_page);
 
-	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
+	make_dentry_ptr_block(NULL, &d, dentry_blk);
 	do_make_empty_dir(inode, parent, &d);
 
 	kunmap_atomic(dentry_blk);
@@ -431,15 +404,19 @@ struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
 		set_cold_node(inode, page);
 	}
 
-	if (new_name)
+	if (new_name) {
 		init_dent_inode(new_name, page);
+		if (f2fs_encrypted_inode(dir))
+			file_set_enc_name(inode);
+	}
 
 	/*
 	 * This file should be checkpointed during fsync.
 	 * We lost i_pino from now on.
 	 */
 	if (is_inode_flag_set(inode, FI_INC_LINK)) {
-		file_lost_pino(inode);
+		if (!S_ISDIR(inode->i_mode))
+			file_lost_pino(inode);
 		/*
 		 * If link the tmpfile to alias through linkat path,
 		 * we should remove this inode from orphan list.
@@ -535,7 +512,7 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
 
 	level = 0;
 	slots = GET_DENTRY_SLOTS(new_name->len);
-	dentry_hash = f2fs_dentry_hash(new_name);
+	dentry_hash = f2fs_dentry_hash(new_name, NULL);
 
 	current_depth = F2FS_I(dir)->i_current_depth;
 	if (F2FS_I(dir)->chash == dentry_hash) {
@@ -545,8 +522,10 @@ int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
 
 start:
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH))
+	if (time_to_inject(F2FS_I_SB(dir), FAULT_DIR_DEPTH)) {
+		f2fs_show_injection_info(FAULT_DIR_DEPTH);
 		return -ENOSPC;
+	}
 #endif
 	if (unlikely(current_depth == MAX_DIR_HASH_DEPTH))
 		return -ENOSPC;
@@ -590,11 +569,9 @@ add_dentry:
 			err = PTR_ERR(page);
 			goto fail;
 		}
-		if (f2fs_encrypted_inode(dir))
-			file_set_enc_name(inode);
 	}
 
-	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 1);
+	make_dentry_ptr_block(NULL, &d, dentry_blk);
 	f2fs_update_dentry(ino, mode, &d, new_name, dentry_hash, bit_pos);
 
 	set_page_dirty(dentry_page);
@@ -643,14 +620,34 @@ int __f2fs_add_link(struct inode *dir, const struct qstr *name,
 				struct inode *inode, nid_t ino, umode_t mode)
 {
 	struct fscrypt_name fname;
+	struct page *page = NULL;
+	struct f2fs_dir_entry *de = NULL;
 	int err;
 
 	err = fscrypt_setup_filename(dir, name, 0, &fname);
 	if (err)
 		return err;
 
-	err = __f2fs_do_add_link(dir, &fname, inode, ino, mode);
-
+	/*
+	 * An immature stakable filesystem shows a race condition between lookup
+	 * and create. If we have same task when doing lookup and create, it's
+	 * definitely fine as expected by VFS normally. Otherwise, let's just
+	 * verify on-disk dentry one more time, which guarantees filesystem
+	 * consistency more.
+	 */
+	if (current != F2FS_I(dir)->task) {
+		de = __f2fs_find_entry(dir, &fname, &page);
+		F2FS_I(dir)->task = NULL;
+	}
+	if (de) {
+		f2fs_dentry_kunmap(dir, page);
+		f2fs_put_page(page, 0);
+		err = -EEXIST;
+	} else if (IS_ERR(page)) {
+		err = PTR_ERR(page);
+	} else {
+		err = __f2fs_do_add_link(dir, &fname, inode, ino, mode);
+	}
 	fscrypt_free_filename(&fname);
 	return err;
 }
@@ -721,7 +718,7 @@ void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
 	dentry_blk = page_address(page);
 	bit_pos = dentry - dentry_blk->dentry;
 	for (i = 0; i < slots; i++)
-		clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
+		__clear_bit_le(bit_pos + i, &dentry_blk->dentry_bitmap);
 
 	/* Let's check and deallocate this dentry page */
 	bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
@@ -882,7 +879,7 @@ static int f2fs_readdir(struct file *file, struct dir_context *ctx)
 
 		dentry_blk = kmap(dentry_page);
 
-		make_dentry_ptr(inode, &d, (void *)dentry_blk, 1);
+		make_dentry_ptr_block(inode, &d, dentry_blk);
 
 		err = f2fs_fill_dentries(ctx, &d,
 				n * NR_DENTRY_IN_BLOCK, &fstr);
diff --git a/fs/f2fs/extent_cache.c b/fs/f2fs/extent_cache.c
index 4db44da7ef69..ff2352a0ed15 100644
--- a/fs/f2fs/extent_cache.c
+++ b/fs/f2fs/extent_cache.c
@@ -18,6 +18,179 @@
 #include "node.h"
 #include <trace/events/f2fs.h>
 
+static struct rb_entry *__lookup_rb_tree_fast(struct rb_entry *cached_re,
+							unsigned int ofs)
+{
+	if (cached_re) {
+		if (cached_re->ofs <= ofs &&
+				cached_re->ofs + cached_re->len > ofs) {
+			return cached_re;
+		}
+	}
+	return NULL;
+}
+
+static struct rb_entry *__lookup_rb_tree_slow(struct rb_root *root,
+							unsigned int ofs)
+{
+	struct rb_node *node = root->rb_node;
+	struct rb_entry *re;
+
+	while (node) {
+		re = rb_entry(node, struct rb_entry, rb_node);
+
+		if (ofs < re->ofs)
+			node = node->rb_left;
+		else if (ofs >= re->ofs + re->len)
+			node = node->rb_right;
+		else
+			return re;
+	}
+	return NULL;
+}
+
+struct rb_entry *__lookup_rb_tree(struct rb_root *root,
+				struct rb_entry *cached_re, unsigned int ofs)
+{
+	struct rb_entry *re;
+
+	re = __lookup_rb_tree_fast(cached_re, ofs);
+	if (!re)
+		return __lookup_rb_tree_slow(root, ofs);
+
+	return re;
+}
+
+struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
+				struct rb_root *root, struct rb_node **parent,
+				unsigned int ofs)
+{
+	struct rb_node **p = &root->rb_node;
+	struct rb_entry *re;
+
+	while (*p) {
+		*parent = *p;
+		re = rb_entry(*parent, struct rb_entry, rb_node);
+
+		if (ofs < re->ofs)
+			p = &(*p)->rb_left;
+		else if (ofs >= re->ofs + re->len)
+			p = &(*p)->rb_right;
+		else
+			f2fs_bug_on(sbi, 1);
+	}
+
+	return p;
+}
+
+/*
+ * lookup rb entry in position of @ofs in rb-tree,
+ * if hit, return the entry, otherwise, return NULL
+ * @prev_ex: extent before ofs
+ * @next_ex: extent after ofs
+ * @insert_p: insert point for new extent at ofs
+ * in order to simpfy the insertion after.
+ * tree must stay unchanged between lookup and insertion.
+ */
+struct rb_entry *__lookup_rb_tree_ret(struct rb_root *root,
+				struct rb_entry *cached_re,
+				unsigned int ofs,
+				struct rb_entry **prev_entry,
+				struct rb_entry **next_entry,
+				struct rb_node ***insert_p,
+				struct rb_node **insert_parent,
+				bool force)
+{
+	struct rb_node **pnode = &root->rb_node;
+	struct rb_node *parent = NULL, *tmp_node;
+	struct rb_entry *re = cached_re;
+
+	*insert_p = NULL;
+	*insert_parent = NULL;
+	*prev_entry = NULL;
+	*next_entry = NULL;
+
+	if (RB_EMPTY_ROOT(root))
+		return NULL;
+
+	if (re) {
+		if (re->ofs <= ofs && re->ofs + re->len > ofs)
+			goto lookup_neighbors;
+	}
+
+	while (*pnode) {
+		parent = *pnode;
+		re = rb_entry(*pnode, struct rb_entry, rb_node);
+
+		if (ofs < re->ofs)
+			pnode = &(*pnode)->rb_left;
+		else if (ofs >= re->ofs + re->len)
+			pnode = &(*pnode)->rb_right;
+		else
+			goto lookup_neighbors;
+	}
+
+	*insert_p = pnode;
+	*insert_parent = parent;
+
+	re = rb_entry(parent, struct rb_entry, rb_node);
+	tmp_node = parent;
+	if (parent && ofs > re->ofs)
+		tmp_node = rb_next(parent);
+	*next_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+
+	tmp_node = parent;
+	if (parent && ofs < re->ofs)
+		tmp_node = rb_prev(parent);
+	*prev_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+	return NULL;
+
+lookup_neighbors:
+	if (ofs == re->ofs || force) {
+		/* lookup prev node for merging backward later */
+		tmp_node = rb_prev(&re->rb_node);
+		*prev_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+	}
+	if (ofs == re->ofs + re->len - 1 || force) {
+		/* lookup next node for merging frontward later */
+		tmp_node = rb_next(&re->rb_node);
+		*next_entry = rb_entry_safe(tmp_node, struct rb_entry, rb_node);
+	}
+	return re;
+}
+
+bool __check_rb_tree_consistence(struct f2fs_sb_info *sbi,
+						struct rb_root *root)
+{
+#ifdef CONFIG_F2FS_CHECK_FS
+	struct rb_node *cur = rb_first(root), *next;
+	struct rb_entry *cur_re, *next_re;
+
+	if (!cur)
+		return true;
+
+	while (cur) {
+		next = rb_next(cur);
+		if (!next)
+			return true;
+
+		cur_re = rb_entry(cur, struct rb_entry, rb_node);
+		next_re = rb_entry(next, struct rb_entry, rb_node);
+
+		if (cur_re->ofs + cur_re->len > next_re->ofs) {
+			f2fs_msg(sbi->sb, KERN_INFO, "inconsistent rbtree, "
+				"cur(%u, %u) next(%u, %u)",
+				cur_re->ofs, cur_re->len,
+				next_re->ofs, next_re->len);
+			return false;
+		}
+
+		cur = next;
+	}
+#endif
+	return true;
+}
+
 static struct kmem_cache *extent_tree_slab;
 static struct kmem_cache *extent_node_slab;
 
@@ -77,7 +250,7 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode)
 	struct extent_tree *et;
 	nid_t ino = inode->i_ino;
 
-	down_write(&sbi->extent_tree_lock);
+	mutex_lock(&sbi->extent_tree_lock);
 	et = radix_tree_lookup(&sbi->extent_tree_root, ino);
 	if (!et) {
 		et = f2fs_kmem_cache_alloc(extent_tree_slab, GFP_NOFS);
@@ -94,7 +267,7 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode)
 		atomic_dec(&sbi->total_zombie_tree);
 		list_del_init(&et->list);
 	}
-	up_write(&sbi->extent_tree_lock);
+	mutex_unlock(&sbi->extent_tree_lock);
 
 	/* never died until evict_inode */
 	F2FS_I(inode)->extent_tree = et;
@@ -102,36 +275,6 @@ static struct extent_tree *__grab_extent_tree(struct inode *inode)
 	return et;
 }
 
-static struct extent_node *__lookup_extent_tree(struct f2fs_sb_info *sbi,
-				struct extent_tree *et, unsigned int fofs)
-{
-	struct rb_node *node = et->root.rb_node;
-	struct extent_node *en = et->cached_en;
-
-	if (en) {
-		struct extent_info *cei = &en->ei;
-
-		if (cei->fofs <= fofs && cei->fofs + cei->len > fofs) {
-			stat_inc_cached_node_hit(sbi);
-			return en;
-		}
-	}
-
-	while (node) {
-		en = rb_entry(node, struct extent_node, rb_node);
-
-		if (fofs < en->ei.fofs) {
-			node = node->rb_left;
-		} else if (fofs >= en->ei.fofs + en->ei.len) {
-			node = node->rb_right;
-		} else {
-			stat_inc_rbtree_node_hit(sbi);
-			return en;
-		}
-	}
-	return NULL;
-}
-
 static struct extent_node *__init_extent_tree(struct f2fs_sb_info *sbi,
 				struct extent_tree *et, struct extent_info *ei)
 {
@@ -177,7 +320,7 @@ static void __drop_largest_extent(struct inode *inode,
 }
 
 /* return true, if inode page is changed */
-bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+static bool __f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct extent_tree *et;
@@ -215,6 +358,16 @@ out:
 	return false;
 }
 
+bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext)
+{
+	bool ret =  __f2fs_init_extent_tree(inode, i_ext);
+
+	if (!F2FS_I(inode)->extent_tree)
+		set_inode_flag(inode, FI_NO_EXTENT);
+
+	return ret;
+}
+
 static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 							struct extent_info *ei)
 {
@@ -237,17 +390,24 @@ static bool f2fs_lookup_extent_tree(struct inode *inode, pgoff_t pgofs,
 		goto out;
 	}
 
-	en = __lookup_extent_tree(sbi, et, pgofs);
-	if (en) {
-		*ei = en->ei;
-		spin_lock(&sbi->extent_lock);
-		if (!list_empty(&en->list)) {
-			list_move_tail(&en->list, &sbi->extent_list);
-			et->cached_en = en;
-		}
-		spin_unlock(&sbi->extent_lock);
-		ret = true;
+	en = (struct extent_node *)__lookup_rb_tree(&et->root,
+				(struct rb_entry *)et->cached_en, pgofs);
+	if (!en)
+		goto out;
+
+	if (en == et->cached_en)
+		stat_inc_cached_node_hit(sbi);
+	else
+		stat_inc_rbtree_node_hit(sbi);
+
+	*ei = en->ei;
+	spin_lock(&sbi->extent_lock);
+	if (!list_empty(&en->list)) {
+		list_move_tail(&en->list, &sbi->extent_list);
+		et->cached_en = en;
 	}
+	spin_unlock(&sbi->extent_lock);
+	ret = true;
 out:
 	stat_inc_total_hit(sbi);
 	read_unlock(&et->lock);
@@ -256,87 +416,6 @@ out:
 	return ret;
 }
 
-
-/*
- * lookup extent at @fofs, if hit, return the extent
- * if not, return NULL and
- * @prev_ex: extent before fofs
- * @next_ex: extent after fofs
- * @insert_p: insert point for new extent at fofs
- * in order to simpfy the insertion after.
- * tree must stay unchanged between lookup and insertion.
- */
-static struct extent_node *__lookup_extent_tree_ret(struct extent_tree *et,
-				unsigned int fofs,
-				struct extent_node **prev_ex,
-				struct extent_node **next_ex,
-				struct rb_node ***insert_p,
-				struct rb_node **insert_parent)
-{
-	struct rb_node **pnode = &et->root.rb_node;
-	struct rb_node *parent = NULL, *tmp_node;
-	struct extent_node *en = et->cached_en;
-
-	*insert_p = NULL;
-	*insert_parent = NULL;
-	*prev_ex = NULL;
-	*next_ex = NULL;
-
-	if (RB_EMPTY_ROOT(&et->root))
-		return NULL;
-
-	if (en) {
-		struct extent_info *cei = &en->ei;
-
-		if (cei->fofs <= fofs && cei->fofs + cei->len > fofs)
-			goto lookup_neighbors;
-	}
-
-	while (*pnode) {
-		parent = *pnode;
-		en = rb_entry(*pnode, struct extent_node, rb_node);
-
-		if (fofs < en->ei.fofs)
-			pnode = &(*pnode)->rb_left;
-		else if (fofs >= en->ei.fofs + en->ei.len)
-			pnode = &(*pnode)->rb_right;
-		else
-			goto lookup_neighbors;
-	}
-
-	*insert_p = pnode;
-	*insert_parent = parent;
-
-	en = rb_entry(parent, struct extent_node, rb_node);
-	tmp_node = parent;
-	if (parent && fofs > en->ei.fofs)
-		tmp_node = rb_next(parent);
-	*next_ex = tmp_node ?
-		rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
-
-	tmp_node = parent;
-	if (parent && fofs < en->ei.fofs)
-		tmp_node = rb_prev(parent);
-	*prev_ex = tmp_node ?
-		rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
-	return NULL;
-
-lookup_neighbors:
-	if (fofs == en->ei.fofs) {
-		/* lookup prev node for merging backward later */
-		tmp_node = rb_prev(&en->rb_node);
-		*prev_ex = tmp_node ?
-			rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
-	}
-	if (fofs == en->ei.fofs + en->ei.len - 1) {
-		/* lookup next node for merging frontward later */
-		tmp_node = rb_next(&en->rb_node);
-		*next_ex = tmp_node ?
-			rb_entry(tmp_node, struct extent_node, rb_node) : NULL;
-	}
-	return en;
-}
-
 static struct extent_node *__try_merge_extent_node(struct inode *inode,
 				struct extent_tree *et, struct extent_info *ei,
 				struct extent_node *prev_ex,
@@ -352,11 +431,12 @@ static struct extent_node *__try_merge_extent_node(struct inode *inode,
 	}
 
 	if (next_ex && __is_front_mergeable(ei, &next_ex->ei)) {
-		if (en)
-			__release_extent_node(sbi, et, prev_ex);
 		next_ex->ei.fofs = ei->fofs;
 		next_ex->ei.blk = ei->blk;
 		next_ex->ei.len += ei->len;
+		if (en)
+			__release_extent_node(sbi, et, prev_ex);
+
 		en = next_ex;
 	}
 
@@ -390,17 +470,7 @@ static struct extent_node *__insert_extent_tree(struct inode *inode,
 		goto do_insert;
 	}
 
-	while (*p) {
-		parent = *p;
-		en = rb_entry(parent, struct extent_node, rb_node);
-
-		if (ei->fofs < en->ei.fofs)
-			p = &(*p)->rb_left;
-		else if (ei->fofs >= en->ei.fofs + en->ei.len)
-			p = &(*p)->rb_right;
-		else
-			f2fs_bug_on(sbi, 1);
-	}
+	p = __lookup_rb_tree_for_insert(sbi, &et->root, &parent, ei->fofs);
 do_insert:
 	en = __attach_extent_node(sbi, et, ei, parent, p);
 	if (!en)
@@ -416,7 +486,7 @@ do_insert:
 	return en;
 }
 
-static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
+static void f2fs_update_extent_tree_range(struct inode *inode,
 				pgoff_t fofs, block_t blkaddr, unsigned int len)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
@@ -429,7 +499,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 	unsigned int pos = (unsigned int)fofs;
 
 	if (!et)
-		return false;
+		return;
 
 	trace_f2fs_update_extent_tree_range(inode, fofs, blkaddr, len);
 
@@ -437,7 +507,7 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 
 	if (is_inode_flag_set(inode, FI_NO_EXTENT)) {
 		write_unlock(&et->lock);
-		return false;
+		return;
 	}
 
 	prev = et->largest;
@@ -450,8 +520,11 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 	__drop_largest_extent(inode, fofs, len);
 
 	/* 1. lookup first extent node in range [fofs, fofs + len - 1] */
-	en = __lookup_extent_tree_ret(et, fofs, &prev_en, &next_en,
-					&insert_p, &insert_parent);
+	en = (struct extent_node *)__lookup_rb_tree_ret(&et->root,
+					(struct rb_entry *)et->cached_en, fofs,
+					(struct rb_entry **)&prev_en,
+					(struct rb_entry **)&next_en,
+					&insert_p, &insert_parent, false);
 	if (!en)
 		en = next_en;
 
@@ -492,9 +565,8 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 		if (!next_en) {
 			struct rb_node *node = rb_next(&en->rb_node);
 
-			next_en = node ?
-				rb_entry(node, struct extent_node, rb_node)
-				: NULL;
+			next_en = rb_entry_safe(node, struct extent_node,
+						rb_node);
 		}
 
 		if (parts)
@@ -535,8 +607,6 @@ static unsigned int f2fs_update_extent_tree_range(struct inode *inode,
 		__free_extent_tree(sbi, et);
 
 	write_unlock(&et->lock);
-
-	return !__is_extent_same(&prev, &et->largest);
 }
 
 unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
@@ -552,7 +622,7 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 	if (!atomic_read(&sbi->total_zombie_tree))
 		goto free_node;
 
-	if (!down_write_trylock(&sbi->extent_tree_lock))
+	if (!mutex_trylock(&sbi->extent_tree_lock))
 		goto out;
 
 	/* 1. remove unreferenced extent tree */
@@ -574,11 +644,11 @@ unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink)
 			goto unlock_out;
 		cond_resched();
 	}
-	up_write(&sbi->extent_tree_lock);
+	mutex_unlock(&sbi->extent_tree_lock);
 
 free_node:
 	/* 2. remove LRU extent entries */
-	if (!down_write_trylock(&sbi->extent_tree_lock))
+	if (!mutex_trylock(&sbi->extent_tree_lock))
 		goto out;
 
 	remained = nr_shrink - (node_cnt + tree_cnt);
@@ -608,7 +678,7 @@ free_node:
 	spin_unlock(&sbi->extent_lock);
 
 unlock_out:
-	up_write(&sbi->extent_tree_lock);
+	mutex_unlock(&sbi->extent_tree_lock);
 out:
 	trace_f2fs_shrink_extent_tree(sbi, node_cnt, tree_cnt);
 
@@ -655,10 +725,10 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 
 	if (inode->i_nlink && !is_bad_inode(inode) &&
 					atomic_read(&et->node_cnt)) {
-		down_write(&sbi->extent_tree_lock);
+		mutex_lock(&sbi->extent_tree_lock);
 		list_add_tail(&et->list, &sbi->zombie_list);
 		atomic_inc(&sbi->total_zombie_tree);
-		up_write(&sbi->extent_tree_lock);
+		mutex_unlock(&sbi->extent_tree_lock);
 		return;
 	}
 
@@ -666,12 +736,12 @@ void f2fs_destroy_extent_tree(struct inode *inode)
 	node_cnt = f2fs_destroy_extent_node(inode);
 
 	/* delete extent tree entry in radix tree */
-	down_write(&sbi->extent_tree_lock);
+	mutex_lock(&sbi->extent_tree_lock);
 	f2fs_bug_on(sbi, atomic_read(&et->node_cnt));
 	radix_tree_delete(&sbi->extent_tree_root, inode->i_ino);
 	kmem_cache_free(extent_tree_slab, et);
 	atomic_dec(&sbi->total_ext_tree);
-	up_write(&sbi->extent_tree_lock);
+	mutex_unlock(&sbi->extent_tree_lock);
 
 	F2FS_I(inode)->extent_tree = NULL;
 
@@ -718,7 +788,7 @@ void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
 void init_extent_cache_info(struct f2fs_sb_info *sbi)
 {
 	INIT_RADIX_TREE(&sbi->extent_tree_root, GFP_NOIO);
-	init_rwsem(&sbi->extent_tree_lock);
+	mutex_init(&sbi->extent_tree_lock);
 	INIT_LIST_HEAD(&sbi->extent_list);
 	spin_lock_init(&sbi->extent_lock);
 	atomic_set(&sbi->total_ext_tree, 0);
diff --git a/fs/f2fs/f2fs.h b/fs/f2fs/f2fs.h
index 2da8c3aa0ce5..94a88b233e98 100644
--- a/fs/f2fs/f2fs.h
+++ b/fs/f2fs/f2fs.h
@@ -22,7 +22,12 @@
 #include <linux/vmalloc.h>
 #include <linux/bio.h>
 #include <linux/blkdev.h>
-#include <linux/fscrypto.h>
+#include <linux/quotaops.h>
+#ifdef CONFIG_F2FS_FS_ENCRYPTION
+#include <linux/fscrypt_supp.h>
+#else
+#include <linux/fscrypt_notsupp.h>
+#endif
 #include <crypto/hash.h>
 
 #ifdef CONFIG_F2FS_CHECK_FS
@@ -46,6 +51,7 @@ enum {
 	FAULT_BLOCK,
 	FAULT_DIR_DEPTH,
 	FAULT_EVICT_INODE,
+	FAULT_TRUNCATE,
 	FAULT_IO,
 	FAULT_CHECKPOINT,
 	FAULT_MAX,
@@ -58,7 +64,7 @@ struct f2fs_fault_info {
 };
 
 extern char *fault_name[FAULT_MAX];
-#define IS_FAULT_SET(fi, type) (fi->inject_type & (1 << (type)))
+#define IS_FAULT_SET(fi, type) ((fi)->inject_type & (1 << (type)))
 #endif
 
 /*
@@ -83,10 +89,12 @@ extern char *fault_name[FAULT_MAX];
 #define F2FS_MOUNT_FAULT_INJECTION	0x00010000
 #define F2FS_MOUNT_ADAPTIVE		0x00020000
 #define F2FS_MOUNT_LFS			0x00040000
+#define F2FS_MOUNT_USRQUOTA		0x00080000
+#define F2FS_MOUNT_GRPQUOTA		0x00100000
 
-#define clear_opt(sbi, option)	(sbi->mount_opt.opt &= ~F2FS_MOUNT_##option)
-#define set_opt(sbi, option)	(sbi->mount_opt.opt |= F2FS_MOUNT_##option)
-#define test_opt(sbi, option)	(sbi->mount_opt.opt & F2FS_MOUNT_##option)
+#define clear_opt(sbi, option)	((sbi)->mount_opt.opt &= ~F2FS_MOUNT_##option)
+#define set_opt(sbi, option)	((sbi)->mount_opt.opt |= F2FS_MOUNT_##option)
+#define test_opt(sbi, option)	((sbi)->mount_opt.opt & F2FS_MOUNT_##option)
 
 #define ver_after(a, b)	(typecheck(unsigned long long, a) &&		\
 		typecheck(unsigned long long, b) &&			\
@@ -108,9 +116,9 @@ struct f2fs_mount_info {
 #define F2FS_HAS_FEATURE(sb, mask)					\
 	((F2FS_SB(sb)->raw_super->feature & cpu_to_le32(mask)) != 0)
 #define F2FS_SET_FEATURE(sb, mask)					\
-	F2FS_SB(sb)->raw_super->feature |= cpu_to_le32(mask)
+	(F2FS_SB(sb)->raw_super->feature |= cpu_to_le32(mask))
 #define F2FS_CLEAR_FEATURE(sb, mask)					\
-	F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask)
+	(F2FS_SB(sb)->raw_super->feature &= ~cpu_to_le32(mask))
 
 /*
  * For checkpoint manager
@@ -120,19 +128,20 @@ enum {
 	SIT_BITMAP
 };
 
-enum {
-	CP_UMOUNT,
-	CP_FASTBOOT,
-	CP_SYNC,
-	CP_RECOVERY,
-	CP_DISCARD,
-};
+#define	CP_UMOUNT	0x00000001
+#define	CP_FASTBOOT	0x00000002
+#define	CP_SYNC		0x00000004
+#define	CP_RECOVERY	0x00000008
+#define	CP_DISCARD	0x00000010
+#define CP_TRIMMED	0x00000020
 
-#define DEF_BATCHED_TRIM_SECTIONS	2
+#define DEF_BATCHED_TRIM_SECTIONS	2048
 #define BATCHED_TRIM_SEGMENTS(sbi)	\
-		(SM_I(sbi)->trim_sections * (sbi)->segs_per_sec)
+		(GET_SEG_FROM_SEC(sbi, SM_I(sbi)->trim_sections))
 #define BATCHED_TRIM_BLOCKS(sbi)	\
 		(BATCHED_TRIM_SEGMENTS(sbi) << (sbi)->log_blocks_per_seg)
+#define MAX_DISCARD_BLOCKS(sbi)		BLKS_PER_SEC(sbi)
+#define DISCARD_ISSUE_RATE		8
 #define DEF_CP_INTERVAL			60	/* 60 secs */
 #define DEF_IDLE_INTERVAL		5	/* 5 secs */
 
@@ -174,18 +183,63 @@ struct inode_entry {
 	struct inode *inode;	/* vfs inode pointer */
 };
 
-/* for the list of blockaddresses to be discarded */
+/* for the bitmap indicate blocks to be discarded */
 struct discard_entry {
 	struct list_head list;	/* list head */
-	block_t blkaddr;	/* block address to be discarded */
-	int len;		/* # of consecutive blocks of the discard */
+	block_t start_blkaddr;	/* start blockaddr of current segment */
+	unsigned char discard_map[SIT_VBLOCK_MAP_SIZE];	/* segment discard bitmap */
 };
 
-struct bio_entry {
-	struct list_head list;
-	struct bio *bio;
-	struct completion event;
-	int error;
+/* max discard pend list number */
+#define MAX_PLIST_NUM		512
+#define plist_idx(blk_num)	((blk_num) >= MAX_PLIST_NUM ?		\
+					(MAX_PLIST_NUM - 1) : (blk_num - 1))
+
+enum {
+	D_PREP,
+	D_SUBMIT,
+	D_DONE,
+};
+
+struct discard_info {
+	block_t lstart;			/* logical start address */
+	block_t len;			/* length */
+	block_t start;			/* actual start address in dev */
+};
+
+struct discard_cmd {
+	struct rb_node rb_node;		/* rb node located in rb-tree */
+	union {
+		struct {
+			block_t lstart;	/* logical start address */
+			block_t len;	/* length */
+			block_t start;	/* actual start address in dev */
+		};
+		struct discard_info di;	/* discard info */
+
+	};
+	struct list_head list;		/* command list */
+	struct completion wait;		/* compleation */
+	struct block_device *bdev;	/* bdev */
+	unsigned short ref;		/* reference count */
+	unsigned char state;		/* state */
+	int error;			/* bio error */
+};
+
+struct discard_cmd_control {
+	struct task_struct *f2fs_issue_discard;	/* discard thread */
+	struct list_head entry_list;		/* 4KB discard entry list */
+	struct list_head pend_list[MAX_PLIST_NUM];/* store pending entries */
+	struct list_head wait_list;		/* store on-flushing entries */
+	wait_queue_head_t discard_wait_queue;	/* waiting queue for wake-up */
+	struct mutex cmd_lock;
+	unsigned int nr_discards;		/* # of discards in the list */
+	unsigned int max_discards;		/* max. discards to be issued */
+	unsigned int undiscard_blks;		/* # of undiscard blocks */
+	atomic_t issued_discard;		/* # of issued discard */
+	atomic_t issing_discard;		/* # of issing discard */
+	atomic_t discard_cmd_cnt;		/* # of cached cmd count */
+	struct rb_root root;			/* root of discard rb-tree */
 };
 
 /* for the list of fsync inodes, used only during recovery */
@@ -196,13 +250,13 @@ struct fsync_inode_entry {
 	block_t last_dentry;	/* block address locating the last dentry */
 };
 
-#define nats_in_cursum(jnl)		(le16_to_cpu(jnl->n_nats))
-#define sits_in_cursum(jnl)		(le16_to_cpu(jnl->n_sits))
+#define nats_in_cursum(jnl)		(le16_to_cpu((jnl)->n_nats))
+#define sits_in_cursum(jnl)		(le16_to_cpu((jnl)->n_sits))
 
-#define nat_in_journal(jnl, i)		(jnl->nat_j.entries[i].ne)
-#define nid_in_journal(jnl, i)		(jnl->nat_j.entries[i].nid)
-#define sit_in_journal(jnl, i)		(jnl->sit_j.entries[i].se)
-#define segno_in_journal(jnl, i)	(jnl->sit_j.entries[i].segno)
+#define nat_in_journal(jnl, i)		((jnl)->nat_j.entries[i].ne)
+#define nid_in_journal(jnl, i)		((jnl)->nat_j.entries[i].nid)
+#define sit_in_journal(jnl, i)		((jnl)->sit_j.entries[i].se)
+#define segno_in_journal(jnl, i)	((jnl)->sit_j.entries[i].segno)
 
 #define MAX_NAT_JENTRIES(jnl)	(NAT_JOURNAL_ENTRIES - nats_in_cursum(jnl))
 #define MAX_SIT_JENTRIES(jnl)	(SIT_JOURNAL_ENTRIES - sits_in_cursum(jnl))
@@ -210,6 +264,7 @@ struct fsync_inode_entry {
 static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
 {
 	int before = nats_in_cursum(journal);
+
 	journal->n_nats = cpu_to_le16(before + i);
 	return before;
 }
@@ -217,6 +272,7 @@ static inline int update_nats_in_cursum(struct f2fs_journal *journal, int i)
 static inline int update_sits_in_cursum(struct f2fs_journal *journal, int i)
 {
 	int before = sits_in_cursum(journal);
+
 	journal->n_sits = cpu_to_le16(before + i);
 	return before;
 }
@@ -242,11 +298,16 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
 #define F2FS_IOC_START_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 3)
 #define F2FS_IOC_RELEASE_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 4)
 #define F2FS_IOC_ABORT_VOLATILE_WRITE	_IO(F2FS_IOCTL_MAGIC, 5)
-#define F2FS_IOC_GARBAGE_COLLECT	_IO(F2FS_IOCTL_MAGIC, 6)
+#define F2FS_IOC_GARBAGE_COLLECT	_IOW(F2FS_IOCTL_MAGIC, 6, __u32)
 #define F2FS_IOC_WRITE_CHECKPOINT	_IO(F2FS_IOCTL_MAGIC, 7)
-#define F2FS_IOC_DEFRAGMENT		_IO(F2FS_IOCTL_MAGIC, 8)
+#define F2FS_IOC_DEFRAGMENT		_IOWR(F2FS_IOCTL_MAGIC, 8,	\
+						struct f2fs_defragment)
 #define F2FS_IOC_MOVE_RANGE		_IOWR(F2FS_IOCTL_MAGIC, 9,	\
 						struct f2fs_move_range)
+#define F2FS_IOC_FLUSH_DEVICE		_IOW(F2FS_IOCTL_MAGIC, 10,	\
+						struct f2fs_flush_device)
+#define F2FS_IOC_GARBAGE_COLLECT_RANGE	_IOW(F2FS_IOCTL_MAGIC, 11,	\
+						struct f2fs_gc_range)
 
 #define F2FS_IOC_SET_ENCRYPTION_POLICY	FS_IOC_SET_ENCRYPTION_POLICY
 #define F2FS_IOC_GET_ENCRYPTION_POLICY	FS_IOC_GET_ENCRYPTION_POLICY
@@ -271,6 +332,12 @@ static inline bool __has_cursum_space(struct f2fs_journal *journal,
 #define F2FS_IOC32_GETVERSION		FS_IOC32_GETVERSION
 #endif
 
+struct f2fs_gc_range {
+	u32 sync;
+	u64 start;
+	u64 len;
+};
+
 struct f2fs_defragment {
 	u64 start;
 	u64 len;
@@ -283,6 +350,11 @@ struct f2fs_move_range {
 	u64 len;		/* size to move */
 };
 
+struct f2fs_flush_device {
+	u32 dev_num;		/* device number to flush */
+	u32 segments;		/* # of segments to flush */
+};
+
 /*
  * For INODE and NODE manager
  */
@@ -295,24 +367,24 @@ struct f2fs_dentry_ptr {
 	int max;
 };
 
-static inline void make_dentry_ptr(struct inode *inode,
-		struct f2fs_dentry_ptr *d, void *src, int type)
+static inline void make_dentry_ptr_block(struct inode *inode,
+		struct f2fs_dentry_ptr *d, struct f2fs_dentry_block *t)
 {
 	d->inode = inode;
+	d->max = NR_DENTRY_IN_BLOCK;
+	d->bitmap = &t->dentry_bitmap;
+	d->dentry = t->dentry;
+	d->filename = t->filename;
+}
 
-	if (type == 1) {
-		struct f2fs_dentry_block *t = (struct f2fs_dentry_block *)src;
-		d->max = NR_DENTRY_IN_BLOCK;
-		d->bitmap = &t->dentry_bitmap;
-		d->dentry = t->dentry;
-		d->filename = t->filename;
-	} else {
-		struct f2fs_inline_dentry *t = (struct f2fs_inline_dentry *)src;
-		d->max = NR_INLINE_DENTRY;
-		d->bitmap = &t->dentry_bitmap;
-		d->dentry = t->dentry;
-		d->filename = t->filename;
-	}
+static inline void make_dentry_ptr_inline(struct inode *inode,
+		struct f2fs_dentry_ptr *d, struct f2fs_inline_dentry *t)
+{
+	d->inode = inode;
+	d->max = NR_INLINE_DENTRY;
+	d->bitmap = &t->dentry_bitmap;
+	d->dentry = t->dentry;
+	d->filename = t->filename;
 }
 
 /*
@@ -344,16 +416,30 @@ enum {
 /* number of extent info in extent cache we try to shrink */
 #define EXTENT_CACHE_SHRINK_NUMBER	128
 
+struct rb_entry {
+	struct rb_node rb_node;		/* rb node located in rb-tree */
+	unsigned int ofs;		/* start offset of the entry */
+	unsigned int len;		/* length of the entry */
+};
+
 struct extent_info {
 	unsigned int fofs;		/* start offset in a file */
-	u32 blk;			/* start block address of the extent */
 	unsigned int len;		/* length of the extent */
+	u32 blk;			/* start block address of the extent */
 };
 
 struct extent_node {
-	struct rb_node rb_node;		/* rb node located in rb-tree */
+	struct rb_node rb_node;
+	union {
+		struct {
+			unsigned int fofs;
+			unsigned int len;
+			u32 blk;
+		};
+		struct extent_info ei;	/* extent info */
+
+	};
 	struct list_head list;		/* node in global extent list of sbi */
-	struct extent_info ei;		/* extent info */
 	struct extent_tree *et;		/* extent tree pointer */
 };
 
@@ -434,16 +520,23 @@ struct f2fs_inode_info {
 	atomic_t dirty_pages;		/* # of dirty pages */
 	f2fs_hash_t chash;		/* hash value of given file name */
 	unsigned int clevel;		/* maximum level of given file name */
+	struct task_struct *task;	/* lookup and create consistency */
 	nid_t i_xattr_nid;		/* node id that contains xattrs */
-	unsigned long long xattr_ver;	/* cp version of xattr modification */
 	loff_t	last_disk_size;		/* lastly written file size */
 
+#ifdef CONFIG_QUOTA
+	struct dquot *i_dquot[MAXQUOTAS];
+
+	/* quota space reservation, managed internally by quota code */
+	qsize_t i_reserved_quota;
+#endif
 	struct list_head dirty_list;	/* dirty list for dirs and files */
 	struct list_head gdirty_list;	/* linked in global dirty list */
 	struct list_head inmem_pages;	/* inmemory pages managed by f2fs */
 	struct mutex inmem_lock;	/* lock for inmemory pages */
 	struct extent_tree *extent_tree;	/* cached extent_tree entry */
 	struct rw_semaphore dio_rwsem[2];/* avoid racing between dio and gc */
+	struct rw_semaphore i_mmap_sem;
 };
 
 static inline void get_extent_info(struct extent_info *ext,
@@ -470,11 +563,22 @@ static inline void set_extent_info(struct extent_info *ei, unsigned int fofs,
 	ei->len = len;
 }
 
-static inline bool __is_extent_same(struct extent_info *ei1,
-						struct extent_info *ei2)
+static inline bool __is_discard_mergeable(struct discard_info *back,
+						struct discard_info *front)
+{
+	return back->lstart + back->len == front->lstart;
+}
+
+static inline bool __is_discard_back_mergeable(struct discard_info *cur,
+						struct discard_info *back)
 {
-	return (ei1->fofs == ei2->fofs && ei1->blk == ei2->blk &&
-						ei1->len == ei2->len);
+	return __is_discard_mergeable(back, cur);
+}
+
+static inline bool __is_discard_front_mergeable(struct discard_info *cur,
+						struct discard_info *front)
+{
+	return __is_discard_mergeable(cur, front);
 }
 
 static inline bool __is_extent_mergeable(struct extent_info *back,
@@ -496,7 +600,7 @@ static inline bool __is_front_mergeable(struct extent_info *cur,
 	return __is_extent_mergeable(cur, front);
 }
 
-extern void f2fs_mark_inode_dirty_sync(struct inode *, bool);
+extern void f2fs_mark_inode_dirty_sync(struct inode *inode, bool sync);
 static inline void __try_update_largest_extent(struct inode *inode,
 			struct extent_tree *et, struct extent_node *en)
 {
@@ -528,6 +632,7 @@ struct f2fs_nm_info {
 	struct list_head nat_entries;	/* cached nat entry list (clean) */
 	unsigned int nat_cnt;		/* the # of cached nat entries */
 	unsigned int dirty_nat_cnt;	/* total num of nat entries in set */
+	unsigned int nat_blocks;	/* # of nat blocks */
 
 	/* free node ids management */
 	struct radix_tree_root free_nid_root;/* root of the free_nid cache */
@@ -535,9 +640,20 @@ struct f2fs_nm_info {
 	unsigned int nid_cnt[MAX_NID_LIST];	/* the number of free node id */
 	spinlock_t nid_list_lock;	/* protect nid lists ops */
 	struct mutex build_lock;	/* lock for build free nids */
+	unsigned char (*free_nid_bitmap)[NAT_ENTRY_BITMAP_SIZE];
+	unsigned char *nat_block_bitmap;
+	unsigned short *free_nid_count;	/* free nid count of NAT block */
 
 	/* for checkpoint */
 	char *nat_bitmap;		/* NAT bitmap pointer */
+
+	unsigned int nat_bits_blocks;	/* # of nat bits blocks */
+	unsigned char *nat_bits;	/* NAT bits blocks */
+	unsigned char *full_nat_bits;	/* full NAT pages */
+	unsigned char *empty_nat_bits;	/* empty NAT pages */
+#ifdef CONFIG_F2FS_CHECK_FS
+	char *nat_bitmap_mir;		/* NAT bitmap mirror */
+#endif
 	int bitmap_size;		/* bitmap size */
 };
 
@@ -605,7 +721,8 @@ struct flush_cmd {
 struct flush_cmd_control {
 	struct task_struct *f2fs_issue_flush;	/* flush thread */
 	wait_queue_head_t flush_wait_queue;	/* waiting queue for wake-up */
-	atomic_t submit_flush;			/* # of issued flushes */
+	atomic_t issued_flush;			/* # of issued flushes */
+	atomic_t issing_flush;			/* # of issing flushes */
 	struct llist_head issue_list;		/* list for command issue */
 	struct llist_node *dispatch_list;	/* list for command dispatch */
 };
@@ -628,12 +745,6 @@ struct f2fs_sm_info {
 	/* a threshold to reclaim prefree segments */
 	unsigned int rec_prefree_segments;
 
-	/* for small discard management */
-	struct list_head discard_list;		/* 4KB discard list */
-	struct list_head wait_list;		/* linked with issued discard bio */
-	int nr_discards;			/* # of discards in the list */
-	int max_discards;			/* max. discards to be issued */
-
 	/* for batched trimming */
 	unsigned int trim_sections;		/* # of sections to trim */
 
@@ -642,10 +753,13 @@ struct f2fs_sm_info {
 	unsigned int ipu_policy;	/* in-place-update policy */
 	unsigned int min_ipu_util;	/* in-place-update threshold */
 	unsigned int min_fsync_blocks;	/* threshold for fsync */
+	unsigned int min_hot_blocks;	/* threshold for hot block allocation */
 
 	/* for flush command control */
-	struct flush_cmd_control *cmd_control_info;
+	struct flush_cmd_control *fcc_info;
 
+	/* for discard command control */
+	struct discard_cmd_control *dcc_info;
 };
 
 /*
@@ -690,29 +804,50 @@ enum page_type {
 	META_FLUSH,
 	INMEM,		/* the below types are used by tracepoints only. */
 	INMEM_DROP,
+	INMEM_INVALIDATE,
 	INMEM_REVOKE,
 	IPU,
 	OPU,
 };
 
+enum temp_type {
+	HOT = 0,	/* must be zero for meta bio */
+	WARM,
+	COLD,
+	NR_TEMP_TYPE,
+};
+
+enum need_lock_type {
+	LOCK_REQ = 0,
+	LOCK_DONE,
+	LOCK_RETRY,
+};
+
 struct f2fs_io_info {
 	struct f2fs_sb_info *sbi;	/* f2fs_sb_info pointer */
 	enum page_type type;	/* contains DATA/NODE/META/META_FLUSH */
+	enum temp_type temp;	/* contains HOT/WARM/COLD */
 	int op;			/* contains REQ_OP_ */
 	int op_flags;		/* req_flag_bits */
 	block_t new_blkaddr;	/* new block address to be written */
 	block_t old_blkaddr;	/* old block address before Cow */
 	struct page *page;	/* page to be written */
 	struct page *encrypted_page;	/* encrypted page */
+	struct list_head list;		/* serialize IOs */
+	bool submitted;		/* indicate IO submission */
+	int need_lock;		/* indicate we need to lock cp_rwsem */
+	bool in_list;		/* indicate fio is in io_list */
 };
 
-#define is_read_io(rw) (rw == READ)
+#define is_read_io(rw) ((rw) == READ)
 struct f2fs_bio_info {
 	struct f2fs_sb_info *sbi;	/* f2fs superblock */
 	struct bio *bio;		/* bios to merge */
 	sector_t last_block_in_bio;	/* last block number */
 	struct f2fs_io_info fio;	/* store buffered io info. */
 	struct rw_semaphore io_rwsem;	/* blocking op for bio */
+	spinlock_t io_lock;		/* serialize DATA/NODE IOs */
+	struct list_head io_list;	/* track fios */
 };
 
 #define FDEV(i)				(sbi->devs[i])
@@ -760,10 +895,6 @@ enum {
 	MAX_TIME,
 };
 
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-#define F2FS_KEY_DESC_PREFIX "f2fs:"
-#define F2FS_KEY_DESC_PREFIX_SIZE 5
-#endif
 struct f2fs_sb_info {
 	struct super_block *sb;			/* pointer to VFS super block */
 	struct proc_dir_entry *s_proc;		/* proc entry */
@@ -771,11 +902,6 @@ struct f2fs_sb_info {
 	int valid_super_block;			/* valid super block no */
 	unsigned long s_flag;				/* flags for sbi */
 
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	u8 key_prefix[F2FS_KEY_DESC_PREFIX_SIZE];
-	u8 key_prefix_size;
-#endif
-
 #ifdef CONFIG_BLK_DEV_ZONED
 	unsigned int blocks_per_blkz;		/* F2FS blocks per zone */
 	unsigned int log_blocks_per_blkz;	/* log2 F2FS blocks per zone */
@@ -789,9 +915,11 @@ struct f2fs_sb_info {
 	struct f2fs_sm_info *sm_info;		/* segment manager */
 
 	/* for bio operations */
-	struct f2fs_bio_info read_io;			/* for read bios */
-	struct f2fs_bio_info write_io[NR_PAGE_TYPE];	/* for write bios */
-	struct mutex wio_mutex[NODE + 1];	/* bio ordering for NODE/DATA */
+	struct f2fs_bio_info *write_io[NR_PAGE_TYPE];	/* for write bios */
+	struct mutex wio_mutex[NR_PAGE_TYPE - 1][NR_TEMP_TYPE];
+						/* bio ordering for NODE/DATA */
+	int write_io_size_bits;			/* Write IO size bits */
+	mempool_t *write_io_dummy;		/* Dummy pages */
 
 	/* for checkpoint */
 	struct f2fs_checkpoint *ckpt;		/* raw checkpoint pointer */
@@ -801,6 +929,7 @@ struct f2fs_sb_info {
 	struct mutex cp_mutex;			/* checkpoint procedure lock */
 	struct rw_semaphore cp_rwsem;		/* blocking FS operations */
 	struct rw_semaphore node_write;		/* locking node writes */
+	struct rw_semaphore node_change;	/* locking node change */
 	wait_queue_head_t cp_wait;
 	unsigned long last_time[MAX_TIME];	/* to store time in jiffies */
 	long interval_time[MAX_TIME];		/* to store thresholds */
@@ -816,7 +945,7 @@ struct f2fs_sb_info {
 
 	/* for extent tree cache */
 	struct radix_tree_root extent_tree_root;/* cache extent cache entries */
-	struct rw_semaphore extent_tree_lock;	/* locking extent radix tree */
+	struct mutex extent_tree_lock;	/* locking extent radix tree */
 	struct list_head extent_list;		/* lru list for shrinker */
 	spinlock_t extent_lock;			/* locking extent lru list */
 	atomic_t total_ext_tree;		/* extent tree count */
@@ -846,6 +975,8 @@ struct f2fs_sb_info {
 	block_t total_valid_block_count;	/* # of valid blocks */
 	block_t discard_blks;			/* discard command candidats */
 	block_t last_valid_block_count;		/* for recovery */
+	block_t reserved_blocks;		/* configurable reserved blocks */
+
 	u32 s_next_generation;			/* for NFS support */
 
 	/* # of pages, see count_type */
@@ -853,6 +984,9 @@ struct f2fs_sb_info {
 	/* # of allocated blocks */
 	struct percpu_counter alloc_valid_block_count;
 
+	/* writeback control */
+	atomic_t wb_sync_req;			/* count # of WB_SYNC threads */
+
 	/* valid inode count */
 	struct percpu_counter total_valid_inode_count;
 
@@ -863,6 +997,9 @@ struct f2fs_sb_info {
 	struct f2fs_gc_kthread	*gc_thread;	/* GC thread */
 	unsigned int cur_victim_sec;		/* current victim section num */
 
+	/* threshold for converting bg victims for fg */
+	u64 fggc_threshold;
+
 	/* maximum # of trials to find a victim segment for SSR and GC */
 	unsigned int max_victim_search;
 
@@ -882,10 +1019,13 @@ struct f2fs_sb_info {
 	atomic_t inline_xattr;			/* # of inline_xattr inodes */
 	atomic_t inline_inode;			/* # of inline_data inodes */
 	atomic_t inline_dir;			/* # of inline_dentry inodes */
+	atomic_t aw_cnt;			/* # of atomic writes */
+	atomic_t vw_cnt;			/* # of volatile writes */
+	atomic_t max_aw_cnt;			/* max # of atomic writes */
+	atomic_t max_vw_cnt;			/* max # of volatile writes */
 	int bg_gc;				/* background gc calls */
 	unsigned int ndirty_inode[NR_INODE_TYPE];	/* # of dirty inodes */
 #endif
-	unsigned int last_victim[2];		/* last victim segment # */
 	spinlock_t stat_lock;			/* lock for stat operations */
 
 	/* For sysfs suppport */
@@ -913,6 +1053,10 @@ struct f2fs_sb_info {
 };
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
+#define f2fs_show_injection_info(type)				\
+	printk("%sF2FS-fs : inject %s in %s of %pF\n",		\
+		KERN_INFO, fault_name[type],			\
+		__func__, __builtin_return_address(0))
 static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
 {
 	struct f2fs_fault_info *ffi = &sbi->fault_info;
@@ -926,10 +1070,6 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
 	atomic_inc(&ffi->inject_ops);
 	if (atomic_read(&ffi->inject_ops) >= ffi->inject_rate) {
 		atomic_set(&ffi->inject_ops, 0);
-		printk("%sF2FS-fs : inject %s in %pF\n",
-				KERN_INFO,
-				fault_name[type],
-				__builtin_return_address(0));
 		return true;
 	}
 	return false;
@@ -940,8 +1080,8 @@ static inline bool time_to_inject(struct f2fs_sb_info *sbi, int type)
  * and the return value is in kbytes. s is of struct f2fs_sb_info.
  */
 #define BD_PART_WRITTEN(s)						 \
-(((u64)part_stat_read(s->sb->s_bdev->bd_part, sectors[1]) -		 \
-		s->sectors_written_start) >> 1)
+(((u64)part_stat_read((s)->sb->s_bdev->bd_part, sectors[1]) -		 \
+		(s)->sectors_written_start) >> 1)
 
 static inline void f2fs_update_time(struct f2fs_sb_info *sbi, int type)
 {
@@ -976,6 +1116,7 @@ static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address,
 {
 	SHASH_DESC_ON_STACK(shash, sbi->s_chksum_driver);
 	u32 *ctx = (u32 *)shash_desc_ctx(shash);
+	u32 retval;
 	int err;
 
 	shash->tfm = sbi->s_chksum_driver;
@@ -985,7 +1126,9 @@ static inline u32 f2fs_crc32(struct f2fs_sb_info *sbi, const void *address,
 	err = crypto_shash_update(shash, address, length);
 	BUG_ON(err);
 
-	return *ctx;
+	retval = *ctx;
+	barrier_data(ctx);
+	return retval;
 }
 
 static inline bool f2fs_crc_valid(struct f2fs_sb_info *sbi, __u32 blk_crc,
@@ -1094,6 +1237,12 @@ static inline unsigned long long cur_cp_version(struct f2fs_checkpoint *cp)
 	return le64_to_cpu(cp->checkpoint_ver);
 }
 
+static inline __u64 cur_cp_crc(struct f2fs_checkpoint *cp)
+{
+	size_t crc_offset = le32_to_cpu(cp->checksum_offset);
+	return le32_to_cpu(*((__le32 *)((unsigned char *)cp + crc_offset)));
+}
+
 static inline bool __is_set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
 {
 	unsigned int ckpt_flags = le32_to_cpu(cp->ckpt_flags);
@@ -1117,9 +1266,11 @@ static inline void __set_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
 
 static inline void set_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
 {
-	spin_lock(&sbi->cp_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->cp_lock, flags);
 	__set_ckpt_flags(F2FS_CKPT(sbi), f);
-	spin_unlock(&sbi->cp_lock);
+	spin_unlock_irqrestore(&sbi->cp_lock, flags);
 }
 
 static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f)
@@ -1133,9 +1284,34 @@ static inline void __clear_ckpt_flags(struct f2fs_checkpoint *cp, unsigned int f
 
 static inline void clear_ckpt_flags(struct f2fs_sb_info *sbi, unsigned int f)
 {
-	spin_lock(&sbi->cp_lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&sbi->cp_lock, flags);
 	__clear_ckpt_flags(F2FS_CKPT(sbi), f);
-	spin_unlock(&sbi->cp_lock);
+	spin_unlock_irqrestore(&sbi->cp_lock, flags);
+}
+
+static inline void disable_nat_bits(struct f2fs_sb_info *sbi, bool lock)
+{
+	unsigned long flags;
+
+	set_sbi_flag(sbi, SBI_NEED_FSCK);
+
+	if (lock)
+		spin_lock_irqsave(&sbi->cp_lock, flags);
+	__clear_ckpt_flags(F2FS_CKPT(sbi), CP_NAT_BITS_FLAG);
+	kfree(NM_I(sbi)->nat_bits);
+	NM_I(sbi)->nat_bits = NULL;
+	if (lock)
+		spin_unlock_irqrestore(&sbi->cp_lock, flags);
+}
+
+static inline bool enabled_nat_bits(struct f2fs_sb_info *sbi,
+					struct cp_control *cpc)
+{
+	bool set = is_set_ckpt_flags(sbi, CP_NAT_BITS_FLAG);
+
+	return (cpc) ? (cpc->reason & CP_UMOUNT) && set : set;
 }
 
 static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
@@ -1143,6 +1319,11 @@ static inline void f2fs_lock_op(struct f2fs_sb_info *sbi)
 	down_read(&sbi->cp_rwsem);
 }
 
+static inline int f2fs_trylock_op(struct f2fs_sb_info *sbi)
+{
+	return down_read_trylock(&sbi->cp_rwsem);
+}
+
 static inline void f2fs_unlock_op(struct f2fs_sb_info *sbi)
 {
 	up_read(&sbi->cp_rwsem);
@@ -1171,7 +1352,7 @@ static inline int __get_cp_reason(struct f2fs_sb_info *sbi)
 
 static inline bool __remain_node_summaries(int reason)
 {
-	return (reason == CP_UMOUNT || reason == CP_FASTBOOT);
+	return (reason & (CP_UMOUNT | CP_FASTBOOT));
 }
 
 static inline bool __exist_node_summaries(struct f2fs_sb_info *sbi)
@@ -1192,17 +1373,14 @@ static inline int check_nid_range(struct f2fs_sb_info *sbi, nid_t nid)
 	return 0;
 }
 
-#define F2FS_DEFAULT_ALLOCATED_BLOCKS	1
-
 /*
  * Check whether the inode has blocks or not
  */
 static inline int F2FS_HAS_BLOCKS(struct inode *inode)
 {
-	if (F2FS_I(inode)->i_xattr_nid)
-		return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS + 1;
-	else
-		return inode->i_blocks > F2FS_DEFAULT_ALLOCATED_BLOCKS;
+	block_t xattr_block = F2FS_I(inode)->i_xattr_nid ? 1 : 0;
+
+	return (inode->i_blocks >> F2FS_LOG_SECTORS_PER_BLOCK) > xattr_block;
 }
 
 static inline bool f2fs_has_xattr_block(unsigned int ofs)
@@ -1210,15 +1388,24 @@ static inline bool f2fs_has_xattr_block(unsigned int ofs)
 	return ofs == XATTR_NODE_OFFSET;
 }
 
-static inline void f2fs_i_blocks_write(struct inode *, blkcnt_t, bool);
-static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
+static inline void f2fs_i_blocks_write(struct inode *, block_t, bool, bool);
+static inline int inc_valid_block_count(struct f2fs_sb_info *sbi,
 				 struct inode *inode, blkcnt_t *count)
 {
-	blkcnt_t diff;
+	blkcnt_t diff = 0, release = 0;
+	block_t avail_user_block_count;
+	int ret;
+
+	ret = dquot_reserve_block(inode, *count);
+	if (ret)
+		return ret;
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(sbi, FAULT_BLOCK))
-		return false;
+	if (time_to_inject(sbi, FAULT_BLOCK)) {
+		f2fs_show_injection_info(FAULT_BLOCK);
+		release = *count;
+		goto enospc;
+	}
 #endif
 	/*
 	 * let's increase this in prior to actual block count change in order
@@ -1228,32 +1415,42 @@ static inline bool inc_valid_block_count(struct f2fs_sb_info *sbi,
 
 	spin_lock(&sbi->stat_lock);
 	sbi->total_valid_block_count += (block_t)(*count);
-	if (unlikely(sbi->total_valid_block_count > sbi->user_block_count)) {
-		diff = sbi->total_valid_block_count - sbi->user_block_count;
+	avail_user_block_count = sbi->user_block_count - sbi->reserved_blocks;
+	if (unlikely(sbi->total_valid_block_count > avail_user_block_count)) {
+		diff = sbi->total_valid_block_count - avail_user_block_count;
 		*count -= diff;
-		sbi->total_valid_block_count = sbi->user_block_count;
+		release = diff;
+		sbi->total_valid_block_count = avail_user_block_count;
 		if (!*count) {
 			spin_unlock(&sbi->stat_lock);
 			percpu_counter_sub(&sbi->alloc_valid_block_count, diff);
-			return false;
+			goto enospc;
 		}
 	}
 	spin_unlock(&sbi->stat_lock);
 
-	f2fs_i_blocks_write(inode, *count, true);
-	return true;
+	if (release)
+		dquot_release_reservation_block(inode, release);
+	f2fs_i_blocks_write(inode, *count, true, true);
+	return 0;
+
+enospc:
+	dquot_release_reservation_block(inode, release);
+	return -ENOSPC;
 }
 
 static inline void dec_valid_block_count(struct f2fs_sb_info *sbi,
 						struct inode *inode,
-						blkcnt_t count)
+						block_t count)
 {
+	blkcnt_t sectors = count << F2FS_LOG_SECTORS_PER_BLOCK;
+
 	spin_lock(&sbi->stat_lock);
 	f2fs_bug_on(sbi, sbi->total_valid_block_count < (block_t) count);
-	f2fs_bug_on(sbi, inode->i_blocks < count);
+	f2fs_bug_on(sbi, inode->i_blocks < sectors);
 	sbi->total_valid_block_count -= (block_t)count;
 	spin_unlock(&sbi->stat_lock);
-	f2fs_i_blocks_write(inode, count, false);
+	f2fs_i_blocks_write(inode, count, false, true);
 }
 
 static inline void inc_page_count(struct f2fs_sb_info *sbi, int count_type)
@@ -1382,51 +1579,70 @@ static inline block_t __start_sum_addr(struct f2fs_sb_info *sbi)
 	return le32_to_cpu(F2FS_CKPT(sbi)->cp_pack_start_sum);
 }
 
-static inline bool inc_valid_node_count(struct f2fs_sb_info *sbi,
-						struct inode *inode)
+static inline int inc_valid_node_count(struct f2fs_sb_info *sbi,
+					struct inode *inode, bool is_inode)
 {
 	block_t	valid_block_count;
 	unsigned int valid_node_count;
+	bool quota = inode && !is_inode;
+
+	if (quota) {
+		int ret = dquot_reserve_block(inode, 1);
+		if (ret)
+			return ret;
+	}
 
 	spin_lock(&sbi->stat_lock);
 
 	valid_block_count = sbi->total_valid_block_count + 1;
-	if (unlikely(valid_block_count > sbi->user_block_count)) {
+	if (unlikely(valid_block_count + sbi->reserved_blocks >
+						sbi->user_block_count)) {
 		spin_unlock(&sbi->stat_lock);
-		return false;
+		goto enospc;
 	}
 
 	valid_node_count = sbi->total_valid_node_count + 1;
 	if (unlikely(valid_node_count > sbi->total_node_count)) {
 		spin_unlock(&sbi->stat_lock);
-		return false;
+		goto enospc;
 	}
 
-	if (inode)
-		f2fs_i_blocks_write(inode, 1, true);
-
 	sbi->total_valid_node_count++;
 	sbi->total_valid_block_count++;
 	spin_unlock(&sbi->stat_lock);
 
+	if (inode) {
+		if (is_inode)
+			f2fs_mark_inode_dirty_sync(inode, true);
+		else
+			f2fs_i_blocks_write(inode, 1, true, true);
+	}
+
 	percpu_counter_inc(&sbi->alloc_valid_block_count);
-	return true;
+	return 0;
+
+enospc:
+	if (quota)
+		dquot_release_reservation_block(inode, 1);
+	return -ENOSPC;
 }
 
 static inline void dec_valid_node_count(struct f2fs_sb_info *sbi,
-						struct inode *inode)
+					struct inode *inode, bool is_inode)
 {
 	spin_lock(&sbi->stat_lock);
 
 	f2fs_bug_on(sbi, !sbi->total_valid_block_count);
 	f2fs_bug_on(sbi, !sbi->total_valid_node_count);
-	f2fs_bug_on(sbi, !inode->i_blocks);
+	f2fs_bug_on(sbi, !is_inode && !inode->i_blocks);
 
-	f2fs_i_blocks_write(inode, 1, false);
 	sbi->total_valid_node_count--;
 	sbi->total_valid_block_count--;
 
 	spin_unlock(&sbi->stat_lock);
+
+	if (!is_inode)
+		f2fs_i_blocks_write(inode, 1, false, true);
 }
 
 static inline unsigned int valid_node_count(struct f2fs_sb_info *sbi)
@@ -1454,11 +1670,14 @@ static inline struct page *f2fs_grab_cache_page(struct address_space *mapping,
 {
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	struct page *page = find_lock_page(mapping, index);
+
 	if (page)
 		return page;
 
-	if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC))
+	if (time_to_inject(F2FS_M_SB(mapping), FAULT_PAGE_ALLOC)) {
+		f2fs_show_injection_info(FAULT_PAGE_ALLOC);
 		return NULL;
+	}
 #endif
 	if (!for_write)
 		return grab_cache_page(mapping, index);
@@ -1537,6 +1756,7 @@ static inline void f2fs_radix_tree_insert(struct radix_tree_root *root,
 static inline bool IS_INODE(struct page *page)
 {
 	struct f2fs_node *p = F2FS_NODE(page);
+
 	return RAW_IS_INODE(p);
 }
 
@@ -1550,6 +1770,7 @@ static inline block_t datablock_addr(struct page *node_page,
 {
 	struct f2fs_node *raw_node;
 	__le32 *addr_array;
+
 	raw_node = F2FS_NODE(node_page);
 	addr_array = blkaddr_in_node(raw_node);
 	return le32_to_cpu(addr_array[offset]);
@@ -1633,6 +1854,7 @@ enum {
 	FI_UPDATE_WRITE,	/* inode has in-place-update data */
 	FI_NEED_IPU,		/* used for ipu per file */
 	FI_ATOMIC_FILE,		/* indicate atomic file */
+	FI_ATOMIC_COMMIT,	/* indicate the state of atomical committing */
 	FI_VOLATILE_FILE,	/* indicate volatile file */
 	FI_FIRST_BLOCK_WRITTEN,	/* indicate #0 data block was written */
 	FI_DROP_CACHE,		/* drop dirty page cache */
@@ -1640,6 +1862,8 @@ enum {
 	FI_INLINE_DOTS,		/* indicate inline dot dentries */
 	FI_DO_DEFRAG,		/* indicate defragment is running */
 	FI_DIRTY_FILE,		/* indicate regular/symlink has dirty pages */
+	FI_NO_PREALLOC,		/* indicate skipped preallocated blocks */
+	FI_HOT_DATA,		/* indicate file is hot */
 };
 
 static inline void __mark_inode_dirty_flag(struct inode *inode,
@@ -1693,13 +1917,21 @@ static inline void f2fs_i_links_write(struct inode *inode, bool inc)
 }
 
 static inline void f2fs_i_blocks_write(struct inode *inode,
-					blkcnt_t diff, bool add)
+					block_t diff, bool add, bool claim)
 {
 	bool clean = !is_inode_flag_set(inode, FI_DIRTY_INODE);
 	bool recover = is_inode_flag_set(inode, FI_AUTO_RECOVER);
 
-	inode->i_blocks = add ? inode->i_blocks + diff :
-				inode->i_blocks - diff;
+	/* add = 1, claim = 1 should be dquot_reserve_block in pair */
+	if (add) {
+		if (claim)
+			dquot_claim_block(inode, diff);
+		else
+			dquot_alloc_block_nofail(inode, diff);
+	} else {
+		dquot_free_block(inode, diff);
+	}
+
 	f2fs_mark_inode_dirty_sync(inode, true);
 	if (clean || recover)
 		set_inode_flag(inode, FI_AUTO_RECOVER);
@@ -1784,6 +2016,7 @@ static inline unsigned int addrs_per_inode(struct inode *inode)
 static inline void *inline_xattr_addr(struct page *page)
 {
 	struct f2fs_inode *ri = F2FS_INODE(page);
+
 	return (void *)&(ri->i_addr[DEF_ADDRS_PER_INODE -
 					F2FS_INLINE_XATTR_ADDRS]);
 }
@@ -1801,12 +2034,6 @@ static inline int f2fs_has_inline_data(struct inode *inode)
 	return is_inode_flag_set(inode, FI_INLINE_DATA);
 }
 
-static inline void f2fs_clear_inline_inode(struct inode *inode)
-{
-	clear_inode_flag(inode, FI_INLINE_DATA);
-	clear_inode_flag(inode, FI_DATA_EXIST);
-}
-
 static inline int f2fs_exist_data(struct inode *inode)
 {
 	return is_inode_flag_set(inode, FI_DATA_EXIST);
@@ -1822,6 +2049,11 @@ static inline bool f2fs_is_atomic_file(struct inode *inode)
 	return is_inode_flag_set(inode, FI_ATOMIC_FILE);
 }
 
+static inline bool f2fs_is_commit_atomic_write(struct inode *inode)
+{
+	return is_inode_flag_set(inode, FI_ATOMIC_COMMIT);
+}
+
 static inline bool f2fs_is_volatile_file(struct inode *inode)
 {
 	return is_inode_flag_set(inode, FI_VOLATILE_FILE);
@@ -1840,6 +2072,7 @@ static inline bool f2fs_is_drop_cache(struct inode *inode)
 static inline void *inline_data_addr(struct page *page)
 {
 	struct f2fs_inode *ri = F2FS_INODE(page);
+
 	return (void *)&(ri->i_addr[1]);
 }
 
@@ -1923,68 +2156,45 @@ static inline void *f2fs_kmalloc(struct f2fs_sb_info *sbi,
 					size_t size, gfp_t flags)
 {
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(sbi, FAULT_KMALLOC))
+	if (time_to_inject(sbi, FAULT_KMALLOC)) {
+		f2fs_show_injection_info(FAULT_KMALLOC);
 		return NULL;
+	}
 #endif
 	return kmalloc(size, flags);
 }
 
-static inline void *f2fs_kvmalloc(size_t size, gfp_t flags)
-{
-	void *ret;
-
-	ret = kmalloc(size, flags | __GFP_NOWARN);
-	if (!ret)
-		ret = __vmalloc(size, flags, PAGE_KERNEL);
-	return ret;
-}
-
-static inline void *f2fs_kvzalloc(size_t size, gfp_t flags)
-{
-	void *ret;
-
-	ret = kzalloc(size, flags | __GFP_NOWARN);
-	if (!ret)
-		ret = __vmalloc(size, flags | __GFP_ZERO, PAGE_KERNEL);
-	return ret;
-}
-
 #define get_inode_mode(i) \
 	((is_inode_flag_set(i, FI_ACL_MODE)) ? \
 	 (F2FS_I(i)->i_acl_mode) : ((i)->i_mode))
 
-/* get offset of first page in next direct node */
-#define PGOFS_OF_NEXT_DNODE(pgofs, inode)				\
-	((pgofs < ADDRS_PER_INODE(inode)) ? ADDRS_PER_INODE(inode) :	\
-	(pgofs - ADDRS_PER_INODE(inode) + ADDRS_PER_BLOCK) /	\
-	ADDRS_PER_BLOCK * ADDRS_PER_BLOCK + ADDRS_PER_INODE(inode))
-
 /*
  * file.c
  */
-int f2fs_sync_file(struct file *, loff_t, loff_t, int);
-void truncate_data_blocks(struct dnode_of_data *);
-int truncate_blocks(struct inode *, u64, bool);
-int f2fs_truncate(struct inode *);
-int f2fs_getattr(struct vfsmount *, struct dentry *, struct kstat *);
-int f2fs_setattr(struct dentry *, struct iattr *);
-int truncate_hole(struct inode *, pgoff_t, pgoff_t);
-int truncate_data_blocks_range(struct dnode_of_data *, int);
-long f2fs_ioctl(struct file *, unsigned int, unsigned long);
-long f2fs_compat_ioctl(struct file *, unsigned int, unsigned long);
+int f2fs_sync_file(struct file *file, loff_t start, loff_t end, int datasync);
+void truncate_data_blocks(struct dnode_of_data *dn);
+int truncate_blocks(struct inode *inode, u64 from, bool lock);
+int f2fs_truncate(struct inode *inode);
+int f2fs_getattr(const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int flags);
+int f2fs_setattr(struct dentry *dentry, struct iattr *attr);
+int truncate_hole(struct inode *inode, pgoff_t pg_start, pgoff_t pg_end);
+int truncate_data_blocks_range(struct dnode_of_data *dn, int count);
+long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg);
+long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg);
 
 /*
  * inode.c
  */
-void f2fs_set_inode_flags(struct inode *);
-struct inode *f2fs_iget(struct super_block *, unsigned long);
-struct inode *f2fs_iget_retry(struct super_block *, unsigned long);
-int try_to_free_nats(struct f2fs_sb_info *, int);
-int update_inode(struct inode *, struct page *);
-int update_inode_page(struct inode *);
-int f2fs_write_inode(struct inode *, struct writeback_control *);
-void f2fs_evict_inode(struct inode *);
-void handle_failed_inode(struct inode *);
+void f2fs_set_inode_flags(struct inode *inode);
+struct inode *f2fs_iget(struct super_block *sb, unsigned long ino);
+struct inode *f2fs_iget_retry(struct super_block *sb, unsigned long ino);
+int try_to_free_nats(struct f2fs_sb_info *sbi, int nr_shrink);
+int update_inode(struct inode *inode, struct page *node_page);
+int update_inode_page(struct inode *inode);
+int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc);
+void f2fs_evict_inode(struct inode *inode);
+void handle_failed_inode(struct inode *inode);
 
 /*
  * namei.c
@@ -1994,40 +2204,45 @@ struct dentry *f2fs_get_parent(struct dentry *child);
 /*
  * dir.c
  */
-void set_de_type(struct f2fs_dir_entry *, umode_t);
-unsigned char get_de_type(struct f2fs_dir_entry *);
-struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *,
-			f2fs_hash_t, int *, struct f2fs_dentry_ptr *);
-int f2fs_fill_dentries(struct dir_context *, struct f2fs_dentry_ptr *,
-			unsigned int, struct fscrypt_str *);
-void do_make_empty_dir(struct inode *, struct inode *,
-			struct f2fs_dentry_ptr *);
-struct page *init_inode_metadata(struct inode *, struct inode *,
-		const struct qstr *, const struct qstr *, struct page *);
-void update_parent_metadata(struct inode *, struct inode *, unsigned int);
-int room_for_filename(const void *, int, int);
-void f2fs_drop_nlink(struct inode *, struct inode *);
-struct f2fs_dir_entry *__f2fs_find_entry(struct inode *, struct fscrypt_name *,
-							struct page **);
-struct f2fs_dir_entry *f2fs_find_entry(struct inode *, const struct qstr *,
-							struct page **);
-struct f2fs_dir_entry *f2fs_parent_dir(struct inode *, struct page **);
-ino_t f2fs_inode_by_name(struct inode *, const struct qstr *, struct page **);
-void f2fs_set_link(struct inode *, struct f2fs_dir_entry *,
-				struct page *, struct inode *);
-int update_dent_inode(struct inode *, struct inode *, const struct qstr *);
-void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *,
-			const struct qstr *, f2fs_hash_t , unsigned int);
-int f2fs_add_regular_entry(struct inode *, const struct qstr *,
-			const struct qstr *, struct inode *, nid_t, umode_t);
-int __f2fs_do_add_link(struct inode *, struct fscrypt_name*, struct inode *,
-			nid_t, umode_t);
-int __f2fs_add_link(struct inode *, const struct qstr *, struct inode *, nid_t,
-			umode_t);
-void f2fs_delete_entry(struct f2fs_dir_entry *, struct page *, struct inode *,
-							struct inode *);
-int f2fs_do_tmpfile(struct inode *, struct inode *);
-bool f2fs_empty_dir(struct inode *);
+void set_de_type(struct f2fs_dir_entry *de, umode_t mode);
+unsigned char get_de_type(struct f2fs_dir_entry *de);
+struct f2fs_dir_entry *find_target_dentry(struct fscrypt_name *fname,
+			f2fs_hash_t namehash, int *max_slots,
+			struct f2fs_dentry_ptr *d);
+int f2fs_fill_dentries(struct dir_context *ctx, struct f2fs_dentry_ptr *d,
+			unsigned int start_pos, struct fscrypt_str *fstr);
+void do_make_empty_dir(struct inode *inode, struct inode *parent,
+			struct f2fs_dentry_ptr *d);
+struct page *init_inode_metadata(struct inode *inode, struct inode *dir,
+			const struct qstr *new_name,
+			const struct qstr *orig_name, struct page *dpage);
+void update_parent_metadata(struct inode *dir, struct inode *inode,
+			unsigned int current_depth);
+int room_for_filename(const void *bitmap, int slots, int max_slots);
+void f2fs_drop_nlink(struct inode *dir, struct inode *inode);
+struct f2fs_dir_entry *__f2fs_find_entry(struct inode *dir,
+			struct fscrypt_name *fname, struct page **res_page);
+struct f2fs_dir_entry *f2fs_find_entry(struct inode *dir,
+			const struct qstr *child, struct page **res_page);
+struct f2fs_dir_entry *f2fs_parent_dir(struct inode *dir, struct page **p);
+ino_t f2fs_inode_by_name(struct inode *dir, const struct qstr *qstr,
+			struct page **page);
+void f2fs_set_link(struct inode *dir, struct f2fs_dir_entry *de,
+			struct page *page, struct inode *inode);
+void f2fs_update_dentry(nid_t ino, umode_t mode, struct f2fs_dentry_ptr *d,
+			const struct qstr *name, f2fs_hash_t name_hash,
+			unsigned int bit_pos);
+int f2fs_add_regular_entry(struct inode *dir, const struct qstr *new_name,
+			const struct qstr *orig_name,
+			struct inode *inode, nid_t ino, umode_t mode);
+int __f2fs_do_add_link(struct inode *dir, struct fscrypt_name *fname,
+			struct inode *inode, nid_t ino, umode_t mode);
+int __f2fs_add_link(struct inode *dir, const struct qstr *name,
+			struct inode *inode, nid_t ino, umode_t mode);
+void f2fs_delete_entry(struct f2fs_dir_entry *dentry, struct page *page,
+			struct inode *dir, struct inode *inode);
+int f2fs_do_tmpfile(struct inode *inode, struct inode *dir);
+bool f2fs_empty_dir(struct inode *dir);
 
 static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
 {
@@ -2038,18 +2253,19 @@ static inline int f2fs_add_link(struct dentry *dentry, struct inode *inode)
 /*
  * super.c
  */
-int f2fs_inode_dirtied(struct inode *, bool);
-void f2fs_inode_synced(struct inode *);
-int f2fs_commit_super(struct f2fs_sb_info *, bool);
-int f2fs_sync_fs(struct super_block *, int);
+int f2fs_inode_dirtied(struct inode *inode, bool sync);
+void f2fs_inode_synced(struct inode *inode);
+int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover);
+int f2fs_sync_fs(struct super_block *sb, int sync);
 extern __printf(3, 4)
-void f2fs_msg(struct super_block *, const char *, const char *, ...);
+void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...);
 int sanity_check_ckpt(struct f2fs_sb_info *sbi);
 
 /*
  * hash.c
  */
-f2fs_hash_t f2fs_dentry_hash(const struct qstr *);
+f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info,
+				struct fscrypt_name *fname);
 
 /*
  * node.c
@@ -2057,163 +2273,186 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *);
 struct dnode_of_data;
 struct node_info;
 
-bool available_free_memory(struct f2fs_sb_info *, int);
-int need_dentry_mark(struct f2fs_sb_info *, nid_t);
-bool is_checkpointed_node(struct f2fs_sb_info *, nid_t);
-bool need_inode_block_update(struct f2fs_sb_info *, nid_t);
-void get_node_info(struct f2fs_sb_info *, nid_t, struct node_info *);
-pgoff_t get_next_page_offset(struct dnode_of_data *, pgoff_t);
-int get_dnode_of_data(struct dnode_of_data *, pgoff_t, int);
-int truncate_inode_blocks(struct inode *, pgoff_t);
-int truncate_xattr_node(struct inode *, struct page *);
-int wait_on_node_pages_writeback(struct f2fs_sb_info *, nid_t);
-int remove_inode_page(struct inode *);
-struct page *new_inode_page(struct inode *);
-struct page *new_node_page(struct dnode_of_data *, unsigned int, struct page *);
-void ra_node_page(struct f2fs_sb_info *, nid_t);
-struct page *get_node_page(struct f2fs_sb_info *, pgoff_t);
-struct page *get_node_page_ra(struct page *, int);
-void move_node_page(struct page *, int);
-int fsync_node_pages(struct f2fs_sb_info *, struct inode *,
-			struct writeback_control *, bool);
-int sync_node_pages(struct f2fs_sb_info *, struct writeback_control *);
-void build_free_nids(struct f2fs_sb_info *, bool);
-bool alloc_nid(struct f2fs_sb_info *, nid_t *);
-void alloc_nid_done(struct f2fs_sb_info *, nid_t);
-void alloc_nid_failed(struct f2fs_sb_info *, nid_t);
-int try_to_free_nids(struct f2fs_sb_info *, int);
-void recover_inline_xattr(struct inode *, struct page *);
-void recover_xattr_data(struct inode *, struct page *, block_t);
-int recover_inode_page(struct f2fs_sb_info *, struct page *);
-int restore_node_summary(struct f2fs_sb_info *, unsigned int,
-				struct f2fs_summary_block *);
-void flush_nat_entries(struct f2fs_sb_info *);
-int build_node_manager(struct f2fs_sb_info *);
-void destroy_node_manager(struct f2fs_sb_info *);
+bool available_free_memory(struct f2fs_sb_info *sbi, int type);
+int need_dentry_mark(struct f2fs_sb_info *sbi, nid_t nid);
+bool is_checkpointed_node(struct f2fs_sb_info *sbi, nid_t nid);
+bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino);
+void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni);
+pgoff_t get_next_page_offset(struct dnode_of_data *dn, pgoff_t pgofs);
+int get_dnode_of_data(struct dnode_of_data *dn, pgoff_t index, int mode);
+int truncate_inode_blocks(struct inode *inode, pgoff_t from);
+int truncate_xattr_node(struct inode *inode, struct page *page);
+int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino);
+int remove_inode_page(struct inode *inode);
+struct page *new_inode_page(struct inode *inode);
+struct page *new_node_page(struct dnode_of_data *dn,
+			unsigned int ofs, struct page *ipage);
+void ra_node_page(struct f2fs_sb_info *sbi, nid_t nid);
+struct page *get_node_page(struct f2fs_sb_info *sbi, pgoff_t nid);
+struct page *get_node_page_ra(struct page *parent, int start);
+void move_node_page(struct page *node_page, int gc_type);
+int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
+			struct writeback_control *wbc, bool atomic);
+int sync_node_pages(struct f2fs_sb_info *sbi, struct writeback_control *wbc);
+void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount);
+bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid);
+void alloc_nid_done(struct f2fs_sb_info *sbi, nid_t nid);
+void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid);
+int try_to_free_nids(struct f2fs_sb_info *sbi, int nr_shrink);
+void recover_inline_xattr(struct inode *inode, struct page *page);
+int recover_xattr_data(struct inode *inode, struct page *page,
+			block_t blkaddr);
+int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page);
+int restore_node_summary(struct f2fs_sb_info *sbi,
+			unsigned int segno, struct f2fs_summary_block *sum);
+void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int build_node_manager(struct f2fs_sb_info *sbi);
+void destroy_node_manager(struct f2fs_sb_info *sbi);
 int __init create_node_manager_caches(void);
 void destroy_node_manager_caches(void);
 
 /*
  * segment.c
  */
-void register_inmem_page(struct inode *, struct page *);
-void drop_inmem_pages(struct inode *);
-int commit_inmem_pages(struct inode *);
-void f2fs_balance_fs(struct f2fs_sb_info *, bool);
-void f2fs_balance_fs_bg(struct f2fs_sb_info *);
-int f2fs_issue_flush(struct f2fs_sb_info *);
-int create_flush_cmd_control(struct f2fs_sb_info *);
-void destroy_flush_cmd_control(struct f2fs_sb_info *, bool);
-void invalidate_blocks(struct f2fs_sb_info *, block_t);
-bool is_checkpointed_data(struct f2fs_sb_info *, block_t);
-void refresh_sit_entry(struct f2fs_sb_info *, block_t, block_t);
-void f2fs_wait_all_discard_bio(struct f2fs_sb_info *);
-void clear_prefree_segments(struct f2fs_sb_info *, struct cp_control *);
-void release_discard_addrs(struct f2fs_sb_info *);
-int npages_for_summary_flush(struct f2fs_sb_info *, bool);
-void allocate_new_segments(struct f2fs_sb_info *);
-int f2fs_trim_fs(struct f2fs_sb_info *, struct fstrim_range *);
-struct page *get_sum_page(struct f2fs_sb_info *, unsigned int);
-void update_meta_page(struct f2fs_sb_info *, void *, block_t);
-void write_meta_page(struct f2fs_sb_info *, struct page *);
-void write_node_page(unsigned int, struct f2fs_io_info *);
-void write_data_page(struct dnode_of_data *, struct f2fs_io_info *);
-void rewrite_data_page(struct f2fs_io_info *);
-void __f2fs_replace_block(struct f2fs_sb_info *, struct f2fs_summary *,
-					block_t, block_t, bool, bool);
-void f2fs_replace_block(struct f2fs_sb_info *, struct dnode_of_data *,
-				block_t, block_t, unsigned char, bool, bool);
-void allocate_data_block(struct f2fs_sb_info *, struct page *,
-		block_t, block_t *, struct f2fs_summary *, int);
-void f2fs_wait_on_page_writeback(struct page *, enum page_type, bool);
-void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *, block_t);
-void write_data_summaries(struct f2fs_sb_info *, block_t);
-void write_node_summaries(struct f2fs_sb_info *, block_t);
-int lookup_journal_in_cursum(struct f2fs_journal *, int, unsigned int, int);
-void flush_sit_entries(struct f2fs_sb_info *, struct cp_control *);
-int build_segment_manager(struct f2fs_sb_info *);
-void destroy_segment_manager(struct f2fs_sb_info *);
+void register_inmem_page(struct inode *inode, struct page *page);
+void drop_inmem_pages(struct inode *inode);
+void drop_inmem_page(struct inode *inode, struct page *page);
+int commit_inmem_pages(struct inode *inode);
+void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need);
+void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi);
+int f2fs_issue_flush(struct f2fs_sb_info *sbi);
+int create_flush_cmd_control(struct f2fs_sb_info *sbi);
+void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free);
+void invalidate_blocks(struct f2fs_sb_info *sbi, block_t addr);
+bool is_checkpointed_data(struct f2fs_sb_info *sbi, block_t blkaddr);
+void refresh_sit_entry(struct f2fs_sb_info *sbi, block_t old, block_t new);
+void stop_discard_thread(struct f2fs_sb_info *sbi);
+void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi);
+void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+void release_discard_addrs(struct f2fs_sb_info *sbi);
+int npages_for_summary_flush(struct f2fs_sb_info *sbi, bool for_ra);
+void allocate_new_segments(struct f2fs_sb_info *sbi);
+int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range);
+bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+struct page *get_sum_page(struct f2fs_sb_info *sbi, unsigned int segno);
+void update_meta_page(struct f2fs_sb_info *sbi, void *src, block_t blk_addr);
+void write_meta_page(struct f2fs_sb_info *sbi, struct page *page);
+void write_node_page(unsigned int nid, struct f2fs_io_info *fio);
+void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio);
+int rewrite_data_page(struct f2fs_io_info *fio);
+void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
+			block_t old_blkaddr, block_t new_blkaddr,
+			bool recover_curseg, bool recover_newaddr);
+void f2fs_replace_block(struct f2fs_sb_info *sbi, struct dnode_of_data *dn,
+			block_t old_addr, block_t new_addr,
+			unsigned char version, bool recover_curseg,
+			bool recover_newaddr);
+void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
+			block_t old_blkaddr, block_t *new_blkaddr,
+			struct f2fs_summary *sum, int type,
+			struct f2fs_io_info *fio, bool add_list);
+void f2fs_wait_on_page_writeback(struct page *page,
+			enum page_type type, bool ordered);
+void f2fs_wait_on_encrypted_page_writeback(struct f2fs_sb_info *sbi,
+			block_t blkaddr);
+void write_data_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
+void write_node_summaries(struct f2fs_sb_info *sbi, block_t start_blk);
+int lookup_journal_in_cursum(struct f2fs_journal *journal, int type,
+			unsigned int val, int alloc);
+void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+int build_segment_manager(struct f2fs_sb_info *sbi);
+void destroy_segment_manager(struct f2fs_sb_info *sbi);
 int __init create_segment_manager_caches(void);
 void destroy_segment_manager_caches(void);
 
 /*
  * checkpoint.c
  */
-void f2fs_stop_checkpoint(struct f2fs_sb_info *, bool);
-struct page *grab_meta_page(struct f2fs_sb_info *, pgoff_t);
-struct page *get_meta_page(struct f2fs_sb_info *, pgoff_t);
-struct page *get_tmp_page(struct f2fs_sb_info *, pgoff_t);
-bool is_valid_blkaddr(struct f2fs_sb_info *, block_t, int);
-int ra_meta_pages(struct f2fs_sb_info *, block_t, int, int, bool);
-void ra_meta_pages_cond(struct f2fs_sb_info *, pgoff_t);
-long sync_meta_pages(struct f2fs_sb_info *, enum page_type, long);
-void add_ino_entry(struct f2fs_sb_info *, nid_t, int type);
-void remove_ino_entry(struct f2fs_sb_info *, nid_t, int type);
-void release_ino_entry(struct f2fs_sb_info *, bool);
-bool exist_written_data(struct f2fs_sb_info *, nid_t, int);
-int f2fs_sync_inode_meta(struct f2fs_sb_info *);
-int acquire_orphan_inode(struct f2fs_sb_info *);
-void release_orphan_inode(struct f2fs_sb_info *);
-void add_orphan_inode(struct inode *);
-void remove_orphan_inode(struct f2fs_sb_info *, nid_t);
-int recover_orphan_inodes(struct f2fs_sb_info *);
-int get_valid_checkpoint(struct f2fs_sb_info *);
-void update_dirty_page(struct inode *, struct page *);
-void remove_dirty_inode(struct inode *);
-int sync_dirty_inodes(struct f2fs_sb_info *, enum inode_type);
-int write_checkpoint(struct f2fs_sb_info *, struct cp_control *);
-void init_ino_entry_info(struct f2fs_sb_info *);
+void f2fs_stop_checkpoint(struct f2fs_sb_info *sbi, bool end_io);
+struct page *grab_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *get_meta_page(struct f2fs_sb_info *sbi, pgoff_t index);
+struct page *get_tmp_page(struct f2fs_sb_info *sbi, pgoff_t index);
+bool is_valid_blkaddr(struct f2fs_sb_info *sbi, block_t blkaddr, int type);
+int ra_meta_pages(struct f2fs_sb_info *sbi, block_t start, int nrpages,
+			int type, bool sync);
+void ra_meta_pages_cond(struct f2fs_sb_info *sbi, pgoff_t index);
+long sync_meta_pages(struct f2fs_sb_info *sbi, enum page_type type,
+			long nr_to_write);
+void add_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
+void remove_ino_entry(struct f2fs_sb_info *sbi, nid_t ino, int type);
+void release_ino_entry(struct f2fs_sb_info *sbi, bool all);
+bool exist_written_data(struct f2fs_sb_info *sbi, nid_t ino, int mode);
+int f2fs_sync_inode_meta(struct f2fs_sb_info *sbi);
+int acquire_orphan_inode(struct f2fs_sb_info *sbi);
+void release_orphan_inode(struct f2fs_sb_info *sbi);
+void add_orphan_inode(struct inode *inode);
+void remove_orphan_inode(struct f2fs_sb_info *sbi, nid_t ino);
+int recover_orphan_inodes(struct f2fs_sb_info *sbi);
+int get_valid_checkpoint(struct f2fs_sb_info *sbi);
+void update_dirty_page(struct inode *inode, struct page *page);
+void remove_dirty_inode(struct inode *inode);
+int sync_dirty_inodes(struct f2fs_sb_info *sbi, enum inode_type type);
+int write_checkpoint(struct f2fs_sb_info *sbi, struct cp_control *cpc);
+void init_ino_entry_info(struct f2fs_sb_info *sbi);
 int __init create_checkpoint_caches(void);
 void destroy_checkpoint_caches(void);
 
 /*
  * data.c
  */
-void f2fs_submit_merged_bio(struct f2fs_sb_info *, enum page_type, int);
-void f2fs_submit_merged_bio_cond(struct f2fs_sb_info *, struct inode *,
-				struct page *, nid_t, enum page_type, int);
-void f2fs_flush_merged_bios(struct f2fs_sb_info *);
-int f2fs_submit_page_bio(struct f2fs_io_info *);
-void f2fs_submit_page_mbio(struct f2fs_io_info *);
-struct block_device *f2fs_target_device(struct f2fs_sb_info *,
-				block_t, struct bio *);
-int f2fs_target_device_index(struct f2fs_sb_info *, block_t);
-void set_data_blkaddr(struct dnode_of_data *);
-void f2fs_update_data_blkaddr(struct dnode_of_data *, block_t);
-int reserve_new_blocks(struct dnode_of_data *, blkcnt_t);
-int reserve_new_block(struct dnode_of_data *);
-int f2fs_get_block(struct dnode_of_data *, pgoff_t);
-int f2fs_preallocate_blocks(struct kiocb *, struct iov_iter *);
-int f2fs_reserve_block(struct dnode_of_data *, pgoff_t);
-struct page *get_read_data_page(struct inode *, pgoff_t, int, bool);
-struct page *find_data_page(struct inode *, pgoff_t);
-struct page *get_lock_data_page(struct inode *, pgoff_t, bool);
-struct page *get_new_data_page(struct inode *, struct page *, pgoff_t, bool);
-int do_write_data_page(struct f2fs_io_info *);
-int f2fs_map_blocks(struct inode *, struct f2fs_map_blocks *, int, int);
-int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *, u64, u64);
-void f2fs_set_page_dirty_nobuffers(struct page *);
-void f2fs_invalidate_page(struct page *, unsigned int, unsigned int);
-int f2fs_release_page(struct page *, gfp_t);
+void f2fs_submit_merged_write(struct f2fs_sb_info *sbi, enum page_type type);
+void f2fs_submit_merged_write_cond(struct f2fs_sb_info *sbi,
+				struct inode *inode, nid_t ino, pgoff_t idx,
+				enum page_type type);
+void f2fs_flush_merged_writes(struct f2fs_sb_info *sbi);
+int f2fs_submit_page_bio(struct f2fs_io_info *fio);
+int f2fs_submit_page_write(struct f2fs_io_info *fio);
+struct block_device *f2fs_target_device(struct f2fs_sb_info *sbi,
+			block_t blk_addr, struct bio *bio);
+int f2fs_target_device_index(struct f2fs_sb_info *sbi, block_t blkaddr);
+void set_data_blkaddr(struct dnode_of_data *dn);
+void f2fs_update_data_blkaddr(struct dnode_of_data *dn, block_t blkaddr);
+int reserve_new_blocks(struct dnode_of_data *dn, blkcnt_t count);
+int reserve_new_block(struct dnode_of_data *dn);
+int f2fs_get_block(struct dnode_of_data *dn, pgoff_t index);
+int f2fs_preallocate_blocks(struct kiocb *iocb, struct iov_iter *from);
+int f2fs_reserve_block(struct dnode_of_data *dn, pgoff_t index);
+struct page *get_read_data_page(struct inode *inode, pgoff_t index,
+			int op_flags, bool for_write);
+struct page *find_data_page(struct inode *inode, pgoff_t index);
+struct page *get_lock_data_page(struct inode *inode, pgoff_t index,
+			bool for_write);
+struct page *get_new_data_page(struct inode *inode,
+			struct page *ipage, pgoff_t index, bool new_i_size);
+int do_write_data_page(struct f2fs_io_info *fio);
+int f2fs_map_blocks(struct inode *inode, struct f2fs_map_blocks *map,
+			int create, int flag);
+int f2fs_fiemap(struct inode *inode, struct fiemap_extent_info *fieinfo,
+			u64 start, u64 len);
+void f2fs_set_page_dirty_nobuffers(struct page *page);
+void f2fs_invalidate_page(struct page *page, unsigned int offset,
+			unsigned int length);
+int f2fs_release_page(struct page *page, gfp_t wait);
 #ifdef CONFIG_MIGRATION
-int f2fs_migrate_page(struct address_space *, struct page *, struct page *,
-				enum migrate_mode);
+int f2fs_migrate_page(struct address_space *mapping, struct page *newpage,
+			struct page *page, enum migrate_mode mode);
 #endif
 
 /*
  * gc.c
  */
-int start_gc_thread(struct f2fs_sb_info *);
-void stop_gc_thread(struct f2fs_sb_info *);
-block_t start_bidx_of_node(unsigned int, struct inode *);
-int f2fs_gc(struct f2fs_sb_info *, bool, bool);
-void build_gc_manager(struct f2fs_sb_info *);
+int start_gc_thread(struct f2fs_sb_info *sbi);
+void stop_gc_thread(struct f2fs_sb_info *sbi);
+block_t start_bidx_of_node(unsigned int node_ofs, struct inode *inode);
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background,
+			unsigned int segno);
+void build_gc_manager(struct f2fs_sb_info *sbi);
 
 /*
  * recovery.c
  */
-int recover_fsync_data(struct f2fs_sb_info *, bool);
-bool space_for_roll_forward(struct f2fs_sb_info *);
+int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only);
+bool space_for_roll_forward(struct f2fs_sb_info *sbi);
 
 /*
  * debug.c
@@ -2230,10 +2469,15 @@ struct f2fs_stat_info {
 	int ndirty_node, ndirty_dent, ndirty_meta, ndirty_data, ndirty_imeta;
 	int inmem_pages;
 	unsigned int ndirty_dirs, ndirty_files, ndirty_all;
-	int nats, dirty_nats, sits, dirty_sits, free_nids, alloc_nids;
+	int nats, dirty_nats, sits, dirty_sits;
+	int free_nids, avail_nids, alloc_nids;
 	int total_count, utilization;
 	int bg_gc, nr_wb_cp_data, nr_wb_data;
-	int inline_xattr, inline_inode, inline_dir, orphans;
+	int nr_flushing, nr_flushed, nr_discarding, nr_discarded;
+	int nr_discard_cmd;
+	unsigned int undiscard_blks;
+	int inline_xattr, inline_inode, inline_dir, append, update, orphans;
+	int aw_cnt, max_aw_cnt, vw_cnt, max_vw_cnt;
 	unsigned int valid_count, valid_node_count, valid_inode_count, discard_blks;
 	unsigned int bimodal, avg_vblocks;
 	int util_free, util_valid, util_invalid;
@@ -2305,11 +2549,33 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 		((sbi)->block_count[(curseg)->alloc_type]++)
 #define stat_inc_inplace_blocks(sbi)					\
 		(atomic_inc(&(sbi)->inplace_count))
+#define stat_inc_atomic_write(inode)					\
+		(atomic_inc(&F2FS_I_SB(inode)->aw_cnt))
+#define stat_dec_atomic_write(inode)					\
+		(atomic_dec(&F2FS_I_SB(inode)->aw_cnt))
+#define stat_update_max_atomic_write(inode)				\
+	do {								\
+		int cur = atomic_read(&F2FS_I_SB(inode)->aw_cnt);	\
+		int max = atomic_read(&F2FS_I_SB(inode)->max_aw_cnt);	\
+		if (cur > max)						\
+			atomic_set(&F2FS_I_SB(inode)->max_aw_cnt, cur);	\
+	} while (0)
+#define stat_inc_volatile_write(inode)					\
+		(atomic_inc(&F2FS_I_SB(inode)->vw_cnt))
+#define stat_dec_volatile_write(inode)					\
+		(atomic_dec(&F2FS_I_SB(inode)->vw_cnt))
+#define stat_update_max_volatile_write(inode)				\
+	do {								\
+		int cur = atomic_read(&F2FS_I_SB(inode)->vw_cnt);	\
+		int max = atomic_read(&F2FS_I_SB(inode)->max_vw_cnt);	\
+		if (cur > max)						\
+			atomic_set(&F2FS_I_SB(inode)->max_vw_cnt, cur);	\
+	} while (0)
 #define stat_inc_seg_count(sbi, type, gc_type)				\
 	do {								\
 		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
-		(si)->tot_segs++;					\
-		if (type == SUM_TYPE_DATA) {				\
+		si->tot_segs++;						\
+		if ((type) == SUM_TYPE_DATA) {				\
 			si->data_segs++;				\
 			si->bg_data_segs += (gc_type == BG_GC) ? 1 : 0;	\
 		} else {						\
@@ -2319,14 +2585,14 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 	} while (0)
 
 #define stat_inc_tot_blk_count(si, blks)				\
-	(si->tot_blks += (blks))
+	((si)->tot_blks += (blks))
 
 #define stat_inc_data_blk_count(sbi, blks, gc_type)			\
 	do {								\
 		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
 		stat_inc_tot_blk_count(si, blks);			\
 		si->data_blks += (blks);				\
-		si->bg_data_blks += (gc_type == BG_GC) ? (blks) : 0;	\
+		si->bg_data_blks += ((gc_type) == BG_GC) ? (blks) : 0;	\
 	} while (0)
 
 #define stat_inc_node_blk_count(sbi, blks, gc_type)			\
@@ -2334,37 +2600,43 @@ static inline struct f2fs_stat_info *F2FS_STAT(struct f2fs_sb_info *sbi)
 		struct f2fs_stat_info *si = F2FS_STAT(sbi);		\
 		stat_inc_tot_blk_count(si, blks);			\
 		si->node_blks += (blks);				\
-		si->bg_node_blks += (gc_type == BG_GC) ? (blks) : 0;	\
+		si->bg_node_blks += ((gc_type) == BG_GC) ? (blks) : 0;	\
 	} while (0)
 
-int f2fs_build_stats(struct f2fs_sb_info *);
-void f2fs_destroy_stats(struct f2fs_sb_info *);
+int f2fs_build_stats(struct f2fs_sb_info *sbi);
+void f2fs_destroy_stats(struct f2fs_sb_info *sbi);
 int __init f2fs_create_root_stats(void);
 void f2fs_destroy_root_stats(void);
 #else
-#define stat_inc_cp_count(si)
-#define stat_inc_bg_cp_count(si)
-#define stat_inc_call_count(si)
-#define stat_inc_bggc_count(si)
-#define stat_inc_dirty_inode(sbi, type)
-#define stat_dec_dirty_inode(sbi, type)
-#define stat_inc_total_hit(sb)
-#define stat_inc_rbtree_node_hit(sb)
-#define stat_inc_largest_node_hit(sbi)
-#define stat_inc_cached_node_hit(sbi)
-#define stat_inc_inline_xattr(inode)
-#define stat_dec_inline_xattr(inode)
-#define stat_inc_inline_inode(inode)
-#define stat_dec_inline_inode(inode)
-#define stat_inc_inline_dir(inode)
-#define stat_dec_inline_dir(inode)
-#define stat_inc_seg_type(sbi, curseg)
-#define stat_inc_block_count(sbi, curseg)
-#define stat_inc_inplace_blocks(sbi)
-#define stat_inc_seg_count(sbi, type, gc_type)
-#define stat_inc_tot_blk_count(si, blks)
-#define stat_inc_data_blk_count(sbi, blks, gc_type)
-#define stat_inc_node_blk_count(sbi, blks, gc_type)
+#define stat_inc_cp_count(si)				do { } while (0)
+#define stat_inc_bg_cp_count(si)			do { } while (0)
+#define stat_inc_call_count(si)				do { } while (0)
+#define stat_inc_bggc_count(si)				do { } while (0)
+#define stat_inc_dirty_inode(sbi, type)			do { } while (0)
+#define stat_dec_dirty_inode(sbi, type)			do { } while (0)
+#define stat_inc_total_hit(sb)				do { } while (0)
+#define stat_inc_rbtree_node_hit(sb)			do { } while (0)
+#define stat_inc_largest_node_hit(sbi)			do { } while (0)
+#define stat_inc_cached_node_hit(sbi)			do { } while (0)
+#define stat_inc_inline_xattr(inode)			do { } while (0)
+#define stat_dec_inline_xattr(inode)			do { } while (0)
+#define stat_inc_inline_inode(inode)			do { } while (0)
+#define stat_dec_inline_inode(inode)			do { } while (0)
+#define stat_inc_inline_dir(inode)			do { } while (0)
+#define stat_dec_inline_dir(inode)			do { } while (0)
+#define stat_inc_atomic_write(inode)			do { } while (0)
+#define stat_dec_atomic_write(inode)			do { } while (0)
+#define stat_update_max_atomic_write(inode)		do { } while (0)
+#define stat_inc_volatile_write(inode)			do { } while (0)
+#define stat_dec_volatile_write(inode)			do { } while (0)
+#define stat_update_max_volatile_write(inode)		do { } while (0)
+#define stat_inc_seg_type(sbi, curseg)			do { } while (0)
+#define stat_inc_block_count(sbi, curseg)		do { } while (0)
+#define stat_inc_inplace_blocks(sbi)			do { } while (0)
+#define stat_inc_seg_count(sbi, type, gc_type)		do { } while (0)
+#define stat_inc_tot_blk_count(si, blks)		do { } while (0)
+#define stat_inc_data_blk_count(sbi, blks, gc_type)	do { } while (0)
+#define stat_inc_node_blk_count(sbi, blks, gc_type)	do { } while (0)
 
 static inline int f2fs_build_stats(struct f2fs_sb_info *sbi) { return 0; }
 static inline void f2fs_destroy_stats(struct f2fs_sb_info *sbi) { }
@@ -2387,53 +2659,79 @@ extern struct kmem_cache *inode_entry_slab;
 /*
  * inline.c
  */
-bool f2fs_may_inline_data(struct inode *);
-bool f2fs_may_inline_dentry(struct inode *);
-void read_inline_data(struct page *, struct page *);
-bool truncate_inline_inode(struct page *, u64);
-int f2fs_read_inline_data(struct inode *, struct page *);
-int f2fs_convert_inline_page(struct dnode_of_data *, struct page *);
-int f2fs_convert_inline_inode(struct inode *);
-int f2fs_write_inline_data(struct inode *, struct page *);
-bool recover_inline_data(struct inode *, struct page *);
-struct f2fs_dir_entry *find_in_inline_dir(struct inode *,
-				struct fscrypt_name *, struct page **);
-int make_empty_inline_dir(struct inode *inode, struct inode *, struct page *);
-int f2fs_add_inline_entry(struct inode *, const struct qstr *,
-		const struct qstr *, struct inode *, nid_t, umode_t);
-void f2fs_delete_inline_entry(struct f2fs_dir_entry *, struct page *,
-						struct inode *, struct inode *);
-bool f2fs_empty_inline_dir(struct inode *);
-int f2fs_read_inline_dir(struct file *, struct dir_context *,
-						struct fscrypt_str *);
-int f2fs_inline_data_fiemap(struct inode *,
-		struct fiemap_extent_info *, __u64, __u64);
+bool f2fs_may_inline_data(struct inode *inode);
+bool f2fs_may_inline_dentry(struct inode *inode);
+void read_inline_data(struct page *page, struct page *ipage);
+void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from);
+int f2fs_read_inline_data(struct inode *inode, struct page *page);
+int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page);
+int f2fs_convert_inline_inode(struct inode *inode);
+int f2fs_write_inline_data(struct inode *inode, struct page *page);
+bool recover_inline_data(struct inode *inode, struct page *npage);
+struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
+			struct fscrypt_name *fname, struct page **res_page);
+int make_empty_inline_dir(struct inode *inode, struct inode *parent,
+			struct page *ipage);
+int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
+			const struct qstr *orig_name,
+			struct inode *inode, nid_t ino, umode_t mode);
+void f2fs_delete_inline_entry(struct f2fs_dir_entry *dentry, struct page *page,
+			struct inode *dir, struct inode *inode);
+bool f2fs_empty_inline_dir(struct inode *dir);
+int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
+			struct fscrypt_str *fstr);
+int f2fs_inline_data_fiemap(struct inode *inode,
+			struct fiemap_extent_info *fieinfo,
+			__u64 start, __u64 len);
 
 /*
  * shrinker.c
  */
-unsigned long f2fs_shrink_count(struct shrinker *, struct shrink_control *);
-unsigned long f2fs_shrink_scan(struct shrinker *, struct shrink_control *);
-void f2fs_join_shrinker(struct f2fs_sb_info *);
-void f2fs_leave_shrinker(struct f2fs_sb_info *);
+unsigned long f2fs_shrink_count(struct shrinker *shrink,
+			struct shrink_control *sc);
+unsigned long f2fs_shrink_scan(struct shrinker *shrink,
+			struct shrink_control *sc);
+void f2fs_join_shrinker(struct f2fs_sb_info *sbi);
+void f2fs_leave_shrinker(struct f2fs_sb_info *sbi);
 
 /*
  * extent_cache.c
  */
-unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *, int);
-bool f2fs_init_extent_tree(struct inode *, struct f2fs_extent *);
-void f2fs_drop_extent_tree(struct inode *);
-unsigned int f2fs_destroy_extent_node(struct inode *);
-void f2fs_destroy_extent_tree(struct inode *);
-bool f2fs_lookup_extent_cache(struct inode *, pgoff_t, struct extent_info *);
-void f2fs_update_extent_cache(struct dnode_of_data *);
+struct rb_entry *__lookup_rb_tree(struct rb_root *root,
+				struct rb_entry *cached_re, unsigned int ofs);
+struct rb_node **__lookup_rb_tree_for_insert(struct f2fs_sb_info *sbi,
+				struct rb_root *root, struct rb_node **parent,
+				unsigned int ofs);
+struct rb_entry *__lookup_rb_tree_ret(struct rb_root *root,
+		struct rb_entry *cached_re, unsigned int ofs,
+		struct rb_entry **prev_entry, struct rb_entry **next_entry,
+		struct rb_node ***insert_p, struct rb_node **insert_parent,
+		bool force);
+bool __check_rb_tree_consistence(struct f2fs_sb_info *sbi,
+						struct rb_root *root);
+unsigned int f2fs_shrink_extent_tree(struct f2fs_sb_info *sbi, int nr_shrink);
+bool f2fs_init_extent_tree(struct inode *inode, struct f2fs_extent *i_ext);
+void f2fs_drop_extent_tree(struct inode *inode);
+unsigned int f2fs_destroy_extent_node(struct inode *inode);
+void f2fs_destroy_extent_tree(struct inode *inode);
+bool f2fs_lookup_extent_cache(struct inode *inode, pgoff_t pgofs,
+			struct extent_info *ei);
+void f2fs_update_extent_cache(struct dnode_of_data *dn);
 void f2fs_update_extent_cache_range(struct dnode_of_data *dn,
-						pgoff_t, block_t, unsigned int);
-void init_extent_cache_info(struct f2fs_sb_info *);
+			pgoff_t fofs, block_t blkaddr, unsigned int len);
+void init_extent_cache_info(struct f2fs_sb_info *sbi);
 int __init create_extent_cache(void);
 void destroy_extent_cache(void);
 
 /*
+ * sysfs.c
+ */
+int __init f2fs_register_sysfs(void);
+void f2fs_unregister_sysfs(void);
+int f2fs_init_sysfs(struct f2fs_sb_info *sbi);
+void f2fs_exit_sysfs(struct f2fs_sb_info *sbi);
+
+/*
  * crypto support
  */
 static inline bool f2fs_encrypted_inode(struct inode *inode)
@@ -2510,28 +2808,4 @@ static inline bool f2fs_may_encrypt(struct inode *inode)
 #endif
 }
 
-#ifndef CONFIG_F2FS_FS_ENCRYPTION
-#define fscrypt_set_d_op(i)
-#define fscrypt_get_ctx			fscrypt_notsupp_get_ctx
-#define fscrypt_release_ctx		fscrypt_notsupp_release_ctx
-#define fscrypt_encrypt_page		fscrypt_notsupp_encrypt_page
-#define fscrypt_decrypt_page		fscrypt_notsupp_decrypt_page
-#define fscrypt_decrypt_bio_pages	fscrypt_notsupp_decrypt_bio_pages
-#define fscrypt_pullback_bio_page	fscrypt_notsupp_pullback_bio_page
-#define fscrypt_restore_control_page	fscrypt_notsupp_restore_control_page
-#define fscrypt_zeroout_range		fscrypt_notsupp_zeroout_range
-#define fscrypt_ioctl_set_policy	fscrypt_notsupp_ioctl_set_policy
-#define fscrypt_ioctl_get_policy	fscrypt_notsupp_ioctl_get_policy
-#define fscrypt_has_permitted_context	fscrypt_notsupp_has_permitted_context
-#define fscrypt_inherit_context		fscrypt_notsupp_inherit_context
-#define fscrypt_get_encryption_info	fscrypt_notsupp_get_encryption_info
-#define fscrypt_put_encryption_info	fscrypt_notsupp_put_encryption_info
-#define fscrypt_setup_filename		fscrypt_notsupp_setup_filename
-#define fscrypt_free_filename		fscrypt_notsupp_free_filename
-#define fscrypt_fname_encrypted_size	fscrypt_notsupp_fname_encrypted_size
-#define fscrypt_fname_alloc_buffer	fscrypt_notsupp_fname_alloc_buffer
-#define fscrypt_fname_free_buffer	fscrypt_notsupp_fname_free_buffer
-#define fscrypt_fname_disk_to_usr	fscrypt_notsupp_fname_disk_to_usr
-#define fscrypt_fname_usr_to_disk	fscrypt_notsupp_fname_usr_to_disk
-#endif
 #endif
diff --git a/fs/f2fs/file.c b/fs/f2fs/file.c
index 49f10dce817d..2706130c261b 100644
--- a/fs/f2fs/file.c
+++ b/fs/f2fs/file.c
@@ -20,6 +20,7 @@
 #include <linux/uaccess.h>
 #include <linux/mount.h>
 #include <linux/pagevec.h>
+#include <linux/uio.h>
 #include <linux/uuid.h>
 #include <linux/file.h>
 
@@ -32,11 +33,22 @@
 #include "trace.h"
 #include <trace/events/f2fs.h>
 
-static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
-						struct vm_fault *vmf)
+static int f2fs_filemap_fault(struct vm_fault *vmf)
+{
+	struct inode *inode = file_inode(vmf->vma->vm_file);
+	int err;
+
+	down_read(&F2FS_I(inode)->i_mmap_sem);
+	err = filemap_fault(vmf);
+	up_read(&F2FS_I(inode)->i_mmap_sem);
+
+	return err;
+}
+
+static int f2fs_vm_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct dnode_of_data dn;
 	int err;
@@ -58,14 +70,15 @@ static int f2fs_vm_page_mkwrite(struct vm_area_struct *vma,
 
 	f2fs_balance_fs(sbi, dn.node_changed);
 
-	file_update_time(vma->vm_file);
+	file_update_time(vmf->vma->vm_file);
+	down_read(&F2FS_I(inode)->i_mmap_sem);
 	lock_page(page);
 	if (unlikely(page->mapping != inode->i_mapping ||
 			page_offset(page) > i_size_read(inode) ||
 			!PageUptodate(page))) {
 		unlock_page(page);
 		err = -EFAULT;
-		goto out;
+		goto out_sem;
 	}
 
 	/*
@@ -94,6 +107,8 @@ mapped:
 	if (f2fs_encrypted_inode(inode) && S_ISREG(inode->i_mode))
 		f2fs_wait_on_encrypted_page_writeback(sbi, dn.data_blkaddr);
 
+out_sem:
+	up_read(&F2FS_I(inode)->i_mmap_sem);
 out:
 	sb_end_pagefault(inode->i_sb);
 	f2fs_update_time(sbi, REQ_TIME);
@@ -101,7 +116,7 @@ out:
 }
 
 static const struct vm_operations_struct f2fs_file_vm_ops = {
-	.fault		= filemap_fault,
+	.fault		= f2fs_filemap_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= f2fs_vm_page_mkwrite,
 };
@@ -116,11 +131,6 @@ static int get_parent_ino(struct inode *inode, nid_t *pino)
 	if (!dentry)
 		return 0;
 
-	if (update_dent_inode(inode, inode, &dentry->d_name)) {
-		dput(dentry);
-		return 0;
-	}
-
 	*pino = parent_ino(dentry);
 	dput(dentry);
 	return 1;
@@ -141,8 +151,6 @@ static inline bool need_do_checkpoint(struct inode *inode)
 		need_cp = true;
 	else if (!is_checkpointed_node(sbi, F2FS_I(inode)->i_pino))
 		need_cp = true;
-	else if (F2FS_I(inode)->xattr_ver == cur_cp_version(F2FS_CKPT(sbi)))
-		need_cp = true;
 	else if (test_opt(sbi, FASTBOOT))
 		need_cp = true;
 	else if (sbi->active_logs == 2)
@@ -168,7 +176,6 @@ static void try_to_fix_pino(struct inode *inode)
 	nid_t pino;
 
 	down_write(&fi->i_sem);
-	fi->xattr_ver = 0;
 	if (file_wrong_pino(inode) && inode->i_nlink == 1 &&
 			get_parent_ino(inode, &pino)) {
 		f2fs_i_pino_write(inode, pino);
@@ -277,7 +284,8 @@ sync_nodes:
 flush_out:
 	remove_ino_entry(sbi, ino, UPDATE_INO);
 	clear_inode_flag(inode, FI_UPDATE_WRITE);
-	ret = f2fs_issue_flush(sbi);
+	if (!atomic)
+		ret = f2fs_issue_flush(sbi);
 	f2fs_update_time(sbi, REQ_TIME);
 out:
 	trace_f2fs_sync_file_exit(inode, need_cp, datasync, ret);
@@ -422,14 +430,6 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	struct inode *inode = file_inode(file);
 	int err;
 
-	if (f2fs_encrypted_inode(inode)) {
-		err = fscrypt_get_encryption_info(inode);
-		if (err)
-			return 0;
-		if (!f2fs_encrypted_inode(inode))
-			return -ENOKEY;
-	}
-
 	/* we don't need to use inline_data strictly */
 	err = f2fs_convert_inline_inode(inode);
 	if (err)
@@ -442,11 +442,10 @@ static int f2fs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 static int f2fs_file_open(struct inode *inode, struct file *filp)
 {
-	int ret = generic_file_open(inode, filp);
 	struct dentry *dir;
 
-	if (!ret && f2fs_encrypted_inode(inode)) {
-		ret = fscrypt_get_encryption_info(inode);
+	if (f2fs_encrypted_inode(inode)) {
+		int ret = fscrypt_get_encryption_info(inode);
 		if (ret)
 			return -EACCES;
 		if (!fscrypt_has_encryption_key(inode))
@@ -459,7 +458,7 @@ static int f2fs_file_open(struct inode *inode, struct file *filp)
 		return -EPERM;
 	}
 	dput(dir);
-	return ret;
+	return dquot_file_open(inode, filp);
 }
 
 int truncate_data_blocks_range(struct dnode_of_data *dn, int count)
@@ -530,12 +529,14 @@ static int truncate_partial_data_page(struct inode *inode, u64 from,
 
 	page = get_lock_data_page(inode, index, true);
 	if (IS_ERR(page))
-		return 0;
+		return PTR_ERR(page) == -ENOENT ? 0 : PTR_ERR(page);
 truncate_out:
 	f2fs_wait_on_page_writeback(page, DATA, true);
 	zero_user(page, offset, PAGE_SIZE - offset);
-	if (!cache_only || !f2fs_encrypted_inode(inode) ||
-					!S_ISREG(inode->i_mode))
+
+	/* An encrypted inode should have a key and truncate the last page. */
+	f2fs_bug_on(F2FS_I_SB(inode), cache_only && f2fs_encrypted_inode(inode));
+	if (!cache_only)
 		set_page_dirty(page);
 	f2fs_put_page(page, 1);
 	return 0;
@@ -568,8 +569,7 @@ int truncate_blocks(struct inode *inode, u64 from, bool lock)
 	}
 
 	if (f2fs_has_inline_data(inode)) {
-		if (truncate_inline_inode(ipage, from))
-			set_page_dirty(ipage);
+		truncate_inline_inode(inode, ipage, from);
 		f2fs_put_page(ipage, 1);
 		truncate_page = true;
 		goto out;
@@ -618,6 +618,12 @@ int f2fs_truncate(struct inode *inode)
 
 	trace_f2fs_truncate(inode);
 
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(F2FS_I_SB(inode), FAULT_TRUNCATE)) {
+		f2fs_show_injection_info(FAULT_TRUNCATE);
+		return -EIO;
+	}
+#endif
 	/* we should check inline_data size */
 	if (!f2fs_may_inline_data(inode)) {
 		err = f2fs_convert_inline_inode(inode);
@@ -634,12 +640,32 @@ int f2fs_truncate(struct inode *inode)
 	return 0;
 }
 
-int f2fs_getattr(struct vfsmount *mnt,
-			 struct dentry *dentry, struct kstat *stat)
+int f2fs_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	unsigned int flags;
+
+	flags = fi->i_flags & FS_FL_USER_VISIBLE;
+	if (flags & FS_APPEND_FL)
+		stat->attributes |= STATX_ATTR_APPEND;
+	if (flags & FS_COMPR_FL)
+		stat->attributes |= STATX_ATTR_COMPRESSED;
+	if (f2fs_encrypted_inode(inode))
+		stat->attributes |= STATX_ATTR_ENCRYPTED;
+	if (flags & FS_IMMUTABLE_FL)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+	if (flags & FS_NODUMP_FL)
+		stat->attributes |= STATX_ATTR_NODUMP;
+
+	stat->attributes_mask |= (STATX_ATTR_APPEND |
+				  STATX_ATTR_COMPRESSED |
+				  STATX_ATTR_ENCRYPTED |
+				  STATX_ATTR_IMMUTABLE |
+				  STATX_ATTR_NODUMP);
+
 	generic_fillattr(inode, stat);
-	stat->blocks <<= 3;
 	return 0;
 }
 
@@ -683,14 +709,34 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 	if (err)
 		return err;
 
+	if (is_quota_modification(inode, attr)) {
+		err = dquot_initialize(inode);
+		if (err)
+			return err;
+	}
+	if ((attr->ia_valid & ATTR_UID &&
+		!uid_eq(attr->ia_uid, inode->i_uid)) ||
+		(attr->ia_valid & ATTR_GID &&
+		!gid_eq(attr->ia_gid, inode->i_gid))) {
+		err = dquot_transfer(inode, attr);
+		if (err)
+			return err;
+	}
+
 	if (attr->ia_valid & ATTR_SIZE) {
-		if (f2fs_encrypted_inode(inode) &&
-				fscrypt_get_encryption_info(inode))
-			return -EACCES;
+		if (f2fs_encrypted_inode(inode)) {
+			err = fscrypt_get_encryption_info(inode);
+			if (err)
+				return err;
+			if (!fscrypt_has_encryption_key(inode))
+				return -ENOKEY;
+		}
 
 		if (attr->ia_size <= i_size_read(inode)) {
+			down_write(&F2FS_I(inode)->i_mmap_sem);
 			truncate_setsize(inode, attr->ia_size);
 			err = f2fs_truncate(inode);
+			up_write(&F2FS_I(inode)->i_mmap_sem);
 			if (err)
 				return err;
 		} else {
@@ -698,7 +744,9 @@ int f2fs_setattr(struct dentry *dentry, struct iattr *attr)
 			 * do not trim all blocks after i_size if target size is
 			 * larger than i_size.
 			 */
+			down_write(&F2FS_I(inode)->i_mmap_sem);
 			truncate_setsize(inode, attr->ia_size);
+			up_write(&F2FS_I(inode)->i_mmap_sem);
 
 			/* should convert inline inode here */
 			if (!f2fs_may_inline_data(inode)) {
@@ -841,12 +889,14 @@ static int punch_hole(struct inode *inode, loff_t offset, loff_t len)
 
 			blk_start = (loff_t)pg_start << PAGE_SHIFT;
 			blk_end = (loff_t)pg_end << PAGE_SHIFT;
+			down_write(&F2FS_I(inode)->i_mmap_sem);
 			truncate_inode_pages_range(mapping, blk_start,
 					blk_end - 1);
 
 			f2fs_lock_op(sbi);
 			ret = truncate_hole(inode, pg_start, pg_end);
 			f2fs_unlock_op(sbi);
+			up_write(&F2FS_I(inode)->i_mmap_sem);
 		}
 	}
 
@@ -959,9 +1009,9 @@ static int __clone_blkaddrs(struct inode *src_inode, struct inode *dst_inode,
 
 				if (do_replace[i]) {
 					f2fs_i_blocks_write(src_inode,
-								1, false);
+							1, false, false);
 					f2fs_i_blocks_write(dst_inode,
-								1, true);
+							1, true, false);
 					f2fs_replace_block(sbi, &dn, dn.data_blkaddr,
 					blkaddr[i], ni.version, true, false);
 
@@ -1013,11 +1063,11 @@ static int __exchange_data_block(struct inode *src_inode,
 	while (len) {
 		olen = min((pgoff_t)4 * ADDRS_PER_BLOCK, len);
 
-		src_blkaddr = f2fs_kvzalloc(sizeof(block_t) * olen, GFP_KERNEL);
+		src_blkaddr = kvzalloc(sizeof(block_t) * olen, GFP_KERNEL);
 		if (!src_blkaddr)
 			return -ENOMEM;
 
-		do_replace = f2fs_kvzalloc(sizeof(int) * olen, GFP_KERNEL);
+		do_replace = kvzalloc(sizeof(int) * olen, GFP_KERNEL);
 		if (!do_replace) {
 			kvfree(src_blkaddr);
 			return -ENOMEM;
@@ -1085,16 +1135,17 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	pg_start = offset >> PAGE_SHIFT;
 	pg_end = (offset + len) >> PAGE_SHIFT;
 
+	down_write(&F2FS_I(inode)->i_mmap_sem);
 	/* write out all dirty pages from offset */
 	ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
 	if (ret)
-		return ret;
+		goto out;
 
 	truncate_pagecache(inode, offset);
 
 	ret = f2fs_do_collapse(inode, pg_start, pg_end);
 	if (ret)
-		return ret;
+		goto out;
 
 	/* write out all moved pages, if possible */
 	filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
@@ -1107,6 +1158,8 @@ static int f2fs_collapse_range(struct inode *inode, loff_t offset, loff_t len)
 	if (!ret)
 		f2fs_i_size_write(inode, new_size);
 
+out:
+	up_write(&F2FS_I(inode)->i_mmap_sem);
 	return ret;
 }
 
@@ -1171,9 +1224,10 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 	if (ret)
 		return ret;
 
+	down_write(&F2FS_I(inode)->i_mmap_sem);
 	ret = filemap_write_and_wait_range(mapping, offset, offset + len - 1);
 	if (ret)
-		return ret;
+		goto out_sem;
 
 	truncate_pagecache_range(inode, offset, offset + len - 1);
 
@@ -1187,17 +1241,15 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 		ret = fill_zero(inode, pg_start, off_start,
 						off_end - off_start);
 		if (ret)
-			return ret;
+			goto out_sem;
 
-		if (offset + len > new_size)
-			new_size = offset + len;
 		new_size = max_t(loff_t, new_size, offset + len);
 	} else {
 		if (off_start) {
 			ret = fill_zero(inode, pg_start++, off_start,
 						PAGE_SIZE - off_start);
 			if (ret)
-				return ret;
+				goto out_sem;
 
 			new_size = max_t(loff_t, new_size,
 					(loff_t)pg_start << PAGE_SHIFT);
@@ -1246,6 +1298,8 @@ static int f2fs_zero_range(struct inode *inode, loff_t offset, loff_t len,
 out:
 	if (!(mode & FALLOC_FL_KEEP_SIZE) && i_size_read(inode) < new_size)
 		f2fs_i_size_write(inode, new_size);
+out_sem:
+	up_write(&F2FS_I(inode)->i_mmap_sem);
 
 	return ret;
 }
@@ -1258,8 +1312,9 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 	int ret = 0;
 
 	new_size = i_size_read(inode) + len;
-	if (new_size > inode->i_sb->s_maxbytes)
-		return -EFBIG;
+	ret = inode_newsize_ok(inode, new_size);
+	if (ret)
+		return ret;
 
 	if (offset >= i_size_read(inode))
 		return -EINVAL;
@@ -1274,14 +1329,15 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 	f2fs_balance_fs(sbi, true);
 
+	down_write(&F2FS_I(inode)->i_mmap_sem);
 	ret = truncate_blocks(inode, i_size_read(inode), true);
 	if (ret)
-		return ret;
+		goto out;
 
 	/* write out all dirty pages from offset */
 	ret = filemap_write_and_wait_range(inode->i_mapping, offset, LLONG_MAX);
 	if (ret)
-		return ret;
+		goto out;
 
 	truncate_pagecache(inode, offset);
 
@@ -1310,6 +1366,8 @@ static int f2fs_insert_range(struct inode *inode, loff_t offset, loff_t len)
 
 	if (!ret)
 		f2fs_i_size_write(inode, new_size);
+out:
+	up_write(&F2FS_I(inode)->i_mmap_sem);
 	return ret;
 }
 
@@ -1429,6 +1487,7 @@ static int f2fs_release_file(struct inode *inode, struct file *filp)
 		drop_inmem_pages(inode);
 	if (f2fs_is_volatile_file(inode)) {
 		clear_inode_flag(inode, FI_VOLATILE_FILE);
+		stat_dec_volatile_write(inode);
 		set_inode_flag(inode, FI_DROP_CACHE);
 		filemap_fdatawrite(inode->i_mapping);
 		clear_inode_flag(inode, FI_DROP_CACHE);
@@ -1475,28 +1534,34 @@ static int f2fs_ioc_setflags(struct file *filp, unsigned long arg)
 	if (ret)
 		return ret;
 
-	flags = f2fs_mask_flags(inode->i_mode, flags);
-
 	inode_lock(inode);
 
+	/* Is it quota file? Do not allow user to mess with it */
+	if (IS_NOQUOTA(inode)) {
+		ret = -EPERM;
+		goto unlock_out;
+	}
+
+	flags = f2fs_mask_flags(inode->i_mode, flags);
+
 	oldflags = fi->i_flags;
 
 	if ((flags ^ oldflags) & (FS_APPEND_FL | FS_IMMUTABLE_FL)) {
 		if (!capable(CAP_LINUX_IMMUTABLE)) {
-			inode_unlock(inode);
 			ret = -EPERM;
-			goto out;
+			goto unlock_out;
 		}
 	}
 
 	flags = flags & FS_FL_USER_MODIFIABLE;
 	flags |= oldflags & ~FS_FL_USER_MODIFIABLE;
 	fi->i_flags = flags;
-	inode_unlock(inode);
 
 	inode->i_ctime = current_time(inode);
 	f2fs_set_inode_flags(inode);
-out:
+	f2fs_mark_inode_dirty_sync(inode, false);
+unlock_out:
+	inode_unlock(inode);
 	mnt_drop_write_file(filp);
 	return ret;
 }
@@ -1516,6 +1581,9 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
+	if (!S_ISREG(inode->i_mode))
+		return -EINVAL;
+
 	ret = mnt_want_write_file(filp);
 	if (ret)
 		return ret;
@@ -1530,17 +1598,24 @@ static int f2fs_ioc_start_atomic_write(struct file *filp)
 		goto out;
 
 	set_inode_flag(inode, FI_ATOMIC_FILE);
+	set_inode_flag(inode, FI_HOT_DATA);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 
 	if (!get_dirty_pages(inode))
-		goto out;
+		goto inc_stat;
 
 	f2fs_msg(F2FS_I_SB(inode)->sb, KERN_WARNING,
 		"Unexpected flush for atomic writes: ino=%lu, npages=%u",
 					inode->i_ino, get_dirty_pages(inode));
 	ret = filemap_write_and_wait_range(inode->i_mapping, 0, LLONG_MAX);
-	if (ret)
+	if (ret) {
 		clear_inode_flag(inode, FI_ATOMIC_FILE);
+		goto out;
+	}
+
+inc_stat:
+	stat_inc_atomic_write(inode);
+	stat_update_max_atomic_write(inode);
 out:
 	inode_unlock(inode);
 	mnt_drop_write_file(filp);
@@ -1565,15 +1640,18 @@ static int f2fs_ioc_commit_atomic_write(struct file *filp)
 		goto err_out;
 
 	if (f2fs_is_atomic_file(inode)) {
-		clear_inode_flag(inode, FI_ATOMIC_FILE);
 		ret = commit_inmem_pages(inode);
-		if (ret) {
-			set_inode_flag(inode, FI_ATOMIC_FILE);
+		if (ret)
 			goto err_out;
+
+		ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
+		if (!ret) {
+			clear_inode_flag(inode, FI_ATOMIC_FILE);
+			stat_dec_atomic_write(inode);
 		}
+	} else {
+		ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
 	}
-
-	ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
 err_out:
 	inode_unlock(inode);
 	mnt_drop_write_file(filp);
@@ -1588,6 +1666,9 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
 	if (!inode_owner_or_capable(inode))
 		return -EACCES;
 
+	if (!S_ISREG(inode->i_mode))
+		return -EINVAL;
+
 	ret = mnt_want_write_file(filp);
 	if (ret)
 		return ret;
@@ -1601,6 +1682,9 @@ static int f2fs_ioc_start_volatile_write(struct file *filp)
 	if (ret)
 		goto out;
 
+	stat_inc_volatile_write(inode);
+	stat_update_max_volatile_write(inode);
+
 	set_inode_flag(inode, FI_VOLATILE_FILE);
 	f2fs_update_time(F2FS_I_SB(inode), REQ_TIME);
 out:
@@ -1656,6 +1740,7 @@ static int f2fs_ioc_abort_volatile_write(struct file *filp)
 		drop_inmem_pages(inode);
 	if (f2fs_is_volatile_file(inode)) {
 		clear_inode_flag(inode, FI_VOLATILE_FILE);
+		stat_dec_volatile_write(inode);
 		ret = f2fs_do_sync_file(filp, 0, LLONG_MAX, 0, true);
 	}
 
@@ -1837,7 +1922,51 @@ static int f2fs_ioc_gc(struct file *filp, unsigned long arg)
 		mutex_lock(&sbi->gc_mutex);
 	}
 
-	ret = f2fs_gc(sbi, sync, true);
+	ret = f2fs_gc(sbi, sync, true, NULL_SEGNO);
+out:
+	mnt_drop_write_file(filp);
+	return ret;
+}
+
+static int f2fs_ioc_gc_range(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct f2fs_gc_range range;
+	u64 end;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (copy_from_user(&range, (struct f2fs_gc_range __user *)arg,
+							sizeof(range)))
+		return -EFAULT;
+
+	if (f2fs_readonly(sbi->sb))
+		return -EROFS;
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	end = range.start + range.len;
+	if (range.start < MAIN_BLKADDR(sbi) || end >= MAX_BLKADDR(sbi))
+		return -EINVAL;
+do_more:
+	if (!range.sync) {
+		if (!mutex_trylock(&sbi->gc_mutex)) {
+			ret = -EBUSY;
+			goto out;
+		}
+	} else {
+		mutex_lock(&sbi->gc_mutex);
+	}
+
+	ret = f2fs_gc(sbi, range.sync, true, GET_SEGNO(sbi, range.start));
+	range.start += sbi->blocks_per_seg;
+	if (range.start <= end)
+		goto do_more;
 out:
 	mnt_drop_write_file(filp);
 	return ret;
@@ -1871,17 +2000,16 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
 {
 	struct inode *inode = file_inode(filp);
 	struct f2fs_map_blocks map = { .m_next_pgofs = NULL };
-	struct extent_info ei;
+	struct extent_info ei = {0,0,0};
 	pgoff_t pg_start, pg_end;
 	unsigned int blk_per_seg = sbi->blocks_per_seg;
 	unsigned int total = 0, sec_num;
-	unsigned int pages_per_sec = sbi->segs_per_sec * blk_per_seg;
 	block_t blk_end = 0;
 	bool fragmented = false;
 	int err;
 
 	/* if in-place-update policy is enabled, don't waste time here */
-	if (need_inplace_update(inode))
+	if (need_inplace_update_policy(inode, NULL))
 		return -EINVAL;
 
 	pg_start = range->start >> PAGE_SHIFT;
@@ -1939,7 +2067,7 @@ static int f2fs_defragment_range(struct f2fs_sb_info *sbi,
 	map.m_lblk = pg_start;
 	map.m_len = pg_end - pg_start;
 
-	sec_num = (map.m_len + pages_per_sec - 1) / pages_per_sec;
+	sec_num = (map.m_len + BLKS_PER_SEC(sbi) - 1) / BLKS_PER_SEC(sbi);
 
 	/*
 	 * make sure there are enough free section for LFS allocation, this can
@@ -2016,42 +2144,40 @@ static int f2fs_ioc_defragment(struct file *filp, unsigned long arg)
 	if (!capable(CAP_SYS_ADMIN))
 		return -EPERM;
 
-	if (!S_ISREG(inode->i_mode))
+	if (!S_ISREG(inode->i_mode) || f2fs_is_atomic_file(inode))
 		return -EINVAL;
 
-	err = mnt_want_write_file(filp);
-	if (err)
-		return err;
-
-	if (f2fs_readonly(sbi->sb)) {
-		err = -EROFS;
-		goto out;
-	}
+	if (f2fs_readonly(sbi->sb))
+		return -EROFS;
 
 	if (copy_from_user(&range, (struct f2fs_defragment __user *)arg,
-							sizeof(range))) {
-		err = -EFAULT;
-		goto out;
-	}
+							sizeof(range)))
+		return -EFAULT;
 
 	/* verify alignment of offset & size */
-	if (range.start & (F2FS_BLKSIZE - 1) ||
-		range.len & (F2FS_BLKSIZE - 1)) {
-		err = -EINVAL;
-		goto out;
-	}
+	if (range.start & (F2FS_BLKSIZE - 1) || range.len & (F2FS_BLKSIZE - 1))
+		return -EINVAL;
+
+	if (unlikely((range.start + range.len) >> PAGE_SHIFT >
+					sbi->max_file_blocks))
+		return -EINVAL;
+
+	err = mnt_want_write_file(filp);
+	if (err)
+		return err;
 
 	err = f2fs_defragment_range(sbi, filp, &range);
+	mnt_drop_write_file(filp);
+
 	f2fs_update_time(sbi, REQ_TIME);
 	if (err < 0)
-		goto out;
+		return err;
 
 	if (copy_to_user((struct f2fs_defragment __user *)arg, &range,
 							sizeof(range)))
-		err = -EFAULT;
-out:
-	mnt_drop_write_file(filp);
-	return err;
+		return -EFAULT;
+
+	return 0;
 }
 
 static int f2fs_move_file_range(struct file *file_in, loff_t pos_in,
@@ -2185,6 +2311,8 @@ static int f2fs_ioc_move_range(struct file *filp, unsigned long arg)
 					range.pos_out, range.len);
 
 	mnt_drop_write_file(filp);
+	if (err)
+		goto err_out;
 
 	if (copy_to_user((struct f2fs_move_range __user *)arg,
 						&range, sizeof(range)))
@@ -2194,6 +2322,69 @@ err_out:
 	return err;
 }
 
+static int f2fs_ioc_flush_device(struct file *filp, unsigned long arg)
+{
+	struct inode *inode = file_inode(filp);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct sit_info *sm = SIT_I(sbi);
+	unsigned int start_segno = 0, end_segno = 0;
+	unsigned int dev_start_segno = 0, dev_end_segno = 0;
+	struct f2fs_flush_device range;
+	int ret;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	if (f2fs_readonly(sbi->sb))
+		return -EROFS;
+
+	if (copy_from_user(&range, (struct f2fs_flush_device __user *)arg,
+							sizeof(range)))
+		return -EFAULT;
+
+	if (sbi->s_ndevs <= 1 || sbi->s_ndevs - 1 <= range.dev_num ||
+			sbi->segs_per_sec != 1) {
+		f2fs_msg(sbi->sb, KERN_WARNING,
+			"Can't flush %u in %d for segs_per_sec %u != 1\n",
+				range.dev_num, sbi->s_ndevs,
+				sbi->segs_per_sec);
+		return -EINVAL;
+	}
+
+	ret = mnt_want_write_file(filp);
+	if (ret)
+		return ret;
+
+	if (range.dev_num != 0)
+		dev_start_segno = GET_SEGNO(sbi, FDEV(range.dev_num).start_blk);
+	dev_end_segno = GET_SEGNO(sbi, FDEV(range.dev_num).end_blk);
+
+	start_segno = sm->last_victim[FLUSH_DEVICE];
+	if (start_segno < dev_start_segno || start_segno >= dev_end_segno)
+		start_segno = dev_start_segno;
+	end_segno = min(start_segno + range.segments, dev_end_segno);
+
+	while (start_segno < end_segno) {
+		if (!mutex_trylock(&sbi->gc_mutex)) {
+			ret = -EBUSY;
+			goto out;
+		}
+		sm->last_victim[GC_CB] = end_segno + 1;
+		sm->last_victim[GC_GREEDY] = end_segno + 1;
+		sm->last_victim[ALLOC_NEXT] = end_segno + 1;
+		ret = f2fs_gc(sbi, true, true, start_segno);
+		if (ret == -EAGAIN)
+			ret = 0;
+		else if (ret < 0)
+			break;
+		start_segno++;
+	}
+out:
+	mnt_drop_write_file(filp);
+	return ret;
+}
+
+
 long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	switch (cmd) {
@@ -2225,12 +2416,16 @@ long f2fs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		return f2fs_ioc_get_encryption_pwsalt(filp, arg);
 	case F2FS_IOC_GARBAGE_COLLECT:
 		return f2fs_ioc_gc(filp, arg);
+	case F2FS_IOC_GARBAGE_COLLECT_RANGE:
+		return f2fs_ioc_gc_range(filp, arg);
 	case F2FS_IOC_WRITE_CHECKPOINT:
 		return f2fs_ioc_write_checkpoint(filp, arg);
 	case F2FS_IOC_DEFRAGMENT:
 		return f2fs_ioc_defragment(filp, arg);
 	case F2FS_IOC_MOVE_RANGE:
 		return f2fs_ioc_move_range(filp, arg);
+	case F2FS_IOC_FLUSH_DEVICE:
+		return f2fs_ioc_flush_device(filp, arg);
 	default:
 		return -ENOTTY;
 	}
@@ -2243,16 +2438,15 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 	struct blk_plug plug;
 	ssize_t ret;
 
-	if (f2fs_encrypted_inode(inode) &&
-				!fscrypt_has_encryption_key(inode) &&
-				fscrypt_get_encryption_info(inode))
-		return -EACCES;
-
 	inode_lock(inode);
 	ret = generic_write_checks(iocb, from);
 	if (ret > 0) {
-		int err = f2fs_preallocate_blocks(iocb, from);
+		int err;
+
+		if (iov_iter_fault_in_readable(from, iov_iter_count(from)))
+			set_inode_flag(inode, FI_NO_PREALLOC);
 
+		err = f2fs_preallocate_blocks(iocb, from);
 		if (err) {
 			inode_unlock(inode);
 			return err;
@@ -2260,6 +2454,7 @@ static ssize_t f2fs_file_write_iter(struct kiocb *iocb, struct iov_iter *from)
 		blk_start_plug(&plug);
 		ret = __generic_file_write_iter(iocb, from);
 		blk_finish_plug(&plug);
+		clear_inode_flag(inode, FI_NO_PREALLOC);
 	}
 	inode_unlock(inode);
 
@@ -2291,10 +2486,11 @@ long f2fs_compat_ioctl(struct file *file, unsigned int cmd, unsigned long arg)
 	case F2FS_IOC_GET_ENCRYPTION_PWSALT:
 	case F2FS_IOC_GET_ENCRYPTION_POLICY:
 	case F2FS_IOC_GARBAGE_COLLECT:
+	case F2FS_IOC_GARBAGE_COLLECT_RANGE:
 	case F2FS_IOC_WRITE_CHECKPOINT:
 	case F2FS_IOC_DEFRAGMENT:
-		break;
 	case F2FS_IOC_MOVE_RANGE:
+	case F2FS_IOC_FLUSH_DEVICE:
 		break;
 	default:
 		return -ENOIOCTLCMD;
diff --git a/fs/f2fs/gc.c b/fs/f2fs/gc.c
index 88bfc3dff496..fa3d2e2df8e7 100644
--- a/fs/f2fs/gc.c
+++ b/fs/f2fs/gc.c
@@ -32,13 +32,14 @@ static int gc_thread_func(void *data)
 
 	wait_ms = gc_th->min_sleep_time;
 
+	set_freezable();
 	do {
+		wait_event_interruptible_timeout(*wq,
+				kthread_should_stop() || freezing(current),
+				msecs_to_jiffies(wait_ms));
+
 		if (try_to_freeze())
 			continue;
-		else
-			wait_event_interruptible_timeout(*wq,
-						kthread_should_stop(),
-						msecs_to_jiffies(wait_ms));
 		if (kthread_should_stop())
 			break;
 
@@ -48,8 +49,10 @@ static int gc_thread_func(void *data)
 		}
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-		if (time_to_inject(sbi, FAULT_CHECKPOINT))
+		if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
+			f2fs_show_injection_info(FAULT_CHECKPOINT);
 			f2fs_stop_checkpoint(sbi, false);
+		}
 #endif
 
 		/*
@@ -82,7 +85,7 @@ static int gc_thread_func(void *data)
 		stat_inc_bggc_count(sbi);
 
 		/* if return value is not zero, no victim was selected */
-		if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC), true))
+		if (f2fs_gc(sbi, test_opt(sbi, FORCE_FG_GC), true, NULL_SEGNO))
 			wait_ms = gc_th->no_gc_sleep_time;
 
 		trace_f2fs_background_gc(sbi->sb, wait_ms,
@@ -166,10 +169,15 @@ static void select_policy(struct f2fs_sb_info *sbi, int gc_type,
 		p->ofs_unit = sbi->segs_per_sec;
 	}
 
-	if (p->max_search > sbi->max_victim_search)
+	/* we need to check every dirty segments in the FG_GC case */
+	if (gc_type != FG_GC && p->max_search > sbi->max_victim_search)
 		p->max_search = sbi->max_victim_search;
 
-	p->offset = sbi->last_victim[p->gc_mode];
+	/* let's select beginning hot/small space first */
+	if (type == CURSEG_HOT_DATA || IS_NODESEG(type))
+		p->offset = 0;
+	else
+		p->offset = SIT_I(sbi)->last_victim[p->gc_mode];
 }
 
 static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
@@ -179,7 +187,7 @@ static unsigned int get_max_cost(struct f2fs_sb_info *sbi,
 	if (p->alloc_mode == SSR)
 		return sbi->blocks_per_seg;
 	if (p->gc_mode == GC_GREEDY)
-		return sbi->blocks_per_seg * p->ofs_unit;
+		return 2 * sbi->blocks_per_seg * p->ofs_unit;
 	else if (p->gc_mode == GC_CB)
 		return UINT_MAX;
 	else /* No other gc_mode */
@@ -199,8 +207,12 @@ static unsigned int check_bg_victims(struct f2fs_sb_info *sbi)
 	for_each_set_bit(secno, dirty_i->victim_secmap, MAIN_SECS(sbi)) {
 		if (sec_usage_check(sbi, secno))
 			continue;
+
+		if (no_fggc_candidate(sbi, secno))
+			continue;
+
 		clear_bit(secno, dirty_i->victim_secmap);
-		return secno * sbi->segs_per_sec;
+		return GET_SEG_FROM_SEC(sbi, secno);
 	}
 	return NULL_SEGNO;
 }
@@ -208,8 +220,8 @@ static unsigned int check_bg_victims(struct f2fs_sb_info *sbi)
 static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
-	unsigned int secno = GET_SECNO(sbi, segno);
-	unsigned int start = secno * sbi->segs_per_sec;
+	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+	unsigned int start = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned long long mtime = 0;
 	unsigned int vblocks;
 	unsigned char age = 0;
@@ -218,7 +230,7 @@ static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno)
 
 	for (i = 0; i < sbi->segs_per_sec; i++)
 		mtime += get_seg_entry(sbi, start + i)->mtime;
-	vblocks = get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+	vblocks = get_valid_blocks(sbi, segno, true);
 
 	mtime = div_u64(mtime, sbi->segs_per_sec);
 	vblocks = div_u64(vblocks, sbi->segs_per_sec);
@@ -237,15 +249,34 @@ static unsigned int get_cb_cost(struct f2fs_sb_info *sbi, unsigned int segno)
 	return UINT_MAX - ((100 * (100 - u) * age) / (100 + u));
 }
 
+static unsigned int get_greedy_cost(struct f2fs_sb_info *sbi,
+						unsigned int segno)
+{
+	unsigned int valid_blocks =
+			get_valid_blocks(sbi, segno, true);
+
+	return IS_DATASEG(get_seg_entry(sbi, segno)->type) ?
+				valid_blocks * 2 : valid_blocks;
+}
+
+static unsigned int get_ssr_cost(struct f2fs_sb_info *sbi,
+						unsigned int segno)
+{
+	struct seg_entry *se = get_seg_entry(sbi, segno);
+
+	return se->ckpt_valid_blocks > se->valid_blocks ?
+				se->ckpt_valid_blocks : se->valid_blocks;
+}
+
 static inline unsigned int get_gc_cost(struct f2fs_sb_info *sbi,
 			unsigned int segno, struct victim_sel_policy *p)
 {
 	if (p->alloc_mode == SSR)
-		return get_seg_entry(sbi, segno)->ckpt_valid_blocks;
+		return get_ssr_cost(sbi, segno);
 
 	/* alloc_mode == LFS */
 	if (p->gc_mode == GC_GREEDY)
-		return get_valid_blocks(sbi, segno, sbi->segs_per_sec);
+		return get_greedy_cost(sbi, segno);
 	else
 		return get_cb_cost(sbi, segno);
 }
@@ -274,6 +305,7 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 		unsigned int *result, int gc_type, int type, char alloc_mode)
 {
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
+	struct sit_info *sm = SIT_I(sbi);
 	struct victim_sel_policy p;
 	unsigned int secno, last_victim;
 	unsigned int last_segment = MAIN_SEGS(sbi);
@@ -287,10 +319,18 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 	p.min_segno = NULL_SEGNO;
 	p.min_cost = get_max_cost(sbi, &p);
 
+	if (*result != NULL_SEGNO) {
+		if (IS_DATASEG(get_seg_entry(sbi, *result)->type) &&
+			get_valid_blocks(sbi, *result, false) &&
+			!sec_usage_check(sbi, GET_SEC_FROM_SEG(sbi, *result)))
+			p.min_segno = *result;
+		goto out;
+	}
+
 	if (p.max_search == 0)
 		goto out;
 
-	last_victim = sbi->last_victim[p.gc_mode];
+	last_victim = sm->last_victim[p.gc_mode];
 	if (p.alloc_mode == LFS && gc_type == FG_GC) {
 		p.min_segno = check_bg_victims(sbi);
 		if (p.min_segno != NULL_SEGNO)
@@ -303,9 +343,10 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 
 		segno = find_next_bit(p.dirty_segmap, last_segment, p.offset);
 		if (segno >= last_segment) {
-			if (sbi->last_victim[p.gc_mode]) {
-				last_segment = sbi->last_victim[p.gc_mode];
-				sbi->last_victim[p.gc_mode] = 0;
+			if (sm->last_victim[p.gc_mode]) {
+				last_segment =
+					sm->last_victim[p.gc_mode];
+				sm->last_victim[p.gc_mode] = 0;
 				p.offset = 0;
 				continue;
 			}
@@ -322,13 +363,15 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 			nsearched++;
 		}
 
-
-		secno = GET_SECNO(sbi, segno);
+		secno = GET_SEC_FROM_SEG(sbi, segno);
 
 		if (sec_usage_check(sbi, secno))
 			goto next;
 		if (gc_type == BG_GC && test_bit(secno, dirty_i->victim_secmap))
 			goto next;
+		if (gc_type == FG_GC && p.alloc_mode == LFS &&
+					no_fggc_candidate(sbi, secno))
+			goto next;
 
 		cost = get_gc_cost(sbi, segno, &p);
 
@@ -338,17 +381,18 @@ static int get_victim_by_default(struct f2fs_sb_info *sbi,
 		}
 next:
 		if (nsearched >= p.max_search) {
-			if (!sbi->last_victim[p.gc_mode] && segno <= last_victim)
-				sbi->last_victim[p.gc_mode] = last_victim + 1;
+			if (!sm->last_victim[p.gc_mode] && segno <= last_victim)
+				sm->last_victim[p.gc_mode] = last_victim + 1;
 			else
-				sbi->last_victim[p.gc_mode] = segno + 1;
+				sm->last_victim[p.gc_mode] = segno + 1;
+			sm->last_victim[p.gc_mode] %= MAIN_SEGS(sbi);
 			break;
 		}
 	}
 	if (p.min_segno != NULL_SEGNO) {
 got_it:
 		if (p.alloc_mode == LFS) {
-			secno = GET_SECNO(sbi, p.min_segno);
+			secno = GET_SEC_FROM_SEG(sbi, p.min_segno);
 			if (gc_type == FG_GC)
 				sbi->cur_victim_sec = secno;
 			else
@@ -531,8 +575,10 @@ static bool is_alive(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
 	get_node_info(sbi, nid, dni);
 
 	if (sum->version != dni->version) {
-		f2fs_put_page(node_page, 1);
-		return false;
+		f2fs_msg(sbi->sb, KERN_WARNING,
+				"%s: valid data with mismatched node version.",
+				__func__);
+		set_sbi_flag(sbi, SBI_NEED_FSCK);
 	}
 
 	*nofs = ofs_of_node(node_page);
@@ -550,9 +596,11 @@ static void move_encrypted_block(struct inode *inode, block_t bidx,
 	struct f2fs_io_info fio = {
 		.sbi = F2FS_I_SB(inode),
 		.type = DATA,
+		.temp = COLD,
 		.op = REQ_OP_READ,
 		.op_flags = 0,
 		.encrypted_page = NULL,
+		.in_list = false,
 	};
 	struct dnode_of_data dn;
 	struct f2fs_summary sum;
@@ -569,6 +617,9 @@ static void move_encrypted_block(struct inode *inode, block_t bidx,
 	if (!check_valid_map(F2FS_I_SB(inode), segno, off))
 		goto out;
 
+	if (f2fs_is_atomic_file(inode))
+		goto out;
+
 	set_new_dnode(&dn, inode, NULL, NULL, 0);
 	err = get_dnode_of_data(&dn, bidx, LOOKUP_NODE);
 	if (err)
@@ -593,7 +644,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx,
 	fio.new_blkaddr = fio.old_blkaddr = dn.data_blkaddr;
 
 	allocate_data_block(fio.sbi, NULL, fio.old_blkaddr, &newaddr,
-							&sum, CURSEG_COLD_DATA);
+					&sum, CURSEG_COLD_DATA, NULL, false);
 
 	fio.encrypted_page = pagecache_get_page(META_MAPPING(fio.sbi), newaddr,
 					FGP_LOCK | FGP_CREAT, GFP_NOFS);
@@ -631,7 +682,7 @@ static void move_encrypted_block(struct inode *inode, block_t bidx,
 	fio.op = REQ_OP_WRITE;
 	fio.op_flags = REQ_SYNC;
 	fio.new_blkaddr = newaddr;
-	f2fs_submit_page_mbio(&fio);
+	f2fs_submit_page_write(&fio);
 
 	f2fs_update_data_blkaddr(&dn, newaddr);
 	set_inode_flag(inode, FI_APPEND_WRITE);
@@ -661,6 +712,9 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type,
 	if (!check_valid_map(F2FS_I_SB(inode), segno, off))
 		goto out;
 
+	if (f2fs_is_atomic_file(inode))
+		goto out;
+
 	if (gc_type == BG_GC) {
 		if (PageWriteback(page))
 			goto out;
@@ -670,10 +724,13 @@ static void move_data_page(struct inode *inode, block_t bidx, int gc_type,
 		struct f2fs_io_info fio = {
 			.sbi = F2FS_I_SB(inode),
 			.type = DATA,
+			.temp = COLD,
 			.op = REQ_OP_WRITE,
 			.op_flags = REQ_SYNC,
+			.old_blkaddr = NULL_ADDR,
 			.page = page,
 			.encrypted_page = NULL,
+			.need_lock = LOCK_REQ,
 		};
 		bool is_dirty = PageDirty(page);
 		int err;
@@ -865,7 +922,7 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 					GET_SUM_BLOCK(sbi, segno));
 		f2fs_put_page(sum_page, 0);
 
-		if (get_valid_blocks(sbi, segno, 1) == 0 ||
+		if (get_valid_blocks(sbi, segno, false) == 0 ||
 				!PageUptodate(sum_page) ||
 				unlikely(f2fs_cp_error(sbi)))
 			goto next;
@@ -880,7 +937,6 @@ static int do_garbage_collect(struct f2fs_sb_info *sbi,
 		 *   - mutex_lock(sentry_lock)     - change_curseg()
 		 *                                  - lock_page(sum_page)
 		 */
-
 		if (type == SUM_TYPE_NODE)
 			gc_node_segment(sbi, sum->entries, segno, gc_type);
 		else
@@ -893,13 +949,13 @@ next:
 	}
 
 	if (gc_type == FG_GC)
-		f2fs_submit_merged_bio(sbi,
-				(type == SUM_TYPE_NODE) ? NODE : DATA, WRITE);
+		f2fs_submit_merged_write(sbi,
+				(type == SUM_TYPE_NODE) ? NODE : DATA);
 
 	blk_finish_plug(&plug);
 
 	if (gc_type == FG_GC &&
-		get_valid_blocks(sbi, start_segno, sbi->segs_per_sec) == 0)
+		get_valid_blocks(sbi, start_segno, true) == 0)
 		sec_freed = 1;
 
 	stat_inc_call_count(sbi->stat_info);
@@ -907,13 +963,14 @@ next:
 	return sec_freed;
 }
 
-int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background)
+int f2fs_gc(struct f2fs_sb_info *sbi, bool sync,
+			bool background, unsigned int segno)
 {
-	unsigned int segno;
 	int gc_type = sync ? FG_GC : BG_GC;
 	int sec_freed = 0;
-	int ret = -EINVAL;
+	int ret;
 	struct cp_control cpc;
+	unsigned int init_segno = segno;
 	struct gc_inode_list gc_list = {
 		.ilist = LIST_HEAD_INIT(gc_list.ilist),
 		.iroot = RADIX_TREE_INIT(GFP_NOFS),
@@ -921,39 +978,35 @@ int f2fs_gc(struct f2fs_sb_info *sbi, bool sync, bool background)
 
 	cpc.reason = __get_cp_reason(sbi);
 gc_more:
-	segno = NULL_SEGNO;
-
-	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE)))
+	if (unlikely(!(sbi->sb->s_flags & MS_ACTIVE))) {
+		ret = -EINVAL;
 		goto stop;
+	}
 	if (unlikely(f2fs_cp_error(sbi))) {
 		ret = -EIO;
 		goto stop;
 	}
 
-	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, sec_freed, 0)) {
-		gc_type = FG_GC;
+	if (gc_type == BG_GC && has_not_enough_free_secs(sbi, 0, 0)) {
 		/*
-		 * If there is no victim and no prefree segment but still not
-		 * enough free sections, we should flush dent/node blocks and do
-		 * garbage collections.
+		 * For example, if there are many prefree_segments below given
+		 * threshold, we can make them free by checkpoint. Then, we
+		 * secure free segments which doesn't need fggc any more.
 		 */
-		if (__get_victim(sbi, &segno, gc_type) ||
-						prefree_segments(sbi)) {
-			ret = write_checkpoint(sbi, &cpc);
-			if (ret)
-				goto stop;
-			segno = NULL_SEGNO;
-		} else if (has_not_enough_free_secs(sbi, 0, 0)) {
+		if (prefree_segments(sbi)) {
 			ret = write_checkpoint(sbi, &cpc);
 			if (ret)
 				goto stop;
 		}
-	} else if (gc_type == BG_GC && !background) {
-		/* f2fs_balance_fs doesn't need to do BG_GC in critical path. */
-		goto stop;
+		if (has_not_enough_free_secs(sbi, 0, 0))
+			gc_type = FG_GC;
 	}
 
-	if (segno == NULL_SEGNO && !__get_victim(sbi, &segno, gc_type))
+	ret = -EINVAL;
+	/* f2fs_balance_fs doesn't need to do BG_GC in critical path. */
+	if (gc_type == BG_GC && !background)
+		goto stop;
+	if (!__get_victim(sbi, &segno, gc_type))
 		goto stop;
 	ret = 0;
 
@@ -965,13 +1018,17 @@ gc_more:
 		sbi->cur_victim_sec = NULL_SEGNO;
 
 	if (!sync) {
-		if (has_not_enough_free_secs(sbi, sec_freed, 0))
+		if (has_not_enough_free_secs(sbi, sec_freed, 0)) {
+			segno = NULL_SEGNO;
 			goto gc_more;
+		}
 
 		if (gc_type == FG_GC)
 			ret = write_checkpoint(sbi, &cpc);
 	}
 stop:
+	SIT_I(sbi)->last_victim[ALLOC_NEXT] = 0;
+	SIT_I(sbi)->last_victim[FLUSH_DEVICE] = init_segno;
 	mutex_unlock(&sbi->gc_mutex);
 
 	put_gc_inode(&gc_list);
@@ -983,5 +1040,20 @@ stop:
 
 void build_gc_manager(struct f2fs_sb_info *sbi)
 {
+	u64 main_count, resv_count, ovp_count;
+
 	DIRTY_I(sbi)->v_ops = &default_v_ops;
+
+	/* threshold of # of valid blocks in a section for victims of FG_GC */
+	main_count = SM_I(sbi)->main_segments << sbi->log_blocks_per_seg;
+	resv_count = SM_I(sbi)->reserved_segments << sbi->log_blocks_per_seg;
+	ovp_count = SM_I(sbi)->ovp_segments << sbi->log_blocks_per_seg;
+
+	sbi->fggc_threshold = div64_u64((main_count - ovp_count) *
+				BLKS_PER_SEC(sbi), (main_count - resv_count));
+
+	/* give warm/cold data area from slower device */
+	if (sbi->s_ndevs && sbi->segs_per_sec == 1)
+		SIT_I(sbi)->last_victim[ALLOC_NEXT] =
+				GET_SEGNO(sbi, FDEV(0).end_blk) + 1;
 }
diff --git a/fs/f2fs/hash.c b/fs/f2fs/hash.c
index 71b7206c431e..eb2e031ea887 100644
--- a/fs/f2fs/hash.c
+++ b/fs/f2fs/hash.c
@@ -70,7 +70,8 @@ static void str2hashbuf(const unsigned char *msg, size_t len,
 		*buf++ = pad;
 }
 
-f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info)
+f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info,
+				struct fscrypt_name *fname)
 {
 	__u32 hash;
 	f2fs_hash_t f2fs_hash;
@@ -79,6 +80,10 @@ f2fs_hash_t f2fs_dentry_hash(const struct qstr *name_info)
 	const unsigned char *name = name_info->name;
 	size_t len = name_info->len;
 
+	/* encrypted bigname case */
+	if (fname && !fname->disk_name.name)
+		return cpu_to_le32(fname->hash);
+
 	if (is_dot_dotdot(name_info))
 		return 0;
 
diff --git a/fs/f2fs/inline.c b/fs/f2fs/inline.c
index e32a9e527968..e0fd4376e6fb 100644
--- a/fs/f2fs/inline.c
+++ b/fs/f2fs/inline.c
@@ -63,19 +63,21 @@ void read_inline_data(struct page *page, struct page *ipage)
 		SetPageUptodate(page);
 }
 
-bool truncate_inline_inode(struct page *ipage, u64 from)
+void truncate_inline_inode(struct inode *inode, struct page *ipage, u64 from)
 {
 	void *addr;
 
 	if (from >= MAX_INLINE_DATA)
-		return false;
+		return;
 
 	addr = inline_data_addr(ipage);
 
 	f2fs_wait_on_page_writeback(ipage, NODE, true);
 	memset(addr + from, 0, MAX_INLINE_DATA - from);
 	set_page_dirty(ipage);
-	return true;
+
+	if (from == 0)
+		clear_inode_flag(inode, FI_DATA_EXIST);
 }
 
 int f2fs_read_inline_data(struct inode *inode, struct page *page)
@@ -135,6 +137,7 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	/* write data page to try to make data consistent */
 	set_page_writeback(page);
 	fio.old_blkaddr = dn->data_blkaddr;
+	set_inode_flag(dn->inode, FI_HOT_DATA);
 	write_data_page(dn, &fio);
 	f2fs_wait_on_page_writeback(page, DATA, true);
 	if (dirty) {
@@ -146,11 +149,11 @@ int f2fs_convert_inline_page(struct dnode_of_data *dn, struct page *page)
 	set_inode_flag(dn->inode, FI_APPEND_WRITE);
 
 	/* clear inline data and flag after data writeback */
-	truncate_inline_inode(dn->inode_page, 0);
+	truncate_inline_inode(dn->inode, dn->inode_page, 0);
 	clear_inline_node(dn->inode_page);
 clear_out:
 	stat_dec_inline_inode(dn->inode);
-	f2fs_clear_inline_inode(dn->inode);
+	clear_inode_flag(dn->inode, FI_INLINE_DATA);
 	f2fs_put_dnode(dn);
 	return 0;
 }
@@ -267,9 +270,8 @@ process_inline:
 	if (f2fs_has_inline_data(inode)) {
 		ipage = get_node_page(sbi, inode->i_ino);
 		f2fs_bug_on(sbi, IS_ERR(ipage));
-		if (!truncate_inline_inode(ipage, 0))
-			return false;
-		f2fs_clear_inline_inode(inode);
+		truncate_inline_inode(inode, ipage, 0);
+		clear_inode_flag(inode, FI_INLINE_DATA);
 		f2fs_put_page(ipage, 1);
 	} else if (ri && (ri->i_inline & F2FS_INLINE_DATA)) {
 		if (truncate_blocks(inode, 0, false))
@@ -296,11 +298,11 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
 		return NULL;
 	}
 
-	namehash = f2fs_dentry_hash(&name);
+	namehash = f2fs_dentry_hash(&name, fname);
 
 	inline_dentry = inline_data_addr(ipage);
 
-	make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
+	make_dentry_ptr_inline(NULL, &d, inline_dentry);
 	de = find_target_dentry(fname, namehash, NULL, &d);
 	unlock_page(ipage);
 	if (de)
@@ -314,12 +316,12 @@ struct f2fs_dir_entry *find_in_inline_dir(struct inode *dir,
 int make_empty_inline_dir(struct inode *inode, struct inode *parent,
 							struct page *ipage)
 {
-	struct f2fs_inline_dentry *dentry_blk;
+	struct f2fs_inline_dentry *inline_dentry;
 	struct f2fs_dentry_ptr d;
 
-	dentry_blk = inline_data_addr(ipage);
+	inline_dentry = inline_data_addr(ipage);
 
-	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
+	make_dentry_ptr_inline(NULL, &d, inline_dentry);
 	do_make_empty_dir(inode, parent, &d);
 
 	set_page_dirty(ipage);
@@ -380,7 +382,7 @@ static int f2fs_move_inline_dirents(struct inode *dir, struct page *ipage,
 	set_page_dirty(page);
 
 	/* clear inline dir and flag after data writeback */
-	truncate_inline_inode(ipage, 0);
+	truncate_inline_inode(dir, ipage, 0);
 
 	stat_dec_inline_dir(dir);
 	clear_inode_flag(dir, FI_INLINE_DENTRY);
@@ -400,7 +402,7 @@ static int f2fs_add_inline_entries(struct inode *dir,
 	unsigned long bit_pos = 0;
 	int err = 0;
 
-	make_dentry_ptr(NULL, &d, (void *)inline_dentry, 2);
+	make_dentry_ptr_inline(NULL, &d, inline_dentry);
 
 	while (bit_pos < d.max) {
 		struct f2fs_dir_entry *de;
@@ -455,7 +457,7 @@ static int f2fs_move_rehashed_dirents(struct inode *dir, struct page *ipage,
 	}
 
 	memcpy(backup_dentry, inline_dentry, MAX_INLINE_DATA);
-	truncate_inline_inode(ipage, 0);
+	truncate_inline_inode(dir, ipage, 0);
 
 	unlock_page(ipage);
 
@@ -498,7 +500,7 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
 	struct page *ipage;
 	unsigned int bit_pos;
 	f2fs_hash_t name_hash;
-	struct f2fs_inline_dentry *dentry_blk = NULL;
+	struct f2fs_inline_dentry *inline_dentry = NULL;
 	struct f2fs_dentry_ptr d;
 	int slots = GET_DENTRY_SLOTS(new_name->len);
 	struct page *page = NULL;
@@ -508,11 +510,11 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
 	if (IS_ERR(ipage))
 		return PTR_ERR(ipage);
 
-	dentry_blk = inline_data_addr(ipage);
-	bit_pos = room_for_filename(&dentry_blk->dentry_bitmap,
+	inline_dentry = inline_data_addr(ipage);
+	bit_pos = room_for_filename(&inline_dentry->dentry_bitmap,
 						slots, NR_INLINE_DENTRY);
 	if (bit_pos >= NR_INLINE_DENTRY) {
-		err = f2fs_convert_inline_dir(dir, ipage, dentry_blk);
+		err = f2fs_convert_inline_dir(dir, ipage, inline_dentry);
 		if (err)
 			return err;
 		err = -EAGAIN;
@@ -527,14 +529,12 @@ int f2fs_add_inline_entry(struct inode *dir, const struct qstr *new_name,
 			err = PTR_ERR(page);
 			goto fail;
 		}
-		if (f2fs_encrypted_inode(dir))
-			file_set_enc_name(inode);
 	}
 
 	f2fs_wait_on_page_writeback(ipage, NODE, true);
 
-	name_hash = f2fs_dentry_hash(new_name);
-	make_dentry_ptr(NULL, &d, (void *)dentry_blk, 2);
+	name_hash = f2fs_dentry_hash(new_name, NULL);
+	make_dentry_ptr_inline(NULL, &d, inline_dentry);
 	f2fs_update_dentry(ino, mode, &d, new_name, name_hash, bit_pos);
 
 	set_page_dirty(ipage);
@@ -586,14 +586,14 @@ bool f2fs_empty_inline_dir(struct inode *dir)
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dir);
 	struct page *ipage;
 	unsigned int bit_pos = 2;
-	struct f2fs_inline_dentry *dentry_blk;
+	struct f2fs_inline_dentry *inline_dentry;
 
 	ipage = get_node_page(sbi, dir->i_ino);
 	if (IS_ERR(ipage))
 		return false;
 
-	dentry_blk = inline_data_addr(ipage);
-	bit_pos = find_next_bit_le(&dentry_blk->dentry_bitmap,
+	inline_dentry = inline_data_addr(ipage);
+	bit_pos = find_next_bit_le(&inline_dentry->dentry_bitmap,
 					NR_INLINE_DENTRY,
 					bit_pos);
 
@@ -623,7 +623,7 @@ int f2fs_read_inline_dir(struct file *file, struct dir_context *ctx,
 
 	inline_dentry = inline_data_addr(ipage);
 
-	make_dentry_ptr(inode, &d, (void *)inline_dentry, 2);
+	make_dentry_ptr_inline(inode, &d, inline_dentry);
 
 	err = f2fs_fill_dentries(ctx, &d, 0, fstr);
 	if (!err)
diff --git a/fs/f2fs/inode.c b/fs/f2fs/inode.c
index af06bda51a54..6cd312a17c69 100644
--- a/fs/f2fs/inode.c
+++ b/fs/f2fs/inode.c
@@ -16,6 +16,7 @@
 
 #include "f2fs.h"
 #include "node.h"
+#include "segment.h"
 
 #include <trace/events/f2fs.h>
 
@@ -44,7 +45,6 @@ void f2fs_set_inode_flags(struct inode *inode)
 		new_fl |= S_DIRSYNC;
 	inode_set_flags(inode, new_fl,
 			S_SYNC|S_APPEND|S_IMMUTABLE|S_NOATIME|S_DIRSYNC);
-	f2fs_mark_inode_dirty_sync(inode, false);
 }
 
 static void __get_inode_rdev(struct inode *inode, struct f2fs_inode *ri)
@@ -130,7 +130,7 @@ static int do_read_inode(struct inode *inode)
 	i_gid_write(inode, le32_to_cpu(ri->i_gid));
 	set_nlink(inode, le32_to_cpu(ri->i_links));
 	inode->i_size = le64_to_cpu(ri->i_size);
-	inode->i_blocks = le64_to_cpu(ri->i_blocks);
+	inode->i_blocks = SECTOR_FROM_BLOCK(le64_to_cpu(ri->i_blocks) - 1);
 
 	inode->i_atime.tv_sec = le64_to_cpu(ri->i_atime);
 	inode->i_ctime.tv_sec = le64_to_cpu(ri->i_ctime);
@@ -226,6 +226,7 @@ make_now:
 		ret = -EIO;
 		goto bad_inode;
 	}
+	f2fs_set_inode_flags(inode);
 	unlock_new_inode(inode);
 	trace_f2fs_iget(inode);
 	return inode;
@@ -267,7 +268,7 @@ int update_inode(struct inode *inode, struct page *node_page)
 	ri->i_gid = cpu_to_le32(i_gid_read(inode));
 	ri->i_links = cpu_to_le32(inode->i_nlink);
 	ri->i_size = cpu_to_le64(i_size_read(inode));
-	ri->i_blocks = cpu_to_le64(inode->i_blocks);
+	ri->i_blocks = cpu_to_le64(SECTOR_TO_BLOCK(inode->i_blocks) + 1);
 
 	if (et) {
 		read_lock(&et->lock);
@@ -316,7 +317,6 @@ retry:
 		} else if (err != -ENOENT) {
 			f2fs_stop_checkpoint(sbi, false);
 		}
-		f2fs_inode_synced(inode);
 		return 0;
 	}
 	ret = update_inode(inode, node_page);
@@ -339,7 +339,8 @@ int f2fs_write_inode(struct inode *inode, struct writeback_control *wbc)
 	 * We need to balance fs here to prevent from producing dirty node pages
 	 * during the urgent cleaning time when runing out of free sections.
 	 */
-	if (update_inode_page(inode) && wbc && wbc->nr_to_write)
+	update_inode_page(inode);
+	if (wbc && wbc->nr_to_write)
 		f2fs_balance_fs(sbi, true);
 	return 0;
 }
@@ -372,10 +373,7 @@ void f2fs_evict_inode(struct inode *inode)
 	if (inode->i_nlink || is_bad_inode(inode))
 		goto no_delete;
 
-#ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(sbi, FAULT_EVICT_INODE))
-		goto no_delete;
-#endif
+	dquot_initialize(inode);
 
 	remove_ino_entry(sbi, inode->i_ino, APPEND_INO);
 	remove_ino_entry(sbi, inode->i_ino, UPDATE_INO);
@@ -387,6 +385,12 @@ retry:
 	if (F2FS_HAS_BLOCKS(inode))
 		err = f2fs_truncate(inode);
 
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (time_to_inject(sbi, FAULT_EVICT_INODE)) {
+		f2fs_show_injection_info(FAULT_EVICT_INODE);
+		err = -EIO;
+	}
+#endif
 	if (!err) {
 		f2fs_lock_op(sbi);
 		err = remove_inode_page(inode);
@@ -403,13 +407,19 @@ retry:
 
 	if (err)
 		update_inode_page(inode);
+	dquot_free_inode(inode);
 	sb_end_intwrite(inode->i_sb);
 no_delete:
+	dquot_drop(inode);
+
 	stat_dec_inline_xattr(inode);
 	stat_dec_inline_dir(inode);
 	stat_dec_inline_inode(inode);
 
-	invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino, inode->i_ino);
+	/* ino == 0, if f2fs_new_inode() was failed t*/
+	if (inode->i_ino)
+		invalidate_mapping_pages(NODE_MAPPING(sbi), inode->i_ino,
+							inode->i_ino);
 	if (xnid)
 		invalidate_mapping_pages(NODE_MAPPING(sbi), xnid, xnid);
 	if (inode->i_nlink) {
@@ -421,9 +431,10 @@ no_delete:
 	if (is_inode_flag_set(inode, FI_FREE_NID)) {
 		alloc_nid_failed(sbi, inode->i_ino);
 		clear_inode_flag(inode, FI_FREE_NID);
+	} else {
+		f2fs_bug_on(sbi, err &&
+			!exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
 	}
-	f2fs_bug_on(sbi, err &&
-		!exist_written_data(sbi, inode->i_ino, ORPHAN_INO));
 out_clear:
 	fscrypt_put_encryption_info(inode, NULL);
 	clear_inode(inode);
@@ -446,6 +457,7 @@ void handle_failed_inode(struct inode *inode)
 	 * in a panic when flushing dirty inodes in gdirty_list.
 	 */
 	update_inode_page(inode);
+	f2fs_inode_synced(inode);
 
 	/* don't make bad inode, since it becomes a regular file. */
 	unlock_new_inode(inode);
diff --git a/fs/f2fs/namei.c b/fs/f2fs/namei.c
index 56c19b0610a8..760d85223c81 100644
--- a/fs/f2fs/namei.c
+++ b/fs/f2fs/namei.c
@@ -15,6 +15,7 @@
 #include <linux/ctype.h>
 #include <linux/dcache.h>
 #include <linux/namei.h>
+#include <linux/quotaops.h>
 
 #include "f2fs.h"
 #include "node.h"
@@ -42,6 +43,8 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	}
 	f2fs_unlock_op(sbi);
 
+	nid_free = true;
+
 	inode_init_owner(inode, dir, mode);
 
 	inode->i_ino = ino;
@@ -52,10 +55,17 @@ static struct inode *f2fs_new_inode(struct inode *dir, umode_t mode)
 	err = insert_inode_locked(inode);
 	if (err) {
 		err = -EINVAL;
-		nid_free = true;
 		goto fail;
 	}
 
+	err = dquot_initialize(inode);
+	if (err)
+		goto fail_drop;
+
+	err = dquot_alloc_inode(inode);
+	if (err)
+		goto fail_drop;
+
 	/* If the directory encrypted, then we should encrypt the inode. */
 	if (f2fs_encrypted_inode(dir) && f2fs_may_encrypt(inode))
 		f2fs_set_encrypted_inode(inode);
@@ -85,6 +95,16 @@ fail:
 		set_inode_flag(inode, FI_FREE_NID);
 	iput(inode);
 	return ERR_PTR(err);
+fail_drop:
+	trace_f2fs_new_inode(inode, err);
+	dquot_drop(inode);
+	inode->i_flags |= S_NOQUOTA;
+	if (nid_free)
+		set_inode_flag(inode, FI_FREE_NID);
+	clear_nlink(inode);
+	unlock_new_inode(inode);
+	iput(inode);
+	return ERR_PTR(err);
 }
 
 static int is_multimedia_file(const unsigned char *s, const char *sub)
@@ -136,6 +156,10 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	nid_t ino = 0;
 	int err;
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -148,8 +172,6 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	ino = inode->i_ino;
 
-	f2fs_balance_fs(sbi, true);
-
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -163,6 +185,8 @@ static int f2fs_create(struct inode *dir, struct dentry *dentry, umode_t mode,
 
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
+
+	f2fs_balance_fs(sbi, true);
 	return 0;
 out:
 	handle_failed_inode(inode);
@@ -180,6 +204,10 @@ static int f2fs_link(struct dentry *old_dentry, struct inode *dir,
 			!fscrypt_has_permitted_context(dir, inode))
 		return -EPERM;
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	f2fs_balance_fs(sbi, true);
 
 	inode->i_ctime = current_time(inode);
@@ -321,12 +349,13 @@ static struct dentry *f2fs_lookup(struct inode *dir, struct dentry *dentry,
 		if (err)
 			goto err_out;
 	}
-	if (!IS_ERR(inode) && f2fs_encrypted_inode(dir) &&
-			(S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
-			!fscrypt_has_permitted_context(dir, inode)) {
-		bool nokey = f2fs_encrypted_inode(inode) &&
-			!fscrypt_has_encryption_key(inode);
-		err = nokey ? -ENOKEY : -EPERM;
+	if (f2fs_encrypted_inode(dir) &&
+	    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
+	    !fscrypt_has_permitted_context(dir, inode)) {
+		f2fs_msg(inode->i_sb, KERN_WARNING,
+			 "Inconsistent encryption contexts: %lu/%lu",
+			 dir->i_ino, inode->i_ino);
+		err = -EPERM;
 		goto err_out;
 	}
 	return d_splice_alias(inode, dentry);
@@ -346,6 +375,10 @@ static int f2fs_unlink(struct inode *dir, struct dentry *dentry)
 
 	trace_f2fs_unlink_enter(dir, dentry);
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	de = f2fs_find_entry(dir, &dentry->d_name, &page);
 	if (!de) {
 		if (IS_ERR(page))
@@ -403,7 +436,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 			return err;
 
 		if (!fscrypt_has_encryption_key(dir))
-			return -EPERM;
+			return -ENOKEY;
 
 		disk_link.len = (fscrypt_fname_encrypted_size(dir, len) +
 				sizeof(struct fscrypt_symlink_data));
@@ -412,6 +445,10 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	if (disk_link.len > dir->i_sb->s_blocksize)
 		return -ENAMETOOLONG;
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	inode = f2fs_new_inode(dir, S_IFLNK | S_IRWXUGO);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -423,8 +460,6 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 	inode_nohighmem(inode);
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 
-	f2fs_balance_fs(sbi, true);
-
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -447,7 +482,7 @@ static int f2fs_symlink(struct inode *dir, struct dentry *dentry,
 			goto err_out;
 
 		if (!fscrypt_has_encryption_key(inode)) {
-			err = -EPERM;
+			err = -ENOKEY;
 			goto err_out;
 		}
 
@@ -487,6 +522,8 @@ err_out:
 	}
 
 	kfree(sd);
+
+	f2fs_balance_fs(sbi, true);
 	return err;
 out:
 	handle_failed_inode(inode);
@@ -499,6 +536,10 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	struct inode *inode;
 	int err;
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	inode = f2fs_new_inode(dir, S_IFDIR | mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -508,8 +549,6 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 	inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	mapping_set_gfp_mask(inode->i_mapping, GFP_F2FS_HIGH_ZERO);
 
-	f2fs_balance_fs(sbi, true);
-
 	set_inode_flag(inode, FI_INC_LINK);
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
@@ -524,6 +563,8 @@ static int f2fs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode)
 
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
+
+	f2fs_balance_fs(sbi, true);
 	return 0;
 
 out_fail:
@@ -547,6 +588,10 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err = 0;
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -554,8 +599,6 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 	init_special_inode(inode, inode->i_mode, rdev);
 	inode->i_op = &f2fs_special_inode_operations;
 
-	f2fs_balance_fs(sbi, true);
-
 	f2fs_lock_op(sbi);
 	err = f2fs_add_link(dentry, inode);
 	if (err)
@@ -569,6 +612,8 @@ static int f2fs_mknod(struct inode *dir, struct dentry *dentry,
 
 	if (IS_DIRSYNC(dir))
 		f2fs_sync_fs(sbi->sb, 1);
+
+	f2fs_balance_fs(sbi, true);
 	return 0;
 out:
 	handle_failed_inode(inode);
@@ -582,6 +627,10 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 	struct inode *inode;
 	int err;
 
+	err = dquot_initialize(dir);
+	if (err)
+		return err;
+
 	inode = f2fs_new_inode(dir, mode);
 	if (IS_ERR(inode))
 		return PTR_ERR(inode);
@@ -595,8 +644,6 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 		inode->i_mapping->a_ops = &f2fs_dblock_aops;
 	}
 
-	f2fs_balance_fs(sbi, true);
-
 	f2fs_lock_op(sbi);
 	err = acquire_orphan_inode(sbi);
 	if (err)
@@ -622,6 +669,8 @@ static int __f2fs_tmpfile(struct inode *dir, struct dentry *dentry,
 	/* link_count was changed by d_tmpfile as well. */
 	f2fs_unlock_op(sbi);
 	unlock_new_inode(inode);
+
+	f2fs_balance_fs(sbi, true);
 	return 0;
 
 release_out:
@@ -663,12 +712,26 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	bool is_old_inline = f2fs_has_inline_dentry(old_dir);
 	int err = -ENOENT;
 
+	if ((f2fs_encrypted_inode(old_dir) &&
+			!fscrypt_has_encryption_key(old_dir)) ||
+			(f2fs_encrypted_inode(new_dir) &&
+			!fscrypt_has_encryption_key(new_dir)))
+		return -ENOKEY;
+
 	if ((old_dir != new_dir) && f2fs_encrypted_inode(new_dir) &&
 			!fscrypt_has_permitted_context(new_dir, old_inode)) {
 		err = -EPERM;
 		goto out;
 	}
 
+	err = dquot_initialize(old_dir);
+	if (err)
+		goto out;
+
+	err = dquot_initialize(new_dir);
+	if (err)
+		goto out;
+
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
 	if (!old_entry) {
 		if (IS_ERR(old_page))
@@ -714,13 +777,6 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 		if (err)
 			goto put_out_dir;
 
-		err = update_dent_inode(old_inode, new_inode,
-						&new_dentry->d_name);
-		if (err) {
-			release_orphan_inode(sbi);
-			goto put_out_dir;
-		}
-
 		f2fs_set_link(new_dir, new_entry, new_page, old_inode);
 
 		new_inode->i_ctime = current_time(new_inode);
@@ -772,9 +828,10 @@ static int f2fs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 
 	down_write(&F2FS_I(old_inode)->i_sem);
-	file_lost_pino(old_inode);
-	if (new_inode && file_enc_name(new_inode))
-		file_set_enc_name(old_inode);
+	if (!old_dir_entry || whiteout)
+		file_lost_pino(old_inode);
+	else
+		F2FS_I(old_inode)->i_pino = new_dir->i_ino;
 	up_write(&F2FS_I(old_inode)->i_sem);
 
 	old_inode->i_ctime = current_time(old_inode);
@@ -843,12 +900,26 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	int old_nlink = 0, new_nlink = 0;
 	int err = -ENOENT;
 
+	if ((f2fs_encrypted_inode(old_dir) &&
+			!fscrypt_has_encryption_key(old_dir)) ||
+			(f2fs_encrypted_inode(new_dir) &&
+			!fscrypt_has_encryption_key(new_dir)))
+		return -ENOKEY;
+
 	if ((f2fs_encrypted_inode(old_dir) || f2fs_encrypted_inode(new_dir)) &&
 			(old_dir != new_dir) &&
 			(!fscrypt_has_permitted_context(new_dir, old_inode) ||
 			 !fscrypt_has_permitted_context(old_dir, new_inode)))
 		return -EPERM;
 
+	err = dquot_initialize(old_dir);
+	if (err)
+		goto out;
+
+	err = dquot_initialize(new_dir);
+	if (err)
+		goto out;
+
 	old_entry = f2fs_find_entry(old_dir, &old_dentry->d_name, &old_page);
 	if (!old_entry) {
 		if (IS_ERR(old_page))
@@ -896,8 +967,8 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 		old_nlink = old_dir_entry ? -1 : 1;
 		new_nlink = -old_nlink;
 		err = -EMLINK;
-		if ((old_nlink > 0 && old_inode->i_nlink >= F2FS_LINK_MAX) ||
-			(new_nlink > 0 && new_inode->i_nlink >= F2FS_LINK_MAX))
+		if ((old_nlink > 0 && old_dir->i_nlink >= F2FS_LINK_MAX) ||
+			(new_nlink > 0 && new_dir->i_nlink >= F2FS_LINK_MAX))
 			goto out_new_dir;
 	}
 
@@ -905,18 +976,6 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 	f2fs_lock_op(sbi);
 
-	err = update_dent_inode(old_inode, new_inode, &new_dentry->d_name);
-	if (err)
-		goto out_unlock;
-	if (file_enc_name(new_inode))
-		file_set_enc_name(old_inode);
-
-	err = update_dent_inode(new_inode, old_inode, &old_dentry->d_name);
-	if (err)
-		goto out_undo;
-	if (file_enc_name(old_inode))
-		file_set_enc_name(new_inode);
-
 	/* update ".." directory entry info of old dentry */
 	if (old_dir_entry)
 		f2fs_set_link(old_inode, old_dir_entry, old_dir_page, new_dir);
@@ -960,14 +1019,6 @@ static int f2fs_cross_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (IS_DIRSYNC(old_dir) || IS_DIRSYNC(new_dir))
 		f2fs_sync_fs(sbi->sb, 1);
 	return 0;
-out_undo:
-	/*
-	 * Still we may fail to recover name info of f2fs_inode here
-	 * Drop it, once its name is set as encrypted
-	 */
-	update_dent_inode(old_inode, old_inode, &old_dentry->d_name);
-out_unlock:
-	f2fs_unlock_op(sbi);
 out_new_dir:
 	if (new_dir_entry) {
 		f2fs_dentry_kunmap(new_inode, new_dir_page);
diff --git a/fs/f2fs/node.c b/fs/f2fs/node.c
index b9078fdb3743..d53fe620939e 100644
--- a/fs/f2fs/node.c
+++ b/fs/f2fs/node.c
@@ -22,7 +22,7 @@
 #include "trace.h"
 #include <trace/events/f2fs.h>
 
-#define on_build_free_nids(nmi) mutex_is_locked(&nm_i->build_lock)
+#define on_build_free_nids(nmi) mutex_is_locked(&(nm_i)->build_lock)
 
 static struct kmem_cache *nat_entry_slab;
 static struct kmem_cache *free_nid_slab;
@@ -63,8 +63,9 @@ bool available_free_memory(struct f2fs_sb_info *sbi, int type)
 		int i;
 
 		for (i = 0; i <= UPDATE_INO; i++)
-			mem_size += (sbi->im[i].ino_num *
-				sizeof(struct ino_entry)) >> PAGE_SHIFT;
+			mem_size += sbi->im[i].ino_num *
+						sizeof(struct ino_entry);
+		mem_size >>= PAGE_SHIFT;
 		res = mem_size < ((avail_ram * nm_i->ram_thresh / 100) >> 1);
 	} else if (type == EXTENT_CACHE) {
 		mem_size = (atomic_read(&sbi->total_ext_tree) *
@@ -157,9 +158,6 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
 	nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid);
 	struct nat_entry_set *head;
 
-	if (get_nat_flag(ne, IS_DIRTY))
-		return;
-
 	head = radix_tree_lookup(&nm_i->nat_set_root, set);
 	if (!head) {
 		head = f2fs_kmem_cache_alloc(nat_entry_set_slab, GFP_NOFS);
@@ -170,25 +168,27 @@ static void __set_nat_cache_dirty(struct f2fs_nm_info *nm_i,
 		head->entry_cnt = 0;
 		f2fs_radix_tree_insert(&nm_i->nat_set_root, set, head);
 	}
-	list_move_tail(&ne->list, &head->entry_list);
+
+	if (get_nat_flag(ne, IS_DIRTY))
+		goto refresh_list;
+
 	nm_i->dirty_nat_cnt++;
 	head->entry_cnt++;
 	set_nat_flag(ne, IS_DIRTY, true);
+refresh_list:
+	if (nat_get_blkaddr(ne) == NEW_ADDR)
+		list_del_init(&ne->list);
+	else
+		list_move_tail(&ne->list, &head->entry_list);
 }
 
 static void __clear_nat_cache_dirty(struct f2fs_nm_info *nm_i,
-						struct nat_entry *ne)
+		struct nat_entry_set *set, struct nat_entry *ne)
 {
-	nid_t set = NAT_BLOCK_OFFSET(ne->ni.nid);
-	struct nat_entry_set *head;
-
-	head = radix_tree_lookup(&nm_i->nat_set_root, set);
-	if (head) {
-		list_move_tail(&ne->list, &nm_i->nat_entries);
-		set_nat_flag(ne, IS_DIRTY, false);
-		head->entry_cnt--;
-		nm_i->dirty_nat_cnt--;
-	}
+	list_move_tail(&ne->list, &nm_i->nat_entries);
+	set_nat_flag(ne, IS_DIRTY, false);
+	set->entry_cnt--;
+	nm_i->dirty_nat_cnt--;
 }
 
 static unsigned int __gang_lookup_nat_set(struct f2fs_nm_info *nm_i,
@@ -245,12 +245,24 @@ bool need_inode_block_update(struct f2fs_sb_info *sbi, nid_t ino)
 	return need_update;
 }
 
-static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid)
+static struct nat_entry *grab_nat_entry(struct f2fs_nm_info *nm_i, nid_t nid,
+								bool no_fail)
 {
 	struct nat_entry *new;
 
-	new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS);
-	f2fs_radix_tree_insert(&nm_i->nat_root, nid, new);
+	if (no_fail) {
+		new = f2fs_kmem_cache_alloc(nat_entry_slab, GFP_NOFS);
+		f2fs_radix_tree_insert(&nm_i->nat_root, nid, new);
+	} else {
+		new = kmem_cache_alloc(nat_entry_slab, GFP_NOFS);
+		if (!new)
+			return NULL;
+		if (radix_tree_insert(&nm_i->nat_root, nid, new)) {
+			kmem_cache_free(nat_entry_slab, new);
+			return NULL;
+		}
+	}
+
 	memset(new, 0, sizeof(struct nat_entry));
 	nat_set_nid(new, nid);
 	nat_reset_flag(new);
@@ -267,8 +279,9 @@ static void cache_nat_entry(struct f2fs_sb_info *sbi, nid_t nid,
 
 	e = __lookup_nat_cache(nm_i, nid);
 	if (!e) {
-		e = grab_nat_entry(nm_i, nid);
-		node_info_from_raw_nat(&e->ni, ne);
+		e = grab_nat_entry(nm_i, nid, false);
+		if (e)
+			node_info_from_raw_nat(&e->ni, ne);
 	} else {
 		f2fs_bug_on(sbi, nat_get_ino(e) != le32_to_cpu(ne->ino) ||
 				nat_get_blkaddr(e) !=
@@ -286,7 +299,7 @@ static void set_node_addr(struct f2fs_sb_info *sbi, struct node_info *ni,
 	down_write(&nm_i->nat_tree_lock);
 	e = __lookup_nat_cache(nm_i, ni->nid);
 	if (!e) {
-		e = grab_nat_entry(nm_i, ni->nid);
+		e = grab_nat_entry(nm_i, ni->nid, true);
 		copy_node_info(&e->ni, ni);
 		f2fs_bug_on(sbi, ni->blk_addr == NEW_ADDR);
 	} else if (new_blkaddr == NEW_ADDR) {
@@ -368,6 +381,7 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 	struct page *page = NULL;
 	struct f2fs_nat_entry ne;
 	struct nat_entry *e;
+	pgoff_t index;
 	int i;
 
 	ni->nid = nid;
@@ -393,17 +407,21 @@ void get_node_info(struct f2fs_sb_info *sbi, nid_t nid, struct node_info *ni)
 		node_info_from_raw_nat(ni, &ne);
 	}
 	up_read(&curseg->journal_rwsem);
-	if (i >= 0)
+	if (i >= 0) {
+		up_read(&nm_i->nat_tree_lock);
 		goto cache;
+	}
 
 	/* Fill node_info from nat page */
-	page = get_current_nat_page(sbi, start_nid);
+	index = current_nat_addr(sbi, nid);
+	up_read(&nm_i->nat_tree_lock);
+
+	page = get_meta_page(sbi, index);
 	nat_blk = (struct f2fs_nat_block *)page_address(page);
 	ne = nat_blk->entries[nid - start_nid];
 	node_info_from_raw_nat(ni, &ne);
 	f2fs_put_page(page, 1);
 cache:
-	up_read(&nm_i->nat_tree_lock);
 	/* cache nat entry */
 	down_write(&nm_i->nat_tree_lock);
 	cache_nat_entry(sbi, nid, &ne);
@@ -660,15 +678,11 @@ static void truncate_node(struct dnode_of_data *dn)
 	struct node_info ni;
 
 	get_node_info(sbi, dn->nid, &ni);
-	if (dn->inode->i_blocks == 0) {
-		f2fs_bug_on(sbi, ni.blk_addr != NULL_ADDR);
-		goto invalidate;
-	}
 	f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR);
 
 	/* Deallocate node address */
 	invalidate_blocks(sbi, ni.blk_addr);
-	dec_valid_node_count(sbi, dn->inode);
+	dec_valid_node_count(sbi, dn->inode, dn->nid == dn->inode->i_ino);
 	set_node_addr(sbi, &ni, NULL_ADDR, false);
 
 	if (dn->nid == dn->inode->i_ino) {
@@ -676,7 +690,7 @@ static void truncate_node(struct dnode_of_data *dn)
 		dec_valid_inode_count(sbi);
 		f2fs_inode_synced(dn->inode);
 	}
-invalidate:
+
 	clear_node_page_dirty(dn->node_page);
 	set_sbi_flag(sbi, SBI_IS_DIRTY);
 
@@ -958,9 +972,6 @@ int truncate_xattr_node(struct inode *inode, struct page *page)
 
 	f2fs_i_xnid_write(inode, 0);
 
-	/* need to do checkpoint during fsync */
-	F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
-
 	set_new_dnode(&dn, inode, page, npage, nid);
 
 	if (page)
@@ -996,7 +1007,7 @@ int remove_inode_page(struct inode *inode)
 
 	/* 0 is possible, after f2fs_new_inode() has failed */
 	f2fs_bug_on(F2FS_I_SB(inode),
-			inode->i_blocks != 0 && inode->i_blocks != 1);
+			inode->i_blocks != 0 && inode->i_blocks != 8);
 
 	/* will put inode & node pages */
 	truncate_node(&dn);
@@ -1018,7 +1029,7 @@ struct page *new_node_page(struct dnode_of_data *dn,
 				unsigned int ofs, struct page *ipage)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(dn->inode);
-	struct node_info old_ni, new_ni;
+	struct node_info new_ni;
 	struct page *page;
 	int err;
 
@@ -1029,17 +1040,18 @@ struct page *new_node_page(struct dnode_of_data *dn,
 	if (!page)
 		return ERR_PTR(-ENOMEM);
 
-	if (unlikely(!inc_valid_node_count(sbi, dn->inode))) {
-		err = -ENOSPC;
+	if (unlikely((err = inc_valid_node_count(sbi, dn->inode, !ofs))))
 		goto fail;
-	}
-
-	get_node_info(sbi, dn->nid, &old_ni);
 
-	/* Reinitialize old_ni with new node page */
-	f2fs_bug_on(sbi, old_ni.blk_addr != NULL_ADDR);
-	new_ni = old_ni;
+#ifdef CONFIG_F2FS_CHECK_FS
+	get_node_info(sbi, dn->nid, &new_ni);
+	f2fs_bug_on(sbi, new_ni.blk_addr != NULL_ADDR);
+#endif
+	new_ni.nid = dn->nid;
 	new_ni.ino = dn->inode->i_ino;
+	new_ni.blk_addr = NULL_ADDR;
+	new_ni.flag = 0;
+	new_ni.version = 0;
 	set_node_addr(sbi, &new_ni, NEW_ADDR, false);
 
 	f2fs_wait_on_page_writeback(page, NODE, true);
@@ -1140,6 +1152,7 @@ repeat:
 		f2fs_put_page(page, 1);
 		return ERR_PTR(err);
 	} else if (err == LOCKED_PAGE) {
+		err = 0;
 		goto page_hit;
 	}
 
@@ -1153,15 +1166,22 @@ repeat:
 		goto repeat;
 	}
 
-	if (unlikely(!PageUptodate(page)))
+	if (unlikely(!PageUptodate(page))) {
+		err = -EIO;
 		goto out_err;
+	}
 page_hit:
 	if(unlikely(nid != nid_of_node(page))) {
-		f2fs_bug_on(sbi, 1);
+		f2fs_msg(sbi->sb, KERN_WARNING, "inconsistent node block, "
+			"nid:%lu, node_footer[nid:%u,ino:%u,ofs:%u,cpver:%llu,blkaddr:%u]",
+			nid, nid_of_node(page), ino_of_node(page),
+			ofs_of_node(page), cpver_of_node(page),
+			next_blkaddr_of_node(page));
 		ClearPageUptodate(page);
+		err = -EINVAL;
 out_err:
 		f2fs_put_page(page, 1);
-		return ERR_PTR(-EIO);
+		return ERR_PTR(err);
 	}
 	return page;
 }
@@ -1305,16 +1325,99 @@ continue_unlock:
 	return last_page;
 }
 
+static int __write_node_page(struct page *page, bool atomic, bool *submitted,
+				struct writeback_control *wbc)
+{
+	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
+	nid_t nid;
+	struct node_info ni;
+	struct f2fs_io_info fio = {
+		.sbi = sbi,
+		.type = NODE,
+		.op = REQ_OP_WRITE,
+		.op_flags = wbc_to_write_flags(wbc),
+		.page = page,
+		.encrypted_page = NULL,
+		.submitted = false,
+	};
+
+	trace_f2fs_writepage(page, NODE);
+
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto redirty_out;
+	if (unlikely(f2fs_cp_error(sbi)))
+		goto redirty_out;
+
+	/* get old block addr of this node page */
+	nid = nid_of_node(page);
+	f2fs_bug_on(sbi, page->index != nid);
+
+	if (wbc->for_reclaim) {
+		if (!down_read_trylock(&sbi->node_write))
+			goto redirty_out;
+	} else {
+		down_read(&sbi->node_write);
+	}
+
+	get_node_info(sbi, nid, &ni);
+
+	/* This page is already truncated */
+	if (unlikely(ni.blk_addr == NULL_ADDR)) {
+		ClearPageUptodate(page);
+		dec_page_count(sbi, F2FS_DIRTY_NODES);
+		up_read(&sbi->node_write);
+		unlock_page(page);
+		return 0;
+	}
+
+	if (atomic && !test_opt(sbi, NOBARRIER))
+		fio.op_flags |= REQ_PREFLUSH | REQ_FUA;
+
+	set_page_writeback(page);
+	fio.old_blkaddr = ni.blk_addr;
+	write_node_page(nid, &fio);
+	set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
+	dec_page_count(sbi, F2FS_DIRTY_NODES);
+	up_read(&sbi->node_write);
+
+	if (wbc->for_reclaim) {
+		f2fs_submit_merged_write_cond(sbi, page->mapping->host, 0,
+						page->index, NODE);
+		submitted = NULL;
+	}
+
+	unlock_page(page);
+
+	if (unlikely(f2fs_cp_error(sbi))) {
+		f2fs_submit_merged_write(sbi, NODE);
+		submitted = NULL;
+	}
+	if (submitted)
+		*submitted = fio.submitted;
+
+	return 0;
+
+redirty_out:
+	redirty_page_for_writepage(wbc, page);
+	return AOP_WRITEPAGE_ACTIVATE;
+}
+
+static int f2fs_write_node_page(struct page *page,
+				struct writeback_control *wbc)
+{
+	return __write_node_page(page, false, NULL, wbc);
+}
+
 int fsync_node_pages(struct f2fs_sb_info *sbi, struct inode *inode,
 			struct writeback_control *wbc, bool atomic)
 {
 	pgoff_t index, end;
+	pgoff_t last_idx = ULONG_MAX;
 	struct pagevec pvec;
 	int ret = 0;
 	struct page *last_page = NULL;
 	bool marked = false;
 	nid_t ino = inode->i_ino;
-	int nwritten = 0;
 
 	if (atomic) {
 		last_page = last_fsync_dnode(sbi, ino);
@@ -1336,6 +1439,7 @@ retry:
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
+			bool submitted = false;
 
 			if (unlikely(f2fs_cp_error(sbi))) {
 				f2fs_put_page(last_page, 0);
@@ -1367,6 +1471,9 @@ continue_unlock:
 			f2fs_wait_on_page_writeback(page, NODE, true);
 			BUG_ON(PageWriteback(page));
 
+			set_fsync_mark(page, 0);
+			set_dentry_mark(page, 0);
+
 			if (!atomic || page == last_page) {
 				set_fsync_mark(page, 1);
 				if (IS_INODE(page)) {
@@ -1384,13 +1491,15 @@ continue_unlock:
 			if (!clear_page_dirty_for_io(page))
 				goto continue_unlock;
 
-			ret = NODE_MAPPING(sbi)->a_ops->writepage(page, wbc);
+			ret = __write_node_page(page, atomic &&
+						page == last_page,
+						&submitted, wbc);
 			if (ret) {
 				unlock_page(page);
 				f2fs_put_page(last_page, 0);
 				break;
-			} else {
-				nwritten++;
+			} else if (submitted) {
+				last_idx = page->index;
 			}
 
 			if (page == last_page) {
@@ -1416,8 +1525,8 @@ continue_unlock:
 		goto retry;
 	}
 out:
-	if (nwritten)
-		f2fs_submit_merged_bio_cond(sbi, NULL, NULL, ino, NODE, WRITE);
+	if (last_idx != ULONG_MAX)
+		f2fs_submit_merged_write_cond(sbi, NULL, ino, last_idx, NODE);
 	return ret ? -EIO: 0;
 }
 
@@ -1445,6 +1554,7 @@ next_step:
 
 		for (i = 0; i < nr_pages; i++) {
 			struct page *page = pvec.pages[i];
+			bool submitted = false;
 
 			if (unlikely(f2fs_cp_error(sbi))) {
 				pagevec_release(&pvec);
@@ -1498,9 +1608,10 @@ continue_unlock:
 			set_fsync_mark(page, 0);
 			set_dentry_mark(page, 0);
 
-			if (NODE_MAPPING(sbi)->a_ops->writepage(page, wbc))
+			ret = __write_node_page(page, false, &submitted, wbc);
+			if (ret)
 				unlock_page(page);
-			else
+			else if (submitted)
 				nwritten++;
 
 			if (--wbc->nr_to_write == 0)
@@ -1521,7 +1632,7 @@ continue_unlock:
 	}
 out:
 	if (nwritten)
-		f2fs_submit_merged_bio(sbi, NODE, WRITE);
+		f2fs_submit_merged_write(sbi, NODE);
 	return ret;
 }
 
@@ -1564,72 +1675,6 @@ int wait_on_node_pages_writeback(struct f2fs_sb_info *sbi, nid_t ino)
 	return ret;
 }
 
-static int f2fs_write_node_page(struct page *page,
-				struct writeback_control *wbc)
-{
-	struct f2fs_sb_info *sbi = F2FS_P_SB(page);
-	nid_t nid;
-	struct node_info ni;
-	struct f2fs_io_info fio = {
-		.sbi = sbi,
-		.type = NODE,
-		.op = REQ_OP_WRITE,
-		.op_flags = wbc_to_write_flags(wbc),
-		.page = page,
-		.encrypted_page = NULL,
-	};
-
-	trace_f2fs_writepage(page, NODE);
-
-	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
-		goto redirty_out;
-	if (unlikely(f2fs_cp_error(sbi)))
-		goto redirty_out;
-
-	/* get old block addr of this node page */
-	nid = nid_of_node(page);
-	f2fs_bug_on(sbi, page->index != nid);
-
-	if (wbc->for_reclaim) {
-		if (!down_read_trylock(&sbi->node_write))
-			goto redirty_out;
-	} else {
-		down_read(&sbi->node_write);
-	}
-
-	get_node_info(sbi, nid, &ni);
-
-	/* This page is already truncated */
-	if (unlikely(ni.blk_addr == NULL_ADDR)) {
-		ClearPageUptodate(page);
-		dec_page_count(sbi, F2FS_DIRTY_NODES);
-		up_read(&sbi->node_write);
-		unlock_page(page);
-		return 0;
-	}
-
-	set_page_writeback(page);
-	fio.old_blkaddr = ni.blk_addr;
-	write_node_page(nid, &fio);
-	set_node_addr(sbi, &ni, fio.new_blkaddr, is_fsync_dnode(page));
-	dec_page_count(sbi, F2FS_DIRTY_NODES);
-	up_read(&sbi->node_write);
-
-	if (wbc->for_reclaim)
-		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, NODE, WRITE);
-
-	unlock_page(page);
-
-	if (unlikely(f2fs_cp_error(sbi)))
-		f2fs_submit_merged_bio(sbi, NODE, WRITE);
-
-	return 0;
-
-redirty_out:
-	redirty_page_for_writepage(wbc, page);
-	return AOP_WRITEPAGE_ACTIVATE;
-}
-
 static int f2fs_write_node_pages(struct address_space *mapping,
 			    struct writeback_control *wbc)
 {
@@ -1637,6 +1682,9 @@ static int f2fs_write_node_pages(struct address_space *mapping,
 	struct blk_plug plug;
 	long diff;
 
+	if (unlikely(is_sbi_flag_set(sbi, SBI_POR_DOING)))
+		goto skip_write;
+
 	/* balancing f2fs's metadata in background */
 	f2fs_balance_fs_bg(sbi);
 
@@ -1727,43 +1775,71 @@ static void __remove_nid_from_list(struct f2fs_sb_info *sbi,
 		radix_tree_delete(&nm_i->free_nid_root, i->nid);
 }
 
-static int add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
+/* return if the nid is recognized as free */
+static bool add_free_nid(struct f2fs_sb_info *sbi, nid_t nid, bool build)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
-	struct free_nid *i;
+	struct free_nid *i, *e;
 	struct nat_entry *ne;
-	int err;
+	int err = -EINVAL;
+	bool ret = false;
 
 	/* 0 nid should not be used */
 	if (unlikely(nid == 0))
-		return 0;
-
-	if (build) {
-		/* do not add allocated nids */
-		ne = __lookup_nat_cache(nm_i, nid);
-		if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
-				nat_get_blkaddr(ne) != NULL_ADDR))
-			return 0;
-	}
+		return false;
 
 	i = f2fs_kmem_cache_alloc(free_nid_slab, GFP_NOFS);
 	i->nid = nid;
 	i->state = NID_NEW;
 
-	if (radix_tree_preload(GFP_NOFS)) {
-		kmem_cache_free(free_nid_slab, i);
-		return 0;
-	}
+	if (radix_tree_preload(GFP_NOFS))
+		goto err;
 
 	spin_lock(&nm_i->nid_list_lock);
+
+	if (build) {
+		/*
+		 *   Thread A             Thread B
+		 *  - f2fs_create
+		 *   - f2fs_new_inode
+		 *    - alloc_nid
+		 *     - __insert_nid_to_list(ALLOC_NID_LIST)
+		 *                     - f2fs_balance_fs_bg
+		 *                      - build_free_nids
+		 *                       - __build_free_nids
+		 *                        - scan_nat_page
+		 *                         - add_free_nid
+		 *                          - __lookup_nat_cache
+		 *  - f2fs_add_link
+		 *   - init_inode_metadata
+		 *    - new_inode_page
+		 *     - new_node_page
+		 *      - set_node_addr
+		 *  - alloc_nid_done
+		 *   - __remove_nid_from_list(ALLOC_NID_LIST)
+		 *                         - __insert_nid_to_list(FREE_NID_LIST)
+		 */
+		ne = __lookup_nat_cache(nm_i, nid);
+		if (ne && (!get_nat_flag(ne, IS_CHECKPOINTED) ||
+				nat_get_blkaddr(ne) != NULL_ADDR))
+			goto err_out;
+
+		e = __lookup_free_nid_list(nm_i, nid);
+		if (e) {
+			if (e->state == NID_NEW)
+				ret = true;
+			goto err_out;
+		}
+	}
+	ret = true;
 	err = __insert_nid_to_list(sbi, i, FREE_NID_LIST, true);
+err_out:
 	spin_unlock(&nm_i->nid_list_lock);
 	radix_tree_preload_end();
-	if (err) {
+err:
+	if (err)
 		kmem_cache_free(free_nid_slab, i);
-		return 0;
-	}
-	return 1;
+	return ret;
 }
 
 static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid)
@@ -1784,17 +1860,45 @@ static void remove_free_nid(struct f2fs_sb_info *sbi, nid_t nid)
 		kmem_cache_free(free_nid_slab, i);
 }
 
+static void update_free_nid_bitmap(struct f2fs_sb_info *sbi, nid_t nid,
+							bool set, bool build)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	unsigned int nat_ofs = NAT_BLOCK_OFFSET(nid);
+	unsigned int nid_ofs = nid - START_NID(nid);
+
+	if (!test_bit_le(nat_ofs, nm_i->nat_block_bitmap))
+		return;
+
+	if (set)
+		__set_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+	else
+		__clear_bit_le(nid_ofs, nm_i->free_nid_bitmap[nat_ofs]);
+
+	if (set)
+		nm_i->free_nid_count[nat_ofs]++;
+	else if (!build)
+		nm_i->free_nid_count[nat_ofs]--;
+}
+
 static void scan_nat_page(struct f2fs_sb_info *sbi,
 			struct page *nat_page, nid_t start_nid)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct f2fs_nat_block *nat_blk = page_address(nat_page);
 	block_t blk_addr;
+	unsigned int nat_ofs = NAT_BLOCK_OFFSET(start_nid);
 	int i;
 
+	if (test_bit_le(nat_ofs, nm_i->nat_block_bitmap))
+		return;
+
+	__set_bit_le(nat_ofs, nm_i->nat_block_bitmap);
+
 	i = start_nid % NAT_ENTRY_PER_BLOCK;
 
 	for (; i < NAT_ENTRY_PER_BLOCK; i++, start_nid++) {
+		bool freed = false;
 
 		if (unlikely(start_nid >= nm_i->max_nid))
 			break;
@@ -1802,11 +1906,58 @@ static void scan_nat_page(struct f2fs_sb_info *sbi,
 		blk_addr = le32_to_cpu(nat_blk->entries[i].block_addr);
 		f2fs_bug_on(sbi, blk_addr == NEW_ADDR);
 		if (blk_addr == NULL_ADDR)
-			add_free_nid(sbi, start_nid, true);
+			freed = add_free_nid(sbi, start_nid, true);
+		spin_lock(&NM_I(sbi)->nid_list_lock);
+		update_free_nid_bitmap(sbi, start_nid, freed, true);
+		spin_unlock(&NM_I(sbi)->nid_list_lock);
+	}
+}
+
+static void scan_free_nid_bits(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
+	struct f2fs_journal *journal = curseg->journal;
+	unsigned int i, idx;
+
+	down_read(&nm_i->nat_tree_lock);
+
+	for (i = 0; i < nm_i->nat_blocks; i++) {
+		if (!test_bit_le(i, nm_i->nat_block_bitmap))
+			continue;
+		if (!nm_i->free_nid_count[i])
+			continue;
+		for (idx = 0; idx < NAT_ENTRY_PER_BLOCK; idx++) {
+			nid_t nid;
+
+			if (!test_bit_le(idx, nm_i->free_nid_bitmap[i]))
+				continue;
+
+			nid = i * NAT_ENTRY_PER_BLOCK + idx;
+			add_free_nid(sbi, nid, true);
+
+			if (nm_i->nid_cnt[FREE_NID_LIST] >= MAX_FREE_NIDS)
+				goto out;
+		}
+	}
+out:
+	down_read(&curseg->journal_rwsem);
+	for (i = 0; i < nats_in_cursum(journal); i++) {
+		block_t addr;
+		nid_t nid;
+
+		addr = le32_to_cpu(nat_in_journal(journal, i).block_addr);
+		nid = le32_to_cpu(nid_in_journal(journal, i));
+		if (addr == NULL_ADDR)
+			add_free_nid(sbi, nid, true);
+		else
+			remove_free_nid(sbi, nid);
 	}
+	up_read(&curseg->journal_rwsem);
+	up_read(&nm_i->nat_tree_lock);
 }
 
-static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync)
+static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
@@ -1814,6 +1965,9 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync)
 	int i = 0;
 	nid_t nid = nm_i->next_scan_nid;
 
+	if (unlikely(nid >= nm_i->max_nid))
+		nid = 0;
+
 	/* Enough entries */
 	if (nm_i->nid_cnt[FREE_NID_LIST] >= NAT_ENTRY_PER_BLOCK)
 		return;
@@ -1821,6 +1975,14 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync)
 	if (!sync && !available_free_memory(sbi, FREE_NIDS))
 		return;
 
+	if (!mount) {
+		/* try to find free nids in free_nid_bitmap */
+		scan_free_nid_bits(sbi);
+
+		if (nm_i->nid_cnt[FREE_NID_LIST])
+			return;
+	}
+
 	/* readahead nat pages to be scanned */
 	ra_meta_pages(sbi, NAT_BLOCK_OFFSET(nid), FREE_NID_PAGES,
 							META_NAT, true);
@@ -1863,10 +2025,10 @@ static void __build_free_nids(struct f2fs_sb_info *sbi, bool sync)
 					nm_i->ra_nid_pages, META_NAT, false);
 }
 
-void build_free_nids(struct f2fs_sb_info *sbi, bool sync)
+void build_free_nids(struct f2fs_sb_info *sbi, bool sync, bool mount)
 {
 	mutex_lock(&NM_I(sbi)->build_lock);
-	__build_free_nids(sbi, sync);
+	__build_free_nids(sbi, sync, mount);
 	mutex_unlock(&NM_I(sbi)->build_lock);
 }
 
@@ -1881,8 +2043,10 @@ bool alloc_nid(struct f2fs_sb_info *sbi, nid_t *nid)
 	struct free_nid *i = NULL;
 retry:
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(sbi, FAULT_ALLOC_NID))
+	if (time_to_inject(sbi, FAULT_ALLOC_NID)) {
+		f2fs_show_injection_info(FAULT_ALLOC_NID);
 		return false;
+	}
 #endif
 	spin_lock(&nm_i->nid_list_lock);
 
@@ -1902,13 +2066,16 @@ retry:
 		i->state = NID_ALLOC;
 		__insert_nid_to_list(sbi, i, ALLOC_NID_LIST, false);
 		nm_i->available_nids--;
+
+		update_free_nid_bitmap(sbi, *nid, false, false);
+
 		spin_unlock(&nm_i->nid_list_lock);
 		return true;
 	}
 	spin_unlock(&nm_i->nid_list_lock);
 
 	/* Let's scan nat pages and its caches to get free nids */
-	build_free_nids(sbi, true);
+	build_free_nids(sbi, true, false);
 	goto retry;
 }
 
@@ -1956,6 +2123,8 @@ void alloc_nid_failed(struct f2fs_sb_info *sbi, nid_t nid)
 
 	nm_i->available_nids++;
 
+	update_free_nid_bitmap(sbi, nid, true, false);
+
 	spin_unlock(&nm_i->nid_list_lock);
 
 	if (need_free)
@@ -2018,38 +2187,46 @@ update_inode:
 	f2fs_put_page(ipage, 1);
 }
 
-void recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
+int recover_xattr_data(struct inode *inode, struct page *page, block_t blkaddr)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	nid_t prev_xnid = F2FS_I(inode)->i_xattr_nid;
 	nid_t new_xnid = nid_of_node(page);
 	struct node_info ni;
+	struct page *xpage;
 
-	/* 1: invalidate the previous xattr nid */
 	if (!prev_xnid)
 		goto recover_xnid;
 
-	/* Deallocate node address */
+	/* 1: invalidate the previous xattr nid */
 	get_node_info(sbi, prev_xnid, &ni);
 	f2fs_bug_on(sbi, ni.blk_addr == NULL_ADDR);
 	invalidate_blocks(sbi, ni.blk_addr);
-	dec_valid_node_count(sbi, inode);
+	dec_valid_node_count(sbi, inode, false);
 	set_node_addr(sbi, &ni, NULL_ADDR, false);
 
 recover_xnid:
-	/* 2: allocate new xattr nid */
-	if (unlikely(!inc_valid_node_count(sbi, inode)))
+	/* 2: update xattr nid in inode */
+	remove_free_nid(sbi, new_xnid);
+	f2fs_i_xnid_write(inode, new_xnid);
+	if (unlikely(inc_valid_node_count(sbi, inode, false)))
 		f2fs_bug_on(sbi, 1);
+	update_inode_page(inode);
+
+	/* 3: update and set xattr node page dirty */
+	xpage = grab_cache_page(NODE_MAPPING(sbi), new_xnid);
+	if (!xpage)
+		return -ENOMEM;
+
+	memcpy(F2FS_NODE(xpage), F2FS_NODE(page), PAGE_SIZE);
 
-	remove_free_nid(sbi, new_xnid);
 	get_node_info(sbi, new_xnid, &ni);
 	ni.ino = inode->i_ino;
 	set_node_addr(sbi, &ni, NEW_ADDR, false);
-	f2fs_i_xnid_write(inode, new_xnid);
+	set_page_dirty(xpage);
+	f2fs_put_page(xpage, 1);
 
-	/* 3: update xattr blkaddr */
-	refresh_sit_entry(sbi, NEW_ADDR, blkaddr);
-	set_node_addr(sbi, &ni, blkaddr, false);
+	return 0;
 }
 
 int recover_inode_page(struct f2fs_sb_info *sbi, struct page *page)
@@ -2090,7 +2267,7 @@ retry:
 	new_ni = old_ni;
 	new_ni.ino = ino;
 
-	if (unlikely(!inc_valid_node_count(sbi, NULL)))
+	if (unlikely(inc_valid_node_count(sbi, NULL, true)))
 		WARN_ON(1);
 	set_node_addr(sbi, &new_ni, NEW_ADDR, false);
 	inc_valid_inode_count(sbi);
@@ -2152,7 +2329,7 @@ static void remove_nats_in_journal(struct f2fs_sb_info *sbi)
 
 		ne = __lookup_nat_cache(nm_i, nid);
 		if (!ne) {
-			ne = grab_nat_entry(nm_i, nid);
+			ne = grab_nat_entry(nm_i, nid, true);
 			node_info_from_raw_nat(&ne->ni, &raw_ne);
 		}
 
@@ -2192,8 +2369,39 @@ add_out:
 	list_add_tail(&nes->set_list, head);
 }
 
+static void __update_nat_bits(struct f2fs_sb_info *sbi, nid_t start_nid,
+						struct page *page)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	unsigned int nat_index = start_nid / NAT_ENTRY_PER_BLOCK;
+	struct f2fs_nat_block *nat_blk = page_address(page);
+	int valid = 0;
+	int i;
+
+	if (!enabled_nat_bits(sbi, NULL))
+		return;
+
+	for (i = 0; i < NAT_ENTRY_PER_BLOCK; i++) {
+		if (start_nid == 0 && i == 0)
+			valid++;
+		if (nat_blk->entries[i].block_addr)
+			valid++;
+	}
+	if (valid == 0) {
+		__set_bit_le(nat_index, nm_i->empty_nat_bits);
+		__clear_bit_le(nat_index, nm_i->full_nat_bits);
+		return;
+	}
+
+	__clear_bit_le(nat_index, nm_i->empty_nat_bits);
+	if (valid == NAT_ENTRY_PER_BLOCK)
+		__set_bit_le(nat_index, nm_i->full_nat_bits);
+	else
+		__clear_bit_le(nat_index, nm_i->full_nat_bits);
+}
+
 static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
-					struct nat_entry_set *set)
+		struct nat_entry_set *set, struct cp_control *cpc)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
 	struct f2fs_journal *journal = curseg->journal;
@@ -2208,7 +2416,8 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 	 * #1, flush nat entries to journal in current hot data summary block.
 	 * #2, flush nat entries to nat page.
 	 */
-	if (!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
+	if (enabled_nat_bits(sbi, cpc) ||
+		!__has_cursum_space(journal, set->entry_cnt, NAT_JOURNAL))
 		to_journal = false;
 
 	if (to_journal) {
@@ -2225,8 +2434,7 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 		nid_t nid = nat_get_nid(ne);
 		int offset;
 
-		if (nat_get_blkaddr(ne) == NEW_ADDR)
-			continue;
+		f2fs_bug_on(sbi, nat_get_blkaddr(ne) == NEW_ADDR);
 
 		if (to_journal) {
 			offset = lookup_journal_in_cursum(journal,
@@ -2239,30 +2447,38 @@ static void __flush_nat_entry_set(struct f2fs_sb_info *sbi,
 		}
 		raw_nat_from_node_info(raw_ne, &ne->ni);
 		nat_reset_flag(ne);
-		__clear_nat_cache_dirty(NM_I(sbi), ne);
+		__clear_nat_cache_dirty(NM_I(sbi), set, ne);
 		if (nat_get_blkaddr(ne) == NULL_ADDR) {
 			add_free_nid(sbi, nid, false);
 			spin_lock(&NM_I(sbi)->nid_list_lock);
 			NM_I(sbi)->available_nids++;
+			update_free_nid_bitmap(sbi, nid, true, false);
+			spin_unlock(&NM_I(sbi)->nid_list_lock);
+		} else {
+			spin_lock(&NM_I(sbi)->nid_list_lock);
+			update_free_nid_bitmap(sbi, nid, false, false);
 			spin_unlock(&NM_I(sbi)->nid_list_lock);
 		}
 	}
 
-	if (to_journal)
+	if (to_journal) {
 		up_write(&curseg->journal_rwsem);
-	else
+	} else {
+		__update_nat_bits(sbi, start_nid, page);
 		f2fs_put_page(page, 1);
+	}
 
-	f2fs_bug_on(sbi, set->entry_cnt);
-
-	radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set);
-	kmem_cache_free(nat_entry_set_slab, set);
+	/* Allow dirty nats by node block allocation in write_begin */
+	if (!set->entry_cnt) {
+		radix_tree_delete(&NM_I(sbi)->nat_set_root, set->set);
+		kmem_cache_free(nat_entry_set_slab, set);
+	}
 }
 
 /*
  * This function is called during the checkpointing process.
  */
-void flush_nat_entries(struct f2fs_sb_info *sbi)
+void flush_nat_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_HOT_DATA);
@@ -2283,7 +2499,8 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 	 * entries, remove all entries from journal and merge them
 	 * into nat entry set.
 	 */
-	if (!__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
+	if (enabled_nat_bits(sbi, cpc) ||
+		!__has_cursum_space(journal, nm_i->dirty_nat_cnt, NAT_JOURNAL))
 		remove_nats_in_journal(sbi);
 
 	while ((found = __gang_lookup_nat_set(nm_i,
@@ -2297,11 +2514,86 @@ void flush_nat_entries(struct f2fs_sb_info *sbi)
 
 	/* flush dirty nats in nat entry set */
 	list_for_each_entry_safe(set, tmp, &sets, set_list)
-		__flush_nat_entry_set(sbi, set);
+		__flush_nat_entry_set(sbi, set, cpc);
 
 	up_write(&nm_i->nat_tree_lock);
+	/* Allow dirty nats by node block allocation in write_begin */
+}
+
+static int __get_nat_bitmaps(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	unsigned int nat_bits_bytes = nm_i->nat_blocks / BITS_PER_BYTE;
+	unsigned int i;
+	__u64 cp_ver = cur_cp_version(ckpt);
+	block_t nat_bits_addr;
+
+	if (!enabled_nat_bits(sbi, NULL))
+		return 0;
+
+	nm_i->nat_bits_blocks = F2FS_BYTES_TO_BLK((nat_bits_bytes << 1) + 8 +
+						F2FS_BLKSIZE - 1);
+	nm_i->nat_bits = kzalloc(nm_i->nat_bits_blocks << F2FS_BLKSIZE_BITS,
+						GFP_KERNEL);
+	if (!nm_i->nat_bits)
+		return -ENOMEM;
+
+	nat_bits_addr = __start_cp_addr(sbi) + sbi->blocks_per_seg -
+						nm_i->nat_bits_blocks;
+	for (i = 0; i < nm_i->nat_bits_blocks; i++) {
+		struct page *page = get_meta_page(sbi, nat_bits_addr++);
+
+		memcpy(nm_i->nat_bits + (i << F2FS_BLKSIZE_BITS),
+					page_address(page), F2FS_BLKSIZE);
+		f2fs_put_page(page, 1);
+	}
+
+	cp_ver |= (cur_cp_crc(ckpt) << 32);
+	if (cpu_to_le64(cp_ver) != *(__le64 *)nm_i->nat_bits) {
+		disable_nat_bits(sbi, true);
+		return 0;
+	}
+
+	nm_i->full_nat_bits = nm_i->nat_bits + 8;
+	nm_i->empty_nat_bits = nm_i->full_nat_bits + nat_bits_bytes;
 
-	f2fs_bug_on(sbi, nm_i->dirty_nat_cnt);
+	f2fs_msg(sbi->sb, KERN_NOTICE, "Found nat_bits in checkpoint");
+	return 0;
+}
+
+static inline void load_free_nid_bitmap(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+	unsigned int i = 0;
+	nid_t nid, last_nid;
+
+	if (!enabled_nat_bits(sbi, NULL))
+		return;
+
+	for (i = 0; i < nm_i->nat_blocks; i++) {
+		i = find_next_bit_le(nm_i->empty_nat_bits, nm_i->nat_blocks, i);
+		if (i >= nm_i->nat_blocks)
+			break;
+
+		__set_bit_le(i, nm_i->nat_block_bitmap);
+
+		nid = i * NAT_ENTRY_PER_BLOCK;
+		last_nid = (i + 1) * NAT_ENTRY_PER_BLOCK;
+
+		spin_lock(&NM_I(sbi)->nid_list_lock);
+		for (; nid < last_nid; nid++)
+			update_free_nid_bitmap(sbi, nid, true, true);
+		spin_unlock(&NM_I(sbi)->nid_list_lock);
+	}
+
+	for (i = 0; i < nm_i->nat_blocks; i++) {
+		i = find_next_bit_le(nm_i->full_nat_bits, nm_i->nat_blocks, i);
+		if (i >= nm_i->nat_blocks)
+			break;
+
+		__set_bit_le(i, nm_i->nat_block_bitmap);
+	}
 }
 
 static int init_node_manager(struct f2fs_sb_info *sbi)
@@ -2309,15 +2601,15 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 	struct f2fs_super_block *sb_raw = F2FS_RAW_SUPER(sbi);
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	unsigned char *version_bitmap;
-	unsigned int nat_segs, nat_blocks;
+	unsigned int nat_segs;
+	int err;
 
 	nm_i->nat_blkaddr = le32_to_cpu(sb_raw->nat_blkaddr);
 
 	/* segment_count_nat includes pair segment so divide to 2. */
 	nat_segs = le32_to_cpu(sb_raw->segment_count_nat) >> 1;
-	nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg);
-
-	nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nat_blocks;
+	nm_i->nat_blocks = nat_segs << le32_to_cpu(sb_raw->log_blocks_per_seg);
+	nm_i->max_nid = NAT_ENTRY_PER_BLOCK * nm_i->nat_blocks;
 
 	/* not used nids: 0, node, meta, (and root counted as valid node) */
 	nm_i->available_nids = nm_i->max_nid - sbi->total_valid_node_count -
@@ -2350,6 +2642,39 @@ static int init_node_manager(struct f2fs_sb_info *sbi)
 					GFP_KERNEL);
 	if (!nm_i->nat_bitmap)
 		return -ENOMEM;
+
+	err = __get_nat_bitmaps(sbi);
+	if (err)
+		return err;
+
+#ifdef CONFIG_F2FS_CHECK_FS
+	nm_i->nat_bitmap_mir = kmemdup(version_bitmap, nm_i->bitmap_size,
+					GFP_KERNEL);
+	if (!nm_i->nat_bitmap_mir)
+		return -ENOMEM;
+#endif
+
+	return 0;
+}
+
+static int init_free_nid_cache(struct f2fs_sb_info *sbi)
+{
+	struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+	nm_i->free_nid_bitmap = kvzalloc(nm_i->nat_blocks *
+					NAT_ENTRY_BITMAP_SIZE, GFP_KERNEL);
+	if (!nm_i->free_nid_bitmap)
+		return -ENOMEM;
+
+	nm_i->nat_block_bitmap = kvzalloc(nm_i->nat_blocks / 8,
+								GFP_KERNEL);
+	if (!nm_i->nat_block_bitmap)
+		return -ENOMEM;
+
+	nm_i->free_nid_count = kvzalloc(nm_i->nat_blocks *
+					sizeof(unsigned short), GFP_KERNEL);
+	if (!nm_i->free_nid_count)
+		return -ENOMEM;
 	return 0;
 }
 
@@ -2365,7 +2690,14 @@ int build_node_manager(struct f2fs_sb_info *sbi)
 	if (err)
 		return err;
 
-	build_free_nids(sbi, true);
+	err = init_free_nid_cache(sbi);
+	if (err)
+		return err;
+
+	/* load free nid status from nat_bits table */
+	load_free_nid_bitmap(sbi);
+
+	build_free_nids(sbi, true, true);
 	return 0;
 }
 
@@ -2423,7 +2755,15 @@ void destroy_node_manager(struct f2fs_sb_info *sbi)
 	}
 	up_write(&nm_i->nat_tree_lock);
 
+	kvfree(nm_i->nat_block_bitmap);
+	kvfree(nm_i->free_nid_bitmap);
+	kvfree(nm_i->free_nid_count);
+
 	kfree(nm_i->nat_bitmap);
+	kfree(nm_i->nat_bits);
+#ifdef CONFIG_F2FS_CHECK_FS
+	kfree(nm_i->nat_bitmap_mir);
+#endif
 	sbi->nm_info = NULL;
 	kfree(nm_i);
 }
diff --git a/fs/f2fs/node.h b/fs/f2fs/node.h
index e7997e240366..bb53e9955ff2 100644
--- a/fs/f2fs/node.h
+++ b/fs/f2fs/node.h
@@ -9,10 +9,10 @@
  * published by the Free Software Foundation.
  */
 /* start node id of a node block dedicated to the given node id */
-#define	START_NID(nid) ((nid / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK)
+#define	START_NID(nid) (((nid) / NAT_ENTRY_PER_BLOCK) * NAT_ENTRY_PER_BLOCK)
 
 /* node block offset on the NAT area dedicated to the given start node id */
-#define	NAT_BLOCK_OFFSET(start_nid) (start_nid / NAT_ENTRY_PER_BLOCK)
+#define	NAT_BLOCK_OFFSET(start_nid) ((start_nid) / NAT_ENTRY_PER_BLOCK)
 
 /* # of pages to perform synchronous readahead before building free nids */
 #define FREE_NID_PAGES	8
@@ -62,16 +62,16 @@ struct nat_entry {
 	struct node_info ni;	/* in-memory node information */
 };
 
-#define nat_get_nid(nat)		(nat->ni.nid)
-#define nat_set_nid(nat, n)		(nat->ni.nid = n)
-#define nat_get_blkaddr(nat)		(nat->ni.blk_addr)
-#define nat_set_blkaddr(nat, b)		(nat->ni.blk_addr = b)
-#define nat_get_ino(nat)		(nat->ni.ino)
-#define nat_set_ino(nat, i)		(nat->ni.ino = i)
-#define nat_get_version(nat)		(nat->ni.version)
-#define nat_set_version(nat, v)		(nat->ni.version = v)
+#define nat_get_nid(nat)		((nat)->ni.nid)
+#define nat_set_nid(nat, n)		((nat)->ni.nid = (n))
+#define nat_get_blkaddr(nat)		((nat)->ni.blk_addr)
+#define nat_set_blkaddr(nat, b)		((nat)->ni.blk_addr = (b))
+#define nat_get_ino(nat)		((nat)->ni.ino)
+#define nat_set_ino(nat, i)		((nat)->ni.ino = (i))
+#define nat_get_version(nat)		((nat)->ni.version)
+#define nat_set_version(nat, v)		((nat)->ni.version = (v))
 
-#define inc_node_version(version)	(++version)
+#define inc_node_version(version)	(++(version))
 
 static inline void copy_node_info(struct node_info *dst,
 						struct node_info *src)
@@ -174,7 +174,7 @@ static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
 		spin_unlock(&nm_i->nid_list_lock);
 		return;
 	}
-	fnid = list_entry(nm_i->nid_list[FREE_NID_LIST].next,
+	fnid = list_first_entry(&nm_i->nid_list[FREE_NID_LIST],
 						struct free_nid, list);
 	*nid = fnid->nid;
 	spin_unlock(&nm_i->nid_list_lock);
@@ -186,6 +186,12 @@ static inline void next_free_nid(struct f2fs_sb_info *sbi, nid_t *nid)
 static inline void get_nat_bitmap(struct f2fs_sb_info *sbi, void *addr)
 {
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+	if (memcmp(nm_i->nat_bitmap, nm_i->nat_bitmap_mir,
+						nm_i->bitmap_size))
+		f2fs_bug_on(sbi, 1);
+#endif
 	memcpy(addr, nm_i->nat_bitmap, nm_i->bitmap_size);
 }
 
@@ -194,13 +200,16 @@ static inline pgoff_t current_nat_addr(struct f2fs_sb_info *sbi, nid_t start)
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 	pgoff_t block_off;
 	pgoff_t block_addr;
-	int seg_off;
 
+	/*
+	 * block_off = segment_off * 512 + off_in_segment
+	 * OLD = (segment_off * 512) * 2 + off_in_segment
+	 * NEW = 2 * (segment_off * 512 + off_in_segment) - off_in_segment
+	 */
 	block_off = NAT_BLOCK_OFFSET(start);
-	seg_off = block_off >> sbi->log_blocks_per_seg;
 
 	block_addr = (pgoff_t)(nm_i->nat_blkaddr +
-		(seg_off << sbi->log_blocks_per_seg << 1) +
+		(block_off << 1) -
 		(block_off & (sbi->blocks_per_seg - 1)));
 
 	if (f2fs_test_bit(block_off, nm_i->nat_bitmap))
@@ -215,11 +224,7 @@ static inline pgoff_t next_nat_addr(struct f2fs_sb_info *sbi,
 	struct f2fs_nm_info *nm_i = NM_I(sbi);
 
 	block_addr -= nm_i->nat_blkaddr;
-	if ((block_addr >> sbi->log_blocks_per_seg) % 2)
-		block_addr -= sbi->blocks_per_seg;
-	else
-		block_addr += sbi->blocks_per_seg;
-
+	block_addr ^= 1 << sbi->log_blocks_per_seg;
 	return block_addr + nm_i->nat_blkaddr;
 }
 
@@ -228,6 +233,9 @@ static inline void set_to_next_nat(struct f2fs_nm_info *nm_i, nid_t start_nid)
 	unsigned int block_off = NAT_BLOCK_OFFSET(start_nid);
 
 	f2fs_change_bit(block_off, nm_i->nat_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+	f2fs_change_bit(block_off, nm_i->nat_bitmap_mir);
+#endif
 }
 
 static inline nid_t ino_of_node(struct page *node_page)
@@ -291,14 +299,11 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
 	struct f2fs_node *rn = F2FS_NODE(page);
-	size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
-	__u64 cp_ver = le64_to_cpu(ckpt->checkpoint_ver);
+	__u64 cp_ver = cur_cp_version(ckpt);
+
+	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
+		cp_ver |= (cur_cp_crc(ckpt) << 32);
 
-	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
-		__u64 crc = le32_to_cpu(*((__le32 *)
-				((unsigned char *)ckpt + crc_offset)));
-		cp_ver |= (crc << 32);
-	}
 	rn->footer.cp_ver = cpu_to_le64(cp_ver);
 	rn->footer.next_blkaddr = cpu_to_le32(blkaddr);
 }
@@ -306,14 +311,11 @@ static inline void fill_node_footer_blkaddr(struct page *page, block_t blkaddr)
 static inline bool is_recoverable_dnode(struct page *page)
 {
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(F2FS_P_SB(page));
-	size_t crc_offset = le32_to_cpu(ckpt->checksum_offset);
 	__u64 cp_ver = cur_cp_version(ckpt);
 
-	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG)) {
-		__u64 crc = le32_to_cpu(*((__le32 *)
-				((unsigned char *)ckpt + crc_offset)));
-		cp_ver |= (crc << 32);
-	}
+	if (__is_set_ckpt_flags(ckpt, CP_CRC_RECOVERY_FLAG))
+		cp_ver |= (cur_cp_crc(ckpt) << 32);
+
 	return cp_ver == cpver_of_node(page);
 }
 
@@ -343,7 +345,7 @@ static inline bool IS_DNODE(struct page *node_page)
 	unsigned int ofs = ofs_of_node(node_page);
 
 	if (f2fs_has_xattr_block(ofs))
-		return false;
+		return true;
 
 	if (ofs == 3 || ofs == 4 + NIDS_PER_BLOCK ||
 			ofs == 5 + 2 * NIDS_PER_BLOCK)
diff --git a/fs/f2fs/recovery.c b/fs/f2fs/recovery.c
index 981a9584b62f..907d6b7dde6a 100644
--- a/fs/f2fs/recovery.c
+++ b/fs/f2fs/recovery.c
@@ -198,7 +198,8 @@ static void recover_inode(struct inode *inode, struct page *page)
 			ino_of_node(page), name);
 }
 
-static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
+static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head,
+				bool check_only)
 {
 	struct curseg_info *curseg;
 	struct page *page = NULL;
@@ -225,7 +226,8 @@ static int find_fsync_dnodes(struct f2fs_sb_info *sbi, struct list_head *head)
 
 		entry = get_fsync_inode(head, ino_of_node(page));
 		if (!entry) {
-			if (IS_INODE(page) && is_dent_dnode(page)) {
+			if (!check_only &&
+					IS_INODE(page) && is_dent_dnode(page)) {
 				err = recover_inode_page(sbi, page);
 				if (err)
 					break;
@@ -378,11 +380,9 @@ static int do_recover_data(struct f2fs_sb_info *sbi, struct inode *inode,
 	if (IS_INODE(page)) {
 		recover_inline_xattr(inode, page);
 	} else if (f2fs_has_xattr_block(ofs_of_node(page))) {
-		/*
-		 * Deprecated; xattr blocks should be found from cold log.
-		 * But, we should remain this for backward compatibility.
-		 */
-		recover_xattr_data(inode, page, blkaddr);
+		err = recover_xattr_data(inode, page, blkaddr);
+		if (!err)
+			recovered++;
 		goto out;
 	}
 
@@ -428,8 +428,9 @@ retry_dn:
 		}
 
 		if (!file_keep_isize(inode) &&
-				(i_size_read(inode) <= (start << PAGE_SHIFT)))
-			f2fs_i_size_write(inode, (start + 1) << PAGE_SHIFT);
+			(i_size_read(inode) <= ((loff_t)start << PAGE_SHIFT)))
+			f2fs_i_size_write(inode,
+				(loff_t)(start + 1) << PAGE_SHIFT);
 
 		/*
 		 * dest is reserved block, invalidate src block
@@ -552,10 +553,8 @@ next:
 
 int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 {
-	struct curseg_info *curseg = CURSEG_I(sbi, CURSEG_WARM_NODE);
 	struct list_head inode_list;
 	struct list_head dir_list;
-	block_t blkaddr;
 	int err;
 	int ret = 0;
 	bool need_writecp = false;
@@ -571,10 +570,8 @@ int recover_fsync_data(struct f2fs_sb_info *sbi, bool check_only)
 	/* prevent checkpoint */
 	mutex_lock(&sbi->cp_mutex);
 
-	blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
-
 	/* step #1: find fsynced inode numbers */
-	err = find_fsync_dnodes(sbi, &inode_list);
+	err = find_fsync_dnodes(sbi, &inode_list, check_only);
 	if (err || list_empty(&inode_list))
 		goto out;
 
diff --git a/fs/f2fs/segment.c b/fs/f2fs/segment.c
index 0d8802453758..f964b68718c1 100644
--- a/fs/f2fs/segment.c
+++ b/fs/f2fs/segment.c
@@ -16,6 +16,7 @@
 #include <linux/kthread.h>
 #include <linux/swap.h>
 #include <linux/timer.h>
+#include <linux/freezer.h>
 
 #include "f2fs.h"
 #include "segment.h"
@@ -26,7 +27,7 @@
 #define __reverse_ffz(x) __reverse_ffs(~(x))
 
 static struct kmem_cache *discard_entry_slab;
-static struct kmem_cache *bio_entry_slab;
+static struct kmem_cache *discard_cmd_slab;
 static struct kmem_cache *sit_entry_set_slab;
 static struct kmem_cache *inmem_entry_slab;
 
@@ -242,11 +243,42 @@ void drop_inmem_pages(struct inode *inode)
 {
 	struct f2fs_inode_info *fi = F2FS_I(inode);
 
+	mutex_lock(&fi->inmem_lock);
+	__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
+	mutex_unlock(&fi->inmem_lock);
+
 	clear_inode_flag(inode, FI_ATOMIC_FILE);
+	stat_dec_atomic_write(inode);
+}
+
+void drop_inmem_page(struct inode *inode, struct page *page)
+{
+	struct f2fs_inode_info *fi = F2FS_I(inode);
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	struct list_head *head = &fi->inmem_pages;
+	struct inmem_pages *cur = NULL;
+
+	f2fs_bug_on(sbi, !IS_ATOMIC_WRITTEN_PAGE(page));
 
 	mutex_lock(&fi->inmem_lock);
-	__revoke_inmem_pages(inode, &fi->inmem_pages, true, false);
+	list_for_each_entry(cur, head, list) {
+		if (cur->page == page)
+			break;
+	}
+
+	f2fs_bug_on(sbi, !cur || cur->page != page);
+	list_del(&cur->list);
 	mutex_unlock(&fi->inmem_lock);
+
+	dec_page_count(sbi, F2FS_INMEM_PAGES);
+	kmem_cache_free(inmem_entry_slab, cur);
+
+	ClearPageUptodate(page);
+	set_page_private(page, 0);
+	ClearPagePrivate(page);
+	f2fs_put_page(page, 0);
+
+	trace_f2fs_commit_inmem_page(page, INMEM_INVALIDATE);
 }
 
 static int __commit_inmem_pages(struct inode *inode,
@@ -260,9 +292,8 @@ static int __commit_inmem_pages(struct inode *inode,
 		.type = DATA,
 		.op = REQ_OP_WRITE,
 		.op_flags = REQ_SYNC | REQ_PRIO,
-		.encrypted_page = NULL,
 	};
-	bool submit_bio = false;
+	pgoff_t last_idx = ULONG_MAX;
 	int err = 0;
 
 	list_for_each_entry_safe(cur, tmp, &fi->inmem_pages, list) {
@@ -280,6 +311,9 @@ static int __commit_inmem_pages(struct inode *inode,
 			}
 
 			fio.page = page;
+			fio.old_blkaddr = NULL_ADDR;
+			fio.encrypted_page = NULL;
+			fio.need_lock = LOCK_DONE;
 			err = do_write_data_page(&fio);
 			if (err) {
 				unlock_page(page);
@@ -288,15 +322,14 @@ static int __commit_inmem_pages(struct inode *inode,
 
 			/* record old blkaddr for revoking */
 			cur->old_addr = fio.old_blkaddr;
-
-			submit_bio = true;
+			last_idx = page->index;
 		}
 		unlock_page(page);
 		list_move_tail(&cur->list, revoke_list);
 	}
 
-	if (submit_bio)
-		f2fs_submit_merged_bio_cond(sbi, inode, NULL, 0, DATA, WRITE);
+	if (last_idx != ULONG_MAX)
+		f2fs_submit_merged_write_cond(sbi, inode, 0, last_idx, DATA);
 
 	if (!err)
 		__revoke_inmem_pages(inode, revoke_list, false, false);
@@ -315,6 +348,8 @@ int commit_inmem_pages(struct inode *inode)
 	f2fs_balance_fs(sbi, true);
 	f2fs_lock_op(sbi);
 
+	set_inode_flag(inode, FI_ATOMIC_COMMIT);
+
 	mutex_lock(&fi->inmem_lock);
 	err = __commit_inmem_pages(inode, &revoke_list);
 	if (err) {
@@ -336,6 +371,8 @@ int commit_inmem_pages(struct inode *inode)
 	}
 	mutex_unlock(&fi->inmem_lock);
 
+	clear_inode_flag(inode, FI_ATOMIC_COMMIT);
+
 	f2fs_unlock_op(sbi);
 	return err;
 }
@@ -347,15 +384,14 @@ int commit_inmem_pages(struct inode *inode)
 void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 {
 #ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (time_to_inject(sbi, FAULT_CHECKPOINT))
+	if (time_to_inject(sbi, FAULT_CHECKPOINT)) {
+		f2fs_show_injection_info(FAULT_CHECKPOINT);
 		f2fs_stop_checkpoint(sbi, false);
+	}
 #endif
 
-	if (!need)
-		return;
-
 	/* balance_fs_bg is able to be pending */
-	if (excess_cached_nats(sbi))
+	if (need && excess_cached_nats(sbi))
 		f2fs_balance_fs_bg(sbi);
 
 	/*
@@ -364,7 +400,7 @@ void f2fs_balance_fs(struct f2fs_sb_info *sbi, bool need)
 	 */
 	if (has_not_enough_free_secs(sbi, 0, 0)) {
 		mutex_lock(&sbi->gc_mutex);
-		f2fs_gc(sbi, false, false);
+		f2fs_gc(sbi, false, false, NULL_SEGNO);
 	}
 }
 
@@ -381,9 +417,9 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 	if (!available_free_memory(sbi, FREE_NIDS))
 		try_to_free_nids(sbi, MAX_FREE_NIDS);
 	else
-		build_free_nids(sbi, false);
+		build_free_nids(sbi, false, false);
 
-	if (!is_idle(sbi))
+	if (!is_idle(sbi) && !excess_dirty_nats(sbi))
 		return;
 
 	/* checkpoint is the only way to shrink partial cached entries */
@@ -404,29 +440,34 @@ void f2fs_balance_fs_bg(struct f2fs_sb_info *sbi)
 	}
 }
 
-static int __submit_flush_wait(struct block_device *bdev)
+static int __submit_flush_wait(struct f2fs_sb_info *sbi,
+				struct block_device *bdev)
 {
 	struct bio *bio = f2fs_bio_alloc(0);
 	int ret;
 
-	bio->bi_opf = REQ_OP_WRITE | REQ_PREFLUSH;
+	bio->bi_opf = REQ_OP_WRITE | REQ_SYNC | REQ_PREFLUSH;
 	bio->bi_bdev = bdev;
 	ret = submit_bio_wait(bio);
 	bio_put(bio);
+
+	trace_f2fs_issue_flush(bdev, test_opt(sbi, NOBARRIER),
+				test_opt(sbi, FLUSH_MERGE), ret);
 	return ret;
 }
 
 static int submit_flush_wait(struct f2fs_sb_info *sbi)
 {
-	int ret = __submit_flush_wait(sbi->sb->s_bdev);
+	int ret = __submit_flush_wait(sbi, sbi->sb->s_bdev);
 	int i;
 
-	if (sbi->s_ndevs && !ret) {
-		for (i = 1; i < sbi->s_ndevs; i++) {
-			ret = __submit_flush_wait(FDEV(i).bdev);
-			if (ret)
-				break;
-		}
+	if (!sbi->s_ndevs || ret)
+		return ret;
+
+	for (i = 1; i < sbi->s_ndevs; i++) {
+		ret = __submit_flush_wait(sbi, FDEV(i).bdev);
+		if (ret)
+			break;
 	}
 	return ret;
 }
@@ -434,7 +475,7 @@ static int submit_flush_wait(struct f2fs_sb_info *sbi)
 static int issue_flush_thread(void *data)
 {
 	struct f2fs_sb_info *sbi = data;
-	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+	struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
 	wait_queue_head_t *q = &fcc->flush_wait_queue;
 repeat:
 	if (kthread_should_stop())
@@ -448,6 +489,8 @@ repeat:
 		fcc->dispatch_list = llist_reverse_order(fcc->dispatch_list);
 
 		ret = submit_flush_wait(sbi);
+		atomic_inc(&fcc->issued_flush);
+
 		llist_for_each_entry_safe(cmd, next,
 					  fcc->dispatch_list, llnode) {
 			cmd->ret = ret;
@@ -463,27 +506,31 @@ repeat:
 
 int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 {
-	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+	struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
 	struct flush_cmd cmd;
-
-	trace_f2fs_issue_flush(sbi->sb, test_opt(sbi, NOBARRIER),
-					test_opt(sbi, FLUSH_MERGE));
+	int ret;
 
 	if (test_opt(sbi, NOBARRIER))
 		return 0;
 
-	if (!test_opt(sbi, FLUSH_MERGE) || !atomic_read(&fcc->submit_flush)) {
-		int ret;
+	if (!test_opt(sbi, FLUSH_MERGE)) {
+		ret = submit_flush_wait(sbi);
+		atomic_inc(&fcc->issued_flush);
+		return ret;
+	}
 
-		atomic_inc(&fcc->submit_flush);
+	if (!atomic_read(&fcc->issing_flush)) {
+		atomic_inc(&fcc->issing_flush);
 		ret = submit_flush_wait(sbi);
-		atomic_dec(&fcc->submit_flush);
+		atomic_dec(&fcc->issing_flush);
+
+		atomic_inc(&fcc->issued_flush);
 		return ret;
 	}
 
 	init_completion(&cmd.wait);
 
-	atomic_inc(&fcc->submit_flush);
+	atomic_inc(&fcc->issing_flush);
 	llist_add(&cmd.llnode, &fcc->issue_list);
 
 	if (!fcc->dispatch_list)
@@ -491,10 +538,10 @@ int f2fs_issue_flush(struct f2fs_sb_info *sbi)
 
 	if (fcc->f2fs_issue_flush) {
 		wait_for_completion(&cmd.wait);
-		atomic_dec(&fcc->submit_flush);
+		atomic_dec(&fcc->issing_flush);
 	} else {
 		llist_del_all(&fcc->issue_list);
-		atomic_set(&fcc->submit_flush, 0);
+		atomic_set(&fcc->issing_flush, 0);
 	}
 
 	return cmd.ret;
@@ -506,25 +553,31 @@ int create_flush_cmd_control(struct f2fs_sb_info *sbi)
 	struct flush_cmd_control *fcc;
 	int err = 0;
 
-	if (SM_I(sbi)->cmd_control_info) {
-		fcc = SM_I(sbi)->cmd_control_info;
+	if (SM_I(sbi)->fcc_info) {
+		fcc = SM_I(sbi)->fcc_info;
+		if (fcc->f2fs_issue_flush)
+			return err;
 		goto init_thread;
 	}
 
 	fcc = kzalloc(sizeof(struct flush_cmd_control), GFP_KERNEL);
 	if (!fcc)
 		return -ENOMEM;
-	atomic_set(&fcc->submit_flush, 0);
+	atomic_set(&fcc->issued_flush, 0);
+	atomic_set(&fcc->issing_flush, 0);
 	init_waitqueue_head(&fcc->flush_wait_queue);
 	init_llist_head(&fcc->issue_list);
-	SM_I(sbi)->cmd_control_info = fcc;
+	SM_I(sbi)->fcc_info = fcc;
+	if (!test_opt(sbi, FLUSH_MERGE))
+		return err;
+
 init_thread:
 	fcc->f2fs_issue_flush = kthread_run(issue_flush_thread, sbi,
 				"f2fs_flush-%u:%u", MAJOR(dev), MINOR(dev));
 	if (IS_ERR(fcc->f2fs_issue_flush)) {
 		err = PTR_ERR(fcc->f2fs_issue_flush);
 		kfree(fcc);
-		SM_I(sbi)->cmd_control_info = NULL;
+		SM_I(sbi)->fcc_info = NULL;
 		return err;
 	}
 
@@ -533,7 +586,7 @@ init_thread:
 
 void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
 {
-	struct flush_cmd_control *fcc = SM_I(sbi)->cmd_control_info;
+	struct flush_cmd_control *fcc = SM_I(sbi)->fcc_info;
 
 	if (fcc && fcc->f2fs_issue_flush) {
 		struct task_struct *flush_thread = fcc->f2fs_issue_flush;
@@ -543,7 +596,7 @@ void destroy_flush_cmd_control(struct f2fs_sb_info *sbi, bool free)
 	}
 	if (free) {
 		kfree(fcc);
-		SM_I(sbi)->cmd_control_info = NULL;
+		SM_I(sbi)->fcc_info = NULL;
 	}
 }
 
@@ -587,8 +640,8 @@ static void __remove_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno,
 		if (test_and_clear_bit(segno, dirty_i->dirty_segmap[t]))
 			dirty_i->nr_dirty[t]--;
 
-		if (get_valid_blocks(sbi, segno, sbi->segs_per_sec) == 0)
-			clear_bit(GET_SECNO(sbi, segno),
+		if (get_valid_blocks(sbi, segno, true) == 0)
+			clear_bit(GET_SEC_FROM_SEG(sbi, segno),
 						dirty_i->victim_secmap);
 	}
 }
@@ -608,7 +661,7 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
 
 	mutex_lock(&dirty_i->seglist_lock);
 
-	valid_blocks = get_valid_blocks(sbi, segno, 0);
+	valid_blocks = get_valid_blocks(sbi, segno, false);
 
 	if (valid_blocks == 0) {
 		__locate_dirty_segment(sbi, segno, PRE);
@@ -623,104 +676,476 @@ static void locate_dirty_segment(struct f2fs_sb_info *sbi, unsigned int segno)
 	mutex_unlock(&dirty_i->seglist_lock);
 }
 
-static struct bio_entry *__add_bio_entry(struct f2fs_sb_info *sbi,
-							struct bio *bio)
+static struct discard_cmd *__create_discard_cmd(struct f2fs_sb_info *sbi,
+		struct block_device *bdev, block_t lstart,
+		block_t start, block_t len)
 {
-	struct list_head *wait_list = &(SM_I(sbi)->wait_list);
-	struct bio_entry *be = f2fs_kmem_cache_alloc(bio_entry_slab, GFP_NOFS);
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct list_head *pend_list;
+	struct discard_cmd *dc;
 
-	INIT_LIST_HEAD(&be->list);
-	be->bio = bio;
-	init_completion(&be->event);
-	list_add_tail(&be->list, wait_list);
+	f2fs_bug_on(sbi, !len);
 
-	return be;
+	pend_list = &dcc->pend_list[plist_idx(len)];
+
+	dc = f2fs_kmem_cache_alloc(discard_cmd_slab, GFP_NOFS);
+	INIT_LIST_HEAD(&dc->list);
+	dc->bdev = bdev;
+	dc->lstart = lstart;
+	dc->start = start;
+	dc->len = len;
+	dc->ref = 0;
+	dc->state = D_PREP;
+	dc->error = 0;
+	init_completion(&dc->wait);
+	list_add_tail(&dc->list, pend_list);
+	atomic_inc(&dcc->discard_cmd_cnt);
+	dcc->undiscard_blks += len;
+
+	return dc;
 }
 
-void f2fs_wait_all_discard_bio(struct f2fs_sb_info *sbi)
+static struct discard_cmd *__attach_discard_cmd(struct f2fs_sb_info *sbi,
+				struct block_device *bdev, block_t lstart,
+				block_t start, block_t len,
+				struct rb_node *parent, struct rb_node **p)
 {
-	struct list_head *wait_list = &(SM_I(sbi)->wait_list);
-	struct bio_entry *be, *tmp;
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct discard_cmd *dc;
 
-	list_for_each_entry_safe(be, tmp, wait_list, list) {
-		struct bio *bio = be->bio;
-		int err;
+	dc = __create_discard_cmd(sbi, bdev, lstart, start, len);
 
-		wait_for_completion_io(&be->event);
-		err = be->error;
-		if (err == -EOPNOTSUPP)
-			err = 0;
+	rb_link_node(&dc->rb_node, parent, p);
+	rb_insert_color(&dc->rb_node, &dcc->root);
 
-		if (err)
-			f2fs_msg(sbi->sb, KERN_INFO,
-				"Issue discard failed, ret: %d", err);
+	return dc;
+}
 
-		bio_put(bio);
-		list_del(&be->list);
-		kmem_cache_free(bio_entry_slab, be);
-	}
+static void __detach_discard_cmd(struct discard_cmd_control *dcc,
+							struct discard_cmd *dc)
+{
+	if (dc->state == D_DONE)
+		atomic_dec(&dcc->issing_discard);
+
+	list_del(&dc->list);
+	rb_erase(&dc->rb_node, &dcc->root);
+	dcc->undiscard_blks -= dc->len;
+
+	kmem_cache_free(discard_cmd_slab, dc);
+
+	atomic_dec(&dcc->discard_cmd_cnt);
 }
 
-static void f2fs_submit_bio_wait_endio(struct bio *bio)
+static void __remove_discard_cmd(struct f2fs_sb_info *sbi,
+							struct discard_cmd *dc)
 {
-	struct bio_entry *be = (struct bio_entry *)bio->bi_private;
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+
+	f2fs_bug_on(sbi, dc->ref);
 
-	be->error = bio->bi_error;
-	complete(&be->event);
+	if (dc->error == -EOPNOTSUPP)
+		dc->error = 0;
+
+	if (dc->error)
+		f2fs_msg(sbi->sb, KERN_INFO,
+			"Issue discard(%u, %u, %u) failed, ret: %d",
+			dc->lstart, dc->start, dc->len, dc->error);
+	__detach_discard_cmd(dcc, dc);
+}
+
+static void f2fs_submit_discard_endio(struct bio *bio)
+{
+	struct discard_cmd *dc = (struct discard_cmd *)bio->bi_private;
+
+	dc->error = blk_status_to_errno(bio->bi_status);
+	dc->state = D_DONE;
+	complete_all(&dc->wait);
+	bio_put(bio);
+}
+
+void __check_sit_bitmap(struct f2fs_sb_info *sbi,
+				block_t start, block_t end)
+{
+#ifdef CONFIG_F2FS_CHECK_FS
+	struct seg_entry *sentry;
+	unsigned int segno;
+	block_t blk = start;
+	unsigned long offset, size, max_blocks = sbi->blocks_per_seg;
+	unsigned long *map;
+
+	while (blk < end) {
+		segno = GET_SEGNO(sbi, blk);
+		sentry = get_seg_entry(sbi, segno);
+		offset = GET_BLKOFF_FROM_SEG0(sbi, blk);
+
+		size = min((unsigned long)(end - blk), max_blocks);
+		map = (unsigned long *)(sentry->cur_valid_map);
+		offset = __find_rev_next_bit(map, size, offset);
+		f2fs_bug_on(sbi, offset != size);
+		blk += size;
+	}
+#endif
 }
 
 /* this function is copied from blkdev_issue_discard from block/blk-lib.c */
-static int __f2fs_issue_discard_async(struct f2fs_sb_info *sbi,
-		struct block_device *bdev, block_t blkstart, block_t blklen)
+static void __submit_discard_cmd(struct f2fs_sb_info *sbi,
+				struct discard_cmd *dc)
 {
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
 	struct bio *bio = NULL;
-	int err;
 
-	trace_f2fs_issue_discard(sbi->sb, blkstart, blklen);
+	if (dc->state != D_PREP)
+		return;
+
+	trace_f2fs_issue_discard(dc->bdev, dc->start, dc->len);
+
+	dc->error = __blkdev_issue_discard(dc->bdev,
+				SECTOR_FROM_BLOCK(dc->start),
+				SECTOR_FROM_BLOCK(dc->len),
+				GFP_NOFS, 0, &bio);
+	if (!dc->error) {
+		/* should keep before submission to avoid D_DONE right away */
+		dc->state = D_SUBMIT;
+		atomic_inc(&dcc->issued_discard);
+		atomic_inc(&dcc->issing_discard);
+		if (bio) {
+			bio->bi_private = dc;
+			bio->bi_end_io = f2fs_submit_discard_endio;
+			bio->bi_opf |= REQ_SYNC;
+			submit_bio(bio);
+			list_move_tail(&dc->list, &dcc->wait_list);
+			__check_sit_bitmap(sbi, dc->start, dc->start + dc->len);
+		}
+	} else {
+		__remove_discard_cmd(sbi, dc);
+	}
+}
+
+static struct discard_cmd *__insert_discard_tree(struct f2fs_sb_info *sbi,
+				struct block_device *bdev, block_t lstart,
+				block_t start, block_t len,
+				struct rb_node **insert_p,
+				struct rb_node *insert_parent)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct rb_node **p = &dcc->root.rb_node;
+	struct rb_node *parent = NULL;
+	struct discard_cmd *dc = NULL;
+
+	if (insert_p && insert_parent) {
+		parent = insert_parent;
+		p = insert_p;
+		goto do_insert;
+	}
+
+	p = __lookup_rb_tree_for_insert(sbi, &dcc->root, &parent, lstart);
+do_insert:
+	dc = __attach_discard_cmd(sbi, bdev, lstart, start, len, parent, p);
+	if (!dc)
+		return NULL;
+
+	return dc;
+}
+
+static void __relocate_discard_cmd(struct discard_cmd_control *dcc,
+						struct discard_cmd *dc)
+{
+	list_move_tail(&dc->list, &dcc->pend_list[plist_idx(dc->len)]);
+}
+
+static void __punch_discard_cmd(struct f2fs_sb_info *sbi,
+				struct discard_cmd *dc, block_t blkaddr)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct discard_info di = dc->di;
+	bool modified = false;
+
+	if (dc->state == D_DONE || dc->len == 1) {
+		__remove_discard_cmd(sbi, dc);
+		return;
+	}
+
+	dcc->undiscard_blks -= di.len;
+
+	if (blkaddr > di.lstart) {
+		dc->len = blkaddr - dc->lstart;
+		dcc->undiscard_blks += dc->len;
+		__relocate_discard_cmd(dcc, dc);
+		modified = true;
+	}
+
+	if (blkaddr < di.lstart + di.len - 1) {
+		if (modified) {
+			__insert_discard_tree(sbi, dc->bdev, blkaddr + 1,
+					di.start + blkaddr + 1 - di.lstart,
+					di.lstart + di.len - 1 - blkaddr,
+					NULL, NULL);
+		} else {
+			dc->lstart++;
+			dc->len--;
+			dc->start++;
+			dcc->undiscard_blks += dc->len;
+			__relocate_discard_cmd(dcc, dc);
+		}
+	}
+}
+
+static void __update_discard_tree_range(struct f2fs_sb_info *sbi,
+				struct block_device *bdev, block_t lstart,
+				block_t start, block_t len)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct discard_cmd *prev_dc = NULL, *next_dc = NULL;
+	struct discard_cmd *dc;
+	struct discard_info di = {0};
+	struct rb_node **insert_p = NULL, *insert_parent = NULL;
+	block_t end = lstart + len;
+
+	mutex_lock(&dcc->cmd_lock);
+
+	dc = (struct discard_cmd *)__lookup_rb_tree_ret(&dcc->root,
+					NULL, lstart,
+					(struct rb_entry **)&prev_dc,
+					(struct rb_entry **)&next_dc,
+					&insert_p, &insert_parent, true);
+	if (dc)
+		prev_dc = dc;
+
+	if (!prev_dc) {
+		di.lstart = lstart;
+		di.len = next_dc ? next_dc->lstart - lstart : len;
+		di.len = min(di.len, len);
+		di.start = start;
+	}
+
+	while (1) {
+		struct rb_node *node;
+		bool merged = false;
+		struct discard_cmd *tdc = NULL;
+
+		if (prev_dc) {
+			di.lstart = prev_dc->lstart + prev_dc->len;
+			if (di.lstart < lstart)
+				di.lstart = lstart;
+			if (di.lstart >= end)
+				break;
+
+			if (!next_dc || next_dc->lstart > end)
+				di.len = end - di.lstart;
+			else
+				di.len = next_dc->lstart - di.lstart;
+			di.start = start + di.lstart - lstart;
+		}
+
+		if (!di.len)
+			goto next;
+
+		if (prev_dc && prev_dc->state == D_PREP &&
+			prev_dc->bdev == bdev &&
+			__is_discard_back_mergeable(&di, &prev_dc->di)) {
+			prev_dc->di.len += di.len;
+			dcc->undiscard_blks += di.len;
+			__relocate_discard_cmd(dcc, prev_dc);
+			di = prev_dc->di;
+			tdc = prev_dc;
+			merged = true;
+		}
+
+		if (next_dc && next_dc->state == D_PREP &&
+			next_dc->bdev == bdev &&
+			__is_discard_front_mergeable(&di, &next_dc->di)) {
+			next_dc->di.lstart = di.lstart;
+			next_dc->di.len += di.len;
+			next_dc->di.start = di.start;
+			dcc->undiscard_blks += di.len;
+			__relocate_discard_cmd(dcc, next_dc);
+			if (tdc)
+				__remove_discard_cmd(sbi, tdc);
+			merged = true;
+		}
+
+		if (!merged) {
+			__insert_discard_tree(sbi, bdev, di.lstart, di.start,
+							di.len, NULL, NULL);
+		}
+ next:
+		prev_dc = next_dc;
+		if (!prev_dc)
+			break;
+
+		node = rb_next(&prev_dc->rb_node);
+		next_dc = rb_entry_safe(node, struct discard_cmd, rb_node);
+	}
+
+	mutex_unlock(&dcc->cmd_lock);
+}
+
+static int __queue_discard_cmd(struct f2fs_sb_info *sbi,
+		struct block_device *bdev, block_t blkstart, block_t blklen)
+{
+	block_t lblkstart = blkstart;
+
+	trace_f2fs_queue_discard(bdev, blkstart, blklen);
 
 	if (sbi->s_ndevs) {
 		int devi = f2fs_target_device_index(sbi, blkstart);
 
 		blkstart -= FDEV(devi).start_blk;
 	}
-	err = __blkdev_issue_discard(bdev,
-				SECTOR_FROM_BLOCK(blkstart),
-				SECTOR_FROM_BLOCK(blklen),
-				GFP_NOFS, 0, &bio);
-	if (!err && bio) {
-		struct bio_entry *be = __add_bio_entry(sbi, bio);
+	__update_discard_tree_range(sbi, bdev, lblkstart, blkstart, blklen);
+	return 0;
+}
+
+static void __issue_discard_cmd(struct f2fs_sb_info *sbi, bool issue_cond)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct list_head *pend_list;
+	struct discard_cmd *dc, *tmp;
+	struct blk_plug plug;
+	int i, iter = 0;
 
-		bio->bi_private = be;
-		bio->bi_end_io = f2fs_submit_bio_wait_endio;
-		bio->bi_opf |= REQ_SYNC;
-		submit_bio(bio);
+	mutex_lock(&dcc->cmd_lock);
+	f2fs_bug_on(sbi,
+		!__check_rb_tree_consistence(sbi, &dcc->root));
+	blk_start_plug(&plug);
+	for (i = MAX_PLIST_NUM - 1; i >= 0; i--) {
+		pend_list = &dcc->pend_list[i];
+		list_for_each_entry_safe(dc, tmp, pend_list, list) {
+			f2fs_bug_on(sbi, dc->state != D_PREP);
+
+			if (!issue_cond || is_idle(sbi))
+				__submit_discard_cmd(sbi, dc);
+			if (issue_cond && iter++ > DISCARD_ISSUE_RATE)
+				goto out;
+		}
 	}
+out:
+	blk_finish_plug(&plug);
+	mutex_unlock(&dcc->cmd_lock);
+}
 
-	return err;
+static void __wait_one_discard_bio(struct f2fs_sb_info *sbi,
+							struct discard_cmd *dc)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+
+	wait_for_completion_io(&dc->wait);
+	mutex_lock(&dcc->cmd_lock);
+	f2fs_bug_on(sbi, dc->state != D_DONE);
+	dc->ref--;
+	if (!dc->ref)
+		__remove_discard_cmd(sbi, dc);
+	mutex_unlock(&dcc->cmd_lock);
+}
+
+static void __wait_discard_cmd(struct f2fs_sb_info *sbi, bool wait_cond)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct list_head *wait_list = &(dcc->wait_list);
+	struct discard_cmd *dc, *tmp;
+	bool need_wait;
+
+next:
+	need_wait = false;
+
+	mutex_lock(&dcc->cmd_lock);
+	list_for_each_entry_safe(dc, tmp, wait_list, list) {
+		if (!wait_cond || (dc->state == D_DONE && !dc->ref)) {
+			wait_for_completion_io(&dc->wait);
+			__remove_discard_cmd(sbi, dc);
+		} else {
+			dc->ref++;
+			need_wait = true;
+			break;
+		}
+	}
+	mutex_unlock(&dcc->cmd_lock);
+
+	if (need_wait) {
+		__wait_one_discard_bio(sbi, dc);
+		goto next;
+	}
+}
+
+/* This should be covered by global mutex, &sit_i->sentry_lock */
+void f2fs_wait_discard_bio(struct f2fs_sb_info *sbi, block_t blkaddr)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	struct discard_cmd *dc;
+	bool need_wait = false;
+
+	mutex_lock(&dcc->cmd_lock);
+	dc = (struct discard_cmd *)__lookup_rb_tree(&dcc->root, NULL, blkaddr);
+	if (dc) {
+		if (dc->state == D_PREP) {
+			__punch_discard_cmd(sbi, dc, blkaddr);
+		} else {
+			dc->ref++;
+			need_wait = true;
+		}
+	}
+	mutex_unlock(&dcc->cmd_lock);
+
+	if (need_wait)
+		__wait_one_discard_bio(sbi, dc);
+}
+
+void stop_discard_thread(struct f2fs_sb_info *sbi)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+
+	if (dcc && dcc->f2fs_issue_discard) {
+		struct task_struct *discard_thread = dcc->f2fs_issue_discard;
+
+		dcc->f2fs_issue_discard = NULL;
+		kthread_stop(discard_thread);
+	}
+}
+
+/* This comes from f2fs_put_super */
+void f2fs_wait_discard_bios(struct f2fs_sb_info *sbi)
+{
+	__issue_discard_cmd(sbi, false);
+	__wait_discard_cmd(sbi, false);
+}
+
+static int issue_discard_thread(void *data)
+{
+	struct f2fs_sb_info *sbi = data;
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+	wait_queue_head_t *q = &dcc->discard_wait_queue;
+
+	set_freezable();
+
+	do {
+		wait_event_interruptible(*q, kthread_should_stop() ||
+					freezing(current) ||
+					atomic_read(&dcc->discard_cmd_cnt));
+		if (try_to_freeze())
+			continue;
+		if (kthread_should_stop())
+			return 0;
+
+		__issue_discard_cmd(sbi, true);
+		__wait_discard_cmd(sbi, true);
+
+		congestion_wait(BLK_RW_SYNC, HZ/50);
+	} while (!kthread_should_stop());
+	return 0;
 }
 
 #ifdef CONFIG_BLK_DEV_ZONED
 static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
 		struct block_device *bdev, block_t blkstart, block_t blklen)
 {
-	sector_t nr_sects = SECTOR_FROM_BLOCK(blklen);
-	sector_t sector;
+	sector_t sector, nr_sects;
+	block_t lblkstart = blkstart;
 	int devi = 0;
 
 	if (sbi->s_ndevs) {
 		devi = f2fs_target_device_index(sbi, blkstart);
 		blkstart -= FDEV(devi).start_blk;
 	}
-	sector = SECTOR_FROM_BLOCK(blkstart);
-
-	if (sector & (bdev_zone_sectors(bdev) - 1) ||
-	    nr_sects != bdev_zone_sectors(bdev)) {
-		f2fs_msg(sbi->sb, KERN_INFO,
-			"(%d) %s: Unaligned discard attempted (block %x + %x)",
-			devi, sbi->s_ndevs ? FDEV(devi).path: "",
-			blkstart, blklen);
-		return -EIO;
-	}
 
 	/*
 	 * We need to know the type of the zone: for conventional zones,
@@ -732,10 +1157,21 @@ static int __f2fs_issue_discard_zone(struct f2fs_sb_info *sbi,
 	case BLK_ZONE_TYPE_CONVENTIONAL:
 		if (!blk_queue_discard(bdev_get_queue(bdev)))
 			return 0;
-		return __f2fs_issue_discard_async(sbi, bdev, blkstart, blklen);
+		return __queue_discard_cmd(sbi, bdev, lblkstart, blklen);
 	case BLK_ZONE_TYPE_SEQWRITE_REQ:
 	case BLK_ZONE_TYPE_SEQWRITE_PREF:
-		trace_f2fs_issue_reset_zone(sbi->sb, blkstart);
+		sector = SECTOR_FROM_BLOCK(blkstart);
+		nr_sects = SECTOR_FROM_BLOCK(blklen);
+
+		if (sector & (bdev_zone_sectors(bdev) - 1) ||
+				nr_sects != bdev_zone_sectors(bdev)) {
+			f2fs_msg(sbi->sb, KERN_INFO,
+				"(%d) %s: Unaligned discard attempted (block %x + %x)",
+				devi, sbi->s_ndevs ? FDEV(devi).path: "",
+				blkstart, blklen);
+			return -EIO;
+		}
+		trace_f2fs_issue_reset_zone(bdev, blkstart);
 		return blkdev_reset_zones(bdev, sector,
 					  nr_sects, GFP_NOFS);
 	default:
@@ -753,7 +1189,7 @@ static int __issue_discard_async(struct f2fs_sb_info *sbi,
 				bdev_zoned_model(bdev) != BLK_ZONED_NONE)
 		return __f2fs_issue_discard_zone(sbi, bdev, blkstart, blklen);
 #endif
-	return __f2fs_issue_discard_async(sbi, bdev, blkstart, blklen);
+	return __queue_discard_cmd(sbi, bdev, blkstart, blklen);
 }
 
 static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
@@ -796,32 +1232,8 @@ static int f2fs_issue_discard(struct f2fs_sb_info *sbi,
 	return err;
 }
 
-static void __add_discard_entry(struct f2fs_sb_info *sbi,
-		struct cp_control *cpc, struct seg_entry *se,
-		unsigned int start, unsigned int end)
-{
-	struct list_head *head = &SM_I(sbi)->discard_list;
-	struct discard_entry *new, *last;
-
-	if (!list_empty(head)) {
-		last = list_last_entry(head, struct discard_entry, list);
-		if (START_BLOCK(sbi, cpc->trim_start) + start ==
-						last->blkaddr + last->len) {
-			last->len += end - start;
-			goto done;
-		}
-	}
-
-	new = f2fs_kmem_cache_alloc(discard_entry_slab, GFP_NOFS);
-	INIT_LIST_HEAD(&new->list);
-	new->blkaddr = START_BLOCK(sbi, cpc->trim_start) + start;
-	new->len = end - start;
-	list_add_tail(&new->list, head);
-done:
-	SM_I(sbi)->nr_discards += end - start;
-}
-
-static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+static bool add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc,
+							bool check_only)
 {
 	int entries = SIT_VBLOCK_MAP_SIZE / sizeof(unsigned long);
 	int max_blocks = sbi->blocks_per_seg;
@@ -831,16 +1243,19 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	unsigned long *discard_map = (unsigned long *)se->discard_map;
 	unsigned long *dmap = SIT_I(sbi)->tmp_map;
 	unsigned int start = 0, end = -1;
-	bool force = (cpc->reason == CP_DISCARD);
+	bool force = (cpc->reason & CP_DISCARD);
+	struct discard_entry *de = NULL;
+	struct list_head *head = &SM_I(sbi)->dcc_info->entry_list;
 	int i;
 
 	if (se->valid_blocks == max_blocks || !f2fs_discard_en(sbi))
-		return;
+		return false;
 
 	if (!force) {
 		if (!test_opt(sbi, DISCARD) || !se->valid_blocks ||
-		    SM_I(sbi)->nr_discards >= SM_I(sbi)->max_discards)
-			return;
+			SM_I(sbi)->dcc_info->nr_discards >=
+				SM_I(sbi)->dcc_info->max_discards)
+			return false;
 	}
 
 	/* SIT_VBLOCK_MAP_SIZE should be multiple of sizeof(unsigned long) */
@@ -848,7 +1263,8 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 		dmap[i] = force ? ~ckpt_map[i] & ~discard_map[i] :
 				(cur_map[i] ^ ckpt_map[i]) & ckpt_map[i];
 
-	while (force || SM_I(sbi)->nr_discards <= SM_I(sbi)->max_discards) {
+	while (force || SM_I(sbi)->dcc_info->nr_discards <=
+				SM_I(sbi)->dcc_info->max_discards) {
 		start = __find_rev_next_bit(dmap, max_blocks, end + 1);
 		if (start >= max_blocks)
 			break;
@@ -858,13 +1274,27 @@ static void add_discard_addrs(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 					&& (end - start) < cpc->trim_minlen)
 			continue;
 
-		__add_discard_entry(sbi, cpc, se, start, end);
+		if (check_only)
+			return true;
+
+		if (!de) {
+			de = f2fs_kmem_cache_alloc(discard_entry_slab,
+								GFP_F2FS_ZERO);
+			de->start_blkaddr = START_BLOCK(sbi, cpc->trim_start);
+			list_add_tail(&de->list, head);
+		}
+
+		for (i = start; i < end; i++)
+			__set_bit_le(i, (void *)de->discard_map);
+
+		SM_I(sbi)->dcc_info->nr_discards += end - start;
 	}
+	return false;
 }
 
 void release_discard_addrs(struct f2fs_sb_info *sbi)
 {
-	struct list_head *head = &(SM_I(sbi)->discard_list);
+	struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list);
 	struct discard_entry *entry, *this;
 
 	/* drop caches */
@@ -890,16 +1320,13 @@ static void set_prefree_as_free_segments(struct f2fs_sb_info *sbi)
 
 void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 {
-	struct list_head *head = &(SM_I(sbi)->discard_list);
+	struct list_head *head = &(SM_I(sbi)->dcc_info->entry_list);
 	struct discard_entry *entry, *this;
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
-	struct blk_plug plug;
 	unsigned long *prefree_map = dirty_i->dirty_segmap[PRE];
 	unsigned int start = 0, end = -1;
 	unsigned int secno, start_segno;
-	bool force = (cpc->reason == CP_DISCARD);
-
-	blk_start_plug(&plug);
+	bool force = (cpc->reason & CP_DISCARD);
 
 	mutex_lock(&dirty_i->seglist_lock);
 
@@ -916,41 +1343,126 @@ void clear_prefree_segments(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 
 		dirty_i->nr_dirty[PRE] -= end - start;
 
-		if (force || !test_opt(sbi, DISCARD))
+		if (!test_opt(sbi, DISCARD))
 			continue;
 
+		if (force && start >= cpc->trim_start &&
+					(end - 1) <= cpc->trim_end)
+				continue;
+
 		if (!test_opt(sbi, LFS) || sbi->segs_per_sec == 1) {
 			f2fs_issue_discard(sbi, START_BLOCK(sbi, start),
 				(end - start) << sbi->log_blocks_per_seg);
 			continue;
 		}
 next:
-		secno = GET_SECNO(sbi, start);
-		start_segno = secno * sbi->segs_per_sec;
+		secno = GET_SEC_FROM_SEG(sbi, start);
+		start_segno = GET_SEG_FROM_SEC(sbi, secno);
 		if (!IS_CURSEC(sbi, secno) &&
-			!get_valid_blocks(sbi, start, sbi->segs_per_sec))
+			!get_valid_blocks(sbi, start, true))
 			f2fs_issue_discard(sbi, START_BLOCK(sbi, start_segno),
 				sbi->segs_per_sec << sbi->log_blocks_per_seg);
 
 		start = start_segno + sbi->segs_per_sec;
 		if (start < end)
 			goto next;
+		else
+			end = start - 1;
 	}
 	mutex_unlock(&dirty_i->seglist_lock);
 
 	/* send small discards */
 	list_for_each_entry_safe(entry, this, head, list) {
-		if (force && entry->len < cpc->trim_minlen)
-			goto skip;
-		f2fs_issue_discard(sbi, entry->blkaddr, entry->len);
-		cpc->trimmed += entry->len;
+		unsigned int cur_pos = 0, next_pos, len, total_len = 0;
+		bool is_valid = test_bit_le(0, entry->discard_map);
+
+find_next:
+		if (is_valid) {
+			next_pos = find_next_zero_bit_le(entry->discard_map,
+					sbi->blocks_per_seg, cur_pos);
+			len = next_pos - cur_pos;
+
+			if (f2fs_sb_mounted_blkzoned(sbi->sb) ||
+			    (force && len < cpc->trim_minlen))
+				goto skip;
+
+			f2fs_issue_discard(sbi, entry->start_blkaddr + cur_pos,
+									len);
+			cpc->trimmed += len;
+			total_len += len;
+		} else {
+			next_pos = find_next_bit_le(entry->discard_map,
+					sbi->blocks_per_seg, cur_pos);
+		}
 skip:
+		cur_pos = next_pos;
+		is_valid = !is_valid;
+
+		if (cur_pos < sbi->blocks_per_seg)
+			goto find_next;
+
 		list_del(&entry->list);
-		SM_I(sbi)->nr_discards -= entry->len;
+		SM_I(sbi)->dcc_info->nr_discards -= total_len;
 		kmem_cache_free(discard_entry_slab, entry);
 	}
 
-	blk_finish_plug(&plug);
+	wake_up(&SM_I(sbi)->dcc_info->discard_wait_queue);
+}
+
+static int create_discard_cmd_control(struct f2fs_sb_info *sbi)
+{
+	dev_t dev = sbi->sb->s_bdev->bd_dev;
+	struct discard_cmd_control *dcc;
+	int err = 0, i;
+
+	if (SM_I(sbi)->dcc_info) {
+		dcc = SM_I(sbi)->dcc_info;
+		goto init_thread;
+	}
+
+	dcc = kzalloc(sizeof(struct discard_cmd_control), GFP_KERNEL);
+	if (!dcc)
+		return -ENOMEM;
+
+	INIT_LIST_HEAD(&dcc->entry_list);
+	for (i = 0; i < MAX_PLIST_NUM; i++)
+		INIT_LIST_HEAD(&dcc->pend_list[i]);
+	INIT_LIST_HEAD(&dcc->wait_list);
+	mutex_init(&dcc->cmd_lock);
+	atomic_set(&dcc->issued_discard, 0);
+	atomic_set(&dcc->issing_discard, 0);
+	atomic_set(&dcc->discard_cmd_cnt, 0);
+	dcc->nr_discards = 0;
+	dcc->max_discards = MAIN_SEGS(sbi) << sbi->log_blocks_per_seg;
+	dcc->undiscard_blks = 0;
+	dcc->root = RB_ROOT;
+
+	init_waitqueue_head(&dcc->discard_wait_queue);
+	SM_I(sbi)->dcc_info = dcc;
+init_thread:
+	dcc->f2fs_issue_discard = kthread_run(issue_discard_thread, sbi,
+				"f2fs_discard-%u:%u", MAJOR(dev), MINOR(dev));
+	if (IS_ERR(dcc->f2fs_issue_discard)) {
+		err = PTR_ERR(dcc->f2fs_issue_discard);
+		kfree(dcc);
+		SM_I(sbi)->dcc_info = NULL;
+		return err;
+	}
+
+	return err;
+}
+
+static void destroy_discard_cmd_control(struct f2fs_sb_info *sbi)
+{
+	struct discard_cmd_control *dcc = SM_I(sbi)->dcc_info;
+
+	if (!dcc)
+		return;
+
+	stop_discard_thread(sbi);
+
+	kfree(dcc);
+	SM_I(sbi)->dcc_info = NULL;
 }
 
 static bool __mark_sit_entry_dirty(struct f2fs_sb_info *sbi, unsigned int segno)
@@ -995,14 +1507,38 @@ static void update_sit_entry(struct f2fs_sb_info *sbi, block_t blkaddr, int del)
 
 	/* Update valid block bitmap */
 	if (del > 0) {
-		if (f2fs_test_and_set_bit(offset, se->cur_valid_map))
+		if (f2fs_test_and_set_bit(offset, se->cur_valid_map)) {
+#ifdef CONFIG_F2FS_CHECK_FS
+			if (f2fs_test_and_set_bit(offset,
+						se->cur_valid_map_mir))
+				f2fs_bug_on(sbi, 1);
+			else
+				WARN_ON(1);
+#else
 			f2fs_bug_on(sbi, 1);
+#endif
+		}
 		if (f2fs_discard_en(sbi) &&
 			!f2fs_test_and_set_bit(offset, se->discard_map))
 			sbi->discard_blks--;
+
+		/* don't overwrite by SSR to keep node chain */
+		if (se->type == CURSEG_WARM_NODE) {
+			if (!f2fs_test_and_set_bit(offset, se->ckpt_valid_map))
+				se->ckpt_valid_blocks++;
+		}
 	} else {
-		if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map))
+		if (!f2fs_test_and_clear_bit(offset, se->cur_valid_map)) {
+#ifdef CONFIG_F2FS_CHECK_FS
+			if (!f2fs_test_and_clear_bit(offset,
+						se->cur_valid_map_mir))
+				f2fs_bug_on(sbi, 1);
+			else
+				WARN_ON(1);
+#else
 			f2fs_bug_on(sbi, 1);
+#endif
+		}
 		if (f2fs_discard_en(sbi) &&
 			f2fs_test_and_clear_bit(offset, se->discard_map))
 			sbi->discard_blks++;
@@ -1188,8 +1724,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 	struct free_segmap_info *free_i = FREE_I(sbi);
 	unsigned int segno, secno, zoneno;
 	unsigned int total_zones = MAIN_SECS(sbi) / sbi->secs_per_zone;
-	unsigned int hint = *newseg / sbi->segs_per_sec;
-	unsigned int old_zoneno = GET_ZONENO_FROM_SEGNO(sbi, *newseg);
+	unsigned int hint = GET_SEC_FROM_SEG(sbi, *newseg);
+	unsigned int old_zoneno = GET_ZONE_FROM_SEG(sbi, *newseg);
 	unsigned int left_start = hint;
 	bool init = true;
 	int go_left = 0;
@@ -1199,8 +1735,8 @@ static void get_new_segment(struct f2fs_sb_info *sbi,
 
 	if (!new_sec && ((*newseg + 1) % sbi->segs_per_sec)) {
 		segno = find_next_zero_bit(free_i->free_segmap,
-				(hint + 1) * sbi->segs_per_sec, *newseg + 1);
-		if (segno < (hint + 1) * sbi->segs_per_sec)
+			GET_SEG_FROM_SEC(sbi, hint + 1), *newseg + 1);
+		if (segno < GET_SEG_FROM_SEC(sbi, hint + 1))
 			goto got_it;
 	}
 find_other_zone:
@@ -1231,8 +1767,8 @@ find_other_zone:
 	secno = left_start;
 skip_left:
 	hint = secno;
-	segno = secno * sbi->segs_per_sec;
-	zoneno = secno / sbi->secs_per_zone;
+	segno = GET_SEG_FROM_SEC(sbi, secno);
+	zoneno = GET_ZONE_FROM_SEC(sbi, secno);
 
 	/* give up on finding another zone */
 	if (!init)
@@ -1276,7 +1812,7 @@ static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
 	struct summary_footer *sum_footer;
 
 	curseg->segno = curseg->next_segno;
-	curseg->zone = GET_ZONENO_FROM_SEGNO(sbi, curseg->segno);
+	curseg->zone = GET_ZONE_FROM_SEG(sbi, curseg->segno);
 	curseg->next_blkoff = 0;
 	curseg->next_segno = NULL_SEGNO;
 
@@ -1289,6 +1825,20 @@ static void reset_curseg(struct f2fs_sb_info *sbi, int type, int modified)
 	__set_sit_entry_type(sbi, type, curseg->segno, modified);
 }
 
+static unsigned int __get_next_segno(struct f2fs_sb_info *sbi, int type)
+{
+	/* if segs_per_sec is large than 1, we need to keep original policy. */
+	if (sbi->segs_per_sec != 1)
+		return CURSEG_I(sbi, type)->segno;
+
+	if (type == CURSEG_HOT_DATA || IS_NODESEG(type))
+		return 0;
+
+	if (SIT_I(sbi)->last_victim[ALLOC_NEXT])
+		return SIT_I(sbi)->last_victim[ALLOC_NEXT];
+	return CURSEG_I(sbi, type)->segno;
+}
+
 /*
  * Allocate a current working segment.
  * This function always allocates a free segment in LFS manner.
@@ -1307,6 +1857,7 @@ static void new_curseg(struct f2fs_sb_info *sbi, int type, bool new_sec)
 	if (test_opt(sbi, NOHEAP))
 		dir = ALLOC_RIGHT;
 
+	segno = __get_next_segno(sbi, type);
 	get_new_segment(sbi, &segno, new_sec, dir);
 	curseg->next_segno = segno;
 	reset_curseg(sbi, type, 1);
@@ -1382,16 +1933,43 @@ static int get_ssr_segment(struct f2fs_sb_info *sbi, int type)
 {
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
 	const struct victim_selection *v_ops = DIRTY_I(sbi)->v_ops;
+	unsigned segno = NULL_SEGNO;
+	int i, cnt;
+	bool reversed = false;
 
-	if (IS_NODESEG(type) || !has_not_enough_free_secs(sbi, 0, 0))
-		return v_ops->get_victim(sbi,
-				&(curseg)->next_segno, BG_GC, type, SSR);
+	/* need_SSR() already forces to do this */
+	if (v_ops->get_victim(sbi, &segno, BG_GC, type, SSR)) {
+		curseg->next_segno = segno;
+		return 1;
+	}
 
-	/* For data segments, let's do SSR more intensively */
-	for (; type >= CURSEG_HOT_DATA; type--)
-		if (v_ops->get_victim(sbi, &(curseg)->next_segno,
-						BG_GC, type, SSR))
+	/* For node segments, let's do SSR more intensively */
+	if (IS_NODESEG(type)) {
+		if (type >= CURSEG_WARM_NODE) {
+			reversed = true;
+			i = CURSEG_COLD_NODE;
+		} else {
+			i = CURSEG_HOT_NODE;
+		}
+		cnt = NR_CURSEG_NODE_TYPE;
+	} else {
+		if (type >= CURSEG_WARM_DATA) {
+			reversed = true;
+			i = CURSEG_COLD_DATA;
+		} else {
+			i = CURSEG_HOT_DATA;
+		}
+		cnt = NR_CURSEG_DATA_TYPE;
+	}
+
+	for (; cnt-- > 0; reversed ? i-- : i++) {
+		if (i == type)
+			continue;
+		if (v_ops->get_victim(sbi, &segno, BG_GC, i, SSR)) {
+			curseg->next_segno = segno;
 			return 1;
+		}
+	}
 	return 0;
 }
 
@@ -1406,7 +1984,8 @@ static void allocate_segment_by_default(struct f2fs_sb_info *sbi,
 
 	if (force)
 		new_curseg(sbi, type, true);
-	else if (type == CURSEG_WARM_NODE)
+	else if (!is_set_ckpt_flags(sbi, CP_CRC_RECOVERY_FLAG) &&
+					type == CURSEG_WARM_NODE)
 		new_curseg(sbi, type, false);
 	else if (curseg->alloc_type == LFS && is_next_segment_free(sbi, type))
 		new_curseg(sbi, type, false);
@@ -1424,9 +2003,6 @@ void allocate_new_segments(struct f2fs_sb_info *sbi)
 	unsigned int old_segno;
 	int i;
 
-	if (test_opt(sbi, LFS))
-		return;
-
 	for (i = CURSEG_HOT_DATA; i <= CURSEG_COLD_DATA; i++) {
 		curseg = CURSEG_I(sbi, i);
 		old_segno = curseg->segno;
@@ -1439,6 +2015,24 @@ static const struct segment_allocation default_salloc_ops = {
 	.allocate_segment = allocate_segment_by_default,
 };
 
+bool exist_trim_candidates(struct f2fs_sb_info *sbi, struct cp_control *cpc)
+{
+	__u64 trim_start = cpc->trim_start;
+	bool has_candidate = false;
+
+	mutex_lock(&SIT_I(sbi)->sentry_lock);
+	for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++) {
+		if (add_discard_addrs(sbi, cpc, true)) {
+			has_candidate = true;
+			break;
+		}
+	}
+	mutex_unlock(&SIT_I(sbi)->sentry_lock);
+
+	cpc->trim_start = trim_start;
+	return has_candidate;
+}
+
 int f2fs_trim_fs(struct f2fs_sb_info *sbi, struct fstrim_range *range)
 {
 	__u64 start = F2FS_BYTES_TO_BLK(range->start);
@@ -1502,68 +2096,80 @@ static bool __has_curseg_space(struct f2fs_sb_info *sbi, int type)
 	return false;
 }
 
-static int __get_segment_type_2(struct page *page, enum page_type p_type)
+static int __get_segment_type_2(struct f2fs_io_info *fio)
 {
-	if (p_type == DATA)
+	if (fio->type == DATA)
 		return CURSEG_HOT_DATA;
 	else
 		return CURSEG_HOT_NODE;
 }
 
-static int __get_segment_type_4(struct page *page, enum page_type p_type)
+static int __get_segment_type_4(struct f2fs_io_info *fio)
 {
-	if (p_type == DATA) {
-		struct inode *inode = page->mapping->host;
+	if (fio->type == DATA) {
+		struct inode *inode = fio->page->mapping->host;
 
 		if (S_ISDIR(inode->i_mode))
 			return CURSEG_HOT_DATA;
 		else
 			return CURSEG_COLD_DATA;
 	} else {
-		if (IS_DNODE(page) && is_cold_node(page))
+		if (IS_DNODE(fio->page) && is_cold_node(fio->page))
 			return CURSEG_WARM_NODE;
 		else
 			return CURSEG_COLD_NODE;
 	}
 }
 
-static int __get_segment_type_6(struct page *page, enum page_type p_type)
+static int __get_segment_type_6(struct f2fs_io_info *fio)
 {
-	if (p_type == DATA) {
-		struct inode *inode = page->mapping->host;
+	if (fio->type == DATA) {
+		struct inode *inode = fio->page->mapping->host;
 
-		if (S_ISDIR(inode->i_mode))
-			return CURSEG_HOT_DATA;
-		else if (is_cold_data(page) || file_is_cold(inode))
+		if (is_cold_data(fio->page) || file_is_cold(inode))
 			return CURSEG_COLD_DATA;
-		else
-			return CURSEG_WARM_DATA;
+		if (is_inode_flag_set(inode, FI_HOT_DATA))
+			return CURSEG_HOT_DATA;
+		return CURSEG_WARM_DATA;
 	} else {
-		if (IS_DNODE(page))
-			return is_cold_node(page) ? CURSEG_WARM_NODE :
+		if (IS_DNODE(fio->page))
+			return is_cold_node(fio->page) ? CURSEG_WARM_NODE :
 						CURSEG_HOT_NODE;
-		else
-			return CURSEG_COLD_NODE;
+		return CURSEG_COLD_NODE;
 	}
 }
 
-static int __get_segment_type(struct page *page, enum page_type p_type)
+static int __get_segment_type(struct f2fs_io_info *fio)
 {
-	switch (F2FS_P_SB(page)->active_logs) {
+	int type = 0;
+
+	switch (fio->sbi->active_logs) {
 	case 2:
-		return __get_segment_type_2(page, p_type);
+		type = __get_segment_type_2(fio);
+		break;
 	case 4:
-		return __get_segment_type_4(page, p_type);
+		type = __get_segment_type_4(fio);
+		break;
+	case 6:
+		type = __get_segment_type_6(fio);
+		break;
+	default:
+		f2fs_bug_on(fio->sbi, true);
 	}
-	/* NR_CURSEG_TYPE(6) logs by default */
-	f2fs_bug_on(F2FS_P_SB(page),
-		F2FS_P_SB(page)->active_logs != NR_CURSEG_TYPE);
-	return __get_segment_type_6(page, p_type);
+
+	if (IS_HOT(type))
+		fio->temp = HOT;
+	else if (IS_WARM(type))
+		fio->temp = WARM;
+	else
+		fio->temp = COLD;
+	return type;
 }
 
 void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 		block_t old_blkaddr, block_t *new_blkaddr,
-		struct f2fs_summary *sum, int type)
+		struct f2fs_summary *sum, int type,
+		struct f2fs_io_info *fio, bool add_list)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
 	struct curseg_info *curseg = CURSEG_I(sbi, type);
@@ -1573,6 +2179,8 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 
 	*new_blkaddr = NEXT_FREE_BLKADDR(sbi, curseg);
 
+	f2fs_wait_discard_bio(sbi, *new_blkaddr);
+
 	/*
 	 * __add_sum_entry should be resided under the curseg_mutex
 	 * because, this function updates a summary entry in the
@@ -1587,8 +2195,8 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	if (!__has_curseg_space(sbi, type))
 		sit_i->s_ops->allocate_segment(sbi, type, false);
 	/*
-	 * SIT information should be updated before segment allocation,
-	 * since SSR needs latest valid block information.
+	 * SIT information should be updated after segment allocation,
+	 * since we need to keep dirty segments precisely under SSR.
 	 */
 	refresh_sit_entry(sbi, old_blkaddr, *new_blkaddr);
 
@@ -1597,24 +2205,35 @@ void allocate_data_block(struct f2fs_sb_info *sbi, struct page *page,
 	if (page && IS_NODESEG(type))
 		fill_node_footer_blkaddr(page, NEXT_FREE_BLKADDR(sbi, curseg));
 
+	if (add_list) {
+		struct f2fs_bio_info *io;
+
+		INIT_LIST_HEAD(&fio->list);
+		fio->in_list = true;
+		io = sbi->write_io[fio->type] + fio->temp;
+		spin_lock(&io->io_lock);
+		list_add_tail(&fio->list, &io->io_list);
+		spin_unlock(&io->io_lock);
+	}
+
 	mutex_unlock(&curseg->curseg_mutex);
 }
 
 static void do_write_page(struct f2fs_summary *sum, struct f2fs_io_info *fio)
 {
-	int type = __get_segment_type(fio->page, fio->type);
-
-	if (fio->type == NODE || fio->type == DATA)
-		mutex_lock(&fio->sbi->wio_mutex[fio->type]);
+	int type = __get_segment_type(fio);
+	int err;
 
+reallocate:
 	allocate_data_block(fio->sbi, fio->page, fio->old_blkaddr,
-					&fio->new_blkaddr, sum, type);
+			&fio->new_blkaddr, sum, type, fio, true);
 
 	/* writeout dirty page into bdev */
-	f2fs_submit_page_mbio(fio);
-
-	if (fio->type == NODE || fio->type == DATA)
-		mutex_unlock(&fio->sbi->wio_mutex[fio->type]);
+	err = f2fs_submit_page_write(fio);
+	if (err == -EAGAIN) {
+		fio->old_blkaddr = fio->new_blkaddr;
+		goto reallocate;
+	}
 }
 
 void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
@@ -1628,13 +2247,14 @@ void write_meta_page(struct f2fs_sb_info *sbi, struct page *page)
 		.new_blkaddr = page->index,
 		.page = page,
 		.encrypted_page = NULL,
+		.in_list = false,
 	};
 
 	if (unlikely(page->index >= MAIN_BLKADDR(sbi)))
 		fio.op_flags &= ~REQ_META;
 
 	set_page_writeback(page);
-	f2fs_submit_page_mbio(&fio);
+	f2fs_submit_page_write(&fio);
 }
 
 void write_node_page(unsigned int nid, struct f2fs_io_info *fio)
@@ -1658,11 +2278,11 @@ void write_data_page(struct dnode_of_data *dn, struct f2fs_io_info *fio)
 	f2fs_update_data_blkaddr(dn, fio->new_blkaddr);
 }
 
-void rewrite_data_page(struct f2fs_io_info *fio)
+int rewrite_data_page(struct f2fs_io_info *fio)
 {
 	fio->new_blkaddr = fio->old_blkaddr;
 	stat_inc_inplace_blocks(fio->sbi);
-	f2fs_submit_page_mbio(fio);
+	return f2fs_submit_page_bio(fio);
 }
 
 void __f2fs_replace_block(struct f2fs_sb_info *sbi, struct f2fs_summary *sum,
@@ -1753,7 +2373,8 @@ void f2fs_wait_on_page_writeback(struct page *page,
 	if (PageWriteback(page)) {
 		struct f2fs_sb_info *sbi = F2FS_P_SB(page);
 
-		f2fs_submit_merged_bio_cond(sbi, NULL, page, 0, type, WRITE);
+		f2fs_submit_merged_write_cond(sbi, page->mapping->host,
+						0, page->index, type);
 		if (ordered)
 			wait_on_page_writeback(page);
 		else
@@ -1911,6 +2532,8 @@ static int read_normal_summaries(struct f2fs_sb_info *sbi, int type)
 
 static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 {
+	struct f2fs_journal *sit_j = CURSEG_I(sbi, CURSEG_COLD_DATA)->journal;
+	struct f2fs_journal *nat_j = CURSEG_I(sbi, CURSEG_HOT_DATA)->journal;
 	int type = CURSEG_HOT_DATA;
 	int err;
 
@@ -1937,6 +2560,11 @@ static int restore_curseg_summaries(struct f2fs_sb_info *sbi)
 			return err;
 	}
 
+	/* sanity check for summary blocks */
+	if (nats_in_cursum(nat_j) > NAT_JOURNAL_ENTRIES ||
+			sits_in_cursum(sit_j) > SIT_JOURNAL_ENTRIES)
+		return -EINVAL;
+
 	return 0;
 }
 
@@ -2226,9 +2854,9 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 			se = get_seg_entry(sbi, segno);
 
 			/* add discard candidates */
-			if (cpc->reason != CP_DISCARD) {
+			if (!(cpc->reason & CP_DISCARD)) {
 				cpc->trim_start = segno;
-				add_discard_addrs(sbi, cpc);
+				add_discard_addrs(sbi, cpc, false);
 			}
 
 			if (to_journal) {
@@ -2262,9 +2890,13 @@ void flush_sit_entries(struct f2fs_sb_info *sbi, struct cp_control *cpc)
 	f2fs_bug_on(sbi, !list_empty(head));
 	f2fs_bug_on(sbi, sit_i->dirty_sentries);
 out:
-	if (cpc->reason == CP_DISCARD) {
+	if (cpc->reason & CP_DISCARD) {
+		__u64 trim_start = cpc->trim_start;
+
 		for (; cpc->trim_start <= cpc->trim_end; cpc->trim_start++)
-			add_discard_addrs(sbi, cpc);
+			add_discard_addrs(sbi, cpc, false);
+
+		cpc->trim_start = trim_start;
 	}
 	mutex_unlock(&sit_i->sentry_lock);
 
@@ -2276,7 +2908,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct sit_info *sit_i;
 	unsigned int sit_segs, start;
-	char *src_bitmap, *dst_bitmap;
+	char *src_bitmap;
 	unsigned int bitmap_size;
 
 	/* allocate memory for SIT information */
@@ -2286,13 +2918,13 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 
 	SM_I(sbi)->sit_info = sit_i;
 
-	sit_i->sentries = f2fs_kvzalloc(MAIN_SEGS(sbi) *
+	sit_i->sentries = kvzalloc(MAIN_SEGS(sbi) *
 					sizeof(struct seg_entry), GFP_KERNEL);
 	if (!sit_i->sentries)
 		return -ENOMEM;
 
 	bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
-	sit_i->dirty_sentries_bitmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
+	sit_i->dirty_sentries_bitmap = kvzalloc(bitmap_size, GFP_KERNEL);
 	if (!sit_i->dirty_sentries_bitmap)
 		return -ENOMEM;
 
@@ -2305,6 +2937,13 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 				!sit_i->sentries[start].ckpt_valid_map)
 			return -ENOMEM;
 
+#ifdef CONFIG_F2FS_CHECK_FS
+		sit_i->sentries[start].cur_valid_map_mir
+			= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
+		if (!sit_i->sentries[start].cur_valid_map_mir)
+			return -ENOMEM;
+#endif
+
 		if (f2fs_discard_en(sbi)) {
 			sit_i->sentries[start].discard_map
 				= kzalloc(SIT_VBLOCK_MAP_SIZE, GFP_KERNEL);
@@ -2318,7 +2957,7 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 		return -ENOMEM;
 
 	if (sbi->segs_per_sec > 1) {
-		sit_i->sec_entries = f2fs_kvzalloc(MAIN_SECS(sbi) *
+		sit_i->sec_entries = kvzalloc(MAIN_SECS(sbi) *
 					sizeof(struct sec_entry), GFP_KERNEL);
 		if (!sit_i->sec_entries)
 			return -ENOMEM;
@@ -2331,22 +2970,27 @@ static int build_sit_info(struct f2fs_sb_info *sbi)
 	bitmap_size = __bitmap_size(sbi, SIT_BITMAP);
 	src_bitmap = __bitmap_ptr(sbi, SIT_BITMAP);
 
-	dst_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
-	if (!dst_bitmap)
+	sit_i->sit_bitmap = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
+	if (!sit_i->sit_bitmap)
 		return -ENOMEM;
 
+#ifdef CONFIG_F2FS_CHECK_FS
+	sit_i->sit_bitmap_mir = kmemdup(src_bitmap, bitmap_size, GFP_KERNEL);
+	if (!sit_i->sit_bitmap_mir)
+		return -ENOMEM;
+#endif
+
 	/* init SIT information */
 	sit_i->s_ops = &default_salloc_ops;
 
 	sit_i->sit_base_addr = le32_to_cpu(raw_super->sit_blkaddr);
 	sit_i->sit_blocks = sit_segs << sbi->log_blocks_per_seg;
 	sit_i->written_valid_blocks = 0;
-	sit_i->sit_bitmap = dst_bitmap;
 	sit_i->bitmap_size = bitmap_size;
 	sit_i->dirty_sentries = 0;
 	sit_i->sents_per_block = SIT_ENTRY_PER_BLOCK;
 	sit_i->elapsed_time = le64_to_cpu(sbi->ckpt->elapsed_time);
-	sit_i->mounted_time = CURRENT_TIME_SEC.tv_sec;
+	sit_i->mounted_time = ktime_get_real_seconds();
 	mutex_init(&sit_i->sentry_lock);
 	return 0;
 }
@@ -2364,12 +3008,12 @@ static int build_free_segmap(struct f2fs_sb_info *sbi)
 	SM_I(sbi)->free_info = free_i;
 
 	bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
-	free_i->free_segmap = f2fs_kvmalloc(bitmap_size, GFP_KERNEL);
+	free_i->free_segmap = kvmalloc(bitmap_size, GFP_KERNEL);
 	if (!free_i->free_segmap)
 		return -ENOMEM;
 
 	sec_bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
-	free_i->free_secmap = f2fs_kvmalloc(sec_bitmap_size, GFP_KERNEL);
+	free_i->free_secmap = kvmalloc(sec_bitmap_size, GFP_KERNEL);
 	if (!free_i->free_secmap)
 		return -ENOMEM;
 
@@ -2445,10 +3089,17 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 
 			/* build discard map only one time */
 			if (f2fs_discard_en(sbi)) {
-				memcpy(se->discard_map, se->cur_valid_map,
-							SIT_VBLOCK_MAP_SIZE);
-				sbi->discard_blks += sbi->blocks_per_seg -
-							se->valid_blocks;
+				if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
+					memset(se->discard_map, 0xff,
+						SIT_VBLOCK_MAP_SIZE);
+				} else {
+					memcpy(se->discard_map,
+						se->cur_valid_map,
+						SIT_VBLOCK_MAP_SIZE);
+					sbi->discard_blks +=
+						sbi->blocks_per_seg -
+						se->valid_blocks;
+				}
 			}
 
 			if (sbi->segs_per_sec > 1)
@@ -2472,10 +3123,15 @@ static void build_sit_entries(struct f2fs_sb_info *sbi)
 		seg_info_from_raw_sit(se, &sit);
 
 		if (f2fs_discard_en(sbi)) {
-			memcpy(se->discard_map, se->cur_valid_map,
-						SIT_VBLOCK_MAP_SIZE);
-			sbi->discard_blks += old_valid_blocks -
-						se->valid_blocks;
+			if (is_set_ckpt_flags(sbi, CP_TRIMMED_FLAG)) {
+				memset(se->discard_map, 0xff,
+							SIT_VBLOCK_MAP_SIZE);
+			} else {
+				memcpy(se->discard_map, se->cur_valid_map,
+							SIT_VBLOCK_MAP_SIZE);
+				sbi->discard_blks += old_valid_blocks -
+							se->valid_blocks;
+			}
 		}
 
 		if (sbi->segs_per_sec > 1)
@@ -2519,7 +3175,7 @@ static void init_dirty_segmap(struct f2fs_sb_info *sbi)
 		if (segno >= MAIN_SEGS(sbi))
 			break;
 		offset = segno + 1;
-		valid_blocks = get_valid_blocks(sbi, segno, 0);
+		valid_blocks = get_valid_blocks(sbi, segno, false);
 		if (valid_blocks == sbi->blocks_per_seg || !valid_blocks)
 			continue;
 		if (valid_blocks > sbi->blocks_per_seg) {
@@ -2537,7 +3193,7 @@ static int init_victim_secmap(struct f2fs_sb_info *sbi)
 	struct dirty_seglist_info *dirty_i = DIRTY_I(sbi);
 	unsigned int bitmap_size = f2fs_bitmap_size(MAIN_SECS(sbi));
 
-	dirty_i->victim_secmap = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
+	dirty_i->victim_secmap = kvzalloc(bitmap_size, GFP_KERNEL);
 	if (!dirty_i->victim_secmap)
 		return -ENOMEM;
 	return 0;
@@ -2559,7 +3215,7 @@ static int build_dirty_segmap(struct f2fs_sb_info *sbi)
 	bitmap_size = f2fs_bitmap_size(MAIN_SEGS(sbi));
 
 	for (i = 0; i < NR_DIRTY_TYPE; i++) {
-		dirty_i->dirty_segmap[i] = f2fs_kvzalloc(bitmap_size, GFP_KERNEL);
+		dirty_i->dirty_segmap[i] = kvzalloc(bitmap_size, GFP_KERNEL);
 		if (!dirty_i->dirty_segmap[i])
 			return -ENOMEM;
 	}
@@ -2625,22 +3281,22 @@ int build_segment_manager(struct f2fs_sb_info *sbi)
 		sm_info->ipu_policy = 1 << F2FS_IPU_FSYNC;
 	sm_info->min_ipu_util = DEF_MIN_IPU_UTIL;
 	sm_info->min_fsync_blocks = DEF_MIN_FSYNC_BLOCKS;
-
-	INIT_LIST_HEAD(&sm_info->discard_list);
-	INIT_LIST_HEAD(&sm_info->wait_list);
-	sm_info->nr_discards = 0;
-	sm_info->max_discards = 0;
+	sm_info->min_hot_blocks = DEF_MIN_HOT_BLOCKS;
 
 	sm_info->trim_sections = DEF_BATCHED_TRIM_SECTIONS;
 
 	INIT_LIST_HEAD(&sm_info->sit_entry_set);
 
-	if (test_opt(sbi, FLUSH_MERGE) && !f2fs_readonly(sbi->sb)) {
+	if (!f2fs_readonly(sbi->sb)) {
 		err = create_flush_cmd_control(sbi);
 		if (err)
 			return err;
 	}
 
+	err = create_discard_cmd_control(sbi);
+	if (err)
+		return err;
+
 	err = build_sit_info(sbi);
 	if (err)
 		return err;
@@ -2734,6 +3390,9 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
 	if (sit_i->sentries) {
 		for (start = 0; start < MAIN_SEGS(sbi); start++) {
 			kfree(sit_i->sentries[start].cur_valid_map);
+#ifdef CONFIG_F2FS_CHECK_FS
+			kfree(sit_i->sentries[start].cur_valid_map_mir);
+#endif
 			kfree(sit_i->sentries[start].ckpt_valid_map);
 			kfree(sit_i->sentries[start].discard_map);
 		}
@@ -2746,6 +3405,9 @@ static void destroy_sit_info(struct f2fs_sb_info *sbi)
 
 	SM_I(sbi)->sit_info = NULL;
 	kfree(sit_i->sit_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+	kfree(sit_i->sit_bitmap_mir);
+#endif
 	kfree(sit_i);
 }
 
@@ -2756,6 +3418,7 @@ void destroy_segment_manager(struct f2fs_sb_info *sbi)
 	if (!sm_info)
 		return;
 	destroy_flush_cmd_control(sbi, true);
+	destroy_discard_cmd_control(sbi);
 	destroy_dirty_segmap(sbi);
 	destroy_curseg(sbi);
 	destroy_free_segmap(sbi);
@@ -2771,15 +3434,15 @@ int __init create_segment_manager_caches(void)
 	if (!discard_entry_slab)
 		goto fail;
 
-	bio_entry_slab = f2fs_kmem_cache_create("bio_entry",
-			sizeof(struct bio_entry));
-	if (!bio_entry_slab)
+	discard_cmd_slab = f2fs_kmem_cache_create("discard_cmd",
+			sizeof(struct discard_cmd));
+	if (!discard_cmd_slab)
 		goto destroy_discard_entry;
 
 	sit_entry_set_slab = f2fs_kmem_cache_create("sit_entry_set",
 			sizeof(struct sit_entry_set));
 	if (!sit_entry_set_slab)
-		goto destroy_bio_entry;
+		goto destroy_discard_cmd;
 
 	inmem_entry_slab = f2fs_kmem_cache_create("inmem_page_entry",
 			sizeof(struct inmem_pages));
@@ -2789,8 +3452,8 @@ int __init create_segment_manager_caches(void)
 
 destroy_sit_entry_set:
 	kmem_cache_destroy(sit_entry_set_slab);
-destroy_bio_entry:
-	kmem_cache_destroy(bio_entry_slab);
+destroy_discard_cmd:
+	kmem_cache_destroy(discard_cmd_slab);
 destroy_discard_entry:
 	kmem_cache_destroy(discard_entry_slab);
 fail:
@@ -2800,7 +3463,7 @@ fail:
 void destroy_segment_manager_caches(void)
 {
 	kmem_cache_destroy(sit_entry_set_slab);
-	kmem_cache_destroy(bio_entry_slab);
+	kmem_cache_destroy(discard_cmd_slab);
 	kmem_cache_destroy(discard_entry_slab);
 	kmem_cache_destroy(inmem_entry_slab);
 }
diff --git a/fs/f2fs/segment.h b/fs/f2fs/segment.h
index 9d44ce83acb2..6b871b492fd5 100644
--- a/fs/f2fs/segment.h
+++ b/fs/f2fs/segment.h
@@ -21,78 +21,88 @@
 #define F2FS_MIN_SEGMENTS	9 /* SB + 2 (CP + SIT + NAT) + SSA + MAIN */
 
 /* L: Logical segment # in volume, R: Relative segment # in main area */
-#define GET_L2R_SEGNO(free_i, segno)	(segno - free_i->start_segno)
-#define GET_R2L_SEGNO(free_i, segno)	(segno + free_i->start_segno)
+#define GET_L2R_SEGNO(free_i, segno)	((segno) - (free_i)->start_segno)
+#define GET_R2L_SEGNO(free_i, segno)	((segno) + (free_i)->start_segno)
 
-#define IS_DATASEG(t)	(t <= CURSEG_COLD_DATA)
-#define IS_NODESEG(t)	(t >= CURSEG_HOT_NODE)
+#define IS_DATASEG(t)	((t) <= CURSEG_COLD_DATA)
+#define IS_NODESEG(t)	((t) >= CURSEG_HOT_NODE)
+
+#define IS_HOT(t)	((t) == CURSEG_HOT_NODE || (t) == CURSEG_HOT_DATA)
+#define IS_WARM(t)	((t) == CURSEG_WARM_NODE || (t) == CURSEG_WARM_DATA)
+#define IS_COLD(t)	((t) == CURSEG_COLD_NODE || (t) == CURSEG_COLD_DATA)
 
 #define IS_CURSEG(sbi, seg)						\
-	((seg == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) ||	\
-	 (seg == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) ||	\
-	 (seg == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) ||	\
-	 (seg == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) ||	\
-	 (seg == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) ||	\
-	 (seg == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
+	(((seg) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno) ||	\
+	 ((seg) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno) ||	\
+	 ((seg) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno) ||	\
+	 ((seg) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno) ||	\
+	 ((seg) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno) ||	\
+	 ((seg) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno))
 
 #define IS_CURSEC(sbi, secno)						\
-	((secno == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno /		\
-	  sbi->segs_per_sec) ||	\
-	 (secno == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno /		\
-	  sbi->segs_per_sec) ||	\
-	 (secno == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno /		\
-	  sbi->segs_per_sec) ||	\
-	 (secno == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno /		\
-	  sbi->segs_per_sec) ||	\
-	 (secno == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno /		\
-	  sbi->segs_per_sec) ||	\
-	 (secno == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno /		\
-	  sbi->segs_per_sec))	\
+	(((secno) == CURSEG_I(sbi, CURSEG_HOT_DATA)->segno /		\
+	  (sbi)->segs_per_sec) ||	\
+	 ((secno) == CURSEG_I(sbi, CURSEG_WARM_DATA)->segno /		\
+	  (sbi)->segs_per_sec) ||	\
+	 ((secno) == CURSEG_I(sbi, CURSEG_COLD_DATA)->segno /		\
+	  (sbi)->segs_per_sec) ||	\
+	 ((secno) == CURSEG_I(sbi, CURSEG_HOT_NODE)->segno /		\
+	  (sbi)->segs_per_sec) ||	\
+	 ((secno) == CURSEG_I(sbi, CURSEG_WARM_NODE)->segno /		\
+	  (sbi)->segs_per_sec) ||	\
+	 ((secno) == CURSEG_I(sbi, CURSEG_COLD_NODE)->segno /		\
+	  (sbi)->segs_per_sec))	\
 
 #define MAIN_BLKADDR(sbi)	(SM_I(sbi)->main_blkaddr)
 #define SEG0_BLKADDR(sbi)	(SM_I(sbi)->seg0_blkaddr)
 
 #define MAIN_SEGS(sbi)	(SM_I(sbi)->main_segments)
-#define MAIN_SECS(sbi)	(sbi->total_sections)
+#define MAIN_SECS(sbi)	((sbi)->total_sections)
 
 #define TOTAL_SEGS(sbi)	(SM_I(sbi)->segment_count)
-#define TOTAL_BLKS(sbi)	(TOTAL_SEGS(sbi) << sbi->log_blocks_per_seg)
+#define TOTAL_BLKS(sbi)	(TOTAL_SEGS(sbi) << (sbi)->log_blocks_per_seg)
 
 #define MAX_BLKADDR(sbi)	(SEG0_BLKADDR(sbi) + TOTAL_BLKS(sbi))
-#define SEGMENT_SIZE(sbi)	(1ULL << (sbi->log_blocksize +		\
-					sbi->log_blocks_per_seg))
+#define SEGMENT_SIZE(sbi)	(1ULL << ((sbi)->log_blocksize +	\
+					(sbi)->log_blocks_per_seg))
 
 #define START_BLOCK(sbi, segno)	(SEG0_BLKADDR(sbi) +			\
-	 (GET_R2L_SEGNO(FREE_I(sbi), segno) << sbi->log_blocks_per_seg))
+	 (GET_R2L_SEGNO(FREE_I(sbi), segno) << (sbi)->log_blocks_per_seg))
 
 #define NEXT_FREE_BLKADDR(sbi, curseg)					\
-	(START_BLOCK(sbi, curseg->segno) + curseg->next_blkoff)
+	(START_BLOCK(sbi, (curseg)->segno) + (curseg)->next_blkoff)
 
 #define GET_SEGOFF_FROM_SEG0(sbi, blk_addr)	((blk_addr) - SEG0_BLKADDR(sbi))
 #define GET_SEGNO_FROM_SEG0(sbi, blk_addr)				\
-	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> sbi->log_blocks_per_seg)
+	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) >> (sbi)->log_blocks_per_seg)
 #define GET_BLKOFF_FROM_SEG0(sbi, blk_addr)				\
-	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & (sbi->blocks_per_seg - 1))
+	(GET_SEGOFF_FROM_SEG0(sbi, blk_addr) & ((sbi)->blocks_per_seg - 1))
 
 #define GET_SEGNO(sbi, blk_addr)					\
-	(((blk_addr == NULL_ADDR) || (blk_addr == NEW_ADDR)) ?		\
+	((((blk_addr) == NULL_ADDR) || ((blk_addr) == NEW_ADDR)) ?	\
 	NULL_SEGNO : GET_L2R_SEGNO(FREE_I(sbi),			\
 		GET_SEGNO_FROM_SEG0(sbi, blk_addr)))
-#define GET_SECNO(sbi, segno)					\
-	((segno) / sbi->segs_per_sec)
-#define GET_ZONENO_FROM_SEGNO(sbi, segno)				\
-	((segno / sbi->segs_per_sec) / sbi->secs_per_zone)
+#define BLKS_PER_SEC(sbi)					\
+	((sbi)->segs_per_sec * (sbi)->blocks_per_seg)
+#define GET_SEC_FROM_SEG(sbi, segno)				\
+	((segno) / (sbi)->segs_per_sec)
+#define GET_SEG_FROM_SEC(sbi, secno)				\
+	((secno) * (sbi)->segs_per_sec)
+#define GET_ZONE_FROM_SEC(sbi, secno)				\
+	((secno) / (sbi)->secs_per_zone)
+#define GET_ZONE_FROM_SEG(sbi, segno)				\
+	GET_ZONE_FROM_SEC(sbi, GET_SEC_FROM_SEG(sbi, segno))
 
 #define GET_SUM_BLOCK(sbi, segno)				\
-	((sbi->sm_info->ssa_blkaddr) + segno)
+	((sbi)->sm_info->ssa_blkaddr + (segno))
 
 #define GET_SUM_TYPE(footer) ((footer)->entry_type)
-#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = type)
+#define SET_SUM_TYPE(footer, type) ((footer)->entry_type = (type))
 
 #define SIT_ENTRY_OFFSET(sit_i, segno)					\
-	(segno % sit_i->sents_per_block)
+	((segno) % (sit_i)->sents_per_block)
 #define SIT_BLOCK_OFFSET(segno)					\
-	(segno / SIT_ENTRY_PER_BLOCK)
+	((segno) / SIT_ENTRY_PER_BLOCK)
 #define	START_SEGNO(segno)		\
 	(SIT_BLOCK_OFFSET(segno) * SIT_ENTRY_PER_BLOCK)
 #define SIT_BLK_CNT(sbi)			\
@@ -103,7 +113,7 @@
 #define SECTOR_FROM_BLOCK(blk_addr)					\
 	(((sector_t)blk_addr) << F2FS_LOG_SECTORS_PER_BLOCK)
 #define SECTOR_TO_BLOCK(sectors)					\
-	(sectors >> F2FS_LOG_SECTORS_PER_BLOCK)
+	((sectors) >> F2FS_LOG_SECTORS_PER_BLOCK)
 
 /*
  * indicate a block allocation direction: RIGHT and LEFT.
@@ -132,7 +142,10 @@ enum {
  */
 enum {
 	GC_CB = 0,
-	GC_GREEDY
+	GC_GREEDY,
+	ALLOC_NEXT,
+	FLUSH_DEVICE,
+	MAX_GC_POLICY,
 };
 
 /*
@@ -164,6 +177,9 @@ struct seg_entry {
 	unsigned int ckpt_valid_blocks:10;	/* # of valid blocks last cp */
 	unsigned int padding:6;		/* padding */
 	unsigned char *cur_valid_map;	/* validity bitmap of blocks */
+#ifdef CONFIG_F2FS_CHECK_FS
+	unsigned char *cur_valid_map_mir;	/* mirror of current valid bitmap */
+#endif
 	/*
 	 * # of valid blocks and the validity bitmap stored in the the last
 	 * checkpoint pack. This information is used by the SSR mode.
@@ -186,9 +202,12 @@ struct segment_allocation {
  * the page is atomically written, and it is in inmem_pages list.
  */
 #define ATOMIC_WRITTEN_PAGE		((unsigned long)-1)
+#define DUMMY_WRITTEN_PAGE		((unsigned long)-2)
 
 #define IS_ATOMIC_WRITTEN_PAGE(page)			\
 		(page_private(page) == (unsigned long)ATOMIC_WRITTEN_PAGE)
+#define IS_DUMMY_WRITTEN_PAGE(page)			\
+		(page_private(page) == (unsigned long)DUMMY_WRITTEN_PAGE)
 
 struct inmem_pages {
 	struct list_head list;
@@ -203,6 +222,9 @@ struct sit_info {
 	block_t sit_blocks;		/* # of blocks used by SIT area */
 	block_t written_valid_blocks;	/* # of valid blocks in main area */
 	char *sit_bitmap;		/* SIT bitmap pointer */
+#ifdef CONFIG_F2FS_CHECK_FS
+	char *sit_bitmap_mir;		/* SIT bitmap mirror */
+#endif
 	unsigned int bitmap_size;	/* SIT bitmap size */
 
 	unsigned long *tmp_map;			/* bitmap for temporal use */
@@ -218,6 +240,8 @@ struct sit_info {
 	unsigned long long mounted_time;	/* mount time */
 	unsigned long long min_mtime;		/* min. modification time */
 	unsigned long long max_mtime;		/* max. modification time */
+
+	unsigned int last_victim[MAX_GC_POLICY]; /* last victim segment # */
 };
 
 struct free_segmap_info {
@@ -294,17 +318,17 @@ static inline struct sec_entry *get_sec_entry(struct f2fs_sb_info *sbi,
 						unsigned int segno)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
-	return &sit_i->sec_entries[GET_SECNO(sbi, segno)];
+	return &sit_i->sec_entries[GET_SEC_FROM_SEG(sbi, segno)];
 }
 
 static inline unsigned int get_valid_blocks(struct f2fs_sb_info *sbi,
-				unsigned int segno, int section)
+				unsigned int segno, bool use_section)
 {
 	/*
 	 * In order to get # of valid blocks in a section instantly from many
 	 * segments, f2fs manages two counting structures separately.
 	 */
-	if (section > 1)
+	if (use_section && sbi->segs_per_sec > 1)
 		return get_sec_entry(sbi, segno)->valid_blocks;
 	else
 		return get_seg_entry(sbi, segno)->valid_blocks;
@@ -317,6 +341,9 @@ static inline void seg_info_from_raw_sit(struct seg_entry *se,
 	se->ckpt_valid_blocks = GET_SIT_VBLOCKS(rs);
 	memcpy(se->cur_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
 	memcpy(se->ckpt_valid_map, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+#ifdef CONFIG_F2FS_CHECK_FS
+	memcpy(se->cur_valid_map_mir, rs->valid_map, SIT_VBLOCK_MAP_SIZE);
+#endif
 	se->type = GET_SIT_TYPE(rs);
 	se->mtime = le64_to_cpu(rs->mtime);
 }
@@ -346,8 +373,8 @@ static inline unsigned int find_next_inuse(struct free_segmap_info *free_i,
 static inline void __set_free(struct f2fs_sb_info *sbi, unsigned int segno)
 {
 	struct free_segmap_info *free_i = FREE_I(sbi);
-	unsigned int secno = segno / sbi->segs_per_sec;
-	unsigned int start_segno = secno * sbi->segs_per_sec;
+	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned int next;
 
 	spin_lock(&free_i->segmap_lock);
@@ -367,7 +394,8 @@ static inline void __set_inuse(struct f2fs_sb_info *sbi,
 		unsigned int segno)
 {
 	struct free_segmap_info *free_i = FREE_I(sbi);
-	unsigned int secno = segno / sbi->segs_per_sec;
+	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+
 	set_bit(segno, free_i->free_segmap);
 	free_i->free_segments--;
 	if (!test_and_set_bit(secno, free_i->free_secmap))
@@ -378,8 +406,8 @@ static inline void __set_test_and_free(struct f2fs_sb_info *sbi,
 		unsigned int segno)
 {
 	struct free_segmap_info *free_i = FREE_I(sbi);
-	unsigned int secno = segno / sbi->segs_per_sec;
-	unsigned int start_segno = secno * sbi->segs_per_sec;
+	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+	unsigned int start_segno = GET_SEG_FROM_SEC(sbi, secno);
 	unsigned int next;
 
 	spin_lock(&free_i->segmap_lock);
@@ -400,7 +428,8 @@ static inline void __set_test_and_inuse(struct f2fs_sb_info *sbi,
 		unsigned int segno)
 {
 	struct free_segmap_info *free_i = FREE_I(sbi);
-	unsigned int secno = segno / sbi->segs_per_sec;
+	unsigned int secno = GET_SEC_FROM_SEG(sbi, segno);
+
 	spin_lock(&free_i->segmap_lock);
 	if (!test_and_set_bit(segno, free_i->free_segmap)) {
 		free_i->free_segments--;
@@ -414,6 +443,12 @@ static inline void get_sit_bitmap(struct f2fs_sb_info *sbi,
 		void *dst_addr)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
+
+#ifdef CONFIG_F2FS_CHECK_FS
+	if (memcmp(sit_i->sit_bitmap, sit_i->sit_bitmap_mir,
+						sit_i->bitmap_size))
+		f2fs_bug_on(sbi, 1);
+#endif
 	memcpy(dst_addr, sit_i->sit_bitmap, sit_i->bitmap_size);
 }
 
@@ -459,12 +494,12 @@ static inline int overprovision_segments(struct f2fs_sb_info *sbi)
 
 static inline int overprovision_sections(struct f2fs_sb_info *sbi)
 {
-	return ((unsigned int) overprovision_segments(sbi)) / sbi->segs_per_sec;
+	return GET_SEC_FROM_SEG(sbi, (unsigned int)overprovision_segments(sbi));
 }
 
 static inline int reserved_sections(struct f2fs_sb_info *sbi)
 {
-	return ((unsigned int) reserved_segments(sbi)) / sbi->segs_per_sec;
+	return GET_SEC_FROM_SEG(sbi, (unsigned int)reserved_segments(sbi));
 }
 
 static inline bool need_SSR(struct f2fs_sb_info *sbi)
@@ -477,7 +512,7 @@ static inline bool need_SSR(struct f2fs_sb_info *sbi)
 		return false;
 
 	return free_sections(sbi) <= (node_secs + 2 * dent_secs + imeta_secs +
-						reserved_sections(sbi) + 1);
+						2 * reserved_sections(sbi));
 }
 
 static inline bool has_not_enough_free_secs(struct f2fs_sb_info *sbi,
@@ -522,6 +557,7 @@ static inline int utilization(struct f2fs_sb_info *sbi)
  */
 #define DEF_MIN_IPU_UTIL	70
 #define DEF_MIN_FSYNC_BLOCKS	8
+#define DEF_MIN_HOT_BLOCKS	16
 
 enum {
 	F2FS_IPU_FORCE,
@@ -529,17 +565,15 @@ enum {
 	F2FS_IPU_UTIL,
 	F2FS_IPU_SSR_UTIL,
 	F2FS_IPU_FSYNC,
+	F2FS_IPU_ASYNC,
 };
 
-static inline bool need_inplace_update(struct inode *inode)
+static inline bool need_inplace_update_policy(struct inode *inode,
+				struct f2fs_io_info *fio)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	unsigned int policy = SM_I(sbi)->ipu_policy;
 
-	/* IPU can be done only for the user data */
-	if (S_ISDIR(inode->i_mode) || f2fs_is_atomic_file(inode))
-		return false;
-
 	if (test_opt(sbi, LFS))
 		return false;
 
@@ -554,6 +588,15 @@ static inline bool need_inplace_update(struct inode *inode)
 			utilization(sbi) > SM_I(sbi)->min_ipu_util)
 		return true;
 
+	/*
+	 * IPU for rewrite async pages
+	 */
+	if (policy & (0x1 << F2FS_IPU_ASYNC) &&
+			fio && fio->op == REQ_OP_WRITE &&
+			!(fio->op_flags & REQ_SYNC) &&
+			!f2fs_encrypted_inode(inode))
+		return true;
+
 	/* this is only set during fdatasync */
 	if (policy & (0x1 << F2FS_IPU_FSYNC) &&
 			is_inode_flag_set(inode, FI_NEED_IPU))
@@ -634,6 +677,12 @@ static inline pgoff_t current_sit_addr(struct f2fs_sb_info *sbi,
 
 	check_seg_range(sbi, start);
 
+#ifdef CONFIG_F2FS_CHECK_FS
+	if (f2fs_test_bit(offset, sit_i->sit_bitmap) !=
+			f2fs_test_bit(offset, sit_i->sit_bitmap_mir))
+		f2fs_bug_on(sbi, 1);
+#endif
+
 	/* calculate sit block address */
 	if (f2fs_test_bit(offset, sit_i->sit_bitmap))
 		blk_addr += sit_i->sit_blocks;
@@ -659,13 +708,17 @@ static inline void set_to_next_sit(struct sit_info *sit_i, unsigned int start)
 	unsigned int block_off = SIT_BLOCK_OFFSET(start);
 
 	f2fs_change_bit(block_off, sit_i->sit_bitmap);
+#ifdef CONFIG_F2FS_CHECK_FS
+	f2fs_change_bit(block_off, sit_i->sit_bitmap_mir);
+#endif
 }
 
 static inline unsigned long long get_mtime(struct f2fs_sb_info *sbi)
 {
 	struct sit_info *sit_i = SIT_I(sbi);
-	return sit_i->elapsed_time + CURRENT_TIME_SEC.tv_sec -
-						sit_i->mounted_time;
+	time64_t now = ktime_get_real_seconds();
+
+	return sit_i->elapsed_time + now - sit_i->mounted_time;
 }
 
 static inline void set_summary(struct f2fs_summary *sum, nid_t nid,
@@ -689,6 +742,15 @@ static inline block_t sum_blk_addr(struct f2fs_sb_info *sbi, int base, int type)
 				- (base + 1) + type;
 }
 
+static inline bool no_fggc_candidate(struct f2fs_sb_info *sbi,
+						unsigned int secno)
+{
+	if (get_valid_blocks(sbi, GET_SEG_FROM_SEC(sbi, secno), true) >=
+						sbi->fggc_threshold)
+		return true;
+	return false;
+}
+
 static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
 {
 	if (IS_CURSEC(sbi, secno) || (sbi->cur_victim_sec == secno))
@@ -700,8 +762,8 @@ static inline bool sec_usage_check(struct f2fs_sb_info *sbi, unsigned int secno)
  * It is very important to gather dirty pages and write at once, so that we can
  * submit a big bio without interfering other data writes.
  * By default, 512 pages for directory data,
- * 512 pages (2MB) * 3 for three types of nodes, and
- * max_bio_blocks for meta are set.
+ * 512 pages (2MB) * 8 for nodes, and
+ * 256 pages * 8 for meta are set.
  */
 static inline int nr_pages_to_skip(struct f2fs_sb_info *sbi, int type)
 {
diff --git a/fs/f2fs/super.c b/fs/f2fs/super.c
index 46fd30d8af77..32e4c025e97e 100644
--- a/fs/f2fs/super.c
+++ b/fs/f2fs/super.c
@@ -22,6 +22,7 @@
 #include <linux/random.h>
 #include <linux/exportfs.h>
 #include <linux/blkdev.h>
+#include <linux/quotaops.h>
 #include <linux/f2fs_fs.h>
 #include <linux/sysfs.h>
 
@@ -35,9 +36,7 @@
 #define CREATE_TRACE_POINTS
 #include <trace/events/f2fs.h>
 
-static struct proc_dir_entry *f2fs_proc_root;
 static struct kmem_cache *f2fs_inode_cachep;
-static struct kset *f2fs_kset;
 
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 
@@ -49,6 +48,7 @@ char *fault_name[FAULT_MAX] = {
 	[FAULT_BLOCK]		= "no more block",
 	[FAULT_DIR_DEPTH]	= "too big dir depth",
 	[FAULT_EVICT_INODE]	= "evict_inode fail",
+	[FAULT_TRUNCATE]	= "truncate fail",
 	[FAULT_IO]		= "IO error",
 	[FAULT_CHECKPOINT]	= "checkpoint error",
 };
@@ -82,6 +82,7 @@ enum {
 	Opt_discard,
 	Opt_nodiscard,
 	Opt_noheap,
+	Opt_heap,
 	Opt_user_xattr,
 	Opt_nouser_xattr,
 	Opt_acl,
@@ -89,6 +90,7 @@ enum {
 	Opt_active_logs,
 	Opt_disable_ext_identify,
 	Opt_inline_xattr,
+	Opt_noinline_xattr,
 	Opt_inline_data,
 	Opt_inline_dentry,
 	Opt_noinline_dentry,
@@ -101,9 +103,12 @@ enum {
 	Opt_noinline_data,
 	Opt_data_flush,
 	Opt_mode,
+	Opt_io_size_bits,
 	Opt_fault_injection,
 	Opt_lazytime,
 	Opt_nolazytime,
+	Opt_usrquota,
+	Opt_grpquota,
 	Opt_err,
 };
 
@@ -114,6 +119,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_discard, "discard"},
 	{Opt_nodiscard, "nodiscard"},
 	{Opt_noheap, "no_heap"},
+	{Opt_heap, "heap"},
 	{Opt_user_xattr, "user_xattr"},
 	{Opt_nouser_xattr, "nouser_xattr"},
 	{Opt_acl, "acl"},
@@ -121,6 +127,7 @@ static match_table_t f2fs_tokens = {
 	{Opt_active_logs, "active_logs=%u"},
 	{Opt_disable_ext_identify, "disable_ext_identify"},
 	{Opt_inline_xattr, "inline_xattr"},
+	{Opt_noinline_xattr, "noinline_xattr"},
 	{Opt_inline_data, "inline_data"},
 	{Opt_inline_dentry, "inline_dentry"},
 	{Opt_noinline_dentry, "noinline_dentry"},
@@ -133,210 +140,15 @@ static match_table_t f2fs_tokens = {
 	{Opt_noinline_data, "noinline_data"},
 	{Opt_data_flush, "data_flush"},
 	{Opt_mode, "mode=%s"},
+	{Opt_io_size_bits, "io_bits=%u"},
 	{Opt_fault_injection, "fault_injection=%u"},
 	{Opt_lazytime, "lazytime"},
 	{Opt_nolazytime, "nolazytime"},
+	{Opt_usrquota, "usrquota"},
+	{Opt_grpquota, "grpquota"},
 	{Opt_err, NULL},
 };
 
-/* Sysfs support for f2fs */
-enum {
-	GC_THREAD,	/* struct f2fs_gc_thread */
-	SM_INFO,	/* struct f2fs_sm_info */
-	NM_INFO,	/* struct f2fs_nm_info */
-	F2FS_SBI,	/* struct f2fs_sb_info */
-#ifdef CONFIG_F2FS_FAULT_INJECTION
-	FAULT_INFO_RATE,	/* struct f2fs_fault_info */
-	FAULT_INFO_TYPE,	/* struct f2fs_fault_info */
-#endif
-};
-
-struct f2fs_attr {
-	struct attribute attr;
-	ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *);
-	ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *,
-			 const char *, size_t);
-	int struct_type;
-	int offset;
-};
-
-static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
-{
-	if (struct_type == GC_THREAD)
-		return (unsigned char *)sbi->gc_thread;
-	else if (struct_type == SM_INFO)
-		return (unsigned char *)SM_I(sbi);
-	else if (struct_type == NM_INFO)
-		return (unsigned char *)NM_I(sbi);
-	else if (struct_type == F2FS_SBI)
-		return (unsigned char *)sbi;
-#ifdef CONFIG_F2FS_FAULT_INJECTION
-	else if (struct_type == FAULT_INFO_RATE ||
-					struct_type == FAULT_INFO_TYPE)
-		return (unsigned char *)&sbi->fault_info;
-#endif
-	return NULL;
-}
-
-static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
-		struct f2fs_sb_info *sbi, char *buf)
-{
-	struct super_block *sb = sbi->sb;
-
-	if (!sb->s_bdev->bd_part)
-		return snprintf(buf, PAGE_SIZE, "0\n");
-
-	return snprintf(buf, PAGE_SIZE, "%llu\n",
-		(unsigned long long)(sbi->kbytes_written +
-			BD_PART_WRITTEN(sbi)));
-}
-
-static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
-			struct f2fs_sb_info *sbi, char *buf)
-{
-	unsigned char *ptr = NULL;
-	unsigned int *ui;
-
-	ptr = __struct_ptr(sbi, a->struct_type);
-	if (!ptr)
-		return -EINVAL;
-
-	ui = (unsigned int *)(ptr + a->offset);
-
-	return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
-}
-
-static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
-			struct f2fs_sb_info *sbi,
-			const char *buf, size_t count)
-{
-	unsigned char *ptr;
-	unsigned long t;
-	unsigned int *ui;
-	ssize_t ret;
-
-	ptr = __struct_ptr(sbi, a->struct_type);
-	if (!ptr)
-		return -EINVAL;
-
-	ui = (unsigned int *)(ptr + a->offset);
-
-	ret = kstrtoul(skip_spaces(buf), 0, &t);
-	if (ret < 0)
-		return ret;
-#ifdef CONFIG_F2FS_FAULT_INJECTION
-	if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX))
-		return -EINVAL;
-#endif
-	*ui = t;
-	return count;
-}
-
-static ssize_t f2fs_attr_show(struct kobject *kobj,
-				struct attribute *attr, char *buf)
-{
-	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
-								s_kobj);
-	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
-
-	return a->show ? a->show(a, sbi, buf) : 0;
-}
-
-static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr,
-						const char *buf, size_t len)
-{
-	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
-									s_kobj);
-	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
-
-	return a->store ? a->store(a, sbi, buf, len) : 0;
-}
-
-static void f2fs_sb_release(struct kobject *kobj)
-{
-	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
-								s_kobj);
-	complete(&sbi->s_kobj_unregister);
-}
-
-#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \
-static struct f2fs_attr f2fs_attr_##_name = {			\
-	.attr = {.name = __stringify(_name), .mode = _mode },	\
-	.show	= _show,					\
-	.store	= _store,					\
-	.struct_type = _struct_type,				\
-	.offset = _offset					\
-}
-
-#define F2FS_RW_ATTR(struct_type, struct_name, name, elname)	\
-	F2FS_ATTR_OFFSET(struct_type, name, 0644,		\
-		f2fs_sbi_show, f2fs_sbi_store,			\
-		offsetof(struct struct_name, elname))
-
-#define F2FS_GENERAL_RO_ATTR(name) \
-static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
-
-F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
-F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
-F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
-F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, max_small_discards, max_discards);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
-F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
-F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
-F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
-F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
-F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
-#ifdef CONFIG_F2FS_FAULT_INJECTION
-F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
-F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
-#endif
-F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
-
-#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
-static struct attribute *f2fs_attrs[] = {
-	ATTR_LIST(gc_min_sleep_time),
-	ATTR_LIST(gc_max_sleep_time),
-	ATTR_LIST(gc_no_gc_sleep_time),
-	ATTR_LIST(gc_idle),
-	ATTR_LIST(reclaim_segments),
-	ATTR_LIST(max_small_discards),
-	ATTR_LIST(batched_trim_sections),
-	ATTR_LIST(ipu_policy),
-	ATTR_LIST(min_ipu_util),
-	ATTR_LIST(min_fsync_blocks),
-	ATTR_LIST(max_victim_search),
-	ATTR_LIST(dir_level),
-	ATTR_LIST(ram_thresh),
-	ATTR_LIST(ra_nid_pages),
-	ATTR_LIST(dirty_nats_ratio),
-	ATTR_LIST(cp_interval),
-	ATTR_LIST(idle_interval),
-#ifdef CONFIG_F2FS_FAULT_INJECTION
-	ATTR_LIST(inject_rate),
-	ATTR_LIST(inject_type),
-#endif
-	ATTR_LIST(lifetime_write_kbytes),
-	NULL,
-};
-
-static const struct sysfs_ops f2fs_attr_ops = {
-	.show	= f2fs_attr_show,
-	.store	= f2fs_attr_store,
-};
-
-static struct kobj_type f2fs_ktype = {
-	.default_attrs	= f2fs_attrs,
-	.sysfs_ops	= &f2fs_attr_ops,
-	.release	= f2fs_sb_release,
-};
-
 void f2fs_msg(struct super_block *sb, const char *level, const char *fmt, ...)
 {
 	struct va_format vaf;
@@ -429,6 +241,9 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_noheap:
 			set_opt(sbi, NOHEAP);
 			break;
+		case Opt_heap:
+			clear_opt(sbi, NOHEAP);
+			break;
 #ifdef CONFIG_F2FS_FS_XATTR
 		case Opt_user_xattr:
 			set_opt(sbi, XATTR_USER);
@@ -439,6 +254,9 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_inline_xattr:
 			set_opt(sbi, INLINE_XATTR);
 			break;
+		case Opt_noinline_xattr:
+			clear_opt(sbi, INLINE_XATTR);
+			break;
 #else
 		case Opt_user_xattr:
 			f2fs_msg(sb, KERN_INFO,
@@ -452,6 +270,10 @@ static int parse_options(struct super_block *sb, char *options)
 			f2fs_msg(sb, KERN_INFO,
 				"inline_xattr options not supported");
 			break;
+		case Opt_noinline_xattr:
+			f2fs_msg(sb, KERN_INFO,
+				"noinline_xattr options not supported");
+			break;
 #endif
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
 		case Opt_acl:
@@ -535,11 +357,23 @@ static int parse_options(struct super_block *sb, char *options)
 			}
 			kfree(name);
 			break;
+		case Opt_io_size_bits:
+			if (args->from && match_int(args, &arg))
+				return -EINVAL;
+			if (arg > __ilog2_u32(BIO_MAX_PAGES)) {
+				f2fs_msg(sb, KERN_WARNING,
+					"Not support %d, larger than %d",
+					1 << arg, BIO_MAX_PAGES);
+				return -EINVAL;
+			}
+			sbi->write_io_size_bits = arg;
+			break;
 		case Opt_fault_injection:
 			if (args->from && match_int(args, &arg))
 				return -EINVAL;
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 			f2fs_build_fault_attr(sbi, arg);
+			set_opt(sbi, FAULT_INJECTION);
 #else
 			f2fs_msg(sb, KERN_INFO,
 				"FAULT_INJECTION was not selected");
@@ -551,6 +385,20 @@ static int parse_options(struct super_block *sb, char *options)
 		case Opt_nolazytime:
 			sb->s_flags &= ~MS_LAZYTIME;
 			break;
+#ifdef CONFIG_QUOTA
+		case Opt_usrquota:
+			set_opt(sbi, USRQUOTA);
+			break;
+		case Opt_grpquota:
+			set_opt(sbi, GRPQUOTA);
+			break;
+#else
+		case Opt_usrquota:
+		case Opt_grpquota:
+			f2fs_msg(sb, KERN_INFO,
+					"quota operations not supported");
+			break;
+#endif
 		default:
 			f2fs_msg(sb, KERN_ERR,
 				"Unrecognized mount option \"%s\" or missing value",
@@ -558,6 +406,13 @@ static int parse_options(struct super_block *sb, char *options)
 			return -EINVAL;
 		}
 	}
+
+	if (F2FS_IO_SIZE_BITS(sbi) && !test_opt(sbi, LFS)) {
+		f2fs_msg(sb, KERN_ERR,
+				"Should set mode=lfs with %uKB-sized IO",
+				F2FS_IO_SIZE_KB(sbi));
+		return -EINVAL;
+	}
 	return 0;
 }
 
@@ -583,7 +438,12 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 	mutex_init(&fi->inmem_lock);
 	init_rwsem(&fi->dio_rwsem[READ]);
 	init_rwsem(&fi->dio_rwsem[WRITE]);
+	init_rwsem(&fi->i_mmap_sem);
 
+#ifdef CONFIG_QUOTA
+	memset(&fi->i_dquot, 0, sizeof(fi->i_dquot));
+	fi->i_reserved_quota = 0;
+#endif
 	/* Will be used by directory only */
 	fi->i_dir_level = F2FS_SB(sb)->dir_level;
 	return &fi->vfs_inode;
@@ -591,6 +451,7 @@ static struct inode *f2fs_alloc_inode(struct super_block *sb)
 
 static int f2fs_drop_inode(struct inode *inode)
 {
+	int ret;
 	/*
 	 * This is to avoid a deadlock condition like below.
 	 * writeback_single_inode(inode)
@@ -623,10 +484,12 @@ static int f2fs_drop_inode(struct inode *inode)
 			spin_lock(&inode->i_lock);
 			atomic_dec(&inode->i_count);
 		}
+		trace_f2fs_drop_inode(inode, 0);
 		return 0;
 	}
-
-	return generic_drop_inode(inode);
+	ret = generic_drop_inode(inode);
+	trace_f2fs_drop_inode(inode, ret);
+	return ret;
 }
 
 int f2fs_inode_dirtied(struct inode *inode, bool sync)
@@ -721,18 +584,13 @@ static void destroy_device_list(struct f2fs_sb_info *sbi)
 	kfree(sbi->devs);
 }
 
+static void f2fs_quota_off_umount(struct super_block *sb);
 static void f2fs_put_super(struct super_block *sb)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	int i;
 
-	if (sbi->s_proc) {
-		remove_proc_entry("segment_info", sbi->s_proc);
-		remove_proc_entry("segment_bits", sbi->s_proc);
-		remove_proc_entry(sb->s_id, f2fs_proc_root);
-	}
-	kobject_del(&sbi->s_kobj);
-
-	stop_gc_thread(sbi);
+	f2fs_quota_off_umount(sb);
 
 	/* prevent remaining shrinker jobs */
 	mutex_lock(&sbi->umount_mutex);
@@ -750,6 +608,16 @@ static void f2fs_put_super(struct super_block *sb)
 		write_checkpoint(sbi, &cpc);
 	}
 
+	/* be sure to wait for any on-going discard commands */
+	f2fs_wait_discard_bios(sbi);
+
+	if (f2fs_discard_en(sbi) && !sbi->discard_blks) {
+		struct cp_control cpc = {
+			.reason = CP_UMOUNT | CP_TRIMMED,
+		};
+		write_checkpoint(sbi, &cpc);
+	}
+
 	/* write_checkpoint can update stat informaion */
 	f2fs_destroy_stats(sbi);
 
@@ -763,7 +631,7 @@ static void f2fs_put_super(struct super_block *sb)
 	mutex_unlock(&sbi->umount_mutex);
 
 	/* our cp_error case, we can wait for any writeback page */
-	f2fs_flush_merged_bios(sbi);
+	f2fs_flush_merged_writes(sbi);
 
 	iput(sbi->node_inode);
 	iput(sbi->meta_inode);
@@ -773,8 +641,8 @@ static void f2fs_put_super(struct super_block *sb)
 	destroy_segment_manager(sbi);
 
 	kfree(sbi->ckpt);
-	kobject_put(&sbi->s_kobj);
-	wait_for_completion(&sbi->s_kobj_unregister);
+
+	f2fs_exit_sysfs(sbi);
 
 	sb->s_fs_info = NULL;
 	if (sbi->s_chksum_driver)
@@ -782,8 +650,10 @@ static void f2fs_put_super(struct super_block *sb)
 	kfree(sbi->raw_super);
 
 	destroy_device_list(sbi);
-
+	mempool_destroy(sbi->write_io_dummy);
 	destroy_percpu_info(sbi);
+	for (i = 0; i < NR_PAGE_TYPE; i++)
+		kfree(sbi->write_io[i]);
 	kfree(sbi);
 }
 
@@ -834,6 +704,7 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	u64 id = huge_encode_dev(sb->s_bdev->bd_dev);
 	block_t total_count, user_block_count, start_count, ovp_count;
+	u64 avail_node_count;
 
 	total_count = le64_to_cpu(sbi->raw_super->block_count);
 	user_block_count = sbi->user_block_count;
@@ -844,11 +715,19 @@ static int f2fs_statfs(struct dentry *dentry, struct kstatfs *buf)
 
 	buf->f_blocks = total_count - start_count;
 	buf->f_bfree = user_block_count - valid_user_blocks(sbi) + ovp_count;
-	buf->f_bavail = user_block_count - valid_user_blocks(sbi);
+	buf->f_bavail = user_block_count - valid_user_blocks(sbi) -
+						sbi->reserved_blocks;
 
-	buf->f_files = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
-	buf->f_ffree = min(buf->f_files - valid_node_count(sbi),
-							buf->f_bavail);
+	avail_node_count = sbi->total_node_count - F2FS_RESERVED_NODE_NUM;
+
+	if (avail_node_count > user_block_count) {
+		buf->f_files = user_block_count;
+		buf->f_ffree = buf->f_bavail;
+	} else {
+		buf->f_files = avail_node_count;
+		buf->f_ffree = min(avail_node_count - valid_node_count(sbi),
+					buf->f_bavail);
+	}
 
 	buf->f_namelen = F2FS_NAME_LEN;
 	buf->f_fsid.val[0] = (u32)id;
@@ -874,7 +753,9 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 	if (test_opt(sbi, DISCARD))
 		seq_puts(seq, ",discard");
 	if (test_opt(sbi, NOHEAP))
-		seq_puts(seq, ",no_heap_alloc");
+		seq_puts(seq, ",no_heap");
+	else
+		seq_puts(seq, ",heap");
 #ifdef CONFIG_F2FS_FS_XATTR
 	if (test_opt(sbi, XATTR_USER))
 		seq_puts(seq, ",user_xattr");
@@ -882,6 +763,8 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 		seq_puts(seq, ",nouser_xattr");
 	if (test_opt(sbi, INLINE_XATTR))
 		seq_puts(seq, ",inline_xattr");
+	else
+		seq_puts(seq, ",noinline_xattr");
 #endif
 #ifdef CONFIG_F2FS_FS_POSIX_ACL
 	if (test_opt(sbi, POSIX_ACL))
@@ -918,86 +801,34 @@ static int f2fs_show_options(struct seq_file *seq, struct dentry *root)
 	else if (test_opt(sbi, LFS))
 		seq_puts(seq, "lfs");
 	seq_printf(seq, ",active_logs=%u", sbi->active_logs);
+	if (F2FS_IO_SIZE_BITS(sbi))
+		seq_printf(seq, ",io_size=%uKB", F2FS_IO_SIZE_KB(sbi));
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (test_opt(sbi, FAULT_INJECTION))
+		seq_printf(seq, ",fault_injection=%u",
+				sbi->fault_info.inject_rate);
+#endif
+#ifdef CONFIG_QUOTA
+	if (test_opt(sbi, USRQUOTA))
+		seq_puts(seq, ",usrquota");
+	if (test_opt(sbi, GRPQUOTA))
+		seq_puts(seq, ",grpquota");
+#endif
 
 	return 0;
 }
 
-static int segment_info_seq_show(struct seq_file *seq, void *offset)
-{
-	struct super_block *sb = seq->private;
-	struct f2fs_sb_info *sbi = F2FS_SB(sb);
-	unsigned int total_segs =
-			le32_to_cpu(sbi->raw_super->segment_count_main);
-	int i;
-
-	seq_puts(seq, "format: segment_type|valid_blocks\n"
-		"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
-
-	for (i = 0; i < total_segs; i++) {
-		struct seg_entry *se = get_seg_entry(sbi, i);
-
-		if ((i % 10) == 0)
-			seq_printf(seq, "%-10d", i);
-		seq_printf(seq, "%d|%-3u", se->type,
-					get_valid_blocks(sbi, i, 1));
-		if ((i % 10) == 9 || i == (total_segs - 1))
-			seq_putc(seq, '\n');
-		else
-			seq_putc(seq, ' ');
-	}
-
-	return 0;
-}
-
-static int segment_bits_seq_show(struct seq_file *seq, void *offset)
-{
-	struct super_block *sb = seq->private;
-	struct f2fs_sb_info *sbi = F2FS_SB(sb);
-	unsigned int total_segs =
-			le32_to_cpu(sbi->raw_super->segment_count_main);
-	int i, j;
-
-	seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n"
-		"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
-
-	for (i = 0; i < total_segs; i++) {
-		struct seg_entry *se = get_seg_entry(sbi, i);
-
-		seq_printf(seq, "%-10d", i);
-		seq_printf(seq, "%d|%-3u|", se->type,
-					get_valid_blocks(sbi, i, 1));
-		for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
-			seq_printf(seq, " %.2x", se->cur_valid_map[j]);
-		seq_putc(seq, '\n');
-	}
-	return 0;
-}
-
-#define F2FS_PROC_FILE_DEF(_name)					\
-static int _name##_open_fs(struct inode *inode, struct file *file)	\
-{									\
-	return single_open(file, _name##_seq_show, PDE_DATA(inode));	\
-}									\
-									\
-static const struct file_operations f2fs_seq_##_name##_fops = {		\
-	.open = _name##_open_fs,					\
-	.read = seq_read,						\
-	.llseek = seq_lseek,						\
-	.release = single_release,					\
-};
-
-F2FS_PROC_FILE_DEF(segment_info);
-F2FS_PROC_FILE_DEF(segment_bits);
-
 static void default_options(struct f2fs_sb_info *sbi)
 {
 	/* init some FS parameters */
 	sbi->active_logs = NR_CURSEG_TYPE;
 
 	set_opt(sbi, BG_GC);
+	set_opt(sbi, INLINE_XATTR);
 	set_opt(sbi, INLINE_DATA);
 	set_opt(sbi, INLINE_DENTRY);
 	set_opt(sbi, EXTENT_CACHE);
+	set_opt(sbi, NOHEAP);
 	sbi->sb->s_flags |= MS_LAZYTIME;
 	set_opt(sbi, FLUSH_MERGE);
 	if (f2fs_sb_mounted_blkzoned(sbi->sb)) {
@@ -1023,6 +854,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct f2fs_sb_info *sbi = F2FS_SB(sb);
 	struct f2fs_mount_info org_mount_opt;
+	unsigned long old_sb_flags;
 	int err, active_logs;
 	bool need_restart_gc = false;
 	bool need_stop_gc = false;
@@ -1036,6 +868,7 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	 * need to restore them.
 	 */
 	org_mount_opt = sbi->mount_opt;
+	old_sb_flags = sb->s_flags;
 	active_logs = sbi->active_logs;
 
 	/* recover superblocks we couldn't write due to previous RO mount */
@@ -1047,7 +880,6 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 			clear_sbi_flag(sbi, SBI_NEED_SB_WRITE);
 	}
 
-	sbi->mount_opt.opt = 0;
 	default_options(sbi);
 
 	/* parse mount options */
@@ -1062,6 +894,16 @@ static int f2fs_remount(struct super_block *sb, int *flags, char *data)
 	if (f2fs_readonly(sb) && (*flags & MS_RDONLY))
 		goto skip;
 
+	if (!f2fs_readonly(sb) && (*flags & MS_RDONLY)) {
+		err = dquot_suspend(sb, -1);
+		if (err < 0)
+			goto restore_opts;
+	} else {
+		/* dquot_resume needs RW */
+		sb->s_flags &= ~MS_RDONLY;
+		dquot_resume(sb, -1);
+	}
+
 	/* disallow enable/disable extent_cache dynamically */
 	if (no_extent_cache == !!test_opt(sbi, EXTENT_CACHE)) {
 		err = -EINVAL;
@@ -1126,12 +968,237 @@ restore_gc:
 restore_opts:
 	sbi->mount_opt = org_mount_opt;
 	sbi->active_logs = active_logs;
+	sb->s_flags = old_sb_flags;
 #ifdef CONFIG_F2FS_FAULT_INJECTION
 	sbi->fault_info = ffi;
 #endif
 	return err;
 }
 
+#ifdef CONFIG_QUOTA
+/* Read data from quotafile */
+static ssize_t f2fs_quota_read(struct super_block *sb, int type, char *data,
+			       size_t len, loff_t off)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	struct address_space *mapping = inode->i_mapping;
+	block_t blkidx = F2FS_BYTES_TO_BLK(off);
+	int offset = off & (sb->s_blocksize - 1);
+	int tocopy;
+	size_t toread;
+	loff_t i_size = i_size_read(inode);
+	struct page *page;
+	char *kaddr;
+
+	if (off > i_size)
+		return 0;
+
+	if (off + len > i_size)
+		len = i_size - off;
+	toread = len;
+	while (toread > 0) {
+		tocopy = min_t(unsigned long, sb->s_blocksize - offset, toread);
+repeat:
+		page = read_mapping_page(mapping, blkidx, NULL);
+		if (IS_ERR(page))
+			return PTR_ERR(page);
+
+		lock_page(page);
+
+		if (unlikely(page->mapping != mapping)) {
+			f2fs_put_page(page, 1);
+			goto repeat;
+		}
+		if (unlikely(!PageUptodate(page))) {
+			f2fs_put_page(page, 1);
+			return -EIO;
+		}
+
+		kaddr = kmap_atomic(page);
+		memcpy(data, kaddr + offset, tocopy);
+		kunmap_atomic(kaddr);
+		f2fs_put_page(page, 1);
+
+		offset = 0;
+		toread -= tocopy;
+		data += tocopy;
+		blkidx++;
+	}
+	return len;
+}
+
+/* Write to quotafile */
+static ssize_t f2fs_quota_write(struct super_block *sb, int type,
+				const char *data, size_t len, loff_t off)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	struct address_space *mapping = inode->i_mapping;
+	const struct address_space_operations *a_ops = mapping->a_ops;
+	int offset = off & (sb->s_blocksize - 1);
+	size_t towrite = len;
+	struct page *page;
+	char *kaddr;
+	int err = 0;
+	int tocopy;
+
+	while (towrite > 0) {
+		tocopy = min_t(unsigned long, sb->s_blocksize - offset,
+								towrite);
+
+		err = a_ops->write_begin(NULL, mapping, off, tocopy, 0,
+							&page, NULL);
+		if (unlikely(err))
+			break;
+
+		kaddr = kmap_atomic(page);
+		memcpy(kaddr + offset, data, tocopy);
+		kunmap_atomic(kaddr);
+		flush_dcache_page(page);
+
+		a_ops->write_end(NULL, mapping, off, tocopy, tocopy,
+						page, NULL);
+		offset = 0;
+		towrite -= tocopy;
+		off += tocopy;
+		data += tocopy;
+		cond_resched();
+	}
+
+	if (len == towrite)
+		return err;
+	inode->i_version++;
+	inode->i_mtime = inode->i_ctime = current_time(inode);
+	f2fs_mark_inode_dirty_sync(inode, false);
+	return len - towrite;
+}
+
+static struct dquot **f2fs_get_dquots(struct inode *inode)
+{
+	return F2FS_I(inode)->i_dquot;
+}
+
+static qsize_t *f2fs_get_reserved_space(struct inode *inode)
+{
+	return &F2FS_I(inode)->i_reserved_quota;
+}
+
+static int f2fs_quota_sync(struct super_block *sb, int type)
+{
+	struct quota_info *dqopt = sb_dqopt(sb);
+	int cnt;
+	int ret;
+
+	ret = dquot_writeback_dquots(sb, type);
+	if (ret)
+		return ret;
+
+	/*
+	 * Now when everything is written we can discard the pagecache so
+	 * that userspace sees the changes.
+	 */
+	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
+		if (type != -1 && cnt != type)
+			continue;
+		if (!sb_has_quota_active(sb, cnt))
+			continue;
+
+		ret = filemap_write_and_wait(dqopt->files[cnt]->i_mapping);
+		if (ret)
+			return ret;
+
+		inode_lock(dqopt->files[cnt]);
+		truncate_inode_pages(&dqopt->files[cnt]->i_data, 0);
+		inode_unlock(dqopt->files[cnt]);
+	}
+	return 0;
+}
+
+static int f2fs_quota_on(struct super_block *sb, int type, int format_id,
+							const struct path *path)
+{
+	struct inode *inode;
+	int err;
+
+	err = f2fs_quota_sync(sb, -1);
+	if (err)
+		return err;
+
+	err = dquot_quota_on(sb, type, format_id, path);
+	if (err)
+		return err;
+
+	inode = d_inode(path->dentry);
+
+	inode_lock(inode);
+	F2FS_I(inode)->i_flags |= FS_NOATIME_FL | FS_IMMUTABLE_FL;
+	inode_set_flags(inode, S_NOATIME | S_IMMUTABLE,
+					S_NOATIME | S_IMMUTABLE);
+	inode_unlock(inode);
+	f2fs_mark_inode_dirty_sync(inode, false);
+
+	return 0;
+}
+
+static int f2fs_quota_off(struct super_block *sb, int type)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	int err;
+
+	if (!inode || !igrab(inode))
+		return dquot_quota_off(sb, type);
+
+	f2fs_quota_sync(sb, -1);
+
+	err = dquot_quota_off(sb, type);
+	if (err)
+		goto out_put;
+
+	inode_lock(inode);
+	F2FS_I(inode)->i_flags &= ~(FS_NOATIME_FL | FS_IMMUTABLE_FL);
+	inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE);
+	inode_unlock(inode);
+	f2fs_mark_inode_dirty_sync(inode, false);
+out_put:
+	iput(inode);
+	return err;
+}
+
+static void f2fs_quota_off_umount(struct super_block *sb)
+{
+	int type;
+
+	for (type = 0; type < MAXQUOTAS; type++)
+		f2fs_quota_off(sb, type);
+}
+
+static const struct dquot_operations f2fs_quota_operations = {
+	.get_reserved_space = f2fs_get_reserved_space,
+	.write_dquot	= dquot_commit,
+	.acquire_dquot	= dquot_acquire,
+	.release_dquot	= dquot_release,
+	.mark_dirty	= dquot_mark_dquot_dirty,
+	.write_info	= dquot_commit_info,
+	.alloc_dquot	= dquot_alloc,
+	.destroy_dquot	= dquot_destroy,
+	.get_next_id	= dquot_get_next_id,
+};
+
+static const struct quotactl_ops f2fs_quotactl_ops = {
+	.quota_on	= f2fs_quota_on,
+	.quota_off	= f2fs_quota_off,
+	.quota_sync	= f2fs_quota_sync,
+	.get_state	= dquot_get_state,
+	.set_info	= dquot_set_dqinfo,
+	.get_dqblk	= dquot_get_dqblk,
+	.set_dqblk	= dquot_set_dqblk,
+	.get_nextdqblk	= dquot_get_next_dqblk,
+};
+#else
+static inline void f2fs_quota_off_umount(struct super_block *sb)
+{
+}
+#endif
+
 static struct super_operations f2fs_sops = {
 	.alloc_inode	= f2fs_alloc_inode,
 	.drop_inode	= f2fs_drop_inode,
@@ -1139,6 +1206,11 @@ static struct super_operations f2fs_sops = {
 	.write_inode	= f2fs_write_inode,
 	.dirty_inode	= f2fs_dirty_inode,
 	.show_options	= f2fs_show_options,
+#ifdef CONFIG_QUOTA
+	.quota_read	= f2fs_quota_read,
+	.quota_write	= f2fs_quota_write,
+	.get_dquots	= f2fs_get_dquots,
+#endif
 	.evict_inode	= f2fs_evict_inode,
 	.put_super	= f2fs_put_super,
 	.sync_fs	= f2fs_sync_fs,
@@ -1156,12 +1228,6 @@ static int f2fs_get_context(struct inode *inode, void *ctx, size_t len)
 				ctx, len, NULL);
 }
 
-static int f2fs_key_prefix(struct inode *inode, u8 **key)
-{
-	*key = F2FS_I_SB(inode)->key_prefix;
-	return F2FS_I_SB(inode)->key_prefix_size;
-}
-
 static int f2fs_set_context(struct inode *inode, const void *ctx, size_t len,
 							void *fs_data)
 {
@@ -1176,16 +1242,16 @@ static unsigned f2fs_max_namelen(struct inode *inode)
 			inode->i_sb->s_blocksize : F2FS_NAME_LEN;
 }
 
-static struct fscrypt_operations f2fs_cryptops = {
+static const struct fscrypt_operations f2fs_cryptops = {
+	.key_prefix	= "f2fs:",
 	.get_context	= f2fs_get_context,
-	.key_prefix	= f2fs_key_prefix,
 	.set_context	= f2fs_set_context,
 	.is_encrypted	= f2fs_encrypted_inode,
 	.empty_dir	= f2fs_empty_dir,
 	.max_namelen	= f2fs_max_namelen,
 };
 #else
-static struct fscrypt_operations f2fs_cryptops = {
+static const struct fscrypt_operations f2fs_cryptops = {
 	.is_encrypted	= f2fs_encrypted_inode,
 };
 #endif
@@ -1265,7 +1331,7 @@ static int __f2fs_commit_super(struct buffer_head *bh,
 	unlock_buffer(bh);
 
 	/* it's rare case, we can do fua all the time */
-	return __sync_dirty_buffer(bh, REQ_PREFLUSH | REQ_FUA);
+	return __sync_dirty_buffer(bh, REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
 }
 
 static inline bool sanity_check_area_boundary(struct f2fs_sb_info *sbi,
@@ -1441,6 +1507,13 @@ static int sanity_check_raw_super(struct f2fs_sb_info *sbi,
 		return 1;
 	}
 
+	if (le32_to_cpu(raw_super->segment_count) > F2FS_MAX_SEGMENT) {
+		f2fs_msg(sb, KERN_INFO,
+			"Invalid segment count (%u)",
+			le32_to_cpu(raw_super->segment_count));
+		return 1;
+	}
+
 	/* check CP/SIT/NAT/SSA/MAIN_AREA area boundary */
 	if (sanity_check_area_boundary(sbi, bh))
 		return 1;
@@ -1454,6 +1527,8 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
 	struct f2fs_checkpoint *ckpt = F2FS_CKPT(sbi);
 	unsigned int ovp_segments, reserved_segments;
+	unsigned int main_segs, blocks_per_seg;
+	int i;
 
 	total = le32_to_cpu(raw_super->segment_count);
 	fsmeta = le32_to_cpu(raw_super->segment_count_ckpt);
@@ -1475,6 +1550,20 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 		return 1;
 	}
 
+	main_segs = le32_to_cpu(raw_super->segment_count_main);
+	blocks_per_seg = sbi->blocks_per_seg;
+
+	for (i = 0; i < NR_CURSEG_NODE_TYPE; i++) {
+		if (le32_to_cpu(ckpt->cur_node_segno[i]) >= main_segs ||
+			le16_to_cpu(ckpt->cur_node_blkoff[i]) >= blocks_per_seg)
+			return 1;
+	}
+	for (i = 0; i < NR_CURSEG_DATA_TYPE; i++) {
+		if (le32_to_cpu(ckpt->cur_data_segno[i]) >= main_segs ||
+			le16_to_cpu(ckpt->cur_data_blkoff[i]) >= blocks_per_seg)
+			return 1;
+	}
+
 	if (unlikely(f2fs_cp_error(sbi))) {
 		f2fs_msg(sbi->sb, KERN_ERR, "A bug case: need to run fsck");
 		return 1;
@@ -1485,7 +1574,7 @@ int sanity_check_ckpt(struct f2fs_sb_info *sbi)
 static void init_sb_info(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = sbi->raw_super;
-	int i;
+	int i, j;
 
 	sbi->log_sectors_per_block =
 		le32_to_cpu(raw_super->log_sectors_per_block);
@@ -1513,17 +1602,14 @@ static void init_sb_info(struct f2fs_sb_info *sbi)
 	for (i = 0; i < NR_COUNT_TYPE; i++)
 		atomic_set(&sbi->nr_pages[i], 0);
 
+	atomic_set(&sbi->wb_sync_req, 0);
+
 	INIT_LIST_HEAD(&sbi->s_list);
 	mutex_init(&sbi->umount_mutex);
-	mutex_init(&sbi->wio_mutex[NODE]);
-	mutex_init(&sbi->wio_mutex[DATA]);
+	for (i = 0; i < NR_PAGE_TYPE - 1; i++)
+		for (j = HOT; j < NR_TEMP_TYPE; j++)
+			mutex_init(&sbi->wio_mutex[i][j]);
 	spin_lock_init(&sbi->cp_lock);
-
-#ifdef CONFIG_F2FS_FS_ENCRYPTION
-	memcpy(sbi->key_prefix, F2FS_KEY_DESC_PREFIX,
-				F2FS_KEY_DESC_PREFIX_SIZE);
-	sbi->key_prefix_size = F2FS_KEY_DESC_PREFIX_SIZE;
-#endif
 }
 
 static int init_percpu_info(struct f2fs_sb_info *sbi)
@@ -1698,36 +1784,55 @@ int f2fs_commit_super(struct f2fs_sb_info *sbi, bool recover)
 static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 {
 	struct f2fs_super_block *raw_super = F2FS_RAW_SUPER(sbi);
+	unsigned int max_devices = MAX_DEVICES;
 	int i;
 
-	for (i = 0; i < MAX_DEVICES; i++) {
-		if (!RDEV(i).path[0])
+	/* Initialize single device information */
+	if (!RDEV(0).path[0]) {
+		if (!bdev_is_zoned(sbi->sb->s_bdev))
 			return 0;
+		max_devices = 1;
+	}
 
-		if (i == 0) {
-			sbi->devs = kzalloc(sizeof(struct f2fs_dev_info) *
-						MAX_DEVICES, GFP_KERNEL);
-			if (!sbi->devs)
-				return -ENOMEM;
-		}
+	/*
+	 * Initialize multiple devices information, or single
+	 * zoned block device information.
+	 */
+	sbi->devs = kcalloc(max_devices, sizeof(struct f2fs_dev_info),
+				GFP_KERNEL);
+	if (!sbi->devs)
+		return -ENOMEM;
 
-		memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN);
-		FDEV(i).total_segments = le32_to_cpu(RDEV(i).total_segments);
-		if (i == 0) {
-			FDEV(i).start_blk = 0;
-			FDEV(i).end_blk = FDEV(i).start_blk +
-				(FDEV(i).total_segments <<
-				sbi->log_blocks_per_seg) - 1 +
-				le32_to_cpu(raw_super->segment0_blkaddr);
-		} else {
-			FDEV(i).start_blk = FDEV(i - 1).end_blk + 1;
-			FDEV(i).end_blk = FDEV(i).start_blk +
-				(FDEV(i).total_segments <<
-				sbi->log_blocks_per_seg) - 1;
-		}
+	for (i = 0; i < max_devices; i++) {
+
+		if (i > 0 && !RDEV(i).path[0])
+			break;
 
-		FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path,
+		if (max_devices == 1) {
+			/* Single zoned block device mount */
+			FDEV(0).bdev =
+				blkdev_get_by_dev(sbi->sb->s_bdev->bd_dev,
 					sbi->sb->s_mode, sbi->sb->s_type);
+		} else {
+			/* Multi-device mount */
+			memcpy(FDEV(i).path, RDEV(i).path, MAX_PATH_LEN);
+			FDEV(i).total_segments =
+				le32_to_cpu(RDEV(i).total_segments);
+			if (i == 0) {
+				FDEV(i).start_blk = 0;
+				FDEV(i).end_blk = FDEV(i).start_blk +
+				    (FDEV(i).total_segments <<
+				    sbi->log_blocks_per_seg) - 1 +
+				    le32_to_cpu(raw_super->segment0_blkaddr);
+			} else {
+				FDEV(i).start_blk = FDEV(i - 1).end_blk + 1;
+				FDEV(i).end_blk = FDEV(i).start_blk +
+					(FDEV(i).total_segments <<
+					sbi->log_blocks_per_seg) - 1;
+			}
+			FDEV(i).bdev = blkdev_get_by_path(FDEV(i).path,
+					sbi->sb->s_mode, sbi->sb->s_type);
+		}
 		if (IS_ERR(FDEV(i).bdev))
 			return PTR_ERR(FDEV(i).bdev);
 
@@ -1747,6 +1852,8 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 					"Failed to initialize F2FS blkzone information");
 				return -EINVAL;
 			}
+			if (max_devices == 1)
+				break;
 			f2fs_msg(sbi->sb, KERN_INFO,
 				"Mount Device [%2d]: %20s, %8u, %8x - %8x (zone: %s)",
 				i, FDEV(i).path,
@@ -1763,6 +1870,8 @@ static int f2fs_scan_devices(struct f2fs_sb_info *sbi)
 				FDEV(i).total_segments,
 				FDEV(i).start_blk, FDEV(i).end_blk);
 	}
+	f2fs_msg(sbi->sb, KERN_INFO,
+			"IO Block Size: %8d KB", F2FS_IO_SIZE_KB(sbi));
 	return 0;
 }
 
@@ -1822,6 +1931,7 @@ try_onemore:
 	if (f2fs_sb_mounted_blkzoned(sb)) {
 		f2fs_msg(sb, KERN_ERR,
 			 "Zoned block device support is not enabled\n");
+		err = -EOPNOTSUPP;
 		goto free_sb_buf;
 	}
 #endif
@@ -1843,6 +1953,12 @@ try_onemore:
 	sb->s_max_links = F2FS_LINK_MAX;
 	get_random_bytes(&sbi->s_next_generation, sizeof(u32));
 
+#ifdef CONFIG_QUOTA
+	sb->dq_op = &f2fs_quota_operations;
+	sb->s_qcop = &f2fs_quotactl_ops;
+	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
+#endif
+
 	sb->s_op = &f2fs_sops;
 	sb->s_cop = &f2fs_cryptops;
 	sb->s_xattr = f2fs_xattr_handlers;
@@ -1851,25 +1967,37 @@ try_onemore:
 	sb->s_time_gran = 1;
 	sb->s_flags = (sb->s_flags & ~MS_POSIXACL) |
 		(test_opt(sbi, POSIX_ACL) ? MS_POSIXACL : 0);
-	memcpy(sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
+	memcpy(&sb->s_uuid, raw_super->uuid, sizeof(raw_super->uuid));
 
 	/* init f2fs-specific super block info */
 	sbi->valid_super_block = valid_super_block;
 	mutex_init(&sbi->gc_mutex);
 	mutex_init(&sbi->cp_mutex);
 	init_rwsem(&sbi->node_write);
+	init_rwsem(&sbi->node_change);
 
 	/* disallow all the data/node/meta page writes */
 	set_sbi_flag(sbi, SBI_POR_DOING);
 	spin_lock_init(&sbi->stat_lock);
 
-	init_rwsem(&sbi->read_io.io_rwsem);
-	sbi->read_io.sbi = sbi;
-	sbi->read_io.bio = NULL;
 	for (i = 0; i < NR_PAGE_TYPE; i++) {
-		init_rwsem(&sbi->write_io[i].io_rwsem);
-		sbi->write_io[i].sbi = sbi;
-		sbi->write_io[i].bio = NULL;
+		int n = (i == META) ? 1: NR_TEMP_TYPE;
+		int j;
+
+		sbi->write_io[i] = kmalloc(n * sizeof(struct f2fs_bio_info),
+								GFP_KERNEL);
+		if (!sbi->write_io[i]) {
+			err = -ENOMEM;
+			goto free_options;
+		}
+
+		for (j = HOT; j < n; j++) {
+			init_rwsem(&sbi->write_io[i][j].io_rwsem);
+			sbi->write_io[i][j].sbi = sbi;
+			sbi->write_io[i][j].bio = NULL;
+			spin_lock_init(&sbi->write_io[i][j].io_lock);
+			INIT_LIST_HEAD(&sbi->write_io[i][j].io_list);
+		}
 	}
 
 	init_rwsem(&sbi->cp_rwsem);
@@ -1880,12 +2008,21 @@ try_onemore:
 	if (err)
 		goto free_options;
 
+	if (F2FS_IO_SIZE(sbi) > 1) {
+		sbi->write_io_dummy =
+			mempool_create_page_pool(2 * (F2FS_IO_SIZE(sbi) - 1), 0);
+		if (!sbi->write_io_dummy) {
+			err = -ENOMEM;
+			goto free_options;
+		}
+	}
+
 	/* get an inode for meta space */
 	sbi->meta_inode = f2fs_iget(sb, F2FS_META_INO(sbi));
 	if (IS_ERR(sbi->meta_inode)) {
 		f2fs_msg(sb, KERN_ERR, "Failed to read F2FS meta data inode");
 		err = PTR_ERR(sbi->meta_inode);
-		goto free_options;
+		goto free_io_dummy;
 	}
 
 	err = get_valid_checkpoint(sbi);
@@ -1909,6 +2046,7 @@ try_onemore:
 	sbi->total_valid_block_count =
 				le64_to_cpu(sbi->ckpt->valid_block_count);
 	sbi->last_valid_block_count = sbi->total_valid_block_count;
+	sbi->reserved_blocks = 0;
 
 	for (i = 0; i < NR_INODE_TYPE; i++) {
 		INIT_LIST_HEAD(&sbi->inode_list[i]);
@@ -1956,6 +2094,10 @@ try_onemore:
 
 	f2fs_join_shrinker(sbi);
 
+	err = f2fs_build_stats(sbi);
+	if (err)
+		goto free_nm;
+
 	/* if there are nt orphan nodes free them */
 	err = recover_orphan_inodes(sbi);
 	if (err)
@@ -1980,27 +2122,10 @@ try_onemore:
 		goto free_root_inode;
 	}
 
-	err = f2fs_build_stats(sbi);
+	err = f2fs_init_sysfs(sbi);
 	if (err)
 		goto free_root_inode;
 
-	if (f2fs_proc_root)
-		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
-
-	if (sbi->s_proc) {
-		proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
-				 &f2fs_seq_segment_info_fops, sb);
-		proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
-				 &f2fs_seq_segment_bits_fops, sb);
-	}
-
-	sbi->s_kobj.kset = f2fs_kset;
-	init_completion(&sbi->s_kobj_unregister);
-	err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
-							"%s", sb->s_id);
-	if (err)
-		goto free_proc;
-
 	/* recover fsynced data */
 	if (!test_opt(sbi, DISABLE_ROLL_FORWARD)) {
 		/*
@@ -2010,7 +2135,7 @@ try_onemore:
 		if (bdev_read_only(sb->s_bdev) &&
 				!is_set_ckpt_flags(sbi, CP_UMOUNT_FLAG)) {
 			err = -EROFS;
-			goto free_kobj;
+			goto free_sysfs;
 		}
 
 		if (need_fsck)
@@ -2024,7 +2149,7 @@ try_onemore:
 			need_fsck = true;
 			f2fs_msg(sb, KERN_ERR,
 				"Cannot recover all fsync data errno=%d", err);
-			goto free_kobj;
+			goto free_sysfs;
 		}
 	} else {
 		err = recover_fsync_data(sbi, true);
@@ -2033,7 +2158,7 @@ try_onemore:
 			err = -EINVAL;
 			f2fs_msg(sb, KERN_ERR,
 				"Need to recover fsync data");
-			goto free_kobj;
+			goto free_sysfs;
 		}
 	}
 skip_recovery:
@@ -2048,7 +2173,7 @@ skip_recovery:
 		/* After POR, we can run background GC thread.*/
 		err = start_gc_thread(sbi);
 		if (err)
-			goto free_kobj;
+			goto free_sysfs;
 	}
 	kfree(options);
 
@@ -2060,22 +2185,15 @@ skip_recovery:
 			sbi->valid_super_block ? 1 : 2, err);
 	}
 
+	f2fs_msg(sbi->sb, KERN_NOTICE, "Mounted with checkpoint version = %llx",
+				cur_cp_version(F2FS_CKPT(sbi)));
 	f2fs_update_time(sbi, CP_TIME);
 	f2fs_update_time(sbi, REQ_TIME);
 	return 0;
 
-free_kobj:
+free_sysfs:
 	f2fs_sync_inode_meta(sbi);
-	kobject_del(&sbi->s_kobj);
-	kobject_put(&sbi->s_kobj);
-	wait_for_completion(&sbi->s_kobj_unregister);
-free_proc:
-	if (sbi->s_proc) {
-		remove_proc_entry("segment_info", sbi->s_proc);
-		remove_proc_entry("segment_bits", sbi->s_proc);
-		remove_proc_entry(sb->s_id, f2fs_proc_root);
-	}
-	f2fs_destroy_stats(sbi);
+	f2fs_exit_sysfs(sbi);
 free_root_inode:
 	dput(sb->s_root);
 	sb->s_root = NULL;
@@ -2093,6 +2211,7 @@ free_node_inode:
 	truncate_inode_pages_final(META_MAPPING(sbi));
 	iput(sbi->node_inode);
 	mutex_unlock(&sbi->umount_mutex);
+	f2fs_destroy_stats(sbi);
 free_nm:
 	destroy_node_manager(sbi);
 free_sm:
@@ -2103,7 +2222,11 @@ free_devices:
 free_meta_inode:
 	make_bad_inode(sbi->meta_inode);
 	iput(sbi->meta_inode);
+free_io_dummy:
+	mempool_destroy(sbi->write_io_dummy);
 free_options:
+	for (i = 0; i < NR_PAGE_TYPE; i++)
+		kfree(sbi->write_io[i]);
 	destroy_percpu_info(sbi);
 	kfree(options);
 free_sb_buf:
@@ -2130,8 +2253,11 @@ static struct dentry *f2fs_mount(struct file_system_type *fs_type, int flags,
 
 static void kill_f2fs_super(struct super_block *sb)
 {
-	if (sb->s_root)
+	if (sb->s_root) {
 		set_sbi_flag(F2FS_SB(sb), SBI_IS_CLOSE);
+		stop_gc_thread(F2FS_SB(sb));
+		stop_discard_thread(F2FS_SB(sb));
+	}
 	kill_block_super(sb);
 }
 
@@ -2185,30 +2311,26 @@ static int __init init_f2fs_fs(void)
 	err = create_extent_cache();
 	if (err)
 		goto free_checkpoint_caches;
-	f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
-	if (!f2fs_kset) {
-		err = -ENOMEM;
+	err = f2fs_register_sysfs();
+	if (err)
 		goto free_extent_cache;
-	}
 	err = register_shrinker(&f2fs_shrinker_info);
 	if (err)
-		goto free_kset;
-
+		goto free_sysfs;
 	err = register_filesystem(&f2fs_fs_type);
 	if (err)
 		goto free_shrinker;
 	err = f2fs_create_root_stats();
 	if (err)
 		goto free_filesystem;
-	f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
 	return 0;
 
 free_filesystem:
 	unregister_filesystem(&f2fs_fs_type);
 free_shrinker:
 	unregister_shrinker(&f2fs_shrinker_info);
-free_kset:
-	kset_unregister(f2fs_kset);
+free_sysfs:
+	f2fs_unregister_sysfs();
 free_extent_cache:
 	destroy_extent_cache();
 free_checkpoint_caches:
@@ -2225,11 +2347,10 @@ fail:
 
 static void __exit exit_f2fs_fs(void)
 {
-	remove_proc_entry("fs/f2fs", NULL);
 	f2fs_destroy_root_stats();
 	unregister_filesystem(&f2fs_fs_type);
 	unregister_shrinker(&f2fs_shrinker_info);
-	kset_unregister(f2fs_kset);
+	f2fs_unregister_sysfs();
 	destroy_extent_cache();
 	destroy_checkpoint_caches();
 	destroy_segment_manager_caches();
diff --git a/fs/f2fs/sysfs.c b/fs/f2fs/sysfs.c
new file mode 100644
index 000000000000..71191d89917d
--- /dev/null
+++ b/fs/f2fs/sysfs.c
@@ -0,0 +1,365 @@
+/*
+ * f2fs sysfs interface
+ *
+ * Copyright (c) 2012 Samsung Electronics Co., Ltd.
+ *             http://www.samsung.com/
+ * Copyright (c) 2017 Chao Yu <chao@kernel.org>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+#include <linux/proc_fs.h>
+#include <linux/f2fs_fs.h>
+#include <linux/seq_file.h>
+
+#include "f2fs.h"
+#include "segment.h"
+#include "gc.h"
+
+static struct proc_dir_entry *f2fs_proc_root;
+static struct kset *f2fs_kset;
+
+/* Sysfs support for f2fs */
+enum {
+	GC_THREAD,	/* struct f2fs_gc_thread */
+	SM_INFO,	/* struct f2fs_sm_info */
+	DCC_INFO,	/* struct discard_cmd_control */
+	NM_INFO,	/* struct f2fs_nm_info */
+	F2FS_SBI,	/* struct f2fs_sb_info */
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	FAULT_INFO_RATE,	/* struct f2fs_fault_info */
+	FAULT_INFO_TYPE,	/* struct f2fs_fault_info */
+#endif
+	RESERVED_BLOCKS,
+};
+
+struct f2fs_attr {
+	struct attribute attr;
+	ssize_t (*show)(struct f2fs_attr *, struct f2fs_sb_info *, char *);
+	ssize_t (*store)(struct f2fs_attr *, struct f2fs_sb_info *,
+			 const char *, size_t);
+	int struct_type;
+	int offset;
+};
+
+static unsigned char *__struct_ptr(struct f2fs_sb_info *sbi, int struct_type)
+{
+	if (struct_type == GC_THREAD)
+		return (unsigned char *)sbi->gc_thread;
+	else if (struct_type == SM_INFO)
+		return (unsigned char *)SM_I(sbi);
+	else if (struct_type == DCC_INFO)
+		return (unsigned char *)SM_I(sbi)->dcc_info;
+	else if (struct_type == NM_INFO)
+		return (unsigned char *)NM_I(sbi);
+	else if (struct_type == F2FS_SBI || struct_type == RESERVED_BLOCKS)
+		return (unsigned char *)sbi;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	else if (struct_type == FAULT_INFO_RATE ||
+					struct_type == FAULT_INFO_TYPE)
+		return (unsigned char *)&sbi->fault_info;
+#endif
+	return NULL;
+}
+
+static ssize_t lifetime_write_kbytes_show(struct f2fs_attr *a,
+		struct f2fs_sb_info *sbi, char *buf)
+{
+	struct super_block *sb = sbi->sb;
+
+	if (!sb->s_bdev->bd_part)
+		return snprintf(buf, PAGE_SIZE, "0\n");
+
+	return snprintf(buf, PAGE_SIZE, "%llu\n",
+		(unsigned long long)(sbi->kbytes_written +
+			BD_PART_WRITTEN(sbi)));
+}
+
+static ssize_t f2fs_sbi_show(struct f2fs_attr *a,
+			struct f2fs_sb_info *sbi, char *buf)
+{
+	unsigned char *ptr = NULL;
+	unsigned int *ui;
+
+	ptr = __struct_ptr(sbi, a->struct_type);
+	if (!ptr)
+		return -EINVAL;
+
+	ui = (unsigned int *)(ptr + a->offset);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n", *ui);
+}
+
+static ssize_t f2fs_sbi_store(struct f2fs_attr *a,
+			struct f2fs_sb_info *sbi,
+			const char *buf, size_t count)
+{
+	unsigned char *ptr;
+	unsigned long t;
+	unsigned int *ui;
+	ssize_t ret;
+
+	ptr = __struct_ptr(sbi, a->struct_type);
+	if (!ptr)
+		return -EINVAL;
+
+	ui = (unsigned int *)(ptr + a->offset);
+
+	ret = kstrtoul(skip_spaces(buf), 0, &t);
+	if (ret < 0)
+		return ret;
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	if (a->struct_type == FAULT_INFO_TYPE && t >= (1 << FAULT_MAX))
+		return -EINVAL;
+#endif
+	if (a->struct_type == RESERVED_BLOCKS) {
+		spin_lock(&sbi->stat_lock);
+		if ((unsigned long)sbi->total_valid_block_count + t >
+				(unsigned long)sbi->user_block_count) {
+			spin_unlock(&sbi->stat_lock);
+			return -EINVAL;
+		}
+		*ui = t;
+		spin_unlock(&sbi->stat_lock);
+		return count;
+	}
+	*ui = t;
+	return count;
+}
+
+static ssize_t f2fs_attr_show(struct kobject *kobj,
+				struct attribute *attr, char *buf)
+{
+	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+								s_kobj);
+	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
+
+	return a->show ? a->show(a, sbi, buf) : 0;
+}
+
+static ssize_t f2fs_attr_store(struct kobject *kobj, struct attribute *attr,
+						const char *buf, size_t len)
+{
+	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+									s_kobj);
+	struct f2fs_attr *a = container_of(attr, struct f2fs_attr, attr);
+
+	return a->store ? a->store(a, sbi, buf, len) : 0;
+}
+
+static void f2fs_sb_release(struct kobject *kobj)
+{
+	struct f2fs_sb_info *sbi = container_of(kobj, struct f2fs_sb_info,
+								s_kobj);
+	complete(&sbi->s_kobj_unregister);
+}
+
+#define F2FS_ATTR_OFFSET(_struct_type, _name, _mode, _show, _store, _offset) \
+static struct f2fs_attr f2fs_attr_##_name = {			\
+	.attr = {.name = __stringify(_name), .mode = _mode },	\
+	.show	= _show,					\
+	.store	= _store,					\
+	.struct_type = _struct_type,				\
+	.offset = _offset					\
+}
+
+#define F2FS_RW_ATTR(struct_type, struct_name, name, elname)	\
+	F2FS_ATTR_OFFSET(struct_type, name, 0644,		\
+		f2fs_sbi_show, f2fs_sbi_store,			\
+		offsetof(struct struct_name, elname))
+
+#define F2FS_GENERAL_RO_ATTR(name) \
+static struct f2fs_attr f2fs_attr_##name = __ATTR(name, 0444, name##_show, NULL)
+
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_min_sleep_time, min_sleep_time);
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_max_sleep_time, max_sleep_time);
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_no_gc_sleep_time, no_gc_sleep_time);
+F2FS_RW_ATTR(GC_THREAD, f2fs_gc_kthread, gc_idle, gc_idle);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, reclaim_segments, rec_prefree_segments);
+F2FS_RW_ATTR(DCC_INFO, discard_cmd_control, max_small_discards, max_discards);
+F2FS_RW_ATTR(RESERVED_BLOCKS, f2fs_sb_info, reserved_blocks, reserved_blocks);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, batched_trim_sections, trim_sections);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, ipu_policy, ipu_policy);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_ipu_util, min_ipu_util);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_fsync_blocks, min_fsync_blocks);
+F2FS_RW_ATTR(SM_INFO, f2fs_sm_info, min_hot_blocks, min_hot_blocks);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ram_thresh, ram_thresh);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, ra_nid_pages, ra_nid_pages);
+F2FS_RW_ATTR(NM_INFO, f2fs_nm_info, dirty_nats_ratio, dirty_nats_ratio);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, max_victim_search, max_victim_search);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, dir_level, dir_level);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, cp_interval, interval_time[CP_TIME]);
+F2FS_RW_ATTR(F2FS_SBI, f2fs_sb_info, idle_interval, interval_time[REQ_TIME]);
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+F2FS_RW_ATTR(FAULT_INFO_RATE, f2fs_fault_info, inject_rate, inject_rate);
+F2FS_RW_ATTR(FAULT_INFO_TYPE, f2fs_fault_info, inject_type, inject_type);
+#endif
+F2FS_GENERAL_RO_ATTR(lifetime_write_kbytes);
+
+#define ATTR_LIST(name) (&f2fs_attr_##name.attr)
+static struct attribute *f2fs_attrs[] = {
+	ATTR_LIST(gc_min_sleep_time),
+	ATTR_LIST(gc_max_sleep_time),
+	ATTR_LIST(gc_no_gc_sleep_time),
+	ATTR_LIST(gc_idle),
+	ATTR_LIST(reclaim_segments),
+	ATTR_LIST(max_small_discards),
+	ATTR_LIST(batched_trim_sections),
+	ATTR_LIST(ipu_policy),
+	ATTR_LIST(min_ipu_util),
+	ATTR_LIST(min_fsync_blocks),
+	ATTR_LIST(min_hot_blocks),
+	ATTR_LIST(max_victim_search),
+	ATTR_LIST(dir_level),
+	ATTR_LIST(ram_thresh),
+	ATTR_LIST(ra_nid_pages),
+	ATTR_LIST(dirty_nats_ratio),
+	ATTR_LIST(cp_interval),
+	ATTR_LIST(idle_interval),
+#ifdef CONFIG_F2FS_FAULT_INJECTION
+	ATTR_LIST(inject_rate),
+	ATTR_LIST(inject_type),
+#endif
+	ATTR_LIST(lifetime_write_kbytes),
+	ATTR_LIST(reserved_blocks),
+	NULL,
+};
+
+static const struct sysfs_ops f2fs_attr_ops = {
+	.show	= f2fs_attr_show,
+	.store	= f2fs_attr_store,
+};
+
+static struct kobj_type f2fs_ktype = {
+	.default_attrs	= f2fs_attrs,
+	.sysfs_ops	= &f2fs_attr_ops,
+	.release	= f2fs_sb_release,
+};
+
+static int segment_info_seq_show(struct seq_file *seq, void *offset)
+{
+	struct super_block *sb = seq->private;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	unsigned int total_segs =
+			le32_to_cpu(sbi->raw_super->segment_count_main);
+	int i;
+
+	seq_puts(seq, "format: segment_type|valid_blocks\n"
+		"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
+
+	for (i = 0; i < total_segs; i++) {
+		struct seg_entry *se = get_seg_entry(sbi, i);
+
+		if ((i % 10) == 0)
+			seq_printf(seq, "%-10d", i);
+		seq_printf(seq, "%d|%-3u", se->type,
+					get_valid_blocks(sbi, i, false));
+		if ((i % 10) == 9 || i == (total_segs - 1))
+			seq_putc(seq, '\n');
+		else
+			seq_putc(seq, ' ');
+	}
+
+	return 0;
+}
+
+static int segment_bits_seq_show(struct seq_file *seq, void *offset)
+{
+	struct super_block *sb = seq->private;
+	struct f2fs_sb_info *sbi = F2FS_SB(sb);
+	unsigned int total_segs =
+			le32_to_cpu(sbi->raw_super->segment_count_main);
+	int i, j;
+
+	seq_puts(seq, "format: segment_type|valid_blocks|bitmaps\n"
+		"segment_type(0:HD, 1:WD, 2:CD, 3:HN, 4:WN, 5:CN)\n");
+
+	for (i = 0; i < total_segs; i++) {
+		struct seg_entry *se = get_seg_entry(sbi, i);
+
+		seq_printf(seq, "%-10d", i);
+		seq_printf(seq, "%d|%-3u|", se->type,
+					get_valid_blocks(sbi, i, false));
+		for (j = 0; j < SIT_VBLOCK_MAP_SIZE; j++)
+			seq_printf(seq, " %.2x", se->cur_valid_map[j]);
+		seq_putc(seq, '\n');
+	}
+	return 0;
+}
+
+#define F2FS_PROC_FILE_DEF(_name)					\
+static int _name##_open_fs(struct inode *inode, struct file *file)	\
+{									\
+	return single_open(file, _name##_seq_show, PDE_DATA(inode));	\
+}									\
+									\
+static const struct file_operations f2fs_seq_##_name##_fops = {		\
+	.open = _name##_open_fs,					\
+	.read = seq_read,						\
+	.llseek = seq_lseek,						\
+	.release = single_release,					\
+};
+
+F2FS_PROC_FILE_DEF(segment_info);
+F2FS_PROC_FILE_DEF(segment_bits);
+
+int __init f2fs_register_sysfs(void)
+{
+	f2fs_proc_root = proc_mkdir("fs/f2fs", NULL);
+
+	f2fs_kset = kset_create_and_add("f2fs", NULL, fs_kobj);
+	if (!f2fs_kset)
+		return -ENOMEM;
+	return 0;
+}
+
+void f2fs_unregister_sysfs(void)
+{
+	kset_unregister(f2fs_kset);
+	remove_proc_entry("fs/f2fs", NULL);
+}
+
+int f2fs_init_sysfs(struct f2fs_sb_info *sbi)
+{
+	struct super_block *sb = sbi->sb;
+	int err;
+
+	if (f2fs_proc_root)
+		sbi->s_proc = proc_mkdir(sb->s_id, f2fs_proc_root);
+
+	if (sbi->s_proc) {
+		proc_create_data("segment_info", S_IRUGO, sbi->s_proc,
+				 &f2fs_seq_segment_info_fops, sb);
+		proc_create_data("segment_bits", S_IRUGO, sbi->s_proc,
+				 &f2fs_seq_segment_bits_fops, sb);
+	}
+
+	sbi->s_kobj.kset = f2fs_kset;
+	init_completion(&sbi->s_kobj_unregister);
+	err = kobject_init_and_add(&sbi->s_kobj, &f2fs_ktype, NULL,
+							"%s", sb->s_id);
+	if (err)
+		goto err_out;
+	return 0;
+err_out:
+	if (sbi->s_proc) {
+		remove_proc_entry("segment_info", sbi->s_proc);
+		remove_proc_entry("segment_bits", sbi->s_proc);
+		remove_proc_entry(sb->s_id, f2fs_proc_root);
+	}
+	return err;
+}
+
+void f2fs_exit_sysfs(struct f2fs_sb_info *sbi)
+{
+	kobject_del(&sbi->s_kobj);
+	kobject_put(&sbi->s_kobj);
+	wait_for_completion(&sbi->s_kobj_unregister);
+
+	if (sbi->s_proc) {
+		remove_proc_entry("segment_info", sbi->s_proc);
+		remove_proc_entry("segment_bits", sbi->s_proc);
+		remove_proc_entry(sbi->sb->s_id, f2fs_proc_root);
+	}
+}
diff --git a/fs/f2fs/trace.c b/fs/f2fs/trace.c
index 73b4e1d1912a..bccbbf2616d2 100644
--- a/fs/f2fs/trace.c
+++ b/fs/f2fs/trace.c
@@ -59,7 +59,7 @@ void f2fs_trace_pid(struct page *page)
 	pid_t pid = task_pid_nr(current);
 	void *p;
 
-	page->private = pid;
+	set_page_private(page, (unsigned long)pid);
 
 	if (radix_tree_preload(GFP_NOFS))
 		return;
@@ -138,7 +138,7 @@ static unsigned int gang_lookup_pids(pid_t *results, unsigned long first_index,
 
 	radix_tree_for_each_slot(slot, &pids, &iter, first_index) {
 		results[ret] = iter.index;
-		if (++ret == PIDVEC_SIZE)
+		if (++ret == max_items)
 			break;
 	}
 	return ret;
diff --git a/fs/f2fs/xattr.c b/fs/f2fs/xattr.c
index c47ce2f330a1..832c5110abab 100644
--- a/fs/f2fs/xattr.c
+++ b/fs/f2fs/xattr.c
@@ -217,18 +217,123 @@ static struct f2fs_xattr_entry *__find_xattr(void *base_addr, int index,
 	return entry;
 }
 
+static struct f2fs_xattr_entry *__find_inline_xattr(void *base_addr,
+					void **last_addr, int index,
+					size_t len, const char *name)
+{
+	struct f2fs_xattr_entry *entry;
+	unsigned int inline_size = F2FS_INLINE_XATTR_ADDRS << 2;
+
+	list_for_each_xattr(entry, base_addr) {
+		if ((void *)entry + sizeof(__u32) > base_addr + inline_size ||
+			(void *)XATTR_NEXT_ENTRY(entry) + sizeof(__u32) >
+			base_addr + inline_size) {
+			*last_addr = entry;
+			return NULL;
+		}
+		if (entry->e_name_index != index)
+			continue;
+		if (entry->e_name_len != len)
+			continue;
+		if (!memcmp(entry->e_name, name, len))
+			break;
+	}
+	return entry;
+}
+
+static int lookup_all_xattrs(struct inode *inode, struct page *ipage,
+				unsigned int index, unsigned int len,
+				const char *name, struct f2fs_xattr_entry **xe,
+				void **base_addr)
+{
+	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
+	void *cur_addr, *txattr_addr, *last_addr = NULL;
+	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+	unsigned int size = xnid ? VALID_XATTR_BLOCK_SIZE : 0;
+	unsigned int inline_size = inline_xattr_size(inode);
+	int err = 0;
+
+	if (!size && !inline_size)
+		return -ENODATA;
+
+	txattr_addr = kzalloc(inline_size + size + XATTR_PADDING_SIZE,
+							GFP_F2FS_ZERO);
+	if (!txattr_addr)
+		return -ENOMEM;
+
+	/* read from inline xattr */
+	if (inline_size) {
+		struct page *page = NULL;
+		void *inline_addr;
+
+		if (ipage) {
+			inline_addr = inline_xattr_addr(ipage);
+		} else {
+			page = get_node_page(sbi, inode->i_ino);
+			if (IS_ERR(page)) {
+				err = PTR_ERR(page);
+				goto out;
+			}
+			inline_addr = inline_xattr_addr(page);
+		}
+		memcpy(txattr_addr, inline_addr, inline_size);
+		f2fs_put_page(page, 1);
+
+		*xe = __find_inline_xattr(txattr_addr, &last_addr,
+						index, len, name);
+		if (*xe)
+			goto check;
+	}
+
+	/* read from xattr node block */
+	if (xnid) {
+		struct page *xpage;
+		void *xattr_addr;
+
+		/* The inode already has an extended attribute block. */
+		xpage = get_node_page(sbi, xnid);
+		if (IS_ERR(xpage)) {
+			err = PTR_ERR(xpage);
+			goto out;
+		}
+
+		xattr_addr = page_address(xpage);
+		memcpy(txattr_addr + inline_size, xattr_addr, size);
+		f2fs_put_page(xpage, 1);
+	}
+
+	if (last_addr)
+		cur_addr = XATTR_HDR(last_addr) - 1;
+	else
+		cur_addr = txattr_addr;
+
+	*xe = __find_xattr(cur_addr, index, len, name);
+check:
+	if (IS_XATTR_LAST_ENTRY(*xe)) {
+		err = -ENODATA;
+		goto out;
+	}
+
+	*base_addr = txattr_addr;
+	return 0;
+out:
+	kzfree(txattr_addr);
+	return err;
+}
+
 static int read_all_xattrs(struct inode *inode, struct page *ipage,
 							void **base_addr)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
 	struct f2fs_xattr_header *header;
-	size_t size = PAGE_SIZE, inline_size = 0;
+	nid_t xnid = F2FS_I(inode)->i_xattr_nid;
+	unsigned int size = VALID_XATTR_BLOCK_SIZE;
+	unsigned int inline_size = inline_xattr_size(inode);
 	void *txattr_addr;
 	int err;
 
-	inline_size = inline_xattr_size(inode);
-
-	txattr_addr = kzalloc(inline_size + size, GFP_F2FS_ZERO);
+	txattr_addr = kzalloc(inline_size + size + XATTR_PADDING_SIZE,
+							GFP_F2FS_ZERO);
 	if (!txattr_addr)
 		return -ENOMEM;
 
@@ -252,19 +357,19 @@ static int read_all_xattrs(struct inode *inode, struct page *ipage,
 	}
 
 	/* read from xattr node block */
-	if (F2FS_I(inode)->i_xattr_nid) {
+	if (xnid) {
 		struct page *xpage;
 		void *xattr_addr;
 
 		/* The inode already has an extended attribute block. */
-		xpage = get_node_page(sbi, F2FS_I(inode)->i_xattr_nid);
+		xpage = get_node_page(sbi, xnid);
 		if (IS_ERR(xpage)) {
 			err = PTR_ERR(xpage);
 			goto fail;
 		}
 
 		xattr_addr = page_address(xpage);
-		memcpy(txattr_addr + inline_size, xattr_addr, PAGE_SIZE);
+		memcpy(txattr_addr + inline_size, xattr_addr, size);
 		f2fs_put_page(xpage, 1);
 	}
 
@@ -286,14 +391,12 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 				void *txattr_addr, struct page *ipage)
 {
 	struct f2fs_sb_info *sbi = F2FS_I_SB(inode);
-	size_t inline_size = 0;
+	size_t inline_size = inline_xattr_size(inode);
 	void *xattr_addr;
 	struct page *xpage;
 	nid_t new_nid = 0;
 	int err;
 
-	inline_size = inline_xattr_size(inode);
-
 	if (hsize > inline_size && !F2FS_I(inode)->i_xattr_nid)
 		if (!alloc_nid(sbi, &new_nid))
 			return -ENOSPC;
@@ -348,23 +451,20 @@ static inline int write_all_xattrs(struct inode *inode, __u32 hsize,
 	}
 
 	xattr_addr = page_address(xpage);
-	memcpy(xattr_addr, txattr_addr + inline_size, PAGE_SIZE -
-						sizeof(struct node_footer));
+	memcpy(xattr_addr, txattr_addr + inline_size, VALID_XATTR_BLOCK_SIZE);
 	set_page_dirty(xpage);
 	f2fs_put_page(xpage, 1);
 
-	/* need to checkpoint during fsync */
-	F2FS_I(inode)->xattr_ver = cur_cp_version(F2FS_CKPT(sbi));
 	return 0;
 }
 
 int f2fs_getxattr(struct inode *inode, int index, const char *name,
 		void *buffer, size_t buffer_size, struct page *ipage)
 {
-	struct f2fs_xattr_entry *entry;
-	void *base_addr;
+	struct f2fs_xattr_entry *entry = NULL;
 	int error = 0;
-	size_t size, len;
+	unsigned int size, len;
+	void *base_addr = NULL;
 
 	if (name == NULL)
 		return -EINVAL;
@@ -373,21 +473,16 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
 	if (len > F2FS_NAME_LEN)
 		return -ERANGE;
 
-	error = read_all_xattrs(inode, ipage, &base_addr);
+	error = lookup_all_xattrs(inode, ipage, index, len, name,
+				&entry, &base_addr);
 	if (error)
 		return error;
 
-	entry = __find_xattr(base_addr, index, len, name);
-	if (IS_XATTR_LAST_ENTRY(entry)) {
-		error = -ENODATA;
-		goto cleanup;
-	}
-
 	size = le16_to_cpu(entry->e_value_size);
 
 	if (buffer && size > buffer_size) {
 		error = -ERANGE;
-		goto cleanup;
+		goto out;
 	}
 
 	if (buffer) {
@@ -395,8 +490,7 @@ int f2fs_getxattr(struct inode *inode, int index, const char *name,
 		memcpy(buffer, pval, size);
 	}
 	error = size;
-
-cleanup:
+out:
 	kzfree(base_addr);
 	return error;
 }
@@ -445,6 +539,15 @@ cleanup:
 	return error;
 }
 
+static bool f2fs_xattr_value_same(struct f2fs_xattr_entry *entry,
+					const void *value, size_t size)
+{
+	void *pval = entry->e_name + entry->e_name_len;
+
+	return (le16_to_cpu(entry->e_value_size) == size) &&
+					!memcmp(pval, value, size);
+}
+
 static int __f2fs_setxattr(struct inode *inode, int index,
 			const char *name, const void *value, size_t size,
 			struct page *ipage, int flags)
@@ -479,12 +582,17 @@ static int __f2fs_setxattr(struct inode *inode, int index,
 
 	found = IS_XATTR_LAST_ENTRY(here) ? 0 : 1;
 
-	if ((flags & XATTR_REPLACE) && !found) {
+	if (found) {
+		if ((flags & XATTR_CREATE)) {
+			error = -EEXIST;
+			goto exit;
+		}
+
+		if (f2fs_xattr_value_same(here, value, size))
+			goto exit;
+	} else if ((flags & XATTR_REPLACE)) {
 		error = -ENODATA;
 		goto exit;
-	} else if ((flags & XATTR_CREATE) && found) {
-		error = -EEXIST;
-		goto exit;
 	}
 
 	last = here;
diff --git a/fs/f2fs/xattr.h b/fs/f2fs/xattr.h
index f990de20cdcd..dbcd1d16e669 100644
--- a/fs/f2fs/xattr.h
+++ b/fs/f2fs/xattr.h
@@ -58,10 +58,10 @@ struct f2fs_xattr_entry {
 #define XATTR_FIRST_ENTRY(ptr)	(XATTR_ENTRY(XATTR_HDR(ptr) + 1))
 #define XATTR_ROUND		(3)
 
-#define XATTR_ALIGN(size)	((size + XATTR_ROUND) & ~XATTR_ROUND)
+#define XATTR_ALIGN(size)	(((size) + XATTR_ROUND) & ~XATTR_ROUND)
 
 #define ENTRY_SIZE(entry) (XATTR_ALIGN(sizeof(struct f2fs_xattr_entry) + \
-			entry->e_name_len + le16_to_cpu(entry->e_value_size)))
+			(entry)->e_name_len + le16_to_cpu((entry)->e_value_size)))
 
 #define XATTR_NEXT_ENTRY(entry)	((struct f2fs_xattr_entry *)((char *)(entry) +\
 			ENTRY_SIZE(entry)))
@@ -72,9 +72,10 @@ struct f2fs_xattr_entry {
 		for (entry = XATTR_FIRST_ENTRY(addr);\
 				!IS_XATTR_LAST_ENTRY(entry);\
 				entry = XATTR_NEXT_ENTRY(entry))
-
-#define MIN_OFFSET(i)	XATTR_ALIGN(inline_xattr_size(i) + PAGE_SIZE -	\
-				sizeof(struct node_footer) - sizeof(__u32))
+#define VALID_XATTR_BLOCK_SIZE	(PAGE_SIZE - sizeof(struct node_footer))
+#define XATTR_PADDING_SIZE	(sizeof(__u32))
+#define MIN_OFFSET(i)		XATTR_ALIGN(inline_xattr_size(i) +	\
+						VALID_XATTR_BLOCK_SIZE)
 
 #define MAX_VALUE_LEN(i)	(MIN_OFFSET(i) -			\
 				sizeof(struct f2fs_xattr_header) -	\
diff --git a/fs/fat/fat.h b/fs/fat/fat.h
index e6b764a17a9c..051dac1ce3be 100644
--- a/fs/fat/fat.h
+++ b/fs/fat/fat.h
@@ -364,8 +364,8 @@ extern const struct file_operations fat_file_operations;
 extern const struct inode_operations fat_file_inode_operations;
 extern int fat_setattr(struct dentry *dentry, struct iattr *attr);
 extern void fat_truncate_blocks(struct inode *inode, loff_t offset);
-extern int fat_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		       struct kstat *stat);
+extern int fat_getattr(const struct path *path, struct kstat *stat,
+		       u32 request_mask, unsigned int flags);
 extern int fat_file_fsync(struct file *file, loff_t start, loff_t end,
 			  int datasync);
 
diff --git a/fs/fat/file.c b/fs/fat/file.c
index 3d04b124bce0..4724cc9ad650 100644
--- a/fs/fat/file.c
+++ b/fs/fat/file.c
@@ -365,9 +365,10 @@ void fat_truncate_blocks(struct inode *inode, loff_t offset)
 	fat_flush_inodes(inode->i_sb, inode, NULL);
 }
 
-int fat_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int fat_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	generic_fillattr(inode, stat);
 	stat->blksize = MSDOS_SB(inode->i_sb)->cluster_size;
 
diff --git a/fs/fat/inode.c b/fs/fat/inode.c
index 338d2f73eb29..a2c05f2ada6d 100644
--- a/fs/fat/inode.c
+++ b/fs/fat/inode.c
@@ -1359,6 +1359,16 @@ out:
 	return 0;
 }
 
+static void fat_dummy_inode_init(struct inode *inode)
+{
+	/* Initialize this dummy inode to work as no-op. */
+	MSDOS_I(inode)->mmu_private = 0;
+	MSDOS_I(inode)->i_start = 0;
+	MSDOS_I(inode)->i_logstart = 0;
+	MSDOS_I(inode)->i_attrs = 0;
+	MSDOS_I(inode)->i_pos = 0;
+}
+
 static int fat_read_root(struct inode *inode)
 {
 	struct msdos_sb_info *sbi = MSDOS_SB(inode->i_sb);
@@ -1803,12 +1813,13 @@ int fat_fill_super(struct super_block *sb, void *data, int silent, int isvfat,
 	fat_inode = new_inode(sb);
 	if (!fat_inode)
 		goto out_fail;
-	MSDOS_I(fat_inode)->i_pos = 0;
+	fat_dummy_inode_init(fat_inode);
 	sbi->fat_inode = fat_inode;
 
 	fsinfo_inode = new_inode(sb);
 	if (!fsinfo_inode)
 		goto out_fail;
+	fat_dummy_inode_init(fsinfo_inode);
 	fsinfo_inode->i_ino = MSDOS_FSINFO_INO;
 	sbi->fsinfo_inode = fsinfo_inode;
 	insert_inode_hash(fsinfo_inode);
diff --git a/fs/fcntl.c b/fs/fcntl.c
index e1c54f20325c..3b01b646e528 100644
--- a/fs/fcntl.c
+++ b/fs/fcntl.c
@@ -7,6 +7,7 @@
 #include <linux/syscalls.h>
 #include <linux/init.h>
 #include <linux/mm.h>
+#include <linux/sched/task.h>
 #include <linux/fs.h>
 #include <linux/file.h>
 #include <linux/fdtable.h>
@@ -22,6 +23,7 @@
 #include <linux/pid_namespace.h>
 #include <linux/user_namespace.h>
 #include <linux/shmem_fs.h>
+#include <linux/compat.h>
 
 #include <asm/poll.h>
 #include <asm/siginfo.h>
@@ -107,20 +109,34 @@ void __f_setown(struct file *filp, struct pid *pid, enum pid_type type,
 }
 EXPORT_SYMBOL(__f_setown);
 
-void f_setown(struct file *filp, unsigned long arg, int force)
+int f_setown(struct file *filp, unsigned long arg, int force)
 {
 	enum pid_type type;
-	struct pid *pid;
-	int who = arg;
+	struct pid *pid = NULL;
+	int who = arg, ret = 0;
+
 	type = PIDTYPE_PID;
 	if (who < 0) {
+		/* avoid overflow below */
+		if (who == INT_MIN)
+			return -EINVAL;
+
 		type = PIDTYPE_PGID;
 		who = -who;
 	}
+
 	rcu_read_lock();
-	pid = find_vpid(who);
-	__f_setown(filp, pid, type, force);
+	if (who) {
+		pid = find_vpid(who);
+		if (!pid)
+			ret = -ESRCH;
+	}
+
+	if (!ret)
+		__f_setown(filp, pid, type, force);
 	rcu_read_unlock();
+
+	return ret;
 }
 EXPORT_SYMBOL(f_setown);
 
@@ -241,9 +257,72 @@ static int f_getowner_uids(struct file *filp, unsigned long arg)
 }
 #endif
 
+static bool rw_hint_valid(enum rw_hint hint)
+{
+	switch (hint) {
+	case RWF_WRITE_LIFE_NOT_SET:
+	case RWH_WRITE_LIFE_NONE:
+	case RWH_WRITE_LIFE_SHORT:
+	case RWH_WRITE_LIFE_MEDIUM:
+	case RWH_WRITE_LIFE_LONG:
+	case RWH_WRITE_LIFE_EXTREME:
+		return true;
+	default:
+		return false;
+	}
+}
+
+static long fcntl_rw_hint(struct file *file, unsigned int cmd,
+			  unsigned long arg)
+{
+	struct inode *inode = file_inode(file);
+	u64 *argp = (u64 __user *)arg;
+	enum rw_hint hint;
+	u64 h;
+
+	switch (cmd) {
+	case F_GET_FILE_RW_HINT:
+		h = file_write_hint(file);
+		if (copy_to_user(argp, &h, sizeof(*argp)))
+			return -EFAULT;
+		return 0;
+	case F_SET_FILE_RW_HINT:
+		if (copy_from_user(&h, argp, sizeof(h)))
+			return -EFAULT;
+		hint = (enum rw_hint) h;
+		if (!rw_hint_valid(hint))
+			return -EINVAL;
+
+		spin_lock(&file->f_lock);
+		file->f_write_hint = hint;
+		spin_unlock(&file->f_lock);
+		return 0;
+	case F_GET_RW_HINT:
+		h = inode->i_write_hint;
+		if (copy_to_user(argp, &h, sizeof(*argp)))
+			return -EFAULT;
+		return 0;
+	case F_SET_RW_HINT:
+		if (copy_from_user(&h, argp, sizeof(h)))
+			return -EFAULT;
+		hint = (enum rw_hint) h;
+		if (!rw_hint_valid(hint))
+			return -EINVAL;
+
+		inode_lock(inode);
+		inode->i_write_hint = hint;
+		inode_unlock(inode);
+		return 0;
+	default:
+		return -EINVAL;
+	}
+}
+
 static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		struct file *filp)
 {
+	void __user *argp = (void __user *)arg;
+	struct flock flock;
 	long err = -EINVAL;
 
 	switch (cmd) {
@@ -271,7 +350,11 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	case F_OFD_GETLK:
 #endif
 	case F_GETLK:
-		err = fcntl_getlk(filp, cmd, (struct flock __user *) arg);
+		if (copy_from_user(&flock, argp, sizeof(flock)))
+			return -EFAULT;
+		err = fcntl_getlk(filp, cmd, &flock);
+		if (!err && copy_to_user(argp, &flock, sizeof(flock)))
+			return -EFAULT;
 		break;
 #if BITS_PER_LONG != 32
 	/* 32-bit arches must use fcntl64() */
@@ -281,7 +364,9 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		/* Fallthrough */
 	case F_SETLK:
 	case F_SETLKW:
-		err = fcntl_setlk(fd, filp, cmd, (struct flock __user *) arg);
+		if (copy_from_user(&flock, argp, sizeof(flock)))
+			return -EFAULT;
+		err = fcntl_setlk(fd, filp, cmd, &flock);
 		break;
 	case F_GETOWN:
 		/*
@@ -295,8 +380,7 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 		force_successful_syscall_return();
 		break;
 	case F_SETOWN:
-		f_setown(filp, arg, 1);
-		err = 0;
+		err = f_setown(filp, arg, 1);
 		break;
 	case F_GETOWN_EX:
 		err = f_getown_ex(filp, arg);
@@ -335,6 +419,12 @@ static long do_fcntl(int fd, unsigned int cmd, unsigned long arg,
 	case F_GET_SEALS:
 		err = shmem_fcntl(filp, cmd, arg);
 		break;
+	case F_GET_RW_HINT:
+	case F_SET_RW_HINT:
+	case F_GET_FILE_RW_HINT:
+	case F_SET_FILE_RW_HINT:
+		err = fcntl_rw_hint(filp, cmd, arg);
+		break;
 	default:
 		break;
 	}
@@ -381,7 +471,9 @@ out:
 SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
 		unsigned long, arg)
 {	
+	void __user *argp = (void __user *)arg;
 	struct fd f = fdget_raw(fd);
+	struct flock64 flock;
 	long err = -EBADF;
 
 	if (!f.file)
@@ -399,14 +491,21 @@ SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
 	switch (cmd) {
 	case F_GETLK64:
 	case F_OFD_GETLK:
-		err = fcntl_getlk64(f.file, cmd, (struct flock64 __user *) arg);
+		err = -EFAULT;
+		if (copy_from_user(&flock, argp, sizeof(flock)))
+			break;
+		err = fcntl_getlk64(f.file, cmd, &flock);
+		if (!err && copy_to_user(argp, &flock, sizeof(flock)))
+			err = -EFAULT;
 		break;
 	case F_SETLK64:
 	case F_SETLKW64:
 	case F_OFD_SETLK:
 	case F_OFD_SETLKW:
-		err = fcntl_setlk64(fd, f.file, cmd,
-				(struct flock64 __user *) arg);
+		err = -EFAULT;
+		if (copy_from_user(&flock, argp, sizeof(flock)))
+			break;
+		err = fcntl_setlk64(fd, f.file, cmd, &flock);
 		break;
 	default:
 		err = do_fcntl(fd, cmd, arg, f.file);
@@ -419,6 +518,177 @@ out:
 }
 #endif
 
+#ifdef CONFIG_COMPAT
+/* careful - don't use anywhere else */
+#define copy_flock_fields(dst, src)		\
+	(dst)->l_type = (src)->l_type;		\
+	(dst)->l_whence = (src)->l_whence;	\
+	(dst)->l_start = (src)->l_start;	\
+	(dst)->l_len = (src)->l_len;		\
+	(dst)->l_pid = (src)->l_pid;
+
+static int get_compat_flock(struct flock *kfl, const struct compat_flock __user *ufl)
+{
+	struct compat_flock fl;
+
+	if (copy_from_user(&fl, ufl, sizeof(struct compat_flock)))
+		return -EFAULT;
+	copy_flock_fields(kfl, &fl);
+	return 0;
+}
+
+static int get_compat_flock64(struct flock *kfl, const struct compat_flock64 __user *ufl)
+{
+	struct compat_flock64 fl;
+
+	if (copy_from_user(&fl, ufl, sizeof(struct compat_flock64)))
+		return -EFAULT;
+	copy_flock_fields(kfl, &fl);
+	return 0;
+}
+
+static int put_compat_flock(const struct flock *kfl, struct compat_flock __user *ufl)
+{
+	struct compat_flock fl;
+
+	memset(&fl, 0, sizeof(struct compat_flock));
+	copy_flock_fields(&fl, kfl);
+	if (copy_to_user(ufl, &fl, sizeof(struct compat_flock)))
+		return -EFAULT;
+	return 0;
+}
+
+static int put_compat_flock64(const struct flock *kfl, struct compat_flock64 __user *ufl)
+{
+	struct compat_flock64 fl;
+
+	memset(&fl, 0, sizeof(struct compat_flock64));
+	copy_flock_fields(&fl, kfl);
+	if (copy_to_user(ufl, &fl, sizeof(struct compat_flock64)))
+		return -EFAULT;
+	return 0;
+}
+#undef copy_flock_fields
+
+static unsigned int
+convert_fcntl_cmd(unsigned int cmd)
+{
+	switch (cmd) {
+	case F_GETLK64:
+		return F_GETLK;
+	case F_SETLK64:
+		return F_SETLK;
+	case F_SETLKW64:
+		return F_SETLKW;
+	}
+
+	return cmd;
+}
+
+/*
+ * GETLK was successful and we need to return the data, but it needs to fit in
+ * the compat structure.
+ * l_start shouldn't be too big, unless the original start + end is greater than
+ * COMPAT_OFF_T_MAX, in which case the app was asking for trouble, so we return
+ * -EOVERFLOW in that case.  l_len could be too big, in which case we just
+ * truncate it, and only allow the app to see that part of the conflicting lock
+ * that might make sense to it anyway
+ */
+static int fixup_compat_flock(struct flock *flock)
+{
+	if (flock->l_start > COMPAT_OFF_T_MAX)
+		return -EOVERFLOW;
+	if (flock->l_len > COMPAT_OFF_T_MAX)
+		flock->l_len = COMPAT_OFF_T_MAX;
+	return 0;
+}
+
+COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd,
+		       compat_ulong_t, arg)
+{
+	struct fd f = fdget_raw(fd);
+	struct flock flock;
+	long err = -EBADF;
+
+	if (!f.file)
+		return err;
+
+	if (unlikely(f.file->f_mode & FMODE_PATH)) {
+		if (!check_fcntl_cmd(cmd))
+			goto out_put;
+	}
+
+	err = security_file_fcntl(f.file, cmd, arg);
+	if (err)
+		goto out_put;
+
+	switch (cmd) {
+	case F_GETLK:
+		err = get_compat_flock(&flock, compat_ptr(arg));
+		if (err)
+			break;
+		err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock);
+		if (err)
+			break;
+		err = fixup_compat_flock(&flock);
+		if (err)
+			return err;
+		err = put_compat_flock(&flock, compat_ptr(arg));
+		break;
+	case F_GETLK64:
+	case F_OFD_GETLK:
+		err = get_compat_flock64(&flock, compat_ptr(arg));
+		if (err)
+			break;
+		err = fcntl_getlk(f.file, convert_fcntl_cmd(cmd), &flock);
+		if (err)
+			break;
+		err = fixup_compat_flock(&flock);
+		if (err)
+			return err;
+		err = put_compat_flock64(&flock, compat_ptr(arg));
+		break;
+	case F_SETLK:
+	case F_SETLKW:
+		err = get_compat_flock(&flock, compat_ptr(arg));
+		if (err)
+			break;
+		err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock);
+		break;
+	case F_SETLK64:
+	case F_SETLKW64:
+	case F_OFD_SETLK:
+	case F_OFD_SETLKW:
+		err = get_compat_flock64(&flock, compat_ptr(arg));
+		if (err)
+			break;
+		err = fcntl_setlk(fd, f.file, convert_fcntl_cmd(cmd), &flock);
+		break;
+	default:
+		err = do_fcntl(fd, cmd, arg, f.file);
+		break;
+	}
+out_put:
+	fdput(f);
+	return err;
+}
+
+COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd,
+		       compat_ulong_t, arg)
+{
+	switch (cmd) {
+	case F_GETLK64:
+	case F_SETLK64:
+	case F_SETLKW64:
+	case F_OFD_GETLK:
+	case F_OFD_SETLK:
+	case F_OFD_SETLKW:
+		return -EINVAL;
+	}
+	return compat_sys_fcntl64(fd, cmd, arg);
+}
+#endif
+
 /* Table to convert sigio signal codes into poll band bitmaps */
 
 static const long band_table[NSIGPOLL] = {
@@ -741,16 +1011,10 @@ static int __init fcntl_init(void)
 	 * Exceptions: O_NONBLOCK is a two bit define on parisc; O_NDELAY
 	 * is defined as O_NONBLOCK on some platforms and not on others.
 	 */
-	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ != HWEIGHT32(
-		O_RDONLY	| O_WRONLY	| O_RDWR	|
-		O_CREAT		| O_EXCL	| O_NOCTTY	|
-		O_TRUNC		| O_APPEND	| /* O_NONBLOCK	| */
-		__O_SYNC	| O_DSYNC	| FASYNC	|
-		O_DIRECT	| O_LARGEFILE	| O_DIRECTORY	|
-		O_NOFOLLOW	| O_NOATIME	| O_CLOEXEC	|
-		__FMODE_EXEC	| O_PATH	| __O_TMPFILE	|
-		__FMODE_NONOTIFY
-		));
+	BUILD_BUG_ON(21 - 1 /* for O_RDONLY being 0 */ !=
+		HWEIGHT32(
+			(VALID_OPEN_FLAGS & ~(O_NONBLOCK | O_NDELAY)) |
+			__FMODE_EXEC | __FMODE_NONOTIFY));
 
 	fasync_cache = kmem_cache_create("fasync_cache",
 		sizeof(struct fasync_struct), 0, SLAB_PANIC, NULL);
diff --git a/fs/fhandle.c b/fs/fhandle.c
index 5559168d5637..58a61f55e0d0 100644
--- a/fs/fhandle.c
+++ b/fs/fhandle.c
@@ -9,6 +9,7 @@
 #include <linux/fsnotify.h>
 #include <linux/personality.h>
 #include <linux/uaccess.h>
+#include <linux/compat.h>
 #include "internal.h"
 #include "mount.h"
 
@@ -264,3 +265,15 @@ SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
 	ret = do_handle_open(mountdirfd, handle, flags);
 	return ret;
 }
+
+#ifdef CONFIG_COMPAT
+/*
+ * Exactly like fs/open.c:sys_open_by_handle_at(), except that it
+ * doesn't set the O_LARGEFILE flag.
+ */
+COMPAT_SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd,
+			     struct file_handle __user *, handle, int, flags)
+{
+	return do_handle_open(mountdirfd, handle, flags);
+}
+#endif
diff --git a/fs/file.c b/fs/file.c
index 69d6990e3021..1fc7fbbb4510 100644
--- a/fs/file.c
+++ b/fs/file.c
@@ -12,7 +12,7 @@
 #include <linux/mm.h>
 #include <linux/mmzone.h>
 #include <linux/time.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/vmalloc.h>
 #include <linux/file.h>
@@ -30,21 +30,6 @@ unsigned int sysctl_nr_open_min = BITS_PER_LONG;
 unsigned int sysctl_nr_open_max =
 	__const_min(INT_MAX, ~(size_t)0/sizeof(void *)) & -BITS_PER_LONG;
 
-static void *alloc_fdmem(size_t size)
-{
-	/*
-	 * Very large allocations can stress page reclaim, so fall back to
-	 * vmalloc() if the allocation size will be considered "large" by the VM.
-	 */
-	if (size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER)) {
-		void *data = kmalloc(size, GFP_KERNEL_ACCOUNT |
-				     __GFP_NOWARN | __GFP_NORETRY);
-		if (data != NULL)
-			return data;
-	}
-	return __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_HIGHMEM, PAGE_KERNEL);
-}
-
 static void __free_fdtable(struct fdtable *fdt)
 {
 	kvfree(fdt->fd);
@@ -131,13 +116,14 @@ static struct fdtable * alloc_fdtable(unsigned int nr)
 	if (!fdt)
 		goto out;
 	fdt->max_fds = nr;
-	data = alloc_fdmem(nr * sizeof(struct file *));
+	data = kvmalloc_array(nr, sizeof(struct file *), GFP_KERNEL_ACCOUNT);
 	if (!data)
 		goto out_fdt;
 	fdt->fd = data;
 
-	data = alloc_fdmem(max_t(size_t,
-				 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES));
+	data = kvmalloc(max_t(size_t,
+				 2 * nr / BITS_PER_BYTE + BITBIT_SIZE(nr), L1_CACHE_BYTES),
+				 GFP_KERNEL_ACCOUNT);
 	if (!data)
 		goto out_arr;
 	fdt->open_fds = data;
diff --git a/fs/file_table.c b/fs/file_table.c
index 6d982b57de92..72e861a35a7f 100644
--- a/fs/file_table.c
+++ b/fs/file_table.c
@@ -13,6 +13,7 @@
 #include <linux/module.h>
 #include <linux/fs.h>
 #include <linux/security.h>
+#include <linux/cred.h>
 #include <linux/eventpoll.h>
 #include <linux/rcupdate.h>
 #include <linux/mount.h>
@@ -167,6 +168,7 @@ struct file *alloc_file(const struct path *path, fmode_t mode,
 	file->f_path = *path;
 	file->f_inode = path->dentry->d_inode;
 	file->f_mapping = path->dentry->d_inode->i_mapping;
+	file->f_wb_err = filemap_sample_wb_err(file->f_mapping);
 	if ((mode & FMODE_READ) &&
 	     likely(fop->read || fop->read_iter))
 		mode |= FMODE_CAN_READ;
diff --git a/fs/filesystems.c b/fs/filesystems.c
index cac75547d35c..a920ad2629ac 100644
--- a/fs/filesystems.c
+++ b/fs/filesystems.c
@@ -33,9 +33,10 @@ static struct file_system_type *file_systems;
 static DEFINE_RWLOCK(file_systems_lock);
 
 /* WARNING: This can be used only if we _already_ own a reference */
-void get_filesystem(struct file_system_type *fs)
+struct file_system_type *get_filesystem(struct file_system_type *fs)
 {
 	__module_get(fs->owner);
+	return fs;
 }
 
 void put_filesystem(struct file_system_type *fs)
@@ -275,8 +276,10 @@ struct file_system_type *get_fs_type(const char *name)
 	int len = dot ? dot - name : strlen(name);
 
 	fs = __get_fs_type(name, len);
-	if (!fs && (request_module("fs-%.*s", len, name) == 0))
+	if (!fs && (request_module("fs-%.*s", len, name) == 0)) {
 		fs = __get_fs_type(name, len);
+		WARN_ONCE(!fs, "request_module fs-%.*s succeeded, but still no fs?\n", len, name);
+	}
 
 	if (dot && fs && !(fs->fs_flags & FS_HAS_SUBTYPE)) {
 		put_filesystem(fs);
diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c
index ef600591d96f..245c430a2e41 100644
--- a/fs/fs-writeback.c
+++ b/fs/fs-writeback.c
@@ -173,19 +173,33 @@ static void wb_wakeup(struct bdi_writeback *wb)
 	spin_unlock_bh(&wb->work_lock);
 }
 
+static void finish_writeback_work(struct bdi_writeback *wb,
+				  struct wb_writeback_work *work)
+{
+	struct wb_completion *done = work->done;
+
+	if (work->auto_free)
+		kfree(work);
+	if (done && atomic_dec_and_test(&done->cnt))
+		wake_up_all(&wb->bdi->wb_waitq);
+}
+
 static void wb_queue_work(struct bdi_writeback *wb,
 			  struct wb_writeback_work *work)
 {
 	trace_writeback_queue(wb, work);
 
-	spin_lock_bh(&wb->work_lock);
-	if (!test_bit(WB_registered, &wb->state))
-		goto out_unlock;
 	if (work->done)
 		atomic_inc(&work->done->cnt);
-	list_add_tail(&work->list, &wb->work_list);
-	mod_delayed_work(bdi_wq, &wb->dwork, 0);
-out_unlock:
+
+	spin_lock_bh(&wb->work_lock);
+
+	if (test_bit(WB_registered, &wb->state)) {
+		list_add_tail(&work->list, &wb->work_list);
+		mod_delayed_work(bdi_wq, &wb->dwork, 0);
+	} else
+		finish_writeback_work(wb, work);
+
 	spin_unlock_bh(&wb->work_lock);
 }
 
@@ -366,8 +380,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
 		struct page *page = radix_tree_deref_slot_protected(slot,
 							&mapping->tree_lock);
 		if (likely(page) && PageDirty(page)) {
-			__dec_wb_stat(old_wb, WB_RECLAIMABLE);
-			__inc_wb_stat(new_wb, WB_RECLAIMABLE);
+			dec_wb_stat(old_wb, WB_RECLAIMABLE);
+			inc_wb_stat(new_wb, WB_RECLAIMABLE);
 		}
 	}
 
@@ -377,8 +391,8 @@ static void inode_switch_wbs_work_fn(struct work_struct *work)
 							&mapping->tree_lock);
 		if (likely(page)) {
 			WARN_ON_ONCE(!PageWriteback(page));
-			__dec_wb_stat(old_wb, WB_WRITEBACK);
-			__inc_wb_stat(new_wb, WB_WRITEBACK);
+			dec_wb_stat(old_wb, WB_WRITEBACK);
+			inc_wb_stat(new_wb, WB_WRITEBACK);
 		}
 	}
 
@@ -1873,16 +1887,9 @@ static long wb_do_writeback(struct bdi_writeback *wb)
 
 	set_bit(WB_writeback_running, &wb->state);
 	while ((work = get_next_work_item(wb)) != NULL) {
-		struct wb_completion *done = work->done;
-
 		trace_writeback_exec(wb, work);
-
 		wrote += wb_writeback(wb, work);
-
-		if (work->auto_free)
-			kfree(work);
-		if (done && atomic_dec_and_test(&done->cnt))
-			wake_up_all(&wb->bdi->wb_waitq);
+		finish_writeback_work(wb, work);
 	}
 
 	/*
@@ -2045,11 +2052,13 @@ static noinline void block_dump___mark_inode_dirty(struct inode *inode)
 }
 
 /**
- *	__mark_inode_dirty -	internal function
- *	@inode: inode to mark
- *	@flags: what kind of dirty (i.e. I_DIRTY_SYNC)
- *	Mark an inode as dirty. Callers should use mark_inode_dirty or
- *  	mark_inode_dirty_sync.
+ * __mark_inode_dirty -	internal function
+ *
+ * @inode: inode to mark
+ * @flags: what kind of dirty (i.e. I_DIRTY_SYNC)
+ *
+ * Mark an inode as dirty. Callers should use mark_inode_dirty or
+ * mark_inode_dirty_sync.
  *
  * Put the inode on the super block's dirty list.
  *
diff --git a/fs/fs_pin.c b/fs/fs_pin.c
index 611b5408f6ec..e747b3d720ee 100644
--- a/fs/fs_pin.c
+++ b/fs/fs_pin.c
@@ -34,7 +34,7 @@ void pin_insert(struct fs_pin *pin, struct vfsmount *m)
 
 void pin_kill(struct fs_pin *p)
 {
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	if (!p) {
 		rcu_read_unlock();
@@ -61,7 +61,7 @@ void pin_kill(struct fs_pin *p)
 		rcu_read_unlock();
 		schedule();
 		rcu_read_lock();
-		if (likely(list_empty(&wait.task_list)))
+		if (likely(list_empty(&wait.entry)))
 			break;
 		/* OK, we know p couldn't have been freed yet */
 		spin_lock_irq(&p->wait.lock);
diff --git a/fs/fs_struct.c b/fs/fs_struct.c
index 7dca743b2ce1..be0250788b73 100644
--- a/fs/fs_struct.c
+++ b/fs/fs_struct.c
@@ -1,5 +1,6 @@
 #include <linux/export.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/task.h>
 #include <linux/fs.h>
 #include <linux/path.h>
 #include <linux/slab.h>
diff --git a/fs/fscache/object-list.c b/fs/fscache/object-list.c
index 5d5ddaa84b21..67f940892ef8 100644
--- a/fs/fscache/object-list.c
+++ b/fs/fscache/object-list.c
@@ -329,7 +329,7 @@ static void fscache_objlist_config(struct fscache_objlist_data *data)
 	config = 0;
 	rcu_read_lock();
 
-	confkey = user_key_payload(key);
+	confkey = user_key_payload_rcu(key);
 	buf = confkey->data;
 
 	for (len = confkey->datalen - 1; len >= 0; len--) {
diff --git a/fs/fuse/control.c b/fs/fuse/control.c
index 6e22748b0704..b9ea99c5b5b3 100644
--- a/fs/fuse/control.c
+++ b/fs/fuse/control.c
@@ -292,7 +292,7 @@ void fuse_ctl_remove_conn(struct fuse_conn *fc)
 
 static int fuse_ctl_fill_super(struct super_block *sb, void *data, int silent)
 {
-	struct tree_descr empty_descr = {""};
+	static const struct tree_descr empty_descr = {""};
 	struct fuse_conn *fc;
 	int err;
 
diff --git a/fs/fuse/dev.c b/fs/fuse/dev.c
index 4e06a27ed7f8..c16d00e53264 100644
--- a/fs/fuse/dev.c
+++ b/fs/fuse/dev.c
@@ -11,6 +11,7 @@
 #include <linux/init.h>
 #include <linux/module.h>
 #include <linux/poll.h>
+#include <linux/sched/signal.h>
 #include <linux/uio.h>
 #include <linux/miscdevice.h>
 #include <linux/pagemap.h>
@@ -19,6 +20,7 @@
 #include <linux/pipe_fs_i.h>
 #include <linux/swap.h>
 #include <linux/splice.h>
+#include <linux/sched.h>
 
 MODULE_ALIAS_MISCDEV(FUSE_MINOR);
 MODULE_ALIAS("devname:fuse");
@@ -44,7 +46,7 @@ static void fuse_request_init(struct fuse_req *req, struct page **pages,
 	INIT_LIST_HEAD(&req->list);
 	INIT_LIST_HEAD(&req->intr_entry);
 	init_waitqueue_head(&req->waitq);
-	atomic_set(&req->count, 1);
+	refcount_set(&req->count, 1);
 	req->pages = pages;
 	req->page_descs = page_descs;
 	req->max_pages = npages;
@@ -101,21 +103,20 @@ void fuse_request_free(struct fuse_req *req)
 
 void __fuse_get_request(struct fuse_req *req)
 {
-	atomic_inc(&req->count);
+	refcount_inc(&req->count);
 }
 
 /* Must be called with > 1 refcount */
 static void __fuse_put_request(struct fuse_req *req)
 {
-	BUG_ON(atomic_read(&req->count) < 2);
-	atomic_dec(&req->count);
+	refcount_dec(&req->count);
 }
 
-static void fuse_req_init_context(struct fuse_req *req)
+static void fuse_req_init_context(struct fuse_conn *fc, struct fuse_req *req)
 {
 	req->in.h.uid = from_kuid_munged(&init_user_ns, current_fsuid());
 	req->in.h.gid = from_kgid_munged(&init_user_ns, current_fsgid());
-	req->in.h.pid = current->pid;
+	req->in.h.pid = pid_nr_ns(task_pid(current), fc->pid_ns);
 }
 
 void fuse_set_initialized(struct fuse_conn *fc)
@@ -162,7 +163,7 @@ static struct fuse_req *__fuse_get_req(struct fuse_conn *fc, unsigned npages,
 		goto out;
 	}
 
-	fuse_req_init_context(req);
+	fuse_req_init_context(fc, req);
 	__set_bit(FR_WAITING, &req->flags);
 	if (for_background)
 		__set_bit(FR_BACKGROUND, &req->flags);
@@ -255,7 +256,7 @@ struct fuse_req *fuse_get_req_nofail_nopages(struct fuse_conn *fc,
 	if (!req)
 		req = get_reserved_req(fc, file);
 
-	fuse_req_init_context(req);
+	fuse_req_init_context(fc, req);
 	__set_bit(FR_WAITING, &req->flags);
 	__clear_bit(FR_BACKGROUND, &req->flags);
 	return req;
@@ -263,7 +264,7 @@ struct fuse_req *fuse_get_req_nofail_nopages(struct fuse_conn *fc,
 
 void fuse_put_request(struct fuse_conn *fc, struct fuse_req *req)
 {
-	if (atomic_dec_and_test(&req->count)) {
+	if (refcount_dec_and_test(&req->count)) {
 		if (test_bit(FR_BACKGROUND, &req->flags)) {
 			/*
 			 * We get here in the unlikely case that a background
@@ -381,9 +382,9 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req)
 			wake_up(&fc->blocked_waitq);
 
 		if (fc->num_background == fc->congestion_threshold &&
-		    fc->connected && fc->bdi_initialized) {
-			clear_bdi_congested(&fc->bdi, BLK_RW_SYNC);
-			clear_bdi_congested(&fc->bdi, BLK_RW_ASYNC);
+		    fc->connected && fc->sb) {
+			clear_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
+			clear_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
 		}
 		fc->num_background--;
 		fc->active_background--;
@@ -399,6 +400,10 @@ static void request_end(struct fuse_conn *fc, struct fuse_req *req)
 static void queue_interrupt(struct fuse_iqueue *fiq, struct fuse_req *req)
 {
 	spin_lock(&fiq->waitq.lock);
+	if (test_bit(FR_FINISHED, &req->flags)) {
+		spin_unlock(&fiq->waitq.lock);
+		return;
+	}
 	if (list_empty(&req->intr_entry)) {
 		list_add_tail(&req->intr_entry, &fiq->interrupts);
 		wake_up_locked(&fiq->waitq);
@@ -568,10 +573,9 @@ void fuse_request_send_background_locked(struct fuse_conn *fc,
 	fc->num_background++;
 	if (fc->num_background == fc->max_background)
 		fc->blocked = 1;
-	if (fc->num_background == fc->congestion_threshold &&
-	    fc->bdi_initialized) {
-		set_bdi_congested(&fc->bdi, BLK_RW_SYNC);
-		set_bdi_congested(&fc->bdi, BLK_RW_ASYNC);
+	if (fc->num_background == fc->congestion_threshold && fc->sb) {
+		set_bdi_congested(fc->sb->s_bdi, BLK_RW_SYNC);
+		set_bdi_congested(fc->sb->s_bdi, BLK_RW_ASYNC);
 	}
 	list_add_tail(&req->list, &fc->bg_queue);
 	flush_bg_queue(fc);
@@ -1218,6 +1222,9 @@ static ssize_t fuse_dev_do_read(struct fuse_dev *fud, struct file *file,
 	struct fuse_in *in;
 	unsigned reqsize;
 
+	if (task_active_pid_ns(current) != fc->pid_ns)
+		return -EIO;
+
  restart:
 	spin_lock(&fiq->waitq.lock);
 	err = -EAGAIN;
@@ -1372,6 +1379,7 @@ static ssize_t fuse_dev_splice_read(struct file *in, loff_t *ppos,
 		 * code can Oops if the buffer persists after module unload.
 		 */
 		bufs[page_nr].ops = &nosteal_pipe_buf_ops;
+		bufs[page_nr].flags = 0;
 		ret = add_to_pipe(pipe, &bufs[page_nr++]);
 		if (unlikely(ret < 0))
 			break;
@@ -1815,6 +1823,9 @@ static ssize_t fuse_dev_do_write(struct fuse_dev *fud,
 	struct fuse_req *req;
 	struct fuse_out_header oh;
 
+	if (task_active_pid_ns(current) != fc->pid_ns)
+		return -EIO;
+
 	if (nbytes < sizeof(struct fuse_out_header))
 		return -EINVAL;
 
diff --git a/fs/fuse/dir.c b/fs/fuse/dir.c
index 811fd8929a18..00800c07ba1c 100644
--- a/fs/fuse/dir.c
+++ b/fs/fuse/dir.c
@@ -473,7 +473,7 @@ static int fuse_create_open(struct inode *dir, struct dentry *entry,
 	if (err) {
 		fuse_sync_release(ff, flags);
 	} else {
-		file->private_data = fuse_file_get(ff);
+		file->private_data = ff;
 		fuse_finish_open(inode, file);
 	}
 	return err;
@@ -1777,10 +1777,10 @@ static int fuse_setattr(struct dentry *entry, struct iattr *attr)
 	return ret;
 }
 
-static int fuse_getattr(struct vfsmount *mnt, struct dentry *entry,
-			struct kstat *stat)
+static int fuse_getattr(const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int flags)
 {
-	struct inode *inode = d_inode(entry);
+	struct inode *inode = d_inode(path->dentry);
 	struct fuse_conn *fc = get_fuse_conn(inode);
 
 	if (!fuse_allow_current_process(fc))
diff --git a/fs/fuse/file.c b/fs/fuse/file.c
index 2401c5dabb2a..3ee4fdc3da9e 100644
--- a/fs/fuse/file.c
+++ b/fs/fuse/file.c
@@ -58,7 +58,7 @@ struct fuse_file *fuse_file_alloc(struct fuse_conn *fc)
 	}
 
 	INIT_LIST_HEAD(&ff->write_entry);
-	atomic_set(&ff->count, 0);
+	refcount_set(&ff->count, 1);
 	RB_CLEAR_NODE(&ff->polled_node);
 	init_waitqueue_head(&ff->poll_wait);
 
@@ -75,9 +75,9 @@ void fuse_file_free(struct fuse_file *ff)
 	kfree(ff);
 }
 
-struct fuse_file *fuse_file_get(struct fuse_file *ff)
+static struct fuse_file *fuse_file_get(struct fuse_file *ff)
 {
-	atomic_inc(&ff->count);
+	refcount_inc(&ff->count);
 	return ff;
 }
 
@@ -88,7 +88,7 @@ static void fuse_release_end(struct fuse_conn *fc, struct fuse_req *req)
 
 static void fuse_file_put(struct fuse_file *ff, bool sync)
 {
-	if (atomic_dec_and_test(&ff->count)) {
+	if (refcount_dec_and_test(&ff->count)) {
 		struct fuse_req *req = ff->reserved_req;
 
 		if (ff->fc->no_open) {
@@ -100,6 +100,7 @@ static void fuse_file_put(struct fuse_file *ff, bool sync)
 			iput(req->misc.release.inode);
 			fuse_put_request(ff->fc, req);
 		} else if (sync) {
+			__set_bit(FR_FORCE, &req->flags);
 			__clear_bit(FR_BACKGROUND, &req->flags);
 			fuse_request_send(ff->fc, req);
 			iput(req->misc.release.inode);
@@ -146,7 +147,7 @@ int fuse_do_open(struct fuse_conn *fc, u64 nodeid, struct file *file,
 		ff->open_flags &= ~FOPEN_DIRECT_IO;
 
 	ff->nodeid = nodeid;
-	file->private_data = fuse_file_get(ff);
+	file->private_data = ff;
 
 	return 0;
 }
@@ -245,14 +246,9 @@ static void fuse_prepare_release(struct fuse_file *ff, int flags, int opcode)
 
 void fuse_release_common(struct file *file, int opcode)
 {
-	struct fuse_file *ff;
-	struct fuse_req *req;
-
-	ff = file->private_data;
-	if (unlikely(!ff))
-		return;
+	struct fuse_file *ff = file->private_data;
+	struct fuse_req *req = ff->reserved_req;
 
-	req = ff->reserved_req;
 	fuse_prepare_release(ff, file->f_flags, opcode);
 
 	if (ff->flock) {
@@ -297,13 +293,13 @@ static int fuse_release(struct inode *inode, struct file *file)
 
 void fuse_sync_release(struct fuse_file *ff, int flags)
 {
-	WARN_ON(atomic_read(&ff->count) > 1);
+	WARN_ON(refcount_read(&ff->count) > 1);
 	fuse_prepare_release(ff, flags, FUSE_RELEASE);
-	__set_bit(FR_FORCE, &ff->reserved_req->flags);
-	__clear_bit(FR_BACKGROUND, &ff->reserved_req->flags);
-	fuse_request_send(ff->fc, ff->reserved_req);
-	fuse_put_request(ff->fc, ff->reserved_req);
-	kfree(ff);
+	/*
+	 * iput(NULL) is a no-op and since the refcount is 1 and everything's
+	 * synchronous, we are fine with not doing igrab() here"
+	 */
+	fuse_file_put(ff, true);
 }
 EXPORT_SYMBOL_GPL(fuse_sync_release);
 
@@ -2043,12 +2039,12 @@ static void fuse_vma_close(struct vm_area_struct *vma)
  * - sync(2)
  * - try_to_free_pages() with order > PAGE_ALLOC_COSTLY_ORDER
  */
-static int fuse_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int fuse_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 
-	file_update_time(vma->vm_file);
+	file_update_time(vmf->vma->vm_file);
 	lock_page(page);
 	if (page->mapping != inode->i_mapping) {
 		unlock_page(page);
@@ -2087,7 +2083,8 @@ static int fuse_direct_mmap(struct file *file, struct vm_area_struct *vma)
 	return generic_file_mmap(file, vma);
 }
 
-static int convert_fuse_file_lock(const struct fuse_file_lock *ffl,
+static int convert_fuse_file_lock(struct fuse_conn *fc,
+				  const struct fuse_file_lock *ffl,
 				  struct file_lock *fl)
 {
 	switch (ffl->type) {
@@ -2102,7 +2099,14 @@ static int convert_fuse_file_lock(const struct fuse_file_lock *ffl,
 
 		fl->fl_start = ffl->start;
 		fl->fl_end = ffl->end;
-		fl->fl_pid = ffl->pid;
+
+		/*
+		 * Convert pid into the caller's pid namespace. If the pid
+		 * does not map into the namespace fl_pid will get set to 0.
+		 */
+		rcu_read_lock();
+		fl->fl_pid = pid_vnr(find_pid_ns(ffl->pid, fc->pid_ns));
+		rcu_read_unlock();
 		break;
 
 	default:
@@ -2151,7 +2155,7 @@ static int fuse_getlk(struct file *file, struct file_lock *fl)
 	args.out.args[0].value = &outarg;
 	err = fuse_simple_request(fc, &args);
 	if (!err)
-		err = convert_fuse_file_lock(&outarg.lk, fl);
+		err = convert_fuse_file_lock(fc, &outarg.lk, fl);
 
 	return err;
 }
@@ -2163,7 +2167,8 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
 	FUSE_ARGS(args);
 	struct fuse_lk_in inarg;
 	int opcode = (fl->fl_flags & FL_SLEEP) ? FUSE_SETLKW : FUSE_SETLK;
-	pid_t pid = fl->fl_type != F_UNLCK ? current->tgid : 0;
+	struct pid *pid = fl->fl_type != F_UNLCK ? task_tgid(current) : NULL;
+	pid_t pid_nr = pid_nr_ns(pid, fc->pid_ns);
 	int err;
 
 	if (fl->fl_lmops && fl->fl_lmops->lm_grant) {
@@ -2172,10 +2177,13 @@ static int fuse_setlk(struct file *file, struct file_lock *fl, int flock)
 	}
 
 	/* Unlock on close is handled by the flush method */
-	if (fl->fl_flags & FL_CLOSE)
+	if ((fl->fl_flags & FL_CLOSE_POSIX) == FL_CLOSE_POSIX)
 		return 0;
 
-	fuse_lk_fill(&args, file, fl, opcode, pid, flock, &inarg);
+	if (pid && pid_nr == 0)
+		return -EOVERFLOW;
+
+	fuse_lk_fill(&args, file, fl, opcode, pid_nr, flock, &inarg);
 	err = fuse_simple_request(fc, &args);
 
 	/* locking is restartable */
diff --git a/fs/fuse/fuse_i.h b/fs/fuse/fuse_i.h
index 91307940c8ac..1bd7ffdad593 100644
--- a/fs/fuse/fuse_i.h
+++ b/fs/fuse/fuse_i.h
@@ -24,6 +24,8 @@
 #include <linux/workqueue.h>
 #include <linux/kref.h>
 #include <linux/xattr.h>
+#include <linux/pid_namespace.h>
+#include <linux/refcount.h>
 
 /** Max number of pages that can be used in a single read request */
 #define FUSE_MAX_PAGES_PER_REQ 32
@@ -137,7 +139,7 @@ struct fuse_file {
 	u64 nodeid;
 
 	/** Refcount */
-	atomic_t count;
+	refcount_t count;
 
 	/** FOPEN_* flags returned by open */
 	u32 open_flags;
@@ -256,7 +258,7 @@ struct fuse_io_priv {
 
 #define FUSE_IO_PRIV_SYNC(f) \
 {					\
-	.refcnt = { ATOMIC_INIT(1) },	\
+	.refcnt = KREF_INIT(1),		\
 	.async = 0,			\
 	.file = f,			\
 }
@@ -306,7 +308,7 @@ struct fuse_req {
 	struct list_head intr_entry;
 
 	/** refcount */
-	atomic_t count;
+	refcount_t count;
 
 	/** Unique ID for the interrupt request */
 	u64 intr_unique;
@@ -448,7 +450,7 @@ struct fuse_conn {
 	spinlock_t lock;
 
 	/** Refcount */
-	atomic_t count;
+	refcount_t count;
 
 	/** Number of fuse_dev's */
 	atomic_t dev_count;
@@ -461,6 +463,9 @@ struct fuse_conn {
 	/** The group id for this mount */
 	kgid_t group_id;
 
+	/** The pid namespace for this mount */
+	struct pid_namespace *pid_ns;
+
 	/** Maximum read size */
 	unsigned max_read;
 
@@ -527,9 +532,6 @@ struct fuse_conn {
 	/** Filesystem supports NFS exporting.  Only set in INIT */
 	unsigned export_support:1;
 
-	/** Set if bdi is valid */
-	unsigned bdi_initialized:1;
-
 	/** write-back cache policy (default is write-through) */
 	unsigned writeback_cache:1;
 
@@ -631,9 +633,6 @@ struct fuse_conn {
 	/** Negotiated minor version */
 	unsigned minor;
 
-	/** Backing dev info */
-	struct backing_dev_info bdi;
-
 	/** Entry on the fuse_conn_list */
 	struct list_head entry;
 
@@ -732,7 +731,6 @@ void fuse_read_fill(struct fuse_req *req, struct file *file,
 int fuse_open_common(struct inode *inode, struct file *file, bool isdir);
 
 struct fuse_file *fuse_file_alloc(struct fuse_conn *fc);
-struct fuse_file *fuse_file_get(struct fuse_file *ff);
 void fuse_file_free(struct fuse_file *ff);
 void fuse_finish_open(struct inode *inode, struct file *file);
 
diff --git a/fs/fuse/inode.c b/fs/fuse/inode.c
index 6fe6a88ecb4a..65c88379a3a1 100644
--- a/fs/fuse/inode.c
+++ b/fs/fuse/inode.c
@@ -21,6 +21,7 @@
 #include <linux/sched.h>
 #include <linux/exportfs.h>
 #include <linux/posix_acl.h>
+#include <linux/pid_namespace.h>
 
 MODULE_AUTHOR("Miklos Szeredi <miklos@szeredi.hu>");
 MODULE_DESCRIPTION("Filesystem in Userspace");
@@ -386,12 +387,6 @@ static void fuse_send_destroy(struct fuse_conn *fc)
 	}
 }
 
-static void fuse_bdi_destroy(struct fuse_conn *fc)
-{
-	if (fc->bdi_initialized)
-		bdi_destroy(&fc->bdi);
-}
-
 static void fuse_put_super(struct super_block *sb)
 {
 	struct fuse_conn *fc = get_fuse_conn_super(sb);
@@ -403,7 +398,6 @@ static void fuse_put_super(struct super_block *sb)
 	list_del(&fc->entry);
 	fuse_ctl_remove_conn(fc);
 	mutex_unlock(&fuse_mutex);
-	fuse_bdi_destroy(fc);
 
 	fuse_conn_put(fc);
 }
@@ -608,7 +602,7 @@ void fuse_conn_init(struct fuse_conn *fc)
 	memset(fc, 0, sizeof(*fc));
 	spin_lock_init(&fc->lock);
 	init_rwsem(&fc->killsb);
-	atomic_set(&fc->count, 1);
+	refcount_set(&fc->count, 1);
 	atomic_set(&fc->dev_count, 1);
 	init_waitqueue_head(&fc->blocked_waitq);
 	init_waitqueue_head(&fc->reserved_req_waitq);
@@ -626,14 +620,16 @@ void fuse_conn_init(struct fuse_conn *fc)
 	fc->connected = 1;
 	fc->attr_version = 1;
 	get_random_bytes(&fc->scramble_key, sizeof(fc->scramble_key));
+	fc->pid_ns = get_pid_ns(task_active_pid_ns(current));
 }
 EXPORT_SYMBOL_GPL(fuse_conn_init);
 
 void fuse_conn_put(struct fuse_conn *fc)
 {
-	if (atomic_dec_and_test(&fc->count)) {
+	if (refcount_dec_and_test(&fc->count)) {
 		if (fc->destroy_req)
 			fuse_request_free(fc->destroy_req);
+		put_pid_ns(fc->pid_ns);
 		fc->release(fc);
 	}
 }
@@ -641,7 +637,7 @@ EXPORT_SYMBOL_GPL(fuse_conn_put);
 
 struct fuse_conn *fuse_conn_get(struct fuse_conn *fc)
 {
-	atomic_inc(&fc->count);
+	refcount_inc(&fc->count);
 	return fc;
 }
 EXPORT_SYMBOL_GPL(fuse_conn_get);
@@ -928,7 +924,8 @@ static void process_init_reply(struct fuse_conn *fc, struct fuse_req *req)
 			fc->no_flock = 1;
 		}
 
-		fc->bdi.ra_pages = min(fc->bdi.ra_pages, ra_pages);
+		fc->sb->s_bdi->ra_pages =
+				min(fc->sb->s_bdi->ra_pages, ra_pages);
 		fc->minor = arg->minor;
 		fc->max_write = arg->minor < 5 ? 4096 : arg->max_write;
 		fc->max_write = max_t(unsigned, 4096, fc->max_write);
@@ -944,7 +941,7 @@ static void fuse_send_init(struct fuse_conn *fc, struct fuse_req *req)
 
 	arg->major = FUSE_KERNEL_VERSION;
 	arg->minor = FUSE_KERNEL_MINOR_VERSION;
-	arg->max_readahead = fc->bdi.ra_pages * PAGE_SIZE;
+	arg->max_readahead = fc->sb->s_bdi->ra_pages * PAGE_SIZE;
 	arg->flags |= FUSE_ASYNC_READ | FUSE_POSIX_LOCKS | FUSE_ATOMIC_O_TRUNC |
 		FUSE_EXPORT_SUPPORT | FUSE_BIG_WRITES | FUSE_DONT_MASK |
 		FUSE_SPLICE_WRITE | FUSE_SPLICE_MOVE | FUSE_SPLICE_READ |
@@ -976,28 +973,26 @@ static void fuse_free_conn(struct fuse_conn *fc)
 static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 {
 	int err;
-
-	fc->bdi.name = "fuse";
-	fc->bdi.ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
-	/* fuse does it's own writeback accounting */
-	fc->bdi.capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT;
-
-	err = bdi_init(&fc->bdi);
-	if (err)
-		return err;
-
-	fc->bdi_initialized = 1;
+	char *suffix = "";
 
 	if (sb->s_bdev) {
-		err =  bdi_register(&fc->bdi, NULL, "%u:%u-fuseblk",
-				    MAJOR(fc->dev), MINOR(fc->dev));
-	} else {
-		err = bdi_register_dev(&fc->bdi, fc->dev);
+		suffix = "-fuseblk";
+		/*
+		 * sb->s_bdi points to blkdev's bdi however we want to redirect
+		 * it to our private bdi...
+		 */
+		bdi_put(sb->s_bdi);
+		sb->s_bdi = &noop_backing_dev_info;
 	}
-
+	err = super_setup_bdi_name(sb, "%u:%u%s", MAJOR(fc->dev),
+				   MINOR(fc->dev), suffix);
 	if (err)
 		return err;
 
+	sb->s_bdi->ra_pages = (VM_MAX_READAHEAD * 1024) / PAGE_SIZE;
+	/* fuse does it's own writeback accounting */
+	sb->s_bdi->capabilities = BDI_CAP_NO_ACCT_WB | BDI_CAP_STRICTLIMIT;
+
 	/*
 	 * For a single fuse filesystem use max 1% of dirty +
 	 * writeback threshold.
@@ -1010,7 +1005,7 @@ static int fuse_bdi_init(struct fuse_conn *fc, struct super_block *sb)
 	 *
 	 *    /sys/class/bdi/<bdi>/max_ratio
 	 */
-	bdi_set_max_ratio(&fc->bdi, 1);
+	bdi_set_max_ratio(sb->s_bdi, 1);
 
 	return 0;
 }
@@ -1113,8 +1108,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
 	if (err)
 		goto err_dev_free;
 
-	sb->s_bdi = &fc->bdi;
-
 	/* Handle umasking inside the fuse code */
 	if (sb->s_flags & MS_POSIXACL)
 		fc->dont_mask = 1;
@@ -1182,7 +1175,6 @@ static int fuse_fill_super(struct super_block *sb, void *data, int silent)
  err_dev_free:
 	fuse_dev_free(fud);
  err_put_conn:
-	fuse_bdi_destroy(fc);
 	fuse_conn_put(fc);
  err_fput:
 	fput(file);
diff --git a/fs/gfs2/aops.c b/fs/gfs2/aops.c
index 6b039d7ce160..ed7a2e252ad8 100644
--- a/fs/gfs2/aops.c
+++ b/fs/gfs2/aops.c
@@ -143,8 +143,8 @@ static int gfs2_writepage(struct page *page, struct writeback_control *wbc)
 /* This is the same as calling block_write_full_page, but it also
  * writes pages outside of i_size
  */
-int gfs2_write_full_page(struct page *page, get_block_t *get_block,
-			 struct writeback_control *wbc)
+static int gfs2_write_full_page(struct page *page, get_block_t *get_block,
+				struct writeback_control *wbc)
 {
 	struct inode * const inode = page->mapping->host;
 	loff_t i_size = i_size_read(inode);
diff --git a/fs/gfs2/bmap.c b/fs/gfs2/bmap.c
index fc5da4cbe88c..9fa3aef9a5b3 100644
--- a/fs/gfs2/bmap.c
+++ b/fs/gfs2/bmap.c
@@ -38,11 +38,6 @@ struct metapath {
 	__u16 mp_list[GFS2_MAX_META_HEIGHT];
 };
 
-struct strip_mine {
-	int sm_first;
-	unsigned int sm_height;
-};
-
 /**
  * gfs2_unstuffer_page - unstuff a stuffed inode into a block cached by a page
  * @ip: the inode
@@ -253,6 +248,19 @@ static inline unsigned int metapath_branch_start(const struct metapath *mp)
 }
 
 /**
+ * metaptr1 - Return the first possible metadata pointer in a metaath buffer
+ * @height: The metadata height (0 = dinode)
+ * @mp: The metapath
+ */
+static inline __be64 *metaptr1(unsigned int height, const struct metapath *mp)
+{
+	struct buffer_head *bh = mp->mp_bh[height];
+	if (height == 0)
+		return ((__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)));
+	return ((__be64 *)(bh->b_data + sizeof(struct gfs2_meta_header)));
+}
+
+/**
  * metapointer - Return pointer to start of metadata in a buffer
  * @height: The metadata height (0 = dinode)
  * @mp: The metapath
@@ -264,10 +272,8 @@ static inline unsigned int metapath_branch_start(const struct metapath *mp)
 
 static inline __be64 *metapointer(unsigned int height, const struct metapath *mp)
 {
-	struct buffer_head *bh = mp->mp_bh[height];
-	unsigned int head_size = (height > 0) ?
-		sizeof(struct gfs2_meta_header) : sizeof(struct gfs2_dinode);
-	return ((__be64 *)(bh->b_data + head_size)) + mp->mp_list[height];
+	__be64 *p = metaptr1(height, mp);
+	return p + mp->mp_list[height];
 }
 
 static void gfs2_metapath_ra(struct gfs2_glock *gl,
@@ -296,6 +302,23 @@ static void gfs2_metapath_ra(struct gfs2_glock *gl,
 }
 
 /**
+ * lookup_mp_height - helper function for lookup_metapath
+ * @ip: the inode
+ * @mp: the metapath
+ * @h: the height which needs looking up
+ */
+static int lookup_mp_height(struct gfs2_inode *ip, struct metapath *mp, int h)
+{
+	__be64 *ptr = metapointer(h, mp);
+	u64 dblock = be64_to_cpu(*ptr);
+
+	if (!dblock)
+		return h + 1;
+
+	return gfs2_meta_indirect_buffer(ip, h + 1, dblock, &mp->mp_bh[h + 1]);
+}
+
+/**
  * lookup_metapath - Walk the metadata tree to a specific point
  * @ip: The inode
  * @mp: The metapath
@@ -316,17 +339,10 @@ static int lookup_metapath(struct gfs2_inode *ip, struct metapath *mp)
 {
 	unsigned int end_of_metadata = ip->i_height - 1;
 	unsigned int x;
-	__be64 *ptr;
-	u64 dblock;
 	int ret;
 
 	for (x = 0; x < end_of_metadata; x++) {
-		ptr = metapointer(x, mp);
-		dblock = be64_to_cpu(*ptr);
-		if (!dblock)
-			return x + 1;
-
-		ret = gfs2_meta_indirect_buffer(ip, x+1, dblock, &mp->mp_bh[x+1]);
+		ret = lookup_mp_height(ip, mp, x);
 		if (ret)
 			return ret;
 	}
@@ -334,6 +350,35 @@ static int lookup_metapath(struct gfs2_inode *ip, struct metapath *mp)
 	return ip->i_height;
 }
 
+/**
+ * fillup_metapath - fill up buffers for the metadata path to a specific height
+ * @ip: The inode
+ * @mp: The metapath
+ * @h: The height to which it should be mapped
+ *
+ * Similar to lookup_metapath, but does lookups for a range of heights
+ *
+ * Returns: error or height of metadata tree
+ */
+
+static int fillup_metapath(struct gfs2_inode *ip, struct metapath *mp, int h)
+{
+	unsigned int start_h = h - 1;
+	int ret;
+
+	if (h) {
+		/* find the first buffer we need to look up. */
+		while (start_h > 0 && mp->mp_bh[start_h] == NULL)
+			start_h--;
+		for (; start_h < h; start_h++) {
+			ret = lookup_mp_height(ip, mp, start_h);
+			if (ret)
+				return ret;
+		}
+	}
+	return ip->i_height;
+}
+
 static inline void release_metapath(struct metapath *mp)
 {
 	int i;
@@ -422,6 +467,13 @@ enum alloc_state {
 	/* ALLOC_UNSTUFF = 3,   TBD and rather complicated */
 };
 
+static inline unsigned int hptrs(struct gfs2_sbd *sdp, const unsigned int hgt)
+{
+	if (hgt)
+		return sdp->sd_inptrs;
+	return sdp->sd_diptrs;
+}
+
 /**
  * gfs2_bmap_alloc - Build a metadata tree of the requested height
  * @inode: The GFS2 inode
@@ -620,7 +672,7 @@ int gfs2_block_map(struct inode *inode, sector_t lblock,
 
 	BUG_ON(maxlen == 0);
 
-	memset(mp.mp_bh, 0, sizeof(mp.mp_bh));
+	memset(&mp, 0, sizeof(mp));
 	bmap_lock(ip, create);
 	clear_buffer_mapped(bh_map);
 	clear_buffer_new(bh_map);
@@ -702,229 +754,6 @@ int gfs2_extent_map(struct inode *inode, u64 lblock, int *new, u64 *dblock, unsi
 }
 
 /**
- * do_strip - Look for a layer a particular layer of the file and strip it off
- * @ip: the inode
- * @dibh: the dinode buffer
- * @bh: A buffer of pointers
- * @top: The first pointer in the buffer
- * @bottom: One more than the last pointer
- * @height: the height this buffer is at
- * @sm: a pointer to a struct strip_mine
- *
- * Returns: errno
- */
-
-static int do_strip(struct gfs2_inode *ip, struct buffer_head *dibh,
-		    struct buffer_head *bh, __be64 *top, __be64 *bottom,
-		    unsigned int height, struct strip_mine *sm)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct gfs2_rgrp_list rlist;
-	u64 bn, bstart;
-	u32 blen, btotal;
-	__be64 *p;
-	unsigned int rg_blocks = 0;
-	int metadata;
-	unsigned int revokes = 0;
-	int x;
-	int error;
-
-	error = gfs2_rindex_update(sdp);
-	if (error)
-		return error;
-
-	if (!*top)
-		sm->sm_first = 0;
-
-	if (height != sm->sm_height)
-		return 0;
-
-	if (sm->sm_first) {
-		top++;
-		sm->sm_first = 0;
-	}
-
-	metadata = (height != ip->i_height - 1);
-	if (metadata)
-		revokes = (height) ? sdp->sd_inptrs : sdp->sd_diptrs;
-	else if (ip->i_depth)
-		revokes = sdp->sd_inptrs;
-
-	memset(&rlist, 0, sizeof(struct gfs2_rgrp_list));
-	bstart = 0;
-	blen = 0;
-
-	for (p = top; p < bottom; p++) {
-		if (!*p)
-			continue;
-
-		bn = be64_to_cpu(*p);
-
-		if (bstart + blen == bn)
-			blen++;
-		else {
-			if (bstart)
-				gfs2_rlist_add(ip, &rlist, bstart);
-
-			bstart = bn;
-			blen = 1;
-		}
-	}
-
-	if (bstart)
-		gfs2_rlist_add(ip, &rlist, bstart);
-	else
-		goto out; /* Nothing to do */
-
-	gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE);
-
-	for (x = 0; x < rlist.rl_rgrps; x++) {
-		struct gfs2_rgrpd *rgd;
-		rgd = rlist.rl_ghs[x].gh_gl->gl_object;
-		rg_blocks += rgd->rd_length;
-	}
-
-	error = gfs2_glock_nq_m(rlist.rl_rgrps, rlist.rl_ghs);
-	if (error)
-		goto out_rlist;
-
-	if (gfs2_rs_active(&ip->i_res)) /* needs to be done with the rgrp glock held */
-		gfs2_rs_deltree(&ip->i_res);
-
-	error = gfs2_trans_begin(sdp, rg_blocks + RES_DINODE +
-				 RES_INDIRECT + RES_STATFS + RES_QUOTA,
-				 revokes);
-	if (error)
-		goto out_rg_gunlock;
-
-	down_write(&ip->i_rw_mutex);
-
-	gfs2_trans_add_meta(ip->i_gl, dibh);
-	gfs2_trans_add_meta(ip->i_gl, bh);
-
-	bstart = 0;
-	blen = 0;
-	btotal = 0;
-
-	for (p = top; p < bottom; p++) {
-		if (!*p)
-			continue;
-
-		bn = be64_to_cpu(*p);
-
-		if (bstart + blen == bn)
-			blen++;
-		else {
-			if (bstart) {
-				__gfs2_free_blocks(ip, bstart, blen, metadata);
-				btotal += blen;
-			}
-
-			bstart = bn;
-			blen = 1;
-		}
-
-		*p = 0;
-		gfs2_add_inode_blocks(&ip->i_inode, -1);
-	}
-	if (bstart) {
-		__gfs2_free_blocks(ip, bstart, blen, metadata);
-		btotal += blen;
-	}
-
-	gfs2_statfs_change(sdp, 0, +btotal, 0);
-	gfs2_quota_change(ip, -(s64)btotal, ip->i_inode.i_uid,
-			  ip->i_inode.i_gid);
-
-	ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode);
-
-	gfs2_dinode_out(ip, dibh->b_data);
-
-	up_write(&ip->i_rw_mutex);
-
-	gfs2_trans_end(sdp);
-
-out_rg_gunlock:
-	gfs2_glock_dq_m(rlist.rl_rgrps, rlist.rl_ghs);
-out_rlist:
-	gfs2_rlist_free(&rlist);
-out:
-	return error;
-}
-
-/**
- * recursive_scan - recursively scan through the end of a file
- * @ip: the inode
- * @dibh: the dinode buffer
- * @mp: the path through the metadata to the point to start
- * @height: the height the recursion is at
- * @block: the indirect block to look at
- * @first: 1 if this is the first block
- * @sm: data opaque to this function to pass to @bc
- *
- * When this is first called @height and @block should be zero and
- * @first should be 1.
- *
- * Returns: errno
- */
-
-static int recursive_scan(struct gfs2_inode *ip, struct buffer_head *dibh,
-			  struct metapath *mp, unsigned int height,
-			  u64 block, int first, struct strip_mine *sm)
-{
-	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	struct buffer_head *bh = NULL;
-	__be64 *top, *bottom;
-	u64 bn;
-	int error;
-	int mh_size = sizeof(struct gfs2_meta_header);
-
-	if (!height) {
-		error = gfs2_meta_inode_buffer(ip, &bh);
-		if (error)
-			return error;
-		dibh = bh;
-
-		top = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + mp->mp_list[0];
-		bottom = (__be64 *)(bh->b_data + sizeof(struct gfs2_dinode)) + sdp->sd_diptrs;
-	} else {
-		error = gfs2_meta_indirect_buffer(ip, height, block, &bh);
-		if (error)
-			return error;
-
-		top = (__be64 *)(bh->b_data + mh_size) +
-				  (first ? mp->mp_list[height] : 0);
-
-		bottom = (__be64 *)(bh->b_data + mh_size) + sdp->sd_inptrs;
-	}
-
-	error = do_strip(ip, dibh, bh, top, bottom, height, sm);
-	if (error)
-		goto out;
-
-	if (height < ip->i_height - 1) {
-
-		gfs2_metapath_ra(ip->i_gl, bh, top);
-
-		for (; top < bottom; top++, first = 0) {
-			if (!*top)
-				continue;
-
-			bn = be64_to_cpu(*top);
-
-			error = recursive_scan(ip, dibh, mp, height + 1, bn,
-					       first, sm);
-			if (error)
-				break;
-		}
-	}
-out:
-	brelse(bh);
-	return error;
-}
-
-
-/**
  * gfs2_block_truncate_page - Deal with zeroing out data for truncate
  *
  * This is partly borrowed from ext3.
@@ -1083,41 +912,406 @@ out:
 	return error;
 }
 
-static int trunc_dealloc(struct gfs2_inode *ip, u64 size)
+/**
+ * sweep_bh_for_rgrps - find an rgrp in a meta buffer and free blocks therein
+ * @ip: inode
+ * @rg_gh: holder of resource group glock
+ * @mp: current metapath fully populated with buffers
+ * @btotal: place to keep count of total blocks freed
+ * @hgt: height we're processing
+ * @first: true if this is the first call to this function for this height
+ *
+ * We sweep a metadata buffer (provided by the metapath) for blocks we need to
+ * free, and free them all. However, we do it one rgrp at a time. If this
+ * block has references to multiple rgrps, we break it into individual
+ * transactions. This allows other processes to use the rgrps while we're
+ * focused on a single one, for better concurrency / performance.
+ * At every transaction boundary, we rewrite the inode into the journal.
+ * That way the bitmaps are kept consistent with the inode and we can recover
+ * if we're interrupted by power-outages.
+ *
+ * Returns: 0, or return code if an error occurred.
+ *          *btotal has the total number of blocks freed
+ */
+static int sweep_bh_for_rgrps(struct gfs2_inode *ip, struct gfs2_holder *rd_gh,
+			      const struct metapath *mp, u32 *btotal, int hgt,
+			      bool preserve1)
 {
 	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
-	unsigned int height = ip->i_height;
-	u64 lblock;
-	struct metapath mp;
-	int error;
+	struct gfs2_rgrpd *rgd;
+	struct gfs2_trans *tr;
+	struct buffer_head *bh = mp->mp_bh[hgt];
+	__be64 *top, *bottom, *p;
+	int blks_outside_rgrp;
+	u64 bn, bstart, isize_blks;
+	s64 blen; /* needs to be s64 or gfs2_add_inode_blocks breaks */
+	int meta = ((hgt != ip->i_height - 1) ? 1 : 0);
+	int ret = 0;
+	bool buf_in_tr = false; /* buffer was added to transaction */
+
+	if (gfs2_metatype_check(sdp, bh,
+				(hgt ? GFS2_METATYPE_IN : GFS2_METATYPE_DI)))
+		return -EIO;
+
+more_rgrps:
+	blks_outside_rgrp = 0;
+	bstart = 0;
+	blen = 0;
+	top = metapointer(hgt, mp); /* first ptr from metapath */
+	/* If we're keeping some data at the truncation point, we've got to
+	   preserve the metadata tree by adding 1 to the starting metapath. */
+	if (preserve1)
+		top++;
+
+	bottom = (__be64 *)(bh->b_data + bh->b_size);
+
+	for (p = top; p < bottom; p++) {
+		if (!*p)
+			continue;
+		bn = be64_to_cpu(*p);
+		if (gfs2_holder_initialized(rd_gh)) {
+			rgd = gfs2_glock2rgrp(rd_gh->gh_gl);
+			gfs2_assert_withdraw(sdp,
+				     gfs2_glock_is_locked_by_me(rd_gh->gh_gl));
+		} else {
+			rgd = gfs2_blk2rgrpd(sdp, bn, false);
+			ret = gfs2_glock_nq_init(rgd->rd_gl, LM_ST_EXCLUSIVE,
+						 0, rd_gh);
+			if (ret)
+				goto out;
+
+			/* Must be done with the rgrp glock held: */
+			if (gfs2_rs_active(&ip->i_res) &&
+			    rgd == ip->i_res.rs_rbm.rgd)
+				gfs2_rs_deltree(&ip->i_res);
+		}
+
+		if (!rgrp_contains_block(rgd, bn)) {
+			blks_outside_rgrp++;
+			continue;
+		}
+
+		/* The size of our transactions will be unknown until we
+		   actually process all the metadata blocks that relate to
+		   the rgrp. So we estimate. We know it can't be more than
+		   the dinode's i_blocks and we don't want to exceed the
+		   journal flush threshold, sd_log_thresh2. */
+		if (current->journal_info == NULL) {
+			unsigned int jblocks_rqsted, revokes;
+
+			jblocks_rqsted = rgd->rd_length + RES_DINODE +
+				RES_INDIRECT;
+			isize_blks = gfs2_get_inode_blocks(&ip->i_inode);
+			if (isize_blks > atomic_read(&sdp->sd_log_thresh2))
+				jblocks_rqsted +=
+					atomic_read(&sdp->sd_log_thresh2);
+			else
+				jblocks_rqsted += isize_blks;
+			revokes = jblocks_rqsted;
+			if (meta)
+				revokes += hptrs(sdp, hgt);
+			else if (ip->i_depth)
+				revokes += sdp->sd_inptrs;
+			ret = gfs2_trans_begin(sdp, jblocks_rqsted, revokes);
+			if (ret)
+				goto out_unlock;
+			down_write(&ip->i_rw_mutex);
+		}
+		/* check if we will exceed the transaction blocks requested */
+		tr = current->journal_info;
+		if (tr->tr_num_buf_new + RES_STATFS +
+		    RES_QUOTA >= atomic_read(&sdp->sd_log_thresh2)) {
+			/* We set blks_outside_rgrp to ensure the loop will
+			   be repeated for the same rgrp, but with a new
+			   transaction. */
+			blks_outside_rgrp++;
+			/* This next part is tricky. If the buffer was added
+			   to the transaction, we've already set some block
+			   pointers to 0, so we better follow through and free
+			   them, or we will introduce corruption (so break).
+			   This may be impossible, or at least rare, but I
+			   decided to cover the case regardless.
+
+			   If the buffer was not added to the transaction
+			   (this call), doing so would exceed our transaction
+			   size, so we need to end the transaction and start a
+			   new one (so goto). */
+
+			if (buf_in_tr)
+				break;
+			goto out_unlock;
+		}
+
+		gfs2_trans_add_meta(ip->i_gl, bh);
+		buf_in_tr = true;
+		*p = 0;
+		if (bstart + blen == bn) {
+			blen++;
+			continue;
+		}
+		if (bstart) {
+			__gfs2_free_blocks(ip, bstart, (u32)blen, meta);
+			(*btotal) += blen;
+			gfs2_add_inode_blocks(&ip->i_inode, -blen);
+		}
+		bstart = bn;
+		blen = 1;
+	}
+	if (bstart) {
+		__gfs2_free_blocks(ip, bstart, (u32)blen, meta);
+		(*btotal) += blen;
+		gfs2_add_inode_blocks(&ip->i_inode, -blen);
+	}
+out_unlock:
+	if (!ret && blks_outside_rgrp) { /* If buffer still has non-zero blocks
+					    outside the rgrp we just processed,
+					    do it all over again. */
+		if (current->journal_info) {
+			struct buffer_head *dibh = mp->mp_bh[0];
+
+			/* Every transaction boundary, we rewrite the dinode
+			   to keep its di_blocks current in case of failure. */
+			ip->i_inode.i_mtime = ip->i_inode.i_ctime =
+				current_time(&ip->i_inode);
+			gfs2_trans_add_meta(ip->i_gl, dibh);
+			gfs2_dinode_out(ip, dibh->b_data);
+			up_write(&ip->i_rw_mutex);
+			gfs2_trans_end(sdp);
+		}
+		gfs2_glock_dq_uninit(rd_gh);
+		cond_resched();
+		goto more_rgrps;
+	}
+out:
+	return ret;
+}
+
+/**
+ * find_nonnull_ptr - find a non-null pointer given a metapath and height
+ * assumes the metapath is valid (with buffers) out to height h
+ * @mp: starting metapath
+ * @h: desired height to search
+ *
+ * Returns: true if a non-null pointer was found in the metapath buffer
+ *          false if all remaining pointers are NULL in the buffer
+ */
+static bool find_nonnull_ptr(struct gfs2_sbd *sdp, struct metapath *mp,
+			     unsigned int h)
+{
+	__be64 *ptr;
+	unsigned int ptrs = hptrs(sdp, h) - 1;
 
-	if (!size)
+	while (true) {
+		ptr = metapointer(h, mp);
+		if (*ptr) /* if we have a non-null pointer */
+			return true;
+
+		if (mp->mp_list[h] < ptrs)
+			mp->mp_list[h]++;
+		else
+			return false; /* no more pointers in this buffer */
+	}
+}
+
+enum dealloc_states {
+	DEALLOC_MP_FULL = 0,    /* Strip a metapath with all buffers read in */
+	DEALLOC_MP_LOWER = 1,   /* lower the metapath strip height */
+	DEALLOC_FILL_MP = 2,  /* Fill in the metapath to the given height. */
+	DEALLOC_DONE = 3,       /* process complete */
+};
+
+/**
+ * trunc_dealloc - truncate a file down to a desired size
+ * @ip: inode to truncate
+ * @newsize: The desired size of the file
+ *
+ * This function truncates a file to newsize. It works from the
+ * bottom up, and from the right to the left. In other words, it strips off
+ * the highest layer (data) before stripping any of the metadata. Doing it
+ * this way is best in case the operation is interrupted by power failure, etc.
+ * The dinode is rewritten in every transaction to guarantee integrity.
+ */
+static int trunc_dealloc(struct gfs2_inode *ip, u64 newsize)
+{
+	struct gfs2_sbd *sdp = GFS2_SB(&ip->i_inode);
+	struct metapath mp;
+	struct buffer_head *dibh, *bh;
+	struct gfs2_holder rd_gh;
+	u64 lblock;
+	__u16 nbof[GFS2_MAX_META_HEIGHT]; /* new beginning of truncation */
+	unsigned int strip_h = ip->i_height - 1;
+	u32 btotal = 0;
+	int ret, state;
+	int mp_h; /* metapath buffers are read in to this height */
+	sector_t last_ra = 0;
+	u64 prev_bnr = 0;
+	bool preserve1; /* need to preserve the first meta pointer? */
+
+	if (!newsize)
 		lblock = 0;
 	else
-		lblock = (size - 1) >> sdp->sd_sb.sb_bsize_shift;
+		lblock = (newsize - 1) >> sdp->sd_sb.sb_bsize_shift;
 
+	memset(&mp, 0, sizeof(mp));
 	find_metapath(sdp, lblock, &mp, ip->i_height);
-	error = gfs2_rindex_update(sdp);
-	if (error)
-		return error;
 
-	error = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
-	if (error)
-		return error;
+	memcpy(&nbof, &mp.mp_list, sizeof(nbof));
 
-	while (height--) {
-		struct strip_mine sm;
-		sm.sm_first = !!size;
-		sm.sm_height = height;
+	ret = gfs2_meta_inode_buffer(ip, &dibh);
+	if (ret)
+		return ret;
 
-		error = recursive_scan(ip, NULL, &mp, 0, 0, 1, &sm);
-		if (error)
+	mp.mp_bh[0] = dibh;
+	ret = lookup_metapath(ip, &mp);
+	if (ret == ip->i_height)
+		state = DEALLOC_MP_FULL; /* We have a complete metapath */
+	else
+		state = DEALLOC_FILL_MP; /* deal with partial metapath */
+
+	ret = gfs2_rindex_update(sdp);
+	if (ret)
+		goto out_metapath;
+
+	ret = gfs2_quota_hold(ip, NO_UID_QUOTA_CHANGE, NO_GID_QUOTA_CHANGE);
+	if (ret)
+		goto out_metapath;
+	gfs2_holder_mark_uninitialized(&rd_gh);
+
+	mp_h = strip_h;
+
+	while (state != DEALLOC_DONE) {
+		switch (state) {
+		/* Truncate a full metapath at the given strip height.
+		 * Note that strip_h == mp_h in order to be in this state. */
+		case DEALLOC_MP_FULL:
+			if (mp_h > 0) { /* issue read-ahead on metadata */
+				__be64 *top;
+
+				bh = mp.mp_bh[mp_h - 1];
+				if (bh->b_blocknr != last_ra) {
+					last_ra = bh->b_blocknr;
+					top = metaptr1(mp_h - 1, &mp);
+					gfs2_metapath_ra(ip->i_gl, bh, top);
+				}
+			}
+			/* If we're truncating to a non-zero size and the mp is
+			   at the beginning of file for the strip height, we
+			   need to preserve the first metadata pointer. */
+			preserve1 = (newsize &&
+				     (mp.mp_list[mp_h] == nbof[mp_h]));
+			bh = mp.mp_bh[mp_h];
+			gfs2_assert_withdraw(sdp, bh);
+			if (gfs2_assert_withdraw(sdp,
+						 prev_bnr != bh->b_blocknr)) {
+				printk(KERN_EMERG "GFS2: fsid=%s:inode %llu, "
+				       "block:%llu, i_h:%u, s_h:%u, mp_h:%u\n",
+				       sdp->sd_fsname,
+				       (unsigned long long)ip->i_no_addr,
+				       prev_bnr, ip->i_height, strip_h, mp_h);
+			}
+			prev_bnr = bh->b_blocknr;
+			ret = sweep_bh_for_rgrps(ip, &rd_gh, &mp, &btotal,
+						 mp_h, preserve1);
+			/* If we hit an error or just swept dinode buffer,
+			   just exit. */
+			if (ret || !mp_h) {
+				state = DEALLOC_DONE;
+				break;
+			}
+			state = DEALLOC_MP_LOWER;
+			break;
+
+		/* lower the metapath strip height */
+		case DEALLOC_MP_LOWER:
+			/* We're done with the current buffer, so release it,
+			   unless it's the dinode buffer. Then back up to the
+			   previous pointer. */
+			if (mp_h) {
+				brelse(mp.mp_bh[mp_h]);
+				mp.mp_bh[mp_h] = NULL;
+			}
+			/* If we can't get any lower in height, we've stripped
+			   off all we can. Next step is to back up and start
+			   stripping the previous level of metadata. */
+			if (mp_h == 0) {
+				strip_h--;
+				memcpy(&mp.mp_list, &nbof, sizeof(nbof));
+				mp_h = strip_h;
+				state = DEALLOC_FILL_MP;
+				break;
+			}
+			mp.mp_list[mp_h] = 0;
+			mp_h--; /* search one metadata height down */
+			if (mp.mp_list[mp_h] >= hptrs(sdp, mp_h) - 1)
+				break; /* loop around in the same state */
+			mp.mp_list[mp_h]++;
+			/* Here we've found a part of the metapath that is not
+			 * allocated. We need to search at that height for the
+			 * next non-null pointer. */
+			if (find_nonnull_ptr(sdp, &mp, mp_h)) {
+				state = DEALLOC_FILL_MP;
+				mp_h++;
+			}
+			/* No more non-null pointers at this height. Back up
+			   to the previous height and try again. */
+			break; /* loop around in the same state */
+
+		/* Fill the metapath with buffers to the given height. */
+		case DEALLOC_FILL_MP:
+			/* Fill the buffers out to the current height. */
+			ret = fillup_metapath(ip, &mp, mp_h);
+			if (ret < 0)
+				goto out;
+
+			/* If buffers found for the entire strip height */
+			if ((ret == ip->i_height) && (mp_h == strip_h)) {
+				state = DEALLOC_MP_FULL;
+				break;
+			}
+			if (ret < ip->i_height) /* We have a partial height */
+				mp_h = ret - 1;
+
+			/* If we find a non-null block pointer, crawl a bit
+			   higher up in the metapath and try again, otherwise
+			   we need to look lower for a new starting point. */
+			if (find_nonnull_ptr(sdp, &mp, mp_h))
+				mp_h++;
+			else
+				state = DEALLOC_MP_LOWER;
 			break;
+		}
 	}
 
-	gfs2_quota_unhold(ip);
+	if (btotal) {
+		if (current->journal_info == NULL) {
+			ret = gfs2_trans_begin(sdp, RES_DINODE + RES_STATFS +
+					       RES_QUOTA, 0);
+			if (ret)
+				goto out;
+			down_write(&ip->i_rw_mutex);
+		}
+		gfs2_statfs_change(sdp, 0, +btotal, 0);
+		gfs2_quota_change(ip, -(s64)btotal, ip->i_inode.i_uid,
+				  ip->i_inode.i_gid);
+		ip->i_inode.i_mtime = ip->i_inode.i_ctime = current_time(&ip->i_inode);
+		gfs2_trans_add_meta(ip->i_gl, dibh);
+		gfs2_dinode_out(ip, dibh->b_data);
+		up_write(&ip->i_rw_mutex);
+		gfs2_trans_end(sdp);
+	}
 
-	return error;
+out:
+	if (gfs2_holder_initialized(&rd_gh))
+		gfs2_glock_dq_uninit(&rd_gh);
+	if (current->journal_info) {
+		up_write(&ip->i_rw_mutex);
+		gfs2_trans_end(sdp);
+		cond_resched();
+	}
+	gfs2_quota_unhold(ip);
+out_metapath:
+	release_metapath(&mp);
+	return ret;
 }
 
 static int trunc_end(struct gfs2_inode *ip)
diff --git a/fs/gfs2/dir.c b/fs/gfs2/dir.c
index 79113219be5f..5ee2e2f8576c 100644
--- a/fs/gfs2/dir.c
+++ b/fs/gfs2/dir.c
@@ -872,7 +872,6 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh,
 	struct buffer_head *bh;
 	struct gfs2_leaf *leaf;
 	struct gfs2_dirent *dent;
-	struct qstr name = { .name = "" };
 	struct timespec tv = current_time(inode);
 
 	error = gfs2_alloc_blocks(ip, &bn, &n, 0, NULL);
@@ -896,7 +895,7 @@ static struct gfs2_leaf *new_leaf(struct inode *inode, struct buffer_head **pbh,
 	leaf->lf_sec = cpu_to_be64(tv.tv_sec);
 	memset(leaf->lf_reserved2, 0, sizeof(leaf->lf_reserved2));
 	dent = (struct gfs2_dirent *)(leaf+1);
-	gfs2_qstr2dirent(&name, bh->b_size - sizeof(struct gfs2_leaf), dent);
+	gfs2_qstr2dirent(&empty_name, bh->b_size - sizeof(struct gfs2_leaf), dent);
 	*pbh = bh;
 	return leaf;
 }
@@ -1444,7 +1443,7 @@ static int gfs2_dir_read_leaf(struct inode *inode, struct dir_context *ctx,
 						"g.offset (%u)\n",
 					(unsigned long long)bh->b_blocknr,
 					entries2, g.offset);
-					
+				gfs2_consist_inode(ip);
 				error = -EIO;
 				goto out_free;
 			}
@@ -1612,6 +1611,7 @@ int gfs2_dir_read(struct inode *inode, struct dir_context *ctx,
 				(unsigned long long)dip->i_no_addr,
 				dip->i_entries,
 				g.offset);
+			gfs2_consist_inode(dip);
 			error = -EIO;
 			goto out;
 		}
@@ -2031,8 +2031,8 @@ static int leaf_dealloc(struct gfs2_inode *dip, u32 index, u32 len,
 	gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE);
 
 	for (x = 0; x < rlist.rl_rgrps; x++) {
-		struct gfs2_rgrpd *rgd;
-		rgd = rlist.rl_ghs[x].gh_gl->gl_object;
+		struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(rlist.rl_ghs[x].gh_gl);
+
 		rg_blocks += rgd->rd_length;
 	}
 
diff --git a/fs/gfs2/file.c b/fs/gfs2/file.c
index 016c11eaca7c..c2062a108d19 100644
--- a/fs/gfs2/file.c
+++ b/fs/gfs2/file.c
@@ -379,10 +379,10 @@ static int gfs2_allocate_page_backing(struct page *page)
  * blocks allocated on disk to back that page.
  */
 
-static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int gfs2_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_alloc_parms ap = { .aflags = 0, };
@@ -399,7 +399,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	if (ret)
 		goto out;
 
-	gfs2_size_hint(vma->vm_file, pos, PAGE_SIZE);
+	gfs2_size_hint(vmf->vma->vm_file, pos, PAGE_SIZE);
 
 	gfs2_holder_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
 	ret = gfs2_glock_nq(&gh);
@@ -407,7 +407,7 @@ static int gfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 		goto out_uninit;
 
 	/* Update file times before taking page lock */
-	file_update_time(vma->vm_file);
+	file_update_time(vmf->vma->vm_file);
 
 	set_bit(GLF_DIRTY, &ip->i_gl->gl_flags);
 	set_bit(GIF_SW_PAGED, &ip->i_flags);
@@ -911,11 +911,15 @@ out_qunlock:
 static long gfs2_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 {
 	struct inode *inode = file_inode(file);
+	struct gfs2_sbd *sdp = GFS2_SB(inode);
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
 	int ret;
 
-	if ((mode & ~FALLOC_FL_KEEP_SIZE) || gfs2_is_jdata(ip))
+	if (mode & ~FALLOC_FL_KEEP_SIZE)
+		return -EOPNOTSUPP;
+	/* fallocate is needed by gfs2_grow to reserve space in the rindex */
+	if (gfs2_is_jdata(ip) && inode != sdp->sd_rindex)
 		return -EOPNOTSUPP;
 
 	inode_lock(inode);
diff --git a/fs/gfs2/glock.c b/fs/gfs2/glock.c
index 94f50cac91c6..c38ab6c81898 100644
--- a/fs/gfs2/glock.c
+++ b/fs/gfs2/glock.c
@@ -73,16 +73,16 @@ static DEFINE_SPINLOCK(lru_lock);
 
 static struct rhashtable_params ht_parms = {
 	.nelem_hint = GFS2_GL_HASH_SIZE * 3 / 4,
-	.key_len = sizeof(struct lm_lockname),
+	.key_len = offsetofend(struct lm_lockname, ln_type),
 	.key_offset = offsetof(struct gfs2_glock, gl_name),
 	.head_offset = offsetof(struct gfs2_glock, gl_node),
 };
 
 static struct rhashtable gl_hash_table;
 
-void gfs2_glock_free(struct gfs2_glock *gl)
+static void gfs2_glock_dealloc(struct rcu_head *rcu)
 {
-	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+	struct gfs2_glock *gl = container_of(rcu, struct gfs2_glock, gl_rcu);
 
 	if (gl->gl_ops->go_flags & GLOF_ASPACE) {
 		kmem_cache_free(gfs2_glock_aspace_cachep, gl);
@@ -90,6 +90,13 @@ void gfs2_glock_free(struct gfs2_glock *gl)
 		kfree(gl->gl_lksb.sb_lvbptr);
 		kmem_cache_free(gfs2_glock_cachep, gl);
 	}
+}
+
+void gfs2_glock_free(struct gfs2_glock *gl)
+{
+	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
+
+	call_rcu(&gl->gl_rcu, gfs2_glock_dealloc);
 	if (atomic_dec_and_test(&sdp->sd_glock_disposal))
 		wake_up(&sdp->sd_glock_wait);
 }
@@ -152,20 +159,34 @@ static void gfs2_glock_remove_from_lru(struct gfs2_glock *gl)
 	spin_unlock(&lru_lock);
 }
 
-/**
- * gfs2_glock_put() - Decrement reference count on glock
- * @gl: The glock to put
- *
+/*
+ * Enqueue the glock on the work queue.  Passes one glock reference on to the
+ * work queue.
  */
+static void __gfs2_glock_queue_work(struct gfs2_glock *gl, unsigned long delay) {
+	if (!queue_delayed_work(glock_workqueue, &gl->gl_work, delay)) {
+		/*
+		 * We are holding the lockref spinlock, and the work was still
+		 * queued above.  The queued work (glock_work_func) takes that
+		 * spinlock before dropping its glock reference(s), so it
+		 * cannot have dropped them in the meantime.
+		 */
+		GLOCK_BUG_ON(gl, gl->gl_lockref.count < 2);
+		gl->gl_lockref.count--;
+	}
+}
 
-void gfs2_glock_put(struct gfs2_glock *gl)
+static void gfs2_glock_queue_work(struct gfs2_glock *gl, unsigned long delay) {
+	spin_lock(&gl->gl_lockref.lock);
+	__gfs2_glock_queue_work(gl, delay);
+	spin_unlock(&gl->gl_lockref.lock);
+}
+
+static void __gfs2_glock_put(struct gfs2_glock *gl)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct address_space *mapping = gfs2_glock2aspace(gl);
 
-	if (lockref_put_or_lock(&gl->gl_lockref))
-		return;
-
 	lockref_mark_dead(&gl->gl_lockref);
 
 	gfs2_glock_remove_from_lru(gl);
@@ -178,6 +199,20 @@ void gfs2_glock_put(struct gfs2_glock *gl)
 }
 
 /**
+ * gfs2_glock_put() - Decrement reference count on glock
+ * @gl: The glock to put
+ *
+ */
+
+void gfs2_glock_put(struct gfs2_glock *gl)
+{
+	if (lockref_put_or_lock(&gl->gl_lockref))
+		return;
+
+	__gfs2_glock_put(gl);
+}
+
+/**
  * may_grant - check if its ok to grant a new lock
  * @gl: The glock
  * @gh: The lock request which we wish to grant
@@ -449,6 +484,9 @@ __acquires(&gl->gl_lockref.lock)
 	unsigned int lck_flags = (unsigned int)(gh ? gh->gh_flags : 0);
 	int ret;
 
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)) &&
+	    target != LM_ST_UNLOCKED)
+		return;
 	lck_flags &= (LM_FLAG_TRY | LM_FLAG_TRY_1CB | LM_FLAG_NOEXP |
 		      LM_FLAG_PRIORITY);
 	GLOCK_BUG_ON(gl, gl->gl_state == target);
@@ -479,17 +517,16 @@ __acquires(&gl->gl_lockref.lock)
 		    target == LM_ST_UNLOCKED &&
 		    test_bit(SDF_SKIP_DLM_UNLOCK, &sdp->sd_flags)) {
 			finish_xmote(gl, target);
-			if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
-				gfs2_glock_put(gl);
+			gfs2_glock_queue_work(gl, 0);
 		}
 		else if (ret) {
 			pr_err("lm_lock ret %d\n", ret);
-			GLOCK_BUG_ON(gl, 1);
+			GLOCK_BUG_ON(gl, !test_bit(SDF_SHUTDOWN,
+						   &sdp->sd_flags));
 		}
 	} else { /* lock_nolock */
 		finish_xmote(gl, target);
-		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
-			gfs2_glock_put(gl);
+		gfs2_glock_queue_work(gl, 0);
 	}
 
 	spin_lock(&gl->gl_lockref.lock);
@@ -561,8 +598,7 @@ out_sched:
 	clear_bit(GLF_LOCK, &gl->gl_flags);
 	smp_mb__after_atomic();
 	gl->gl_lockref.count++;
-	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
-		gl->gl_lockref.count--;
+	__gfs2_glock_queue_work(gl, 0);
 	return;
 
 out_unlock:
@@ -597,11 +633,11 @@ static void glock_work_func(struct work_struct *work)
 {
 	unsigned long delay = 0;
 	struct gfs2_glock *gl = container_of(work, struct gfs2_glock, gl_work.work);
-	int drop_ref = 0;
+	unsigned int drop_refs = 1;
 
 	if (test_and_clear_bit(GLF_REPLY_PENDING, &gl->gl_flags)) {
 		finish_xmote(gl, gl->gl_reply);
-		drop_ref = 1;
+		drop_refs++;
 	}
 	spin_lock(&gl->gl_lockref.lock);
 	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
@@ -619,17 +655,25 @@ static void glock_work_func(struct work_struct *work)
 		}
 	}
 	run_queue(gl, 0);
-	spin_unlock(&gl->gl_lockref.lock);
-	if (!delay)
-		gfs2_glock_put(gl);
-	else {
+	if (delay) {
+		/* Keep one glock reference for the work we requeue. */
+		drop_refs--;
 		if (gl->gl_name.ln_type != LM_TYPE_INODE)
 			delay = 0;
-		if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
-			gfs2_glock_put(gl);
+		__gfs2_glock_queue_work(gl, delay);
 	}
-	if (drop_ref)
-		gfs2_glock_put(gl);
+
+	/*
+	 * Drop the remaining glock references manually here. (Mind that
+	 * __gfs2_glock_queue_work depends on the lockref spinlock begin held
+	 * here as well.)
+	 */
+	gl->gl_lockref.count -= drop_refs;
+	if (!gl->gl_lockref.count) {
+		__gfs2_glock_put(gl);
+		return;
+	}
+	spin_unlock(&gl->gl_lockref.lock);
 }
 
 /**
@@ -653,14 +697,16 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	struct lm_lockname name = { .ln_number = number,
 				    .ln_type = glops->go_type,
 				    .ln_sbd = sdp };
-	struct gfs2_glock *gl, *tmp = NULL;
+	struct gfs2_glock *gl, *tmp;
 	struct address_space *mapping;
 	struct kmem_cache *cachep;
-	int ret, tries = 0;
+	int ret = 0;
 
+	rcu_read_lock();
 	gl = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms);
 	if (gl && !lockref_get_not_dead(&gl->gl_lockref))
 		gl = NULL;
+	rcu_read_unlock();
 
 	*glp = gl;
 	if (gl)
@@ -719,32 +765,32 @@ int gfs2_glock_get(struct gfs2_sbd *sdp, u64 number,
 	}
 
 again:
-	ret = rhashtable_lookup_insert_fast(&gl_hash_table, &gl->gl_node,
-					    ht_parms);
-	if (ret == 0) {
+	rcu_read_lock();
+	tmp = rhashtable_lookup_get_insert_fast(&gl_hash_table, &gl->gl_node,
+						ht_parms);
+	if (!tmp) {
 		*glp = gl;
-		return 0;
+		goto out;
 	}
-
-	if (ret == -EEXIST) {
-		ret = 0;
-		tmp = rhashtable_lookup_fast(&gl_hash_table, &name, ht_parms);
-		if (tmp == NULL || !lockref_get_not_dead(&tmp->gl_lockref)) {
-			if (++tries < 100) {
-				cond_resched();
-				goto again;
-			}
-			tmp = NULL;
-			ret = -ENOMEM;
-		}
-	} else {
-		WARN_ON_ONCE(ret);
+	if (IS_ERR(tmp)) {
+		ret = PTR_ERR(tmp);
+		goto out_free;
 	}
+	if (lockref_get_not_dead(&tmp->gl_lockref)) {
+		*glp = tmp;
+		goto out_free;
+	}
+	rcu_read_unlock();
+	cond_resched();
+	goto again;
+
+out_free:
 	kfree(gl->gl_lksb.sb_lvbptr);
 	kmem_cache_free(cachep, gl);
 	atomic_dec(&sdp->sd_glock_disposal);
-	*glp = tmp;
 
+out:
+	rcu_read_unlock();
 	return ret;
 }
 
@@ -980,8 +1026,7 @@ int gfs2_glock_nq(struct gfs2_holder *gh)
 		     test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))) {
 		set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
 		gl->gl_lockref.count++;
-		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
-			gl->gl_lockref.count--;
+		__gfs2_glock_queue_work(gl, 0);
 	}
 	run_queue(gl, 1);
 	spin_unlock(&gl->gl_lockref.lock);
@@ -1041,17 +1086,15 @@ void gfs2_glock_dq(struct gfs2_holder *gh)
 		gfs2_glock_add_to_lru(gl);
 
 	trace_gfs2_glock_queue(gh, 0);
+	if (unlikely(!fast_path)) {
+		gl->gl_lockref.count++;
+		if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
+		    !test_bit(GLF_DEMOTE, &gl->gl_flags) &&
+		    gl->gl_name.ln_type == LM_TYPE_INODE)
+			delay = gl->gl_hold_time;
+		__gfs2_glock_queue_work(gl, delay);
+	}
 	spin_unlock(&gl->gl_lockref.lock);
-	if (likely(fast_path))
-		return;
-
-	gfs2_glock_hold(gl);
-	if (test_bit(GLF_PENDING_DEMOTE, &gl->gl_flags) &&
-	    !test_bit(GLF_DEMOTE, &gl->gl_flags) &&
-	    gl->gl_name.ln_type == LM_TYPE_INODE)
-		delay = gl->gl_hold_time;
-	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
-		gfs2_glock_put(gl);
 }
 
 void gfs2_glock_dq_wait(struct gfs2_holder *gh)
@@ -1227,9 +1270,8 @@ void gfs2_glock_cb(struct gfs2_glock *gl, unsigned int state)
 
 	spin_lock(&gl->gl_lockref.lock);
 	handle_callback(gl, state, delay, true);
+	__gfs2_glock_queue_work(gl, delay);
 	spin_unlock(&gl->gl_lockref.lock);
-	if (queue_delayed_work(glock_workqueue, &gl->gl_work, delay) == 0)
-		gfs2_glock_put(gl);
 }
 
 /**
@@ -1288,10 +1330,8 @@ void gfs2_glock_complete(struct gfs2_glock *gl, int ret)
 
 	gl->gl_lockref.count++;
 	set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
+	__gfs2_glock_queue_work(gl, 0);
 	spin_unlock(&gl->gl_lockref.lock);
-
-	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
-		gfs2_glock_put(gl);
 }
 
 static int glock_cmp(void *priv, struct list_head *a, struct list_head *b)
@@ -1349,8 +1389,7 @@ add_back_to_lru:
 		if (demote_ok(gl))
 			handle_callback(gl, LM_ST_UNLOCKED, 0, false);
 		WARN_ON(!test_and_clear_bit(GLF_LOCK, &gl->gl_flags));
-		if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
-			gl->gl_lockref.count--;
+		__gfs2_glock_queue_work(gl, 0);
 		spin_unlock(&gl->gl_lockref.lock);
 		cond_resched_lock(&lru_lock);
 	}
@@ -1420,26 +1459,32 @@ static struct shrinker glock_shrinker = {
  * @sdp: the filesystem
  * @bucket: the bucket
  *
+ * Note that the function can be called multiple times on the same
+ * object.  So the user must ensure that the function can cope with
+ * that.
  */
 
 static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
 {
 	struct gfs2_glock *gl;
-	struct rhash_head *pos;
-	const struct bucket_table *tbl;
-	int i;
+	struct rhashtable_iter iter;
 
-	rcu_read_lock();
-	tbl = rht_dereference_rcu(gl_hash_table.tbl, &gl_hash_table);
-	for (i = 0; i < tbl->size; i++) {
-		rht_for_each_entry_rcu(gl, pos, tbl, i, gl_node) {
+	rhashtable_walk_enter(&gl_hash_table, &iter);
+
+	do {
+		gl = ERR_PTR(rhashtable_walk_start(&iter));
+		if (gl)
+			continue;
+
+		while ((gl = rhashtable_walk_next(&iter)) && !IS_ERR(gl))
 			if ((gl->gl_name.ln_sbd == sdp) &&
 			    lockref_get_not_dead(&gl->gl_lockref))
 				examiner(gl);
-		}
-	}
-	rcu_read_unlock();
-	cond_resched();
+
+		rhashtable_walk_stop(&iter);
+	} while (cond_resched(), gl == ERR_PTR(-EAGAIN));
+
+	rhashtable_walk_exit(&iter);
 }
 
 /**
@@ -1450,13 +1495,12 @@ static void glock_hash_walk(glock_examiner examiner, const struct gfs2_sbd *sdp)
 
 static void thaw_glock(struct gfs2_glock *gl)
 {
-	if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags))
-		goto out;
-	set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
-	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0) {
-out:
+	if (!test_and_clear_bit(GLF_FROZEN, &gl->gl_flags)) {
 		gfs2_glock_put(gl);
+		return;
 	}
+	set_bit(GLF_REPLY_PENDING, &gl->gl_flags);
+	gfs2_glock_queue_work(gl, 0);
 }
 
 /**
@@ -1472,9 +1516,8 @@ static void clear_glock(struct gfs2_glock *gl)
 	spin_lock(&gl->gl_lockref.lock);
 	if (gl->gl_state != LM_ST_UNLOCKED)
 		handle_callback(gl, LM_ST_UNLOCKED, 0, false);
+	__gfs2_glock_queue_work(gl, 0);
 	spin_unlock(&gl->gl_lockref.lock);
-	if (queue_delayed_work(glock_workqueue, &gl->gl_work, 0) == 0)
-		gfs2_glock_put(gl);
 }
 
 /**
@@ -1802,16 +1845,18 @@ void gfs2_glock_exit(void)
 
 static void gfs2_glock_iter_next(struct gfs2_glock_iter *gi)
 {
-	do {
-		gi->gl = rhashtable_walk_next(&gi->hti);
+	while ((gi->gl = rhashtable_walk_next(&gi->hti))) {
 		if (IS_ERR(gi->gl)) {
 			if (PTR_ERR(gi->gl) == -EAGAIN)
 				continue;
 			gi->gl = NULL;
+			return;
 		}
-	/* Skip entries for other sb and dead entries */
-	} while ((gi->gl) && ((gi->sdp != gi->gl->gl_name.ln_sbd) ||
-			      __lockref_is_dead(&gi->gl->gl_lockref)));
+		/* Skip entries for other sb and dead entries */
+		if (gi->sdp == gi->gl->gl_name.ln_sbd &&
+		    !__lockref_is_dead(&gi->gl->gl_lockref))
+			return;
+	}
 }
 
 static void *gfs2_glock_seq_start(struct seq_file *seq, loff_t *pos)
@@ -1905,10 +1950,10 @@ static const struct seq_operations gfs2_sbstats_seq_ops = {
 
 #define GFS2_SEQ_GOODSIZE min(PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER, 65536UL)
 
-static int gfs2_glocks_open(struct inode *inode, struct file *file)
+static int __gfs2_glocks_open(struct inode *inode, struct file *file,
+			      const struct seq_operations *ops)
 {
-	int ret = seq_open_private(file, &gfs2_glock_seq_ops,
-				   sizeof(struct gfs2_glock_iter));
+	int ret = seq_open_private(file, ops, sizeof(struct gfs2_glock_iter));
 	if (ret == 0) {
 		struct seq_file *seq = file->private_data;
 		struct gfs2_glock_iter *gi = seq->private;
@@ -1919,11 +1964,16 @@ static int gfs2_glocks_open(struct inode *inode, struct file *file)
 		if (seq->buf)
 			seq->size = GFS2_SEQ_GOODSIZE;
 		gi->gl = NULL;
-		ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL);
+		rhashtable_walk_enter(&gl_hash_table, &gi->hti);
 	}
 	return ret;
 }
 
+static int gfs2_glocks_open(struct inode *inode, struct file *file)
+{
+	return __gfs2_glocks_open(inode, file, &gfs2_glock_seq_ops);
+}
+
 static int gfs2_glocks_release(struct inode *inode, struct file *file)
 {
 	struct seq_file *seq = file->private_data;
@@ -1936,20 +1986,7 @@ static int gfs2_glocks_release(struct inode *inode, struct file *file)
 
 static int gfs2_glstats_open(struct inode *inode, struct file *file)
 {
-	int ret = seq_open_private(file, &gfs2_glstats_seq_ops,
-				   sizeof(struct gfs2_glock_iter));
-	if (ret == 0) {
-		struct seq_file *seq = file->private_data;
-		struct gfs2_glock_iter *gi = seq->private;
-		gi->sdp = inode->i_private;
-		gi->last_pos = 0;
-		seq->buf = kmalloc(GFS2_SEQ_GOODSIZE, GFP_KERNEL | __GFP_NOWARN);
-		if (seq->buf)
-			seq->size = GFS2_SEQ_GOODSIZE;
-		gi->gl = NULL;
-		ret = rhashtable_walk_init(&gl_hash_table, &gi->hti, GFP_KERNEL);
-	}
-	return ret;
+	return __gfs2_glocks_open(inode, file, &gfs2_glstats_seq_ops);
 }
 
 static int gfs2_sbstats_open(struct inode *inode, struct file *file)
diff --git a/fs/gfs2/glock.h b/fs/gfs2/glock.h
index ab1ef322f7a5..9ad4a6ac6c84 100644
--- a/fs/gfs2/glock.h
+++ b/fs/gfs2/glock.h
@@ -257,4 +257,11 @@ static inline bool gfs2_holder_initialized(struct gfs2_holder *gh)
 	return gh->gh_gl;
 }
 
+static inline void glock_set_object(struct gfs2_glock *gl, void *object)
+{
+	spin_lock(&gl->gl_lockref.lock);
+	gl->gl_object = object;
+	spin_unlock(&gl->gl_lockref.lock);
+}
+
 #endif /* __GLOCK_DOT_H__ */
diff --git a/fs/gfs2/glops.c b/fs/gfs2/glops.c
index 5db59d444838..5e69636d4dd3 100644
--- a/fs/gfs2/glops.c
+++ b/fs/gfs2/glops.c
@@ -137,7 +137,7 @@ void gfs2_ail_flush(struct gfs2_glock *gl, bool fsync)
  *
  * Called when demoting or unlocking an EX glock.  We must flush
  * to disk all dirty buffers/pages relating to this glock, and must not
- * not return to caller to demote/unlock the glock until I/O is complete.
+ * return to caller to demote/unlock the glock until I/O is complete.
  */
 
 static void rgrp_go_sync(struct gfs2_glock *gl)
@@ -184,7 +184,7 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags)
 {
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct address_space *mapping = &sdp->sd_aspace;
-	struct gfs2_rgrpd *rgd = gl->gl_object;
+	struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
 
 	if (rgd)
 		gfs2_rgrp_brelse(rgd);
@@ -197,6 +197,38 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags)
 		rgd->rd_flags &= ~GFS2_RDF_UPTODATE;
 }
 
+static struct gfs2_inode *gfs2_glock2inode(struct gfs2_glock *gl)
+{
+	struct gfs2_inode *ip;
+
+	spin_lock(&gl->gl_lockref.lock);
+	ip = gl->gl_object;
+	if (ip)
+		set_bit(GIF_GLOP_PENDING, &ip->i_flags);
+	spin_unlock(&gl->gl_lockref.lock);
+	return ip;
+}
+
+struct gfs2_rgrpd *gfs2_glock2rgrp(struct gfs2_glock *gl)
+{
+	struct gfs2_rgrpd *rgd;
+
+	spin_lock(&gl->gl_lockref.lock);
+	rgd = gl->gl_object;
+	spin_unlock(&gl->gl_lockref.lock);
+
+	return rgd;
+}
+
+static void gfs2_clear_glop_pending(struct gfs2_inode *ip)
+{
+	if (!ip)
+		return;
+
+	clear_bit_unlock(GIF_GLOP_PENDING, &ip->i_flags);
+	wake_up_bit(&ip->i_flags, GIF_GLOP_PENDING);
+}
+
 /**
  * inode_go_sync - Sync the dirty data and/or metadata for an inode glock
  * @gl: the glock protecting the inode
@@ -205,25 +237,24 @@ static void rgrp_go_inval(struct gfs2_glock *gl, int flags)
 
 static void inode_go_sync(struct gfs2_glock *gl)
 {
-	struct gfs2_inode *ip = gl->gl_object;
+	struct gfs2_inode *ip = gfs2_glock2inode(gl);
+	int isreg = ip && S_ISREG(ip->i_inode.i_mode);
 	struct address_space *metamapping = gfs2_glock2aspace(gl);
 	int error;
 
-	if (ip && !S_ISREG(ip->i_inode.i_mode))
-		ip = NULL;
-	if (ip) {
+	if (isreg) {
 		if (test_and_clear_bit(GIF_SW_PAGED, &ip->i_flags))
 			unmap_shared_mapping_range(ip->i_inode.i_mapping, 0, 0);
 		inode_dio_wait(&ip->i_inode);
 	}
 	if (!test_and_clear_bit(GLF_DIRTY, &gl->gl_flags))
-		return;
+		goto out;
 
 	GLOCK_BUG_ON(gl, gl->gl_state != LM_ST_EXCLUSIVE);
 
 	gfs2_log_flush(gl->gl_name.ln_sbd, gl, NORMAL_FLUSH);
 	filemap_fdatawrite(metamapping);
-	if (ip) {
+	if (isreg) {
 		struct address_space *mapping = ip->i_inode.i_mapping;
 		filemap_fdatawrite(mapping);
 		error = filemap_fdatawait(mapping);
@@ -238,6 +269,9 @@ static void inode_go_sync(struct gfs2_glock *gl)
 	 */
 	smp_mb__before_atomic();
 	clear_bit(GLF_DIRTY, &gl->gl_flags);
+
+out:
+	gfs2_clear_glop_pending(ip);
 }
 
 /**
@@ -253,7 +287,7 @@ static void inode_go_sync(struct gfs2_glock *gl)
 
 static void inode_go_inval(struct gfs2_glock *gl, int flags)
 {
-	struct gfs2_inode *ip = gl->gl_object;
+	struct gfs2_inode *ip = gfs2_glock2inode(gl);
 
 	gfs2_assert_withdraw(gl->gl_name.ln_sbd, !atomic_read(&gl->gl_ail_count));
 
@@ -274,6 +308,8 @@ static void inode_go_inval(struct gfs2_glock *gl, int flags)
 	}
 	if (ip && S_ISREG(ip->i_inode.i_mode))
 		truncate_inode_pages(ip->i_inode.i_mapping, 0);
+
+	gfs2_clear_glop_pending(ip);
 }
 
 /**
@@ -541,7 +577,7 @@ static int freeze_go_demote_ok(const struct gfs2_glock *gl)
  */
 static void iopen_go_callback(struct gfs2_glock *gl, bool remote)
 {
-	struct gfs2_inode *ip = (struct gfs2_inode *)gl->gl_object;
+	struct gfs2_inode *ip = gl->gl_object;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 
 	if (!remote || (sdp->sd_vfs->s_flags & MS_RDONLY))
diff --git a/fs/gfs2/incore.h b/fs/gfs2/incore.h
index a6a3389a07fc..73fce76e67ee 100644
--- a/fs/gfs2/incore.h
+++ b/fs/gfs2/incore.h
@@ -203,9 +203,13 @@ enum {
 	DFL_DLM_RECOVERY	= 6,
 };
 
+/*
+ * We are using struct lm_lockname as an rhashtable key.  Avoid holes within
+ * the struct; padding at the end is fine.
+ */
 struct lm_lockname {
-	struct gfs2_sbd *ln_sbd;
 	u64 ln_number;
+	struct gfs2_sbd *ln_sbd;
 	unsigned int ln_type;
 };
 
@@ -332,7 +336,6 @@ enum {
 };
 
 struct gfs2_glock {
-	struct hlist_bl_node gl_list;
 	unsigned long gl_flags;		/* GLF_... */
 	struct lm_lockname gl_name;
 
@@ -370,6 +373,7 @@ struct gfs2_glock {
 			loff_t end;
 		} gl_vm;
 	};
+	struct rcu_head gl_rcu;
 	struct rhash_head gl_node;
 };
 
@@ -382,6 +386,7 @@ enum {
 	GIF_SW_PAGED		= 3,
 	GIF_ORDERED		= 4,
 	GIF_FREE_VFS_INODE      = 5,
+	GIF_GLOP_PENDING	= 6,
 };
 
 struct gfs2_inode {
@@ -470,15 +475,19 @@ struct gfs2_quota_data {
 	struct rcu_head qd_rcu;
 };
 
+enum {
+	TR_TOUCHED = 1,
+	TR_ATTACHED = 2,
+	TR_ALLOCED = 3,
+};
+
 struct gfs2_trans {
 	unsigned long tr_ip;
 
 	unsigned int tr_blocks;
 	unsigned int tr_revokes;
 	unsigned int tr_reserved;
-	unsigned int tr_touched:1;
-	unsigned int tr_attached:1;
-	unsigned int tr_alloced:1;
+	unsigned long tr_flags;
 
 	unsigned int tr_num_buf_new;
 	unsigned int tr_num_databuf_new;
@@ -794,6 +803,7 @@ struct gfs2_sbd {
 	atomic_t sd_log_thresh1;
 	atomic_t sd_log_thresh2;
 	atomic_t sd_log_blks_free;
+	atomic_t sd_log_blks_needed;
 	wait_queue_head_t sd_log_waitq;
 	wait_queue_head_t sd_logd_waitq;
 
@@ -806,13 +816,11 @@ struct gfs2_sbd {
 	atomic_t sd_log_in_flight;
 	struct bio *sd_log_bio;
 	wait_queue_head_t sd_log_flush_wait;
-	int sd_log_error;
 
 	atomic_t sd_reserving_log;
 	wait_queue_head_t sd_reserving_log_wait;
 
 	unsigned int sd_log_flush_head;
-	u64 sd_log_flush_wrapped;
 
 	spinlock_t sd_ail_lock;
 	struct list_head sd_ail1_list;
@@ -849,5 +857,7 @@ static inline void gfs2_sbstats_inc(const struct gfs2_glock *gl, int which)
 	preempt_enable();
 }
 
+extern struct gfs2_rgrpd *gfs2_glock2rgrp(struct gfs2_glock *gl);
+
 #endif /* __INCORE_DOT_H__ */
 
diff --git a/fs/gfs2/inode.c b/fs/gfs2/inode.c
index eb7724b8578a..acca501f8110 100644
--- a/fs/gfs2/inode.c
+++ b/fs/gfs2/inode.c
@@ -13,6 +13,7 @@
 #include <linux/buffer_head.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
+#include <linux/cred.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
 #include <linux/gfs2_ondisk.h>
@@ -143,7 +144,8 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 		error = gfs2_glock_get(sdp, no_addr, &gfs2_inode_glops, CREATE, &ip->i_gl);
 		if (unlikely(error))
 			goto fail;
-		ip->i_gl->gl_object = ip;
+		flush_delayed_work(&ip->i_gl->gl_work);
+		glock_set_object(ip->i_gl, ip);
 
 		error = gfs2_glock_get(sdp, no_addr, &gfs2_iopen_glops, CREATE, &io_gl);
 		if (unlikely(error))
@@ -172,8 +174,8 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 		error = gfs2_glock_nq_init(io_gl, LM_ST_SHARED, GL_EXACT, &ip->i_iopen_gh);
 		if (unlikely(error))
 			goto fail_put;
-
-		ip->i_iopen_gh.gh_gl->gl_object = ip;
+		flush_delayed_work(&ip->i_iopen_gh.gh_gl->gl_work);
+		glock_set_object(ip->i_iopen_gh.gh_gl, ip);
 		gfs2_glock_put(io_gl);
 		io_gl = NULL;
 
@@ -200,15 +202,14 @@ struct inode *gfs2_inode_lookup(struct super_block *sb, unsigned int type,
 
 fail_refresh:
 	ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-	ip->i_iopen_gh.gh_gl->gl_object = NULL;
-	gfs2_glock_dq_wait(&ip->i_iopen_gh);
-	gfs2_holder_uninit(&ip->i_iopen_gh);
+	glock_set_object(ip->i_iopen_gh.gh_gl, NULL);
+	gfs2_glock_dq_uninit(&ip->i_iopen_gh);
 fail_put:
 	if (io_gl)
 		gfs2_glock_put(io_gl);
 	if (gfs2_holder_initialized(&i_gh))
 		gfs2_glock_dq_uninit(&i_gh);
-	ip->i_gl->gl_object = NULL;
+	glock_set_object(ip->i_gl, NULL);
 fail:
 	iget_failed(inode);
 	return ERR_PTR(error);
@@ -607,6 +608,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	error = gfs2_glock_nq_init(dip->i_gl, LM_ST_EXCLUSIVE, 0, ghs);
 	if (error)
 		goto fail;
+	gfs2_holder_mark_uninitialized(ghs + 1);
 
 	error = create_ok(dip, name, mode);
 	if (error)
@@ -666,6 +668,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	ip->i_height = 0;
 	ip->i_depth = 0;
 	ip->i_entries = 0;
+	ip->i_no_addr = 0; /* Temporarily zero until real addr is assigned */
 
 	switch(mode & S_IFMT) {
 	case S_IFREG:
@@ -704,7 +707,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	if (error)
 		goto fail_free_inode;
 
-	ip->i_gl->gl_object = ip;
+	glock_set_object(ip->i_gl, ip);
 	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, ghs + 1);
 	if (error)
 		goto fail_free_inode;
@@ -730,7 +733,7 @@ static int gfs2_create_inode(struct inode *dir, struct dentry *dentry,
 	if (error)
 		goto fail_gunlock2;
 
-	ip->i_iopen_gh.gh_gl->gl_object = ip;
+	glock_set_object(ip->i_iopen_gh.gh_gl, ip);
 	gfs2_glock_put(io_gl);
 	gfs2_set_iop(inode);
 	insert_inode_hash(inode);
@@ -777,7 +780,6 @@ fail_gunlock3:
 fail_gunlock2:
 	if (io_gl)
 		clear_bit(GLF_INODE_CREATING, &io_gl->gl_flags);
-	gfs2_glock_dq_uninit(ghs + 1);
 fail_free_inode:
 	if (ip->i_gl)
 		gfs2_glock_put(ip->i_gl);
@@ -798,6 +800,8 @@ fail_gunlock:
 			&GFS2_I(inode)->i_flags);
 		iput(inode);
 	}
+	if (gfs2_holder_initialized(ghs + 1))
+		gfs2_glock_dq_uninit(ghs + 1);
 fail:
 	return error;
 }
@@ -1959,9 +1963,10 @@ out:
 
 /**
  * gfs2_getattr - Read out an inode's attributes
- * @mnt: The vfsmount the inode is being accessed from
- * @dentry: The dentry to stat
+ * @path: Object to query
  * @stat: The inode's stats
+ * @request_mask: Mask of STATX_xxx flags indicating the caller's interests
+ * @flags: AT_STATX_xxx setting
  *
  * This may be called from the VFS directly, or from within GFS2 with the
  * inode locked, so we look to see if the glock is already locked and only
@@ -1972,10 +1977,10 @@ out:
  * Returns: errno
  */
 
-static int gfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			struct kstat *stat)
+static int gfs2_getattr(const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct gfs2_inode *ip = GFS2_I(inode);
 	struct gfs2_holder gh;
 	int error;
diff --git a/fs/gfs2/lock_dlm.c b/fs/gfs2/lock_dlm.c
index 8b907c5cc913..0515f0a68637 100644
--- a/fs/gfs2/lock_dlm.c
+++ b/fs/gfs2/lock_dlm.c
@@ -15,6 +15,7 @@
 #include <linux/types.h>
 #include <linux/delay.h>
 #include <linux/gfs2_ondisk.h>
+#include <linux/sched/signal.h>
 
 #include "incore.h"
 #include "glock.h"
diff --git a/fs/gfs2/log.c b/fs/gfs2/log.c
index 27c00a16def0..9a624f694400 100644
--- a/fs/gfs2/log.c
+++ b/fs/gfs2/log.c
@@ -349,6 +349,7 @@ int gfs2_log_reserve(struct gfs2_sbd *sdp, unsigned int blks)
 	if (gfs2_assert_warn(sdp, blks) ||
 	    gfs2_assert_warn(sdp, blks <= sdp->sd_jdesc->jd_blocks))
 		return -EINVAL;
+	atomic_add(blks, &sdp->sd_log_blks_needed);
 retry:
 	free_blocks = atomic_read(&sdp->sd_log_blks_free);
 	if (unlikely(free_blocks <= wanted)) {
@@ -370,6 +371,7 @@ retry:
 			wake_up(&sdp->sd_reserving_log_wait);
 		goto retry;
 	}
+	atomic_sub(blks, &sdp->sd_log_blks_needed);
 	trace_gfs2_log_blocks(sdp, -blks);
 
 	/*
@@ -657,7 +659,7 @@ static void log_write_header(struct gfs2_sbd *sdp, u32 flags)
 	struct gfs2_log_header *lh;
 	unsigned int tail;
 	u32 hash;
-	int op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META;
+	int op_flags = REQ_PREFLUSH | REQ_FUA | REQ_META | REQ_SYNC;
 	struct page *page = mempool_alloc(gfs2_page_pool, GFP_NOIO);
 	enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
 	lh = page_address(page);
@@ -720,7 +722,6 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
 		clear_bit(SDF_JOURNAL_LIVE, &sdp->sd_flags);
 
 	sdp->sd_log_flush_head = sdp->sd_log_head;
-	sdp->sd_log_flush_wrapped = 0;
 	tr = sdp->sd_log_tr;
 	if (tr) {
 		sdp->sd_log_tr = NULL;
@@ -773,7 +774,6 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
 			}
 			atomic_dec(&sdp->sd_log_blks_free); /* Adjust for unreserved buffer */
 			trace_gfs2_log_blocks(sdp, -1);
-			sdp->sd_log_flush_wrapped = 0;
 			log_write_header(sdp, 0);
 			sdp->sd_log_head = sdp->sd_log_flush_head;
 		}
@@ -797,7 +797,7 @@ void gfs2_log_flush(struct gfs2_sbd *sdp, struct gfs2_glock *gl,
 
 static void gfs2_merge_trans(struct gfs2_trans *old, struct gfs2_trans *new)
 {
-	WARN_ON_ONCE(old->tr_attached != 1);
+	WARN_ON_ONCE(!test_bit(TR_ATTACHED, &old->tr_flags));
 
 	old->tr_num_buf_new	+= new->tr_num_buf_new;
 	old->tr_num_databuf_new	+= new->tr_num_databuf_new;
@@ -821,9 +821,9 @@ static void log_refund(struct gfs2_sbd *sdp, struct gfs2_trans *tr)
 	if (sdp->sd_log_tr) {
 		gfs2_merge_trans(sdp->sd_log_tr, tr);
 	} else if (tr->tr_num_buf_new || tr->tr_num_databuf_new) {
-		gfs2_assert_withdraw(sdp, tr->tr_alloced);
+		gfs2_assert_withdraw(sdp, test_bit(TR_ALLOCED, &tr->tr_flags));
 		sdp->sd_log_tr = tr;
-		tr->tr_attached = 1;
+		set_bit(TR_ATTACHED, &tr->tr_flags);
 	}
 
 	sdp->sd_log_commited_revoke += tr->tr_num_revoke - tr->tr_num_revoke_rm;
@@ -878,7 +878,6 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 	gfs2_assert_withdraw(sdp, list_empty(&sdp->sd_ail1_list));
 
 	sdp->sd_log_flush_head = sdp->sd_log_head;
-	sdp->sd_log_flush_wrapped = 0;
 
 	log_write_header(sdp, GFS2_LOG_HEAD_UNMOUNT);
 
@@ -891,13 +890,16 @@ void gfs2_log_shutdown(struct gfs2_sbd *sdp)
 
 static inline int gfs2_jrnl_flush_reqd(struct gfs2_sbd *sdp)
 {
-	return (atomic_read(&sdp->sd_log_pinned) >= atomic_read(&sdp->sd_log_thresh1));
+	return (atomic_read(&sdp->sd_log_pinned) +
+		atomic_read(&sdp->sd_log_blks_needed) >=
+		atomic_read(&sdp->sd_log_thresh1));
 }
 
 static inline int gfs2_ail_flush_reqd(struct gfs2_sbd *sdp)
 {
 	unsigned int used_blocks = sdp->sd_jdesc->jd_blocks - atomic_read(&sdp->sd_log_blks_free);
-	return used_blocks >= atomic_read(&sdp->sd_log_thresh2);
+	return used_blocks + atomic_read(&sdp->sd_log_blks_needed) >=
+		atomic_read(&sdp->sd_log_thresh2);
 }
 
 /**
@@ -913,12 +915,15 @@ int gfs2_logd(void *data)
 	struct gfs2_sbd *sdp = data;
 	unsigned long t = 1;
 	DEFINE_WAIT(wait);
+	bool did_flush;
 
 	while (!kthread_should_stop()) {
 
+		did_flush = false;
 		if (gfs2_jrnl_flush_reqd(sdp) || t == 0) {
 			gfs2_ail1_empty(sdp);
 			gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
+			did_flush = true;
 		}
 
 		if (gfs2_ail_flush_reqd(sdp)) {
@@ -926,9 +931,10 @@ int gfs2_logd(void *data)
 			gfs2_ail1_wait(sdp);
 			gfs2_ail1_empty(sdp);
 			gfs2_log_flush(sdp, NULL, NORMAL_FLUSH);
+			did_flush = true;
 		}
 
-		if (!gfs2_ail_flush_reqd(sdp))
+		if (!gfs2_ail_flush_reqd(sdp) || did_flush)
 			wake_up(&sdp->sd_log_waitq);
 
 		t = gfs2_tune_get(sdp, gt_logd_secs) * HZ;
diff --git a/fs/gfs2/lops.c b/fs/gfs2/lops.c
index b1f9144b42c7..3010f9edd177 100644
--- a/fs/gfs2/lops.c
+++ b/fs/gfs2/lops.c
@@ -71,7 +71,7 @@ static void maybe_release_space(struct gfs2_bufdata *bd)
 {
 	struct gfs2_glock *gl = bd->bd_gl;
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
-	struct gfs2_rgrpd *rgd = gl->gl_object;
+	struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(gl);
 	unsigned int index = bd->bd_bh->b_blocknr - gl->gl_name.ln_number;
 	struct gfs2_bitmap *bi = rgd->rd_bits + index;
 
@@ -134,10 +134,8 @@ static void gfs2_log_incr_head(struct gfs2_sbd *sdp)
 	BUG_ON((sdp->sd_log_flush_head == sdp->sd_log_tail) &&
 	       (sdp->sd_log_flush_head != sdp->sd_log_head));
 
-	if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks) {
+	if (++sdp->sd_log_flush_head == sdp->sd_jdesc->jd_blocks)
 		sdp->sd_log_flush_head = 0;
-		sdp->sd_log_flush_wrapped = 1;
-	}
 }
 
 static u64 gfs2_log_bmap(struct gfs2_sbd *sdp)
@@ -170,7 +168,7 @@ static u64 gfs2_log_bmap(struct gfs2_sbd *sdp)
  */
 
 static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec,
-				  int error)
+				  blk_status_t error)
 {
 	struct buffer_head *bh, *next;
 	struct page *page = bvec->bv_page;
@@ -182,7 +180,7 @@ static void gfs2_end_log_write_bh(struct gfs2_sbd *sdp, struct bio_vec *bvec,
 		bh = bh->b_this_page;
 	do {
 		if (error)
-			set_buffer_write_io_error(bh);
+			mark_buffer_write_io_error(bh);
 		unlock_buffer(bh);
 		next = bh->b_this_page;
 		size -= bh->b_size;
@@ -209,15 +207,13 @@ static void gfs2_end_log_write(struct bio *bio)
 	struct page *page;
 	int i;
 
-	if (bio->bi_error) {
-		sdp->sd_log_error = bio->bi_error;
-		fs_err(sdp, "Error %d writing to log\n", bio->bi_error);
-	}
+	if (bio->bi_status)
+		fs_err(sdp, "Error %d writing to log\n", bio->bi_status);
 
 	bio_for_each_segment_all(bvec, bio, i) {
 		page = bvec->bv_page;
 		if (page_has_buffers(page))
-			gfs2_end_log_write_bh(sdp, bvec, bio->bi_error);
+			gfs2_end_log_write_bh(sdp, bvec, bio->bi_status);
 		else
 			mempool_free(page, gfs2_page_pool);
 	}
diff --git a/fs/gfs2/main.c b/fs/gfs2/main.c
index 67d1fc4668f7..0a89e6f7a314 100644
--- a/fs/gfs2/main.c
+++ b/fs/gfs2/main.c
@@ -52,7 +52,6 @@ static void gfs2_init_glock_once(void *foo)
 {
 	struct gfs2_glock *gl = foo;
 
-	INIT_HLIST_BL_NODE(&gl->gl_list);
 	spin_lock_init(&gl->gl_lockref.lock);
 	INIT_LIST_HEAD(&gl->gl_holders);
 	INIT_LIST_HEAD(&gl->gl_lru);
diff --git a/fs/gfs2/meta_io.c b/fs/gfs2/meta_io.c
index 49db8ef13fdf..fabe1614f879 100644
--- a/fs/gfs2/meta_io.c
+++ b/fs/gfs2/meta_io.c
@@ -201,7 +201,7 @@ static void gfs2_meta_read_endio(struct bio *bio)
 		do {
 			struct buffer_head *next = bh->b_this_page;
 			len -= bh->b_size;
-			bh->b_end_io(bh, !bio->bi_error);
+			bh->b_end_io(bh, !bio->bi_status);
 			bh = next;
 		} while (bh && len);
 	}
@@ -292,7 +292,7 @@ int gfs2_meta_read(struct gfs2_glock *gl, u64 blkno, int flags,
 	wait_on_buffer(bh);
 	if (unlikely(!buffer_uptodate(bh))) {
 		struct gfs2_trans *tr = current->journal_info;
-		if (tr && tr->tr_touched)
+		if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
 			gfs2_io_error_bh(sdp, bh);
 		brelse(bh);
 		*bhp = NULL;
@@ -319,7 +319,7 @@ int gfs2_meta_wait(struct gfs2_sbd *sdp, struct buffer_head *bh)
 
 	if (!buffer_uptodate(bh)) {
 		struct gfs2_trans *tr = current->journal_info;
-		if (tr && tr->tr_touched)
+		if (tr && test_bit(TR_TOUCHED, &tr->tr_flags))
 			gfs2_io_error_bh(sdp, bh);
 		return -EIO;
 	}
@@ -345,7 +345,7 @@ void gfs2_remove_from_journal(struct buffer_head *bh, int meta)
 			tr->tr_num_buf_rm++;
 		else
 			tr->tr_num_databuf_rm++;
-		tr->tr_touched = 1;
+		set_bit(TR_TOUCHED, &tr->tr_flags);
 		was_pinned = 1;
 		brelse(bh);
 	}
diff --git a/fs/gfs2/ops_fstype.c b/fs/gfs2/ops_fstype.c
index a34308df927f..e76058d34b74 100644
--- a/fs/gfs2/ops_fstype.c
+++ b/fs/gfs2/ops_fstype.c
@@ -23,6 +23,7 @@
 #include <linux/quotaops.h>
 #include <linux/lockdep.h>
 #include <linux/module.h>
+#include <linux/backing-dev.h>
 
 #include "gfs2.h"
 #include "incore.h"
@@ -175,10 +176,10 @@ static void end_bio_io_page(struct bio *bio)
 {
 	struct page *page = bio->bi_private;
 
-	if (!bio->bi_error)
+	if (!bio->bi_status)
 		SetPageUptodate(page);
 	else
-		pr_warn("error %d reading superblock\n", bio->bi_error);
+		pr_warn("error %d reading superblock\n", bio->bi_status);
 	unlock_page(page);
 }
 
@@ -202,7 +203,7 @@ static void gfs2_sb_in(struct gfs2_sbd *sdp, const void *buf)
 
 	memcpy(sb->sb_lockproto, str->sb_lockproto, GFS2_LOCKNAME_LEN);
 	memcpy(sb->sb_locktable, str->sb_locktable, GFS2_LOCKNAME_LEN);
-	memcpy(s->s_uuid, str->sb_uuid, 16);
+	memcpy(&s->s_uuid, str->sb_uuid, 16);
 }
 
 /**
@@ -683,6 +684,7 @@ static int init_journal(struct gfs2_sbd *sdp, int undo)
 		goto fail_jindex;
 	}
 
+	atomic_set(&sdp->sd_log_blks_needed, 0);
 	if (sdp->sd_args.ar_spectator) {
 		sdp->sd_jdesc = gfs2_jdesc_find(sdp, 0);
 		atomic_set(&sdp->sd_log_blks_free, sdp->sd_jdesc->jd_blocks);
@@ -1221,12 +1223,7 @@ static int set_gfs2_super(struct super_block *s, void *data)
 {
 	s->s_bdev = data;
 	s->s_dev = s->s_bdev->bd_dev;
-
-	/*
-	 * We set the bdi here to the queue backing, file systems can
-	 * overwrite this in ->fill_super()
-	 */
-	s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info;
+	s->s_bdi = bdi_get(s->s_bdev->bd_bdi);
 	return 0;
 }
 
diff --git a/fs/gfs2/rgrp.c b/fs/gfs2/rgrp.c
index 86ccc0159393..836e38ba5d0a 100644
--- a/fs/gfs2/rgrp.c
+++ b/fs/gfs2/rgrp.c
@@ -483,13 +483,6 @@ void gfs2_rgrp_verify(struct gfs2_rgrpd *rgd)
 	}
 }
 
-static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block)
-{
-	u64 first = rgd->rd_data0;
-	u64 last = first + rgd->rd_data;
-	return first <= block && block < last;
-}
-
 /**
  * gfs2_blk2rgrpd - Find resource group for a given data/meta block number
  * @sdp: The GFS2 superblock
@@ -712,9 +705,7 @@ void gfs2_clear_rgrpd(struct gfs2_sbd *sdp)
 		rb_erase(n, &sdp->sd_rindex_tree);
 
 		if (gl) {
-			spin_lock(&gl->gl_lockref.lock);
-			gl->gl_object = NULL;
-			spin_unlock(&gl->gl_lockref.lock);
+			glock_set_object(gl, NULL);
 			gfs2_glock_add_to_lru(gl);
 			gfs2_glock_put(gl);
 		}
@@ -924,7 +915,7 @@ static int read_rindex_entry(struct gfs2_inode *ip)
 	error = rgd_insert(rgd);
 	spin_unlock(&sdp->sd_rindex_spin);
 	if (!error) {
-		rgd->rd_gl->gl_object = rgd;
+		glock_set_object(rgd->rd_gl, rgd);
 		rgd->rd_gl->gl_vm.start = (rgd->rd_addr * bsize) & PAGE_MASK;
 		rgd->rd_gl->gl_vm.end = PAGE_ALIGN((rgd->rd_addr +
 						    rgd->rd_length) * bsize) - 1;
diff --git a/fs/gfs2/rgrp.h b/fs/gfs2/rgrp.h
index 66b51cf66dfa..e90478e2f545 100644
--- a/fs/gfs2/rgrp.h
+++ b/fs/gfs2/rgrp.h
@@ -83,5 +83,12 @@ static inline bool gfs2_rs_active(const struct gfs2_blkreserv *rs)
 	return rs && !RB_EMPTY_NODE(&rs->rs_node);
 }
 
+static inline int rgrp_contains_block(struct gfs2_rgrpd *rgd, u64 block)
+{
+	u64 first = rgd->rd_data0;
+	u64 last = first + rgd->rd_data;
+	return first <= block && block < last;
+}
+
 extern void check_and_update_goal(struct gfs2_inode *ip);
 #endif /* __RGRP_DOT_H__ */
diff --git a/fs/gfs2/super.c b/fs/gfs2/super.c
index e3ee387a6dfe..fdedec379b78 100644
--- a/fs/gfs2/super.c
+++ b/fs/gfs2/super.c
@@ -10,7 +10,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/bio.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/slab.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
@@ -793,7 +793,8 @@ static void gfs2_dirty_inode(struct inode *inode, int flags)
 
 	if (!(flags & (I_DIRTY_DATASYNC|I_DIRTY_SYNC)))
 		return;
-
+	if (unlikely(test_bit(SDF_SHUTDOWN, &sdp->sd_flags)))
+		return;
 	if (!gfs2_glock_is_locked_by_me(ip->i_gl)) {
 		ret = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, 0, &gh);
 		if (ret) {
@@ -1104,9 +1105,12 @@ static int gfs2_statfs_slow(struct gfs2_sbd *sdp, struct gfs2_statfs_change_host
 					gfs2_holder_uninit(gh);
 					error = err;
 				} else {
-					if (!error)
-						error = statfs_slow_fill(
-							gh->gh_gl->gl_object, sc);
+					if (!error) {
+						struct gfs2_rgrpd *rgd =
+							gfs2_glock2rgrp(gh->gh_gl);
+
+						error = statfs_slow_fill(rgd, sc);
+					}
 					gfs2_glock_dq_uninit(gh);
 				}
 			}
@@ -1534,20 +1538,23 @@ static void gfs2_evict_inode(struct inode *inode)
 	if (inode->i_nlink || (sb->s_flags & MS_RDONLY))
 		goto out;
 
+	if (test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) {
+		BUG_ON(!gfs2_glock_is_locked_by_me(ip->i_gl));
+		gfs2_holder_mark_uninitialized(&gh);
+		goto alloc_failed;
+	}
+
 	/* Must not read inode block until block type has been verified */
 	error = gfs2_glock_nq_init(ip->i_gl, LM_ST_EXCLUSIVE, GL_SKIP, &gh);
 	if (unlikely(error)) {
 		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq_wait(&ip->i_iopen_gh);
-		gfs2_holder_uninit(&ip->i_iopen_gh);
+		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
 		goto out;
 	}
 
-	if (!test_bit(GIF_ALLOC_FAILED, &ip->i_flags)) {
-		error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
-		if (error)
-			goto out_truncate;
-	}
+	error = gfs2_check_blk_type(sdp, ip->i_no_addr, GFS2_BLKST_UNLINKED);
+	if (error)
+		goto out_truncate;
 
 	if (test_bit(GIF_INVALID, &ip->i_flags)) {
 		error = gfs2_inode_refresh(ip);
@@ -1555,6 +1562,7 @@ static void gfs2_evict_inode(struct inode *inode)
 			goto out_truncate;
 	}
 
+alloc_failed:
 	if (gfs2_holder_initialized(&ip->i_iopen_gh) &&
 	    test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
 		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
@@ -1617,11 +1625,12 @@ out_unlock:
 	if (gfs2_holder_initialized(&ip->i_iopen_gh)) {
 		if (test_bit(HIF_HOLDER, &ip->i_iopen_gh.gh_iflags)) {
 			ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-			gfs2_glock_dq_wait(&ip->i_iopen_gh);
+			gfs2_glock_dq(&ip->i_iopen_gh);
 		}
 		gfs2_holder_uninit(&ip->i_iopen_gh);
 	}
-	gfs2_glock_dq_uninit(&gh);
+	if (gfs2_holder_initialized(&gh))
+		gfs2_glock_dq_uninit(&gh);
 	if (error && error != GLR_TRYFAILED && error != -EROFS)
 		fs_warn(sdp, "gfs2_evict_inode: %d\n", error);
 out:
@@ -1631,16 +1640,15 @@ out:
 	gfs2_ordered_del_inode(ip);
 	clear_inode(inode);
 	gfs2_dir_hash_inval(ip);
-	ip->i_gl->gl_object = NULL;
-	flush_delayed_work(&ip->i_gl->gl_work);
+	glock_set_object(ip->i_gl, NULL);
+	wait_on_bit_io(&ip->i_flags, GIF_GLOP_PENDING, TASK_UNINTERRUPTIBLE);
 	gfs2_glock_add_to_lru(ip->i_gl);
 	gfs2_glock_put(ip->i_gl);
 	ip->i_gl = NULL;
 	if (gfs2_holder_initialized(&ip->i_iopen_gh)) {
-		ip->i_iopen_gh.gh_gl->gl_object = NULL;
+		glock_set_object(ip->i_iopen_gh.gh_gl, NULL);
 		ip->i_iopen_gh.gh_flags |= GL_NOCACHE;
-		gfs2_glock_dq_wait(&ip->i_iopen_gh);
-		gfs2_holder_uninit(&ip->i_iopen_gh);
+		gfs2_glock_dq_uninit(&ip->i_iopen_gh);
 	}
 }
 
diff --git a/fs/gfs2/sys.c b/fs/gfs2/sys.c
index f8d30e41d1d3..ca1f97ff898c 100644
--- a/fs/gfs2/sys.c
+++ b/fs/gfs2/sys.c
@@ -10,6 +10,7 @@
 #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
 
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/spinlock.h>
 #include <linux/completion.h>
 #include <linux/buffer_head.h>
@@ -70,25 +71,14 @@ static ssize_t fsname_show(struct gfs2_sbd *sdp, char *buf)
 	return snprintf(buf, PAGE_SIZE, "%s\n", sdp->sd_fsname);
 }
 
-static int gfs2_uuid_valid(const u8 *uuid)
-{
-	int i;
-
-	for (i = 0; i < 16; i++) {
-		if (uuid[i])
-			return 1;
-	}
-	return 0;
-}
-
 static ssize_t uuid_show(struct gfs2_sbd *sdp, char *buf)
 {
 	struct super_block *s = sdp->sd_vfs;
-	const u8 *uuid = s->s_uuid;
+
 	buf[0] = '\0';
-	if (!gfs2_uuid_valid(uuid))
+	if (uuid_is_null(&s->s_uuid))
 		return 0;
-	return snprintf(buf, PAGE_SIZE, "%pUB\n", uuid);
+	return snprintf(buf, PAGE_SIZE, "%pUB\n", &s->s_uuid);
 }
 
 static ssize_t freeze_show(struct gfs2_sbd *sdp, char *buf)
@@ -636,12 +626,12 @@ static struct attribute *tune_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group tune_group = {
+static const struct attribute_group tune_group = {
 	.name = "tune",
 	.attrs = tune_attrs,
 };
 
-static struct attribute_group lock_module_group = {
+static const struct attribute_group lock_module_group = {
 	.name = "lock_module",
 	.attrs = lock_module_attrs,
 };
@@ -711,14 +701,13 @@ static int gfs2_uevent(struct kset *kset, struct kobject *kobj,
 {
 	struct gfs2_sbd *sdp = container_of(kobj, struct gfs2_sbd, sd_kobj);
 	struct super_block *s = sdp->sd_vfs;
-	const u8 *uuid = s->s_uuid;
 
 	add_uevent_var(env, "LOCKTABLE=%s", sdp->sd_table_name);
 	add_uevent_var(env, "LOCKPROTO=%s", sdp->sd_proto_name);
 	if (!test_bit(SDF_NOJOURNALID, &sdp->sd_flags))
 		add_uevent_var(env, "JOURNALID=%d", sdp->sd_lockstruct.ls_jid);
-	if (gfs2_uuid_valid(uuid))
-		add_uevent_var(env, "UUID=%pUB", uuid);
+	if (!uuid_is_null(&s->s_uuid))
+		add_uevent_var(env, "UUID=%pUB", &s->s_uuid);
 	return 0;
 }
 
diff --git a/fs/gfs2/trans.c b/fs/gfs2/trans.c
index 0c1bde395062..affef3c066e0 100644
--- a/fs/gfs2/trans.c
+++ b/fs/gfs2/trans.c
@@ -48,7 +48,7 @@ int gfs2_trans_begin(struct gfs2_sbd *sdp, unsigned int blocks,
 	tr->tr_blocks = blocks;
 	tr->tr_revokes = revokes;
 	tr->tr_reserved = 1;
-	tr->tr_alloced = 1;
+	set_bit(TR_ALLOCED, &tr->tr_flags);
 	if (blocks)
 		tr->tr_reserved += 6 + blocks;
 	if (revokes)
@@ -78,7 +78,8 @@ static void gfs2_print_trans(const struct gfs2_trans *tr)
 {
 	pr_warn("Transaction created at: %pSR\n", (void *)tr->tr_ip);
 	pr_warn("blocks=%u revokes=%u reserved=%u touched=%u\n",
-		tr->tr_blocks, tr->tr_revokes, tr->tr_reserved, tr->tr_touched);
+		tr->tr_blocks, tr->tr_revokes, tr->tr_reserved,
+		test_bit(TR_TOUCHED, &tr->tr_flags));
 	pr_warn("Buf %u/%u Databuf %u/%u Revoke %u/%u\n",
 		tr->tr_num_buf_new, tr->tr_num_buf_rm,
 		tr->tr_num_databuf_new, tr->tr_num_databuf_rm,
@@ -89,12 +90,12 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
 {
 	struct gfs2_trans *tr = current->journal_info;
 	s64 nbuf;
-	int alloced = tr->tr_alloced;
+	int alloced = test_bit(TR_ALLOCED, &tr->tr_flags);
 
 	BUG_ON(!tr);
 	current->journal_info = NULL;
 
-	if (!tr->tr_touched) {
+	if (!test_bit(TR_TOUCHED, &tr->tr_flags)) {
 		gfs2_log_release(sdp, tr->tr_reserved);
 		if (alloced) {
 			kfree(tr);
@@ -112,8 +113,8 @@ void gfs2_trans_end(struct gfs2_sbd *sdp)
 		gfs2_print_trans(tr);
 
 	gfs2_log_commit(sdp, tr);
-	if (alloced && !tr->tr_attached)
-			kfree(tr);
+	if (alloced && !test_bit(TR_ATTACHED, &tr->tr_flags))
+		kfree(tr);
 	up_read(&sdp->sd_log_flush_lock);
 
 	if (sdp->sd_vfs->s_flags & MS_SYNCHRONOUS)
@@ -169,6 +170,10 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
 	}
 
 	lock_buffer(bh);
+	if (buffer_pinned(bh)) {
+		set_bit(TR_TOUCHED, &tr->tr_flags);
+		goto out;
+	}
 	gfs2_log_lock(sdp);
 	bd = bh->b_private;
 	if (bd == NULL) {
@@ -182,7 +187,7 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
 		gfs2_log_lock(sdp);
 	}
 	gfs2_assert(sdp, bd->bd_gl == gl);
-	tr->tr_touched = 1;
+	set_bit(TR_TOUCHED, &tr->tr_flags);
 	if (list_empty(&bd->bd_list)) {
 		set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
 		set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
@@ -191,45 +196,24 @@ void gfs2_trans_add_data(struct gfs2_glock *gl, struct buffer_head *bh)
 		list_add_tail(&bd->bd_list, &tr->tr_databuf);
 	}
 	gfs2_log_unlock(sdp);
+out:
 	unlock_buffer(bh);
 }
 
-static void meta_lo_add(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
-{
-	struct gfs2_meta_header *mh;
-	struct gfs2_trans *tr;
-	enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
-
-	tr = current->journal_info;
-	tr->tr_touched = 1;
-	if (!list_empty(&bd->bd_list))
-		return;
-	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
-	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
-	mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
-	if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
-		pr_err("Attempting to add uninitialised block to journal (inplace block=%lld)\n",
-		       (unsigned long long)bd->bd_bh->b_blocknr);
-		BUG();
-	}
-	if (unlikely(state == SFS_FROZEN)) {
-		printk(KERN_INFO "GFS2:adding buf while frozen\n");
-		gfs2_assert_withdraw(sdp, 0);
-	}
-	gfs2_pin(sdp, bd->bd_bh);
-	mh->__pad0 = cpu_to_be64(0);
-	mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
-	list_add(&bd->bd_list, &tr->tr_buf);
-	tr->tr_num_buf_new++;
-}
-
 void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
 {
 
 	struct gfs2_sbd *sdp = gl->gl_name.ln_sbd;
 	struct gfs2_bufdata *bd;
+	struct gfs2_meta_header *mh;
+	struct gfs2_trans *tr = current->journal_info;
+	enum gfs2_freeze_state state = atomic_read(&sdp->sd_freeze_state);
 
 	lock_buffer(bh);
+	if (buffer_pinned(bh)) {
+		set_bit(TR_TOUCHED, &tr->tr_flags);
+		goto out;
+	}
 	gfs2_log_lock(sdp);
 	bd = bh->b_private;
 	if (bd == NULL) {
@@ -245,8 +229,29 @@ void gfs2_trans_add_meta(struct gfs2_glock *gl, struct buffer_head *bh)
 		gfs2_log_lock(sdp);
 	}
 	gfs2_assert(sdp, bd->bd_gl == gl);
-	meta_lo_add(sdp, bd);
+	set_bit(TR_TOUCHED, &tr->tr_flags);
+	if (!list_empty(&bd->bd_list))
+		goto out_unlock;
+	set_bit(GLF_LFLUSH, &bd->bd_gl->gl_flags);
+	set_bit(GLF_DIRTY, &bd->bd_gl->gl_flags);
+	mh = (struct gfs2_meta_header *)bd->bd_bh->b_data;
+	if (unlikely(mh->mh_magic != cpu_to_be32(GFS2_MAGIC))) {
+		pr_err("Attempting to add uninitialised block to journal (inplace block=%lld)\n",
+		       (unsigned long long)bd->bd_bh->b_blocknr);
+		BUG();
+	}
+	if (unlikely(state == SFS_FROZEN)) {
+		printk(KERN_INFO "GFS2:adding buf while frozen\n");
+		gfs2_assert_withdraw(sdp, 0);
+	}
+	gfs2_pin(sdp, bd->bd_bh);
+	mh->__pad0 = cpu_to_be64(0);
+	mh->mh_jid = cpu_to_be32(sdp->sd_jdesc->jd_jid);
+	list_add(&bd->bd_list, &tr->tr_buf);
+	tr->tr_num_buf_new++;
+out_unlock:
 	gfs2_log_unlock(sdp);
+out:
 	unlock_buffer(bh);
 }
 
@@ -256,7 +261,7 @@ void gfs2_trans_add_revoke(struct gfs2_sbd *sdp, struct gfs2_bufdata *bd)
 
 	BUG_ON(!list_empty(&bd->bd_list));
 	gfs2_add_revoke(sdp, bd);
-	tr->tr_touched = 1;
+	set_bit(TR_TOUCHED, &tr->tr_flags);
 	tr->tr_num_revoke++;
 }
 
diff --git a/fs/gfs2/xattr.c b/fs/gfs2/xattr.c
index d87721aeb575..54179554c7d2 100644
--- a/fs/gfs2/xattr.c
+++ b/fs/gfs2/xattr.c
@@ -1327,8 +1327,8 @@ static int ea_dealloc_indirect(struct gfs2_inode *ip)
 	gfs2_rlist_alloc(&rlist, LM_ST_EXCLUSIVE);
 
 	for (x = 0; x < rlist.rl_rgrps; x++) {
-		struct gfs2_rgrpd *rgd;
-		rgd = rlist.rl_ghs[x].gh_gl->gl_object;
+		struct gfs2_rgrpd *rgd = gfs2_glock2rgrp(rlist.rl_ghs[x].gh_gl);
+
 		rg_blocks += rgd->rd_length;
 	}
 
diff --git a/fs/hfs/dir.c b/fs/hfs/dir.c
index 5de5c48b418d..75b254280ff6 100644
--- a/fs/hfs/dir.c
+++ b/fs/hfs/dir.c
@@ -169,7 +169,7 @@ static int hfs_readdir(struct file *file, struct dir_context *ctx)
 	 * Can be done after the list insertion; exclusion with
 	 * hfs_delete_cat() is provided by directory lock.
 	 */
-	memcpy(&rd->key, &fd.key, sizeof(struct hfs_cat_key));
+	memcpy(&rd->key, &fd.key->cat, sizeof(struct hfs_cat_key));
 out:
 	hfs_find_exit(&fd);
 	return err;
diff --git a/fs/hfs/extent.c b/fs/hfs/extent.c
index e33a0d36a93e..5d0182654580 100644
--- a/fs/hfs/extent.c
+++ b/fs/hfs/extent.c
@@ -485,8 +485,8 @@ void hfs_file_truncate(struct inode *inode)
 
 		/* XXX: Can use generic_cont_expand? */
 		size = inode->i_size - 1;
-		res = pagecache_write_begin(NULL, mapping, size+1, 0,
-				AOP_FLAG_UNINTERRUPTIBLE, &page, &fsdata);
+		res = pagecache_write_begin(NULL, mapping, size+1, 0, 0,
+					    &page, &fsdata);
 		if (!res) {
 			res = pagecache_write_end(NULL, mapping, size+1, 0, 0,
 					page, fsdata);
diff --git a/fs/hfs/inode.c b/fs/hfs/inode.c
index f776acf2378a..bfbba799430f 100644
--- a/fs/hfs/inode.c
+++ b/fs/hfs/inode.c
@@ -14,6 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/uio.h>
 #include <linux/xattr.h>
 
diff --git a/fs/hfs/mdb.c b/fs/hfs/mdb.c
index a3ec3ae7d347..482081bcdf70 100644
--- a/fs/hfs/mdb.c
+++ b/fs/hfs/mdb.c
@@ -38,7 +38,7 @@ static int hfs_get_last_session(struct super_block *sb,
 
 	/* default values */
 	*start = 0;
-	*size = sb->s_bdev->bd_inode->i_size >> 9;
+	*size = i_size_read(sb->s_bdev->bd_inode) >> 9;
 
 	if (HFS_SB(sb)->session >= 0) {
 		te.cdte_track = HFS_SB(sb)->session;
diff --git a/fs/hfsplus/extents.c b/fs/hfsplus/extents.c
index feca524ce2a5..a3eb640b4f8f 100644
--- a/fs/hfsplus/extents.c
+++ b/fs/hfsplus/extents.c
@@ -545,9 +545,8 @@ void hfsplus_file_truncate(struct inode *inode)
 		void *fsdata;
 		loff_t size = inode->i_size;
 
-		res = pagecache_write_begin(NULL, mapping, size, 0,
-						AOP_FLAG_UNINTERRUPTIBLE,
-						&page, &fsdata);
+		res = pagecache_write_begin(NULL, mapping, size, 0, 0,
+					    &page, &fsdata);
 		if (res)
 			return;
 		res = pagecache_write_end(NULL, mapping, size,
diff --git a/fs/hfsplus/inode.c b/fs/hfsplus/inode.c
index 2e796f8302ff..e8638d528195 100644
--- a/fs/hfsplus/inode.c
+++ b/fs/hfsplus/inode.c
@@ -14,6 +14,7 @@
 #include <linux/pagemap.h>
 #include <linux/mpage.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/uio.h>
 
 #include "hfsplus_fs.h"
diff --git a/fs/hfsplus/posix_acl.c b/fs/hfsplus/posix_acl.c
index 9b92058a1240..6bb5d7c42888 100644
--- a/fs/hfsplus/posix_acl.c
+++ b/fs/hfsplus/posix_acl.c
@@ -51,8 +51,8 @@ struct posix_acl *hfsplus_get_posix_acl(struct inode *inode, int type)
 	return acl;
 }
 
-int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl,
-		int type)
+static int __hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl,
+				   int type)
 {
 	int err;
 	char *xattr_name;
@@ -64,12 +64,6 @@ int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl,
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		xattr_name = XATTR_NAME_POSIX_ACL_ACCESS;
-		if (acl) {
-			err = posix_acl_update_mode(inode, &inode->i_mode, &acl);
-			if (err)
-				return err;
-		}
-		err = 0;
 		break;
 
 	case ACL_TYPE_DEFAULT:
@@ -105,6 +99,18 @@ end_set_acl:
 	return err;
 }
 
+int hfsplus_set_posix_acl(struct inode *inode, struct posix_acl *acl, int type)
+{
+	int err;
+
+	if (type == ACL_TYPE_ACCESS && acl) {
+		err = posix_acl_update_mode(inode, &inode->i_mode, &acl);
+		if (err)
+			return err;
+	}
+	return __hfsplus_set_posix_acl(inode, acl, type);
+}
+
 int hfsplus_init_posix_acl(struct inode *inode, struct inode *dir)
 {
 	int err = 0;
@@ -122,15 +128,15 @@ int hfsplus_init_posix_acl(struct inode *inode, struct inode *dir)
 		return err;
 
 	if (default_acl) {
-		err = hfsplus_set_posix_acl(inode, default_acl,
-					    ACL_TYPE_DEFAULT);
+		err = __hfsplus_set_posix_acl(inode, default_acl,
+					      ACL_TYPE_DEFAULT);
 		posix_acl_release(default_acl);
 	}
 
 	if (acl) {
 		if (!err)
-			err = hfsplus_set_posix_acl(inode, acl,
-						    ACL_TYPE_ACCESS);
+			err = __hfsplus_set_posix_acl(inode, acl,
+						      ACL_TYPE_ACCESS);
 		posix_acl_release(acl);
 	}
 	return err;
diff --git a/fs/hfsplus/wrapper.c b/fs/hfsplus/wrapper.c
index ebb85e5f6549..e254fa0f0697 100644
--- a/fs/hfsplus/wrapper.c
+++ b/fs/hfsplus/wrapper.c
@@ -132,7 +132,7 @@ static int hfsplus_get_last_session(struct super_block *sb,
 
 	/* default values */
 	*start = 0;
-	*size = sb->s_bdev->bd_inode->i_size >> 9;
+	*size = i_size_read(sb->s_bdev->bd_inode) >> 9;
 
 	if (HFSPLUS_SB(sb)->session >= 0) {
 		te.cdte_track = HFSPLUS_SB(sb)->session;
diff --git a/fs/hpfs/hpfs_fn.h b/fs/hpfs/hpfs_fn.h
index aebb78f9e47f..d352f3a6af7f 100644
--- a/fs/hpfs/hpfs_fn.h
+++ b/fs/hpfs/hpfs_fn.h
@@ -18,7 +18,7 @@
 #include <linux/pagemap.h>
 #include <linux/buffer_head.h>
 #include <linux/slab.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/blkdev.h>
 #include <asm/unaligned.h>
 
diff --git a/fs/hugetlbfs/inode.c b/fs/hugetlbfs/inode.c
index 54de77e78775..28d2753be094 100644
--- a/fs/hugetlbfs/inode.c
+++ b/fs/hugetlbfs/inode.c
@@ -11,7 +11,7 @@
 
 #include <linux/thread_info.h>
 #include <asm/current.h>
-#include <linux/sched.h>		/* remove ASAP */
+#include <linux/sched/signal.h>		/* remove ASAP */
 #include <linux/falloc.h>
 #include <linux/fs.h>
 #include <linux/mount.h>
@@ -46,13 +46,13 @@ static const struct inode_operations hugetlbfs_dir_inode_operations;
 static const struct inode_operations hugetlbfs_inode_operations;
 
 struct hugetlbfs_config {
-	kuid_t   uid;
-	kgid_t   gid;
-	umode_t mode;
-	long	max_hpages;
-	long	nr_inodes;
-	struct hstate *hstate;
-	long    min_hpages;
+	struct hstate		*hstate;
+	long			max_hpages;
+	long			nr_inodes;
+	long			min_hpages;
+	kuid_t			uid;
+	kgid_t			gid;
+	umode_t			mode;
 };
 
 struct hugetlbfs_inode_info {
@@ -136,17 +136,26 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 	vma->vm_flags |= VM_HUGETLB | VM_DONTEXPAND;
 	vma->vm_ops = &hugetlb_vm_ops;
 
+	/*
+	 * Offset passed to mmap (before page shift) could have been
+	 * negative when represented as a (l)off_t.
+	 */
+	if (((loff_t)vma->vm_pgoff << PAGE_SHIFT) < 0)
+		return -EINVAL;
+
 	if (vma->vm_pgoff & (~huge_page_mask(h) >> PAGE_SHIFT))
 		return -EINVAL;
 
 	vma_len = (loff_t)(vma->vm_end - vma->vm_start);
+	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
+	/* check for overflow */
+	if (len < vma_len)
+		return -EINVAL;
 
 	inode_lock(inode);
 	file_accessed(file);
 
 	ret = -ENOMEM;
-	len = vma_len + ((loff_t)vma->vm_pgoff << PAGE_SHIFT);
-
 	if (hugetlb_reserve_pages(inode,
 				vma->vm_pgoff >> huge_page_order(h),
 				len >> huge_page_shift(h), vma,
@@ -155,7 +164,7 @@ static int hugetlbfs_file_mmap(struct file *file, struct vm_area_struct *vma)
 
 	ret = 0;
 	if (vma->vm_flags & VM_WRITE && inode->i_size < len)
-		inode->i_size = len;
+		i_size_write(inode, len);
 out:
 	inode_unlock(inode);
 
@@ -191,7 +200,7 @@ hugetlb_get_unmapped_area(struct file *file, unsigned long addr,
 		addr = ALIGN(addr, huge_page_size(h));
 		vma = find_vma(mm, addr);
 		if (TASK_SIZE - len >= addr &&
-		    (!vma || addr + len <= vma->vm_start))
+		    (!vma || addr + len <= vm_start_gap(vma)))
 			return addr;
 	}
 
@@ -695,14 +704,11 @@ static struct inode *hugetlbfs_get_root(struct super_block *sb,
 
 	inode = new_inode(sb);
 	if (inode) {
-		struct hugetlbfs_inode_info *info;
 		inode->i_ino = get_next_ino();
 		inode->i_mode = S_IFDIR | config->mode;
 		inode->i_uid = config->uid;
 		inode->i_gid = config->gid;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
-		info = HUGETLBFS_I(inode);
-		mpol_shared_policy_init(&info->policy, NULL);
 		inode->i_op = &hugetlbfs_dir_inode_operations;
 		inode->i_fop = &simple_dir_operations;
 		/* directory inodes start off with i_nlink == 2 (for "." entry) */
@@ -733,7 +739,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 
 	inode = new_inode(sb);
 	if (inode) {
-		struct hugetlbfs_inode_info *info;
 		inode->i_ino = get_next_ino();
 		inode_init_owner(inode, dir, mode);
 		lockdep_set_class(&inode->i_mapping->i_mmap_rwsem,
@@ -741,15 +746,6 @@ static struct inode *hugetlbfs_get_inode(struct super_block *sb,
 		inode->i_mapping->a_ops = &hugetlbfs_aops;
 		inode->i_atime = inode->i_mtime = inode->i_ctime = current_time(inode);
 		inode->i_mapping->private_data = resv_map;
-		info = HUGETLBFS_I(inode);
-		/*
-		 * The policy is initialized here even if we are creating a
-		 * private inode because initialization simply creates an
-		 * an empty rb tree and calls rwlock_init(), later when we
-		 * call mpol_free_shared_policy() it will just return because
-		 * the rb tree will still be empty.
-		 */
-		mpol_shared_policy_init(&info->policy, NULL);
 		switch (mode & S_IFMT) {
 		default:
 			init_special_inode(inode, mode, dev);
@@ -855,6 +851,56 @@ static int hugetlbfs_migrate_page(struct address_space *mapping,
 	return MIGRATEPAGE_SUCCESS;
 }
 
+static int hugetlbfs_error_remove_page(struct address_space *mapping,
+				struct page *page)
+{
+	struct inode *inode = mapping->host;
+
+	remove_huge_page(page);
+	hugetlb_fix_reserve_counts(inode);
+	return 0;
+}
+
+/*
+ * Display the mount options in /proc/mounts.
+ */
+static int hugetlbfs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(root->d_sb);
+	struct hugepage_subpool *spool = sbinfo->spool;
+	unsigned long hpage_size = huge_page_size(sbinfo->hstate);
+	unsigned hpage_shift = huge_page_shift(sbinfo->hstate);
+	char mod;
+
+	if (!uid_eq(sbinfo->uid, GLOBAL_ROOT_UID))
+		seq_printf(m, ",uid=%u",
+			   from_kuid_munged(&init_user_ns, sbinfo->uid));
+	if (!gid_eq(sbinfo->gid, GLOBAL_ROOT_GID))
+		seq_printf(m, ",gid=%u",
+			   from_kgid_munged(&init_user_ns, sbinfo->gid));
+	if (sbinfo->mode != 0755)
+		seq_printf(m, ",mode=%o", sbinfo->mode);
+	if (sbinfo->max_inodes != -1)
+		seq_printf(m, ",nr_inodes=%lu", sbinfo->max_inodes);
+
+	hpage_size /= 1024;
+	mod = 'K';
+	if (hpage_size >= 1024) {
+		hpage_size /= 1024;
+		mod = 'M';
+	}
+	seq_printf(m, ",pagesize=%lu%c", hpage_size, mod);
+	if (spool) {
+		if (spool->max_hpages != -1)
+			seq_printf(m, ",size=%llu",
+				   (unsigned long long)spool->max_hpages << hpage_shift);
+		if (spool->min_hpages != -1)
+			seq_printf(m, ",min_size=%llu",
+				   (unsigned long long)spool->min_hpages << hpage_shift);
+	}
+	return 0;
+}
+
 static int hugetlbfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 {
 	struct hugetlbfs_sb_info *sbinfo = HUGETLBFS_SB(dentry->d_sb);
@@ -937,6 +983,18 @@ static struct inode *hugetlbfs_alloc_inode(struct super_block *sb)
 		hugetlbfs_inc_free_inodes(sbinfo);
 		return NULL;
 	}
+
+	/*
+	 * Any time after allocation, hugetlbfs_destroy_inode can be called
+	 * for the inode.  mpol_free_shared_policy is unconditionally called
+	 * as part of hugetlbfs_destroy_inode.  So, initialize policy here
+	 * in case of a quick call to destroy.
+	 *
+	 * Note that the policy is initialized even if we are creating a
+	 * private inode.  This simplifies hugetlbfs_destroy_inode.
+	 */
+	mpol_shared_policy_init(&p->policy, NULL);
+
 	return &p->vfs_inode;
 }
 
@@ -958,6 +1016,7 @@ static const struct address_space_operations hugetlbfs_aops = {
 	.write_end	= hugetlbfs_write_end,
 	.set_page_dirty	= hugetlbfs_set_page_dirty,
 	.migratepage    = hugetlbfs_migrate_page,
+	.error_remove_page	= hugetlbfs_error_remove_page,
 };
 
 
@@ -1000,19 +1059,19 @@ static const struct super_operations hugetlbfs_ops = {
 	.evict_inode	= hugetlbfs_evict_inode,
 	.statfs		= hugetlbfs_statfs,
 	.put_super	= hugetlbfs_put_super,
-	.show_options	= generic_show_options,
+	.show_options	= hugetlbfs_show_options,
 };
 
-enum { NO_SIZE, SIZE_STD, SIZE_PERCENT };
+enum hugetlbfs_size_type { NO_SIZE, SIZE_STD, SIZE_PERCENT };
 
 /*
  * Convert size option passed from command line to number of huge pages
  * in the pool specified by hstate.  Size option could be in bytes
  * (val_type == SIZE_STD) or percentage of the pool (val_type == SIZE_PERCENT).
  */
-static long long
+static long
 hugetlbfs_size_to_hpages(struct hstate *h, unsigned long long size_opt,
-								int val_type)
+			 enum hugetlbfs_size_type val_type)
 {
 	if (val_type == NO_SIZE)
 		return -1;
@@ -1034,7 +1093,7 @@ hugetlbfs_parse_options(char *options, struct hugetlbfs_config *pconfig)
 	substring_t args[MAX_OPT_ARGS];
 	int option;
 	unsigned long long max_size_opt = 0, min_size_opt = 0;
-	int max_val_type = NO_SIZE, min_val_type = NO_SIZE;
+	enum hugetlbfs_size_type max_val_type = NO_SIZE, min_val_type = NO_SIZE;
 
 	if (!options)
 		return 0;
@@ -1148,8 +1207,6 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
 	struct hugetlbfs_config config;
 	struct hugetlbfs_sb_info *sbinfo;
 
-	save_mount_options(sb, data);
-
 	config.max_hpages = -1; /* No limit on size by default */
 	config.nr_inodes = -1; /* No limit on number of inodes by default */
 	config.uid = current_fsuid();
@@ -1170,6 +1227,10 @@ hugetlbfs_fill_super(struct super_block *sb, void *data, int silent)
 	sbinfo->max_inodes = config.nr_inodes;
 	sbinfo->free_inodes = config.nr_inodes;
 	sbinfo->spool = NULL;
+	sbinfo->uid = config.uid;
+	sbinfo->gid = config.gid;
+	sbinfo->mode = config.mode;
+
 	/*
 	 * Allocate and initialize subpool if maximum or minimum size is
 	 * specified.  Any needed reservations (for minimim size) are taken
diff --git a/fs/inode.c b/fs/inode.c
index 88110fd0b282..50370599e371 100644
--- a/fs/inode.c
+++ b/fs/inode.c
@@ -119,7 +119,7 @@ static int no_open(struct inode *inode, struct file *file)
 }
 
 /**
- * inode_init_always - perform inode structure intialisation
+ * inode_init_always - perform inode structure initialisation
  * @sb: superblock inode belongs to
  * @inode: inode to initialise
  *
@@ -146,6 +146,7 @@ int inode_init_always(struct super_block *sb, struct inode *inode)
 	i_gid_write(inode, 0);
 	atomic_set(&inode->i_writecount, 0);
 	inode->i_size = 0;
+	inode->i_write_hint = WRITE_LIFE_NOT_SET;
 	inode->i_blocks = 0;
 	inode->i_bytes = 0;
 	inode->i_generation = 0;
@@ -371,9 +372,6 @@ void inode_init_once(struct inode *inode)
 	INIT_LIST_HEAD(&inode->i_lru);
 	address_space_init_once(&inode->i_data);
 	i_size_ordered_init(inode);
-#ifdef CONFIG_FSNOTIFY
-	INIT_HLIST_HEAD(&inode->i_fsnotify_marks);
-#endif
 }
 EXPORT_SYMBOL(inode_init_once);
 
@@ -405,6 +403,8 @@ static void inode_lru_list_add(struct inode *inode)
 {
 	if (list_lru_add(&inode->i_sb->s_inode_lru, &inode->i_lru))
 		this_cpu_inc(nr_unused);
+	else
+		inode->i_state |= I_REFERENCED;
 }
 
 /*
@@ -1492,7 +1492,6 @@ static void iput_final(struct inode *inode)
 		drop = generic_drop_inode(inode);
 
 	if (!drop && (sb->s_flags & MS_ACTIVE)) {
-		inode->i_state |= I_REFERENCED;
 		inode_add_lru(inode);
 		spin_unlock(&inode->i_lock);
 		return;
@@ -1893,11 +1892,11 @@ static void __wait_on_freeing_inode(struct inode *inode)
 	wait_queue_head_t *wq;
 	DEFINE_WAIT_BIT(wait, &inode->i_state, __I_NEW);
 	wq = bit_waitqueue(&inode->i_state, __I_NEW);
-	prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+	prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
 	spin_unlock(&inode->i_lock);
 	spin_unlock(&inode_hash_lock);
 	schedule();
-	finish_wait(wq, &wait.wait);
+	finish_wait(wq, &wait.wq_entry);
 	spin_lock(&inode_hash_lock);
 }
 
@@ -1916,8 +1915,6 @@ __setup("ihash_entries=", set_ihash_entries);
  */
 void __init inode_init_early(void)
 {
-	unsigned int loop;
-
 	/* If hashes are distributed across NUMA nodes, defer
 	 * hash allocation until vmalloc space is available.
 	 */
@@ -1929,20 +1926,15 @@ void __init inode_init_early(void)
 					sizeof(struct hlist_head),
 					ihash_entries,
 					14,
-					HASH_EARLY,
+					HASH_EARLY | HASH_ZERO,
 					&i_hash_shift,
 					&i_hash_mask,
 					0,
 					0);
-
-	for (loop = 0; loop < (1U << i_hash_shift); loop++)
-		INIT_HLIST_HEAD(&inode_hashtable[loop]);
 }
 
 void __init inode_init(void)
 {
-	unsigned int loop;
-
 	/* inode slab cache */
 	inode_cachep = kmem_cache_create("inode_cache",
 					 sizeof(struct inode),
@@ -1960,14 +1952,11 @@ void __init inode_init(void)
 					sizeof(struct hlist_head),
 					ihash_entries,
 					14,
-					0,
+					HASH_ZERO,
 					&i_hash_shift,
 					&i_hash_mask,
 					0,
 					0);
-
-	for (loop = 0; loop < (1U << i_hash_shift); loop++)
-		INIT_HLIST_HEAD(&inode_hashtable[loop]);
 }
 
 void init_special_inode(struct inode *inode, umode_t mode, dev_t rdev)
@@ -2025,7 +2014,7 @@ bool inode_owner_or_capable(const struct inode *inode)
 		return true;
 
 	ns = current_user_ns();
-	if (ns_capable(ns, CAP_FOWNER) && kuid_has_mapping(ns, inode->i_uid))
+	if (kuid_has_mapping(ns, inode->i_uid) && ns_capable(ns, CAP_FOWNER))
 		return true;
 	return false;
 }
@@ -2040,11 +2029,11 @@ static void __inode_dio_wait(struct inode *inode)
 	DEFINE_WAIT_BIT(q, &inode->i_state, __I_DIO_WAKEUP);
 
 	do {
-		prepare_to_wait(wq, &q.wait, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(wq, &q.wq_entry, TASK_UNINTERRUPTIBLE);
 		if (atomic_read(&inode->i_dio_count))
 			schedule();
 	} while (atomic_read(&inode->i_dio_count));
-	finish_wait(wq, &q.wait);
+	finish_wait(wq, &q.wq_entry);
 }
 
 /**
diff --git a/fs/internal.h b/fs/internal.h
index b63cf3af2dc2..9676fe11c093 100644
--- a/fs/internal.h
+++ b/fs/internal.h
@@ -108,8 +108,6 @@ extern struct file *do_filp_open(int dfd, struct filename *pathname,
 extern struct file *do_file_open_root(struct dentry *, struct vfsmount *,
 		const char *, const struct open_flags *);
 
-extern long do_handle_open(int mountdirfd,
-			   struct file_handle __user *ufh, int open_flag);
 extern int open_check_o_direct(struct file *f);
 extern int vfs_open(const struct path *, struct file *, const struct cred *);
 extern struct file *filp_clone_open(struct file *);
@@ -128,8 +126,6 @@ static inline bool atime_needs_update_rcu(const struct path *path,
 	return __atime_needs_update(path, inode, true);
 }
 
-extern bool atime_needs_update_rcu(const struct path *, struct inode *);
-
 /*
  * fs-writeback.c
  */
@@ -182,7 +178,7 @@ typedef loff_t (*iomap_actor_t)(struct inode *inode, loff_t pos, loff_t len,
 		void *data, struct iomap *iomap);
 
 loff_t iomap_apply(struct inode *inode, loff_t pos, loff_t length,
-		unsigned flags, struct iomap_ops *ops, void *data,
+		unsigned flags, const struct iomap_ops *ops, void *data,
 		iomap_actor_t actor);
 
 /* direct-io.c: */
diff --git a/fs/ioctl.c b/fs/ioctl.c
index cb9b02940805..569db68d02b3 100644
--- a/fs/ioctl.c
+++ b/fs/ioctl.c
@@ -15,6 +15,8 @@
 #include <linux/writeback.h>
 #include <linux/buffer_head.h>
 #include <linux/falloc.h>
+#include <linux/sched/signal.h>
+
 #include "internal.h"
 
 #include <asm/ioctls.h>
diff --git a/fs/iomap.c b/fs/iomap.c
index a51cb4c07d4d..039266128b7f 100644
--- a/fs/iomap.c
+++ b/fs/iomap.c
@@ -26,6 +26,8 @@
 #include <linux/buffer_head.h>
 #include <linux/task_io_accounting_ops.h>
 #include <linux/dax.h>
+#include <linux/sched/signal.h>
+
 #include "internal.h"
 
 /*
@@ -41,7 +43,7 @@
  */
 loff_t
 iomap_apply(struct inode *inode, loff_t pos, loff_t length, unsigned flags,
-		struct iomap_ops *ops, void *data, iomap_actor_t actor)
+		const struct iomap_ops *ops, void *data, iomap_actor_t actor)
 {
 	struct iomap iomap = { 0 };
 	loff_t written = 0, ret;
@@ -156,12 +158,6 @@ iomap_write_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 	ssize_t written = 0;
 	unsigned int flags = AOP_FLAG_NOFS;
 
-	/*
-	 * Copies from kernel address space cannot fail (NFSD is a big user).
-	 */
-	if (!iter_is_iovec(i))
-		flags |= AOP_FLAG_UNINTERRUPTIBLE;
-
 	do {
 		struct page *page;
 		unsigned long offset;	/* Offset into pagecache page */
@@ -235,7 +231,7 @@ again:
 
 ssize_t
 iomap_file_buffered_write(struct kiocb *iocb, struct iov_iter *iter,
-		struct iomap_ops *ops)
+		const struct iomap_ops *ops)
 {
 	struct inode *inode = iocb->ki_filp->f_mapping->host;
 	loff_t pos = iocb->ki_pos, ret = 0, written = 0;
@@ -289,8 +285,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 			return PTR_ERR(rpage);
 
 		status = iomap_write_begin(inode, pos, bytes,
-				AOP_FLAG_NOFS | AOP_FLAG_UNINTERRUPTIBLE,
-				&page, iomap);
+					   AOP_FLAG_NOFS, &page, iomap);
 		put_page(rpage);
 		if (unlikely(status))
 			return status;
@@ -318,7 +313,7 @@ iomap_dirty_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 
 int
 iomap_file_dirty(struct inode *inode, loff_t pos, loff_t len,
-		struct iomap_ops *ops)
+		const struct iomap_ops *ops)
 {
 	loff_t ret;
 
@@ -341,8 +336,8 @@ static int iomap_zero(struct inode *inode, loff_t pos, unsigned offset,
 	struct page *page;
 	int status;
 
-	status = iomap_write_begin(inode, pos, bytes,
-			AOP_FLAG_UNINTERRUPTIBLE | AOP_FLAG_NOFS, &page, iomap);
+	status = iomap_write_begin(inode, pos, bytes, AOP_FLAG_NOFS, &page,
+				   iomap);
 	if (status)
 		return status;
 
@@ -358,7 +353,8 @@ static int iomap_dax_zero(loff_t pos, unsigned offset, unsigned bytes,
 	sector_t sector = iomap->blkno +
 		(((pos & ~(PAGE_SIZE - 1)) - iomap->offset) >> 9);
 
-	return __dax_zero_page_range(iomap->bdev, sector, offset, bytes);
+	return __dax_zero_page_range(iomap->bdev, iomap->dax_dev, sector,
+			offset, bytes);
 }
 
 static loff_t
@@ -398,7 +394,7 @@ iomap_zero_range_actor(struct inode *inode, loff_t pos, loff_t count,
 
 int
 iomap_zero_range(struct inode *inode, loff_t pos, loff_t len, bool *did_zero,
-		struct iomap_ops *ops)
+		const struct iomap_ops *ops)
 {
 	loff_t ret;
 
@@ -418,10 +414,10 @@ EXPORT_SYMBOL_GPL(iomap_zero_range);
 
 int
 iomap_truncate_page(struct inode *inode, loff_t pos, bool *did_zero,
-		struct iomap_ops *ops)
+		const struct iomap_ops *ops)
 {
-	unsigned blocksize = (1 << inode->i_blkbits);
-	unsigned off = pos & (blocksize - 1);
+	unsigned int blocksize = i_blocksize(inode);
+	unsigned int off = pos & (blocksize - 1);
 
 	/* Block boundary? Nothing to do */
 	if (!off)
@@ -445,11 +441,10 @@ iomap_page_mkwrite_actor(struct inode *inode, loff_t pos, loff_t length,
 	return length;
 }
 
-int iomap_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf,
-		struct iomap_ops *ops)
+int iomap_page_mkwrite(struct vm_fault *vmf, const struct iomap_ops *ops)
 {
 	struct page *page = vmf->page;
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	unsigned long length;
 	loff_t offset, size;
 	ssize_t ret;
@@ -545,7 +540,7 @@ iomap_fiemap_actor(struct inode *inode, loff_t pos, loff_t length, void *data,
 }
 
 int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
-		loff_t start, loff_t len, struct iomap_ops *ops)
+		loff_t start, loff_t len, const struct iomap_ops *ops)
 {
 	struct fiemap_ctx ctx;
 	loff_t ret;
@@ -589,6 +584,100 @@ int iomap_fiemap(struct inode *inode, struct fiemap_extent_info *fi,
 }
 EXPORT_SYMBOL_GPL(iomap_fiemap);
 
+static loff_t
+iomap_seek_hole_actor(struct inode *inode, loff_t offset, loff_t length,
+		      void *data, struct iomap *iomap)
+{
+	switch (iomap->type) {
+	case IOMAP_UNWRITTEN:
+		offset = page_cache_seek_hole_data(inode, offset, length,
+						   SEEK_HOLE);
+		if (offset < 0)
+			return length;
+		/* fall through */
+	case IOMAP_HOLE:
+		*(loff_t *)data = offset;
+		return 0;
+	default:
+		return length;
+	}
+}
+
+loff_t
+iomap_seek_hole(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
+{
+	loff_t size = i_size_read(inode);
+	loff_t length = size - offset;
+	loff_t ret;
+
+	/* Nothing to be found before or beyond the end of the file. */
+	if (offset < 0 || offset >= size)
+		return -ENXIO;
+
+	while (length > 0) {
+		ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops,
+				  &offset, iomap_seek_hole_actor);
+		if (ret < 0)
+			return ret;
+		if (ret == 0)
+			break;
+
+		offset += ret;
+		length -= ret;
+	}
+
+	return offset;
+}
+EXPORT_SYMBOL_GPL(iomap_seek_hole);
+
+static loff_t
+iomap_seek_data_actor(struct inode *inode, loff_t offset, loff_t length,
+		      void *data, struct iomap *iomap)
+{
+	switch (iomap->type) {
+	case IOMAP_HOLE:
+		return length;
+	case IOMAP_UNWRITTEN:
+		offset = page_cache_seek_hole_data(inode, offset, length,
+						   SEEK_DATA);
+		if (offset < 0)
+			return length;
+		/*FALLTHRU*/
+	default:
+		*(loff_t *)data = offset;
+		return 0;
+	}
+}
+
+loff_t
+iomap_seek_data(struct inode *inode, loff_t offset, const struct iomap_ops *ops)
+{
+	loff_t size = i_size_read(inode);
+	loff_t length = size - offset;
+	loff_t ret;
+
+	/* Nothing to be found before or beyond the end of the file. */
+	if (offset < 0 || offset >= size)
+		return -ENXIO;
+
+	while (length > 0) {
+		ret = iomap_apply(inode, offset, length, IOMAP_REPORT, ops,
+				  &offset, iomap_seek_data_actor);
+		if (ret < 0)
+			return ret;
+		if (ret == 0)
+			break;
+
+		offset += ret;
+		length -= ret;
+	}
+
+	if (length <= 0)
+		return -ENXIO;
+	return offset;
+}
+EXPORT_SYMBOL_GPL(iomap_seek_data);
+
 /*
  * Private flags for iomap_dio, must not overlap with the public ones in
  * iomap.h:
@@ -677,8 +766,8 @@ static void iomap_dio_bio_end_io(struct bio *bio)
 	struct iomap_dio *dio = bio->bi_private;
 	bool should_dirty = (dio->flags & IOMAP_DIO_DIRTY);
 
-	if (bio->bi_error)
-		iomap_dio_set_error(dio, bio->bi_error);
+	if (bio->bi_status)
+		iomap_dio_set_error(dio, blk_status_to_errno(bio->bi_status));
 
 	if (atomic_dec_and_test(&dio->ref)) {
 		if (is_sync_kiocb(dio->iocb)) {
@@ -736,9 +825,9 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		void *data, struct iomap *iomap)
 {
 	struct iomap_dio *dio = data;
-	unsigned blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev));
-	unsigned fs_block_size = (1 << inode->i_blkbits), pad;
-	unsigned align = iov_iter_alignment(dio->submit.iter);
+	unsigned int blkbits = blksize_bits(bdev_logical_block_size(iomap->bdev));
+	unsigned int fs_block_size = i_blocksize(inode), pad;
+	unsigned int align = iov_iter_alignment(dio->submit.iter);
 	struct iov_iter iter;
 	struct bio *bio;
 	bool need_zeroout = false;
@@ -798,6 +887,7 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 		bio->bi_bdev = iomap->bdev;
 		bio->bi_iter.bi_sector =
 			iomap->blkno + ((pos - iomap->offset) >> 9);
+		bio->bi_write_hint = dio->iocb->ki_hint;
 		bio->bi_private = dio;
 		bio->bi_end_io = iomap_dio_bio_end_io;
 
@@ -839,13 +929,14 @@ iomap_dio_actor(struct inode *inode, loff_t pos, loff_t length,
 }
 
 ssize_t
-iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops,
-		iomap_dio_end_io_t end_io)
+iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter,
+		const struct iomap_ops *ops, iomap_dio_end_io_t end_io)
 {
 	struct address_space *mapping = iocb->ki_filp->f_mapping;
 	struct inode *inode = file_inode(iocb->ki_filp);
 	size_t count = iov_iter_count(iter);
-	loff_t pos = iocb->ki_pos, end = iocb->ki_pos + count - 1, ret = 0;
+	loff_t pos = iocb->ki_pos, start = pos;
+	loff_t end = iocb->ki_pos + count - 1, ret = 0;
 	unsigned int flags = IOMAP_DIRECT;
 	struct blk_plug plug;
 	struct iomap_dio *dio;
@@ -885,17 +976,23 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops,
 		flags |= IOMAP_WRITE;
 	}
 
-	if (mapping->nrpages) {
-		ret = filemap_write_and_wait_range(mapping, iocb->ki_pos, end);
-		if (ret)
+	if (iocb->ki_flags & IOCB_NOWAIT) {
+		if (filemap_range_has_page(mapping, start, end)) {
+			ret = -EAGAIN;
 			goto out_free_dio;
-
-		ret = invalidate_inode_pages2_range(mapping,
-				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
-		ret = 0;
+		}
+		flags |= IOMAP_NOWAIT;
 	}
 
+	ret = filemap_write_and_wait_range(mapping, start, end);
+	if (ret)
+		goto out_free_dio;
+
+	ret = invalidate_inode_pages2_range(mapping,
+			start >> PAGE_SHIFT, end >> PAGE_SHIFT);
+	WARN_ON_ONCE(ret);
+	ret = 0;
+
 	inode_dio_begin(inode);
 
 	blk_start_plug(&plug);
@@ -909,6 +1006,9 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops,
 			break;
 		}
 		pos += ret;
+
+		if (iov_iter_rw(iter) == READ && pos >= dio->i_size)
+			break;
 	} while ((count = iov_iter_count(iter)) > 0);
 	blk_finish_plug(&plug);
 
@@ -940,6 +1040,8 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops,
 		__set_current_state(TASK_RUNNING);
 	}
 
+	ret = iomap_dio_complete(dio);
+
 	/*
 	 * Try again to invalidate clean pages which might have been cached by
 	 * non-direct readahead, or faulted in by get_user_pages() if the source
@@ -947,13 +1049,13 @@ iomap_dio_rw(struct kiocb *iocb, struct iov_iter *iter, struct iomap_ops *ops,
 	 * one is a pretty crazy thing to do, so we don't support it 100%.  If
 	 * this invalidation fails, tough, the write still worked...
 	 */
-	if (iov_iter_rw(iter) == WRITE && mapping->nrpages) {
-		ret = invalidate_inode_pages2_range(mapping,
-				iocb->ki_pos >> PAGE_SHIFT, end >> PAGE_SHIFT);
-		WARN_ON_ONCE(ret);
+	if (iov_iter_rw(iter) == WRITE) {
+		int err = invalidate_inode_pages2_range(mapping,
+				start >> PAGE_SHIFT, end >> PAGE_SHIFT);
+		WARN_ON_ONCE(err);
 	}
 
-	return iomap_dio_complete(dio);
+	return ret;
 
 out_free_dio:
 	kfree(dio);
diff --git a/fs/isofs/inode.c b/fs/isofs/inode.c
index 871c8b392099..217a5e7815da 100644
--- a/fs/isofs/inode.c
+++ b/fs/isofs/inode.c
@@ -15,6 +15,7 @@
 #include <linux/module.h>
 
 #include <linux/slab.h>
+#include <linux/cred.h>
 #include <linux/nls.h>
 #include <linux/ctype.h>
 #include <linux/statfs.h>
@@ -22,6 +23,7 @@
 #include <linux/parser.h>
 #include <linux/mpage.h>
 #include <linux/user_namespace.h>
+#include <linux/seq_file.h>
 
 #include "isofs.h"
 #include "zisofs.h"
@@ -56,6 +58,7 @@ static void isofs_put_super(struct super_block *sb)
 
 static int isofs_read_inode(struct inode *, int relocated);
 static int isofs_statfs (struct dentry *, struct kstatfs *);
+static int isofs_show_options(struct seq_file *, struct dentry *);
 
 static struct kmem_cache *isofs_inode_cachep;
 
@@ -122,7 +125,7 @@ static const struct super_operations isofs_sops = {
 	.put_super	= isofs_put_super,
 	.statfs		= isofs_statfs,
 	.remount_fs	= isofs_remount,
-	.show_options	= generic_show_options,
+	.show_options	= isofs_show_options,
 };
 
 
@@ -407,7 +410,11 @@ static int parse_options(char *options, struct iso9660_options *popt)
 			if (match_int(&args[0], &option))
 				return 0;
 			n = option;
-			if (n > 99)
+			/*
+			 * Track numbers are supposed to be in range 1-99, the
+			 * mount option starts indexing at 0.
+			 */
+			if (n >= 99)
 				return 0;
 			popt->session = n + 1;
 			break;
@@ -472,6 +479,48 @@ static int parse_options(char *options, struct iso9660_options *popt)
 }
 
 /*
+ * Display the mount options in /proc/mounts.
+ */
+static int isofs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct isofs_sb_info *sbi = ISOFS_SB(root->d_sb);
+
+	if (!sbi->s_rock)		seq_puts(m, ",norock");
+	else if (!sbi->s_joliet_level)	seq_puts(m, ",nojoliet");
+	if (sbi->s_cruft)		seq_puts(m, ",cruft");
+	if (sbi->s_hide)		seq_puts(m, ",hide");
+	if (sbi->s_nocompress)		seq_puts(m, ",nocompress");
+	if (sbi->s_overriderockperm)	seq_puts(m, ",overriderockperm");
+	if (sbi->s_showassoc)		seq_puts(m, ",showassoc");
+	if (sbi->s_utf8)		seq_puts(m, ",utf8");
+
+	if (sbi->s_check)		seq_printf(m, ",check=%c", sbi->s_check);
+	if (sbi->s_mapping)		seq_printf(m, ",map=%c", sbi->s_mapping);
+	if (sbi->s_session != 255)	seq_printf(m, ",session=%u", sbi->s_session - 1);
+	if (sbi->s_sbsector != -1)	seq_printf(m, ",sbsector=%u", sbi->s_sbsector);
+
+	if (root->d_sb->s_blocksize != 1024)
+		seq_printf(m, ",blocksize=%lu", root->d_sb->s_blocksize);
+
+	if (sbi->s_uid_set)
+		seq_printf(m, ",uid=%u",
+			   from_kuid_munged(&init_user_ns, sbi->s_uid));
+	if (sbi->s_gid_set)
+		seq_printf(m, ",gid=%u",
+			   from_kgid_munged(&init_user_ns, sbi->s_gid));
+
+	if (sbi->s_dmode != ISOFS_INVALID_MODE)
+		seq_printf(m, ",dmode=%o", sbi->s_dmode);
+	if (sbi->s_fmode != ISOFS_INVALID_MODE)
+		seq_printf(m, ",fmode=%o", sbi->s_fmode);
+
+	if (sbi->s_nls_iocharset &&
+	    strcmp(sbi->s_nls_iocharset->charset, CONFIG_NLS_DEFAULT) != 0)
+		seq_printf(m, ",iocharset=%s", sbi->s_nls_iocharset->charset);
+	return 0;
+}
+
+/*
  * look if the driver can tell the multi session redirection value
  *
  * don't change this if you don't know what you do, please!
@@ -498,7 +547,7 @@ static unsigned int isofs_get_last_session(struct super_block *sb, s32 session)
 
 	vol_desc_start=0;
 	ms_info.addr_format=CDROM_LBA;
-	if(session >= 0 && session <= 99) {
+	if (session > 0) {
 		struct cdrom_tocentry Te;
 		Te.cdte_track=session;
 		Te.cdte_format=CDROM_LBA;
@@ -582,8 +631,6 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent)
 	int table, error = -EINVAL;
 	unsigned int vol_desc_start;
 
-	save_mount_options(s, data);
-
 	sbi = kzalloc(sizeof(*sbi), GFP_KERNEL);
 	if (!sbi)
 		return -ENOMEM;
@@ -604,6 +651,8 @@ static int isofs_fill_super(struct super_block *s, void *data, int silent)
 	opt.blocksize = sb_min_blocksize(s, opt.blocksize);
 
 	sbi->s_high_sierra = 0; /* default is iso9660 */
+	sbi->s_session = opt.session;
+	sbi->s_sbsector = opt.sbsector;
 
 	vol_desc_start = (opt.sbsector != -1) ?
 		opt.sbsector : isofs_get_last_session(s,opt.session);
@@ -910,6 +959,7 @@ root_found:
 		table += 2;
 	if (opt.check == 'r')
 		table++;
+	sbi->s_check = opt.check;
 
 	if (table)
 		s->s_d_op = &isofs_dentry_ops[table - 1];
diff --git a/fs/isofs/isofs.h b/fs/isofs/isofs.h
index 0ac4c1f73fbd..133a456b0425 100644
--- a/fs/isofs/isofs.h
+++ b/fs/isofs/isofs.h
@@ -36,8 +36,11 @@ struct isofs_sb_info {
 	unsigned long s_max_size;
 	
 	int           s_rock_offset; /* offset of SUSP fields within SU area */
+	s32           s_sbsector;
 	unsigned char s_joliet_level;
 	unsigned char s_mapping;
+	unsigned char s_check;
+	unsigned char s_session;
 	unsigned int  s_high_sierra:1;
 	unsigned int  s_rock:2;
 	unsigned int  s_utf8:1;
diff --git a/fs/jbd2/commit.c b/fs/jbd2/commit.c
index 8c514367ba5a..3c1c31321d9b 100644
--- a/fs/jbd2/commit.c
+++ b/fs/jbd2/commit.c
@@ -263,18 +263,10 @@ static int journal_finish_inode_data_buffers(journal_t *journal,
 			continue;
 		jinode->i_flags |= JI_COMMIT_RUNNING;
 		spin_unlock(&journal->j_list_lock);
-		err = filemap_fdatawait(jinode->i_vfs_inode->i_mapping);
-		if (err) {
-			/*
-			 * Because AS_EIO is cleared by
-			 * filemap_fdatawait_range(), set it again so
-			 * that user process can get -EIO from fsync().
-			 */
-			mapping_set_error(jinode->i_vfs_inode->i_mapping, -EIO);
-
-			if (!ret)
-				ret = err;
-		}
+		err = filemap_fdatawait_keep_errors(
+				jinode->i_vfs_inode->i_mapping);
+		if (!ret)
+			ret = err;
 		spin_lock(&journal->j_list_lock);
 		jinode->i_flags &= ~JI_COMMIT_RUNNING;
 		smp_mb();
@@ -393,7 +385,7 @@ void jbd2_journal_commit_transaction(journal_t *journal)
 	/* Do we need to erase the effects of a prior jbd2_journal_flush? */
 	if (journal->j_flags & JBD2_FLUSHED) {
 		jbd_debug(3, "super block updated\n");
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		/*
 		 * We hold j_checkpoint_mutex so tail cannot change under us.
 		 * We don't need any special data guarantees for writing sb
diff --git a/fs/jbd2/journal.c b/fs/jbd2/journal.c
index a097048ed1a3..7d5ef3bf3f3e 100644
--- a/fs/jbd2/journal.c
+++ b/fs/jbd2/journal.c
@@ -43,6 +43,7 @@
 #include <linux/backing-dev.h>
 #include <linux/bitops.h>
 #include <linux/ratelimit.h>
+#include <linux/sched/mm.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/jbd2.h>
@@ -206,6 +207,14 @@ static int kjournald2(void *arg)
 	wake_up(&journal->j_wait_done_commit);
 
 	/*
+	 * Make sure that no allocations from this kernel thread will ever
+	 * recurse to the fs layer because we are responsible for the
+	 * transaction commit and any fs involvement might get stuck waiting for
+	 * the trasn. commit.
+	 */
+	memalloc_nofs_save();
+
+	/*
 	 * And now, wait forever for commit wakeup events.
 	 */
 	write_lock(&journal->j_state_lock);
@@ -276,11 +285,11 @@ loop:
 	goto loop;
 
 end_loop:
-	write_unlock(&journal->j_state_lock);
 	del_timer_sync(&journal->j_commit_timer);
 	journal->j_task = NULL;
 	wake_up(&journal->j_wait_done_commit);
 	jbd_debug(1, "Journal thread exiting.\n");
+	write_unlock(&journal->j_state_lock);
 	return 0;
 }
 
@@ -691,8 +700,21 @@ int jbd2_log_wait_commit(journal_t *journal, tid_t tid)
 {
 	int err = 0;
 
-	jbd2_might_wait_for_commit(journal);
 	read_lock(&journal->j_state_lock);
+#ifdef CONFIG_PROVE_LOCKING
+	/*
+	 * Some callers make sure transaction is already committing and in that
+	 * case we cannot block on open handles anymore. So don't warn in that
+	 * case.
+	 */
+	if (tid_gt(tid, journal->j_commit_sequence) &&
+	    (!journal->j_committing_transaction ||
+	     journal->j_committing_transaction->t_tid != tid)) {
+		read_unlock(&journal->j_state_lock);
+		jbd2_might_wait_for_commit(journal);
+		read_lock(&journal->j_state_lock);
+	}
+#endif
 #ifdef CONFIG_JBD2_DEBUG
 	if (!tid_geq(journal->j_commit_request, tid)) {
 		printk(KERN_ERR
@@ -913,7 +935,8 @@ int __jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
 	 * space and if we lose sb update during power failure we'd replay
 	 * old transaction with possibly newly overwritten data.
 	 */
-	ret = jbd2_journal_update_sb_log_tail(journal, tid, block, REQ_FUA);
+	ret = jbd2_journal_update_sb_log_tail(journal, tid, block,
+					      REQ_SYNC | REQ_FUA);
 	if (ret)
 		goto out;
 
@@ -944,7 +967,7 @@ out:
  */
 void jbd2_update_log_tail(journal_t *journal, tid_t tid, unsigned long block)
 {
-	mutex_lock(&journal->j_checkpoint_mutex);
+	mutex_lock_io(&journal->j_checkpoint_mutex);
 	if (tid_gt(tid, journal->j_tail_sequence))
 		__jbd2_update_log_tail(journal, tid, block);
 	mutex_unlock(&journal->j_checkpoint_mutex);
@@ -1125,10 +1148,8 @@ static journal_t *journal_init_common(struct block_device *bdev,
 
 	/* Set up a default-sized revoke table for the new mount. */
 	err = jbd2_journal_init_revoke(journal, JOURNAL_REVOKE_DEFAULT_HASH);
-	if (err) {
-		kfree(journal);
-		return NULL;
-	}
+	if (err)
+		goto err_cleanup;
 
 	spin_lock_init(&journal->j_history_lock);
 
@@ -1145,23 +1166,25 @@ static journal_t *journal_init_common(struct block_device *bdev,
 	journal->j_wbufsize = n;
 	journal->j_wbuf = kmalloc_array(n, sizeof(struct buffer_head *),
 					GFP_KERNEL);
-	if (!journal->j_wbuf) {
-		kfree(journal);
-		return NULL;
-	}
+	if (!journal->j_wbuf)
+		goto err_cleanup;
 
 	bh = getblk_unmovable(journal->j_dev, start, journal->j_blocksize);
 	if (!bh) {
 		pr_err("%s: Cannot get buffer for journal superblock\n",
 			__func__);
-		kfree(journal->j_wbuf);
-		kfree(journal);
-		return NULL;
+		goto err_cleanup;
 	}
 	journal->j_sb_buffer = bh;
 	journal->j_superblock = (journal_superblock_t *)bh->b_data;
 
 	return journal;
+
+err_cleanup:
+	kfree(journal->j_wbuf);
+	jbd2_journal_destroy_revoke(journal);
+	kfree(journal);
+	return NULL;
 }
 
 /* jbd2_journal_init_dev and jbd2_journal_init_inode:
@@ -1304,7 +1327,7 @@ static int journal_reset(journal_t *journal)
 		journal->j_flags |= JBD2_FLUSHED;
 	} else {
 		/* Lock here to make assertions happy... */
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		/*
 		 * Update log tail information. We use REQ_FUA since new
 		 * transaction will start reusing journal space and so we
@@ -1314,7 +1337,7 @@ static int journal_reset(journal_t *journal)
 		jbd2_journal_update_sb_log_tail(journal,
 						journal->j_tail_sequence,
 						journal->j_tail,
-						REQ_FUA);
+						REQ_SYNC | REQ_FUA);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
 	return jbd2_journal_start_thread(journal);
@@ -1454,7 +1477,7 @@ void jbd2_journal_update_sb_errno(journal_t *journal)
 	sb->s_errno    = cpu_to_be32(journal->j_errno);
 	read_unlock(&journal->j_state_lock);
 
-	jbd2_write_superblock(journal, REQ_FUA);
+	jbd2_write_superblock(journal, REQ_SYNC | REQ_FUA);
 }
 EXPORT_SYMBOL(jbd2_journal_update_sb_errno);
 
@@ -1691,7 +1714,7 @@ int jbd2_journal_destroy(journal_t *journal)
 	spin_lock(&journal->j_list_lock);
 	while (journal->j_checkpoint_transactions != NULL) {
 		spin_unlock(&journal->j_list_lock);
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		err = jbd2_log_do_checkpoint(journal);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 		/*
@@ -1713,7 +1736,7 @@ int jbd2_journal_destroy(journal_t *journal)
 
 	if (journal->j_sb_buffer) {
 		if (!is_journal_aborted(journal)) {
-			mutex_lock(&journal->j_checkpoint_mutex);
+			mutex_lock_io(&journal->j_checkpoint_mutex);
 
 			write_lock(&journal->j_state_lock);
 			journal->j_tail_sequence =
@@ -1721,7 +1744,7 @@ int jbd2_journal_destroy(journal_t *journal)
 			write_unlock(&journal->j_state_lock);
 
 			jbd2_mark_journal_empty(journal,
-					REQ_PREFLUSH | REQ_FUA);
+					REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
 			mutex_unlock(&journal->j_checkpoint_mutex);
 		} else
 			err = -EIO;
@@ -1955,7 +1978,7 @@ int jbd2_journal_flush(journal_t *journal)
 	spin_lock(&journal->j_list_lock);
 	while (!err && journal->j_checkpoint_transactions != NULL) {
 		spin_unlock(&journal->j_list_lock);
-		mutex_lock(&journal->j_checkpoint_mutex);
+		mutex_lock_io(&journal->j_checkpoint_mutex);
 		err = jbd2_log_do_checkpoint(journal);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 		spin_lock(&journal->j_list_lock);
@@ -1965,7 +1988,7 @@ int jbd2_journal_flush(journal_t *journal)
 	if (is_journal_aborted(journal))
 		return -EIO;
 
-	mutex_lock(&journal->j_checkpoint_mutex);
+	mutex_lock_io(&journal->j_checkpoint_mutex);
 	if (!err) {
 		err = jbd2_cleanup_journal_tail(journal);
 		if (err < 0) {
@@ -1980,7 +2003,7 @@ int jbd2_journal_flush(journal_t *journal)
 	 * the magic code for a fully-recovered superblock.  Any future
 	 * commits of data to the journal will restore the current
 	 * s_start value. */
-	jbd2_mark_journal_empty(journal, REQ_FUA);
+	jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
 	mutex_unlock(&journal->j_checkpoint_mutex);
 	write_lock(&journal->j_state_lock);
 	J_ASSERT(!journal->j_running_transaction);
@@ -2026,7 +2049,7 @@ int jbd2_journal_wipe(journal_t *journal, int write)
 	if (write) {
 		/* Lock to make assertions happy... */
 		mutex_lock(&journal->j_checkpoint_mutex);
-		jbd2_mark_journal_empty(journal, REQ_FUA);
+		jbd2_mark_journal_empty(journal, REQ_SYNC | REQ_FUA);
 		mutex_unlock(&journal->j_checkpoint_mutex);
 	}
 
@@ -2340,7 +2363,7 @@ static int jbd2_journal_init_journal_head_cache(void)
 	jbd2_journal_head_cache = kmem_cache_create("jbd2_journal_head",
 				sizeof(struct journal_head),
 				0,		/* offset */
-				SLAB_TEMPORARY | SLAB_DESTROY_BY_RCU,
+				SLAB_TEMPORARY | SLAB_TYPESAFE_BY_RCU,
 				NULL);		/* ctor */
 	retval = 0;
 	if (!jbd2_journal_head_cache) {
@@ -2556,10 +2579,10 @@ restart:
 		wait_queue_head_t *wq;
 		DEFINE_WAIT_BIT(wait, &jinode->i_flags, __JI_COMMIT_RUNNING);
 		wq = bit_waitqueue(&jinode->i_flags, __JI_COMMIT_RUNNING);
-		prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
 		spin_unlock(&journal->j_list_lock);
 		schedule();
-		finish_wait(wq, &wait.wait);
+		finish_wait(wq, &wait.wq_entry);
 		goto restart;
 	}
 
diff --git a/fs/jbd2/revoke.c b/fs/jbd2/revoke.c
index cfc38b552118..f9aefcda5854 100644
--- a/fs/jbd2/revoke.c
+++ b/fs/jbd2/revoke.c
@@ -280,6 +280,7 @@ int jbd2_journal_init_revoke(journal_t *journal, int hash_size)
 
 fail1:
 	jbd2_journal_destroy_revoke_table(journal->j_revoke_table[0]);
+	journal->j_revoke_table[0] = NULL;
 fail0:
 	return -ENOMEM;
 }
diff --git a/fs/jbd2/transaction.c b/fs/jbd2/transaction.c
index e1652665bd93..8b08044b3120 100644
--- a/fs/jbd2/transaction.c
+++ b/fs/jbd2/transaction.c
@@ -29,6 +29,7 @@
 #include <linux/backing-dev.h>
 #include <linux/bug.h>
 #include <linux/module.h>
+#include <linux/sched/mm.h>
 
 #include <trace/events/jbd2.h>
 
@@ -388,6 +389,11 @@ repeat:
 
 	rwsem_acquire_read(&journal->j_trans_commit_map, 0, 0, _THIS_IP_);
 	jbd2_journal_free_transaction(new_transaction);
+	/*
+	 * Ensure that no allocations done while the transaction is open are
+	 * going to recurse back to the fs layer.
+	 */
+	handle->saved_alloc_context = memalloc_nofs_save();
 	return 0;
 }
 
@@ -403,25 +409,6 @@ static handle_t *new_handle(int nblocks)
 	return handle;
 }
 
-/**
- * handle_t *jbd2_journal_start() - Obtain a new handle.
- * @journal: Journal to start transaction on.
- * @nblocks: number of block buffer we might modify
- *
- * We make sure that the transaction can guarantee at least nblocks of
- * modified buffers in the log.  We block until the log can guarantee
- * that much space. Additionally, if rsv_blocks > 0, we also create another
- * handle with rsv_blocks reserved blocks in the journal. This handle is
- * is stored in h_rsv_handle. It is not attached to any particular transaction
- * and thus doesn't block transaction commit. If the caller uses this reserved
- * handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop()
- * on the parent handle will dispose the reserved one. Reserved handle has to
- * be converted to a normal handle using jbd2_journal_start_reserved() before
- * it can be used.
- *
- * Return a pointer to a newly allocated handle, or an ERR_PTR() value
- * on failure.
- */
 handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks,
 			      gfp_t gfp_mask, unsigned int type,
 			      unsigned int line_no)
@@ -466,11 +453,31 @@ handle_t *jbd2__journal_start(journal_t *journal, int nblocks, int rsv_blocks,
 	trace_jbd2_handle_start(journal->j_fs_dev->bd_dev,
 				handle->h_transaction->t_tid, type,
 				line_no, nblocks);
+
 	return handle;
 }
 EXPORT_SYMBOL(jbd2__journal_start);
 
 
+/**
+ * handle_t *jbd2_journal_start() - Obtain a new handle.
+ * @journal: Journal to start transaction on.
+ * @nblocks: number of block buffer we might modify
+ *
+ * We make sure that the transaction can guarantee at least nblocks of
+ * modified buffers in the log.  We block until the log can guarantee
+ * that much space. Additionally, if rsv_blocks > 0, we also create another
+ * handle with rsv_blocks reserved blocks in the journal. This handle is
+ * is stored in h_rsv_handle. It is not attached to any particular transaction
+ * and thus doesn't block transaction commit. If the caller uses this reserved
+ * handle, it has to set h_rsv_handle to NULL as otherwise jbd2_journal_stop()
+ * on the parent handle will dispose the reserved one. Reserved handle has to
+ * be converted to a normal handle using jbd2_journal_start_reserved() before
+ * it can be used.
+ *
+ * Return a pointer to a newly allocated handle, or an ERR_PTR() value
+ * on failure.
+ */
 handle_t *jbd2_journal_start(journal_t *journal, int nblocks)
 {
 	return jbd2__journal_start(journal, nblocks, 0, GFP_NOFS, 0, 0);
@@ -673,6 +680,12 @@ int jbd2__journal_restart(handle_t *handle, int nblocks, gfp_t gfp_mask)
 
 	rwsem_release(&journal->j_trans_commit_map, 1, _THIS_IP_);
 	handle->h_buffer_credits = nblocks;
+	/*
+	 * Restore the original nofs context because the journal restart
+	 * is basically the same thing as journal stop and start.
+	 * start_this_handle will start a new nofs context.
+	 */
+	memalloc_nofs_restore(handle->saved_alloc_context);
 	ret = start_this_handle(journal, handle, gfp_mask);
 	return ret;
 }
@@ -1059,10 +1072,10 @@ out:
  * @handle: transaction to add buffer modifications to
  * @bh:     bh to be used for metadata writes
  *
- * Returns an error code or 0 on success.
+ * Returns: error code or 0 on success.
  *
  * In full data journalling mode the buffer may be of type BJ_AsyncData,
- * because we're write()ing a buffer which is also part of a shared mapping.
+ * because we're ``write()ing`` a buffer which is also part of a shared mapping.
  */
 
 int jbd2_journal_get_write_access(handle_t *handle, struct buffer_head *bh)
@@ -1760,6 +1773,11 @@ int jbd2_journal_stop(handle_t *handle)
 	if (handle->h_rsv_handle)
 		jbd2_journal_free_reserved(handle->h_rsv_handle);
 free_and_exit:
+	/*
+	 * Scope of the GFP_NOFS context is over here and so we can restore the
+	 * original alloc context.
+	 */
+	memalloc_nofs_restore(handle->saved_alloc_context);
 	jbd2_free_handle(handle);
 	return err;
 }
@@ -1863,7 +1881,9 @@ static void __jbd2_journal_temp_unlink_buffer(struct journal_head *jh)
 
 	__blist_del_buffer(list, jh);
 	jh->b_jlist = BJ_None;
-	if (test_clear_buffer_jbddirty(bh))
+	if (transaction && is_journal_aborted(transaction->t_journal))
+		clear_buffer_jbddirty(bh);
+	else if (test_clear_buffer_jbddirty(bh))
 		mark_buffer_dirty(bh);	/* Expose it to the VM */
 }
 
diff --git a/fs/jffs2/background.c b/fs/jffs2/background.c
index e5c1783ab64a..453a6a1fff34 100644
--- a/fs/jffs2/background.c
+++ b/fs/jffs2/background.c
@@ -16,7 +16,7 @@
 #include <linux/jffs2.h>
 #include <linux/mtd/mtd.h>
 #include <linux/completion.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/freezer.h>
 #include <linux/kthread.h>
 #include "nodelist.h"
diff --git a/fs/jffs2/fs.c b/fs/jffs2/fs.c
index 567653f7c0ce..76fa814df3d1 100644
--- a/fs/jffs2/fs.c
+++ b/fs/jffs2/fs.c
@@ -15,6 +15,7 @@
 #include <linux/capability.h>
 #include <linux/kernel.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/fs.h>
 #include <linux/list.h>
 #include <linux/mtd/mtd.h>
diff --git a/fs/jffs2/nodemgmt.c b/fs/jffs2/nodemgmt.c
index cda0774c2c9c..a7bbe879cfc3 100644
--- a/fs/jffs2/nodemgmt.c
+++ b/fs/jffs2/nodemgmt.c
@@ -14,7 +14,7 @@
 #include <linux/kernel.h>
 #include <linux/mtd/mtd.h>
 #include <linux/compiler.h>
-#include <linux/sched.h> /* For cond_resched() */
+#include <linux/sched/signal.h>
 #include "nodelist.h"
 #include "debug.h"
 
diff --git a/fs/jffs2/readinode.c b/fs/jffs2/readinode.c
index 06a71dbd4833..389ea53ea487 100644
--- a/fs/jffs2/readinode.c
+++ b/fs/jffs2/readinode.c
@@ -1366,7 +1366,7 @@ int jffs2_do_read_inode(struct jffs2_sb_info *c, struct jffs2_inode_info *f,
 		jffs2_add_ino_cache(c, f->inocache);
 	}
 	if (!f->inocache) {
-		JFFS2_ERROR("requestied to read an nonexistent ino %u\n", ino);
+		JFFS2_ERROR("requested to read a nonexistent ino %u\n", ino);
 		return -ENOENT;
 	}
 
diff --git a/fs/jfs/ioctl.c b/fs/jfs/ioctl.c
index fc89f9436784..5c5ac5b3aec3 100644
--- a/fs/jfs/ioctl.c
+++ b/fs/jfs/ioctl.c
@@ -64,7 +64,6 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 
 	switch (cmd) {
 	case JFS_IOC_GETFLAGS:
-		jfs_get_inode_flags(jfs_inode);
 		flags = jfs_inode->mode2 & JFS_FL_USER_VISIBLE;
 		flags = jfs_map_ext2(flags, 0);
 		return put_user(flags, (int __user *) arg);
@@ -98,7 +97,6 @@ long jfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		/* Lock against other parallel changes of flags */
 		inode_lock(inode);
 
-		jfs_get_inode_flags(jfs_inode);
 		oldflags = jfs_inode->mode2;
 
 		/*
diff --git a/fs/jfs/jfs_imap.c b/fs/jfs/jfs_imap.c
index 6aca224a5d68..f36ef68905a7 100644
--- a/fs/jfs/jfs_imap.c
+++ b/fs/jfs/jfs_imap.c
@@ -3148,7 +3148,6 @@ static void copy_to_dinode(struct dinode * dip, struct inode *ip)
 	else
 		dip->di_gid = cpu_to_le32(from_kgid(&init_user_ns,
 						    jfs_ip->saved_gid));
-	jfs_get_inode_flags(jfs_ip);
 	/*
 	 * mode2 is only needed for storing the higher order bits.
 	 * Trust i_mode for the lower order ones
diff --git a/fs/jfs/jfs_inode.c b/fs/jfs/jfs_inode.c
index 375dd257a34f..5e9b7bb3aabf 100644
--- a/fs/jfs/jfs_inode.c
+++ b/fs/jfs/jfs_inode.c
@@ -45,24 +45,6 @@ void jfs_set_inode_flags(struct inode *inode)
 			S_DIRSYNC | S_SYNC);
 }
 
-void jfs_get_inode_flags(struct jfs_inode_info *jfs_ip)
-{
-	unsigned int flags = jfs_ip->vfs_inode.i_flags;
-
-	jfs_ip->mode2 &= ~(JFS_IMMUTABLE_FL | JFS_APPEND_FL | JFS_NOATIME_FL |
-			   JFS_DIRSYNC_FL | JFS_SYNC_FL);
-	if (flags & S_IMMUTABLE)
-		jfs_ip->mode2 |= JFS_IMMUTABLE_FL;
-	if (flags & S_APPEND)
-		jfs_ip->mode2 |= JFS_APPEND_FL;
-	if (flags & S_NOATIME)
-		jfs_ip->mode2 |= JFS_NOATIME_FL;
-	if (flags & S_DIRSYNC)
-		jfs_ip->mode2 |= JFS_DIRSYNC_FL;
-	if (flags & S_SYNC)
-		jfs_ip->mode2 |= JFS_SYNC_FL;
-}
-
 /*
  * NAME:	ialloc()
  *
diff --git a/fs/jfs/jfs_inode.h b/fs/jfs/jfs_inode.h
index 9271cfe4a149..7b0b3a40788f 100644
--- a/fs/jfs/jfs_inode.h
+++ b/fs/jfs/jfs_inode.h
@@ -33,7 +33,6 @@ extern void jfs_truncate(struct inode *);
 extern void jfs_truncate_nolock(struct inode *, loff_t);
 extern void jfs_free_zero_link(struct inode *);
 extern struct dentry *jfs_get_parent(struct dentry *dentry);
-extern void jfs_get_inode_flags(struct jfs_inode_info *);
 extern struct dentry *jfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
 	int fh_len, int fh_type);
 extern struct dentry *jfs_fh_to_parent(struct super_block *sb, struct fid *fid,
diff --git a/fs/jfs/jfs_logmgr.c b/fs/jfs/jfs_logmgr.c
index bb1da1feafeb..a21f0e9eecd4 100644
--- a/fs/jfs/jfs_logmgr.c
+++ b/fs/jfs/jfs_logmgr.c
@@ -2205,7 +2205,7 @@ static void lbmIODone(struct bio *bio)
 
 	bp->l_flag |= lbmDONE;
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		bp->l_flag |= lbmERROR;
 
 		jfs_err("lbmIODone: I/O error in JFS log");
diff --git a/fs/jfs/jfs_metapage.c b/fs/jfs/jfs_metapage.c
index 489aaa1403e5..65120a471729 100644
--- a/fs/jfs/jfs_metapage.c
+++ b/fs/jfs/jfs_metapage.c
@@ -280,7 +280,7 @@ static void metapage_read_end_io(struct bio *bio)
 {
 	struct page *page = bio->bi_private;
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		printk(KERN_ERR "metapage_read_end_io: I/O error\n");
 		SetPageError(page);
 	}
@@ -337,7 +337,7 @@ static void metapage_write_end_io(struct bio *bio)
 
 	BUG_ON(!PagePrivate(page));
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		printk(KERN_ERR "metapage_write_end_io: I/O error\n");
 		SetPageError(page);
 	}
@@ -664,6 +664,7 @@ struct metapage *__get_metapage(struct inode *inode, unsigned long lblock,
 		INCREMENT(mpStat.pagealloc);
 		mp = alloc_metapage(GFP_NOFS);
 		mp->page = page;
+		mp->sb = inode->i_sb;
 		mp->flag = 0;
 		mp->xflag = COMMIT_PAGE;
 		mp->count = 1;
@@ -711,7 +712,8 @@ void force_metapage(struct metapage *mp)
 	get_page(page);
 	lock_page(page);
 	set_page_dirty(page);
-	write_one_page(page, 1);
+	if (write_one_page(page))
+		jfs_error(mp->sb, "write_one_page() failed\n");
 	clear_bit(META_forcewrite, &mp->flag);
 	put_page(page);
 }
@@ -756,7 +758,8 @@ void release_metapage(struct metapage * mp)
 		set_page_dirty(page);
 		if (test_bit(META_sync, &mp->flag)) {
 			clear_bit(META_sync, &mp->flag);
-			write_one_page(page, 1);
+			if (write_one_page(page))
+				jfs_error(mp->sb, "write_one_page() failed\n");
 			lock_page(page); /* write_one_page unlocks the page */
 		}
 	} else if (mp->lsn)	/* discard_metapage doesn't remove it */
diff --git a/fs/jfs/jfs_metapage.h b/fs/jfs/jfs_metapage.h
index a869fb4a20d6..8b0ee514eb84 100644
--- a/fs/jfs/jfs_metapage.h
+++ b/fs/jfs/jfs_metapage.h
@@ -38,6 +38,7 @@ struct metapage {
 
 	/* implementation */
 	struct page *page;
+	struct super_block *sb;
 	unsigned int logical_size;
 
 	/* Journal management */
diff --git a/fs/jfs/super.c b/fs/jfs/super.c
index 51881eb8ccff..78b41e1d5c67 100644
--- a/fs/jfs/super.c
+++ b/fs/jfs/super.c
@@ -45,6 +45,7 @@
 #include "jfs_acl.h"
 #include "jfs_debug.h"
 #include "jfs_xattr.h"
+#include "jfs_dinode.h"
 
 MODULE_DESCRIPTION("The Journaled Filesystem (JFS)");
 MODULE_AUTHOR("Steve Best/Dave Kleikamp/Barry Arndt, IBM");
@@ -181,6 +182,35 @@ static int jfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return 0;
 }
 
+#ifdef CONFIG_QUOTA
+static int jfs_quota_off(struct super_block *sb, int type);
+static int jfs_quota_on(struct super_block *sb, int type, int format_id,
+			const struct path *path);
+
+static void jfs_quota_off_umount(struct super_block *sb)
+{
+	int type;
+
+	for (type = 0; type < MAXQUOTAS; type++)
+		jfs_quota_off(sb, type);
+}
+
+static const struct quotactl_ops jfs_quotactl_ops = {
+	.quota_on	= jfs_quota_on,
+	.quota_off	= jfs_quota_off,
+	.quota_sync	= dquot_quota_sync,
+	.get_state	= dquot_get_state,
+	.set_info	= dquot_set_dqinfo,
+	.get_dqblk	= dquot_get_dqblk,
+	.set_dqblk	= dquot_set_dqblk,
+	.get_nextdqblk	= dquot_get_next_dqblk,
+};
+#else
+static inline void jfs_quota_off_umount(struct super_block *sb)
+{
+}
+#endif
+
 static void jfs_put_super(struct super_block *sb)
 {
 	struct jfs_sb_info *sbi = JFS_SBI(sb);
@@ -188,7 +218,7 @@ static void jfs_put_super(struct super_block *sb)
 
 	jfs_info("In jfs_put_super");
 
-	dquot_disable(sb, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
+	jfs_quota_off_umount(sb);
 
 	rc = jfs_umount(sb);
 	if (rc)
@@ -536,7 +566,7 @@ static int jfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_xattr = jfs_xattr_handlers;
 #ifdef CONFIG_QUOTA
 	sb->dq_op = &dquot_operations;
-	sb->s_qcop = &dquot_quotactl_ops;
+	sb->s_qcop = &jfs_quotactl_ops;
 	sb->s_quota_types = QTYPE_MASK_USR | QTYPE_MASK_GRP;
 #endif
 
@@ -758,7 +788,7 @@ static ssize_t jfs_quota_read(struct super_block *sb, int type, char *data,
 				sb->s_blocksize - offset : toread;
 
 		tmp_bh.b_state = 0;
-		tmp_bh.b_size = 1 << inode->i_blkbits;
+		tmp_bh.b_size = i_blocksize(inode);
 		err = jfs_get_block(inode, blk, &tmp_bh, 0);
 		if (err)
 			return err;
@@ -798,7 +828,7 @@ static ssize_t jfs_quota_write(struct super_block *sb, int type,
 				sb->s_blocksize - offset : towrite;
 
 		tmp_bh.b_state = 0;
-		tmp_bh.b_size = 1 << inode->i_blkbits;
+		tmp_bh.b_size = i_blocksize(inode);
 		err = jfs_get_block(inode, blk, &tmp_bh, 1);
 		if (err)
 			goto out;
@@ -840,6 +870,51 @@ static struct dquot **jfs_get_dquots(struct inode *inode)
 {
 	return JFS_IP(inode)->i_dquot;
 }
+
+static int jfs_quota_on(struct super_block *sb, int type, int format_id,
+			const struct path *path)
+{
+	int err;
+	struct inode *inode;
+
+	err = dquot_quota_on(sb, type, format_id, path);
+	if (err)
+		return err;
+
+	inode = d_inode(path->dentry);
+	inode_lock(inode);
+	JFS_IP(inode)->mode2 |= JFS_NOATIME_FL | JFS_IMMUTABLE_FL;
+	inode_set_flags(inode, S_NOATIME | S_IMMUTABLE,
+			S_NOATIME | S_IMMUTABLE);
+	inode_unlock(inode);
+	mark_inode_dirty(inode);
+
+	return 0;
+}
+
+static int jfs_quota_off(struct super_block *sb, int type)
+{
+	struct inode *inode = sb_dqopt(sb)->files[type];
+	int err;
+
+	if (!inode || !igrab(inode))
+		goto out;
+
+	err = dquot_quota_off(sb, type);
+	if (err)
+		goto out_put;
+
+	inode_lock(inode);
+	JFS_IP(inode)->mode2 &= ~(JFS_NOATIME_FL | JFS_IMMUTABLE_FL);
+	inode_set_flags(inode, 0, S_NOATIME | S_IMMUTABLE);
+	inode_unlock(inode);
+	mark_inode_dirty(inode);
+out_put:
+	iput(inode);
+	return err;
+out:
+	return dquot_quota_off(sb, type);
+}
 #endif
 
 static const struct super_operations jfs_super_operations = {
diff --git a/fs/kernfs/dir.c b/fs/kernfs/dir.c
index cf4c636ff4da..db5900aaa55a 100644
--- a/fs/kernfs/dir.c
+++ b/fs/kernfs/dir.c
@@ -41,6 +41,9 @@ static bool kernfs_lockdep(struct kernfs_node *kn)
 
 static int kernfs_name_locked(struct kernfs_node *kn, char *buf, size_t buflen)
 {
+	if (!kn)
+		return strlcpy(buf, "(null)", buflen);
+
 	return strlcpy(buf, kn->parent ? kn->name : "/", buflen);
 }
 
@@ -110,6 +113,8 @@ static struct kernfs_node *kernfs_common_ancestor(struct kernfs_node *a,
  * kn_to:   /n1/n2/n3         [depth=3]
  * result:  /../..
  *
+ * [3] when @kn_to is NULL result will be "(null)"
+ *
  * Returns the length of the full path.  If the full length is equal to or
  * greater than @buflen, @buf contains the truncated path with the trailing
  * '\0'.  On error, -errno is returned.
@@ -123,6 +128,9 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
 	size_t depth_from, depth_to, len = 0;
 	int i, j;
 
+	if (!kn_to)
+		return strlcpy(buf, "(null)", buflen);
+
 	if (!kn_from)
 		kn_from = kernfs_root(kn_to)->kn;
 
@@ -166,6 +174,8 @@ static int kernfs_path_from_node_locked(struct kernfs_node *kn_to,
  * similar to strlcpy().  It returns the length of @kn's name and if @buf
  * isn't long enough, it's filled upto @buflen-1 and nul terminated.
  *
+ * Fills buffer with "(null)" if @kn is NULL.
+ *
  * This function can be called from any context.
  */
 int kernfs_name(struct kernfs_node *kn, char *buf, size_t buflen)
@@ -468,7 +478,7 @@ static void kernfs_drain(struct kernfs_node *kn)
 		rwsem_release(&kn->dep_map, 1, _RET_IP_);
 	}
 
-	kernfs_unmap_bin_file(kn);
+	kernfs_drain_open_files(kn);
 
 	mutex_lock(&kernfs_mutex);
 }
diff --git a/fs/kernfs/file.c b/fs/kernfs/file.c
index 78219d5644e9..ac2dfe0c5a9c 100644
--- a/fs/kernfs/file.c
+++ b/fs/kernfs/file.c
@@ -13,7 +13,7 @@
 #include <linux/slab.h>
 #include <linux/poll.h>
 #include <linux/pagemap.h>
-#include <linux/sched.h>
+#include <linux/sched/mm.h>
 #include <linux/fsnotify.h>
 
 #include "kernfs-internal.h"
@@ -348,9 +348,9 @@ static void kernfs_vma_open(struct vm_area_struct *vma)
 	kernfs_put_active(of->kn);
 }
 
-static int kernfs_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int kernfs_vma_fault(struct vm_fault *vmf)
 {
-	struct file *file = vma->vm_file;
+	struct file *file = vmf->vma->vm_file;
 	struct kernfs_open_file *of = kernfs_of(file);
 	int ret;
 
@@ -362,16 +362,15 @@ static int kernfs_vma_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
 
 	ret = VM_FAULT_SIGBUS;
 	if (of->vm_ops->fault)
-		ret = of->vm_ops->fault(vma, vmf);
+		ret = of->vm_ops->fault(vmf);
 
 	kernfs_put_active(of->kn);
 	return ret;
 }
 
-static int kernfs_vma_page_mkwrite(struct vm_area_struct *vma,
-				   struct vm_fault *vmf)
+static int kernfs_vma_page_mkwrite(struct vm_fault *vmf)
 {
-	struct file *file = vma->vm_file;
+	struct file *file = vmf->vma->vm_file;
 	struct kernfs_open_file *of = kernfs_of(file);
 	int ret;
 
@@ -383,7 +382,7 @@ static int kernfs_vma_page_mkwrite(struct vm_area_struct *vma,
 
 	ret = 0;
 	if (of->vm_ops->page_mkwrite)
-		ret = of->vm_ops->page_mkwrite(vma, vmf);
+		ret = of->vm_ops->page_mkwrite(vmf);
 	else
 		file_update_time(file);
 
@@ -516,7 +515,7 @@ static int kernfs_fop_mmap(struct file *file, struct vm_area_struct *vma)
 		goto out_put;
 
 	rc = 0;
-	of->mmapped = 1;
+	of->mmapped = true;
 	of->vm_ops = vma->vm_ops;
 	vma->vm_ops = &kernfs_vm_ops;
 out_put:
@@ -708,7 +707,8 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
 	if (error)
 		goto err_free;
 
-	((struct seq_file *)file->private_data)->private = of;
+	of->seq_file = file->private_data;
+	of->seq_file->private = of;
 
 	/* seq_file clears PWRITE unconditionally, restore it if WRITE */
 	if (file->f_mode & FMODE_WRITE)
@@ -717,13 +717,22 @@ static int kernfs_fop_open(struct inode *inode, struct file *file)
 	/* make sure we have open node struct */
 	error = kernfs_get_open_node(kn, of);
 	if (error)
-		goto err_close;
+		goto err_seq_release;
+
+	if (ops->open) {
+		/* nobody has access to @of yet, skip @of->mutex */
+		error = ops->open(of);
+		if (error)
+			goto err_put_node;
+	}
 
 	/* open succeeded, put active references */
 	kernfs_put_active(kn);
 	return 0;
 
-err_close:
+err_put_node:
+	kernfs_put_open_node(kn, of);
+err_seq_release:
 	seq_release(inode, file);
 err_free:
 	kfree(of->prealloc_buf);
@@ -733,11 +742,41 @@ err_out:
 	return error;
 }
 
+/* used from release/drain to ensure that ->release() is called exactly once */
+static void kernfs_release_file(struct kernfs_node *kn,
+				struct kernfs_open_file *of)
+{
+	/*
+	 * @of is guaranteed to have no other file operations in flight and
+	 * we just want to synchronize release and drain paths.
+	 * @kernfs_open_file_mutex is enough.  @of->mutex can't be used
+	 * here because drain path may be called from places which can
+	 * cause circular dependency.
+	 */
+	lockdep_assert_held(&kernfs_open_file_mutex);
+
+	if (!of->released) {
+		/*
+		 * A file is never detached without being released and we
+		 * need to be able to release files which are deactivated
+		 * and being drained.  Don't use kernfs_ops().
+		 */
+		kn->attr.ops->release(of);
+		of->released = true;
+	}
+}
+
 static int kernfs_fop_release(struct inode *inode, struct file *filp)
 {
 	struct kernfs_node *kn = filp->f_path.dentry->d_fsdata;
 	struct kernfs_open_file *of = kernfs_of(filp);
 
+	if (kn->flags & KERNFS_HAS_RELEASE) {
+		mutex_lock(&kernfs_open_file_mutex);
+		kernfs_release_file(kn, of);
+		mutex_unlock(&kernfs_open_file_mutex);
+	}
+
 	kernfs_put_open_node(kn, of);
 	seq_release(inode, filp);
 	kfree(of->prealloc_buf);
@@ -746,12 +785,12 @@ static int kernfs_fop_release(struct inode *inode, struct file *filp)
 	return 0;
 }
 
-void kernfs_unmap_bin_file(struct kernfs_node *kn)
+void kernfs_drain_open_files(struct kernfs_node *kn)
 {
 	struct kernfs_open_node *on;
 	struct kernfs_open_file *of;
 
-	if (!(kn->flags & KERNFS_HAS_MMAP))
+	if (!(kn->flags & (KERNFS_HAS_MMAP | KERNFS_HAS_RELEASE)))
 		return;
 
 	spin_lock_irq(&kernfs_open_node_lock);
@@ -763,10 +802,17 @@ void kernfs_unmap_bin_file(struct kernfs_node *kn)
 		return;
 
 	mutex_lock(&kernfs_open_file_mutex);
+
 	list_for_each_entry(of, &on->files, list) {
 		struct inode *inode = file_inode(of->file);
-		unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+
+		if (kn->flags & KERNFS_HAS_MMAP)
+			unmap_mapping_range(inode->i_mapping, 0, 0, 1);
+
+		if (kn->flags & KERNFS_HAS_RELEASE)
+			kernfs_release_file(kn, of);
 	}
+
 	mutex_unlock(&kernfs_open_file_mutex);
 
 	kernfs_put_open_node(kn, NULL);
@@ -965,6 +1011,8 @@ struct kernfs_node *__kernfs_create_file(struct kernfs_node *parent,
 		kn->flags |= KERNFS_HAS_SEQ_SHOW;
 	if (ops->mmap)
 		kn->flags |= KERNFS_HAS_MMAP;
+	if (ops->release)
+		kn->flags |= KERNFS_HAS_RELEASE;
 
 	rc = kernfs_add_one(kn);
 	if (rc) {
diff --git a/fs/kernfs/inode.c b/fs/kernfs/inode.c
index ac9e108ce1ea..fb4b4a79a0d6 100644
--- a/fs/kernfs/inode.c
+++ b/fs/kernfs/inode.c
@@ -200,11 +200,11 @@ static void kernfs_refresh_inode(struct kernfs_node *kn, struct inode *inode)
 		set_nlink(inode, kn->dir.subdirs + 2);
 }
 
-int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		   struct kstat *stat)
+int kernfs_iop_getattr(const struct path *path, struct kstat *stat,
+		       u32 request_mask, unsigned int query_flags)
 {
-	struct kernfs_node *kn = dentry->d_fsdata;
-	struct inode *inode = d_inode(dentry);
+	struct kernfs_node *kn = path->dentry->d_fsdata;
+	struct inode *inode = d_inode(path->dentry);
 
 	mutex_lock(&kernfs_mutex);
 	kernfs_refresh_inode(kn, inode);
diff --git a/fs/kernfs/kernfs-internal.h b/fs/kernfs/kernfs-internal.h
index bfd551bbf231..2d5144ab4251 100644
--- a/fs/kernfs/kernfs-internal.h
+++ b/fs/kernfs/kernfs-internal.h
@@ -80,8 +80,8 @@ extern const struct xattr_handler *kernfs_xattr_handlers[];
 void kernfs_evict_inode(struct inode *inode);
 int kernfs_iop_permission(struct inode *inode, int mask);
 int kernfs_iop_setattr(struct dentry *dentry, struct iattr *iattr);
-int kernfs_iop_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		       struct kstat *stat);
+int kernfs_iop_getattr(const struct path *path, struct kstat *stat,
+		       u32 request_mask, unsigned int query_flags);
 ssize_t kernfs_iop_listxattr(struct dentry *dentry, char *buf, size_t size);
 
 /*
@@ -104,7 +104,7 @@ struct kernfs_node *kernfs_new_node(struct kernfs_node *parent,
  */
 extern const struct file_operations kernfs_file_fops;
 
-void kernfs_unmap_bin_file(struct kernfs_node *kn);
+void kernfs_drain_open_files(struct kernfs_node *kn);
 
 /*
  * symlink.c
diff --git a/fs/libfs.c b/fs/libfs.c
index 28d6f35feed6..3aabe553fc45 100644
--- a/fs/libfs.c
+++ b/fs/libfs.c
@@ -7,6 +7,7 @@
 #include <linux/export.h>
 #include <linux/pagemap.h>
 #include <linux/slab.h>
+#include <linux/cred.h>
 #include <linux/mount.h>
 #include <linux/vfs.h>
 #include <linux/quotaops.h>
@@ -20,10 +21,10 @@
 
 #include "internal.h"
 
-int simple_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		   struct kstat *stat)
+int simple_getattr(const struct path *path, struct kstat *stat,
+		   u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	generic_fillattr(inode, stat);
 	stat->blocks = inode->i_mapping->nrpages << (PAGE_SHIFT - 9);
 	return 0;
@@ -506,7 +507,7 @@ EXPORT_SYMBOL(simple_write_end);
  * to pass it an appropriate max_reserved value to avoid collisions.
  */
 int simple_fill_super(struct super_block *s, unsigned long magic,
-		      struct tree_descr *files)
+		      const struct tree_descr *files)
 {
 	struct inode *inode;
 	struct dentry *root;
@@ -973,7 +974,7 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end,
 	int err;
 	int ret;
 
-	err = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	err = file_write_and_wait_range(file, start, end);
 	if (err)
 		return err;
 
@@ -990,6 +991,10 @@ int __generic_file_fsync(struct file *file, loff_t start, loff_t end,
 
 out:
 	inode_unlock(inode);
+	/* check and advance again to catch errors after syncing out buffers */
+	err = file_check_and_advance_wb_err(file);
+	if (ret == 0)
+		ret = err;
 	return ret;
 }
 EXPORT_SYMBOL(__generic_file_fsync);
@@ -1143,10 +1148,10 @@ static struct dentry *empty_dir_lookup(struct inode *dir, struct dentry *dentry,
 	return ERR_PTR(-ENOENT);
 }
 
-static int empty_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
-				 struct kstat *stat)
+static int empty_dir_getattr(const struct path *path, struct kstat *stat,
+			     u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	generic_fillattr(inode, stat);
 	return 0;
 }
diff --git a/fs/lockd/clnt4xdr.c b/fs/lockd/clnt4xdr.c
index d3e40db28930..c349fc0f9b80 100644
--- a/fs/lockd/clnt4xdr.c
+++ b/fs/lockd/clnt4xdr.c
@@ -381,8 +381,9 @@ static void encode_nlm4_lock(struct xdr_stream *xdr,
  */
 static void nlm4_xdr_enc_testargs(struct rpc_rqst *req,
 				  struct xdr_stream *xdr,
-				  const struct nlm_args *args)
+				  const void *data)
 {
+	const struct nlm_args *args = data;
 	const struct nlm_lock *lock = &args->lock;
 
 	encode_cookie(xdr, &args->cookie);
@@ -402,8 +403,9 @@ static void nlm4_xdr_enc_testargs(struct rpc_rqst *req,
  */
 static void nlm4_xdr_enc_lockargs(struct rpc_rqst *req,
 				  struct xdr_stream *xdr,
-				  const struct nlm_args *args)
+				  const void *data)
 {
+	const struct nlm_args *args = data;
 	const struct nlm_lock *lock = &args->lock;
 
 	encode_cookie(xdr, &args->cookie);
@@ -424,8 +426,9 @@ static void nlm4_xdr_enc_lockargs(struct rpc_rqst *req,
  */
 static void nlm4_xdr_enc_cancargs(struct rpc_rqst *req,
 				  struct xdr_stream *xdr,
-				  const struct nlm_args *args)
+				  const void *data)
 {
+	const struct nlm_args *args = data;
 	const struct nlm_lock *lock = &args->lock;
 
 	encode_cookie(xdr, &args->cookie);
@@ -442,8 +445,9 @@ static void nlm4_xdr_enc_cancargs(struct rpc_rqst *req,
  */
 static void nlm4_xdr_enc_unlockargs(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    const struct nlm_args *args)
+				    const void *data)
 {
+	const struct nlm_args *args = data;
 	const struct nlm_lock *lock = &args->lock;
 
 	encode_cookie(xdr, &args->cookie);
@@ -458,8 +462,10 @@ static void nlm4_xdr_enc_unlockargs(struct rpc_rqst *req,
  */
 static void nlm4_xdr_enc_res(struct rpc_rqst *req,
 			     struct xdr_stream *xdr,
-			     const struct nlm_res *result)
+			     const void *data)
 {
+	const struct nlm_res *result = data;
+
 	encode_cookie(xdr, &result->cookie);
 	encode_nlm4_stat(xdr, result->status);
 }
@@ -479,8 +485,10 @@ static void nlm4_xdr_enc_res(struct rpc_rqst *req,
  */
 static void nlm4_xdr_enc_testres(struct rpc_rqst *req,
 				 struct xdr_stream *xdr,
-				 const struct nlm_res *result)
+				 const void *data)
 {
+	const struct nlm_res *result = data;
+
 	encode_cookie(xdr, &result->cookie);
 	encode_nlm4_stat(xdr, result->status);
 	if (result->status == nlm_lck_denied)
@@ -525,8 +533,9 @@ out:
 
 static int nlm4_xdr_dec_testres(struct rpc_rqst *req,
 				struct xdr_stream *xdr,
-				struct nlm_res *result)
+				void *data)
 {
+	struct nlm_res *result = data;
 	int error;
 
 	error = decode_cookie(xdr, &result->cookie);
@@ -545,8 +554,9 @@ out:
  */
 static int nlm4_xdr_dec_res(struct rpc_rqst *req,
 			    struct xdr_stream *xdr,
-			    struct nlm_res *result)
+			    void *data)
 {
+	struct nlm_res *result = data;
 	int error;
 
 	error = decode_cookie(xdr, &result->cookie);
@@ -566,15 +576,15 @@ out:
 #define PROC(proc, argtype, restype)					\
 [NLMPROC_##proc] = {							\
 	.p_proc      = NLMPROC_##proc,					\
-	.p_encode    = (kxdreproc_t)nlm4_xdr_enc_##argtype,		\
-	.p_decode    = (kxdrdproc_t)nlm4_xdr_dec_##restype,		\
+	.p_encode    = nlm4_xdr_enc_##argtype,				\
+	.p_decode    = nlm4_xdr_dec_##restype,				\
 	.p_arglen    = NLM4_##argtype##_sz,				\
 	.p_replen    = NLM4_##restype##_sz,				\
 	.p_statidx   = NLMPROC_##proc,					\
 	.p_name      = #proc,						\
 	}
 
-static struct rpc_procinfo	nlm4_procedures[] = {
+static const struct rpc_procinfo nlm4_procedures[] = {
 	PROC(TEST,		testargs,	testres),
 	PROC(LOCK,		lockargs,	res),
 	PROC(CANCEL,		cancargs,	res),
@@ -592,8 +602,10 @@ static struct rpc_procinfo	nlm4_procedures[] = {
 	PROC(GRANTED_RES,	res,		norep),
 };
 
+static unsigned int nlm_version4_counts[ARRAY_SIZE(nlm4_procedures)];
 const struct rpc_version nlm_version4 = {
 	.number		= 4,
 	.nrprocs	= ARRAY_SIZE(nlm4_procedures),
 	.procs		= nlm4_procedures,
+	.counts		= nlm_version4_counts,
 };
diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c
index 41e491b8e5d7..27d577dbe51a 100644
--- a/fs/lockd/clntlock.c
+++ b/fs/lockd/clntlock.c
@@ -69,6 +69,7 @@ struct nlm_host *nlmclnt_init(const struct nlmclnt_initdata *nlm_init)
 	if (host->h_rpcclnt == NULL && nlm_bind_host(host) == NULL)
 		goto out_nobind;
 
+	host->h_nlmclnt_ops = nlm_init->nlmclnt_ops;
 	return host;
 out_nobind:
 	nlmclnt_release_host(host);
diff --git a/fs/lockd/clntproc.c b/fs/lockd/clntproc.c
index 112952037933..066ac313ae5c 100644
--- a/fs/lockd/clntproc.c
+++ b/fs/lockd/clntproc.c
@@ -150,17 +150,22 @@ static void nlmclnt_release_lockargs(struct nlm_rqst *req)
  * @host: address of a valid nlm_host context representing the NLM server
  * @cmd: fcntl-style file lock operation to perform
  * @fl: address of arguments for the lock operation
+ * @data: address of data to be sent to callback operations
  *
  */
-int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl)
+int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl, void *data)
 {
 	struct nlm_rqst		*call;
 	int			status;
+	const struct nlmclnt_operations *nlmclnt_ops = host->h_nlmclnt_ops;
 
 	call = nlm_alloc_call(host);
 	if (call == NULL)
 		return -ENOMEM;
 
+	if (nlmclnt_ops && nlmclnt_ops->nlmclnt_alloc_call)
+		nlmclnt_ops->nlmclnt_alloc_call(data);
+
 	nlmclnt_locks_init_private(fl, host);
 	if (!fl->fl_u.nfs_fl.owner) {
 		/* lockowner allocation has failed */
@@ -169,6 +174,7 @@ int nlmclnt_proc(struct nlm_host *host, int cmd, struct file_lock *fl)
 	}
 	/* Set up the argument struct */
 	nlmclnt_setlockargs(call, fl);
+	call->a_callback_data = data;
 
 	if (IS_SETLK(cmd) || IS_SETLKW(cmd)) {
 		if (fl->fl_type != F_UNLCK) {
@@ -214,8 +220,12 @@ struct nlm_rqst *nlm_alloc_call(struct nlm_host *host)
 
 void nlmclnt_release_call(struct nlm_rqst *call)
 {
+	const struct nlmclnt_operations *nlmclnt_ops = call->a_host->h_nlmclnt_ops;
+
 	if (!atomic_dec_and_test(&call->a_count))
 		return;
+	if (nlmclnt_ops && nlmclnt_ops->nlmclnt_release_call)
+		nlmclnt_ops->nlmclnt_release_call(call->a_callback_data);
 	nlmclnt_release_host(call->a_host);
 	nlmclnt_release_lockargs(call);
 	kfree(call);
@@ -687,6 +697,19 @@ out:
 	return status;
 }
 
+static void nlmclnt_unlock_prepare(struct rpc_task *task, void *data)
+{
+	struct nlm_rqst	*req = data;
+	const struct nlmclnt_operations *nlmclnt_ops = req->a_host->h_nlmclnt_ops;
+	bool defer_call = false;
+
+	if (nlmclnt_ops && nlmclnt_ops->nlmclnt_unlock_prepare)
+		defer_call = nlmclnt_ops->nlmclnt_unlock_prepare(task, req->a_callback_data);
+
+	if (!defer_call)
+		rpc_call_start(task);
+}
+
 static void nlmclnt_unlock_callback(struct rpc_task *task, void *data)
 {
 	struct nlm_rqst	*req = data;
@@ -720,6 +743,7 @@ die:
 }
 
 static const struct rpc_call_ops nlmclnt_unlock_ops = {
+	.rpc_call_prepare = nlmclnt_unlock_prepare,
 	.rpc_call_done = nlmclnt_unlock_callback,
 	.rpc_release = nlmclnt_rpc_release,
 };
diff --git a/fs/lockd/clntxdr.c b/fs/lockd/clntxdr.c
index 3e9f7874b975..3b4724a6c4ee 100644
--- a/fs/lockd/clntxdr.c
+++ b/fs/lockd/clntxdr.c
@@ -374,8 +374,9 @@ static void encode_nlm_lock(struct xdr_stream *xdr,
  */
 static void nlm_xdr_enc_testargs(struct rpc_rqst *req,
 				 struct xdr_stream *xdr,
-				 const struct nlm_args *args)
+				 const void *data)
 {
+	const struct nlm_args *args = data;
 	const struct nlm_lock *lock = &args->lock;
 
 	encode_cookie(xdr, &args->cookie);
@@ -395,8 +396,9 @@ static void nlm_xdr_enc_testargs(struct rpc_rqst *req,
  */
 static void nlm_xdr_enc_lockargs(struct rpc_rqst *req,
 				 struct xdr_stream *xdr,
-				 const struct nlm_args *args)
+				 const void *data)
 {
+	const struct nlm_args *args = data;
 	const struct nlm_lock *lock = &args->lock;
 
 	encode_cookie(xdr, &args->cookie);
@@ -417,8 +419,9 @@ static void nlm_xdr_enc_lockargs(struct rpc_rqst *req,
  */
 static void nlm_xdr_enc_cancargs(struct rpc_rqst *req,
 				 struct xdr_stream *xdr,
-				 const struct nlm_args *args)
+				 const void *data)
 {
+	const struct nlm_args *args = data;
 	const struct nlm_lock *lock = &args->lock;
 
 	encode_cookie(xdr, &args->cookie);
@@ -435,8 +438,9 @@ static void nlm_xdr_enc_cancargs(struct rpc_rqst *req,
  */
 static void nlm_xdr_enc_unlockargs(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   const struct nlm_args *args)
+				   const void *data)
 {
+	const struct nlm_args *args = data;
 	const struct nlm_lock *lock = &args->lock;
 
 	encode_cookie(xdr, &args->cookie);
@@ -451,8 +455,10 @@ static void nlm_xdr_enc_unlockargs(struct rpc_rqst *req,
  */
 static void nlm_xdr_enc_res(struct rpc_rqst *req,
 			    struct xdr_stream *xdr,
-			    const struct nlm_res *result)
+			    const void *data)
 {
+	const struct nlm_res *result = data;
+
 	encode_cookie(xdr, &result->cookie);
 	encode_nlm_stat(xdr, result->status);
 }
@@ -479,8 +485,10 @@ static void encode_nlm_testrply(struct xdr_stream *xdr,
 
 static void nlm_xdr_enc_testres(struct rpc_rqst *req,
 				struct xdr_stream *xdr,
-				const struct nlm_res *result)
+				const void *data)
 {
+	const struct nlm_res *result = data;
+
 	encode_cookie(xdr, &result->cookie);
 	encode_nlm_stat(xdr, result->status);
 	encode_nlm_testrply(xdr, result);
@@ -523,8 +531,9 @@ out:
 
 static int nlm_xdr_dec_testres(struct rpc_rqst *req,
 			       struct xdr_stream *xdr,
-			       struct nlm_res *result)
+			       void *data)
 {
+	struct nlm_res *result = data;
 	int error;
 
 	error = decode_cookie(xdr, &result->cookie);
@@ -543,8 +552,9 @@ out:
  */
 static int nlm_xdr_dec_res(struct rpc_rqst *req,
 			   struct xdr_stream *xdr,
-			   struct nlm_res *result)
+			   void *data)
 {
+	struct nlm_res *result = data;
 	int error;
 
 	error = decode_cookie(xdr, &result->cookie);
@@ -564,15 +574,15 @@ out:
 #define PROC(proc, argtype, restype)	\
 [NLMPROC_##proc] = {							\
 	.p_proc      = NLMPROC_##proc,					\
-	.p_encode    = (kxdreproc_t)nlm_xdr_enc_##argtype,		\
-	.p_decode    = (kxdrdproc_t)nlm_xdr_dec_##restype,		\
+	.p_encode    = nlm_xdr_enc_##argtype,		\
+	.p_decode    = nlm_xdr_dec_##restype,				\
 	.p_arglen    = NLM_##argtype##_sz,				\
 	.p_replen    = NLM_##restype##_sz,				\
 	.p_statidx   = NLMPROC_##proc,					\
 	.p_name      = #proc,						\
 	}
 
-static struct rpc_procinfo	nlm_procedures[] = {
+static const struct rpc_procinfo nlm_procedures[] = {
 	PROC(TEST,		testargs,	testres),
 	PROC(LOCK,		lockargs,	res),
 	PROC(CANCEL,		cancargs,	res),
@@ -590,16 +600,20 @@ static struct rpc_procinfo	nlm_procedures[] = {
 	PROC(GRANTED_RES,	res,		norep),
 };
 
+static unsigned int nlm_version1_counts[ARRAY_SIZE(nlm_procedures)];
 static const struct rpc_version	nlm_version1 = {
-		.number		= 1,
-		.nrprocs	= ARRAY_SIZE(nlm_procedures),
-		.procs		= nlm_procedures,
+	.number		= 1,
+	.nrprocs	= ARRAY_SIZE(nlm_procedures),
+	.procs		= nlm_procedures,
+	.counts		= nlm_version1_counts,
 };
 
+static unsigned int nlm_version3_counts[ARRAY_SIZE(nlm_procedures)];
 static const struct rpc_version	nlm_version3 = {
-		.number		= 3,
-		.nrprocs	= ARRAY_SIZE(nlm_procedures),
-		.procs		= nlm_procedures,
+	.number		= 3,
+	.nrprocs	= ARRAY_SIZE(nlm_procedures),
+	.procs		= nlm_procedures,
+	.counts		= nlm_version3_counts,
 };
 
 static const struct rpc_version	*nlm_versions[] = {
@@ -613,9 +627,9 @@ static const struct rpc_version	*nlm_versions[] = {
 static struct rpc_stat		nlm_rpc_stats;
 
 const struct rpc_program	nlm_program = {
-		.name		= "lockd",
-		.number		= NLM_PROGRAM,
-		.nrvers		= ARRAY_SIZE(nlm_versions),
-		.version	= nlm_versions,
-		.stats		= &nlm_rpc_stats,
+	.name		= "lockd",
+	.number		= NLM_PROGRAM,
+	.nrvers		= ARRAY_SIZE(nlm_versions),
+	.version	= nlm_versions,
+	.stats		= &nlm_rpc_stats,
 };
diff --git a/fs/lockd/mon.c b/fs/lockd/mon.c
index 19166d4a8d31..9d8166c39c54 100644
--- a/fs/lockd/mon.c
+++ b/fs/lockd/mon.c
@@ -476,22 +476,23 @@ static void encode_priv(struct xdr_stream *xdr, const struct nsm_args *argp)
 }
 
 static void nsm_xdr_enc_mon(struct rpc_rqst *req, struct xdr_stream *xdr,
-			    const struct nsm_args *argp)
+			    const void *argp)
 {
 	encode_mon_id(xdr, argp);
 	encode_priv(xdr, argp);
 }
 
 static void nsm_xdr_enc_unmon(struct rpc_rqst *req, struct xdr_stream *xdr,
-			      const struct nsm_args *argp)
+			      const void *argp)
 {
 	encode_mon_id(xdr, argp);
 }
 
 static int nsm_xdr_dec_stat_res(struct rpc_rqst *rqstp,
 				struct xdr_stream *xdr,
-				struct nsm_res *resp)
+				void *data)
 {
+	struct nsm_res *resp = data;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4 + 4);
@@ -507,8 +508,9 @@ static int nsm_xdr_dec_stat_res(struct rpc_rqst *rqstp,
 
 static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp,
 			    struct xdr_stream *xdr,
-			    struct nsm_res *resp)
+			    void *data)
 {
+	struct nsm_res *resp = data;
 	__be32 *p;
 
 	p = xdr_inline_decode(xdr, 4);
@@ -529,11 +531,11 @@ static int nsm_xdr_dec_stat(struct rpc_rqst *rqstp,
 #define SM_monres_sz	2
 #define SM_unmonres_sz	1
 
-static struct rpc_procinfo	nsm_procedures[] = {
+static const struct rpc_procinfo nsm_procedures[] = {
 [NSMPROC_MON] = {
 		.p_proc		= NSMPROC_MON,
-		.p_encode	= (kxdreproc_t)nsm_xdr_enc_mon,
-		.p_decode	= (kxdrdproc_t)nsm_xdr_dec_stat_res,
+		.p_encode	= nsm_xdr_enc_mon,
+		.p_decode	= nsm_xdr_dec_stat_res,
 		.p_arglen	= SM_mon_sz,
 		.p_replen	= SM_monres_sz,
 		.p_statidx	= NSMPROC_MON,
@@ -541,8 +543,8 @@ static struct rpc_procinfo	nsm_procedures[] = {
 	},
 [NSMPROC_UNMON] = {
 		.p_proc		= NSMPROC_UNMON,
-		.p_encode	= (kxdreproc_t)nsm_xdr_enc_unmon,
-		.p_decode	= (kxdrdproc_t)nsm_xdr_dec_stat,
+		.p_encode	= nsm_xdr_enc_unmon,
+		.p_decode	= nsm_xdr_dec_stat,
 		.p_arglen	= SM_mon_id_sz,
 		.p_replen	= SM_unmonres_sz,
 		.p_statidx	= NSMPROC_UNMON,
@@ -550,10 +552,12 @@ static struct rpc_procinfo	nsm_procedures[] = {
 	},
 };
 
+static unsigned int nsm_version1_counts[ARRAY_SIZE(nsm_procedures)];
 static const struct rpc_version nsm_version1 = {
-		.number		= 1,
-		.nrprocs	= ARRAY_SIZE(nsm_procedures),
-		.procs		= nsm_procedures
+	.number		= 1,
+	.nrprocs	= ARRAY_SIZE(nsm_procedures),
+	.procs		= nsm_procedures,
+	.counts		= nsm_version1_counts,
 };
 
 static const struct rpc_version *nsm_version[] = {
@@ -563,9 +567,9 @@ static const struct rpc_version *nsm_version[] = {
 static struct rpc_stat		nsm_stats;
 
 static const struct rpc_program nsm_program = {
-		.name		= "statd",
-		.number		= NSM_PROGRAM,
-		.nrvers		= ARRAY_SIZE(nsm_version),
-		.version	= nsm_version,
-		.stats		= &nsm_stats
+	.name		= "statd",
+	.number		= NSM_PROGRAM,
+	.nrvers		= ARRAY_SIZE(nsm_version),
+	.version	= nsm_version,
+	.stats		= &nsm_stats
 };
diff --git a/fs/lockd/svc.c b/fs/lockd/svc.c
index 1c13dd80744f..726b6cecf430 100644
--- a/fs/lockd/svc.c
+++ b/fs/lockd/svc.c
@@ -17,7 +17,7 @@
 #include <linux/sysctl.h>
 #include <linux/moduleparam.h>
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/in.h>
 #include <linux/uio.h>
@@ -132,6 +132,8 @@ lockd(void *vrqstp)
 {
 	int		err = 0;
 	struct svc_rqst *rqstp = vrqstp;
+	struct net *net = &init_net;
+	struct lockd_net *ln = net_generic(net, lockd_net_id);
 
 	/* try_to_freeze() is called from svc_recv() */
 	set_freezable();
@@ -176,6 +178,8 @@ lockd(void *vrqstp)
 	if (nlmsvc_ops)
 		nlmsvc_invalidate_all();
 	nlm_shutdown_hosts();
+	cancel_delayed_work_sync(&ln->grace_period_end);
+	locks_end_grace(&ln->lockd_manager);
 	return 0;
 }
 
@@ -270,8 +274,6 @@ static void lockd_down_net(struct svc_serv *serv, struct net *net)
 	if (ln->nlmsvc_users) {
 		if (--ln->nlmsvc_users == 0) {
 			nlm_shutdown_hosts_net(net);
-			cancel_delayed_work_sync(&ln->grace_period_end);
-			locks_end_grace(&ln->lockd_manager);
 			svc_shutdown_net(serv, net);
 			dprintk("lockd_down_net: per-net data destroyed; net=%p\n", net);
 		}
@@ -322,6 +324,8 @@ static int lockd_inet6addr_event(struct notifier_block *this,
 		dprintk("lockd_inet6addr_event: removed %pI6\n", &ifa->addr);
 		sin6.sin6_family = AF_INET6;
 		sin6.sin6_addr = ifa->addr;
+		if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
+			sin6.sin6_scope_id = ifa->idev->dev->ifindex;
 		svc_age_temp_xprts_now(nlmsvc_rqst->rq_server,
 			(struct sockaddr *)&sin6);
 	}
@@ -735,27 +739,33 @@ module_exit(exit_nlm);
 /*
  * Define NLM program and procedures
  */
-static struct svc_version	nlmsvc_version1 = {
-		.vs_vers	= 1,
-		.vs_nproc	= 17,
-		.vs_proc	= nlmsvc_procedures,
-		.vs_xdrsize	= NLMSVC_XDRSIZE,
+static unsigned int nlmsvc_version1_count[17];
+static const struct svc_version	nlmsvc_version1 = {
+	.vs_vers	= 1,
+	.vs_nproc	= 17,
+	.vs_proc	= nlmsvc_procedures,
+	.vs_count	= nlmsvc_version1_count,
+	.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
-static struct svc_version	nlmsvc_version3 = {
-		.vs_vers	= 3,
-		.vs_nproc	= 24,
-		.vs_proc	= nlmsvc_procedures,
-		.vs_xdrsize	= NLMSVC_XDRSIZE,
+static unsigned int nlmsvc_version3_count[24];
+static const struct svc_version	nlmsvc_version3 = {
+	.vs_vers	= 3,
+	.vs_nproc	= 24,
+	.vs_proc	= nlmsvc_procedures,
+	.vs_count	= nlmsvc_version3_count,
+	.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
 #ifdef CONFIG_LOCKD_V4
-static struct svc_version	nlmsvc_version4 = {
-		.vs_vers	= 4,
-		.vs_nproc	= 24,
-		.vs_proc	= nlmsvc_procedures4,
-		.vs_xdrsize	= NLMSVC_XDRSIZE,
+static unsigned int nlmsvc_version4_count[24];
+static const struct svc_version	nlmsvc_version4 = {
+	.vs_vers	= 4,
+	.vs_nproc	= 24,
+	.vs_proc	= nlmsvc_procedures4,
+	.vs_count	= nlmsvc_version4_count,
+	.vs_xdrsize	= NLMSVC_XDRSIZE,
 };
 #endif
-static struct svc_version *	nlmsvc_version[] = {
+static const struct svc_version *nlmsvc_version[] = {
 	[1] = &nlmsvc_version1,
 	[3] = &nlmsvc_version3,
 #ifdef CONFIG_LOCKD_V4
diff --git a/fs/lockd/svc4proc.c b/fs/lockd/svc4proc.c
index 09c576f26c7b..82925f17ec45 100644
--- a/fs/lockd/svc4proc.c
+++ b/fs/lockd/svc4proc.c
@@ -62,7 +62,7 @@ no_locks:
  * NULL: Test for presence of service
  */
 static __be32
-nlm4svc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nlm4svc_proc_null(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: NULL          called\n");
 	return rpc_success;
@@ -72,9 +72,9 @@ nlm4svc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
  * TEST: Check for conflicting lock
  */
 static __be32
-nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
-				         struct nlm_res  *resp)
+__nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	__be32 rc = rpc_success;
@@ -99,9 +99,15 @@ nlm4svc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
 }
 
 static __be32
-nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				         struct nlm_res  *resp)
+nlm4svc_proc_test(struct svc_rqst *rqstp)
 {
+	return __nlm4svc_proc_test(rqstp, rqstp->rq_resp);
+}
+
+static __be32
+__nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp)
+{
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	__be32 rc = rpc_success;
@@ -141,9 +147,15 @@ nlm4svc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 }
 
 static __be32
-nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
-				           struct nlm_res  *resp)
+nlm4svc_proc_lock(struct svc_rqst *rqstp)
+{
+	return __nlm4svc_proc_lock(rqstp, rqstp->rq_resp);
+}
+
+static __be32
+__nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -170,13 +182,19 @@ nlm4svc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlm4svc_proc_cancel(struct svc_rqst *rqstp)
+{
+	return __nlm4svc_proc_cancel(rqstp, rqstp->rq_resp);
+}
+
 /*
  * UNLOCK: release a lock
  */
 static __be32
-nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				           struct nlm_res  *resp)
+__nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -203,14 +221,21 @@ nlm4svc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlm4svc_proc_unlock(struct svc_rqst *rqstp)
+{
+	return __nlm4svc_proc_unlock(rqstp, rqstp->rq_resp);
+}
+
 /*
  * GRANTED: A server calls us to tell that a process' lock request
  * was granted
  */
 static __be32
-nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+__nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	resp->cookie = argp->cookie;
 
 	dprintk("lockd: GRANTED       called\n");
@@ -219,6 +244,12 @@ nlm4svc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlm4svc_proc_granted(struct svc_rqst *rqstp)
+{
+	return __nlm4svc_proc_granted(rqstp, rqstp->rq_resp);
+}
+
 /*
  * This is the generic lockd callback for async RPC calls
  */
@@ -243,9 +274,10 @@ static const struct rpc_call_ops nlm4svc_callback_ops = {
  * because we send the callback before the reply proper. I hope this
  * doesn't break any clients.
  */
-static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args *argp,
-		__be32 (*func)(struct svc_rqst *, struct nlm_args *, struct nlm_res  *))
+static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc,
+		__be32 (*func)(struct svc_rqst *,  struct nlm_res *))
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_rqst	*call;
 	__be32 stat;
@@ -261,7 +293,7 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 	if (call == NULL)
 		return rpc_system_err;
 
-	stat = func(rqstp, argp, &call->a_res);
+	stat = func(rqstp, &call->a_res);
 	if (stat != 0) {
 		nlmsvc_release_call(call);
 		return stat;
@@ -273,48 +305,44 @@ static __be32 nlm4svc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 	return rpc_success;
 }
 
-static __be32 nlm4svc_proc_test_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void	     *resp)
+static __be32 nlm4svc_proc_test_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: TEST_MSG      called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_TEST_RES, argp, nlm4svc_proc_test);
+	return nlm4svc_callback(rqstp, NLMPROC_TEST_RES, __nlm4svc_proc_test);
 }
 
-static __be32 nlm4svc_proc_lock_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void	     *resp)
+static __be32 nlm4svc_proc_lock_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: LOCK_MSG      called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_LOCK_RES, argp, nlm4svc_proc_lock);
+	return nlm4svc_callback(rqstp, NLMPROC_LOCK_RES, __nlm4svc_proc_lock);
 }
 
-static __be32 nlm4svc_proc_cancel_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					       void	       *resp)
+static __be32 nlm4svc_proc_cancel_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: CANCEL_MSG    called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_CANCEL_RES, argp, nlm4svc_proc_cancel);
+	return nlm4svc_callback(rqstp, NLMPROC_CANCEL_RES, __nlm4svc_proc_cancel);
 }
 
-static __be32 nlm4svc_proc_unlock_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-                                               void            *resp)
+static __be32 nlm4svc_proc_unlock_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: UNLOCK_MSG    called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_UNLOCK_RES, argp, nlm4svc_proc_unlock);
+	return nlm4svc_callback(rqstp, NLMPROC_UNLOCK_RES, __nlm4svc_proc_unlock);
 }
 
-static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-                                                void            *resp)
+static __be32 nlm4svc_proc_granted_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: GRANTED_MSG   called\n");
-	return nlm4svc_callback(rqstp, NLMPROC_GRANTED_RES, argp, nlm4svc_proc_granted);
+	return nlm4svc_callback(rqstp, NLMPROC_GRANTED_RES, __nlm4svc_proc_granted);
 }
 
 /*
  * SHARE: create a DOS share or alter existing share.
  */
 static __be32
-nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
-				          struct nlm_res  *resp)
+nlm4svc_proc_share(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+	struct nlm_res *resp = rqstp->rq_resp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -345,9 +373,10 @@ nlm4svc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
  * UNSHARE: Release a DOS share.
  */
 static __be32
-nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+nlm4svc_proc_unshare(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+	struct nlm_res *resp = rqstp->rq_resp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -378,22 +407,23 @@ nlm4svc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
  * NM_LOCK: Create an unmonitored lock
  */
 static __be32
-nlm4svc_proc_nm_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+nlm4svc_proc_nm_lock(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	dprintk("lockd: NM_LOCK       called\n");
 
 	argp->monitor = 0;		/* just clean the monitor flag */
-	return nlm4svc_proc_lock(rqstp, argp, resp);
+	return nlm4svc_proc_lock(rqstp);
 }
 
 /*
  * FREE_ALL: Release all locks and shares held by client
  */
 static __be32
-nlm4svc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void            *resp)
+nlm4svc_proc_free_all(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 
 	/* Obtain client */
@@ -409,9 +439,10 @@ nlm4svc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp,
  * SM_NOTIFY: private callback from statd (not part of official NLM proto)
  */
 static __be32
-nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
-					      void	        *resp)
+nlm4svc_proc_sm_notify(struct svc_rqst *rqstp)
 {
+	struct nlm_reboot *argp = rqstp->rq_argp;
+
 	dprintk("lockd: SM_NOTIFY     called\n");
 
 	if (!nlm_privileged_requester(rqstp)) {
@@ -429,9 +460,10 @@ nlm4svc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
  * client sent a GRANTED_RES, let's remove the associated block
  */
 static __be32
-nlm4svc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res  *argp,
-                                                void            *resp)
+nlm4svc_proc_granted_res(struct svc_rqst *rqstp)
 {
+	struct nlm_res *argp = rqstp->rq_argp;
+
         if (!nlmsvc_ops)
                 return rpc_success;
 
@@ -463,9 +495,9 @@ nlm4svc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res  *argp,
 struct nlm_void			{ int dummy; };
 
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
- { .pc_func	= (svc_procfunc) nlm4svc_proc_##name,	\
-   .pc_decode	= (kxdrproc_t) nlm4svc_decode_##xargt,	\
-   .pc_encode	= (kxdrproc_t) nlm4svc_encode_##xrest,	\
+ { .pc_func	= nlm4svc_proc_##name,	\
+   .pc_decode	= nlm4svc_decode_##xargt,	\
+   .pc_encode	= nlm4svc_encode_##xrest,	\
    .pc_release	= NULL,					\
    .pc_argsize	= sizeof(struct nlm_##argt),		\
    .pc_ressize	= sizeof(struct nlm_##rest),		\
@@ -475,7 +507,7 @@ struct nlm_void			{ int dummy; };
 #define	No	(1+1024/4)				/* netobj */
 #define	St	1					/* status */
 #define	Rg	4					/* range (offset + length) */
-struct svc_procedure		nlmsvc_procedures4[] = {
+const struct svc_procedure nlmsvc_procedures4[] = {
   PROC(null,		void,		void,		void,	void, 1),
   PROC(test,		testargs,	testres,	args,	res, Ck+St+2+No+Rg),
   PROC(lock,		lockargs,	res,		args,	res, Ck+St),
diff --git a/fs/lockd/svclock.c b/fs/lockd/svclock.c
index 5581e020644b..3507c80d1d4b 100644
--- a/fs/lockd/svclock.c
+++ b/fs/lockd/svclock.c
@@ -870,15 +870,15 @@ nlmsvc_grant_reply(struct nlm_cookie *cookie, __be32 status)
 	if (!(block = nlmsvc_find_block(cookie)))
 		return;
 
-	if (block) {
-		if (status == nlm_lck_denied_grace_period) {
-			/* Try again in a couple of seconds */
-			nlmsvc_insert_block(block, 10 * HZ);
-		} else {
-			/* Lock is now held by client, or has been rejected.
-			 * In both cases, the block should be removed. */
-			nlmsvc_unlink_block(block);
-		}
+	if (status == nlm_lck_denied_grace_period) {
+		/* Try again in a couple of seconds */
+		nlmsvc_insert_block(block, 10 * HZ);
+	} else {
+		/*
+		 * Lock is now held by client, or has been rejected.
+		 * In both cases, the block should be removed.
+		 */
+		nlmsvc_unlink_block(block);
 	}
 	nlmsvc_release_block(block);
 }
diff --git a/fs/lockd/svcproc.c b/fs/lockd/svcproc.c
index fb26b9f522e7..07915162581d 100644
--- a/fs/lockd/svcproc.c
+++ b/fs/lockd/svcproc.c
@@ -92,7 +92,7 @@ no_locks:
  * NULL: Test for presence of service
  */
 static __be32
-nlmsvc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nlmsvc_proc_null(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: NULL          called\n");
 	return rpc_success;
@@ -102,9 +102,9 @@ nlmsvc_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
  * TEST: Check for conflicting lock
  */
 static __be32
-nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
-				         struct nlm_res  *resp)
+__nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	__be32 rc = rpc_success;
@@ -130,9 +130,15 @@ nlmsvc_proc_test(struct svc_rqst *rqstp, struct nlm_args *argp,
 }
 
 static __be32
-nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				         struct nlm_res  *resp)
+nlmsvc_proc_test(struct svc_rqst *rqstp)
 {
+	return __nlmsvc_proc_test(rqstp, rqstp->rq_resp);
+}
+
+static __be32
+__nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_res *resp)
+{
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	__be32 rc = rpc_success;
@@ -172,9 +178,15 @@ nlmsvc_proc_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
 }
 
 static __be32
-nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
-				           struct nlm_res  *resp)
+nlmsvc_proc_lock(struct svc_rqst *rqstp)
+{
+	return __nlmsvc_proc_lock(rqstp, rqstp->rq_resp);
+}
+
+static __be32
+__nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	struct net *net = SVC_NET(rqstp);
@@ -202,13 +214,19 @@ nlmsvc_proc_cancel(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlmsvc_proc_cancel(struct svc_rqst *rqstp)
+{
+	return __nlmsvc_proc_cancel(rqstp, rqstp->rq_resp);
+}
+
 /*
  * UNLOCK: release a lock
  */
 static __be32
-nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				           struct nlm_res  *resp)
+__nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 	struct net *net = SVC_NET(rqstp);
@@ -236,14 +254,21 @@ nlmsvc_proc_unlock(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlmsvc_proc_unlock(struct svc_rqst *rqstp)
+{
+	return __nlmsvc_proc_unlock(rqstp, rqstp->rq_resp);
+}
+
 /*
  * GRANTED: A server calls us to tell that a process' lock request
  * was granted
  */
 static __be32
-nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+__nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_res *resp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	resp->cookie = argp->cookie;
 
 	dprintk("lockd: GRANTED       called\n");
@@ -252,6 +277,12 @@ nlmsvc_proc_granted(struct svc_rqst *rqstp, struct nlm_args *argp,
 	return rpc_success;
 }
 
+static __be32
+nlmsvc_proc_granted(struct svc_rqst *rqstp)
+{
+	return __nlmsvc_proc_granted(rqstp, rqstp->rq_resp);
+}
+
 /*
  * This is the generic lockd callback for async RPC calls
  */
@@ -284,9 +315,10 @@ static const struct rpc_call_ops nlmsvc_callback_ops = {
  * because we send the callback before the reply proper. I hope this
  * doesn't break any clients.
  */
-static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args *argp,
-		__be32 (*func)(struct svc_rqst *, struct nlm_args *, struct nlm_res  *))
+static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc,
+		__be32 (*func)(struct svc_rqst *, struct nlm_res *))
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 	struct nlm_rqst	*call;
 	__be32 stat;
@@ -302,7 +334,7 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 	if (call == NULL)
 		return rpc_system_err;
 
-	stat = func(rqstp, argp, &call->a_res);
+	stat = func(rqstp, &call->a_res);
 	if (stat != 0) {
 		nlmsvc_release_call(call);
 		return stat;
@@ -314,50 +346,46 @@ static __be32 nlmsvc_callback(struct svc_rqst *rqstp, u32 proc, struct nlm_args
 	return rpc_success;
 }
 
-static __be32 nlmsvc_proc_test_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void	     *resp)
+static __be32 nlmsvc_proc_test_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: TEST_MSG      called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_TEST_RES, argp, nlmsvc_proc_test);
+	return nlmsvc_callback(rqstp, NLMPROC_TEST_RES, __nlmsvc_proc_test);
 }
 
-static __be32 nlmsvc_proc_lock_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void	     *resp)
+static __be32 nlmsvc_proc_lock_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: LOCK_MSG      called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_LOCK_RES, argp, nlmsvc_proc_lock);
+	return nlmsvc_callback(rqstp, NLMPROC_LOCK_RES, __nlmsvc_proc_lock);
 }
 
-static __be32 nlmsvc_proc_cancel_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-					       void	       *resp)
+static __be32 nlmsvc_proc_cancel_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: CANCEL_MSG    called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_CANCEL_RES, argp, nlmsvc_proc_cancel);
+	return nlmsvc_callback(rqstp, NLMPROC_CANCEL_RES, __nlmsvc_proc_cancel);
 }
 
 static __be32
-nlmsvc_proc_unlock_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-                                               void            *resp)
+nlmsvc_proc_unlock_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: UNLOCK_MSG    called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_UNLOCK_RES, argp, nlmsvc_proc_unlock);
+	return nlmsvc_callback(rqstp, NLMPROC_UNLOCK_RES, __nlmsvc_proc_unlock);
 }
 
 static __be32
-nlmsvc_proc_granted_msg(struct svc_rqst *rqstp, struct nlm_args *argp,
-                                                void            *resp)
+nlmsvc_proc_granted_msg(struct svc_rqst *rqstp)
 {
 	dprintk("lockd: GRANTED_MSG   called\n");
-	return nlmsvc_callback(rqstp, NLMPROC_GRANTED_RES, argp, nlmsvc_proc_granted);
+	return nlmsvc_callback(rqstp, NLMPROC_GRANTED_RES, __nlmsvc_proc_granted);
 }
 
 /*
  * SHARE: create a DOS share or alter existing share.
  */
 static __be32
-nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
-				          struct nlm_res  *resp)
+nlmsvc_proc_share(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+	struct nlm_res *resp = rqstp->rq_resp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -388,9 +416,10 @@ nlmsvc_proc_share(struct svc_rqst *rqstp, struct nlm_args *argp,
  * UNSHARE: Release a DOS share.
  */
 static __be32
-nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+nlmsvc_proc_unshare(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+	struct nlm_res *resp = rqstp->rq_resp;
 	struct nlm_host	*host;
 	struct nlm_file	*file;
 
@@ -421,22 +450,23 @@ nlmsvc_proc_unshare(struct svc_rqst *rqstp, struct nlm_args *argp,
  * NM_LOCK: Create an unmonitored lock
  */
 static __be32
-nlmsvc_proc_nm_lock(struct svc_rqst *rqstp, struct nlm_args *argp,
-				            struct nlm_res  *resp)
+nlmsvc_proc_nm_lock(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	dprintk("lockd: NM_LOCK       called\n");
 
 	argp->monitor = 0;		/* just clean the monitor flag */
-	return nlmsvc_proc_lock(rqstp, argp, resp);
+	return nlmsvc_proc_lock(rqstp);
 }
 
 /*
  * FREE_ALL: Release all locks and shares held by client
  */
 static __be32
-nlmsvc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp,
-					     void            *resp)
+nlmsvc_proc_free_all(struct svc_rqst *rqstp)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_host	*host;
 
 	/* Obtain client */
@@ -452,9 +482,10 @@ nlmsvc_proc_free_all(struct svc_rqst *rqstp, struct nlm_args *argp,
  * SM_NOTIFY: private callback from statd (not part of official NLM proto)
  */
 static __be32
-nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
-					      void	        *resp)
+nlmsvc_proc_sm_notify(struct svc_rqst *rqstp)
 {
+	struct nlm_reboot *argp = rqstp->rq_argp;
+
 	dprintk("lockd: SM_NOTIFY     called\n");
 
 	if (!nlm_privileged_requester(rqstp)) {
@@ -472,9 +503,10 @@ nlmsvc_proc_sm_notify(struct svc_rqst *rqstp, struct nlm_reboot *argp,
  * client sent a GRANTED_RES, let's remove the associated block
  */
 static __be32
-nlmsvc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res  *argp,
-                                                void            *resp)
+nlmsvc_proc_granted_res(struct svc_rqst *rqstp)
 {
+	struct nlm_res *argp = rqstp->rq_argp;
+
 	if (!nlmsvc_ops)
 		return rpc_success;
 
@@ -505,9 +537,9 @@ nlmsvc_proc_granted_res(struct svc_rqst *rqstp, struct nlm_res  *argp,
 struct nlm_void			{ int dummy; };
 
 #define PROC(name, xargt, xrest, argt, rest, respsize)	\
- { .pc_func	= (svc_procfunc) nlmsvc_proc_##name,	\
-   .pc_decode	= (kxdrproc_t) nlmsvc_decode_##xargt,	\
-   .pc_encode	= (kxdrproc_t) nlmsvc_encode_##xrest,	\
+ { .pc_func	= nlmsvc_proc_##name,			\
+   .pc_decode	= nlmsvc_decode_##xargt,		\
+   .pc_encode	= nlmsvc_encode_##xrest,		\
    .pc_release	= NULL,					\
    .pc_argsize	= sizeof(struct nlm_##argt),		\
    .pc_ressize	= sizeof(struct nlm_##rest),		\
@@ -519,7 +551,7 @@ struct nlm_void			{ int dummy; };
 #define	No	(1+1024/4)			/* Net Obj */
 #define	Rg	2				/* range - offset + size */
 
-struct svc_procedure		nlmsvc_procedures[] = {
+const struct svc_procedure nlmsvc_procedures[] = {
   PROC(null,		void,		void,		void,	void, 1),
   PROC(test,		testargs,	testres,	args,	res, Ck+St+2+No+Rg),
   PROC(lock,		lockargs,	res,		args,	res, Ck+St),
diff --git a/fs/lockd/xdr.c b/fs/lockd/xdr.c
index 5b651daad518..442bbd0b0b29 100644
--- a/fs/lockd/xdr.c
+++ b/fs/lockd/xdr.c
@@ -182,8 +182,9 @@ nlm_encode_testres(__be32 *p, struct nlm_res *resp)
  * First, the server side XDR functions
  */
 int
-nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm_decode_cookie(p, &argp->cookie)))
@@ -199,16 +200,19 @@ nlmsvc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlmsvc_encode_testres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm_encode_testres(p, resp)))
 		return 0;
 	return xdr_ressize_check(rqstp, p);
 }
 
 int
-nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm_decode_cookie(p, &argp->cookie)))
@@ -227,8 +231,9 @@ nlmsvc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm_decode_cookie(p, &argp->cookie)))
@@ -243,8 +248,10 @@ nlmsvc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	if (!(p = nlm_decode_cookie(p, &argp->cookie))
 	 || !(p = nlm_decode_lock(p, &argp->lock)))
 		return 0;
@@ -253,8 +260,9 @@ nlmsvc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
 	memset(lock, 0, sizeof(*lock));
@@ -274,8 +282,10 @@ nlmsvc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm_encode_cookie(p, &resp->cookie)))
 		return 0;
 	*p++ = resp->status;
@@ -284,8 +294,10 @@ nlmsvc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm_encode_cookie(p, &resp->cookie)))
 		return 0;
 	*p++ = resp->status;
@@ -293,8 +305,9 @@ nlmsvc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp)
+nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
 	if (!(p = xdr_decode_string_inplace(p, &lock->caller,
@@ -305,8 +318,10 @@ nlmsvc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp)
 }
 
 int
-nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp)
+nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_reboot *argp = rqstp->rq_argp;
+
 	if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN)))
 		return 0;
 	argp->state = ntohl(*p++);
@@ -316,8 +331,10 @@ nlmsvc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp)
 }
 
 int
-nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_argp;
+
 	if (!(p = nlm_decode_cookie(p, &resp->cookie)))
 		return 0;
 	resp->status = *p++;
@@ -325,13 +342,13 @@ nlmsvc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nlmsvc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_argsize_check(rqstp, p);
 }
 
 int
-nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nlmsvc_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
diff --git a/fs/lockd/xdr4.c b/fs/lockd/xdr4.c
index dfa4789cd460..2a0cd5679c49 100644
--- a/fs/lockd/xdr4.c
+++ b/fs/lockd/xdr4.c
@@ -179,8 +179,9 @@ nlm4_encode_testres(__be32 *p, struct nlm_res *resp)
  * First, the server side XDR functions
  */
 int
-nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie)))
@@ -196,16 +197,19 @@ nlm4svc_decode_testargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlm4svc_encode_testres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm4_encode_testres(p, resp)))
 		return 0;
 	return xdr_ressize_check(rqstp, p);
 }
 
 int
-nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie)))
@@ -224,8 +228,9 @@ nlm4svc_decode_lockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	u32	exclusive;
 
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie)))
@@ -240,8 +245,10 @@ nlm4svc_decode_cancargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
+
 	if (!(p = nlm4_decode_cookie(p, &argp->cookie))
 	 || !(p = nlm4_decode_lock(p, &argp->lock)))
 		return 0;
@@ -250,8 +257,9 @@ nlm4svc_decode_unlockargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
+nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
 	memset(lock, 0, sizeof(*lock));
@@ -271,8 +279,10 @@ nlm4svc_decode_shareargs(struct svc_rqst *rqstp, __be32 *p, nlm_args *argp)
 }
 
 int
-nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm4_encode_cookie(p, &resp->cookie)))
 		return 0;
 	*p++ = resp->status;
@@ -281,8 +291,10 @@ nlm4svc_encode_shareres(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_resp;
+
 	if (!(p = nlm4_encode_cookie(p, &resp->cookie)))
 		return 0;
 	*p++ = resp->status;
@@ -290,8 +302,9 @@ nlm4svc_encode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp)
+nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_args *argp = rqstp->rq_argp;
 	struct nlm_lock	*lock = &argp->lock;
 
 	if (!(p = xdr_decode_string_inplace(p, &lock->caller,
@@ -302,8 +315,10 @@ nlm4svc_decode_notify(struct svc_rqst *rqstp, __be32 *p, struct nlm_args *argp)
 }
 
 int
-nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp)
+nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_reboot *argp = rqstp->rq_argp;
+
 	if (!(p = xdr_decode_string_inplace(p, &argp->mon, &argp->len, SM_MAXSTRLEN)))
 		return 0;
 	argp->state = ntohl(*p++);
@@ -313,8 +328,10 @@ nlm4svc_decode_reboot(struct svc_rqst *rqstp, __be32 *p, struct nlm_reboot *argp
 }
 
 int
-nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
+nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nlm_res *resp = rqstp->rq_argp;
+
 	if (!(p = nlm4_decode_cookie(p, &resp->cookie)))
 		return 0;
 	resp->status = *p++;
@@ -322,13 +339,13 @@ nlm4svc_decode_res(struct svc_rqst *rqstp, __be32 *p, struct nlm_res *resp)
 }
 
 int
-nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nlm4svc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_argsize_check(rqstp, p);
 }
 
 int
-nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nlm4svc_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
diff --git a/fs/locks.c b/fs/locks.c
index 26811321d39b..afefeb4ad6de 100644
--- a/fs/locks.c
+++ b/fs/locks.c
@@ -1858,8 +1858,8 @@ EXPORT_SYMBOL(generic_setlease);
  *
  * Call this to establish a lease on the file. The "lease" argument is not
  * used for F_UNLCK requests and may be NULL. For commands that set or alter
- * an existing lease, the (*lease)->fl_lmops->lm_break operation must be set;
- * if not, this function will return -ENOLCK (and generate a scary-looking
+ * an existing lease, the ``(*lease)->fl_lmops->lm_break`` operation must be
+ * set; if not, this function will return -ENOLCK (and generate a scary-looking
  * stack trace).
  *
  * The "priv" pointer is passed directly to the lm_setup function as-is. It
@@ -1972,15 +1972,13 @@ EXPORT_SYMBOL(locks_lock_inode_wait);
  *	@cmd: the type of lock to apply.
  *
  *	Apply a %FL_FLOCK style lock to an open file descriptor.
- *	The @cmd can be one of
+ *	The @cmd can be one of:
  *
- *	%LOCK_SH -- a shared lock.
- *
- *	%LOCK_EX -- an exclusive lock.
- *
- *	%LOCK_UN -- remove an existing lock.
- *
- *	%LOCK_MAND -- a `mandatory' flock.  This exists to emulate Windows Share Modes.
+ *	- %LOCK_SH -- a shared lock.
+ *	- %LOCK_EX -- an exclusive lock.
+ *	- %LOCK_UN -- remove an existing lock.
+ *	- %LOCK_MAND -- a 'mandatory' flock.
+ *	  This exists to emulate Windows Share Modes.
  *
  *	%LOCK_MAND can be combined with %LOCK_READ or %LOCK_WRITE to allow other
  *	processes read and write access respectively.
@@ -2086,26 +2084,22 @@ static void posix_lock_to_flock64(struct flock64 *flock, struct file_lock *fl)
 /* Report the first existing lock that would conflict with l.
  * This implements the F_GETLK command of fcntl().
  */
-int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l)
+int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock *flock)
 {
 	struct file_lock file_lock;
-	struct flock flock;
 	int error;
 
-	error = -EFAULT;
-	if (copy_from_user(&flock, l, sizeof(flock)))
-		goto out;
 	error = -EINVAL;
-	if ((flock.l_type != F_RDLCK) && (flock.l_type != F_WRLCK))
+	if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK)
 		goto out;
 
-	error = flock_to_posix_lock(filp, &file_lock, &flock);
+	error = flock_to_posix_lock(filp, &file_lock, flock);
 	if (error)
 		goto out;
 
 	if (cmd == F_OFD_GETLK) {
 		error = -EINVAL;
-		if (flock.l_pid != 0)
+		if (flock->l_pid != 0)
 			goto out;
 
 		cmd = F_GETLK;
@@ -2117,15 +2111,12 @@ int fcntl_getlk(struct file *filp, unsigned int cmd, struct flock __user *l)
 	if (error)
 		goto out;
  
-	flock.l_type = file_lock.fl_type;
+	flock->l_type = file_lock.fl_type;
 	if (file_lock.fl_type != F_UNLCK) {
-		error = posix_lock_to_flock(&flock, &file_lock);
+		error = posix_lock_to_flock(flock, &file_lock);
 		if (error)
 			goto rel_priv;
 	}
-	error = -EFAULT;
-	if (!copy_to_user(l, &flock, sizeof(flock)))
-		error = 0;
 rel_priv:
 	locks_release_private(&file_lock);
 out:
@@ -2218,26 +2209,16 @@ check_fmode_for_setlk(struct file_lock *fl)
  * This implements both the F_SETLK and F_SETLKW commands of fcntl().
  */
 int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
-		struct flock __user *l)
+		struct flock *flock)
 {
 	struct file_lock *file_lock = locks_alloc_lock();
-	struct flock flock;
-	struct inode *inode;
+	struct inode *inode = locks_inode(filp);
 	struct file *f;
 	int error;
 
 	if (file_lock == NULL)
 		return -ENOLCK;
 
-	inode = locks_inode(filp);
-
-	/*
-	 * This might block, so we do it before checking the inode.
-	 */
-	error = -EFAULT;
-	if (copy_from_user(&flock, l, sizeof(flock)))
-		goto out;
-
 	/* Don't allow mandatory locks on files that may be memory mapped
 	 * and shared.
 	 */
@@ -2246,7 +2227,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 		goto out;
 	}
 
-	error = flock_to_posix_lock(filp, file_lock, &flock);
+	error = flock_to_posix_lock(filp, file_lock, flock);
 	if (error)
 		goto out;
 
@@ -2261,7 +2242,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 	switch (cmd) {
 	case F_OFD_SETLK:
 		error = -EINVAL;
-		if (flock.l_pid != 0)
+		if (flock->l_pid != 0)
 			goto out;
 
 		cmd = F_SETLK;
@@ -2270,7 +2251,7 @@ int fcntl_setlk(unsigned int fd, struct file *filp, unsigned int cmd,
 		break;
 	case F_OFD_SETLKW:
 		error = -EINVAL;
-		if (flock.l_pid != 0)
+		if (flock->l_pid != 0)
 			goto out;
 
 		cmd = F_SETLKW;
@@ -2315,26 +2296,22 @@ out:
 /* Report the first existing lock that would conflict with l.
  * This implements the F_GETLK command of fcntl().
  */
-int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l)
+int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 *flock)
 {
 	struct file_lock file_lock;
-	struct flock64 flock;
 	int error;
 
-	error = -EFAULT;
-	if (copy_from_user(&flock, l, sizeof(flock)))
-		goto out;
 	error = -EINVAL;
-	if ((flock.l_type != F_RDLCK) && (flock.l_type != F_WRLCK))
+	if (flock->l_type != F_RDLCK && flock->l_type != F_WRLCK)
 		goto out;
 
-	error = flock64_to_posix_lock(filp, &file_lock, &flock);
+	error = flock64_to_posix_lock(filp, &file_lock, flock);
 	if (error)
 		goto out;
 
 	if (cmd == F_OFD_GETLK) {
 		error = -EINVAL;
-		if (flock.l_pid != 0)
+		if (flock->l_pid != 0)
 			goto out;
 
 		cmd = F_GETLK64;
@@ -2346,13 +2323,9 @@ int fcntl_getlk64(struct file *filp, unsigned int cmd, struct flock64 __user *l)
 	if (error)
 		goto out;
 
-	flock.l_type = file_lock.fl_type;
+	flock->l_type = file_lock.fl_type;
 	if (file_lock.fl_type != F_UNLCK)
-		posix_lock_to_flock64(&flock, &file_lock);
-
-	error = -EFAULT;
-	if (!copy_to_user(l, &flock, sizeof(flock)))
-		error = 0;
+		posix_lock_to_flock64(flock, &file_lock);
 
 	locks_release_private(&file_lock);
 out:
@@ -2363,26 +2336,16 @@ out:
  * This implements both the F_SETLK and F_SETLKW commands of fcntl().
  */
 int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
-		struct flock64 __user *l)
+		struct flock64 *flock)
 {
 	struct file_lock *file_lock = locks_alloc_lock();
-	struct flock64 flock;
-	struct inode *inode;
+	struct inode *inode = locks_inode(filp);
 	struct file *f;
 	int error;
 
 	if (file_lock == NULL)
 		return -ENOLCK;
 
-	/*
-	 * This might block, so we do it before checking the inode.
-	 */
-	error = -EFAULT;
-	if (copy_from_user(&flock, l, sizeof(flock)))
-		goto out;
-
-	inode = locks_inode(filp);
-
 	/* Don't allow mandatory locks on files that may be memory mapped
 	 * and shared.
 	 */
@@ -2391,7 +2354,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 		goto out;
 	}
 
-	error = flock64_to_posix_lock(filp, file_lock, &flock);
+	error = flock64_to_posix_lock(filp, file_lock, flock);
 	if (error)
 		goto out;
 
@@ -2406,7 +2369,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 	switch (cmd) {
 	case F_OFD_SETLK:
 		error = -EINVAL;
-		if (flock.l_pid != 0)
+		if (flock->l_pid != 0)
 			goto out;
 
 		cmd = F_SETLK64;
@@ -2415,7 +2378,7 @@ int fcntl_setlk64(unsigned int fd, struct file *filp, unsigned int cmd,
 		break;
 	case F_OFD_SETLKW:
 		error = -EINVAL;
-		if (flock.l_pid != 0)
+		if (flock->l_pid != 0)
 			goto out;
 
 		cmd = F_SETLKW64;
@@ -2504,7 +2467,7 @@ locks_remove_flock(struct file *filp, struct file_lock_context *flctx)
 		.fl_owner = filp,
 		.fl_pid = current->tgid,
 		.fl_file = filp,
-		.fl_flags = FL_FLOCK,
+		.fl_flags = FL_FLOCK | FL_CLOSE,
 		.fl_type = F_UNLCK,
 		.fl_end = OFFSET_MAX,
 	};
diff --git a/fs/mbcache.c b/fs/mbcache.c
index b19be429d655..d818fd236787 100644
--- a/fs/mbcache.c
+++ b/fs/mbcache.c
@@ -10,13 +10,14 @@
 /*
  * Mbcache is a simple key-value store. Keys need not be unique, however
  * key-value pairs are expected to be unique (we use this fact in
- * mb_cache_entry_delete_block()).
+ * mb_cache_entry_delete()).
  *
  * Ext2 and ext4 use this cache for deduplication of extended attribute blocks.
- * They use hash of a block contents as a key and block number as a value.
- * That's why keys need not be unique (different xattr blocks may end up having
- * the same hash). However block number always uniquely identifies a cache
- * entry.
+ * Ext4 also uses it for deduplication of xattr values stored in inodes.
+ * They use hash of data as a key and provide a value that may represent a
+ * block or inode number. That's why keys need not be unique (hash of different
+ * data may be the same). However user provided value always uniquely
+ * identifies a cache entry.
  *
  * We provide functions for creation and removal of entries, search by key,
  * and a special "delete entry with given key-value pair" operation. Fixed
@@ -62,15 +63,15 @@ static inline struct hlist_bl_head *mb_cache_entry_head(struct mb_cache *cache,
  * @cache - cache where the entry should be created
  * @mask - gfp mask with which the entry should be allocated
  * @key - key of the entry
- * @block - block that contains data
- * @reusable - is the block reusable by other inodes?
+ * @value - value of the entry
+ * @reusable - is the entry reusable by others?
  *
- * Creates entry in @cache with key @key and records that data is stored in
- * block @block. The function returns -EBUSY if entry with the same key
- * and for the same block already exists in cache. Otherwise 0 is returned.
+ * Creates entry in @cache with key @key and value @value. The function returns
+ * -EBUSY if entry with the same key and value already exists in cache.
+ * Otherwise 0 is returned.
  */
 int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key,
-			  sector_t block, bool reusable)
+			  u64 value, bool reusable)
 {
 	struct mb_cache_entry *entry, *dup;
 	struct hlist_bl_node *dup_node;
@@ -91,12 +92,12 @@ int mb_cache_entry_create(struct mb_cache *cache, gfp_t mask, u32 key,
 	/* One ref for hash, one ref returned */
 	atomic_set(&entry->e_refcnt, 1);
 	entry->e_key = key;
-	entry->e_block = block;
+	entry->e_value = value;
 	entry->e_reusable = reusable;
 	head = mb_cache_entry_head(cache, key);
 	hlist_bl_lock(head);
 	hlist_bl_for_each_entry(dup, dup_node, head, e_hash_list) {
-		if (dup->e_key == key && dup->e_block == block) {
+		if (dup->e_key == key && dup->e_value == value) {
 			hlist_bl_unlock(head);
 			kmem_cache_free(mb_entry_cache, entry);
 			return -EBUSY;
@@ -187,13 +188,13 @@ struct mb_cache_entry *mb_cache_entry_find_next(struct mb_cache *cache,
 EXPORT_SYMBOL(mb_cache_entry_find_next);
 
 /*
- * mb_cache_entry_get - get a cache entry by block number (and key)
+ * mb_cache_entry_get - get a cache entry by value (and key)
  * @cache - cache we work with
- * @key - key of block number @block
- * @block - block number
+ * @key - key
+ * @value - value
  */
 struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key,
-					  sector_t block)
+					  u64 value)
 {
 	struct hlist_bl_node *node;
 	struct hlist_bl_head *head;
@@ -202,7 +203,7 @@ struct mb_cache_entry *mb_cache_entry_get(struct mb_cache *cache, u32 key,
 	head = mb_cache_entry_head(cache, key);
 	hlist_bl_lock(head);
 	hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
-		if (entry->e_key == key && entry->e_block == block) {
+		if (entry->e_key == key && entry->e_value == value) {
 			atomic_inc(&entry->e_refcnt);
 			goto out;
 		}
@@ -214,15 +215,14 @@ out:
 }
 EXPORT_SYMBOL(mb_cache_entry_get);
 
-/* mb_cache_entry_delete_block - remove information about block from cache
+/* mb_cache_entry_delete - remove a cache entry
  * @cache - cache we work with
- * @key - key of block @block
- * @block - block number
+ * @key - key
+ * @value - value
  *
- * Remove entry from cache @cache with key @key with data stored in @block.
+ * Remove entry from cache @cache with key @key and value @value.
  */
-void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key,
-				 sector_t block)
+void mb_cache_entry_delete(struct mb_cache *cache, u32 key, u64 value)
 {
 	struct hlist_bl_node *node;
 	struct hlist_bl_head *head;
@@ -231,7 +231,7 @@ void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key,
 	head = mb_cache_entry_head(cache, key);
 	hlist_bl_lock(head);
 	hlist_bl_for_each_entry(entry, node, head, e_hash_list) {
-		if (entry->e_key == key && entry->e_block == block) {
+		if (entry->e_key == key && entry->e_value == value) {
 			/* We keep hash list reference to keep entry alive */
 			hlist_bl_del_init(&entry->e_hash_list);
 			hlist_bl_unlock(head);
@@ -248,7 +248,7 @@ void mb_cache_entry_delete_block(struct mb_cache *cache, u32 key,
 	}
 	hlist_bl_unlock(head);
 }
-EXPORT_SYMBOL(mb_cache_entry_delete_block);
+EXPORT_SYMBOL(mb_cache_entry_delete);
 
 /* mb_cache_entry_touch - cache entry got used
  * @cache - cache the entry belongs to
diff --git a/fs/minix/dir.c b/fs/minix/dir.c
index 7edc9b395700..baa9721f1299 100644
--- a/fs/minix/dir.c
+++ b/fs/minix/dir.c
@@ -57,7 +57,7 @@ static int dir_commit_chunk(struct page *page, loff_t pos, unsigned len)
 		mark_inode_dirty(dir);
 	}
 	if (IS_DIRSYNC(dir))
-		err = write_one_page(page, 1);
+		err = write_one_page(page);
 	else
 		unlock_page(page);
 	return err;
diff --git a/fs/minix/inode.c b/fs/minix/inode.c
index e7d9bf86d975..6ac76b0434e9 100644
--- a/fs/minix/inode.c
+++ b/fs/minix/inode.c
@@ -622,11 +622,14 @@ static int minix_write_inode(struct inode *inode, struct writeback_control *wbc)
 	return err;
 }
 
-int minix_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int minix_getattr(const struct path *path, struct kstat *stat,
+		  u32 request_mask, unsigned int flags)
 {
-	struct super_block *sb = dentry->d_sb;
-	generic_fillattr(d_inode(dentry), stat);
-	if (INODE_VERSION(d_inode(dentry)) == MINIX_V1)
+	struct super_block *sb = path->dentry->d_sb;
+	struct inode *inode = d_inode(path->dentry);
+
+	generic_fillattr(inode, stat);
+	if (INODE_VERSION(inode) == MINIX_V1)
 		stat->blocks = (BLOCK_SIZE / 512) * V1_minix_blocks(stat->size, sb);
 	else
 		stat->blocks = (sb->s_blocksize / 512) * V2_minix_blocks(stat->size, sb);
diff --git a/fs/minix/itree_common.c b/fs/minix/itree_common.c
index 4c57c9af6946..2d1ca08870f7 100644
--- a/fs/minix/itree_common.c
+++ b/fs/minix/itree_common.c
@@ -142,7 +142,7 @@ changed:
 	return -EAGAIN;
 }
 
-static inline int get_block(struct inode * inode, sector_t block,
+static int get_block(struct inode * inode, sector_t block,
 			struct buffer_head *bh, int create)
 {
 	int err = -EIO;
diff --git a/fs/minix/minix.h b/fs/minix/minix.h
index 01ad81dcacc5..663d66138d06 100644
--- a/fs/minix/minix.h
+++ b/fs/minix/minix.h
@@ -51,7 +51,7 @@ extern unsigned long minix_count_free_inodes(struct super_block *sb);
 extern int minix_new_block(struct inode * inode);
 extern void minix_free_block(struct inode *inode, unsigned long block);
 extern unsigned long minix_count_free_blocks(struct super_block *sb);
-extern int minix_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int minix_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int minix_prepare_chunk(struct page *page, loff_t pos, unsigned len);
 
 extern void V1_minix_truncate(struct inode *);
diff --git a/fs/mount.h b/fs/mount.h
index 2c856fc47ae3..6790767d1883 100644
--- a/fs/mount.h
+++ b/fs/mount.h
@@ -16,7 +16,7 @@ struct mnt_namespace {
 	u64 event;
 	unsigned int		mounts; /* # of mounts in the namespace */
 	unsigned int		pending_mounts;
-};
+} __randomize_layout;
 
 struct mnt_pcp {
 	int mnt_count;
@@ -58,8 +58,9 @@ struct mount {
 	struct mnt_namespace *mnt_ns;	/* containing namespace */
 	struct mountpoint *mnt_mp;	/* where is it mounted */
 	struct hlist_node mnt_mp_list;	/* list mounts with the same mountpoint */
+	struct list_head mnt_umounting; /* list entry for umount propagation */
 #ifdef CONFIG_FSNOTIFY
-	struct hlist_head mnt_fsnotify_marks;
+	struct fsnotify_mark_connector __rcu *mnt_fsnotify_marks;
 	__u32 mnt_fsnotify_mask;
 #endif
 	int mnt_id;			/* mount identifier */
@@ -68,7 +69,7 @@ struct mount {
 	struct hlist_head mnt_pins;
 	struct fs_pin mnt_umount;
 	struct dentry *mnt_ex_mountpoint;
-};
+} __randomize_layout;
 
 #define MNT_NS_INTERNAL ERR_PTR(-EINVAL) /* distinct from any mnt_namespace */
 
@@ -89,7 +90,6 @@ static inline int is_mounted(struct vfsmount *mnt)
 }
 
 extern struct mount *__lookup_mnt(struct vfsmount *, struct dentry *);
-extern struct mount *__lookup_mnt_last(struct vfsmount *, struct dentry *);
 
 extern int __legitimize_mnt(struct vfsmount *, unsigned);
 extern bool legitimize_mnt(struct vfsmount *, unsigned);
diff --git a/fs/mpage.c b/fs/mpage.c
index 28af984a3d96..2e4c41ccb5c9 100644
--- a/fs/mpage.c
+++ b/fs/mpage.c
@@ -50,7 +50,8 @@ static void mpage_end_io(struct bio *bio)
 
 	bio_for_each_segment_all(bv, bio, i) {
 		struct page *page = bv->bv_page;
-		page_endio(page, op_is_write(bio_op(bio)), bio->bi_error);
+		page_endio(page, op_is_write(bio_op(bio)),
+				blk_status_to_errno(bio->bi_status));
 	}
 
 	bio_put(bio);
@@ -115,7 +116,7 @@ map_buffer_to_page(struct page *page, struct buffer_head *bh, int page_block)
 			SetPageUptodate(page);    
 			return;
 		}
-		create_empty_buffers(page, 1 << inode->i_blkbits, 0);
+		create_empty_buffers(page, i_blocksize(inode), 0);
 	}
 	head = page_buffers(page);
 	page_bh = head;
@@ -344,6 +345,7 @@ confused:
  *
  * So an mpage read of the first 16 blocks of an ext2 file will cause I/O to be
  * submitted in the following order:
+ *
  * 	12 0 1 2 3 4 5 6 7 8 9 10 11 13 14 15 16
  *
  * because the indirect block has to be read to get the mappings of blocks
@@ -614,6 +616,7 @@ alloc_new:
 			goto confused;
 
 		wbc_init_bio(wbc, bio);
+		bio->bi_write_hint = inode->i_write_hint;
 	}
 
 	/*
diff --git a/fs/namei.c b/fs/namei.c
index ad74877e1442..ddb6a7c2b3d4 100644
--- a/fs/namei.c
+++ b/fs/namei.c
@@ -340,22 +340,14 @@ int generic_permission(struct inode *inode, int mask)
 
 	if (S_ISDIR(inode->i_mode)) {
 		/* DACs are overridable for directories */
-		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
-			return 0;
 		if (!(mask & MAY_WRITE))
 			if (capable_wrt_inode_uidgid(inode,
 						     CAP_DAC_READ_SEARCH))
 				return 0;
-		return -EACCES;
-	}
-	/*
-	 * Read/write DACs are always overridable.
-	 * Executable DACs are overridable when there is
-	 * at least one exec bit set.
-	 */
-	if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
 		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
 			return 0;
+		return -EACCES;
+	}
 
 	/*
 	 * Searching includes executable on directories, else just read.
@@ -364,6 +356,14 @@ int generic_permission(struct inode *inode, int mask)
 	if (mask == MAY_READ)
 		if (capable_wrt_inode_uidgid(inode, CAP_DAC_READ_SEARCH))
 			return 0;
+	/*
+	 * Read/write DACs are always overridable.
+	 * Executable DACs are overridable when there is
+	 * at least one exec bit set.
+	 */
+	if (!(mask & MAY_EXEC) || (inode->i_mode & S_IXUGO))
+		if (capable_wrt_inode_uidgid(inode, CAP_DAC_OVERRIDE))
+			return 0;
 
 	return -EACCES;
 }
@@ -524,7 +524,7 @@ struct nameidata {
 	struct inode	*link_inode;
 	unsigned	root_seq;
 	int		dfd;
-};
+} __randomize_layout;
 
 static void set_nameidata(struct nameidata *p, int dfd, struct filename *name)
 {
@@ -672,17 +672,15 @@ static bool legitimize_links(struct nameidata *nd)
 /**
  * unlazy_walk - try to switch to ref-walk mode.
  * @nd: nameidata pathwalk data
- * @dentry: child of nd->path.dentry or NULL
- * @seq: seq number to check dentry against
  * Returns: 0 on success, -ECHILD on failure
  *
- * unlazy_walk attempts to legitimize the current nd->path, nd->root and dentry
- * for ref-walk mode.  @dentry must be a path found by a do_lookup call on
- * @nd or NULL.  Must be called from rcu-walk context.
+ * unlazy_walk attempts to legitimize the current nd->path and nd->root
+ * for ref-walk mode.
+ * Must be called from rcu-walk context.
  * Nothing should touch nameidata between unlazy_walk() failure and
  * terminate_walk().
  */
-static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq)
+static int unlazy_walk(struct nameidata *nd)
 {
 	struct dentry *parent = nd->path.dentry;
 
@@ -691,33 +689,66 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq
 	nd->flags &= ~LOOKUP_RCU;
 	if (unlikely(!legitimize_links(nd)))
 		goto out2;
+	if (unlikely(!legitimize_path(nd, &nd->path, nd->seq)))
+		goto out1;
+	if (nd->root.mnt && !(nd->flags & LOOKUP_ROOT)) {
+		if (unlikely(!legitimize_path(nd, &nd->root, nd->root_seq)))
+			goto out;
+	}
+	rcu_read_unlock();
+	BUG_ON(nd->inode != parent->d_inode);
+	return 0;
+
+out2:
+	nd->path.mnt = NULL;
+	nd->path.dentry = NULL;
+out1:
+	if (!(nd->flags & LOOKUP_ROOT))
+		nd->root.mnt = NULL;
+out:
+	rcu_read_unlock();
+	return -ECHILD;
+}
+
+/**
+ * unlazy_child - try to switch to ref-walk mode.
+ * @nd: nameidata pathwalk data
+ * @dentry: child of nd->path.dentry
+ * @seq: seq number to check dentry against
+ * Returns: 0 on success, -ECHILD on failure
+ *
+ * unlazy_child attempts to legitimize the current nd->path, nd->root and dentry
+ * for ref-walk mode.  @dentry must be a path found by a do_lookup call on
+ * @nd.  Must be called from rcu-walk context.
+ * Nothing should touch nameidata between unlazy_child() failure and
+ * terminate_walk().
+ */
+static int unlazy_child(struct nameidata *nd, struct dentry *dentry, unsigned seq)
+{
+	BUG_ON(!(nd->flags & LOOKUP_RCU));
+
+	nd->flags &= ~LOOKUP_RCU;
+	if (unlikely(!legitimize_links(nd)))
+		goto out2;
 	if (unlikely(!legitimize_mnt(nd->path.mnt, nd->m_seq)))
 		goto out2;
-	if (unlikely(!lockref_get_not_dead(&parent->d_lockref)))
+	if (unlikely(!lockref_get_not_dead(&nd->path.dentry->d_lockref)))
 		goto out1;
 
 	/*
-	 * For a negative lookup, the lookup sequence point is the parents
-	 * sequence point, and it only needs to revalidate the parent dentry.
-	 *
-	 * For a positive lookup, we need to move both the parent and the
-	 * dentry from the RCU domain to be properly refcounted. And the
-	 * sequence number in the dentry validates *both* dentry counters,
-	 * since we checked the sequence number of the parent after we got
-	 * the child sequence number. So we know the parent must still
-	 * be valid if the child sequence number is still valid.
+	 * We need to move both the parent and the dentry from the RCU domain
+	 * to be properly refcounted. And the sequence number in the dentry
+	 * validates *both* dentry counters, since we checked the sequence
+	 * number of the parent after we got the child sequence number. So we
+	 * know the parent must still be valid if the child sequence number is
 	 */
-	if (!dentry) {
-		if (read_seqcount_retry(&parent->d_seq, nd->seq))
-			goto out;
-		BUG_ON(nd->inode != parent->d_inode);
-	} else {
-		if (!lockref_get_not_dead(&dentry->d_lockref))
-			goto out;
-		if (read_seqcount_retry(&dentry->d_seq, seq))
-			goto drop_dentry;
+	if (unlikely(!lockref_get_not_dead(&dentry->d_lockref)))
+		goto out;
+	if (unlikely(read_seqcount_retry(&dentry->d_seq, seq))) {
+		rcu_read_unlock();
+		dput(dentry);
+		goto drop_root_mnt;
 	}
-
 	/*
 	 * Sequence counts matched. Now make sure that the root is
 	 * still valid and get it if required.
@@ -733,10 +764,6 @@ static int unlazy_walk(struct nameidata *nd, struct dentry *dentry, unsigned seq
 	rcu_read_unlock();
 	return 0;
 
-drop_dentry:
-	rcu_read_unlock();
-	dput(dentry);
-	goto drop_root_mnt;
 out2:
 	nd->path.mnt = NULL;
 out1:
@@ -749,27 +776,12 @@ drop_root_mnt:
 	return -ECHILD;
 }
 
-static int unlazy_link(struct nameidata *nd, struct path *link, unsigned seq)
-{
-	if (unlikely(!legitimize_path(nd, link, seq))) {
-		drop_links(nd);
-		nd->depth = 0;
-		nd->flags &= ~LOOKUP_RCU;
-		nd->path.mnt = NULL;
-		nd->path.dentry = NULL;
-		if (!(nd->flags & LOOKUP_ROOT))
-			nd->root.mnt = NULL;
-		rcu_read_unlock();
-	} else if (likely(unlazy_walk(nd, NULL, 0)) == 0) {
-		return 0;
-	}
-	path_put(link);
-	return -ECHILD;
-}
-
 static inline int d_revalidate(struct dentry *dentry, unsigned int flags)
 {
-	return dentry->d_op->d_revalidate(dentry, flags);
+	if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
+		return dentry->d_op->d_revalidate(dentry, flags);
+	else
+		return 1;
 }
 
 /**
@@ -790,7 +802,7 @@ static int complete_walk(struct nameidata *nd)
 	if (nd->flags & LOOKUP_RCU) {
 		if (!(nd->flags & LOOKUP_ROOT))
 			nd->root.mnt = NULL;
-		if (unlikely(unlazy_walk(nd, NULL, 0)))
+		if (unlikely(unlazy_walk(nd)))
 			return -ECHILD;
 	}
 
@@ -996,7 +1008,7 @@ static int may_linkat(struct path *link)
 	/* Source inode owner (or CAP_FOWNER) can hardlink all they like,
 	 * otherwise, it must be a safe source.
 	 */
-	if (inode_owner_or_capable(inode) || safe_hardlink_source(inode))
+	if (safe_hardlink_source(inode) || inode_owner_or_capable(inode))
 		return 0;
 
 	audit_log_link_denied("linkat", link);
@@ -1016,7 +1028,7 @@ const char *get_link(struct nameidata *nd)
 		touch_atime(&last->link);
 		cond_resched();
 	} else if (atime_needs_update_rcu(&last->link, inode)) {
-		if (unlikely(unlazy_walk(nd, NULL, 0)))
+		if (unlikely(unlazy_walk(nd)))
 			return ERR_PTR(-ECHILD);
 		touch_atime(&last->link);
 	}
@@ -1035,7 +1047,7 @@ const char *get_link(struct nameidata *nd)
 		if (nd->flags & LOOKUP_RCU) {
 			res = get(NULL, inode, &last->done);
 			if (res == ERR_PTR(-ECHILD)) {
-				if (unlikely(unlazy_walk(nd, NULL, 0)))
+				if (unlikely(unlazy_walk(nd)))
 					return ERR_PTR(-ECHILD);
 				res = get(dentry, inode, &last->done);
 			}
@@ -1100,7 +1112,6 @@ static int follow_automount(struct path *path, struct nameidata *nd,
 			    bool *need_mntput)
 {
 	struct vfsmount *mnt;
-	const struct cred *old_cred;
 	int err;
 
 	if (!path->dentry->d_op || !path->dentry->d_op->d_automount)
@@ -1129,9 +1140,7 @@ static int follow_automount(struct path *path, struct nameidata *nd,
 	if (nd->total_link_count >= 40)
 		return -ELOOP;
 
-	old_cred = override_creds(&init_cred);
 	mnt = path->dentry->d_op->d_automount(path);
-	revert_creds(old_cred);
 	if (IS_ERR(mnt)) {
 		/*
 		 * The filesystem is allowed to return -EISDIR here to indicate
@@ -1472,19 +1481,14 @@ static struct dentry *lookup_dcache(const struct qstr *name,
 				    struct dentry *dir,
 				    unsigned int flags)
 {
-	struct dentry *dentry;
-	int error;
-
-	dentry = d_lookup(dir, name);
+	struct dentry *dentry = d_lookup(dir, name);
 	if (dentry) {
-		if (dentry->d_flags & DCACHE_OP_REVALIDATE) {
-			error = d_revalidate(dentry, flags);
-			if (unlikely(error <= 0)) {
-				if (!error)
-					d_invalidate(dentry);
-				dput(dentry);
-				return ERR_PTR(error);
-			}
+		int error = d_revalidate(dentry, flags);
+		if (unlikely(error <= 0)) {
+			if (!error)
+				d_invalidate(dentry);
+			dput(dentry);
+			return ERR_PTR(error);
 		}
 	}
 	return dentry;
@@ -1549,7 +1553,7 @@ static int lookup_fast(struct nameidata *nd,
 		bool negative;
 		dentry = __d_lookup_rcu(parent, &nd->last, &seq);
 		if (unlikely(!dentry)) {
-			if (unlazy_walk(nd, NULL, 0))
+			if (unlazy_walk(nd))
 				return -ECHILD;
 			return 0;
 		}
@@ -1574,14 +1578,8 @@ static int lookup_fast(struct nameidata *nd,
 			return -ECHILD;
 
 		*seqp = seq;
-		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
-			status = d_revalidate(dentry, nd->flags);
-		if (unlikely(status <= 0)) {
-			if (unlazy_walk(nd, dentry, seq))
-				return -ECHILD;
-			if (status == -ECHILD)
-				status = d_revalidate(dentry, nd->flags);
-		} else {
+		status = d_revalidate(dentry, nd->flags);
+		if (likely(status > 0)) {
 			/*
 			 * Note: do negative dentry check after revalidation in
 			 * case that drops it.
@@ -1592,15 +1590,17 @@ static int lookup_fast(struct nameidata *nd,
 			path->dentry = dentry;
 			if (likely(__follow_mount_rcu(nd, path, inode, seqp)))
 				return 1;
-			if (unlazy_walk(nd, dentry, seq))
-				return -ECHILD;
 		}
+		if (unlazy_child(nd, dentry, seq))
+			return -ECHILD;
+		if (unlikely(status == -ECHILD))
+			/* we'd been told to redo it in non-rcu mode */
+			status = d_revalidate(dentry, nd->flags);
 	} else {
 		dentry = __d_lookup(parent, &nd->last);
 		if (unlikely(!dentry))
 			return 0;
-		if (unlikely(dentry->d_flags & DCACHE_OP_REVALIDATE))
-			status = d_revalidate(dentry, nd->flags);
+		status = d_revalidate(dentry, nd->flags);
 	}
 	if (unlikely(status <= 0)) {
 		if (!status)
@@ -1639,8 +1639,7 @@ again:
 	if (IS_ERR(dentry))
 		goto out;
 	if (unlikely(!d_in_lookup(dentry))) {
-		if ((dentry->d_flags & DCACHE_OP_REVALIDATE) &&
-		    !(flags & LOOKUP_NO_REVAL)) {
+		if (!(flags & LOOKUP_NO_REVAL)) {
 			int error = d_revalidate(dentry, flags);
 			if (unlikely(error <= 0)) {
 				if (!error) {
@@ -1671,7 +1670,7 @@ static inline int may_lookup(struct nameidata *nd)
 		int err = inode_permission(nd->inode, MAY_EXEC|MAY_NOT_BLOCK);
 		if (err != -ECHILD)
 			return err;
-		if (unlazy_walk(nd, NULL, 0))
+		if (unlazy_walk(nd))
 			return -ECHILD;
 	}
 	return inode_permission(nd->inode, MAY_EXEC);
@@ -1706,9 +1705,17 @@ static int pick_link(struct nameidata *nd, struct path *link,
 	error = nd_alloc_stack(nd);
 	if (unlikely(error)) {
 		if (error == -ECHILD) {
-			if (unlikely(unlazy_link(nd, link, seq)))
-				return -ECHILD;
-			error = nd_alloc_stack(nd);
+			if (unlikely(!legitimize_path(nd, link, seq))) {
+				drop_links(nd);
+				nd->depth = 0;
+				nd->flags &= ~LOOKUP_RCU;
+				nd->path.mnt = NULL;
+				nd->path.dentry = NULL;
+				if (!(nd->flags & LOOKUP_ROOT))
+					nd->root.mnt = NULL;
+				rcu_read_unlock();
+			} else if (likely(unlazy_walk(nd)) == 0)
+				error = nd_alloc_stack(nd);
 		}
 		if (error) {
 			path_put(link);
@@ -2125,7 +2132,7 @@ OK:
 		}
 		if (unlikely(!d_can_lookup(nd->path.dentry))) {
 			if (nd->flags & LOOKUP_RCU) {
-				if (unlazy_walk(nd, NULL, 0))
+				if (unlazy_walk(nd))
 					return -ECHILD;
 			}
 			return -ENOTDIR;
@@ -2135,22 +2142,19 @@ OK:
 
 static const char *path_init(struct nameidata *nd, unsigned flags)
 {
-	int retval = 0;
 	const char *s = nd->name->name;
 
+	if (!*s)
+		flags &= ~LOOKUP_RCU;
+
 	nd->last_type = LAST_ROOT; /* if there are only slashes... */
 	nd->flags = flags | LOOKUP_JUMPED | LOOKUP_PARENT;
 	nd->depth = 0;
 	if (flags & LOOKUP_ROOT) {
 		struct dentry *root = nd->root.dentry;
 		struct inode *inode = root->d_inode;
-		if (*s) {
-			if (!d_can_lookup(root))
-				return ERR_PTR(-ENOTDIR);
-			retval = inode_permission(inode, MAY_EXEC);
-			if (retval)
-				return ERR_PTR(retval);
-		}
+		if (*s && unlikely(!d_can_lookup(root)))
+			return ERR_PTR(-ENOTDIR);
 		nd->path = nd->root;
 		nd->inode = inode;
 		if (flags & LOOKUP_RCU) {
@@ -2248,6 +2252,35 @@ static inline int lookup_last(struct nameidata *nd)
 	return walk_component(nd, 0);
 }
 
+static int handle_lookup_down(struct nameidata *nd)
+{
+	struct path path = nd->path;
+	struct inode *inode = nd->inode;
+	unsigned seq = nd->seq;
+	int err;
+
+	if (nd->flags & LOOKUP_RCU) {
+		/*
+		 * don't bother with unlazy_walk on failure - we are
+		 * at the very beginning of walk, so we lose nothing
+		 * if we simply redo everything in non-RCU mode
+		 */
+		if (unlikely(!__follow_mount_rcu(nd, &path, &inode, &seq)))
+			return -ECHILD;
+	} else {
+		dget(path.dentry);
+		err = follow_managed(&path, nd);
+		if (unlikely(err < 0))
+			return err;
+		inode = d_backing_inode(path.dentry);
+		seq = 0;
+	}
+	path_to_nameidata(&path, nd);
+	nd->inode = inode;
+	nd->seq = seq;
+	return 0;
+}
+
 /* Returns 0 and nd will be valid on success; Retuns error, otherwise. */
 static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path)
 {
@@ -2256,6 +2289,15 @@ static int path_lookupat(struct nameidata *nd, unsigned flags, struct path *path
 
 	if (IS_ERR(s))
 		return PTR_ERR(s);
+
+	if (unlikely(flags & LOOKUP_DOWN)) {
+		err = handle_lookup_down(nd);
+		if (unlikely(err < 0)) {
+			terminate_walk(nd);
+			return err;
+		}
+	}
+
 	while (!(err = link_path_walk(s, nd))
 		&& ((err = lookup_last(nd)) > 0)) {
 		s = trailing_symlink(nd);
@@ -2582,7 +2624,7 @@ mountpoint_last(struct nameidata *nd)
 
 	/* If we're in rcuwalk, drop out of it to handle last component */
 	if (nd->flags & LOOKUP_RCU) {
-		if (unlazy_walk(nd, NULL, 0))
+		if (unlazy_walk(nd))
 			return -ECHILD;
 	}
 
@@ -2941,10 +2983,16 @@ static inline int open_to_namei_flags(int flag)
 
 static int may_o_create(const struct path *dir, struct dentry *dentry, umode_t mode)
 {
+	struct user_namespace *s_user_ns;
 	int error = security_path_mknod(dir, dentry, mode, 0);
 	if (error)
 		return error;
 
+	s_user_ns = dir->dentry->d_sb->s_user_ns;
+	if (!kuid_has_mapping(s_user_ns, current_fsuid()) ||
+	    !kgid_has_mapping(s_user_ns, current_fsgid()))
+		return -EOVERFLOW;
+
 	error = inode_permission(dir->dentry->d_inode, MAY_WRITE | MAY_EXEC);
 	if (error)
 		return error;
@@ -3069,9 +3117,6 @@ static int lookup_open(struct nameidata *nd, struct path *path,
 		if (d_in_lookup(dentry))
 			break;
 
-		if (!(dentry->d_flags & DCACHE_OP_REVALIDATE))
-			break;
-
 		error = d_revalidate(dentry, nd->flags);
 		if (likely(error > 0))
 			break;
@@ -3353,13 +3398,49 @@ out:
 	return error;
 }
 
+struct dentry *vfs_tmpfile(struct dentry *dentry, umode_t mode, int open_flag)
+{
+	struct dentry *child = NULL;
+	struct inode *dir = dentry->d_inode;
+	struct inode *inode;
+	int error;
+
+	/* we want directory to be writable */
+	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
+	if (error)
+		goto out_err;
+	error = -EOPNOTSUPP;
+	if (!dir->i_op->tmpfile)
+		goto out_err;
+	error = -ENOMEM;
+	child = d_alloc(dentry, &slash_name);
+	if (unlikely(!child))
+		goto out_err;
+	error = dir->i_op->tmpfile(dir, child, mode);
+	if (error)
+		goto out_err;
+	error = -ENOENT;
+	inode = child->d_inode;
+	if (unlikely(!inode))
+		goto out_err;
+	if (!(open_flag & O_EXCL)) {
+		spin_lock(&inode->i_lock);
+		inode->i_state |= I_LINKABLE;
+		spin_unlock(&inode->i_lock);
+	}
+	return child;
+
+out_err:
+	dput(child);
+	return ERR_PTR(error);
+}
+EXPORT_SYMBOL(vfs_tmpfile);
+
 static int do_tmpfile(struct nameidata *nd, unsigned flags,
 		const struct open_flags *op,
 		struct file *file, int *opened)
 {
-	static const struct qstr name = QSTR_INIT("/", 1);
 	struct dentry *child;
-	struct inode *dir;
 	struct path path;
 	int error = path_lookupat(nd, flags | LOOKUP_DIRECTORY, &path);
 	if (unlikely(error))
@@ -3367,25 +3448,12 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	error = mnt_want_write(path.mnt);
 	if (unlikely(error))
 		goto out;
-	dir = path.dentry->d_inode;
-	/* we want directory to be writable */
-	error = inode_permission(dir, MAY_WRITE | MAY_EXEC);
-	if (error)
-		goto out2;
-	if (!dir->i_op->tmpfile) {
-		error = -EOPNOTSUPP;
-		goto out2;
-	}
-	child = d_alloc(path.dentry, &name);
-	if (unlikely(!child)) {
-		error = -ENOMEM;
+	child = vfs_tmpfile(path.dentry, op->mode, op->open_flag);
+	error = PTR_ERR(child);
+	if (unlikely(IS_ERR(child)))
 		goto out2;
-	}
 	dput(path.dentry);
 	path.dentry = child;
-	error = dir->i_op->tmpfile(dir, child, op->mode);
-	if (error)
-		goto out2;
 	audit_inode(nd->name, child, 0);
 	/* Don't check for other permissions, the inode was just created */
 	error = may_open(&path, 0, op->open_flag);
@@ -3396,14 +3464,8 @@ static int do_tmpfile(struct nameidata *nd, unsigned flags,
 	if (error)
 		goto out2;
 	error = open_check_o_direct(file);
-	if (error) {
+	if (error)
 		fput(file);
-	} else if (!(op->open_flag & O_EXCL)) {
-		struct inode *inode = file_inode(file);
-		spin_lock(&inode->i_lock);
-		inode->i_state |= I_LINKABLE;
-		spin_unlock(&inode->i_lock);
-	}
 out2:
 	mnt_drop_write(path.mnt);
 out:
@@ -4269,6 +4331,7 @@ SYSCALL_DEFINE2(link, const char __user *, oldname, const char __user *, newname
  * The worst of all namespace operations - renaming directory. "Perverted"
  * doesn't even start to describe it. Somebody in UCB had a heck of a trip...
  * Problems:
+ *
  *	a) we can get into loop creation.
  *	b) race potential - two innocent renames can create a loop together.
  *	   That's where 4.4 screws up. Current fix: serialization on
@@ -4299,11 +4362,11 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 {
 	int error;
 	bool is_dir = d_is_dir(old_dentry);
-	const unsigned char *old_name;
 	struct inode *source = old_dentry->d_inode;
 	struct inode *target = new_dentry->d_inode;
 	bool new_is_dir = false;
 	unsigned max_links = new_dir->i_sb->s_max_links;
+	struct name_snapshot old_name;
 
 	if (source == target)
 		return 0;
@@ -4350,7 +4413,7 @@ int vfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	if (error)
 		return error;
 
-	old_name = fsnotify_oldname_init(old_dentry->d_name.name);
+	take_dentry_name_snapshot(&old_name, old_dentry);
 	dget(new_dentry);
 	if (!is_dir || (flags & RENAME_EXCHANGE))
 		lock_two_nondirectories(source, target);
@@ -4405,14 +4468,14 @@ out:
 		inode_unlock(target);
 	dput(new_dentry);
 	if (!error) {
-		fsnotify_move(old_dir, new_dir, old_name, is_dir,
+		fsnotify_move(old_dir, new_dir, old_name.name, is_dir,
 			      !(flags & RENAME_EXCHANGE) ? target : NULL, old_dentry);
 		if (flags & RENAME_EXCHANGE) {
 			fsnotify_move(new_dir, old_dir, old_dentry->d_name.name,
 				      new_is_dir, NULL, new_dentry);
 		}
 	}
-	fsnotify_oldname_free(old_name);
+	release_dentry_name_snapshot(&old_name);
 
 	return error;
 }
@@ -4735,7 +4798,7 @@ int __page_symlink(struct inode *inode, const char *symname, int len, int nofs)
 	struct page *page;
 	void *fsdata;
 	int err;
-	unsigned int flags = AOP_FLAG_UNINTERRUPTIBLE;
+	unsigned int flags = 0;
 	if (nofs)
 		flags |= AOP_FLAG_NOFS;
 
diff --git a/fs/namespace.c b/fs/namespace.c
index 487ba30bb5c6..f8893dc6a989 100644
--- a/fs/namespace.c
+++ b/fs/namespace.c
@@ -15,6 +15,7 @@
 #include <linux/user_namespace.h>
 #include <linux/namei.h>
 #include <linux/security.h>
+#include <linux/cred.h>
 #include <linux/idr.h>
 #include <linux/init.h>		/* init_rootfs */
 #include <linux/fs_struct.h>	/* get_fs_root et.al. */
@@ -24,6 +25,8 @@
 #include <linux/magic.h>
 #include <linux/bootmem.h>
 #include <linux/task_work.h>
+#include <linux/sched/task.h>
+
 #include "pnode.h"
 #include "internal.h"
 
@@ -233,9 +236,7 @@ static struct mount *alloc_vfsmnt(const char *name)
 		INIT_LIST_HEAD(&mnt->mnt_slave_list);
 		INIT_LIST_HEAD(&mnt->mnt_slave);
 		INIT_HLIST_NODE(&mnt->mnt_mp_list);
-#ifdef CONFIG_FSNOTIFY
-		INIT_HLIST_HEAD(&mnt->mnt_fsnotify_marks);
-#endif
+		INIT_LIST_HEAD(&mnt->mnt_umounting);
 		init_fs_pin(&mnt->mnt_umount, drop_mountpoint);
 	}
 	return mnt;
@@ -637,28 +638,6 @@ struct mount *__lookup_mnt(struct vfsmount *mnt, struct dentry *dentry)
 }
 
 /*
- * find the last mount at @dentry on vfsmount @mnt.
- * mount_lock must be held.
- */
-struct mount *__lookup_mnt_last(struct vfsmount *mnt, struct dentry *dentry)
-{
-	struct mount *p, *res = NULL;
-	p = __lookup_mnt(mnt, dentry);
-	if (!p)
-		goto out;
-	if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-		res = p;
-	hlist_for_each_entry_continue(p, mnt_hash) {
-		if (&p->mnt_parent->mnt != mnt || p->mnt_mountpoint != dentry)
-			break;
-		if (!(p->mnt.mnt_flags & MNT_UMOUNT))
-			res = p;
-	}
-out:
-	return res;
-}
-
-/*
  * lookup_mnt - Return the first child mount mounted at path
  *
  * "First" means first mounted chronologically.  If you create the
@@ -878,6 +857,13 @@ void mnt_set_mountpoint(struct mount *mnt,
 	hlist_add_head(&child_mnt->mnt_mp_list, &mp->m_list);
 }
 
+static void __attach_mnt(struct mount *mnt, struct mount *parent)
+{
+	hlist_add_head_rcu(&mnt->mnt_hash,
+			   m_hash(&parent->mnt, mnt->mnt_mountpoint));
+	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+}
+
 /*
  * vfsmount lock must be held for write
  */
@@ -886,28 +872,45 @@ static void attach_mnt(struct mount *mnt,
 			struct mountpoint *mp)
 {
 	mnt_set_mountpoint(parent, mp, mnt);
-	hlist_add_head_rcu(&mnt->mnt_hash, m_hash(&parent->mnt, mp->m_dentry));
-	list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
+	__attach_mnt(mnt, parent);
 }
 
-static void attach_shadowed(struct mount *mnt,
-			struct mount *parent,
-			struct mount *shadows)
+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp, struct mount *mnt)
 {
-	if (shadows) {
-		hlist_add_behind_rcu(&mnt->mnt_hash, &shadows->mnt_hash);
-		list_add(&mnt->mnt_child, &shadows->mnt_child);
-	} else {
-		hlist_add_head_rcu(&mnt->mnt_hash,
-				m_hash(&parent->mnt, mnt->mnt_mountpoint));
-		list_add_tail(&mnt->mnt_child, &parent->mnt_mounts);
-	}
+	struct mountpoint *old_mp = mnt->mnt_mp;
+	struct dentry *old_mountpoint = mnt->mnt_mountpoint;
+	struct mount *old_parent = mnt->mnt_parent;
+
+	list_del_init(&mnt->mnt_child);
+	hlist_del_init(&mnt->mnt_mp_list);
+	hlist_del_init_rcu(&mnt->mnt_hash);
+
+	attach_mnt(mnt, parent, mp);
+
+	put_mountpoint(old_mp);
+
+	/*
+	 * Safely avoid even the suggestion this code might sleep or
+	 * lock the mount hash by taking advantage of the knowledge that
+	 * mnt_change_mountpoint will not release the final reference
+	 * to a mountpoint.
+	 *
+	 * During mounting, the mount passed in as the parent mount will
+	 * continue to use the old mountpoint and during unmounting, the
+	 * old mountpoint will continue to exist until namespace_unlock,
+	 * which happens well after mnt_change_mountpoint.
+	 */
+	spin_lock(&old_mountpoint->d_lock);
+	old_mountpoint->d_lockref.count--;
+	spin_unlock(&old_mountpoint->d_lock);
+
+	mnt_add_count(old_parent, -1);
 }
 
 /*
  * vfsmount lock must be held for write
  */
-static void commit_tree(struct mount *mnt, struct mount *shadows)
+static void commit_tree(struct mount *mnt)
 {
 	struct mount *parent = mnt->mnt_parent;
 	struct mount *m;
@@ -925,7 +928,7 @@ static void commit_tree(struct mount *mnt, struct mount *shadows)
 	n->mounts += n->pending_mounts;
 	n->pending_mounts = 0;
 
-	attach_shadowed(mnt, parent, shadows);
+	__attach_mnt(mnt, parent);
 	touch_mnt_namespace(n);
 }
 
@@ -989,6 +992,21 @@ vfs_kern_mount(struct file_system_type *type, int flags, const char *name, void
 }
 EXPORT_SYMBOL_GPL(vfs_kern_mount);
 
+struct vfsmount *
+vfs_submount(const struct dentry *mountpoint, struct file_system_type *type,
+	     const char *name, void *data)
+{
+	/* Until it is worked out how to pass the user namespace
+	 * through from the parent mount to the submount don't support
+	 * unprivileged mounts with submounts.
+	 */
+	if (mountpoint->d_sb->s_user_ns != &init_user_ns)
+		return ERR_PTR(-EPERM);
+
+	return vfs_kern_mount(type, MS_SUBMOUNT, name, data);
+}
+EXPORT_SYMBOL_GPL(vfs_submount);
+
 static struct mount *clone_mnt(struct mount *old, struct dentry *root,
 					int flag)
 {
@@ -1220,65 +1238,6 @@ struct vfsmount *mnt_clone_internal(const struct path *path)
 	return &p->mnt;
 }
 
-static inline void mangle(struct seq_file *m, const char *s)
-{
-	seq_escape(m, s, " \t\n\\");
-}
-
-/*
- * Simple .show_options callback for filesystems which don't want to
- * implement more complex mount option showing.
- *
- * See also save_mount_options().
- */
-int generic_show_options(struct seq_file *m, struct dentry *root)
-{
-	const char *options;
-
-	rcu_read_lock();
-	options = rcu_dereference(root->d_sb->s_options);
-
-	if (options != NULL && options[0]) {
-		seq_putc(m, ',');
-		mangle(m, options);
-	}
-	rcu_read_unlock();
-
-	return 0;
-}
-EXPORT_SYMBOL(generic_show_options);
-
-/*
- * If filesystem uses generic_show_options(), this function should be
- * called from the fill_super() callback.
- *
- * The .remount_fs callback usually needs to be handled in a special
- * way, to make sure, that previous options are not overwritten if the
- * remount fails.
- *
- * Also note, that if the filesystem's .remount_fs function doesn't
- * reset all options to their default value, but changes only newly
- * given options, then the displayed options will not reflect reality
- * any more.
- */
-void save_mount_options(struct super_block *sb, char *options)
-{
-	BUG_ON(sb->s_options);
-	rcu_assign_pointer(sb->s_options, kstrdup(options, GFP_KERNEL));
-}
-EXPORT_SYMBOL(save_mount_options);
-
-void replace_mount_options(struct super_block *sb, char *options)
-{
-	char *old = sb->s_options;
-	rcu_assign_pointer(sb->s_options, options);
-	if (old) {
-		synchronize_rcu();
-		kfree(old);
-	}
-}
-EXPORT_SYMBOL(replace_mount_options);
-
 #ifdef CONFIG_PROC_FS
 /* iterator; we want it to have access to namespace_sem, thus here... */
 static void *m_start(struct seq_file *m, loff_t *pos)
@@ -1639,7 +1598,7 @@ out_unlock:
 	namespace_unlock();
 }
 
-/* 
+/*
  * Is the caller allowed to modify his namespace?
  */
 static inline bool may_mount(void)
@@ -1764,7 +1723,6 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 			continue;
 
 		for (s = r; s; s = next_mnt(s, r)) {
-			struct mount *t = NULL;
 			if (!(flag & CL_COPY_UNBINDABLE) &&
 			    IS_MNT_UNBINDABLE(s)) {
 				s = skip_mnt_tree(s);
@@ -1786,14 +1744,7 @@ struct mount *copy_tree(struct mount *mnt, struct dentry *dentry,
 				goto out;
 			lock_mount_hash();
 			list_add_tail(&q->mnt_list, &res->mnt_list);
-			mnt_set_mountpoint(parent, p->mnt_mp, q);
-			if (!list_empty(&parent->mnt_mounts)) {
-				t = list_last_entry(&parent->mnt_mounts,
-					struct mount, mnt_child);
-				if (t->mnt_mp != p->mnt_mp)
-					t = NULL;
-			}
-			attach_shadowed(q, parent, t);
+			attach_mnt(q, parent, p->mnt_mp);
 			unlock_mount_hash();
 		}
 	}
@@ -1992,10 +1943,18 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 {
 	HLIST_HEAD(tree_list);
 	struct mnt_namespace *ns = dest_mnt->mnt_ns;
+	struct mountpoint *smp;
 	struct mount *child, *p;
 	struct hlist_node *n;
 	int err;
 
+	/* Preallocate a mountpoint in case the new mounts need
+	 * to be tucked under other mounts.
+	 */
+	smp = get_mountpoint(source_mnt->mnt.mnt_root);
+	if (IS_ERR(smp))
+		return PTR_ERR(smp);
+
 	/* Is there space to add these mounts to the mount namespace? */
 	if (!parent_path) {
 		err = count_mounts(ns, source_mnt);
@@ -2022,16 +1981,19 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 		touch_mnt_namespace(source_mnt->mnt_ns);
 	} else {
 		mnt_set_mountpoint(dest_mnt, dest_mp, source_mnt);
-		commit_tree(source_mnt, NULL);
+		commit_tree(source_mnt);
 	}
 
 	hlist_for_each_entry_safe(child, n, &tree_list, mnt_hash) {
 		struct mount *q;
 		hlist_del_init(&child->mnt_hash);
-		q = __lookup_mnt_last(&child->mnt_parent->mnt,
-				      child->mnt_mountpoint);
-		commit_tree(child, q);
+		q = __lookup_mnt(&child->mnt_parent->mnt,
+				 child->mnt_mountpoint);
+		if (q)
+			mnt_change_mountpoint(child, smp, q);
+		commit_tree(child);
 	}
+	put_mountpoint(smp);
 	unlock_mount_hash();
 
 	return 0;
@@ -2046,6 +2008,11 @@ static int attach_recursive_mnt(struct mount *source_mnt,
 	cleanup_group_ids(source_mnt, NULL);
  out:
 	ns->pending_mounts = 0;
+
+	read_seqlock_excl(&mount_lock);
+	put_mountpoint(smp);
+	read_sequnlock_excl(&mount_lock);
+
 	return err;
 }
 
@@ -2185,7 +2152,7 @@ static int do_loopback(struct path *path, const char *old_name,
 
 	err = -EINVAL;
 	if (mnt_ns_loop(old_path.dentry))
-		goto out; 
+		goto out;
 
 	mp = lock_mount(path);
 	err = PTR_ERR(mp);
@@ -2794,7 +2761,7 @@ long do_mount(const char *dev_name, const char __user *dir_name,
 
 	flags &= ~(MS_NOSUID | MS_NOEXEC | MS_NODEV | MS_ACTIVE | MS_BORN |
 		   MS_NOATIME | MS_NODIRATIME | MS_RELATIME| MS_KERNMOUNT |
-		   MS_STRICTATIME | MS_NOREMOTELOCK);
+		   MS_STRICTATIME | MS_NOREMOTELOCK | MS_SUBMOUNT);
 
 	if (flags & MS_REMOUNT)
 		retval = do_remount(&path, flags & ~MS_REMOUNT, mnt_flags,
@@ -3213,7 +3180,6 @@ static void __init init_mount_tree(void)
 
 void __init mnt_init(void)
 {
-	unsigned u;
 	int err;
 
 	mnt_cache = kmem_cache_create("mnt_cache", sizeof(struct mount),
@@ -3222,22 +3188,17 @@ void __init mnt_init(void)
 	mount_hashtable = alloc_large_system_hash("Mount-cache",
 				sizeof(struct hlist_head),
 				mhash_entries, 19,
-				0,
+				HASH_ZERO,
 				&m_hash_shift, &m_hash_mask, 0, 0);
 	mountpoint_hashtable = alloc_large_system_hash("Mountpoint-cache",
 				sizeof(struct hlist_head),
 				mphash_entries, 19,
-				0,
+				HASH_ZERO,
 				&mp_hash_shift, &mp_hash_mask, 0, 0);
 
 	if (!mount_hashtable || !mountpoint_hashtable)
 		panic("Failed to allocate mount hash table\n");
 
-	for (u = 0; u <= m_hash_mask; u++)
-		INIT_HLIST_HEAD(&mount_hashtable[u]);
-	for (u = 0; u <= mp_hash_mask; u++)
-		INIT_HLIST_HEAD(&mountpoint_hashtable[u]);
-
 	kernfs_init();
 
 	err = sysfs_init();
@@ -3437,8 +3398,9 @@ static void mntns_put(struct ns_common *ns)
 static int mntns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 {
 	struct fs_struct *fs = current->fs;
-	struct mnt_namespace *mnt_ns = to_mnt_ns(ns);
+	struct mnt_namespace *mnt_ns = to_mnt_ns(ns), *old_mnt_ns;
 	struct path root;
+	int err;
 
 	if (!ns_capable(mnt_ns->user_ns, CAP_SYS_ADMIN) ||
 	    !ns_capable(current_user_ns(), CAP_SYS_CHROOT) ||
@@ -3449,15 +3411,20 @@ static int mntns_install(struct nsproxy *nsproxy, struct ns_common *ns)
 		return -EINVAL;
 
 	get_mnt_ns(mnt_ns);
-	put_mnt_ns(nsproxy->mnt_ns);
+	old_mnt_ns = nsproxy->mnt_ns;
 	nsproxy->mnt_ns = mnt_ns;
 
 	/* Find the root */
-	root.mnt    = &mnt_ns->root->mnt;
-	root.dentry = mnt_ns->root->mnt.mnt_root;
-	path_get(&root);
-	while(d_mountpoint(root.dentry) && follow_down_one(&root))
-		;
+	err = vfs_path_lookup(mnt_ns->root->mnt.mnt_root, &mnt_ns->root->mnt,
+				"/", LOOKUP_DOWN, &root);
+	if (err) {
+		/* revert to old namespace */
+		nsproxy->mnt_ns = old_mnt_ns;
+		put_mnt_ns(mnt_ns);
+		return err;
+	}
+
+	put_mnt_ns(old_mnt_ns);
 
 	/* Update the pwd and root */
 	set_fs_pwd(fs, &root);
diff --git a/fs/ncpfs/inode.c b/fs/ncpfs/inode.c
index 7eb89c23c847..6d0f14c86099 100644
--- a/fs/ncpfs/inode.c
+++ b/fs/ncpfs/inode.c
@@ -30,6 +30,7 @@
 #include <linux/vfs.h>
 #include <linux/mount.h>
 #include <linux/seq_file.h>
+#include <linux/sched/signal.h>
 #include <linux/namei.h>
 
 #include <net/sock.h>
@@ -553,12 +554,11 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 	sb->s_magic = NCP_SUPER_MAGIC;
 	sb->s_op = &ncp_sops;
 	sb->s_d_op = &ncp_dentry_operations;
-	sb->s_bdi = &server->bdi;
 
 	server = NCP_SBP(sb);
 	memset(server, 0, sizeof(*server));
 
-	error = bdi_setup_and_register(&server->bdi, "ncpfs");
+	error = super_setup_bdi(sb);
 	if (error)
 		goto out_fput;
 
@@ -567,7 +567,7 @@ static int ncp_fill_super(struct super_block *sb, void *raw_data, int silent)
 	if (data.info_fd != -1) {
 		struct socket *info_sock = sockfd_lookup(data.info_fd, &error);
 		if (!info_sock)
-			goto out_bdi;
+			goto out_fput;
 		server->info_sock = info_sock;
 		error = -EBADFD;
 		if (info_sock->type != SOCK_STREAM)
@@ -745,8 +745,6 @@ out_nls:
 out_fput2:
 	if (server->info_sock)
 		sockfd_put(server->info_sock);
-out_bdi:
-	bdi_destroy(&server->bdi);
 out_fput:
 	sockfd_put(sock);
 out:
@@ -787,7 +785,6 @@ static void ncp_put_super(struct super_block *sb)
 	kill_pid(server->m.wdog_pid, SIGTERM, 1);
 	put_pid(server->m.wdog_pid);
 
-	bdi_destroy(&server->bdi);
 	kfree(server->priv.data);
 	kfree(server->auth.object_name);
 	vfree(server->rxbuf);
diff --git a/fs/ncpfs/ioctl.c b/fs/ncpfs/ioctl.c
index 4434e4977cf3..12550c2320cc 100644
--- a/fs/ncpfs/ioctl.c
+++ b/fs/ncpfs/ioctl.c
@@ -19,6 +19,7 @@
 #include <linux/highuid.h>
 #include <linux/vmalloc.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 
 #include <linux/uaccess.h>
 
diff --git a/fs/ncpfs/mmap.c b/fs/ncpfs/mmap.c
index 39f57bef8531..6719c0be674d 100644
--- a/fs/ncpfs/mmap.c
+++ b/fs/ncpfs/mmap.c
@@ -27,10 +27,9 @@
  * XXX: how are we excluding truncate/invalidate here? Maybe need to lock
  * page?
  */
-static int ncp_file_mmap_fault(struct vm_area_struct *area,
-					struct vm_fault *vmf)
+static int ncp_file_mmap_fault(struct vm_fault *vmf)
 {
-	struct inode *inode = file_inode(area->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	char *pg_addr;
 	unsigned int already_read;
 	unsigned int count;
@@ -90,7 +89,7 @@ static int ncp_file_mmap_fault(struct vm_area_struct *area,
 	 * -- nyc
 	 */
 	count_vm_event(PGMAJFAULT);
-	mem_cgroup_count_vm_event(area->vm_mm, PGMAJFAULT);
+	count_memcg_event_mm(vmf->vma->vm_mm, PGMAJFAULT);
 	return VM_FAULT_MAJOR;
 }
 
diff --git a/fs/ncpfs/ncp_fs_sb.h b/fs/ncpfs/ncp_fs_sb.h
index 55e26fd80886..366fd63cc506 100644
--- a/fs/ncpfs/ncp_fs_sb.h
+++ b/fs/ncpfs/ncp_fs_sb.h
@@ -143,7 +143,6 @@ struct ncp_server {
 		size_t len;
 		__u8 data[128];
 	} unexpected_packet;
-	struct backing_dev_info bdi;
 };
 
 extern void ncp_tcp_rcv_proc(struct work_struct *work);
diff --git a/fs/ncpfs/sock.c b/fs/ncpfs/sock.c
index f32f272ee501..98b6db0ed63e 100644
--- a/fs/ncpfs/sock.c
+++ b/fs/ncpfs/sock.c
@@ -16,6 +16,7 @@
 #include <linux/fcntl.h>
 #include <linux/stat.h>
 #include <linux/string.h>
+#include <linux/sched/signal.h>
 #include <linux/uaccess.h>
 #include <linux/in.h>
 #include <linux/net.h>
@@ -40,19 +41,12 @@ static int _recv(struct socket *sock, void *buf, int size, unsigned flags)
 	return kernel_recvmsg(sock, &msg, &iov, 1, size, flags);
 }
 
-static inline int do_send(struct socket *sock, struct kvec *vec, int count,
-			  int len, unsigned flags)
-{
-	struct msghdr msg = { .msg_flags = flags };
-	return kernel_sendmsg(sock, &msg, vec, count, len);
-}
-
 static int _send(struct socket *sock, const void *buff, int len)
 {
-	struct kvec vec;
-	vec.iov_base = (void *) buff;
-	vec.iov_len = len;
-	return do_send(sock, &vec, 1, len, 0);
+	struct msghdr msg = { .msg_flags = 0 };
+	struct kvec vec = {.iov_base = (void *)buff, .iov_len = len};
+	iov_iter_kvec(&msg.msg_iter, WRITE | ITER_KVEC, &vec, 1, len);
+	return sock_sendmsg(sock, &msg);
 }
 
 struct ncp_request_reply {
@@ -63,9 +57,7 @@ struct ncp_request_reply {
 	size_t datalen;
 	int result;
 	enum { RQ_DONE, RQ_INPROGRESS, RQ_QUEUED, RQ_IDLE, RQ_ABANDONED } status;
-	struct kvec* tx_ciov;
-	size_t tx_totallen;
-	size_t tx_iovlen;
+	struct iov_iter from;
 	struct kvec tx_iov[3];
 	u_int16_t tx_type;
 	u_int32_t sign[6];
@@ -205,28 +197,22 @@ static inline void __ncptcp_abort(struct ncp_server *server)
 
 static int ncpdgram_send(struct socket *sock, struct ncp_request_reply *req)
 {
-	struct kvec vec[3];
-	/* sock_sendmsg updates iov pointers for us :-( */
-	memcpy(vec, req->tx_ciov, req->tx_iovlen * sizeof(vec[0]));
-	return do_send(sock, vec, req->tx_iovlen,
-		       req->tx_totallen, MSG_DONTWAIT);
+	struct msghdr msg = { .msg_iter = req->from, .msg_flags = MSG_DONTWAIT };
+	return sock_sendmsg(sock, &msg);
 }
 
 static void __ncptcp_try_send(struct ncp_server *server)
 {
 	struct ncp_request_reply *rq;
-	struct kvec *iov;
-	struct kvec iovc[3];
+	struct msghdr msg = { .msg_flags = MSG_NOSIGNAL | MSG_DONTWAIT };
 	int result;
 
 	rq = server->tx.creq;
 	if (!rq)
 		return;
 
-	/* sock_sendmsg updates iov pointers for us :-( */
-	memcpy(iovc, rq->tx_ciov, rq->tx_iovlen * sizeof(iov[0]));
-	result = do_send(server->ncp_sock, iovc, rq->tx_iovlen,
-			 rq->tx_totallen, MSG_NOSIGNAL | MSG_DONTWAIT);
+	msg.msg_iter = rq->from;
+	result = sock_sendmsg(server->ncp_sock, &msg);
 
 	if (result == -EAGAIN)
 		return;
@@ -236,21 +222,12 @@ static void __ncptcp_try_send(struct ncp_server *server)
 		__ncp_abort_request(server, rq, result);
 		return;
 	}
-	if (result >= rq->tx_totallen) {
+	if (!msg_data_left(&msg)) {
 		server->rcv.creq = rq;
 		server->tx.creq = NULL;
 		return;
 	}
-	rq->tx_totallen -= result;
-	iov = rq->tx_ciov;
-	while (iov->iov_len <= result) {
-		result -= iov->iov_len;
-		iov++;
-		rq->tx_iovlen--;
-	}
-	iov->iov_base += result;
-	iov->iov_len -= result;
-	rq->tx_ciov = iov;
+	rq->from = msg.msg_iter;
 }
 
 static inline void ncp_init_header(struct ncp_server *server, struct ncp_request_reply *req, struct ncp_request_header *h)
@@ -263,22 +240,21 @@ static inline void ncp_init_header(struct ncp_server *server, struct ncp_request
 	
 static void ncpdgram_start_request(struct ncp_server *server, struct ncp_request_reply *req)
 {
-	size_t signlen;
-	struct ncp_request_header* h;
+	size_t signlen, len = req->tx_iov[1].iov_len;
+	struct ncp_request_header *h = req->tx_iov[1].iov_base;
 	
-	req->tx_ciov = req->tx_iov + 1;
-
-	h = req->tx_iov[1].iov_base;
 	ncp_init_header(server, req, h);
-	signlen = sign_packet(server, req->tx_iov[1].iov_base + sizeof(struct ncp_request_header) - 1, 
-			req->tx_iov[1].iov_len - sizeof(struct ncp_request_header) + 1,
-			cpu_to_le32(req->tx_totallen), req->sign);
+	signlen = sign_packet(server,
+			req->tx_iov[1].iov_base + sizeof(struct ncp_request_header) - 1, 
+			len - sizeof(struct ncp_request_header) + 1,
+			cpu_to_le32(len), req->sign);
 	if (signlen) {
-		req->tx_ciov[1].iov_base = req->sign;
-		req->tx_ciov[1].iov_len = signlen;
-		req->tx_iovlen += 1;
-		req->tx_totallen += signlen;
+		/* NCP over UDP appends signature */
+		req->tx_iov[2].iov_base = req->sign;
+		req->tx_iov[2].iov_len = signlen;
 	}
+	iov_iter_kvec(&req->from, WRITE | ITER_KVEC,
+			req->tx_iov + 1, signlen ? 2 : 1, len + signlen);
 	server->rcv.creq = req;
 	server->timeout_last = server->m.time_out;
 	server->timeout_retries = server->m.retry_count;
@@ -292,24 +268,23 @@ static void ncpdgram_start_request(struct ncp_server *server, struct ncp_request
 
 static void ncptcp_start_request(struct ncp_server *server, struct ncp_request_reply *req)
 {
-	size_t signlen;
-	struct ncp_request_header* h;
+	size_t signlen, len = req->tx_iov[1].iov_len;
+	struct ncp_request_header *h = req->tx_iov[1].iov_base;
 
-	req->tx_ciov = req->tx_iov;
-	h = req->tx_iov[1].iov_base;
 	ncp_init_header(server, req, h);
 	signlen = sign_packet(server, req->tx_iov[1].iov_base + sizeof(struct ncp_request_header) - 1,
-			req->tx_iov[1].iov_len - sizeof(struct ncp_request_header) + 1,
-			cpu_to_be32(req->tx_totallen + 24), req->sign + 4) + 16;
+			len - sizeof(struct ncp_request_header) + 1,
+			cpu_to_be32(len + 24), req->sign + 4) + 16;
 
 	req->sign[0] = htonl(NCP_TCP_XMIT_MAGIC);
-	req->sign[1] = htonl(req->tx_totallen + signlen);
+	req->sign[1] = htonl(len + signlen);
 	req->sign[2] = htonl(NCP_TCP_XMIT_VERSION);
 	req->sign[3] = htonl(req->datalen + 8);
+	/* NCP over TCP prepends signature */
 	req->tx_iov[0].iov_base = req->sign;
 	req->tx_iov[0].iov_len = signlen;
-	req->tx_iovlen += 1;
-	req->tx_totallen += signlen;
+	iov_iter_kvec(&req->from, WRITE | ITER_KVEC,
+			req->tx_iov, 2, len + signlen);
 
 	server->tx.creq = req;
 	__ncptcp_try_send(server);
@@ -364,18 +339,17 @@ static void __ncp_next_request(struct ncp_server *server)
 static void info_server(struct ncp_server *server, unsigned int id, const void * data, size_t len)
 {
 	if (server->info_sock) {
-		struct kvec iov[2];
-		__be32 hdr[2];
-	
-		hdr[0] = cpu_to_be32(len + 8);
-		hdr[1] = cpu_to_be32(id);
-	
-		iov[0].iov_base = hdr;
-		iov[0].iov_len = 8;
-		iov[1].iov_base = (void *) data;
-		iov[1].iov_len = len;
+		struct msghdr msg = { .msg_flags = MSG_NOSIGNAL };
+		__be32 hdr[2] = {cpu_to_be32(len + 8), cpu_to_be32(id)};
+		struct kvec iov[2] = {
+			{.iov_base = hdr, .iov_len = 8},
+			{.iov_base = (void *)data, .iov_len = len},
+		};
+
+		iov_iter_kvec(&msg.msg_iter, ITER_KVEC | WRITE,
+				iov, 2, len + 8);
 
-		do_send(server->info_sock, iov, 2, len + 8, MSG_NOSIGNAL);
+		sock_sendmsg(server->info_sock, &msg);
 	}
 }
 
@@ -525,7 +499,7 @@ static int do_tcp_rcv(struct ncp_server *server, void *buffer, size_t len)
 		return result;
 	}
 	if (result > len) {
-		pr_err("tcp: bug in recvmsg (%u > %Zu)\n", result, len);
+		pr_err("tcp: bug in recvmsg (%u > %zu)\n", result, len);
 		return -EIO;			
 	}
 	return result;
@@ -619,7 +593,7 @@ skipdata:;
 					goto skipdata2;
 				}
 				if (datalen > req->datalen + 8) {
-					pr_err("tcp: Unexpected reply len %d (expected at most %Zd)\n", datalen, req->datalen + 8);
+					pr_err("tcp: Unexpected reply len %d (expected at most %zd)\n", datalen, req->datalen + 8);
 					server->rcv.state = 3;
 					goto skipdata;
 				}
@@ -711,8 +685,6 @@ static int do_ncp_rpc_call(struct ncp_server *server, int size,
 	req->datalen = max_reply_size;
 	req->tx_iov[1].iov_base = server->packet;
 	req->tx_iov[1].iov_len = size;
-	req->tx_iovlen = 1;
-	req->tx_totallen = size;
 	req->tx_type = *(u_int16_t*)server->packet;
 
 	result = ncp_add_request(server, req);
diff --git a/fs/nfs/Kconfig b/fs/nfs/Kconfig
index f31fd0dd92c6..69d02cf8cf37 100644
--- a/fs/nfs/Kconfig
+++ b/fs/nfs/Kconfig
@@ -123,11 +123,6 @@ config PNFS_BLOCK
 	depends on NFS_V4_1 && BLK_DEV_DM
 	default NFS_V4
 
-config PNFS_OBJLAYOUT
-	tristate
-	depends on NFS_V4_1 && SCSI_OSD_ULD
-	default NFS_V4
-
 config PNFS_FLEXFILE_LAYOUT
 	tristate
 	depends on NFS_V4_1 && NFS_V3
diff --git a/fs/nfs/Makefile b/fs/nfs/Makefile
index 6abdda209642..1fb118902d57 100644
--- a/fs/nfs/Makefile
+++ b/fs/nfs/Makefile
@@ -7,7 +7,7 @@ obj-$(CONFIG_NFS_FS) += nfs.o
 CFLAGS_nfstrace.o += -I$(src)
 nfs-y 			:= client.o dir.o file.o getroot.o inode.o super.o \
 			   io.o direct.o pagelist.o read.o symlink.o unlink.o \
-			   write.o namespace.o mount_clnt.o nfstrace.o
+			   write.o namespace.o mount_clnt.o nfstrace.o export.o
 nfs-$(CONFIG_ROOT_NFS)	+= nfsroot.o
 nfs-$(CONFIG_SYSCTL)	+= sysctl.o
 nfs-$(CONFIG_NFS_FSCACHE) += fscache.o fscache-index.o
@@ -31,6 +31,5 @@ nfsv4-$(CONFIG_NFS_V4_1)	+= pnfs.o pnfs_dev.o pnfs_nfs.o
 nfsv4-$(CONFIG_NFS_V4_2)	+= nfs42proc.o
 
 obj-$(CONFIG_PNFS_FILE_LAYOUT) += filelayout/
-obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayout/
 obj-$(CONFIG_PNFS_BLOCK) += blocklayout/
 obj-$(CONFIG_PNFS_FLEXFILE_LAYOUT) += flexfilelayout/
diff --git a/fs/nfs/blocklayout/blocklayout.c b/fs/nfs/blocklayout/blocklayout.c
index 2905479f214a..d8863a804b15 100644
--- a/fs/nfs/blocklayout/blocklayout.c
+++ b/fs/nfs/blocklayout/blocklayout.c
@@ -188,7 +188,7 @@ static void bl_end_io_read(struct bio *bio)
 {
 	struct parallel_io *par = bio->bi_private;
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		struct nfs_pgio_header *header = par->data;
 
 		if (!header->pnfs_error)
@@ -319,7 +319,7 @@ static void bl_end_io_write(struct bio *bio)
 	struct parallel_io *par = bio->bi_private;
 	struct nfs_pgio_header *header = par->data;
 
-	if (bio->bi_error) {
+	if (bio->bi_status) {
 		if (!header->pnfs_error)
 			header->pnfs_error = -EIO;
 		pnfs_set_lo_fail(header->lseg);
@@ -381,7 +381,7 @@ bl_write_pagelist(struct nfs_pgio_header *header, int sync)
 	struct blk_plug plug;
 	int i;
 
-	dprintk("%s enter, %Zu@%lld\n", __func__, count, offset);
+	dprintk("%s enter, %zu@%lld\n", __func__, count, offset);
 
 	/* At this point, header->page_aray is a (sequential) list of nfs_pages.
 	 * We want to write each, and if there is an error set pnfs_error
diff --git a/fs/nfs/cache_lib.c b/fs/nfs/cache_lib.c
index 6de15709d024..2ae676f93e6b 100644
--- a/fs/nfs/cache_lib.c
+++ b/fs/nfs/cache_lib.c
@@ -141,8 +141,7 @@ int nfs_cache_register_net(struct net *net, struct cache_detail *cd)
 
 void nfs_cache_unregister_sb(struct super_block *sb, struct cache_detail *cd)
 {
-	if (cd->u.pipefs.dir)
-		sunrpc_cache_unregister_pipefs(cd);
+	sunrpc_cache_unregister_pipefs(cd);
 }
 
 void nfs_cache_unregister_net(struct net *net, struct cache_detail *cd)
diff --git a/fs/nfs/callback.c b/fs/nfs/callback.c
index 484bebc20bca..34323877ec13 100644
--- a/fs/nfs/callback.c
+++ b/fs/nfs/callback.c
@@ -9,6 +9,7 @@
 #include <linux/completion.h>
 #include <linux/ip.h>
 #include <linux/module.h>
+#include <linux/sched/signal.h>
 #include <linux/sunrpc/svc.h>
 #include <linux/sunrpc/svcsock.h>
 #include <linux/nfs_fs.h>
@@ -75,7 +76,10 @@ nfs4_callback_svc(void *vrqstp)
 
 	set_freezable();
 
-	while (!kthread_should_stop()) {
+	while (!kthread_freezable_should_stop(NULL)) {
+
+		if (signal_pending(current))
+			flush_signals(current);
 		/*
 		 * Listen for a request on the socket
 		 */
@@ -84,6 +88,8 @@ nfs4_callback_svc(void *vrqstp)
 			continue;
 		svc_process(rqstp);
 	}
+	svc_exit_thread(rqstp);
+	module_put_and_exit(0);
 	return 0;
 }
 
@@ -102,9 +108,10 @@ nfs41_callback_svc(void *vrqstp)
 
 	set_freezable();
 
-	while (!kthread_should_stop()) {
-		if (try_to_freeze())
-			continue;
+	while (!kthread_freezable_should_stop(NULL)) {
+
+		if (signal_pending(current))
+			flush_signals(current);
 
 		prepare_to_wait(&serv->sv_cb_waitq, &wq, TASK_INTERRUPTIBLE);
 		spin_lock_bh(&serv->sv_cb_lock);
@@ -120,11 +127,13 @@ nfs41_callback_svc(void *vrqstp)
 				error);
 		} else {
 			spin_unlock_bh(&serv->sv_cb_lock);
-			schedule();
+			if (!kthread_should_stop())
+				schedule();
 			finish_wait(&serv->sv_cb_waitq, &wq);
 		}
-		flush_signals(current);
 	}
+	svc_exit_thread(rqstp);
+	module_put_and_exit(0);
 	return 0;
 }
 
@@ -220,23 +229,23 @@ err_bind:
 static struct svc_serv_ops nfs40_cb_sv_ops = {
 	.svo_function		= nfs4_callback_svc,
 	.svo_enqueue_xprt	= svc_xprt_do_enqueue,
-	.svo_setup		= svc_set_num_threads,
+	.svo_setup		= svc_set_num_threads_sync,
 	.svo_module		= THIS_MODULE,
 };
 #if defined(CONFIG_NFS_V4_1)
 static struct svc_serv_ops nfs41_cb_sv_ops = {
 	.svo_function		= nfs41_callback_svc,
 	.svo_enqueue_xprt	= svc_xprt_do_enqueue,
-	.svo_setup		= svc_set_num_threads,
+	.svo_setup		= svc_set_num_threads_sync,
 	.svo_module		= THIS_MODULE,
 };
 
-struct svc_serv_ops *nfs4_cb_sv_ops[] = {
+static struct svc_serv_ops *nfs4_cb_sv_ops[] = {
 	[0] = &nfs40_cb_sv_ops,
 	[1] = &nfs41_cb_sv_ops,
 };
 #else
-struct svc_serv_ops *nfs4_cb_sv_ops[] = {
+static struct svc_serv_ops *nfs4_cb_sv_ops[] = {
 	[0] = &nfs40_cb_sv_ops,
 	[1] = NULL,
 };
@@ -279,7 +288,7 @@ static struct svc_serv *nfs_callback_create_svc(int minorversion)
 		printk(KERN_WARNING "nfs_callback_create_svc: no kthread, %d users??\n",
 			cb_info->users);
 
-	serv = svc_create(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, sv_ops);
+	serv = svc_create_pooled(&nfs4_callback_program, NFS4_CALLBACK_BUFSIZE, sv_ops);
 	if (!serv) {
 		printk(KERN_ERR "nfs_callback_create_svc: create service failed\n");
 		return ERR_PTR(-ENOMEM);
@@ -430,7 +439,7 @@ static int nfs_callback_authenticate(struct svc_rqst *rqstp)
 /*
  * Define NFS4 callback program
  */
-static struct svc_version *nfs4_callback_version[] = {
+static const struct svc_version *nfs4_callback_version[] = {
 	[1] = &nfs4_callback_version1,
 	[4] = &nfs4_callback_version4,
 };
diff --git a/fs/nfs/callback.h b/fs/nfs/callback.h
index c701c308fac5..3dc54d7cb19c 100644
--- a/fs/nfs/callback.h
+++ b/fs/nfs/callback.h
@@ -114,8 +114,7 @@ struct cb_sequenceres {
 	uint32_t			csr_target_highestslotid;
 };
 
-extern __be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
-				       struct cb_sequenceres *res,
+extern __be32 nfs4_callback_sequence(void *argp, void *resp,
 				       struct cb_process_state *cps);
 
 #define RCA4_TYPE_MASK_RDATA_DLG	0
@@ -134,15 +133,13 @@ struct cb_recallanyargs {
 	uint32_t	craa_type_mask;
 };
 
-extern __be32 nfs4_callback_recallany(struct cb_recallanyargs *args,
-					void *dummy,
+extern __be32 nfs4_callback_recallany(void *argp, void *resp,
 					struct cb_process_state *cps);
 
 struct cb_recallslotargs {
 	uint32_t	crsa_target_highest_slotid;
 };
-extern __be32 nfs4_callback_recallslot(struct cb_recallslotargs *args,
-					 void *dummy,
+extern __be32 nfs4_callback_recallslot(void *argp, void *resp,
 					 struct cb_process_state *cps);
 
 struct cb_layoutrecallargs {
@@ -159,9 +156,8 @@ struct cb_layoutrecallargs {
 	};
 };
 
-extern __be32 nfs4_callback_layoutrecall(
-	struct cb_layoutrecallargs *args,
-	void *dummy, struct cb_process_state *cps);
+extern __be32 nfs4_callback_layoutrecall(void *argp, void *resp,
+		struct cb_process_state *cps);
 
 struct cb_devicenotifyitem {
 	uint32_t		cbd_notify_type;
@@ -175,9 +171,8 @@ struct cb_devicenotifyargs {
 	struct cb_devicenotifyitem	 *devs;
 };
 
-extern __be32 nfs4_callback_devicenotify(
-	struct cb_devicenotifyargs *args,
-	void *dummy, struct cb_process_state *cps);
+extern __be32 nfs4_callback_devicenotify(void *argp, void *resp,
+		struct cb_process_state *cps);
 
 struct cb_notify_lock_args {
 	struct nfs_fh			cbnl_fh;
@@ -185,15 +180,13 @@ struct cb_notify_lock_args {
 	bool				cbnl_valid;
 };
 
-extern __be32 nfs4_callback_notify_lock(struct cb_notify_lock_args *args,
-					 void *dummy,
+extern __be32 nfs4_callback_notify_lock(void *argp, void *resp,
 					 struct cb_process_state *cps);
 #endif /* CONFIG_NFS_V4_1 */
 extern int check_gss_callback_principal(struct nfs_client *, struct svc_rqst *);
-extern __be32 nfs4_callback_getattr(struct cb_getattrargs *args,
-				    struct cb_getattrres *res,
+extern __be32 nfs4_callback_getattr(void *argp, void *resp,
 				    struct cb_process_state *cps);
-extern __be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
+extern __be32 nfs4_callback_recall(void *argp, void *resp,
 				   struct cb_process_state *cps);
 #if IS_ENABLED(CONFIG_NFS_V4)
 extern int nfs_callback_up(u32 minorversion, struct rpc_xprt *xprt);
diff --git a/fs/nfs/callback_proc.c b/fs/nfs/callback_proc.c
index f073a6d2c6a5..5427cdf04c5a 100644
--- a/fs/nfs/callback_proc.c
+++ b/fs/nfs/callback_proc.c
@@ -19,10 +19,11 @@
 
 #define NFSDBG_FACILITY NFSDBG_CALLBACK
 
-__be32 nfs4_callback_getattr(struct cb_getattrargs *args,
-			     struct cb_getattrres *res,
+__be32 nfs4_callback_getattr(void *argp, void *resp,
 			     struct cb_process_state *cps)
 {
+	struct cb_getattrargs *args = argp;
+	struct cb_getattrres *res = resp;
 	struct nfs_delegation *delegation;
 	struct nfs_inode *nfsi;
 	struct inode *inode;
@@ -68,9 +69,10 @@ out:
 	return res->status;
 }
 
-__be32 nfs4_callback_recall(struct cb_recallargs *args, void *dummy,
+__be32 nfs4_callback_recall(void *argp, void *resp,
 			    struct cb_process_state *cps)
 {
+	struct cb_recallargs *args = argp;
 	struct inode *inode;
 	__be32 res;
 	
@@ -131,10 +133,11 @@ restart:
 			if (!inode)
 				continue;
 			if (!nfs_sb_active(inode->i_sb)) {
-				rcu_read_lock();
+				rcu_read_unlock();
 				spin_unlock(&clp->cl_lock);
 				iput(inode);
 				spin_lock(&clp->cl_lock);
+				rcu_read_lock();
 				goto restart;
 			}
 			return inode;
@@ -170,10 +173,11 @@ restart:
 			if (!inode)
 				continue;
 			if (!nfs_sb_active(inode->i_sb)) {
-				rcu_read_lock();
+				rcu_read_unlock();
 				spin_unlock(&clp->cl_lock);
 				iput(inode);
 				spin_lock(&clp->cl_lock);
+				rcu_read_lock();
 				goto restart;
 			}
 			return inode;
@@ -317,31 +321,19 @@ static u32 initiate_bulk_draining(struct nfs_client *clp,
 static u32 do_callback_layoutrecall(struct nfs_client *clp,
 				    struct cb_layoutrecallargs *args)
 {
-	u32 res;
-
-	dprintk("%s enter, type=%i\n", __func__, args->cbl_recall_type);
 	if (args->cbl_recall_type == RETURN_FILE)
-		res = initiate_file_draining(clp, args);
-	else
-		res = initiate_bulk_draining(clp, args);
-	dprintk("%s returning %i\n", __func__, res);
-	return res;
-
+		return initiate_file_draining(clp, args);
+	return initiate_bulk_draining(clp, args);
 }
 
-__be32 nfs4_callback_layoutrecall(struct cb_layoutrecallargs *args,
-				  void *dummy, struct cb_process_state *cps)
+__be32 nfs4_callback_layoutrecall(void *argp, void *resp,
+				  struct cb_process_state *cps)
 {
-	u32 res;
-
-	dprintk("%s: -->\n", __func__);
+	struct cb_layoutrecallargs *args = argp;
+	u32 res = NFS4ERR_OP_NOT_IN_SESSION;
 
 	if (cps->clp)
 		res = do_callback_layoutrecall(cps->clp, args);
-	else
-		res = NFS4ERR_OP_NOT_IN_SESSION;
-
-	dprintk("%s: exit with status = %d\n", __func__, res);
 	return cpu_to_be32(res);
 }
 
@@ -356,16 +348,15 @@ static void pnfs_recall_all_layouts(struct nfs_client *clp)
 	do_callback_layoutrecall(clp, &args);
 }
 
-__be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args,
-				  void *dummy, struct cb_process_state *cps)
+__be32 nfs4_callback_devicenotify(void *argp, void *resp,
+				  struct cb_process_state *cps)
 {
+	struct cb_devicenotifyargs *args = argp;
 	int i;
 	__be32 res = 0;
 	struct nfs_client *clp = cps->clp;
 	struct nfs_server *server = NULL;
 
-	dprintk("%s: -->\n", __func__);
-
 	if (!clp) {
 		res = cpu_to_be32(NFS4ERR_OP_NOT_IN_SESSION);
 		goto out;
@@ -384,8 +375,6 @@ __be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args,
 					goto found;
 				}
 			rcu_read_unlock();
-			dprintk("%s: layout type %u not found\n",
-				__func__, dev->cbd_layout_type);
 			continue;
 		}
 
@@ -395,8 +384,6 @@ __be32 nfs4_callback_devicenotify(struct cb_devicenotifyargs *args,
 
 out:
 	kfree(args->devs);
-	dprintk("%s: exit with status = %u\n",
-		__func__, be32_to_cpu(res));
 	return res;
 }
 
@@ -417,16 +404,11 @@ static __be32
 validate_seqid(const struct nfs4_slot_table *tbl, const struct nfs4_slot *slot,
 		const struct cb_sequenceargs * args)
 {
-	dprintk("%s enter. slotid %u seqid %u, slot table seqid: %u\n",
-		__func__, args->csa_slotid, args->csa_sequenceid, slot->seq_nr);
-
 	if (args->csa_slotid > tbl->server_highest_slotid)
 		return htonl(NFS4ERR_BADSLOT);
 
 	/* Replay */
 	if (args->csa_sequenceid == slot->seq_nr) {
-		dprintk("%s seqid %u is a replay\n",
-			__func__, args->csa_sequenceid);
 		if (nfs4_test_locked_slot(tbl, slot->slot_nr))
 			return htonl(NFS4ERR_DELAY);
 		/* Signal process_op to set this error on next op */
@@ -480,15 +462,6 @@ static bool referring_call_exists(struct nfs_client *clp,
 
 		for (j = 0; j < rclist->rcl_nrefcalls; j++) {
 			ref = &rclist->rcl_refcalls[j];
-
-			dprintk("%s: sessionid %x:%x:%x:%x sequenceid %u "
-				"slotid %u\n", __func__,
-				((u32 *)&rclist->rcl_sessionid.data)[0],
-				((u32 *)&rclist->rcl_sessionid.data)[1],
-				((u32 *)&rclist->rcl_sessionid.data)[2],
-				((u32 *)&rclist->rcl_sessionid.data)[3],
-				ref->rc_sequenceid, ref->rc_slotid);
-
 			status = nfs4_slot_wait_on_seqid(tbl, ref->rc_slotid,
 					ref->rc_sequenceid, HZ >> 1) < 0;
 			if (status)
@@ -500,10 +473,11 @@ out:
 	return status;
 }
 
-__be32 nfs4_callback_sequence(struct cb_sequenceargs *args,
-			      struct cb_sequenceres *res,
+__be32 nfs4_callback_sequence(void *argp, void *resp,
 			      struct cb_process_state *cps)
 {
+	struct cb_sequenceargs *args = argp;
+	struct cb_sequenceres *res = resp;
 	struct nfs4_slot_table *tbl;
 	struct nfs4_slot *slot;
 	struct nfs_client *clp;
@@ -593,8 +567,6 @@ out:
 		res->csr_status = status;
 
 	trace_nfs4_cb_sequence(args, res, status);
-	dprintk("%s: exit with status = %d res->csr_status %d\n", __func__,
-		ntohl(status), ntohl(res->csr_status));
 	return status;
 }
 
@@ -604,9 +576,10 @@ validate_bitmap_values(unsigned long mask)
 	return (mask & ~RCA4_TYPE_MASK_ALL) == 0;
 }
 
-__be32 nfs4_callback_recallany(struct cb_recallanyargs *args, void *dummy,
+__be32 nfs4_callback_recallany(void *argp, void *resp,
 			       struct cb_process_state *cps)
 {
+	struct cb_recallanyargs *args = argp;
 	__be32 status;
 	fmode_t flags = 0;
 
@@ -639,9 +612,10 @@ out:
 }
 
 /* Reduce the fore channel's max_slots to the target value */
-__be32 nfs4_callback_recallslot(struct cb_recallslotargs *args, void *dummy,
+__be32 nfs4_callback_recallslot(void *argp, void *resp,
 				struct cb_process_state *cps)
 {
+	struct cb_recallslotargs *args = argp;
 	struct nfs4_slot_table *fc_tbl;
 	__be32 status;
 
@@ -664,9 +638,11 @@ out:
 	return status;
 }
 
-__be32 nfs4_callback_notify_lock(struct cb_notify_lock_args *args, void *dummy,
+__be32 nfs4_callback_notify_lock(void *argp, void *resp,
 				 struct cb_process_state *cps)
 {
+	struct cb_notify_lock_args *args = argp;
+
 	if (!cps->clp) /* set in cb_sequence */
 		return htonl(NFS4ERR_OP_NOT_IN_SESSION);
 
diff --git a/fs/nfs/callback_xdr.c b/fs/nfs/callback_xdr.c
index eb094c6011d8..681dd642f119 100644
--- a/fs/nfs/callback_xdr.c
+++ b/fs/nfs/callback_xdr.c
@@ -43,32 +43,27 @@
 /* Internal error code */
 #define NFS4ERR_RESOURCE_HDR	11050
 
-typedef __be32 (*callback_process_op_t)(void *, void *,
-					struct cb_process_state *);
-typedef __be32 (*callback_decode_arg_t)(struct svc_rqst *, struct xdr_stream *, void *);
-typedef __be32 (*callback_encode_res_t)(struct svc_rqst *, struct xdr_stream *, void *);
-
-
 struct callback_op {
-	callback_process_op_t process_op;
-	callback_decode_arg_t decode_args;
-	callback_encode_res_t encode_res;
+	__be32 (*process_op)(void *, void *, struct cb_process_state *);
+	__be32 (*decode_args)(struct svc_rqst *, struct xdr_stream *, void *);
+	__be32 (*encode_res)(struct svc_rqst *, struct xdr_stream *,
+			const void *);
 	long res_maxsize;
 };
 
 static struct callback_op callback_ops[];
 
-static __be32 nfs4_callback_null(struct svc_rqst *rqstp, void *argp, void *resp)
+static __be32 nfs4_callback_null(struct svc_rqst *rqstp)
 {
 	return htonl(NFS4_OK);
 }
 
-static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+static int nfs4_decode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_argsize_check(rqstp, p);
 }
 
-static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+static int nfs4_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
@@ -83,23 +78,15 @@ static __be32 *read_buf(struct xdr_stream *xdr, size_t nbytes)
 	return p;
 }
 
-static __be32 decode_string(struct xdr_stream *xdr, unsigned int *len, const char **str)
+static __be32 decode_string(struct xdr_stream *xdr, unsigned int *len,
+		const char **str, size_t maxlen)
 {
-	__be32 *p;
-
-	p = read_buf(xdr, 4);
-	if (unlikely(p == NULL))
-		return htonl(NFS4ERR_RESOURCE);
-	*len = ntohl(*p);
-
-	if (*len != 0) {
-		p = read_buf(xdr, *len);
-		if (unlikely(p == NULL))
-			return htonl(NFS4ERR_RESOURCE);
-		*str = (const char *)p;
-	} else
-		*str = NULL;
+	ssize_t err;
 
+	err = xdr_stream_decode_opaque_inline(xdr, (void **)str, maxlen);
+	if (err < 0)
+		return cpu_to_be32(NFS4ERR_RESOURCE);
+	*len = err;
 	return 0;
 }
 
@@ -162,15 +149,9 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound
 	__be32 *p;
 	__be32 status;
 
-	status = decode_string(xdr, &hdr->taglen, &hdr->tag);
+	status = decode_string(xdr, &hdr->taglen, &hdr->tag, CB_OP_TAGLEN_MAXSZ);
 	if (unlikely(status != 0))
 		return status;
-	/* We do not like overly long tags! */
-	if (hdr->taglen > CB_OP_TAGLEN_MAXSZ) {
-		printk("NFS: NFSv4 CALLBACK %s: client sent tag of length %u\n",
-				__func__, hdr->taglen);
-		return htonl(NFS4ERR_RESOURCE);
-	}
 	p = read_buf(xdr, 12);
 	if (unlikely(p == NULL))
 		return htonl(NFS4ERR_RESOURCE);
@@ -185,8 +166,6 @@ static __be32 decode_compound_hdr_arg(struct xdr_stream *xdr, struct cb_compound
 		return htonl(NFS4ERR_MINOR_VERS_MISMATCH);
 	}
 	hdr->nops = ntohl(*p);
-	dprintk("%s: minorversion %d nops %d\n", __func__,
-		hdr->minorversion, hdr->nops);
 	return 0;
 }
 
@@ -200,37 +179,33 @@ static __be32 decode_op_hdr(struct xdr_stream *xdr, unsigned int *op)
 	return 0;
 }
 
-static __be32 decode_getattr_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_getattrargs *args)
+static __be32 decode_getattr_args(struct svc_rqst *rqstp,
+		struct xdr_stream *xdr, void *argp)
 {
+	struct cb_getattrargs *args = argp;
 	__be32 status;
 
 	status = decode_fh(xdr, &args->fh);
 	if (unlikely(status != 0))
-		goto out;
-	status = decode_bitmap(xdr, args->bitmap);
-out:
-	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
-	return status;
+		return status;
+	return decode_bitmap(xdr, args->bitmap);
 }
 
-static __be32 decode_recall_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_recallargs *args)
+static __be32 decode_recall_args(struct svc_rqst *rqstp,
+		struct xdr_stream *xdr, void *argp)
 {
+	struct cb_recallargs *args = argp;
 	__be32 *p;
 	__be32 status;
 
 	status = decode_delegation_stateid(xdr, &args->stateid);
 	if (unlikely(status != 0))
-		goto out;
+		return status;
 	p = read_buf(xdr, 4);
-	if (unlikely(p == NULL)) {
-		status = htonl(NFS4ERR_RESOURCE);
-		goto out;
-	}
+	if (unlikely(p == NULL))
+		return htonl(NFS4ERR_RESOURCE);
 	args->truncate = ntohl(*p);
-	status = decode_fh(xdr, &args->fh);
-out:
-	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
-	return status;
+	return decode_fh(xdr, &args->fh);
 }
 
 #if defined(CONFIG_NFS_V4_1)
@@ -241,18 +216,16 @@ static __be32 decode_layout_stateid(struct xdr_stream *xdr, nfs4_stateid *statei
 }
 
 static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp,
-				       struct xdr_stream *xdr,
-				       struct cb_layoutrecallargs *args)
+				       struct xdr_stream *xdr, void *argp)
 {
+	struct cb_layoutrecallargs *args = argp;
 	__be32 *p;
 	__be32 status = 0;
 	uint32_t iomode;
 
 	p = read_buf(xdr, 4 * sizeof(uint32_t));
-	if (unlikely(p == NULL)) {
-		status = htonl(NFS4ERR_BADXDR);
-		goto out;
-	}
+	if (unlikely(p == NULL))
+		return htonl(NFS4ERR_BADXDR);
 
 	args->cbl_layout_type = ntohl(*p++);
 	/* Depite the spec's xdr, iomode really belongs in the FILE switch,
@@ -266,44 +239,31 @@ static __be32 decode_layoutrecall_args(struct svc_rqst *rqstp,
 		args->cbl_range.iomode = iomode;
 		status = decode_fh(xdr, &args->cbl_fh);
 		if (unlikely(status != 0))
-			goto out;
+			return status;
 
 		p = read_buf(xdr, 2 * sizeof(uint64_t));
-		if (unlikely(p == NULL)) {
-			status = htonl(NFS4ERR_BADXDR);
-			goto out;
-		}
+		if (unlikely(p == NULL))
+			return htonl(NFS4ERR_BADXDR);
 		p = xdr_decode_hyper(p, &args->cbl_range.offset);
 		p = xdr_decode_hyper(p, &args->cbl_range.length);
-		status = decode_layout_stateid(xdr, &args->cbl_stateid);
-		if (unlikely(status != 0))
-			goto out;
+		return decode_layout_stateid(xdr, &args->cbl_stateid);
 	} else if (args->cbl_recall_type == RETURN_FSID) {
 		p = read_buf(xdr, 2 * sizeof(uint64_t));
-		if (unlikely(p == NULL)) {
-			status = htonl(NFS4ERR_BADXDR);
-			goto out;
-		}
+		if (unlikely(p == NULL))
+			return htonl(NFS4ERR_BADXDR);
 		p = xdr_decode_hyper(p, &args->cbl_fsid.major);
 		p = xdr_decode_hyper(p, &args->cbl_fsid.minor);
-	} else if (args->cbl_recall_type != RETURN_ALL) {
-		status = htonl(NFS4ERR_BADXDR);
-		goto out;
-	}
-	dprintk("%s: ltype 0x%x iomode %d changed %d recall_type %d\n",
-		__func__,
-		args->cbl_layout_type, iomode,
-		args->cbl_layoutchanged, args->cbl_recall_type);
-out:
-	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
-	return status;
+	} else if (args->cbl_recall_type != RETURN_ALL)
+		return htonl(NFS4ERR_BADXDR);
+	return 0;
 }
 
 static
 __be32 decode_devicenotify_args(struct svc_rqst *rqstp,
 				struct xdr_stream *xdr,
-				struct cb_devicenotifyargs *args)
+				void *argp)
 {
+	struct cb_devicenotifyargs *args = argp;
 	__be32 *p;
 	__be32 status = 0;
 	u32 tmp;
@@ -443,20 +403,20 @@ out:
 
 static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp,
 					struct xdr_stream *xdr,
-					struct cb_sequenceargs *args)
+					void *argp)
 {
+	struct cb_sequenceargs *args = argp;
 	__be32 *p;
 	int i;
 	__be32 status;
 
 	status = decode_sessionid(xdr, &args->csa_sessionid);
 	if (status)
-		goto out;
+		return status;
 
-	status = htonl(NFS4ERR_RESOURCE);
 	p = read_buf(xdr, 5 * sizeof(uint32_t));
 	if (unlikely(p == NULL))
-		goto out;
+		return htonl(NFS4ERR_RESOURCE);
 
 	args->csa_addr = svc_addr(rqstp);
 	args->csa_sequenceid = ntohl(*p++);
@@ -470,7 +430,7 @@ static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp,
 						  sizeof(*args->csa_rclists),
 						  GFP_KERNEL);
 		if (unlikely(args->csa_rclists == NULL))
-			goto out;
+			return htonl(NFS4ERR_RESOURCE);
 
 		for (i = 0; i < args->csa_nrclists; i++) {
 			status = decode_rc_list(xdr, &args->csa_rclists[i]);
@@ -480,33 +440,20 @@ static __be32 decode_cb_sequence_args(struct svc_rqst *rqstp,
 			}
 		}
 	}
-	status = 0;
-
-	dprintk("%s: sessionid %x:%x:%x:%x sequenceid %u slotid %u "
-		"highestslotid %u cachethis %d nrclists %u\n",
-		__func__,
-		((u32 *)&args->csa_sessionid)[0],
-		((u32 *)&args->csa_sessionid)[1],
-		((u32 *)&args->csa_sessionid)[2],
-		((u32 *)&args->csa_sessionid)[3],
-		args->csa_sequenceid, args->csa_slotid,
-		args->csa_highestslotid, args->csa_cachethis,
-		args->csa_nrclists);
-out:
-	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
-	return status;
+	return 0;
 
 out_free:
 	for (i = 0; i < args->csa_nrclists; i++)
 		kfree(args->csa_rclists[i].rcl_refcalls);
 	kfree(args->csa_rclists);
-	goto out;
+	return status;
 }
 
 static __be32 decode_recallany_args(struct svc_rqst *rqstp,
 				      struct xdr_stream *xdr,
-				      struct cb_recallanyargs *args)
+				      void *argp)
 {
+	struct cb_recallanyargs *args = argp;
 	uint32_t bitmap[2];
 	__be32 *p, status;
 
@@ -524,8 +471,9 @@ static __be32 decode_recallany_args(struct svc_rqst *rqstp,
 
 static __be32 decode_recallslot_args(struct svc_rqst *rqstp,
 					struct xdr_stream *xdr,
-					struct cb_recallslotargs *args)
+					void *argp)
 {
+	struct cb_recallslotargs *args = argp;
 	__be32 *p;
 
 	p = read_buf(xdr, 4);
@@ -565,29 +513,24 @@ static __be32 decode_lockowner(struct xdr_stream *xdr, struct cb_notify_lock_arg
 	return 0;
 }
 
-static __be32 decode_notify_lock_args(struct svc_rqst *rqstp, struct xdr_stream *xdr, struct cb_notify_lock_args *args)
+static __be32 decode_notify_lock_args(struct svc_rqst *rqstp,
+		struct xdr_stream *xdr, void *argp)
 {
+	struct cb_notify_lock_args *args = argp;
 	__be32 status;
 
 	status = decode_fh(xdr, &args->cbnl_fh);
 	if (unlikely(status != 0))
-		goto out;
-	status = decode_lockowner(xdr, args);
-out:
-	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
-	return status;
+		return status;
+	return decode_lockowner(xdr, args);
 }
 
 #endif /* CONFIG_NFS_V4_1 */
 
 static __be32 encode_string(struct xdr_stream *xdr, unsigned int len, const char *str)
 {
-	__be32 *p;
-
-	p = xdr_reserve_space(xdr, 4 + len);
-	if (unlikely(p == NULL))
-		return htonl(NFS4ERR_RESOURCE);
-	xdr_encode_opaque(p, str, len);
+	if (unlikely(xdr_stream_encode_opaque(xdr, str, len) < 0))
+		return cpu_to_be32(NFS4ERR_RESOURCE);
 	return 0;
 }
 
@@ -703,8 +646,10 @@ static __be32 encode_op_hdr(struct xdr_stream *xdr, uint32_t op, __be32 res)
 	return 0;
 }
 
-static __be32 encode_getattr_res(struct svc_rqst *rqstp, struct xdr_stream *xdr, const struct cb_getattrres *res)
+static __be32 encode_getattr_res(struct svc_rqst *rqstp, struct xdr_stream *xdr,
+		const void *resp)
 {
+	const struct cb_getattrres *res = resp;
 	__be32 *savep = NULL;
 	__be32 status = res->status;
 	
@@ -725,7 +670,6 @@ static __be32 encode_getattr_res(struct svc_rqst *rqstp, struct xdr_stream *xdr,
 	status = encode_attr_mtime(xdr, res->bitmap, &res->mtime);
 	*savep = htonl((unsigned int)((char *)xdr->p - (char *)(savep+1)));
 out:
-	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
 	return status;
 }
 
@@ -746,17 +690,18 @@ static __be32 encode_sessionid(struct xdr_stream *xdr,
 
 static __be32 encode_cb_sequence_res(struct svc_rqst *rqstp,
 				       struct xdr_stream *xdr,
-				       const struct cb_sequenceres *res)
+				       const void *resp)
 {
+	const struct cb_sequenceres *res = resp;
 	__be32 *p;
 	__be32 status = res->csr_status;
 
 	if (unlikely(status != 0))
-		goto out;
+		return status;
 
 	status = encode_sessionid(xdr, &res->csr_sessionid);
 	if (status)
-		goto out;
+		return status;
 
 	p = xdr_reserve_space(xdr, 4 * sizeof(uint32_t));
 	if (unlikely(p == NULL))
@@ -766,9 +711,7 @@ static __be32 encode_cb_sequence_res(struct svc_rqst *rqstp,
 	*p++ = htonl(res->csr_slotid);
 	*p++ = htonl(res->csr_highestslotid);
 	*p++ = htonl(res->csr_target_highestslotid);
-out:
-	dprintk("%s: exit with status = %d\n", __func__, ntohl(status));
-	return status;
+	return 0;
 }
 
 static __be32
@@ -818,7 +761,6 @@ static void nfs4_callback_free_slot(struct nfs4_session *session,
 	 * A single slot, so highest used slotid is either 0 or -1
 	 */
 	nfs4_free_slot(tbl, slot);
-	nfs4_slot_tbl_drain_complete(tbl);
 	spin_unlock(&tbl->slot_tbl_lock);
 }
 
@@ -889,14 +831,10 @@ static __be32 process_op(int nop, struct svc_rqst *rqstp,
 	long maxlen;
 	__be32 res;
 
-	dprintk("%s: start\n", __func__);
 	status = decode_op_hdr(xdr_in, &op_nr);
 	if (unlikely(status))
 		return status;
 
-	dprintk("%s: minorversion=%d nop=%d op_nr=%u\n",
-		__func__, cps->minorversion, nop, op_nr);
-
 	switch (cps->minorversion) {
 	case 0:
 		status = preprocess_nfs4_op(op_nr, &op);
@@ -935,14 +873,13 @@ encode_hdr:
 		return res;
 	if (op->encode_res != NULL && status == 0)
 		status = op->encode_res(rqstp, xdr_out, resp);
-	dprintk("%s: done, status = %d\n", __func__, ntohl(status));
 	return status;
 }
 
 /*
  * Decode, process and encode a COMPOUND
  */
-static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *resp)
+static __be32 nfs4_callback_compound(struct svc_rqst *rqstp)
 {
 	struct cb_compound_hdr_arg hdr_arg = { 0 };
 	struct cb_compound_hdr_res hdr_res = { NULL };
@@ -955,8 +892,6 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	};
 	unsigned int nops = 0;
 
-	dprintk("%s: start\n", __func__);
-
 	xdr_init_decode(&xdr_in, &rqstp->rq_arg, rqstp->rq_arg.head[0].iov_base);
 
 	p = (__be32*)((char *)rqstp->rq_res.head[0].iov_base + rqstp->rq_res.head[0].iov_len);
@@ -980,7 +915,8 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 
 	while (status == 0 && nops != hdr_arg.nops) {
 		status = process_op(nops, rqstp, &xdr_in,
-				    argp, &xdr_out, resp, &cps);
+				    rqstp->rq_argp, &xdr_out, rqstp->rq_resp,
+				    &cps);
 		nops++;
 	}
 
@@ -995,7 +931,6 @@ static __be32 nfs4_callback_compound(struct svc_rqst *rqstp, void *argp, void *r
 	*hdr_res.nops = htonl(nops);
 	nfs4_cb_free_slot(&cps);
 	nfs_put_client(cps.clp);
-	dprintk("%s: done, status = %u\n", __func__, ntohl(status));
 	return rpc_success;
 
 out_invalidcred:
@@ -1011,48 +946,46 @@ static struct callback_op callback_ops[] = {
 		.res_maxsize = CB_OP_HDR_RES_MAXSZ,
 	},
 	[OP_CB_GETATTR] = {
-		.process_op = (callback_process_op_t)nfs4_callback_getattr,
-		.decode_args = (callback_decode_arg_t)decode_getattr_args,
-		.encode_res = (callback_encode_res_t)encode_getattr_res,
+		.process_op = nfs4_callback_getattr,
+		.decode_args = decode_getattr_args,
+		.encode_res = encode_getattr_res,
 		.res_maxsize = CB_OP_GETATTR_RES_MAXSZ,
 	},
 	[OP_CB_RECALL] = {
-		.process_op = (callback_process_op_t)nfs4_callback_recall,
-		.decode_args = (callback_decode_arg_t)decode_recall_args,
+		.process_op = nfs4_callback_recall,
+		.decode_args = decode_recall_args,
 		.res_maxsize = CB_OP_RECALL_RES_MAXSZ,
 	},
 #if defined(CONFIG_NFS_V4_1)
 	[OP_CB_LAYOUTRECALL] = {
-		.process_op = (callback_process_op_t)nfs4_callback_layoutrecall,
-		.decode_args =
-			(callback_decode_arg_t)decode_layoutrecall_args,
+		.process_op = nfs4_callback_layoutrecall,
+		.decode_args = decode_layoutrecall_args,
 		.res_maxsize = CB_OP_LAYOUTRECALL_RES_MAXSZ,
 	},
 	[OP_CB_NOTIFY_DEVICEID] = {
-		.process_op = (callback_process_op_t)nfs4_callback_devicenotify,
-		.decode_args =
-			(callback_decode_arg_t)decode_devicenotify_args,
+		.process_op = nfs4_callback_devicenotify,
+		.decode_args = decode_devicenotify_args,
 		.res_maxsize = CB_OP_DEVICENOTIFY_RES_MAXSZ,
 	},
 	[OP_CB_SEQUENCE] = {
-		.process_op = (callback_process_op_t)nfs4_callback_sequence,
-		.decode_args = (callback_decode_arg_t)decode_cb_sequence_args,
-		.encode_res = (callback_encode_res_t)encode_cb_sequence_res,
+		.process_op = nfs4_callback_sequence,
+		.decode_args = decode_cb_sequence_args,
+		.encode_res = encode_cb_sequence_res,
 		.res_maxsize = CB_OP_SEQUENCE_RES_MAXSZ,
 	},
 	[OP_CB_RECALL_ANY] = {
-		.process_op = (callback_process_op_t)nfs4_callback_recallany,
-		.decode_args = (callback_decode_arg_t)decode_recallany_args,
+		.process_op = nfs4_callback_recallany,
+		.decode_args = decode_recallany_args,
 		.res_maxsize = CB_OP_RECALLANY_RES_MAXSZ,
 	},
 	[OP_CB_RECALL_SLOT] = {
-		.process_op = (callback_process_op_t)nfs4_callback_recallslot,
-		.decode_args = (callback_decode_arg_t)decode_recallslot_args,
+		.process_op = nfs4_callback_recallslot,
+		.decode_args = decode_recallslot_args,
 		.res_maxsize = CB_OP_RECALLSLOT_RES_MAXSZ,
 	},
 	[OP_CB_NOTIFY_LOCK] = {
-		.process_op = (callback_process_op_t)nfs4_callback_notify_lock,
-		.decode_args = (callback_decode_arg_t)decode_notify_lock_args,
+		.process_op = nfs4_callback_notify_lock,
+		.decode_args = decode_notify_lock_args,
 		.res_maxsize = CB_OP_NOTIFY_LOCK_RES_MAXSZ,
 	},
 #endif /* CONFIG_NFS_V4_1 */
@@ -1061,36 +994,42 @@ static struct callback_op callback_ops[] = {
 /*
  * Define NFS4 callback procedures
  */
-static struct svc_procedure nfs4_callback_procedures1[] = {
+static const struct svc_procedure nfs4_callback_procedures1[] = {
 	[CB_NULL] = {
 		.pc_func = nfs4_callback_null,
-		.pc_decode = (kxdrproc_t)nfs4_decode_void,
-		.pc_encode = (kxdrproc_t)nfs4_encode_void,
+		.pc_decode = nfs4_decode_void,
+		.pc_encode = nfs4_encode_void,
 		.pc_xdrressize = 1,
 	},
 	[CB_COMPOUND] = {
 		.pc_func = nfs4_callback_compound,
-		.pc_encode = (kxdrproc_t)nfs4_encode_void,
+		.pc_encode = nfs4_encode_void,
 		.pc_argsize = 256,
 		.pc_ressize = 256,
 		.pc_xdrressize = NFS4_CALLBACK_BUFSIZE,
 	}
 };
 
-struct svc_version nfs4_callback_version1 = {
+static unsigned int nfs4_callback_count1[ARRAY_SIZE(nfs4_callback_procedures1)];
+const struct svc_version nfs4_callback_version1 = {
 	.vs_vers = 1,
 	.vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1),
 	.vs_proc = nfs4_callback_procedures1,
+	.vs_count = nfs4_callback_count1,
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
 	.vs_dispatch = NULL,
-	.vs_hidden = 1,
+	.vs_hidden = true,
+	.vs_need_cong_ctrl = true,
 };
 
-struct svc_version nfs4_callback_version4 = {
+static unsigned int nfs4_callback_count4[ARRAY_SIZE(nfs4_callback_procedures1)];
+const struct svc_version nfs4_callback_version4 = {
 	.vs_vers = 4,
 	.vs_nproc = ARRAY_SIZE(nfs4_callback_procedures1),
 	.vs_proc = nfs4_callback_procedures1,
+	.vs_count = nfs4_callback_count4,
 	.vs_xdrsize = NFS4_CALLBACK_XDRSIZE,
 	.vs_dispatch = NULL,
-	.vs_hidden = 1,
+	.vs_hidden = true,
+	.vs_need_cong_ctrl = true,
 };
diff --git a/fs/nfs/client.c b/fs/nfs/client.c
index 91a8d610ba0f..efebe6cf4378 100644
--- a/fs/nfs/client.c
+++ b/fs/nfs/client.c
@@ -218,6 +218,7 @@ static void nfs_cb_idr_remove_locked(struct nfs_client *clp)
 static void pnfs_init_server(struct nfs_server *server)
 {
 	rpc_init_wait_queue(&server->roc_rpcwaitq, "pNFS ROC");
+	rpc_init_wait_queue(&server->uoc_rpcwaitq, "NFS UOC");
 }
 
 #else
@@ -240,8 +241,6 @@ static void pnfs_init_server(struct nfs_server *server)
  */
 void nfs_free_client(struct nfs_client *clp)
 {
-	dprintk("--> nfs_free_client(%u)\n", clp->rpc_ops->version);
-
 	nfs_fscache_release_client_cookie(clp);
 
 	/* -EIO all pending I/O */
@@ -256,8 +255,6 @@ void nfs_free_client(struct nfs_client *clp)
 	kfree(clp->cl_hostname);
 	kfree(clp->cl_acceptor);
 	kfree(clp);
-
-	dprintk("<-- nfs_free_client()\n");
 }
 EXPORT_SYMBOL_GPL(nfs_free_client);
 
@@ -271,7 +268,6 @@ void nfs_put_client(struct nfs_client *clp)
 	if (!clp)
 		return;
 
-	dprintk("--> nfs_put_client({%d})\n", atomic_read(&clp->cl_count));
 	nn = net_generic(clp->cl_net, nfs_net_id);
 
 	if (atomic_dec_and_lock(&clp->cl_count, &nn->nfs_client_lock)) {
@@ -325,10 +321,33 @@ static struct nfs_client *nfs_match_client(const struct nfs_client_initdata *dat
 	return NULL;
 }
 
-static bool nfs_client_init_is_complete(const struct nfs_client *clp)
+/*
+ * Return true if @clp is done initializing, false if still working on it.
+ *
+ * Use nfs_client_init_status to check if it was successful.
+ */
+bool nfs_client_init_is_complete(const struct nfs_client *clp)
 {
 	return clp->cl_cons_state <= NFS_CS_READY;
 }
+EXPORT_SYMBOL_GPL(nfs_client_init_is_complete);
+
+/*
+ * Return 0 if @clp was successfully initialized, -errno otherwise.
+ *
+ * This must be called *after* nfs_client_init_is_complete() returns true,
+ * otherwise it will pop WARN_ON_ONCE and return -EINVAL
+ */
+int nfs_client_init_status(const struct nfs_client *clp)
+{
+	/* called without checking nfs_client_init_is_complete */
+	if (clp->cl_cons_state > NFS_CS_READY) {
+		WARN_ON_ONCE(1);
+		return -EINVAL;
+	}
+	return clp->cl_cons_state;
+}
+EXPORT_SYMBOL_GPL(nfs_client_init_status);
 
 int nfs_wait_client_init_complete(const struct nfs_client *clp)
 {
@@ -359,9 +378,6 @@ nfs_found_client(const struct nfs_client_initdata *cl_init,
 	}
 
 	smp_rmb();
-
-	dprintk("<-- %s found nfs_client %p for %s\n",
-		__func__, clp, cl_init->hostname ?: "");
 	return clp;
 }
 
@@ -380,9 +396,6 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
 		return NULL;
 	}
 
-	dprintk("--> nfs_get_client(%s,v%u)\n",
-		cl_init->hostname, rpc_ops->version);
-
 	/* see if the client already exists */
 	do {
 		spin_lock(&nn->nfs_client_lock);
@@ -407,8 +420,6 @@ struct nfs_client *nfs_get_client(const struct nfs_client_initdata *cl_init)
 		new = rpc_ops->alloc_client(cl_init);
 	} while (!IS_ERR(new));
 
-	dprintk("<-- nfs_get_client() Failed to find %s (%ld)\n",
-		cl_init->hostname, PTR_ERR(new));
 	return new;
 }
 EXPORT_SYMBOL_GPL(nfs_get_client);
@@ -535,6 +546,7 @@ static int nfs_start_lockd(struct nfs_server *server)
 		.noresvport	= server->flags & NFS_MOUNT_NORESVPORT ?
 					1 : 0,
 		.net		= clp->cl_net,
+		.nlmclnt_ops 	= clp->cl_nfs_mod->rpc_ops->nlmclnt_ops,
 	};
 
 	if (nlm_init.nfs_version > 3)
@@ -601,27 +613,21 @@ struct nfs_client *nfs_init_client(struct nfs_client *clp,
 {
 	int error;
 
-	if (clp->cl_cons_state == NFS_CS_READY) {
-		/* the client is already initialised */
-		dprintk("<-- nfs_init_client() = 0 [already %p]\n", clp);
+	/* the client is already initialised */
+	if (clp->cl_cons_state == NFS_CS_READY)
 		return clp;
-	}
 
 	/*
 	 * Create a client RPC handle for doing FSSTAT with UNIX auth only
 	 * - RFC 2623, sec 2.3.2
 	 */
 	error = nfs_create_rpc_client(clp, cl_init, RPC_AUTH_UNIX);
-	if (error < 0)
-		goto error;
-	nfs_mark_client_ready(clp, NFS_CS_READY);
+	nfs_mark_client_ready(clp, error == 0 ? NFS_CS_READY : error);
+	if (error < 0) {
+		nfs_put_client(clp);
+		clp = ERR_PTR(error);
+	}
 	return clp;
-
-error:
-	nfs_mark_client_ready(clp, error);
-	nfs_put_client(clp);
-	dprintk("<-- nfs_init_client() = xerror %d\n", error);
-	return ERR_PTR(error);
 }
 EXPORT_SYMBOL_GPL(nfs_init_client);
 
@@ -645,8 +651,6 @@ static int nfs_init_server(struct nfs_server *server,
 	struct nfs_client *clp;
 	int error;
 
-	dprintk("--> nfs_init_server()\n");
-
 	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
 			data->timeo, data->retrans);
 	if (data->flags & NFS_MOUNT_NORESVPORT)
@@ -654,10 +658,8 @@ static int nfs_init_server(struct nfs_server *server,
 
 	/* Allocate or find a client reference we can use */
 	clp = nfs_get_client(&cl_init);
-	if (IS_ERR(clp)) {
-		dprintk("<-- nfs_init_server() = error %ld\n", PTR_ERR(clp));
+	if (IS_ERR(clp))
 		return PTR_ERR(clp);
-	}
 
 	server->nfs_client = clp;
 
@@ -702,13 +704,11 @@ static int nfs_init_server(struct nfs_server *server,
 	server->mountd_protocol = data->mount_server.protocol;
 
 	server->namelen  = data->namlen;
-	dprintk("<-- nfs_init_server() = 0 [new %p]\n", clp);
 	return 0;
 
 error:
 	server->nfs_client = NULL;
 	nfs_put_client(clp);
-	dprintk("<-- nfs_init_server() = xerror %d\n", error);
 	return error;
 }
 
@@ -738,9 +738,6 @@ static void nfs_server_set_fsinfo(struct nfs_server *server,
 		server->rsize = NFS_MAX_FILE_IO_SIZE;
 	server->rpages = (server->rsize + PAGE_SIZE - 1) >> PAGE_SHIFT;
 
-	server->backing_dev_info.name = "nfs";
-	server->backing_dev_info.ra_pages = server->rpages * NFS_MAX_READAHEAD;
-
 	if (server->wsize > max_rpc_payload)
 		server->wsize = max_rpc_payload;
 	if (server->wsize > NFS_MAX_FILE_IO_SIZE)
@@ -778,12 +775,10 @@ int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs
 	struct nfs_client *clp = server->nfs_client;
 	int error;
 
-	dprintk("--> nfs_probe_fsinfo()\n");
-
 	if (clp->rpc_ops->set_capabilities != NULL) {
 		error = clp->rpc_ops->set_capabilities(server, mntfh);
 		if (error < 0)
-			goto out_error;
+			return error;
 	}
 
 	fsinfo.fattr = fattr;
@@ -791,7 +786,7 @@ int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs
 	memset(fsinfo.layouttype, 0, sizeof(fsinfo.layouttype));
 	error = clp->rpc_ops->fsinfo(server, mntfh, &fsinfo);
 	if (error < 0)
-		goto out_error;
+		return error;
 
 	nfs_server_set_fsinfo(server, &fsinfo);
 
@@ -806,12 +801,7 @@ int nfs_probe_fsinfo(struct nfs_server *server, struct nfs_fh *mntfh, struct nfs
 			server->namelen = pathinfo.max_namelen;
 	}
 
-	dprintk("<-- nfs_probe_fsinfo() = 0\n");
 	return 0;
-
-out_error:
-	dprintk("nfs_probe_fsinfo: error = %d\n", -error);
-	return error;
 }
 EXPORT_SYMBOL_GPL(nfs_probe_fsinfo);
 
@@ -830,6 +820,7 @@ void nfs_server_copy_userdata(struct nfs_server *target, struct nfs_server *sour
 	target->caps = source->caps;
 	target->options = source->options;
 	target->auth_info = source->auth_info;
+	target->port = source->port;
 }
 EXPORT_SYMBOL_GPL(nfs_server_copy_userdata);
 
@@ -894,12 +885,6 @@ struct nfs_server *nfs_alloc_server(void)
 		return NULL;
 	}
 
-	if (bdi_init(&server->backing_dev_info)) {
-		nfs_free_iostats(server->io_stats);
-		kfree(server);
-		return NULL;
-	}
-
 	ida_init(&server->openowner_id);
 	ida_init(&server->lockowner_id);
 	pnfs_init_server(server);
@@ -913,8 +898,6 @@ EXPORT_SYMBOL_GPL(nfs_alloc_server);
  */
 void nfs_free_server(struct nfs_server *server)
 {
-	dprintk("--> nfs_free_server()\n");
-
 	nfs_server_remove_lists(server);
 
 	if (server->destroy != NULL)
@@ -930,10 +913,8 @@ void nfs_free_server(struct nfs_server *server)
 	ida_destroy(&server->lockowner_id);
 	ida_destroy(&server->openowner_id);
 	nfs_free_iostats(server->io_stats);
-	bdi_destroy(&server->backing_dev_info);
 	kfree(server);
 	nfs_release_automount_timer();
-	dprintk("<-- nfs_free_server()\n");
 }
 EXPORT_SYMBOL_GPL(nfs_free_server);
 
@@ -1013,10 +994,6 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
 	struct nfs_fattr *fattr_fsinfo;
 	int error;
 
-	dprintk("--> nfs_clone_server(,%llx:%llx,)\n",
-		(unsigned long long) fattr->fsid.major,
-		(unsigned long long) fattr->fsid.minor);
-
 	server = nfs_alloc_server();
 	if (!server)
 		return ERR_PTR(-ENOMEM);
@@ -1048,10 +1025,6 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
 	if (server->namelen == 0 || server->namelen > NFS4_MAXNAMLEN)
 		server->namelen = NFS4_MAXNAMLEN;
 
-	dprintk("Cloned FSID: %llx:%llx\n",
-		(unsigned long long) server->fsid.major,
-		(unsigned long long) server->fsid.minor);
-
 	error = nfs_start_lockd(server);
 	if (error < 0)
 		goto out_free_server;
@@ -1060,13 +1033,11 @@ struct nfs_server *nfs_clone_server(struct nfs_server *source,
 	server->mount_time = jiffies;
 
 	nfs_free_fattr(fattr_fsinfo);
-	dprintk("<-- nfs_clone_server() = %p\n", server);
 	return server;
 
 out_free_server:
 	nfs_free_fattr(fattr_fsinfo);
 	nfs_free_server(server);
-	dprintk("<-- nfs_clone_server() = error %d\n", error);
 	return ERR_PTR(error);
 }
 EXPORT_SYMBOL_GPL(nfs_clone_server);
diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c
index fad81041f5ab..3522b1249019 100644
--- a/fs/nfs/dir.c
+++ b/fs/nfs/dir.c
@@ -57,7 +57,7 @@ static void nfs_readdir_clear_array(struct page*);
 const struct file_operations nfs_dir_operations = {
 	.llseek		= nfs_llseek_dir,
 	.read		= generic_read_dir,
-	.iterate_shared	= nfs_readdir,
+	.iterate	= nfs_readdir,
 	.open		= nfs_opendir,
 	.release	= nfs_closedir,
 	.fsync		= nfs_fsync_dir,
@@ -145,14 +145,13 @@ struct nfs_cache_array_entry {
 };
 
 struct nfs_cache_array {
-	atomic_t refcount;
 	int size;
 	int eof_index;
 	u64 last_cookie;
 	struct nfs_cache_array_entry array[0];
 };
 
-typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, int);
+typedef int (*decode_dirent_t)(struct xdr_stream *, struct nfs_entry *, bool);
 typedef struct {
 	struct file	*file;
 	struct page	*page;
@@ -166,32 +165,11 @@ typedef struct {
 	unsigned long	timestamp;
 	unsigned long	gencount;
 	unsigned int	cache_entry_index;
-	unsigned int	plus:1;
-	unsigned int	eof:1;
+	bool plus;
+	bool eof;
 } nfs_readdir_descriptor_t;
 
 /*
- * The caller is responsible for calling nfs_readdir_release_array(page)
- */
-static
-struct nfs_cache_array *nfs_readdir_get_array(struct page *page)
-{
-	void *ptr;
-	if (page == NULL)
-		return ERR_PTR(-EIO);
-	ptr = kmap(page);
-	if (ptr == NULL)
-		return ERR_PTR(-ENOMEM);
-	return ptr;
-}
-
-static
-void nfs_readdir_release_array(struct page *page)
-{
-	kunmap(page);
-}
-
-/*
  * we are freeing strings created by nfs_add_to_readdir_array()
  */
 static
@@ -201,18 +179,9 @@ void nfs_readdir_clear_array(struct page *page)
 	int i;
 
 	array = kmap_atomic(page);
-	if (atomic_dec_and_test(&array->refcount))
-		for (i = 0; i < array->size; i++)
-			kfree(array->array[i].string.name);
-	kunmap_atomic(array);
-}
-
-static bool grab_page(struct page *page)
-{
-	struct nfs_cache_array *array = kmap_atomic(page);
-	bool res = atomic_inc_not_zero(&array->refcount);
+	for (i = 0; i < array->size; i++)
+		kfree(array->array[i].string.name);
 	kunmap_atomic(array);
-	return res;
 }
 
 /*
@@ -239,13 +208,10 @@ int nfs_readdir_make_qstr(struct qstr *string, const char *name, unsigned int le
 static
 int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
 {
-	struct nfs_cache_array *array = nfs_readdir_get_array(page);
+	struct nfs_cache_array *array = kmap(page);
 	struct nfs_cache_array_entry *cache_entry;
 	int ret;
 
-	if (IS_ERR(array))
-		return PTR_ERR(array);
-
 	cache_entry = &array->array[array->size];
 
 	/* Check that this entry lies within the page bounds */
@@ -264,7 +230,7 @@ int nfs_readdir_add_to_array(struct nfs_entry *entry, struct page *page)
 	if (entry->eof != 0)
 		array->eof_index = array->size;
 out:
-	nfs_readdir_release_array(page);
+	kunmap(page);
 	return ret;
 }
 
@@ -353,11 +319,7 @@ int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc)
 	struct nfs_cache_array *array;
 	int status;
 
-	array = nfs_readdir_get_array(desc->page);
-	if (IS_ERR(array)) {
-		status = PTR_ERR(array);
-		goto out;
-	}
+	array = kmap(desc->page);
 
 	if (*desc->dir_cookie == 0)
 		status = nfs_readdir_search_for_pos(array, desc);
@@ -369,8 +331,7 @@ int nfs_readdir_search_array(nfs_readdir_descriptor_t *desc)
 		desc->current_index += array->size;
 		desc->page_index++;
 	}
-	nfs_readdir_release_array(desc->page);
-out:
+	kunmap(desc->page);
 	return status;
 }
 
@@ -394,7 +355,7 @@ int nfs_readdir_xdr_filler(struct page **pages, nfs_readdir_descriptor_t *desc,
 		if (error == -ENOTSUPP && desc->plus) {
 			NFS_SERVER(inode)->caps &= ~NFS_CAP_READDIRPLUS;
 			clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
-			desc->plus = 0;
+			desc->plus = false;
 			goto again;
 		}
 		goto error;
@@ -596,7 +557,7 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 
 		count++;
 
-		if (desc->plus != 0)
+		if (desc->plus)
 			nfs_prime_dcache(file_dentry(desc->file), entry);
 
 		status = nfs_readdir_add_to_array(entry, page);
@@ -606,13 +567,10 @@ int nfs_readdir_page_filler(nfs_readdir_descriptor_t *desc, struct nfs_entry *en
 
 out_nopages:
 	if (count == 0 || (status == -EBADCOOKIE && entry->eof != 0)) {
-		array = nfs_readdir_get_array(page);
-		if (!IS_ERR(array)) {
-			array->eof_index = array->size;
-			status = 0;
-			nfs_readdir_release_array(page);
-		} else
-			status = PTR_ERR(array);
+		array = kmap(page);
+		array->eof_index = array->size;
+		status = 0;
+		kunmap(page);
 	}
 
 	put_page(scratch);
@@ -674,13 +632,8 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
 		goto out;
 	}
 
-	array = nfs_readdir_get_array(page);
-	if (IS_ERR(array)) {
-		status = PTR_ERR(array);
-		goto out_label_free;
-	}
+	array = kmap(page);
 	memset(array, 0, sizeof(struct nfs_cache_array));
-	atomic_set(&array->refcount, 1);
 	array->eof_index = -1;
 
 	status = nfs_readdir_alloc_pages(pages, array_size);
@@ -703,8 +656,7 @@ int nfs_readdir_xdr_to_array(nfs_readdir_descriptor_t *desc, struct page *page,
 
 	nfs_readdir_free_pages(pages, array_size);
 out_release_array:
-	nfs_readdir_release_array(page);
-out_label_free:
+	kunmap(page);
 	nfs4_label_free(entry.label);
 out:
 	nfs_free_fattr(entry.fattr);
@@ -743,7 +695,8 @@ int nfs_readdir_filler(nfs_readdir_descriptor_t *desc, struct page* page)
 static
 void cache_page_release(nfs_readdir_descriptor_t *desc)
 {
-	nfs_readdir_clear_array(desc->page);
+	if (!desc->page->mapping)
+		nfs_readdir_clear_array(desc->page);
 	put_page(desc->page);
 	desc->page = NULL;
 }
@@ -751,16 +704,8 @@ void cache_page_release(nfs_readdir_descriptor_t *desc)
 static
 struct page *get_cache_page(nfs_readdir_descriptor_t *desc)
 {
-	struct page *page;
-
-	for (;;) {
-		page = read_cache_page(desc->file->f_mapping,
+	return read_cache_page(desc->file->f_mapping,
 			desc->page_index, (filler_t *)nfs_readdir_filler, desc);
-		if (IS_ERR(page) || grab_page(page))
-			break;
-		put_page(page);
-	}
-	return page;
 }
 
 /*
@@ -809,12 +754,7 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc)
 	struct nfs_cache_array *array = NULL;
 	struct nfs_open_dir_context *ctx = file->private_data;
 
-	array = nfs_readdir_get_array(desc->page);
-	if (IS_ERR(array)) {
-		res = PTR_ERR(array);
-		goto out;
-	}
-
+	array = kmap(desc->page);
 	for (i = desc->cache_entry_index; i < array->size; i++) {
 		struct nfs_cache_array_entry *ent;
 
@@ -835,8 +775,7 @@ int nfs_do_filldir(nfs_readdir_descriptor_t *desc)
 	if (array->eof_index >= 0)
 		desc->eof = 1;
 
-	nfs_readdir_release_array(desc->page);
-out:
+	kunmap(desc->page);
 	cache_page_release(desc);
 	dfprintk(DIRCACHE, "NFS: nfs_do_filldir() filling ended @ cookie %Lu; returning = %d\n",
 			(unsigned long long)*desc->dir_cookie, res);
@@ -921,7 +860,7 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 	desc->ctx = ctx;
 	desc->dir_cookie = &dir_ctx->dir_cookie;
 	desc->decode = NFS_PROTO(inode)->decode_dirent;
-	desc->plus = nfs_use_readdirplus(inode, ctx) ? 1 : 0;
+	desc->plus = nfs_use_readdirplus(inode, ctx);
 
 	if (ctx->pos == 0 || nfs_attribute_cache_expired(inode))
 		res = nfs_revalidate_mapping(inode, file->f_mapping);
@@ -946,8 +885,8 @@ static int nfs_readdir(struct file *file, struct dir_context *ctx)
 			clear_bit(NFS_INO_ADVISE_RDPLUS, &NFS_I(inode)->flags);
 			nfs_zap_caches(inode);
 			desc->page_index = 0;
-			desc->plus = 0;
-			desc->eof = 0;
+			desc->plus = false;
+			desc->eof = false;
 			continue;
 		}
 		if (res < 0)
@@ -966,11 +905,13 @@ out:
 
 static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
 {
+	struct inode *inode = file_inode(filp);
 	struct nfs_open_dir_context *dir_ctx = filp->private_data;
 
 	dfprintk(FILE, "NFS: llseek dir(%pD2, %lld, %d)\n",
 			filp, offset, whence);
 
+	inode_lock(inode);
 	switch (whence) {
 		case 1:
 			offset += filp->f_pos;
@@ -978,13 +919,16 @@ static loff_t nfs_llseek_dir(struct file *filp, loff_t offset, int whence)
 			if (offset >= 0)
 				break;
 		default:
-			return -EINVAL;
+			offset = -EINVAL;
+			goto out;
 	}
 	if (offset != filp->f_pos) {
 		filp->f_pos = offset;
 		dir_ctx->dir_cookie = 0;
 		dir_ctx->duped = 0;
 	}
+out:
+	inode_unlock(inode);
 	return offset;
 }
 
@@ -1171,11 +1115,13 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 	/* Force a full look up iff the parent directory has changed */
 	if (!nfs_is_exclusive_create(dir, flags) &&
 	    nfs_check_verifier(dir, dentry, flags & LOOKUP_RCU)) {
-
-		if (nfs_lookup_verify_inode(inode, flags)) {
+		error = nfs_lookup_verify_inode(inode, flags);
+		if (error) {
 			if (flags & LOOKUP_RCU)
 				return -ECHILD;
-			goto out_zap_parent;
+			if (error == -ESTALE)
+				goto out_zap_parent;
+			goto out_error;
 		}
 		nfs_advise_use_readdirplus(dir);
 		goto out_valid;
@@ -1200,8 +1146,10 @@ static int nfs_lookup_revalidate(struct dentry *dentry, unsigned int flags)
 	trace_nfs_lookup_revalidate_enter(dir, dentry, flags);
 	error = NFS_PROTO(dir)->lookup(dir, &dentry->d_name, fhandle, fattr, label);
 	trace_nfs_lookup_revalidate_exit(dir, dentry, flags, error);
-	if (error)
+	if (error == -ESTALE || error == -ENOENT)
 		goto out_bad;
+	if (error)
+		goto out_error;
 	if (nfs_compare_fh(NFS_FH(inode), fhandle))
 		goto out_bad;
 	if ((error = nfs_refresh_inode(inode, fattr)) != 0)
@@ -1483,8 +1431,10 @@ static int nfs_finish_open(struct nfs_open_context *ctx,
 	err = finish_open(file, dentry, do_open, opened);
 	if (err)
 		goto out;
-	nfs_file_set_open_context(file, ctx);
-
+	if (S_ISREG(file->f_path.dentry->d_inode->i_mode))
+		nfs_file_set_open_context(file, ctx);
+	else
+		err = -ESTALE;
 out:
 	return err;
 }
@@ -1568,7 +1518,7 @@ int nfs_atomic_open(struct inode *dir, struct dentry *dentry,
 		d_drop(dentry);
 		switch (err) {
 		case -ENOENT:
-			d_add(dentry, NULL);
+			d_splice_alias(NULL, dentry);
 			nfs_set_verifier(dentry, nfs_save_change_attribute(dir));
 			break;
 		case -EISDIR:
@@ -2091,7 +2041,11 @@ int nfs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	}
 
 	error = rpc_wait_for_completion_task(task);
-	if (error == 0)
+	if (error != 0) {
+		((struct nfs_renamedata *)task->tk_calldata)->cancelled = 1;
+		/* Paired with the atomic_dec_and_test() barrier in rpc_do_put_task() */
+		smp_wmb();
+	} else
 		error = task->tk_status;
 	rpc_put_task(task);
 	nfs_mark_for_revalidate(old_inode);
@@ -2103,6 +2057,12 @@ out:
 	if (!error) {
 		if (new_inode != NULL)
 			nfs_drop_nlink(new_inode);
+		/*
+		 * The d_move() should be here instead of in an async RPC completion
+		 * handler because we need the proper locks to move the dentry.  If
+		 * we're interrupted by a signal, the async RPC completion handler
+		 * should mark the directories for revalidation.
+		 */
 		d_move(old_dentry, new_dentry);
 		nfs_set_verifier(new_dentry,
 					nfs_save_change_attribute(new_dir));
@@ -2412,16 +2372,40 @@ void nfs_access_add_cache(struct inode *inode, struct nfs_access_entry *set)
 }
 EXPORT_SYMBOL_GPL(nfs_access_add_cache);
 
+#define NFS_MAY_READ (NFS4_ACCESS_READ)
+#define NFS_MAY_WRITE (NFS4_ACCESS_MODIFY | \
+		NFS4_ACCESS_EXTEND | \
+		NFS4_ACCESS_DELETE)
+#define NFS_FILE_MAY_WRITE (NFS4_ACCESS_MODIFY | \
+		NFS4_ACCESS_EXTEND)
+#define NFS_DIR_MAY_WRITE NFS_MAY_WRITE
+#define NFS_MAY_LOOKUP (NFS4_ACCESS_LOOKUP)
+#define NFS_MAY_EXECUTE (NFS4_ACCESS_EXECUTE)
+static int
+nfs_access_calc_mask(u32 access_result, umode_t umode)
+{
+	int mask = 0;
+
+	if (access_result & NFS_MAY_READ)
+		mask |= MAY_READ;
+	if (S_ISDIR(umode)) {
+		if ((access_result & NFS_DIR_MAY_WRITE) == NFS_DIR_MAY_WRITE)
+			mask |= MAY_WRITE;
+		if ((access_result & NFS_MAY_LOOKUP) == NFS_MAY_LOOKUP)
+			mask |= MAY_EXEC;
+	} else if (S_ISREG(umode)) {
+		if ((access_result & NFS_FILE_MAY_WRITE) == NFS_FILE_MAY_WRITE)
+			mask |= MAY_WRITE;
+		if ((access_result & NFS_MAY_EXECUTE) == NFS_MAY_EXECUTE)
+			mask |= MAY_EXEC;
+	} else if (access_result & NFS_MAY_WRITE)
+			mask |= MAY_WRITE;
+	return mask;
+}
+
 void nfs_access_set_mask(struct nfs_access_entry *entry, u32 access_result)
 {
-	entry->mask = 0;
-	if (access_result & NFS4_ACCESS_READ)
-		entry->mask |= MAY_READ;
-	if (access_result &
-	    (NFS4_ACCESS_MODIFY | NFS4_ACCESS_EXTEND | NFS4_ACCESS_DELETE))
-		entry->mask |= MAY_WRITE;
-	if (access_result & (NFS4_ACCESS_LOOKUP|NFS4_ACCESS_EXECUTE))
-		entry->mask |= MAY_EXEC;
+	entry->mask = access_result;
 }
 EXPORT_SYMBOL_GPL(nfs_access_set_mask);
 
@@ -2429,6 +2413,7 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 {
 	struct nfs_access_entry cache;
 	bool may_block = (mask & MAY_NOT_BLOCK) == 0;
+	int cache_mask;
 	int status;
 
 	trace_nfs_access_enter(inode);
@@ -2444,7 +2429,8 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 		goto out;
 
 	/* Be clever: ask server to check for all possible rights */
-	cache.mask = MAY_EXEC | MAY_WRITE | MAY_READ;
+	cache.mask = NFS_MAY_LOOKUP | NFS_MAY_EXECUTE
+		     | NFS_MAY_WRITE | NFS_MAY_READ;
 	cache.cred = cred;
 	cache.jiffies = jiffies;
 	status = NFS_PROTO(inode)->access(inode, &cache);
@@ -2458,7 +2444,8 @@ static int nfs_do_access(struct inode *inode, struct rpc_cred *cred, int mask)
 	}
 	nfs_access_add_cache(inode, &cache);
 out_cached:
-	if ((mask & ~cache.mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0)
+	cache_mask = nfs_access_calc_mask(cache.mask, inode->i_mode);
+	if ((mask & ~cache_mask & (MAY_READ | MAY_WRITE | MAY_EXEC)) != 0)
 		status = -EACCES;
 out:
 	trace_nfs_access_exit(inode, status);
diff --git a/fs/nfs/direct.c b/fs/nfs/direct.c
index aab32fc3d6a8..6fb9fad2d1e6 100644
--- a/fs/nfs/direct.c
+++ b/fs/nfs/direct.c
@@ -392,16 +392,6 @@ static void nfs_direct_complete(struct nfs_direct_req *dreq)
 	nfs_direct_req_release(dreq);
 }
 
-static void nfs_direct_readpage_release(struct nfs_page *req)
-{
-	dprintk("NFS: direct read done (%s/%llu %d@%lld)\n",
-		req->wb_context->dentry->d_sb->s_id,
-		(unsigned long long)NFS_FILEID(d_inode(req->wb_context->dentry)),
-		req->wb_bytes,
-		(long long)req_offset(req));
-	nfs_release_request(req);
-}
-
 static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 {
 	unsigned long bytes = 0;
@@ -426,7 +416,7 @@ static void nfs_direct_read_completion(struct nfs_pgio_header *hdr)
 			set_page_dirty(page);
 		bytes += req->wb_bytes;
 		nfs_list_remove_request(req);
-		nfs_direct_readpage_release(req);
+		nfs_release_request(req);
 	}
 out_put:
 	if (put_dreq(dreq))
@@ -537,7 +527,7 @@ static ssize_t nfs_direct_read_schedule_iovec(struct nfs_direct_req *dreq,
 
 	if (put_dreq(dreq))
 		nfs_direct_complete(dreq);
-	return 0;
+	return requested_bytes;
 }
 
 /**
@@ -566,7 +556,7 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
 	struct inode *inode = mapping->host;
 	struct nfs_direct_req *dreq;
 	struct nfs_lock_context *l_ctx;
-	ssize_t result = -EINVAL;
+	ssize_t result = -EINVAL, requested;
 	size_t count = iov_iter_count(iter);
 	nfs_add_stats(mapping->host, NFSIOS_DIRECTREADBYTES, count);
 
@@ -600,14 +590,19 @@ ssize_t nfs_file_direct_read(struct kiocb *iocb, struct iov_iter *iter)
 	nfs_start_io_direct(inode);
 
 	NFS_I(inode)->read_io += count;
-	result = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);
+	requested = nfs_direct_read_schedule_iovec(dreq, iter, iocb->ki_pos);
 
 	nfs_end_io_direct(inode);
 
-	if (!result) {
+	if (requested > 0) {
 		result = nfs_direct_wait(dreq);
-		if (result > 0)
+		if (result > 0) {
+			requested -= result;
 			iocb->ki_pos += result;
+		}
+		iov_iter_revert(iter, requested);
+	} else {
+		result = requested;
 	}
 
 out_release:
@@ -695,16 +690,9 @@ static void nfs_direct_commit_complete(struct nfs_commit_data *data)
 	int status = data->task.tk_status;
 
 	nfs_init_cinfo_from_dreq(&cinfo, dreq);
-	if (status < 0) {
-		dprintk("NFS: %5u commit failed with error %d.\n",
-			data->task.tk_pid, status);
+	if (status < 0 || nfs_direct_cmp_commit_data_verf(dreq, data))
 		dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
-	} else if (nfs_direct_cmp_commit_data_verf(dreq, data)) {
-		dprintk("NFS: %5u commit verify failed\n", data->task.tk_pid);
-		dreq->flags = NFS_ODIRECT_RESCHED_WRITES;
-	}
 
-	dprintk("NFS: %5u commit returned %d\n", data->task.tk_pid, status);
 	while (!list_empty(&data->pages)) {
 		req = nfs_list_entry(data->pages.next);
 		nfs_list_remove_request(req);
@@ -954,7 +942,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
 
 	if (put_dreq(dreq))
 		nfs_direct_write_complete(dreq);
-	return 0;
+	return requested_bytes;
 }
 
 /**
@@ -979,7 +967,7 @@ static ssize_t nfs_direct_write_schedule_iovec(struct nfs_direct_req *dreq,
  */
 ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 {
-	ssize_t result = -EINVAL;
+	ssize_t result = -EINVAL, requested;
 	size_t count;
 	struct file *file = iocb->ki_filp;
 	struct address_space *mapping = file->f_mapping;
@@ -1022,7 +1010,7 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 
 	nfs_start_io_direct(inode);
 
-	result = nfs_direct_write_schedule_iovec(dreq, iter, pos);
+	requested = nfs_direct_write_schedule_iovec(dreq, iter, pos);
 
 	if (mapping->nrpages) {
 		invalidate_inode_pages2_range(mapping,
@@ -1031,13 +1019,17 @@ ssize_t nfs_file_direct_write(struct kiocb *iocb, struct iov_iter *iter)
 
 	nfs_end_io_direct(inode);
 
-	if (!result) {
+	if (requested > 0) {
 		result = nfs_direct_wait(dreq);
 		if (result > 0) {
+			requested -= result;
 			iocb->ki_pos = pos + result;
 			/* XXX: should check the generic_write_sync retval */
 			generic_write_sync(iocb, result);
 		}
+		iov_iter_revert(iter, requested);
+	} else {
+		result = requested;
 	}
 out_release:
 	nfs_direct_req_release(dreq);
diff --git a/fs/nfs/export.c b/fs/nfs/export.c
new file mode 100644
index 000000000000..249cb96cc5b5
--- /dev/null
+++ b/fs/nfs/export.c
@@ -0,0 +1,177 @@
+/*
+ * Copyright (c) 2015, Primary Data, Inc. All rights reserved.
+ *
+ * Tao Peng <bergwolf@primarydata.com>
+ */
+#include <linux/dcache.h>
+#include <linux/exportfs.h>
+#include <linux/nfs.h>
+#include <linux/nfs_fs.h>
+
+#include "internal.h"
+#include "nfstrace.h"
+
+#define NFSDBG_FACILITY		NFSDBG_VFS
+
+enum {
+	FILEID_HIGH_OFF = 0,	/* inode fileid high */
+	FILEID_LOW_OFF,		/* inode fileid low */
+	FILE_I_TYPE_OFF,	/* inode type */
+	EMBED_FH_OFF		/* embeded server fh */
+};
+
+
+static struct nfs_fh *nfs_exp_embedfh(__u32 *p)
+{
+	return (struct nfs_fh *)(p + EMBED_FH_OFF);
+}
+
+/*
+ * Let's break subtree checking for now... otherwise we'll have to embed parent fh
+ * but there might not be enough space.
+ */
+static int
+nfs_encode_fh(struct inode *inode, __u32 *p, int *max_len, struct inode *parent)
+{
+	struct nfs_fh *server_fh = NFS_FH(inode);
+	struct nfs_fh *clnt_fh = nfs_exp_embedfh(p);
+	size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size;
+	int len = EMBED_FH_OFF + XDR_QUADLEN(fh_size);
+
+	dprintk("%s: max fh len %d inode %p parent %p",
+		__func__, *max_len, inode, parent);
+
+	if (*max_len < len || IS_AUTOMOUNT(inode)) {
+		dprintk("%s: fh len %d too small, required %d\n",
+			__func__, *max_len, len);
+		*max_len = len;
+		return FILEID_INVALID;
+	}
+	if (IS_AUTOMOUNT(inode)) {
+		*max_len = FILEID_INVALID;
+		goto out;
+	}
+
+	p[FILEID_HIGH_OFF] = NFS_FILEID(inode) >> 32;
+	p[FILEID_LOW_OFF] = NFS_FILEID(inode);
+	p[FILE_I_TYPE_OFF] = inode->i_mode & S_IFMT;
+	p[len - 1] = 0; /* Padding */
+	nfs_copy_fh(clnt_fh, server_fh);
+	*max_len = len;
+out:
+	dprintk("%s: result fh fileid %llu mode %u size %d\n",
+		__func__, NFS_FILEID(inode), inode->i_mode, *max_len);
+	return *max_len;
+}
+
+static struct dentry *
+nfs_fh_to_dentry(struct super_block *sb, struct fid *fid,
+		 int fh_len, int fh_type)
+{
+	struct nfs4_label *label = NULL;
+	struct nfs_fattr *fattr = NULL;
+	struct nfs_fh *server_fh = nfs_exp_embedfh(fid->raw);
+	size_t fh_size = offsetof(struct nfs_fh, data) + server_fh->size;
+	const struct nfs_rpc_ops *rpc_ops;
+	struct dentry *dentry;
+	struct inode *inode;
+	int len = EMBED_FH_OFF + XDR_QUADLEN(fh_size);
+	u32 *p = fid->raw;
+	int ret;
+
+	/* NULL translates to ESTALE */
+	if (fh_len < len || fh_type != len)
+		return NULL;
+
+	fattr = nfs_alloc_fattr();
+	if (fattr == NULL) {
+		dentry = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	fattr->fileid = ((u64)p[FILEID_HIGH_OFF] << 32) + p[FILEID_LOW_OFF];
+	fattr->mode = p[FILE_I_TYPE_OFF];
+	fattr->valid |= NFS_ATTR_FATTR_FILEID | NFS_ATTR_FATTR_TYPE;
+
+	dprintk("%s: fileid %llu mode %d\n", __func__, fattr->fileid, fattr->mode);
+
+	inode = nfs_ilookup(sb, fattr, server_fh);
+	if (inode)
+		goto out_found;
+
+	label = nfs4_label_alloc(NFS_SB(sb), GFP_KERNEL);
+	if (IS_ERR(label)) {
+		dentry = ERR_CAST(label);
+		goto out_free_fattr;
+	}
+
+	rpc_ops = NFS_SB(sb)->nfs_client->rpc_ops;
+	ret = rpc_ops->getattr(NFS_SB(sb), server_fh, fattr, label);
+	if (ret) {
+		dprintk("%s: getattr failed %d\n", __func__, ret);
+		dentry = ERR_PTR(ret);
+		goto out_free_label;
+	}
+
+	inode = nfs_fhget(sb, server_fh, fattr, label);
+
+out_found:
+	dentry = d_obtain_alias(inode);
+
+out_free_label:
+	nfs4_label_free(label);
+out_free_fattr:
+	nfs_free_fattr(fattr);
+out:
+	return dentry;
+}
+
+static struct dentry *
+nfs_get_parent(struct dentry *dentry)
+{
+	int ret;
+	struct inode *inode = d_inode(dentry), *pinode;
+	struct super_block *sb = inode->i_sb;
+	struct nfs_server *server = NFS_SB(sb);
+	struct nfs_fattr *fattr = NULL;
+	struct nfs4_label *label = NULL;
+	struct dentry *parent;
+	struct nfs_rpc_ops const *ops = server->nfs_client->rpc_ops;
+	struct nfs_fh fh;
+
+	if (!ops->lookupp)
+		return ERR_PTR(-EACCES);
+
+	fattr = nfs_alloc_fattr();
+	if (fattr == NULL) {
+		parent = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	label = nfs4_label_alloc(server, GFP_KERNEL);
+	if (IS_ERR(label)) {
+		parent = ERR_CAST(label);
+		goto out_free_fattr;
+	}
+
+	ret = ops->lookupp(inode, &fh, fattr, label);
+	if (ret) {
+		parent = ERR_PTR(ret);
+		goto out_free_label;
+	}
+
+	pinode = nfs_fhget(sb, &fh, fattr, label);
+	parent = d_obtain_alias(pinode);
+out_free_label:
+	nfs4_label_free(label);
+out_free_fattr:
+	nfs_free_fattr(fattr);
+out:
+	return parent;
+}
+
+const struct export_operations nfs_export_ops = {
+	.encode_fh = nfs_encode_fh,
+	.fh_to_dentry = nfs_fh_to_dentry,
+	.get_parent = nfs_get_parent,
+};
diff --git a/fs/nfs/file.c b/fs/nfs/file.c
index 26dbe8b0c10d..5713eb32a45e 100644
--- a/fs/nfs/file.c
+++ b/fs/nfs/file.c
@@ -482,7 +482,7 @@ static int nfs_launder_page(struct page *page)
 		inode->i_ino, (long long)page_offset(page));
 
 	nfs_fscache_wait_on_page_write(nfsi, page);
-	return nfs_wb_launder_page(inode, page);
+	return nfs_wb_page(inode, page);
 }
 
 static int nfs_swap_activate(struct swap_info_struct *sis, struct file *file,
@@ -528,10 +528,10 @@ const struct address_space_operations nfs_file_aops = {
  * writable, implying that someone is about to modify the page through a
  * shared-writable mapping
  */
-static int nfs_vm_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int nfs_vm_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
-	struct file *filp = vma->vm_file;
+	struct file *filp = vmf->vma->vm_file;
 	struct inode *inode = file_inode(filp);
 	unsigned pagelen;
 	int ret = VM_FAULT_NOPAGE;
@@ -697,14 +697,14 @@ do_unlk(struct file *filp, int cmd, struct file_lock *fl, int is_local)
 	if (!IS_ERR(l_ctx)) {
 		status = nfs_iocounter_wait(l_ctx);
 		nfs_put_lock_context(l_ctx);
-		if (status < 0)
+		/*  NOTE: special case
+		 * 	If we're signalled while cleaning up locks on process exit, we
+		 * 	still need to complete the unlock.
+		 */
+		if (status < 0 && !(fl->fl_flags & FL_CLOSE))
 			return status;
 	}
 
-	/* NOTE: special case
-	 * 	If we're signalled while cleaning up locks on process exit, we
-	 * 	still need to complete the unlock.
-	 */
 	/*
 	 * Use local locking if mounted with "-onolock" or with appropriate
 	 * "-olocal_lock="
@@ -820,9 +820,23 @@ int nfs_flock(struct file *filp, int cmd, struct file_lock *fl)
 	if (NFS_SERVER(inode)->flags & NFS_MOUNT_LOCAL_FLOCK)
 		is_local = 1;
 
-	/* We're simulating flock() locks using posix locks on the server */
-	if (fl->fl_type == F_UNLCK)
+	/*
+	 * VFS doesn't require the open mode to match a flock() lock's type.
+	 * NFS, however, may simulate flock() locking with posix locking which
+	 * requires the open mode to match the lock type.
+	 */
+	switch (fl->fl_type) {
+	case F_UNLCK:
 		return do_unlk(filp, cmd, fl, is_local);
+	case F_RDLCK:
+		if (!(filp->f_mode & FMODE_READ))
+			return -EBADF;
+		break;
+	case F_WRLCK:
+		if (!(filp->f_mode & FMODE_WRITE))
+			return -EBADF;
+	}
+
 	return do_setlk(filp, cmd, fl, is_local);
 }
 EXPORT_SYMBOL_GPL(nfs_flock);
diff --git a/fs/nfs/filelayout/filelayout.c b/fs/nfs/filelayout/filelayout.c
index a3fc48ba4931..44c638b7876c 100644
--- a/fs/nfs/filelayout/filelayout.c
+++ b/fs/nfs/filelayout/filelayout.c
@@ -126,32 +126,13 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 {
 	struct pnfs_layout_hdr *lo = lseg->pls_layout;
 	struct inode *inode = lo->plh_inode;
-	struct nfs_server *mds_server = NFS_SERVER(inode);
 	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
-	struct nfs_client *mds_client = mds_server->nfs_client;
 	struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table;
 
 	if (task->tk_status >= 0)
 		return 0;
 
 	switch (task->tk_status) {
-	/* MDS state errors */
-	case -NFS4ERR_DELEG_REVOKED:
-	case -NFS4ERR_ADMIN_REVOKED:
-	case -NFS4ERR_BAD_STATEID:
-	case -NFS4ERR_OPENMODE:
-		if (state == NULL)
-			break;
-		if (nfs4_schedule_stateid_recovery(mds_server, state) < 0)
-			goto out_bad_stateid;
-		goto wait_on_recovery;
-	case -NFS4ERR_EXPIRED:
-		if (state != NULL) {
-			if (nfs4_schedule_stateid_recovery(mds_server, state) < 0)
-				goto out_bad_stateid;
-		}
-		nfs4_schedule_lease_recovery(mds_client);
-		goto wait_on_recovery;
 	/* DS session errors */
 	case -NFS4ERR_BADSESSION:
 	case -NFS4ERR_BADSLOT:
@@ -172,6 +153,7 @@ static int filelayout_async_handle_error(struct rpc_task *task,
 	case -NFS4ERR_RETRY_UNCACHED_REP:
 		break;
 	/* Invalidate Layout errors */
+	case -NFS4ERR_ACCESS:
 	case -NFS4ERR_PNFS_NO_LAYOUT:
 	case -ESTALE:           /* mapped NFS4ERR_STALE */
 	case -EBADHANDLE:       /* mapped NFS4ERR_BADHANDLE */
@@ -211,17 +193,8 @@ reset:
 			task->tk_status);
 		return -NFS4ERR_RESET_TO_MDS;
 	}
-out:
 	task->tk_status = 0;
 	return -EAGAIN;
-out_bad_stateid:
-	task->tk_status = -EIO;
-	return 0;
-wait_on_recovery:
-	rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL);
-	if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0)
-		rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task);
-	goto out;
 }
 
 /* NFS_PROTO call done callback routines */
@@ -305,7 +278,7 @@ static void filelayout_read_prepare(struct rpc_task *task, void *data)
 	}
 	hdr->pgio_done_cb = filelayout_read_done_cb;
 
-	if (nfs41_setup_sequence(hdr->ds_clp->cl_session,
+	if (nfs4_setup_sequence(hdr->ds_clp,
 			&hdr->args.seq_args,
 			&hdr->res.seq_res,
 			task))
@@ -403,7 +376,7 @@ static void filelayout_write_prepare(struct rpc_task *task, void *data)
 		rpc_exit(task, 0);
 		return;
 	}
-	if (nfs41_setup_sequence(hdr->ds_clp->cl_session,
+	if (nfs4_setup_sequence(hdr->ds_clp,
 			&hdr->args.seq_args,
 			&hdr->res.seq_res,
 			task))
@@ -438,7 +411,7 @@ static void filelayout_commit_prepare(struct rpc_task *task, void *data)
 {
 	struct nfs_commit_data *wdata = data;
 
-	nfs41_setup_sequence(wdata->ds_clp->cl_session,
+	nfs4_setup_sequence(wdata->ds_clp,
 			&wdata->args.seq_args,
 			&wdata->res.seq_res,
 			task);
@@ -482,7 +455,7 @@ filelayout_read_pagelist(struct nfs_pgio_header *hdr)
 	u32 j, idx;
 	struct nfs_fh *fh;
 
-	dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n",
+	dprintk("--> %s ino %lu pgbase %u req %zu@%llu\n",
 		__func__, hdr->inode->i_ino,
 		hdr->args.pgbase, (size_t)hdr->args.count, offset);
 
@@ -540,7 +513,7 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	if (IS_ERR(ds_clnt))
 		return PNFS_NOT_ATTEMPTED;
 
-	dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d\n",
+	dprintk("%s ino %lu sync %d req %zu@%llu DS: %s cl_count %d\n",
 		__func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count,
 		offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count));
 
@@ -560,6 +533,59 @@ filelayout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 	return PNFS_ATTEMPTED;
 }
 
+static int
+filelayout_check_deviceid(struct pnfs_layout_hdr *lo,
+			  struct nfs4_filelayout_segment *fl,
+			  gfp_t gfp_flags)
+{
+	struct nfs4_deviceid_node *d;
+	struct nfs4_file_layout_dsaddr *dsaddr;
+	int status = -EINVAL;
+
+	/* Is the deviceid already set? If so, we're good. */
+	if (fl->dsaddr != NULL)
+		return 0;
+
+	/* find and reference the deviceid */
+	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), &fl->deviceid,
+			lo->plh_lc_cred, gfp_flags);
+	if (d == NULL)
+		goto out;
+
+	dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
+	/* Found deviceid is unavailable */
+	if (filelayout_test_devid_unavailable(&dsaddr->id_node))
+		goto out_put;
+
+	if (fl->first_stripe_index >= dsaddr->stripe_count) {
+		dprintk("%s Bad first_stripe_index %u\n",
+				__func__, fl->first_stripe_index);
+		goto out_put;
+	}
+
+	if ((fl->stripe_type == STRIPE_SPARSE &&
+	    fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) ||
+	    (fl->stripe_type == STRIPE_DENSE &&
+	    fl->num_fh != dsaddr->stripe_count)) {
+		dprintk("%s num_fh %u not valid for given packing\n",
+			__func__, fl->num_fh);
+		goto out_put;
+	}
+	status = 0;
+
+	/*
+	 * Atomic compare and xchange to ensure we don't scribble
+	 * over a non-NULL pointer.
+	 */
+	if (cmpxchg(&fl->dsaddr, NULL, dsaddr) != NULL)
+		goto out_put;
+out:
+	return status;
+out_put:
+	nfs4_fl_put_deviceid(dsaddr);
+	goto out;
+}
+
 /*
  * filelayout_check_layout()
  *
@@ -572,11 +598,8 @@ static int
 filelayout_check_layout(struct pnfs_layout_hdr *lo,
 			struct nfs4_filelayout_segment *fl,
 			struct nfs4_layoutget_res *lgr,
-			struct nfs4_deviceid *id,
 			gfp_t gfp_flags)
 {
-	struct nfs4_deviceid_node *d;
-	struct nfs4_file_layout_dsaddr *dsaddr;
 	int status = -EINVAL;
 
 	dprintk("--> %s\n", __func__);
@@ -601,41 +624,10 @@ filelayout_check_layout(struct pnfs_layout_hdr *lo,
 		goto out;
 	}
 
-	/* find and reference the deviceid */
-	d = nfs4_find_get_deviceid(NFS_SERVER(lo->plh_inode), id,
-			lo->plh_lc_cred, gfp_flags);
-	if (d == NULL)
-		goto out;
-
-	dsaddr = container_of(d, struct nfs4_file_layout_dsaddr, id_node);
-	/* Found deviceid is unavailable */
-	if (filelayout_test_devid_unavailable(&dsaddr->id_node))
-		goto out_put;
-
-	fl->dsaddr = dsaddr;
-
-	if (fl->first_stripe_index >= dsaddr->stripe_count) {
-		dprintk("%s Bad first_stripe_index %u\n",
-				__func__, fl->first_stripe_index);
-		goto out_put;
-	}
-
-	if ((fl->stripe_type == STRIPE_SPARSE &&
-	    fl->num_fh > 1 && fl->num_fh != dsaddr->ds_num) ||
-	    (fl->stripe_type == STRIPE_DENSE &&
-	    fl->num_fh != dsaddr->stripe_count)) {
-		dprintk("%s num_fh %u not valid for given packing\n",
-			__func__, fl->num_fh);
-		goto out_put;
-	}
-
 	status = 0;
 out:
 	dprintk("--> %s returns %d\n", __func__, status);
 	return status;
-out_put:
-	nfs4_fl_put_deviceid(dsaddr);
-	goto out;
 }
 
 static void _filelayout_free_lseg(struct nfs4_filelayout_segment *fl)
@@ -657,7 +649,6 @@ static int
 filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 			 struct nfs4_filelayout_segment *fl,
 			 struct nfs4_layoutget_res *lgr,
-			 struct nfs4_deviceid *id,
 			 gfp_t gfp_flags)
 {
 	struct xdr_stream stream;
@@ -682,9 +673,9 @@ filelayout_decode_layout(struct pnfs_layout_hdr *flo,
 	if (unlikely(!p))
 		goto out_err;
 
-	memcpy(id, p, sizeof(*id));
+	memcpy(&fl->deviceid, p, sizeof(fl->deviceid));
 	p += XDR_QUADLEN(NFS4_DEVICEID4_SIZE);
-	nfs4_print_deviceid(id);
+	nfs4_print_deviceid(&fl->deviceid);
 
 	nfl_util = be32_to_cpup(p++);
 	if (nfl_util & NFL4_UFLG_COMMIT_THRU_MDS)
@@ -831,15 +822,14 @@ filelayout_alloc_lseg(struct pnfs_layout_hdr *layoutid,
 {
 	struct nfs4_filelayout_segment *fl;
 	int rc;
-	struct nfs4_deviceid id;
 
 	dprintk("--> %s\n", __func__);
 	fl = kzalloc(sizeof(*fl), gfp_flags);
 	if (!fl)
 		return NULL;
 
-	rc = filelayout_decode_layout(layoutid, fl, lgr, &id, gfp_flags);
-	if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, &id, gfp_flags)) {
+	rc = filelayout_decode_layout(layoutid, fl, lgr, gfp_flags);
+	if (rc != 0 || filelayout_check_layout(layoutid, fl, lgr, gfp_flags)) {
 		_filelayout_free_lseg(fl);
 		return NULL;
 	}
@@ -888,18 +878,52 @@ filelayout_pg_test(struct nfs_pageio_descriptor *pgio, struct nfs_page *prev,
 	return min(stripe_unit - (unsigned int)stripe_offset, size);
 }
 
+static struct pnfs_layout_segment *
+fl_pnfs_update_layout(struct inode *ino,
+		      struct nfs_open_context *ctx,
+		      loff_t pos,
+		      u64 count,
+		      enum pnfs_iomode iomode,
+		      bool strict_iomode,
+		      gfp_t gfp_flags)
+{
+	struct pnfs_layout_segment *lseg = NULL;
+	struct pnfs_layout_hdr *lo;
+	struct nfs4_filelayout_segment *fl;
+	int status;
+
+	lseg = pnfs_update_layout(ino, ctx, pos, count, iomode, strict_iomode,
+				  gfp_flags);
+	if (!lseg)
+		lseg = ERR_PTR(-ENOMEM);
+	if (IS_ERR(lseg))
+		goto out;
+
+	lo = NFS_I(ino)->layout;
+	fl = FILELAYOUT_LSEG(lseg);
+
+	status = filelayout_check_deviceid(lo, fl, gfp_flags);
+	if (status) {
+		pnfs_put_lseg(lseg);
+		lseg = ERR_PTR(status);
+	}
+out:
+	return lseg;
+}
+
 static void
 filelayout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 			struct nfs_page *req)
 {
+	pnfs_generic_pg_check_layout(pgio);
 	if (!pgio->pg_lseg) {
-		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
-					   req->wb_context,
-					   0,
-					   NFS4_MAX_UINT64,
-					   IOMODE_READ,
-					   false,
-					   GFP_KERNEL);
+		pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
+						      req->wb_context,
+						      0,
+						      NFS4_MAX_UINT64,
+						      IOMODE_READ,
+						      false,
+						      GFP_KERNEL);
 		if (IS_ERR(pgio->pg_lseg)) {
 			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
 			pgio->pg_lseg = NULL;
@@ -918,14 +942,15 @@ filelayout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	struct nfs_commit_info cinfo;
 	int status;
 
+	pnfs_generic_pg_check_layout(pgio);
 	if (!pgio->pg_lseg) {
-		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
-					   req->wb_context,
-					   0,
-					   NFS4_MAX_UINT64,
-					   IOMODE_RW,
-					   false,
-					   GFP_NOFS);
+		pgio->pg_lseg = fl_pnfs_update_layout(pgio->pg_inode,
+						      req->wb_context,
+						      0,
+						      NFS4_MAX_UINT64,
+						      IOMODE_RW,
+						      false,
+						      GFP_NOFS);
 		if (IS_ERR(pgio->pg_lseg)) {
 			pgio->pg_error = PTR_ERR(pgio->pg_lseg);
 			pgio->pg_lseg = NULL;
diff --git a/fs/nfs/filelayout/filelayout.h b/fs/nfs/filelayout/filelayout.h
index 2896cb833a11..79323b5dab0c 100644
--- a/fs/nfs/filelayout/filelayout.h
+++ b/fs/nfs/filelayout/filelayout.h
@@ -55,15 +55,16 @@ struct nfs4_file_layout_dsaddr {
 };
 
 struct nfs4_filelayout_segment {
-	struct pnfs_layout_segment generic_hdr;
-	u32 stripe_type;
-	u32 commit_through_mds;
-	u32 stripe_unit;
-	u32 first_stripe_index;
-	u64 pattern_offset;
-	struct nfs4_file_layout_dsaddr *dsaddr; /* Point to GETDEVINFO data */
-	unsigned int num_fh;
-	struct nfs_fh **fh_array;
+	struct pnfs_layout_segment	generic_hdr;
+	u32				stripe_type;
+	u32				commit_through_mds;
+	u32				stripe_unit;
+	u32				first_stripe_index;
+	u64				pattern_offset;
+	struct nfs4_deviceid		deviceid;
+	struct nfs4_file_layout_dsaddr	*dsaddr; /* Point to GETDEVINFO data */
+	unsigned int			num_fh;
+	struct nfs_fh			**fh_array;
 };
 
 struct nfs4_filelayout {
diff --git a/fs/nfs/filelayout/filelayoutdev.c b/fs/nfs/filelayout/filelayoutdev.c
index f956ca20a8a3..d913e818858f 100644
--- a/fs/nfs/filelayout/filelayoutdev.c
+++ b/fs/nfs/filelayout/filelayoutdev.c
@@ -266,6 +266,7 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	struct nfs4_deviceid_node *devid = FILELAYOUT_DEVID_NODE(lseg);
 	struct nfs4_pnfs_ds *ret = ds;
 	struct nfs_server *s = NFS_SERVER(lseg->pls_layout->plh_inode);
+	int status;
 
 	if (ds == NULL) {
 		printk(KERN_ERR "NFS: %s: No data server for offset index %d\n",
@@ -277,9 +278,14 @@ nfs4_fl_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx)
 	if (ds->ds_clp)
 		goto out_test_devid;
 
-	nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
+	status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
 			     dataserver_retrans, 4,
 			     s->nfs_client->cl_minorversion);
+	if (status) {
+		nfs4_mark_deviceid_unavailable(devid);
+		ret = NULL;
+		goto out;
+	}
 
 out_test_devid:
 	if (ret->ds_clp == NULL ||
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.c b/fs/nfs/flexfilelayout/flexfilelayout.c
index 0ca4af8cca5d..b0fa83a60754 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.c
+++ b/fs/nfs/flexfilelayout/flexfilelayout.c
@@ -454,6 +454,7 @@ ff_layout_alloc_lseg(struct pnfs_layout_hdr *lh,
 			goto out_err_free;
 
 		/* fh */
+		rc = -EIO;
 		p = xdr_inline_decode(&stream, 4);
 		if (!p)
 			goto out_err_free;
@@ -846,6 +847,7 @@ ff_layout_pg_init_read(struct nfs_pageio_descriptor *pgio,
 	int ds_idx;
 
 retry:
+	pnfs_generic_pg_check_layout(pgio);
 	/* Use full layout for now */
 	if (!pgio->pg_lseg)
 		ff_layout_pg_get_read(pgio, req, false);
@@ -894,6 +896,7 @@ ff_layout_pg_init_write(struct nfs_pageio_descriptor *pgio,
 	int status;
 
 retry:
+	pnfs_generic_pg_check_layout(pgio);
 	if (!pgio->pg_lseg) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   req->wb_context,
@@ -1047,37 +1050,10 @@ static int ff_layout_async_handle_error_v4(struct rpc_task *task,
 {
 	struct pnfs_layout_hdr *lo = lseg->pls_layout;
 	struct inode *inode = lo->plh_inode;
-	struct nfs_server *mds_server = NFS_SERVER(inode);
-
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
-	struct nfs_client *mds_client = mds_server->nfs_client;
 	struct nfs4_slot_table *tbl = &clp->cl_session->fc_slot_table;
 
-	if (task->tk_status >= 0)
-		return 0;
-
 	switch (task->tk_status) {
-	/* MDS state errors */
-	case -NFS4ERR_DELEG_REVOKED:
-	case -NFS4ERR_ADMIN_REVOKED:
-	case -NFS4ERR_BAD_STATEID:
-		if (state == NULL)
-			break;
-		nfs_remove_bad_delegation(state->inode, NULL);
-	case -NFS4ERR_OPENMODE:
-		if (state == NULL)
-			break;
-		if (nfs4_schedule_stateid_recovery(mds_server, state) < 0)
-			goto out_bad_stateid;
-		goto wait_on_recovery;
-	case -NFS4ERR_EXPIRED:
-		if (state != NULL) {
-			if (nfs4_schedule_stateid_recovery(mds_server, state) < 0)
-				goto out_bad_stateid;
-		}
-		nfs4_schedule_lease_recovery(mds_client);
-		goto wait_on_recovery;
-	/* DS session errors */
 	case -NFS4ERR_BADSESSION:
 	case -NFS4ERR_BADSLOT:
 	case -NFS4ERR_BAD_HIGH_SLOT:
@@ -1137,17 +1113,8 @@ reset:
 			task->tk_status);
 		return -NFS4ERR_RESET_TO_MDS;
 	}
-out:
 	task->tk_status = 0;
 	return -EAGAIN;
-out_bad_stateid:
-	task->tk_status = -EIO;
-	return 0;
-wait_on_recovery:
-	rpc_sleep_on(&mds_client->cl_rpcwaitq, task, NULL);
-	if (test_bit(NFS4CLNT_MANAGER_RUNNING, &mds_client->cl_state) == 0)
-		rpc_wake_up_queued_task(&mds_client->cl_rpcwaitq, task);
-	goto out;
 }
 
 /* Retry all errors through either pNFS or MDS except for -EJUKEBOX */
@@ -1157,9 +1124,6 @@ static int ff_layout_async_handle_error_v3(struct rpc_task *task,
 {
 	struct nfs4_deviceid_node *devid = FF_LAYOUT_DEVID_NODE(lseg, idx);
 
-	if (task->tk_status >= 0)
-		return 0;
-
 	switch (task->tk_status) {
 	/* File access problems. Don't mark the device as unavailable */
 	case -EACCES:
@@ -1195,6 +1159,13 @@ static int ff_layout_async_handle_error(struct rpc_task *task,
 {
 	int vers = clp->cl_nfs_mod->rpc_vers->number;
 
+	if (task->tk_status >= 0)
+		return 0;
+
+	/* Handle the case of an invalid layout segment */
+	if (!pnfs_is_valid_lseg(lseg))
+		return -NFS4ERR_RESET_TO_PNFS;
+
 	switch (vers) {
 	case 3:
 		return ff_layout_async_handle_error_v3(task, lseg, idx);
@@ -1384,30 +1355,14 @@ static void ff_layout_read_prepare_v3(struct rpc_task *task, void *data)
 	rpc_call_start(task);
 }
 
-static int ff_layout_setup_sequence(struct nfs_client *ds_clp,
-				    struct nfs4_sequence_args *args,
-				    struct nfs4_sequence_res *res,
-				    struct rpc_task *task)
-{
-	if (ds_clp->cl_session)
-		return nfs41_setup_sequence(ds_clp->cl_session,
-					   args,
-					   res,
-					   task);
-	return nfs40_setup_sequence(ds_clp->cl_slot_tbl,
-				   args,
-				   res,
-				   task);
-}
-
 static void ff_layout_read_prepare_v4(struct rpc_task *task, void *data)
 {
 	struct nfs_pgio_header *hdr = data;
 
-	if (ff_layout_setup_sequence(hdr->ds_clp,
-				     &hdr->args.seq_args,
-				     &hdr->res.seq_res,
-				     task))
+	if (nfs4_setup_sequence(hdr->ds_clp,
+				&hdr->args.seq_args,
+				&hdr->res.seq_res,
+				task))
 		return;
 
 	if (ff_layout_read_prepare_common(task, hdr))
@@ -1578,10 +1533,10 @@ static void ff_layout_write_prepare_v4(struct rpc_task *task, void *data)
 {
 	struct nfs_pgio_header *hdr = data;
 
-	if (ff_layout_setup_sequence(hdr->ds_clp,
-				     &hdr->args.seq_args,
-				     &hdr->res.seq_res,
-				     task))
+	if (nfs4_setup_sequence(hdr->ds_clp,
+				&hdr->args.seq_args,
+				&hdr->res.seq_res,
+				task))
 		return;
 
 	if (ff_layout_write_prepare_common(task, hdr))
@@ -1667,10 +1622,10 @@ static void ff_layout_commit_prepare_v4(struct rpc_task *task, void *data)
 {
 	struct nfs_commit_data *wdata = data;
 
-	if (ff_layout_setup_sequence(wdata->ds_clp,
-				 &wdata->args.seq_args,
-				 &wdata->res.seq_res,
-				 task))
+	if (nfs4_setup_sequence(wdata->ds_clp,
+				&wdata->args.seq_args,
+				&wdata->res.seq_res,
+				task))
 		return;
 	ff_layout_commit_prepare_common(task, data);
 }
@@ -1751,7 +1706,7 @@ ff_layout_read_pagelist(struct nfs_pgio_header *hdr)
 	int vers;
 	struct nfs_fh *fh;
 
-	dprintk("--> %s ino %lu pgbase %u req %Zu@%llu\n",
+	dprintk("--> %s ino %lu pgbase %u req %zu@%llu\n",
 		__func__, hdr->inode->i_ino,
 		hdr->args.pgbase, (size_t)hdr->args.count, offset);
 
@@ -1815,20 +1770,20 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 
 	ds = nfs4_ff_layout_prepare_ds(lseg, idx, true);
 	if (!ds)
-		return PNFS_NOT_ATTEMPTED;
+		goto out_failed;
 
 	ds_clnt = nfs4_ff_find_or_create_ds_client(lseg, idx, ds->ds_clp,
 						   hdr->inode);
 	if (IS_ERR(ds_clnt))
-		return PNFS_NOT_ATTEMPTED;
+		goto out_failed;
 
 	ds_cred = ff_layout_get_ds_cred(lseg, idx, hdr->cred);
 	if (!ds_cred)
-		return PNFS_NOT_ATTEMPTED;
+		goto out_failed;
 
 	vers = nfs4_ff_layout_ds_version(lseg, idx);
 
-	dprintk("%s ino %lu sync %d req %Zu@%llu DS: %s cl_count %d vers %d\n",
+	dprintk("%s ino %lu sync %d req %zu@%llu DS: %s cl_count %d vers %d\n",
 		__func__, hdr->inode->i_ino, sync, (size_t) hdr->args.count,
 		offset, ds->ds_remotestr, atomic_read(&ds->ds_clp->cl_count),
 		vers);
@@ -1854,6 +1809,11 @@ ff_layout_write_pagelist(struct nfs_pgio_header *hdr, int sync)
 			  sync, RPC_TASK_SOFTCONN);
 	put_rpccred(ds_cred);
 	return PNFS_ATTEMPTED;
+
+out_failed:
+	if (ff_layout_avoid_mds_available_ds(lseg))
+		return PNFS_TRY_AGAIN;
+	return PNFS_NOT_ATTEMPTED;
 }
 
 static u32 calc_ds_index_from_commit(struct pnfs_layout_segment *lseg, u32 i)
@@ -1882,6 +1842,10 @@ static int ff_layout_initiate_commit(struct nfs_commit_data *data, int how)
 	int vers, ret;
 	struct nfs_fh *fh;
 
+	if (!lseg || !(pnfs_is_valid_lseg(lseg) ||
+	    test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags)))
+		goto out_err;
+
 	idx = calc_ds_index_from_commit(lseg, data->ds_commit_index);
 	ds = nfs4_ff_layout_prepare_ds(lseg, idx, true);
 	if (!ds)
@@ -1965,10 +1929,7 @@ static int ff_layout_encode_ioerr(struct xdr_stream *xdr,
 static void
 encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len)
 {
-	__be32 *p;
-
-	p = xdr_reserve_space(xdr, len);
-	xdr_encode_opaque_fixed(p, buf, len);
+	WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
 }
 
 static void
@@ -2092,7 +2053,7 @@ ff_layout_free_layoutreturn(struct nfs4_xdr_opaque_data *args)
 	kfree(ff_args);
 }
 
-const struct nfs4_xdr_opaque_ops layoutreturn_ops = {
+static const struct nfs4_xdr_opaque_ops layoutreturn_ops = {
 	.encode = ff_layout_encode_layoutreturn,
 	.free = ff_layout_free_layoutreturn,
 };
@@ -2372,10 +2333,21 @@ ff_layout_prepare_layoutstats(struct nfs42_layoutstat_args *args)
 	return 0;
 }
 
+static int
+ff_layout_set_layoutdriver(struct nfs_server *server,
+		const struct nfs_fh *dummy)
+{
+#if IS_ENABLED(CONFIG_NFS_V4_2)
+	server->caps |= NFS_CAP_LAYOUTSTATS;
+#endif
+	return 0;
+}
+
 static struct pnfs_layoutdriver_type flexfilelayout_type = {
 	.id			= LAYOUT_FLEX_FILES,
 	.name			= "LAYOUT_FLEX_FILES",
 	.owner			= THIS_MODULE,
+	.set_layoutdriver	= ff_layout_set_layoutdriver,
 	.alloc_layout_hdr	= ff_layout_alloc_layout_hdr,
 	.free_layout_hdr	= ff_layout_free_layout_hdr,
 	.alloc_lseg		= ff_layout_alloc_lseg,
diff --git a/fs/nfs/flexfilelayout/flexfilelayout.h b/fs/nfs/flexfilelayout/flexfilelayout.h
index f4f39b0ab09b..98b34c9b0564 100644
--- a/fs/nfs/flexfilelayout/flexfilelayout.h
+++ b/fs/nfs/flexfilelayout/flexfilelayout.h
@@ -175,7 +175,19 @@ ff_layout_no_read_on_rw(struct pnfs_layout_segment *lseg)
 static inline bool
 ff_layout_test_devid_unavailable(struct nfs4_deviceid_node *node)
 {
-	return nfs4_test_deviceid_unavailable(node);
+	/*
+	 * Flexfiles should never mark a DS unavailable, but if it does
+	 * print a (ratelimited) warning as this can affect performance.
+	 */
+	if (nfs4_test_deviceid_unavailable(node)) {
+		u32 *p = (u32 *)node->deviceid.data;
+
+		pr_warn_ratelimited("NFS: flexfiles layout referencing an "
+				"unavailable device [%x%x%x%x]\n",
+				p[0], p[1], p[2], p[3]);
+		return true;
+	}
+	return false;
 }
 
 static inline int
diff --git a/fs/nfs/flexfilelayout/flexfilelayoutdev.c b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
index e5a6f248697b..6df7a0cf5660 100644
--- a/fs/nfs/flexfilelayout/flexfilelayoutdev.c
+++ b/fs/nfs/flexfilelayout/flexfilelayoutdev.c
@@ -119,7 +119,13 @@ nfs4_ff_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
 		if (ds_versions[i].wsize > NFS_MAX_FILE_IO_SIZE)
 			ds_versions[i].wsize = NFS_MAX_FILE_IO_SIZE;
 
-		if (ds_versions[i].version != 3 || ds_versions[i].minor_version != 0) {
+		/*
+		 * check for valid major/minor combination.
+		 * currently we support dataserver which talk:
+		 *   v3, v4.0, v4.1, v4.2
+		 */
+		if (!((ds_versions[i].version == 3 && ds_versions[i].minor_version == 0) ||
+			(ds_versions[i].version == 4 && ds_versions[i].minor_version < 3))) {
 			dprintk("%s: [%d] unsupported ds version %d-%d\n", __func__,
 				i, ds_versions[i].version,
 				ds_versions[i].minor_version);
@@ -208,6 +214,10 @@ static bool ff_layout_mirror_valid(struct pnfs_layout_segment *lseg,
 		} else
 			goto outerr;
 	}
+
+	if (IS_ERR(mirror->mirror_ds))
+		goto outerr;
+
 	if (mirror->mirror_ds->ds == NULL) {
 		struct nfs4_deviceid_node *devid;
 		devid = &mirror->mirror_ds->id_node;
@@ -384,6 +394,7 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
 	struct inode *ino = lseg->pls_layout->plh_inode;
 	struct nfs_server *s = NFS_SERVER(ino);
 	unsigned int max_payload;
+	int status;
 
 	if (!ff_layout_mirror_valid(lseg, mirror, true)) {
 		pr_err_ratelimited("NFS: %s: No data server for offset index %d\n",
@@ -404,13 +415,13 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
 	/* FIXME: For now we assume the server sent only one version of NFS
 	 * to use for the DS.
 	 */
-	nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
+	status = nfs4_pnfs_ds_connect(s, ds, devid, dataserver_timeo,
 			     dataserver_retrans,
 			     mirror->mirror_ds->ds_versions[0].version,
 			     mirror->mirror_ds->ds_versions[0].minor_version);
 
 	/* connect success, check rsize/wsize limit */
-	if (ds->ds_clp) {
+	if (!status) {
 		max_payload =
 			nfs_block_size(rpc_max_payload(ds->ds_clp->cl_rpcclient),
 				       NULL);
@@ -420,11 +431,11 @@ nfs4_ff_layout_prepare_ds(struct pnfs_layout_segment *lseg, u32 ds_idx,
 			mirror->mirror_ds->ds_versions[0].wsize = max_payload;
 		goto out;
 	}
+out_fail:
 	ff_layout_track_ds_error(FF_LAYOUT_FROM_HDR(lseg->pls_layout),
 				 mirror, lseg->pls_range.offset,
 				 lseg->pls_range.length, NFS4ERR_NXIO,
 				 OP_ILLEGAL, GFP_NOIO);
-out_fail:
 	if (fail_return || !ff_layout_has_available_ds(lseg))
 		pnfs_error_mark_layout_for_return(ino, lseg);
 	ds = NULL;
diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c
index 5ca4d96b1942..109279d6d91b 100644
--- a/fs/nfs/inode.c
+++ b/fs/nfs/inode.c
@@ -15,7 +15,7 @@
 
 #include <linux/module.h>
 #include <linux/init.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/time.h>
 #include <linux/kernel.h>
 #include <linux/mm.h>
@@ -386,6 +386,28 @@ void nfs_setsecurity(struct inode *inode, struct nfs_fattr *fattr,
 #endif
 EXPORT_SYMBOL_GPL(nfs_setsecurity);
 
+/* Search for inode identified by fh, fileid and i_mode in inode cache. */
+struct inode *
+nfs_ilookup(struct super_block *sb, struct nfs_fattr *fattr, struct nfs_fh *fh)
+{
+	struct nfs_find_desc desc = {
+		.fh	= fh,
+		.fattr	= fattr,
+	};
+	struct inode *inode;
+	unsigned long hash;
+
+	if (!(fattr->valid & NFS_ATTR_FATTR_FILEID) ||
+	    !(fattr->valid & NFS_ATTR_FATTR_TYPE))
+		return NULL;
+
+	hash = nfs_fattr_to_ino_t(fattr);
+	inode = ilookup5(sb, hash, nfs_find_actor, &desc);
+
+	dprintk("%s: returning %p\n", __func__, inode);
+	return inode;
+}
+
 /*
  * This is our front-end to iget that looks up inodes by file handle
  * instead of inode number.
@@ -525,8 +547,14 @@ nfs_fhget(struct super_block *sb, struct nfs_fh *fh, struct nfs_fattr *fattr, st
 		nfs_fscache_init_inode(inode);
 
 		unlock_new_inode(inode);
-	} else
-		nfs_refresh_inode(inode, fattr);
+	} else {
+		int err = nfs_refresh_inode(inode, fattr);
+		if (err < 0) {
+			iput(inode);
+			inode = ERR_PTR(err);
+			goto out_no_inode;
+		}
+	}
 	dprintk("NFS: nfs_fhget(%s/%Lu fh_crc=0x%08x ct=%d)\n",
 		inode->i_sb->s_id,
 		(unsigned long long)NFS_FILEID(inode),
@@ -703,9 +731,10 @@ static bool nfs_need_revalidate_inode(struct inode *inode)
 	return false;
 }
 
-int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int nfs_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	int need_atime = NFS_I(inode)->cache_validity & NFS_INO_INVALID_ATIME;
 	int err = 0;
 
@@ -726,17 +755,20 @@ int nfs_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 	 *  - NFS never sets MS_NOATIME or MS_NODIRATIME so there is
 	 *    no point in checking those.
 	 */
- 	if ((mnt->mnt_flags & MNT_NOATIME) ||
- 	    ((mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
+	if ((path->mnt->mnt_flags & MNT_NOATIME) ||
+	    ((path->mnt->mnt_flags & MNT_NODIRATIME) && S_ISDIR(inode->i_mode)))
 		need_atime = 0;
 
 	if (need_atime || nfs_need_revalidate_inode(inode)) {
 		struct nfs_server *server = NFS_SERVER(inode);
 
-		nfs_readdirplus_parent_cache_miss(dentry);
+		if (!(server->flags & NFS_MOUNT_NOAC))
+			nfs_readdirplus_parent_cache_miss(path->dentry);
+		else
+			nfs_readdirplus_parent_cache_hit(path->dentry);
 		err = __nfs_revalidate_inode(server, inode);
 	} else
-		nfs_readdirplus_parent_cache_hit(dentry);
+		nfs_readdirplus_parent_cache_hit(path->dentry);
 	if (!err) {
 		generic_fillattr(inode, stat);
 		stat->ino = nfs_compat_user_ino64(NFS_FILEID(inode));
@@ -1311,9 +1343,9 @@ static int nfs_check_inode_attributes(struct inode *inode, struct nfs_fattr *fat
 		return 0;
 	/* Has the inode gone and changed behind our back? */
 	if ((fattr->valid & NFS_ATTR_FATTR_FILEID) && nfsi->fileid != fattr->fileid)
-		return -EIO;
+		return -ESTALE;
 	if ((fattr->valid & NFS_ATTR_FATTR_TYPE) && (inode->i_mode & S_IFMT) != (fattr->mode & S_IFMT))
-		return -EIO;
+		return -ESTALE;
 
 	if (!nfs_file_has_buffered_writers(nfsi)) {
 		/* Verify a few of the more important attributes */
diff --git a/fs/nfs/internal.h b/fs/nfs/internal.h
index 09ca5095c04e..dc456416d2be 100644
--- a/fs/nfs/internal.h
+++ b/fs/nfs/internal.h
@@ -7,9 +7,12 @@
 #include <linux/security.h>
 #include <linux/crc32.h>
 #include <linux/nfs_page.h>
+#include <linux/wait_bit.h>
 
 #define NFS_MS_MASK (MS_RDONLY|MS_NOSUID|MS_NODEV|MS_NOEXEC|MS_SYNCHRONOUS)
 
+extern const struct export_operations nfs_export_ops;
+
 struct nfs_string;
 
 /* Maximum number of readahead requests
@@ -186,6 +189,8 @@ extern struct nfs_server *nfs_clone_server(struct nfs_server *,
 					   struct nfs_fh *,
 					   struct nfs_fattr *,
 					   rpc_authflavor_t);
+extern bool nfs_client_init_is_complete(const struct nfs_client *clp);
+extern int nfs_client_init_status(const struct nfs_client *clp);
 extern int nfs_wait_client_init_complete(const struct nfs_client *clp);
 extern void nfs_mark_client_ready(struct nfs_client *clp, int state);
 extern struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
@@ -223,8 +228,8 @@ static inline void nfs_fs_proc_exit(void)
 #endif
 
 /* callback_xdr.c */
-extern struct svc_version nfs4_callback_version1;
-extern struct svc_version nfs4_callback_version4;
+extern const struct svc_version nfs4_callback_version1;
+extern const struct svc_version nfs4_callback_version4;
 
 struct nfs_pageio_descriptor;
 /* pagelist.c */
@@ -268,19 +273,19 @@ static inline bool nfs_match_open_context(const struct nfs_open_context *ctx1,
 }
 
 /* nfs2xdr.c */
-extern struct rpc_procinfo nfs_procedures[];
+extern const struct rpc_procinfo nfs_procedures[];
 extern int nfs2_decode_dirent(struct xdr_stream *,
-				struct nfs_entry *, int);
+				struct nfs_entry *, bool);
 
 /* nfs3xdr.c */
-extern struct rpc_procinfo nfs3_procedures[];
+extern const struct rpc_procinfo nfs3_procedures[];
 extern int nfs3_decode_dirent(struct xdr_stream *,
-				struct nfs_entry *, int);
+				struct nfs_entry *, bool);
 
 /* nfs4xdr.c */
 #if IS_ENABLED(CONFIG_NFS_V4)
 extern int nfs4_decode_dirent(struct xdr_stream *,
-				struct nfs_entry *, int);
+				struct nfs_entry *, bool);
 #endif
 #ifdef CONFIG_NFS_V4_1
 extern const u32 nfs41_maxread_overhead;
@@ -290,7 +295,7 @@ extern const u32 nfs41_maxgetdevinfo_overhead;
 
 /* nfs4proc.c */
 #if IS_ENABLED(CONFIG_NFS_V4)
-extern struct rpc_procinfo nfs4_procedures[];
+extern const struct rpc_procinfo nfs4_procedures[];
 #endif
 
 #ifdef CONFIG_NFS_V4_SECURITY_LABEL
@@ -396,7 +401,6 @@ extern struct file_system_type nfs4_referral_fs_type;
 bool nfs_auth_info_match(const struct nfs_auth_info *, rpc_authflavor_t);
 struct dentry *nfs_try_mount(int, const char *, struct nfs_mount_info *,
 			struct nfs_subversion *);
-void nfs_initialise_sb(struct super_block *);
 int nfs_set_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *);
 int nfs_clone_sb_security(struct super_block *, struct dentry *, struct nfs_mount_info *);
 struct dentry *nfs_fs_mount_common(struct nfs_server *, int, const char *,
@@ -456,7 +460,6 @@ extern void nfs_read_prepare(struct rpc_task *task, void *calldata);
 extern void nfs_pageio_reset_read_mds(struct nfs_pageio_descriptor *pgio);
 
 /* super.c */
-void nfs_clone_super(struct super_block *, struct nfs_mount_info *);
 void nfs_umount_begin(struct super_block *);
 int  nfs_statfs(struct dentry *, struct kstatfs *);
 int  nfs_show_options(struct seq_file *, struct dentry *);
@@ -493,7 +496,6 @@ void nfs_mark_request_commit(struct nfs_page *req,
 			     u32 ds_commit_idx);
 int nfs_write_need_commit(struct nfs_pgio_header *);
 void nfs_writeback_update_inode(struct nfs_pgio_header *hdr);
-int nfs_commit_file(struct file *file, struct nfs_write_verifier *verf);
 int nfs_generic_commit_list(struct inode *inode, struct list_head *head,
 			    int how, struct nfs_commit_info *cinfo);
 void nfs_retry_commit(struct list_head *page_list,
@@ -754,9 +756,13 @@ static inline bool nfs_error_is_fatal(int err)
 {
 	switch (err) {
 	case -ERESTARTSYS:
+	case -EACCES:
+	case -EDQUOT:
+	case -EFBIG:
 	case -EIO:
 	case -ENOSPC:
 	case -EROFS:
+	case -ESTALE:
 	case -E2BIG:
 		return true;
 	default:
diff --git a/fs/nfs/mount_clnt.c b/fs/nfs/mount_clnt.c
index 09b190015df4..60bad882c123 100644
--- a/fs/nfs/mount_clnt.c
+++ b/fs/nfs/mount_clnt.c
@@ -304,7 +304,7 @@ static void encode_mntdirpath(struct xdr_stream *xdr, const char *pathname)
 }
 
 static void mnt_xdr_enc_dirpath(struct rpc_rqst *req, struct xdr_stream *xdr,
-				const char *dirpath)
+				const void *dirpath)
 {
 	encode_mntdirpath(xdr, dirpath);
 }
@@ -357,8 +357,9 @@ static int decode_fhandle(struct xdr_stream *xdr, struct mountres *res)
 
 static int mnt_xdr_dec_mountres(struct rpc_rqst *req,
 				struct xdr_stream *xdr,
-				struct mountres *res)
+				void *data)
 {
+	struct mountres *res = data;
 	int status;
 
 	status = decode_status(xdr, res);
@@ -449,8 +450,9 @@ static int decode_auth_flavors(struct xdr_stream *xdr, struct mountres *res)
 
 static int mnt_xdr_dec_mountres3(struct rpc_rqst *req,
 				 struct xdr_stream *xdr,
-				 struct mountres *res)
+				 void *data)
 {
+	struct mountres *res = data;
 	int status;
 
 	status = decode_fhs_status(xdr, res);
@@ -464,11 +466,11 @@ static int mnt_xdr_dec_mountres3(struct rpc_rqst *req,
 	return decode_auth_flavors(xdr, res);
 }
 
-static struct rpc_procinfo mnt_procedures[] = {
+static const struct rpc_procinfo mnt_procedures[] = {
 	[MOUNTPROC_MNT] = {
 		.p_proc		= MOUNTPROC_MNT,
-		.p_encode	= (kxdreproc_t)mnt_xdr_enc_dirpath,
-		.p_decode	= (kxdrdproc_t)mnt_xdr_dec_mountres,
+		.p_encode	= mnt_xdr_enc_dirpath,
+		.p_decode	= mnt_xdr_dec_mountres,
 		.p_arglen	= MNT_enc_dirpath_sz,
 		.p_replen	= MNT_dec_mountres_sz,
 		.p_statidx	= MOUNTPROC_MNT,
@@ -476,18 +478,18 @@ static struct rpc_procinfo mnt_procedures[] = {
 	},
 	[MOUNTPROC_UMNT] = {
 		.p_proc		= MOUNTPROC_UMNT,
-		.p_encode	= (kxdreproc_t)mnt_xdr_enc_dirpath,
+		.p_encode	= mnt_xdr_enc_dirpath,
 		.p_arglen	= MNT_enc_dirpath_sz,
 		.p_statidx	= MOUNTPROC_UMNT,
 		.p_name		= "UMOUNT",
 	},
 };
 
-static struct rpc_procinfo mnt3_procedures[] = {
+static const struct rpc_procinfo mnt3_procedures[] = {
 	[MOUNTPROC3_MNT] = {
 		.p_proc		= MOUNTPROC3_MNT,
-		.p_encode	= (kxdreproc_t)mnt_xdr_enc_dirpath,
-		.p_decode	= (kxdrdproc_t)mnt_xdr_dec_mountres3,
+		.p_encode	= mnt_xdr_enc_dirpath,
+		.p_decode	= mnt_xdr_dec_mountres3,
 		.p_arglen	= MNT_enc_dirpath_sz,
 		.p_replen	= MNT_dec_mountres3_sz,
 		.p_statidx	= MOUNTPROC3_MNT,
@@ -495,24 +497,27 @@ static struct rpc_procinfo mnt3_procedures[] = {
 	},
 	[MOUNTPROC3_UMNT] = {
 		.p_proc		= MOUNTPROC3_UMNT,
-		.p_encode	= (kxdreproc_t)mnt_xdr_enc_dirpath,
+		.p_encode	= mnt_xdr_enc_dirpath,
 		.p_arglen	= MNT_enc_dirpath_sz,
 		.p_statidx	= MOUNTPROC3_UMNT,
 		.p_name		= "UMOUNT",
 	},
 };
 
-
+static unsigned int mnt_counts[ARRAY_SIZE(mnt_procedures)];
 static const struct rpc_version mnt_version1 = {
 	.number		= 1,
 	.nrprocs	= ARRAY_SIZE(mnt_procedures),
 	.procs		= mnt_procedures,
+	.counts		= mnt_counts,
 };
 
+static unsigned int mnt3_counts[ARRAY_SIZE(mnt3_procedures)];
 static const struct rpc_version mnt_version3 = {
 	.number		= 3,
 	.nrprocs	= ARRAY_SIZE(mnt3_procedures),
 	.procs		= mnt3_procedures,
+	.counts		= mnt3_counts,
 };
 
 static const struct rpc_version *mnt_version[] = {
diff --git a/fs/nfs/namespace.c b/fs/nfs/namespace.c
index 5551e8ef67fd..e5686be67be8 100644
--- a/fs/nfs/namespace.c
+++ b/fs/nfs/namespace.c
@@ -143,11 +143,8 @@ struct vfsmount *nfs_d_automount(struct path *path)
 	struct nfs_fh *fh = NULL;
 	struct nfs_fattr *fattr = NULL;
 
-	dprintk("--> nfs_d_automount()\n");
-
-	mnt = ERR_PTR(-ESTALE);
 	if (IS_ROOT(path->dentry))
-		goto out_nofree;
+		return ERR_PTR(-ESTALE);
 
 	mnt = ERR_PTR(-ENOMEM);
 	fh = nfs_alloc_fhandle();
@@ -155,13 +152,10 @@ struct vfsmount *nfs_d_automount(struct path *path)
 	if (fh == NULL || fattr == NULL)
 		goto out;
 
-	dprintk("%s: enter\n", __func__);
-
 	mnt = server->nfs_client->rpc_ops->submount(server, path->dentry, fh, fattr);
 	if (IS_ERR(mnt))
 		goto out;
 
-	dprintk("%s: done, success\n", __func__);
 	mntget(mnt); /* prevent immediate expiration */
 	mnt_set_expiry(mnt, &nfs_automount_list);
 	schedule_delayed_work(&nfs_automount_task, nfs_mountpoint_expiry_timeout);
@@ -169,20 +163,16 @@ struct vfsmount *nfs_d_automount(struct path *path)
 out:
 	nfs_free_fattr(fattr);
 	nfs_free_fhandle(fh);
-out_nofree:
-	if (IS_ERR(mnt))
-		dprintk("<-- %s(): error %ld\n", __func__, PTR_ERR(mnt));
-	else
-		dprintk("<-- %s() = %p\n", __func__, mnt);
 	return mnt;
 }
 
 static int
-nfs_namespace_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+nfs_namespace_getattr(const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int query_flags)
 {
-	if (NFS_FH(d_inode(dentry))->size != 0)
-		return nfs_getattr(mnt, dentry, stat);
-	generic_fillattr(d_inode(dentry), stat);
+	if (NFS_FH(d_inode(path->dentry))->size != 0)
+		return nfs_getattr(path, stat, request_mask, query_flags);
+	generic_fillattr(d_inode(path->dentry), stat);
 	return 0;
 }
 
@@ -226,7 +216,7 @@ static struct vfsmount *nfs_do_clone_mount(struct nfs_server *server,
 					   const char *devname,
 					   struct nfs_clone_mount *mountdata)
 {
-	return vfs_kern_mount(&nfs_xdev_fs_type, 0, devname, mountdata);
+	return vfs_submount(mountdata->dentry, &nfs_xdev_fs_type, devname, mountdata);
 }
 
 /**
@@ -247,27 +237,20 @@ struct vfsmount *nfs_do_submount(struct dentry *dentry, struct nfs_fh *fh,
 		.fattr = fattr,
 		.authflavor = authflavor,
 	};
-	struct vfsmount *mnt = ERR_PTR(-ENOMEM);
+	struct vfsmount *mnt;
 	char *page = (char *) __get_free_page(GFP_USER);
 	char *devname;
 
-	dprintk("--> nfs_do_submount()\n");
-
-	dprintk("%s: submounting on %pd2\n", __func__,
-			dentry);
 	if (page == NULL)
-		goto out;
+		return ERR_PTR(-ENOMEM);
+
 	devname = nfs_devname(dentry, page, PAGE_SIZE);
-	mnt = (struct vfsmount *)devname;
 	if (IS_ERR(devname))
-		goto free_page;
-	mnt = nfs_do_clone_mount(NFS_SB(dentry->d_sb), devname, &mountdata);
-free_page:
-	free_page((unsigned long)page);
-out:
-	dprintk("%s: done\n", __func__);
+		mnt = ERR_CAST(devname);
+	else
+		mnt = nfs_do_clone_mount(NFS_SB(dentry->d_sb), devname, &mountdata);
 
-	dprintk("<-- nfs_do_submount() = %p\n", mnt);
+	free_page((unsigned long)page);
 	return mnt;
 }
 EXPORT_SYMBOL_GPL(nfs_do_submount);
diff --git a/fs/nfs/nfs2xdr.c b/fs/nfs/nfs2xdr.c
index b4e03ed8599d..fe68dabfbde6 100644
--- a/fs/nfs/nfs2xdr.c
+++ b/fs/nfs/nfs2xdr.c
@@ -568,8 +568,10 @@ out_default:
 
 static void nfs2_xdr_enc_fhandle(struct rpc_rqst *req,
 				 struct xdr_stream *xdr,
-				 const struct nfs_fh *fh)
+				 const void *data)
 {
+	const struct nfs_fh *fh = data;
+
 	encode_fhandle(xdr, fh);
 }
 
@@ -583,23 +585,29 @@ static void nfs2_xdr_enc_fhandle(struct rpc_rqst *req,
  */
 static void nfs2_xdr_enc_sattrargs(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   const struct nfs_sattrargs *args)
+				   const void *data)
 {
+	const struct nfs_sattrargs *args = data;
+
 	encode_fhandle(xdr, args->fh);
 	encode_sattr(xdr, args->sattr);
 }
 
 static void nfs2_xdr_enc_diropargs(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   const struct nfs_diropargs *args)
+				   const void *data)
 {
+	const struct nfs_diropargs *args = data;
+
 	encode_diropargs(xdr, args->fh, args->name, args->len);
 }
 
 static void nfs2_xdr_enc_readlinkargs(struct rpc_rqst *req,
 				      struct xdr_stream *xdr,
-				      const struct nfs_readlinkargs *args)
+				      const void *data)
 {
+	const struct nfs_readlinkargs *args = data;
+
 	encode_fhandle(xdr, args->fh);
 	prepare_reply_buffer(req, args->pages, args->pgbase,
 					args->pglen, NFS_readlinkres_sz);
@@ -632,8 +640,10 @@ static void encode_readargs(struct xdr_stream *xdr,
 
 static void nfs2_xdr_enc_readargs(struct rpc_rqst *req,
 				  struct xdr_stream *xdr,
-				  const struct nfs_pgio_args *args)
+				  const void *data)
 {
+	const struct nfs_pgio_args *args = data;
+
 	encode_readargs(xdr, args);
 	prepare_reply_buffer(req, args->pages, args->pgbase,
 					args->count, NFS_readres_sz);
@@ -672,8 +682,10 @@ static void encode_writeargs(struct xdr_stream *xdr,
 
 static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   const struct nfs_pgio_args *args)
+				   const void *data)
 {
+	const struct nfs_pgio_args *args = data;
+
 	encode_writeargs(xdr, args);
 	xdr->buf->flags |= XDRBUF_WRITE;
 }
@@ -688,16 +700,20 @@ static void nfs2_xdr_enc_writeargs(struct rpc_rqst *req,
  */
 static void nfs2_xdr_enc_createargs(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    const struct nfs_createargs *args)
+				    const void *data)
 {
+	const struct nfs_createargs *args = data;
+
 	encode_diropargs(xdr, args->fh, args->name, args->len);
 	encode_sattr(xdr, args->sattr);
 }
 
 static void nfs2_xdr_enc_removeargs(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    const struct nfs_removeargs *args)
+				    const void *data)
 {
+	const struct nfs_removeargs *args = data;
+
 	encode_diropargs(xdr, args->fh, args->name.name, args->name.len);
 }
 
@@ -711,8 +727,9 @@ static void nfs2_xdr_enc_removeargs(struct rpc_rqst *req,
  */
 static void nfs2_xdr_enc_renameargs(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    const struct nfs_renameargs *args)
+				    const void *data)
 {
+	const struct nfs_renameargs *args = data;
 	const struct qstr *old = args->old_name;
 	const struct qstr *new = args->new_name;
 
@@ -730,8 +747,10 @@ static void nfs2_xdr_enc_renameargs(struct rpc_rqst *req,
  */
 static void nfs2_xdr_enc_linkargs(struct rpc_rqst *req,
 				  struct xdr_stream *xdr,
-				  const struct nfs_linkargs *args)
+				  const void *data)
 {
+	const struct nfs_linkargs *args = data;
+
 	encode_fhandle(xdr, args->fromfh);
 	encode_diropargs(xdr, args->tofh, args->toname, args->tolen);
 }
@@ -747,8 +766,10 @@ static void nfs2_xdr_enc_linkargs(struct rpc_rqst *req,
  */
 static void nfs2_xdr_enc_symlinkargs(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs_symlinkargs *args)
+				     const void *data)
 {
+	const struct nfs_symlinkargs *args = data;
+
 	encode_diropargs(xdr, args->fromfh, args->fromname, args->fromlen);
 	encode_path(xdr, args->pages, args->pathlen);
 	encode_sattr(xdr, args->sattr);
@@ -777,8 +798,10 @@ static void encode_readdirargs(struct xdr_stream *xdr,
 
 static void nfs2_xdr_enc_readdirargs(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs_readdirargs *args)
+				     const void *data)
 {
+	const struct nfs_readdirargs *args = data;
+
 	encode_readdirargs(xdr, args);
 	prepare_reply_buffer(req, args->pages, 0,
 					args->count, NFS_readdirres_sz);
@@ -809,13 +832,13 @@ out_default:
 }
 
 static int nfs2_xdr_dec_attrstat(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 struct nfs_fattr *result)
+				 void *result)
 {
 	return decode_attrstat(xdr, result, NULL);
 }
 
 static int nfs2_xdr_dec_diropres(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 struct nfs_diropok *result)
+				 void *result)
 {
 	return decode_diropres(xdr, result);
 }
@@ -860,8 +883,9 @@ out_default:
  *	};
  */
 static int nfs2_xdr_dec_readres(struct rpc_rqst *req, struct xdr_stream *xdr,
-				struct nfs_pgio_res *result)
+				void *data)
 {
+	struct nfs_pgio_res *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -882,8 +906,10 @@ out_default:
 }
 
 static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 struct nfs_pgio_res *result)
+				 void *data)
 {
+	struct nfs_pgio_res *result = data;
+
 	/* All NFSv2 writes are "file sync" writes */
 	result->verf->committed = NFS_FILE_SYNC;
 	return decode_attrstat(xdr, result->fattr, &result->op_status);
@@ -913,7 +939,7 @@ static int nfs2_xdr_dec_writeres(struct rpc_rqst *req, struct xdr_stream *xdr,
  *	};
  */
 int nfs2_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
-		       int plus)
+		       bool plus)
 {
 	__be32 *p;
 	int error;
@@ -1034,7 +1060,7 @@ out_overflow:
 }
 
 static int nfs2_xdr_dec_statfsres(struct rpc_rqst *req, struct xdr_stream *xdr,
-				  struct nfs2_fsstat *result)
+				  void *result)
 {
 	enum nfs_stat status;
 	int error;
@@ -1118,15 +1144,15 @@ static int nfs_stat_to_errno(enum nfs_stat status)
 #define PROC(proc, argtype, restype, timer)				\
 [NFSPROC_##proc] = {							\
 	.p_proc	    =  NFSPROC_##proc,					\
-	.p_encode   =  (kxdreproc_t)nfs2_xdr_enc_##argtype,		\
-	.p_decode   =  (kxdrdproc_t)nfs2_xdr_dec_##restype,		\
+	.p_encode   =  nfs2_xdr_enc_##argtype,				\
+	.p_decode   =  nfs2_xdr_dec_##restype,				\
 	.p_arglen   =  NFS_##argtype##_sz,				\
 	.p_replen   =  NFS_##restype##_sz,				\
 	.p_timer    =  timer,						\
 	.p_statidx  =  NFSPROC_##proc,					\
 	.p_name     =  #proc,						\
 	}
-struct rpc_procinfo	nfs_procedures[] = {
+const struct rpc_procinfo nfs_procedures[] = {
 	PROC(GETATTR,	fhandle,	attrstat,	1),
 	PROC(SETATTR,	sattrargs,	attrstat,	0),
 	PROC(LOOKUP,	diropargs,	diropres,	2),
@@ -1144,8 +1170,10 @@ struct rpc_procinfo	nfs_procedures[] = {
 	PROC(STATFS,	fhandle,	statfsres,	0),
 };
 
+static unsigned int nfs_version2_counts[ARRAY_SIZE(nfs_procedures)];
 const struct rpc_version nfs_version2 = {
 	.number			= 2,
 	.nrprocs		= ARRAY_SIZE(nfs_procedures),
-	.procs			= nfs_procedures
+	.procs			= nfs_procedures,
+	.counts			= nfs_version2_counts,
 };
diff --git a/fs/nfs/nfs3proc.c b/fs/nfs/nfs3proc.c
index dc925b531f32..d1e87ec0df84 100644
--- a/fs/nfs/nfs3proc.c
+++ b/fs/nfs/nfs3proc.c
@@ -220,15 +220,8 @@ static int nfs3_proc_access(struct inode *inode, struct nfs_access_entry *entry)
 
 	status = rpc_call_sync(NFS_CLIENT(inode), &msg, 0);
 	nfs_refresh_inode(inode, res.fattr);
-	if (status == 0) {
-		entry->mask = 0;
-		if (res.access & NFS3_ACCESS_READ)
-			entry->mask |= MAY_READ;
-		if (res.access & (NFS3_ACCESS_MODIFY | NFS3_ACCESS_EXTEND | NFS3_ACCESS_DELETE))
-			entry->mask |= MAY_WRITE;
-		if (res.access & (NFS3_ACCESS_LOOKUP|NFS3_ACCESS_EXECUTE))
-			entry->mask |= MAY_EXEC;
-	}
+	if (status == 0)
+		nfs_access_set_mask(entry, res.access);
 	nfs_free_fattr(res.fattr);
 out:
 	dprintk("NFS reply access: %d\n", status);
@@ -621,7 +614,7 @@ out:
  */
 static int
 nfs3_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-		  u64 cookie, struct page **pages, unsigned int count, int plus)
+		  u64 cookie, struct page **pages, unsigned int count, bool plus)
 {
 	struct inode		*dir = d_inode(dentry);
 	__be32			*verf = NFS_I(dir)->cookieverf;
@@ -865,12 +858,63 @@ static void nfs3_proc_commit_setup(struct nfs_commit_data *data, struct rpc_mess
 	msg->rpc_proc = &nfs3_procedures[NFS3PROC_COMMIT];
 }
 
+static void nfs3_nlm_alloc_call(void *data)
+{
+	struct nfs_lock_context *l_ctx = data;
+	if (l_ctx && test_bit(NFS_CONTEXT_UNLOCK, &l_ctx->open_context->flags)) {
+		get_nfs_open_context(l_ctx->open_context);
+		nfs_get_lock_context(l_ctx->open_context);
+	}
+}
+
+static bool nfs3_nlm_unlock_prepare(struct rpc_task *task, void *data)
+{
+	struct nfs_lock_context *l_ctx = data;
+	if (l_ctx && test_bit(NFS_CONTEXT_UNLOCK, &l_ctx->open_context->flags))
+		return nfs_async_iocounter_wait(task, l_ctx);
+	return false;
+
+}
+
+static void nfs3_nlm_release_call(void *data)
+{
+	struct nfs_lock_context *l_ctx = data;
+	struct nfs_open_context *ctx;
+	if (l_ctx && test_bit(NFS_CONTEXT_UNLOCK, &l_ctx->open_context->flags)) {
+		ctx = l_ctx->open_context;
+		nfs_put_lock_context(l_ctx);
+		put_nfs_open_context(ctx);
+	}
+}
+
+const struct nlmclnt_operations nlmclnt_fl_close_lock_ops = {
+	.nlmclnt_alloc_call = nfs3_nlm_alloc_call,
+	.nlmclnt_unlock_prepare = nfs3_nlm_unlock_prepare,
+	.nlmclnt_release_call = nfs3_nlm_release_call,
+};
+
 static int
 nfs3_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
 {
 	struct inode *inode = file_inode(filp);
+	struct nfs_lock_context *l_ctx = NULL;
+	struct nfs_open_context *ctx = nfs_file_open_context(filp);
+	int status;
 
-	return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl);
+	if (fl->fl_flags & FL_CLOSE) {
+		l_ctx = nfs_get_lock_context(ctx);
+		if (IS_ERR(l_ctx))
+			l_ctx = NULL;
+		else
+			set_bit(NFS_CONTEXT_UNLOCK, &ctx->flags);
+	}
+
+	status = nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl, l_ctx);
+
+	if (l_ctx)
+		nfs_put_lock_context(l_ctx);
+
+	return status;
 }
 
 static int nfs3_have_delegation(struct inode *inode, fmode_t flags)
@@ -921,6 +965,7 @@ const struct nfs_rpc_ops nfs_v3_clientops = {
 	.dir_inode_ops	= &nfs3_dir_inode_operations,
 	.file_inode_ops	= &nfs3_file_inode_operations,
 	.file_ops	= &nfs_file_operations,
+	.nlmclnt_ops	= &nlmclnt_fl_close_lock_ops,
 	.getroot	= nfs3_proc_get_root,
 	.submount	= nfs_submount,
 	.try_mount	= nfs_try_mount,
diff --git a/fs/nfs/nfs3xdr.c b/fs/nfs/nfs3xdr.c
index 267126d32ec0..e82c9e553224 100644
--- a/fs/nfs/nfs3xdr.c
+++ b/fs/nfs/nfs3xdr.c
@@ -846,8 +846,10 @@ static void encode_diropargs3(struct xdr_stream *xdr, const struct nfs_fh *fh,
  */
 static void nfs3_xdr_enc_getattr3args(struct rpc_rqst *req,
 				      struct xdr_stream *xdr,
-				      const struct nfs_fh *fh)
+				      const void *data)
 {
+	const struct nfs_fh *fh = data;
+
 	encode_nfs_fh3(xdr, fh);
 }
 
@@ -884,8 +886,9 @@ static void encode_sattrguard3(struct xdr_stream *xdr,
 
 static void nfs3_xdr_enc_setattr3args(struct rpc_rqst *req,
 				      struct xdr_stream *xdr,
-				      const struct nfs3_sattrargs *args)
+				      const void *data)
 {
+	const struct nfs3_sattrargs *args = data;
 	encode_nfs_fh3(xdr, args->fh);
 	encode_sattr3(xdr, args->sattr);
 	encode_sattrguard3(xdr, args);
@@ -900,8 +903,10 @@ static void nfs3_xdr_enc_setattr3args(struct rpc_rqst *req,
  */
 static void nfs3_xdr_enc_lookup3args(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs3_diropargs *args)
+				     const void *data)
 {
+	const struct nfs3_diropargs *args = data;
+
 	encode_diropargs3(xdr, args->fh, args->name, args->len);
 }
 
@@ -922,8 +927,10 @@ static void encode_access3args(struct xdr_stream *xdr,
 
 static void nfs3_xdr_enc_access3args(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs3_accessargs *args)
+				     const void *data)
 {
+	const struct nfs3_accessargs *args = data;
+
 	encode_access3args(xdr, args);
 }
 
@@ -936,8 +943,10 @@ static void nfs3_xdr_enc_access3args(struct rpc_rqst *req,
  */
 static void nfs3_xdr_enc_readlink3args(struct rpc_rqst *req,
 				       struct xdr_stream *xdr,
-				       const struct nfs3_readlinkargs *args)
+				       const void *data)
 {
+	const struct nfs3_readlinkargs *args = data;
+
 	encode_nfs_fh3(xdr, args->fh);
 	prepare_reply_buffer(req, args->pages, args->pgbase,
 					args->pglen, NFS3_readlinkres_sz);
@@ -966,8 +975,10 @@ static void encode_read3args(struct xdr_stream *xdr,
 
 static void nfs3_xdr_enc_read3args(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   const struct nfs_pgio_args *args)
+				   const void *data)
 {
+	const struct nfs_pgio_args *args = data;
+
 	encode_read3args(xdr, args);
 	prepare_reply_buffer(req, args->pages, args->pgbase,
 					args->count, NFS3_readres_sz);
@@ -1008,8 +1019,10 @@ static void encode_write3args(struct xdr_stream *xdr,
 
 static void nfs3_xdr_enc_write3args(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    const struct nfs_pgio_args *args)
+				    const void *data)
 {
+	const struct nfs_pgio_args *args = data;
+
 	encode_write3args(xdr, args);
 	xdr->buf->flags |= XDRBUF_WRITE;
 }
@@ -1055,8 +1068,10 @@ static void encode_createhow3(struct xdr_stream *xdr,
 
 static void nfs3_xdr_enc_create3args(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs3_createargs *args)
+				     const void *data)
 {
+	const struct nfs3_createargs *args = data;
+
 	encode_diropargs3(xdr, args->fh, args->name, args->len);
 	encode_createhow3(xdr, args);
 }
@@ -1071,8 +1086,10 @@ static void nfs3_xdr_enc_create3args(struct rpc_rqst *req,
  */
 static void nfs3_xdr_enc_mkdir3args(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    const struct nfs3_mkdirargs *args)
+				    const void *data)
 {
+	const struct nfs3_mkdirargs *args = data;
+
 	encode_diropargs3(xdr, args->fh, args->name, args->len);
 	encode_sattr3(xdr, args->sattr);
 }
@@ -1091,16 +1108,20 @@ static void nfs3_xdr_enc_mkdir3args(struct rpc_rqst *req,
  *	};
  */
 static void encode_symlinkdata3(struct xdr_stream *xdr,
-				const struct nfs3_symlinkargs *args)
+				const void *data)
 {
+	const struct nfs3_symlinkargs *args = data;
+
 	encode_sattr3(xdr, args->sattr);
 	encode_nfspath3(xdr, args->pages, args->pathlen);
 }
 
 static void nfs3_xdr_enc_symlink3args(struct rpc_rqst *req,
 				      struct xdr_stream *xdr,
-				      const struct nfs3_symlinkargs *args)
+				      const void *data)
 {
+	const struct nfs3_symlinkargs *args = data;
+
 	encode_diropargs3(xdr, args->fromfh, args->fromname, args->fromlen);
 	encode_symlinkdata3(xdr, args);
 	xdr->buf->flags |= XDRBUF_WRITE;
@@ -1160,8 +1181,10 @@ static void encode_mknoddata3(struct xdr_stream *xdr,
 
 static void nfs3_xdr_enc_mknod3args(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    const struct nfs3_mknodargs *args)
+				    const void *data)
 {
+	const struct nfs3_mknodargs *args = data;
+
 	encode_diropargs3(xdr, args->fh, args->name, args->len);
 	encode_mknoddata3(xdr, args);
 }
@@ -1175,8 +1198,10 @@ static void nfs3_xdr_enc_mknod3args(struct rpc_rqst *req,
  */
 static void nfs3_xdr_enc_remove3args(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs_removeargs *args)
+				     const void *data)
 {
+	const struct nfs_removeargs *args = data;
+
 	encode_diropargs3(xdr, args->fh, args->name.name, args->name.len);
 }
 
@@ -1190,8 +1215,9 @@ static void nfs3_xdr_enc_remove3args(struct rpc_rqst *req,
  */
 static void nfs3_xdr_enc_rename3args(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs_renameargs *args)
+				     const void *data)
 {
+	const struct nfs_renameargs *args = data;
 	const struct qstr *old = args->old_name;
 	const struct qstr *new = args->new_name;
 
@@ -1209,8 +1235,10 @@ static void nfs3_xdr_enc_rename3args(struct rpc_rqst *req,
  */
 static void nfs3_xdr_enc_link3args(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   const struct nfs3_linkargs *args)
+				   const void *data)
 {
+	const struct nfs3_linkargs *args = data;
+
 	encode_nfs_fh3(xdr, args->fromfh);
 	encode_diropargs3(xdr, args->tofh, args->toname, args->tolen);
 }
@@ -1240,8 +1268,10 @@ static void encode_readdir3args(struct xdr_stream *xdr,
 
 static void nfs3_xdr_enc_readdir3args(struct rpc_rqst *req,
 				      struct xdr_stream *xdr,
-				      const struct nfs3_readdirargs *args)
+				      const void *data)
 {
+	const struct nfs3_readdirargs *args = data;
+
 	encode_readdir3args(xdr, args);
 	prepare_reply_buffer(req, args->pages, 0,
 				args->count, NFS3_readdirres_sz);
@@ -1280,8 +1310,10 @@ static void encode_readdirplus3args(struct xdr_stream *xdr,
 
 static void nfs3_xdr_enc_readdirplus3args(struct rpc_rqst *req,
 					  struct xdr_stream *xdr,
-					  const struct nfs3_readdirargs *args)
+					  const void *data)
 {
+	const struct nfs3_readdirargs *args = data;
+
 	encode_readdirplus3args(xdr, args);
 	prepare_reply_buffer(req, args->pages, 0,
 				args->count, NFS3_readdirres_sz);
@@ -1310,8 +1342,10 @@ static void encode_commit3args(struct xdr_stream *xdr,
 
 static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs_commitargs *args)
+				     const void *data)
 {
+	const struct nfs_commitargs *args = data;
+
 	encode_commit3args(xdr, args);
 }
 
@@ -1319,8 +1353,10 @@ static void nfs3_xdr_enc_commit3args(struct rpc_rqst *req,
 
 static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs3_getaclargs *args)
+				     const void *data)
 {
+	const struct nfs3_getaclargs *args = data;
+
 	encode_nfs_fh3(xdr, args->fh);
 	encode_uint32(xdr, args->mask);
 	if (args->mask & (NFS_ACL | NFS_DFACL))
@@ -1331,8 +1367,9 @@ static void nfs3_xdr_enc_getacl3args(struct rpc_rqst *req,
 
 static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs3_setaclargs *args)
+				     const void *data)
 {
+	const struct nfs3_setaclargs *args = data;
 	unsigned int base;
 	int error;
 
@@ -1382,7 +1419,7 @@ static void nfs3_xdr_enc_setacl3args(struct rpc_rqst *req,
  */
 static int nfs3_xdr_dec_getattr3res(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    struct nfs_fattr *result)
+				    void *result)
 {
 	enum nfs_stat status;
 	int error;
@@ -1419,7 +1456,7 @@ out_default:
  */
 static int nfs3_xdr_dec_setattr3res(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    struct nfs_fattr *result)
+				    void *result)
 {
 	enum nfs_stat status;
 	int error;
@@ -1460,8 +1497,9 @@ out_status:
  */
 static int nfs3_xdr_dec_lookup3res(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   struct nfs3_diropres *result)
+				   void *data)
 {
+	struct nfs3_diropres *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -1507,8 +1545,9 @@ out_default:
  */
 static int nfs3_xdr_dec_access3res(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   struct nfs3_accessres *result)
+				   void *data)
 {
+	struct nfs3_accessres *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -1548,7 +1587,7 @@ out_default:
  */
 static int nfs3_xdr_dec_readlink3res(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     struct nfs_fattr *result)
+				     void *result)
 {
 	enum nfs_stat status;
 	int error;
@@ -1626,8 +1665,9 @@ out_overflow:
 }
 
 static int nfs3_xdr_dec_read3res(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 struct nfs_pgio_res *result)
+				 void *data)
 {
+	struct nfs_pgio_res *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -1699,8 +1739,9 @@ out_eio:
 }
 
 static int nfs3_xdr_dec_write3res(struct rpc_rqst *req, struct xdr_stream *xdr,
-				  struct nfs_pgio_res *result)
+				  void *data)
 {
+	struct nfs_pgio_res *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -1764,8 +1805,9 @@ out:
 
 static int nfs3_xdr_dec_create3res(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   struct nfs3_diropres *result)
+				   void *data)
 {
+	struct nfs3_diropres *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -1804,8 +1846,9 @@ out_default:
  */
 static int nfs3_xdr_dec_remove3res(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   struct nfs_removeres *result)
+				   void *data)
 {
+	struct nfs_removeres *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -1845,8 +1888,9 @@ out_status:
  */
 static int nfs3_xdr_dec_rename3res(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   struct nfs_renameres *result)
+				   void *data)
 {
+	struct nfs_renameres *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -1888,8 +1932,9 @@ out_status:
  *	};
  */
 static int nfs3_xdr_dec_link3res(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 struct nfs3_linkres *result)
+				 void *data)
 {
+	struct nfs3_linkres *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -1946,7 +1991,7 @@ out_status:
  *	};
  */
 int nfs3_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
-		       int plus)
+		       bool plus)
 {
 	struct nfs_entry old = *entry;
 	__be32 *p;
@@ -2072,8 +2117,9 @@ out:
 
 static int nfs3_xdr_dec_readdir3res(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    struct nfs3_readdirres *result)
+				    void *data)
 {
+	struct nfs3_readdirres *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -2140,8 +2186,9 @@ out_overflow:
 
 static int nfs3_xdr_dec_fsstat3res(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   struct nfs_fsstat *result)
+				   void *data)
 {
+	struct nfs_fsstat *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -2216,8 +2263,9 @@ out_overflow:
 
 static int nfs3_xdr_dec_fsinfo3res(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   struct nfs_fsinfo *result)
+				   void *data)
 {
+	struct nfs_fsinfo *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -2279,8 +2327,9 @@ out_overflow:
 
 static int nfs3_xdr_dec_pathconf3res(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     struct nfs_pathconf *result)
+				     void *data)
 {
+	struct nfs_pathconf *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -2320,8 +2369,9 @@ out_status:
  */
 static int nfs3_xdr_dec_commit3res(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   struct nfs_commitres *result)
+				   void *data)
 {
+	struct nfs_commitres *result = data;
 	enum nfs_stat status;
 	int error;
 
@@ -2389,7 +2439,7 @@ out:
 
 static int nfs3_xdr_dec_getacl3res(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   struct nfs3_getaclres *result)
+				   void *result)
 {
 	enum nfs_stat status;
 	int error;
@@ -2408,7 +2458,7 @@ out_default:
 
 static int nfs3_xdr_dec_setacl3res(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   struct nfs_fattr *result)
+				   void *result)
 {
 	enum nfs_stat status;
 	int error;
@@ -2495,8 +2545,8 @@ static int nfs3_stat_to_errno(enum nfs_stat status)
 #define PROC(proc, argtype, restype, timer)				\
 [NFS3PROC_##proc] = {							\
 	.p_proc      = NFS3PROC_##proc,					\
-	.p_encode    = (kxdreproc_t)nfs3_xdr_enc_##argtype##3args,	\
-	.p_decode    = (kxdrdproc_t)nfs3_xdr_dec_##restype##3res,	\
+	.p_encode    = nfs3_xdr_enc_##argtype##3args,			\
+	.p_decode    = nfs3_xdr_dec_##restype##3res,			\
 	.p_arglen    = NFS3_##argtype##args_sz,				\
 	.p_replen    = NFS3_##restype##res_sz,				\
 	.p_timer     = timer,						\
@@ -2504,7 +2554,7 @@ static int nfs3_stat_to_errno(enum nfs_stat status)
 	.p_name      = #proc,						\
 	}
 
-struct rpc_procinfo	nfs3_procedures[] = {
+const struct rpc_procinfo nfs3_procedures[] = {
 	PROC(GETATTR,		getattr,	getattr,	1),
 	PROC(SETATTR,		setattr,	setattr,	0),
 	PROC(LOOKUP,		lookup,		lookup,		2),
@@ -2528,18 +2578,20 @@ struct rpc_procinfo	nfs3_procedures[] = {
 	PROC(COMMIT,		commit,		commit,		5),
 };
 
+static unsigned int nfs_version3_counts[ARRAY_SIZE(nfs3_procedures)];
 const struct rpc_version nfs_version3 = {
 	.number			= 3,
 	.nrprocs		= ARRAY_SIZE(nfs3_procedures),
-	.procs			= nfs3_procedures
+	.procs			= nfs3_procedures,
+	.counts			= nfs_version3_counts,
 };
 
 #ifdef CONFIG_NFS_V3_ACL
-static struct rpc_procinfo	nfs3_acl_procedures[] = {
+static const struct rpc_procinfo nfs3_acl_procedures[] = {
 	[ACLPROC3_GETACL] = {
 		.p_proc = ACLPROC3_GETACL,
-		.p_encode = (kxdreproc_t)nfs3_xdr_enc_getacl3args,
-		.p_decode = (kxdrdproc_t)nfs3_xdr_dec_getacl3res,
+		.p_encode = nfs3_xdr_enc_getacl3args,
+		.p_decode = nfs3_xdr_dec_getacl3res,
 		.p_arglen = ACL3_getaclargs_sz,
 		.p_replen = ACL3_getaclres_sz,
 		.p_timer = 1,
@@ -2547,8 +2599,8 @@ static struct rpc_procinfo	nfs3_acl_procedures[] = {
 	},
 	[ACLPROC3_SETACL] = {
 		.p_proc = ACLPROC3_SETACL,
-		.p_encode = (kxdreproc_t)nfs3_xdr_enc_setacl3args,
-		.p_decode = (kxdrdproc_t)nfs3_xdr_dec_setacl3res,
+		.p_encode = nfs3_xdr_enc_setacl3args,
+		.p_decode = nfs3_xdr_dec_setacl3res,
 		.p_arglen = ACL3_setaclargs_sz,
 		.p_replen = ACL3_setaclres_sz,
 		.p_timer = 0,
@@ -2556,10 +2608,11 @@ static struct rpc_procinfo	nfs3_acl_procedures[] = {
 	},
 };
 
+static unsigned int nfs3_acl_counts[ARRAY_SIZE(nfs3_acl_procedures)];
 const struct rpc_version nfsacl_version3 = {
 	.number			= 3,
-	.nrprocs		= sizeof(nfs3_acl_procedures)/
-				  sizeof(nfs3_acl_procedures[0]),
+	.nrprocs		= ARRAY_SIZE(nfs3_acl_procedures),
 	.procs			= nfs3_acl_procedures,
+	.counts			= nfs3_acl_counts,
 };
 #endif  /* CONFIG_NFS_V3_ACL */
diff --git a/fs/nfs/nfs42proc.c b/fs/nfs/nfs42proc.c
index d12ff9385f49..6c2db51e67a7 100644
--- a/fs/nfs/nfs42proc.c
+++ b/fs/nfs/nfs42proc.c
@@ -12,6 +12,7 @@
 #include "nfs42.h"
 #include "iostat.h"
 #include "pnfs.h"
+#include "nfs4session.h"
 #include "internal.h"
 
 #define NFSDBG_FACILITY NFSDBG_PROC
@@ -128,30 +129,26 @@ out_unlock:
 	return err;
 }
 
-static ssize_t _nfs42_proc_copy(struct file *src, loff_t pos_src,
+static ssize_t _nfs42_proc_copy(struct file *src,
 				struct nfs_lock_context *src_lock,
-				struct file *dst, loff_t pos_dst,
+				struct file *dst,
 				struct nfs_lock_context *dst_lock,
-				size_t count)
+				struct nfs42_copy_args *args,
+				struct nfs42_copy_res *res)
 {
-	struct nfs42_copy_args args = {
-		.src_fh		= NFS_FH(file_inode(src)),
-		.src_pos	= pos_src,
-		.dst_fh		= NFS_FH(file_inode(dst)),
-		.dst_pos	= pos_dst,
-		.count		= count,
-	};
-	struct nfs42_copy_res res;
 	struct rpc_message msg = {
 		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_COPY],
-		.rpc_argp = &args,
-		.rpc_resp = &res,
+		.rpc_argp = args,
+		.rpc_resp = res,
 	};
 	struct inode *dst_inode = file_inode(dst);
 	struct nfs_server *server = NFS_SERVER(dst_inode);
-	int status;
+	loff_t pos_src = args->src_pos;
+	loff_t pos_dst = args->dst_pos;
+	size_t count = args->count;
+	ssize_t status;
 
-	status = nfs4_set_rw_stateid(&args.src_stateid, src_lock->open_context,
+	status = nfs4_set_rw_stateid(&args->src_stateid, src_lock->open_context,
 				     src_lock, FMODE_READ);
 	if (status)
 		return status;
@@ -161,7 +158,7 @@ static ssize_t _nfs42_proc_copy(struct file *src, loff_t pos_src,
 	if (status)
 		return status;
 
-	status = nfs4_set_rw_stateid(&args.dst_stateid, dst_lock->open_context,
+	status = nfs4_set_rw_stateid(&args->dst_stateid, dst_lock->open_context,
 				     dst_lock, FMODE_WRITE);
 	if (status)
 		return status;
@@ -170,23 +167,29 @@ static ssize_t _nfs42_proc_copy(struct file *src, loff_t pos_src,
 	if (status)
 		return status;
 
+	res->commit_res.verf = kzalloc(sizeof(struct nfs_writeverf), GFP_NOFS);
+	if (!res->commit_res.verf)
+		return -ENOMEM;
 	status = nfs4_call_sync(server->client, server, &msg,
-				&args.seq_args, &res.seq_res, 0);
+				&args->seq_args, &res->seq_res, 0);
 	if (status == -ENOTSUPP)
 		server->caps &= ~NFS_CAP_COPY;
 	if (status)
-		return status;
+		goto out;
 
-	if (res.write_res.verifier.committed != NFS_FILE_SYNC) {
-		status = nfs_commit_file(dst, &res.write_res.verifier.verifier);
-		if (status)
-			return status;
+	if (nfs_write_verifier_cmp(&res->write_res.verifier.verifier,
+				    &res->commit_res.verf->verifier)) {
+		status = -EAGAIN;
+		goto out;
 	}
 
 	truncate_pagecache_range(dst_inode, pos_dst,
-				 pos_dst + res.write_res.count);
+				 pos_dst + res->write_res.count);
 
-	return res.write_res.count;
+	status = res->write_res.count;
+out:
+	kfree(res->commit_res.verf);
+	return status;
 }
 
 ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
@@ -196,8 +199,22 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 	struct nfs_server *server = NFS_SERVER(file_inode(dst));
 	struct nfs_lock_context *src_lock;
 	struct nfs_lock_context *dst_lock;
-	struct nfs4_exception src_exception = { };
-	struct nfs4_exception dst_exception = { };
+	struct nfs42_copy_args args = {
+		.src_fh		= NFS_FH(file_inode(src)),
+		.src_pos	= pos_src,
+		.dst_fh		= NFS_FH(file_inode(dst)),
+		.dst_pos	= pos_dst,
+		.count		= count,
+	};
+	struct nfs42_copy_res res;
+	struct nfs4_exception src_exception = {
+		.inode		= file_inode(src),
+		.stateid	= &args.src_stateid,
+	};
+	struct nfs4_exception dst_exception = {
+		.inode		= file_inode(dst),
+		.stateid	= &args.dst_stateid,
+	};
 	ssize_t err, err2;
 
 	if (!nfs_server_capable(file_inode(dst), NFS_CAP_COPY))
@@ -207,7 +224,6 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 	if (IS_ERR(src_lock))
 		return PTR_ERR(src_lock);
 
-	src_exception.inode = file_inode(src);
 	src_exception.state = src_lock->open_context->state;
 
 	dst_lock = nfs_get_lock_context(nfs_file_open_context(dst));
@@ -216,18 +232,23 @@ ssize_t nfs42_proc_copy(struct file *src, loff_t pos_src,
 		goto out_put_src_lock;
 	}
 
-	dst_exception.inode = file_inode(dst);
 	dst_exception.state = dst_lock->open_context->state;
 
 	do {
 		inode_lock(file_inode(dst));
-		err = _nfs42_proc_copy(src, pos_src, src_lock,
-				       dst, pos_dst, dst_lock, count);
+		err = _nfs42_proc_copy(src, src_lock,
+				dst, dst_lock,
+				&args, &res);
 		inode_unlock(file_inode(dst));
 
+		if (err >= 0)
+			break;
 		if (err == -ENOTSUPP) {
 			err = -EOPNOTSUPP;
 			break;
+		} if (err == -EAGAIN) {
+			dst_exception.retry = 1;
+			continue;
 		}
 
 		err2 = nfs4_handle_exception(server, err, &src_exception);
@@ -331,9 +352,8 @@ nfs42_layoutstat_prepare(struct rpc_task *task, void *calldata)
 	}
 	nfs4_stateid_copy(&data->args.stateid, &lo->plh_stateid);
 	spin_unlock(&inode->i_lock);
-	nfs41_setup_sequence(nfs4_get_session(server), &data->args.seq_args,
-			     &data->res.seq_res, task);
-
+	nfs4_setup_sequence(server->nfs_client, &data->args.seq_args,
+			    &data->res.seq_res, task);
 }
 
 static void
@@ -368,6 +388,7 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
 			pnfs_mark_layout_stateid_invalid(lo, &head);
 			spin_unlock(&inode->i_lock);
 			pnfs_free_lseg_list(&head);
+			nfs_commit_inode(inode, 0);
 		} else
 			spin_unlock(&inode->i_lock);
 		break;
@@ -389,8 +410,6 @@ nfs42_layoutstat_done(struct rpc_task *task, void *calldata)
 	case -EOPNOTSUPP:
 		NFS_SERVER(inode)->caps &= ~NFS_CAP_LAYOUTSTATS;
 	}
-
-	dprintk("%s server returns %d\n", __func__, task->tk_status);
 }
 
 static void
diff --git a/fs/nfs/nfs42xdr.c b/fs/nfs/nfs42xdr.c
index 6c7296454bbc..5ee1b0f0d904 100644
--- a/fs/nfs/nfs42xdr.c
+++ b/fs/nfs/nfs42xdr.c
@@ -66,12 +66,14 @@
 					 encode_putfh_maxsz + \
 					 encode_savefh_maxsz + \
 					 encode_putfh_maxsz + \
-					 encode_copy_maxsz)
+					 encode_copy_maxsz + \
+					 encode_commit_maxsz)
 #define NFS4_dec_copy_sz		(compound_decode_hdr_maxsz + \
 					 decode_putfh_maxsz + \
 					 decode_savefh_maxsz + \
 					 decode_putfh_maxsz + \
-					 decode_copy_maxsz)
+					 decode_copy_maxsz + \
+					 decode_commit_maxsz)
 #define NFS4_enc_deallocate_sz		(compound_encode_hdr_maxsz + \
 					 encode_putfh_maxsz + \
 					 encode_deallocate_maxsz + \
@@ -110,7 +112,7 @@
 					 decode_getattr_maxsz)
 
 static void encode_fallocate(struct xdr_stream *xdr,
-			     struct nfs42_falloc_args *args)
+			     const struct nfs42_falloc_args *args)
 {
 	encode_nfs4_stateid(xdr, &args->falloc_stateid);
 	encode_uint64(xdr, args->falloc_offset);
@@ -118,7 +120,7 @@ static void encode_fallocate(struct xdr_stream *xdr,
 }
 
 static void encode_allocate(struct xdr_stream *xdr,
-			    struct nfs42_falloc_args *args,
+			    const struct nfs42_falloc_args *args,
 			    struct compound_hdr *hdr)
 {
 	encode_op_hdr(xdr, OP_ALLOCATE, decode_allocate_maxsz, hdr);
@@ -126,7 +128,7 @@ static void encode_allocate(struct xdr_stream *xdr,
 }
 
 static void encode_copy(struct xdr_stream *xdr,
-			struct nfs42_copy_args *args,
+			const struct nfs42_copy_args *args,
 			struct compound_hdr *hdr)
 {
 	encode_op_hdr(xdr, OP_COPY, decode_copy_maxsz, hdr);
@@ -143,7 +145,7 @@ static void encode_copy(struct xdr_stream *xdr,
 }
 
 static void encode_deallocate(struct xdr_stream *xdr,
-			      struct nfs42_falloc_args *args,
+			      const struct nfs42_falloc_args *args,
 			      struct compound_hdr *hdr)
 {
 	encode_op_hdr(xdr, OP_DEALLOCATE, decode_deallocate_maxsz, hdr);
@@ -151,7 +153,7 @@ static void encode_deallocate(struct xdr_stream *xdr,
 }
 
 static void encode_seek(struct xdr_stream *xdr,
-			struct nfs42_seek_args *args,
+			const struct nfs42_seek_args *args,
 			struct compound_hdr *hdr)
 {
 	encode_op_hdr(xdr, OP_SEEK, decode_seek_maxsz, hdr);
@@ -161,7 +163,7 @@ static void encode_seek(struct xdr_stream *xdr,
 }
 
 static void encode_layoutstats(struct xdr_stream *xdr,
-			       struct nfs42_layoutstat_args *args,
+			       const struct nfs42_layoutstat_args *args,
 			       struct nfs42_layoutstat_devinfo *devinfo,
 			       struct compound_hdr *hdr)
 {
@@ -189,7 +191,7 @@ static void encode_layoutstats(struct xdr_stream *xdr,
 }
 
 static void encode_clone(struct xdr_stream *xdr,
-			 struct nfs42_clone_args *args,
+			 const struct nfs42_clone_args *args,
 			 struct compound_hdr *hdr)
 {
 	__be32 *p;
@@ -208,8 +210,9 @@ static void encode_clone(struct xdr_stream *xdr,
  */
 static void nfs4_xdr_enc_allocate(struct rpc_rqst *req,
 				  struct xdr_stream *xdr,
-				  struct nfs42_falloc_args *args)
+				  const void *data)
 {
+	const struct nfs42_falloc_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -222,13 +225,26 @@ static void nfs4_xdr_enc_allocate(struct rpc_rqst *req,
 	encode_nops(&hdr);
 }
 
+static void encode_copy_commit(struct xdr_stream *xdr,
+			  const struct nfs42_copy_args *args,
+			  struct compound_hdr *hdr)
+{
+	__be32 *p;
+
+	encode_op_hdr(xdr, OP_COMMIT, decode_commit_maxsz, hdr);
+	p = reserve_space(xdr, 12);
+	p = xdr_encode_hyper(p, args->dst_pos);
+	*p = cpu_to_be32(args->count);
+}
+
 /*
  * Encode COPY request
  */
 static void nfs4_xdr_enc_copy(struct rpc_rqst *req,
 			      struct xdr_stream *xdr,
-			      struct nfs42_copy_args *args)
+			      const void *data)
 {
+	const struct nfs42_copy_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -239,6 +255,7 @@ static void nfs4_xdr_enc_copy(struct rpc_rqst *req,
 	encode_savefh(xdr, &hdr);
 	encode_putfh(xdr, args->dst_fh, &hdr);
 	encode_copy(xdr, args, &hdr);
+	encode_copy_commit(xdr, args, &hdr);
 	encode_nops(&hdr);
 }
 
@@ -247,8 +264,9 @@ static void nfs4_xdr_enc_copy(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    struct nfs42_falloc_args *args)
+				    const void *data)
 {
+	const struct nfs42_falloc_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -266,8 +284,9 @@ static void nfs4_xdr_enc_deallocate(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_seek(struct rpc_rqst *req,
 			      struct xdr_stream *xdr,
-			      struct nfs42_seek_args *args)
+			      const void *data)
 {
+	const struct nfs42_seek_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -284,8 +303,9 @@ static void nfs4_xdr_enc_seek(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_layoutstats(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     struct nfs42_layoutstat_args *args)
+				     const void *data)
 {
+	const struct nfs42_layoutstat_args *args = data;
 	int i;
 
 	struct compound_hdr hdr = {
@@ -306,8 +326,9 @@ static void nfs4_xdr_enc_layoutstats(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_clone(struct rpc_rqst *req,
 			       struct xdr_stream *xdr,
-			       struct nfs42_clone_args *args)
+			       const void *data)
 {
+	const struct nfs42_clone_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -433,8 +454,9 @@ static int decode_clone(struct xdr_stream *xdr)
  */
 static int nfs4_xdr_dec_allocate(struct rpc_rqst *rqstp,
 				 struct xdr_stream *xdr,
-				 struct nfs42_falloc_res *res)
+				 void *data)
 {
+	struct nfs42_falloc_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -460,8 +482,9 @@ out:
  */
 static int nfs4_xdr_dec_copy(struct rpc_rqst *rqstp,
 			     struct xdr_stream *xdr,
-			     struct nfs42_copy_res *res)
+			     void *data)
 {
+	struct nfs42_copy_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -481,6 +504,9 @@ static int nfs4_xdr_dec_copy(struct rpc_rqst *rqstp,
 	if (status)
 		goto out;
 	status = decode_copy(xdr, res);
+	if (status)
+		goto out;
+	status = decode_commit(xdr, &res->commit_res);
 out:
 	return status;
 }
@@ -490,8 +516,9 @@ out:
  */
 static int nfs4_xdr_dec_deallocate(struct rpc_rqst *rqstp,
 				   struct xdr_stream *xdr,
-				   struct nfs42_falloc_res *res)
+				   void *data)
 {
+	struct nfs42_falloc_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -517,8 +544,9 @@ out:
  */
 static int nfs4_xdr_dec_seek(struct rpc_rqst *rqstp,
 			     struct xdr_stream *xdr,
-			     struct nfs42_seek_res *res)
+			     void *data)
 {
+	struct nfs42_seek_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -541,8 +569,9 @@ out:
  */
 static int nfs4_xdr_dec_layoutstats(struct rpc_rqst *rqstp,
 				    struct xdr_stream *xdr,
-				    struct nfs42_layoutstat_res *res)
+				    void *data)
 {
+	struct nfs42_layoutstat_res *res = data;
 	struct compound_hdr hdr;
 	int status, i;
 
@@ -571,8 +600,9 @@ out:
  */
 static int nfs4_xdr_dec_clone(struct rpc_rqst *rqstp,
 			      struct xdr_stream *xdr,
-			      struct nfs42_clone_res *res)
+			      void *data)
 {
+	struct nfs42_clone_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
diff --git a/fs/nfs/nfs4_fs.h b/fs/nfs/nfs4_fs.h
index 665165833660..40bd05f05e74 100644
--- a/fs/nfs/nfs4_fs.h
+++ b/fs/nfs/nfs4_fs.h
@@ -273,14 +273,6 @@ extern int nfs4_set_rw_stateid(nfs4_stateid *stateid,
 		fmode_t fmode);
 
 #if defined(CONFIG_NFS_V4_1)
-static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server)
-{
-	return server->nfs_client->cl_session;
-}
-
-extern int nfs41_setup_sequence(struct nfs4_session *session,
-		struct nfs4_sequence_args *args, struct nfs4_sequence_res *res,
-		struct rpc_task *task);
 extern int nfs41_sequence_done(struct rpc_task *, struct nfs4_sequence_res *);
 extern int nfs4_proc_create_session(struct nfs_client *, struct rpc_cred *);
 extern int nfs4_proc_destroy_session(struct nfs4_session *, struct rpc_cred *);
@@ -357,11 +349,6 @@ nfs4_state_protect_write(struct nfs_client *clp, struct rpc_clnt **clntp,
 		hdr->args.stable = NFS_FILE_SYNC;
 }
 #else /* CONFIG_NFS_v4_1 */
-static inline struct nfs4_session *nfs4_get_session(const struct nfs_server *server)
-{
-	return NULL;
-}
-
 static inline bool
 is_ds_only_client(struct nfs_client *clp)
 {
@@ -466,7 +453,7 @@ extern void nfs_increment_open_seqid(int status, struct nfs_seqid *seqid);
 extern void nfs_increment_lock_seqid(int status, struct nfs_seqid *seqid);
 extern void nfs_release_seqid(struct nfs_seqid *seqid);
 extern void nfs_free_seqid(struct nfs_seqid *seqid);
-extern int nfs40_setup_sequence(struct nfs4_slot_table *tbl,
+extern int nfs4_setup_sequence(const struct nfs_client *client,
 				struct nfs4_sequence_args *args,
 				struct nfs4_sequence_res *res,
 				struct rpc_task *task);
@@ -506,13 +493,13 @@ static inline void nfs4_unregister_sysctl(void)
 #endif
 
 /* nfs4xdr.c */
-extern struct rpc_procinfo nfs4_procedures[];
+extern const struct rpc_procinfo nfs4_procedures[];
 
 struct nfs4_mount_data;
 
 /* callback_xdr.c */
-extern struct svc_version nfs4_callback_version1;
-extern struct svc_version nfs4_callback_version4;
+extern const struct svc_version nfs4_callback_version1;
+extern const struct svc_version nfs4_callback_version4;
 
 static inline void nfs4_stateid_copy(nfs4_stateid *dst, const nfs4_stateid *src)
 {
diff --git a/fs/nfs/nfs4client.c b/fs/nfs/nfs4client.c
index 5ae9d64ea08b..50566acb5469 100644
--- a/fs/nfs/nfs4client.c
+++ b/fs/nfs/nfs4client.c
@@ -359,11 +359,9 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 	struct nfs_client *old;
 	int error;
 
-	if (clp->cl_cons_state == NFS_CS_READY) {
+	if (clp->cl_cons_state == NFS_CS_READY)
 		/* the client is initialised already */
-		dprintk("<-- nfs4_init_client() = 0 [already %p]\n", clp);
 		return clp;
-	}
 
 	/* Check NFS protocol revision and initialize RPC op vector */
 	clp->rpc_ops = &nfs_v4_clientops;
@@ -416,12 +414,12 @@ struct nfs_client *nfs4_init_client(struct nfs_client *clp,
 	if (clp != old)
 		clp->cl_preserve_clid = true;
 	nfs_put_client(clp);
+	clear_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags);
 	return old;
 
 error:
 	nfs_mark_client_ready(clp, error);
 	nfs_put_client(clp);
-	dprintk("<-- nfs4_init_client() = xerror %d\n", error);
 	return ERR_PTR(error);
 }
 
@@ -469,6 +467,50 @@ static bool nfs4_same_verifier(nfs4_verifier *v1, nfs4_verifier *v2)
 	return memcmp(v1->data, v2->data, sizeof(v1->data)) == 0;
 }
 
+static int nfs4_match_client(struct nfs_client  *pos,  struct nfs_client *new,
+			     struct nfs_client **prev, struct nfs_net *nn)
+{
+	int status;
+
+	if (pos->rpc_ops != new->rpc_ops)
+		return 1;
+
+	if (pos->cl_minorversion != new->cl_minorversion)
+		return 1;
+
+	/* If "pos" isn't marked ready, we can't trust the
+	 * remaining fields in "pos", especially the client
+	 * ID and serverowner fields.  Wait for CREATE_SESSION
+	 * to finish. */
+	if (pos->cl_cons_state > NFS_CS_READY) {
+		atomic_inc(&pos->cl_count);
+		spin_unlock(&nn->nfs_client_lock);
+
+		nfs_put_client(*prev);
+		*prev = pos;
+
+		status = nfs_wait_client_init_complete(pos);
+		spin_lock(&nn->nfs_client_lock);
+
+		if (status < 0)
+			return status;
+	}
+
+	if (pos->cl_cons_state != NFS_CS_READY)
+		return 1;
+
+	if (pos->cl_clientid != new->cl_clientid)
+		return 1;
+
+	/* NFSv4.1 always uses the uniform string, however someone
+	 * might switch the uniquifier string on us.
+	 */
+	if (!nfs4_match_client_owner_id(pos, new))
+		return 1;
+
+	return 0;
+}
+
 /**
  * nfs40_walk_client_list - Find server that recognizes a client ID
  *
@@ -497,34 +539,10 @@ int nfs40_walk_client_list(struct nfs_client *new,
 	spin_lock(&nn->nfs_client_lock);
 	list_for_each_entry(pos, &nn->nfs_client_list, cl_share_link) {
 
-		if (pos->rpc_ops != new->rpc_ops)
-			continue;
-
-		if (pos->cl_minorversion != new->cl_minorversion)
-			continue;
-
-		/* If "pos" isn't marked ready, we can't trust the
-		 * remaining fields in "pos" */
-		if (pos->cl_cons_state > NFS_CS_READY) {
-			atomic_inc(&pos->cl_count);
-			spin_unlock(&nn->nfs_client_lock);
-
-			nfs_put_client(prev);
-			prev = pos;
-
-			status = nfs_wait_client_init_complete(pos);
-			if (status < 0)
-				goto out;
-			status = -NFS4ERR_STALE_CLIENTID;
-			spin_lock(&nn->nfs_client_lock);
-		}
-		if (pos->cl_cons_state != NFS_CS_READY)
-			continue;
-
-		if (pos->cl_clientid != new->cl_clientid)
-			continue;
-
-		if (!nfs4_match_client_owner_id(pos, new))
+		status = nfs4_match_client(pos, new, &prev, nn);
+		if (status < 0)
+			goto out_unlock;
+		if (status != 0)
 			continue;
 		/*
 		 * We just sent a new SETCLIENTID, which should have
@@ -557,8 +575,6 @@ int nfs40_walk_client_list(struct nfs_client *new,
 
 			prev = NULL;
 			*result = pos;
-			dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
-				__func__, pos, atomic_read(&pos->cl_count));
 			goto out;
 		case -ERESTARTSYS:
 		case -ETIMEDOUT:
@@ -572,32 +588,17 @@ int nfs40_walk_client_list(struct nfs_client *new,
 
 		spin_lock(&nn->nfs_client_lock);
 	}
+out_unlock:
 	spin_unlock(&nn->nfs_client_lock);
 
 	/* No match found. The server lost our clientid */
 out:
 	nfs_put_client(prev);
-	dprintk("NFS: <-- %s status = %d\n", __func__, status);
 	return status;
 }
 
 #ifdef CONFIG_NFS_V4_1
 /*
- * Returns true if the client IDs match
- */
-static bool nfs4_match_clientids(u64 a, u64 b)
-{
-	if (a != b) {
-		dprintk("NFS: --> %s client ID %llx does not match %llx\n",
-			__func__, a, b);
-		return false;
-	}
-	dprintk("NFS: --> %s client ID %llx matches %llx\n",
-		__func__, a, b);
-	return true;
-}
-
-/*
  * Returns true if the server major ids match
  */
 static bool
@@ -605,36 +606,8 @@ nfs4_check_serverowner_major_id(struct nfs41_server_owner *o1,
 				struct nfs41_server_owner *o2)
 {
 	if (o1->major_id_sz != o2->major_id_sz)
-		goto out_major_mismatch;
-	if (memcmp(o1->major_id, o2->major_id, o1->major_id_sz) != 0)
-		goto out_major_mismatch;
-
-	dprintk("NFS: --> %s server owner major IDs match\n", __func__);
-	return true;
-
-out_major_mismatch:
-	dprintk("NFS: --> %s server owner major IDs do not match\n",
-		__func__);
-	return false;
-}
-
-/*
- * Returns true if server minor ids match
- */
-static bool
-nfs4_check_serverowner_minor_id(struct nfs41_server_owner *o1,
-				struct nfs41_server_owner *o2)
-{
-	/* Check eir_server_owner so_minor_id */
-	if (o1->minor_id != o2->minor_id)
-		goto out_minor_mismatch;
-
-	dprintk("NFS: --> %s server owner minor IDs match\n", __func__);
-	return true;
-
-out_minor_mismatch:
-	dprintk("NFS: --> %s server owner minor IDs do not match\n", __func__);
-	return false;
+		return false;
+	return memcmp(o1->major_id, o2->major_id, o1->major_id_sz) == 0;
 }
 
 /*
@@ -645,18 +618,9 @@ nfs4_check_server_scope(struct nfs41_server_scope *s1,
 			struct nfs41_server_scope *s2)
 {
 	if (s1->server_scope_sz != s2->server_scope_sz)
-		goto out_scope_mismatch;
-	if (memcmp(s1->server_scope, s2->server_scope,
-		   s1->server_scope_sz) != 0)
-		goto out_scope_mismatch;
-
-	dprintk("NFS: --> %s server scopes match\n", __func__);
-	return true;
-
-out_scope_mismatch:
-	dprintk("NFS: --> %s server scopes do not match\n",
-		__func__);
-	return false;
+		return false;
+	return memcmp(s1->server_scope, s2->server_scope,
+					s1->server_scope_sz) == 0;
 }
 
 /**
@@ -680,7 +644,7 @@ int nfs4_detect_session_trunking(struct nfs_client *clp,
 				 struct rpc_xprt *xprt)
 {
 	/* Check eir_clientid */
-	if (!nfs4_match_clientids(clp->cl_clientid, res->clientid))
+	if (clp->cl_clientid != res->clientid)
 		goto out_err;
 
 	/* Check eir_server_owner so_major_id */
@@ -689,8 +653,7 @@ int nfs4_detect_session_trunking(struct nfs_client *clp,
 		goto out_err;
 
 	/* Check eir_server_owner so_minor_id */
-	if (!nfs4_check_serverowner_minor_id(clp->cl_serverowner,
-					     res->server_owner))
+	if (clp->cl_serverowner->minor_id != res->server_owner->minor_id)
 		goto out_err;
 
 	/* Check eir_server_scope */
@@ -739,33 +702,10 @@ int nfs41_walk_client_list(struct nfs_client *new,
 		if (pos == new)
 			goto found;
 
-		if (pos->rpc_ops != new->rpc_ops)
-			continue;
-
-		if (pos->cl_minorversion != new->cl_minorversion)
-			continue;
-
-		/* If "pos" isn't marked ready, we can't trust the
-		 * remaining fields in "pos", especially the client
-		 * ID and serverowner fields.  Wait for CREATE_SESSION
-		 * to finish. */
-		if (pos->cl_cons_state > NFS_CS_READY) {
-			atomic_inc(&pos->cl_count);
-			spin_unlock(&nn->nfs_client_lock);
-
-			nfs_put_client(prev);
-			prev = pos;
-
-			status = nfs_wait_client_init_complete(pos);
-			spin_lock(&nn->nfs_client_lock);
-			if (status < 0)
-				break;
-			status = -NFS4ERR_STALE_CLIENTID;
-		}
-		if (pos->cl_cons_state != NFS_CS_READY)
-			continue;
-
-		if (!nfs4_match_clientids(pos->cl_clientid, new->cl_clientid))
+		status = nfs4_match_client(pos, new, &prev, nn);
+		if (status < 0)
+			goto out;
+		if (status != 0)
 			continue;
 
 		/*
@@ -777,23 +717,15 @@ int nfs41_walk_client_list(struct nfs_client *new,
 						     new->cl_serverowner))
 			continue;
 
-		/* Unlike NFSv4.0, we know that NFSv4.1 always uses the
-		 * uniform string, however someone might switch the
-		 * uniquifier string on us.
-		 */
-		if (!nfs4_match_client_owner_id(pos, new))
-			continue;
 found:
 		atomic_inc(&pos->cl_count);
 		*result = pos;
 		status = 0;
-		dprintk("NFS: <-- %s using nfs_client = %p ({%d})\n",
-			__func__, pos, atomic_read(&pos->cl_count));
 		break;
 	}
 
+out:
 	spin_unlock(&nn->nfs_client_lock);
-	dprintk("NFS: <-- %s status = %d\n", __func__, status);
 	nfs_put_client(prev);
 	return status;
 }
@@ -916,26 +848,21 @@ static int nfs4_set_client(struct nfs_server *server,
 		.timeparms = timeparms,
 	};
 	struct nfs_client *clp;
-	int error;
-
-	dprintk("--> nfs4_set_client()\n");
 
 	if (server->flags & NFS_MOUNT_NORESVPORT)
 		set_bit(NFS_CS_NORESVPORT, &cl_init.init_flags);
 	if (server->options & NFS_OPTION_MIGRATION)
 		set_bit(NFS_CS_MIGRATION, &cl_init.init_flags);
+	if (test_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status))
+		set_bit(NFS_CS_TSM_POSSIBLE, &cl_init.init_flags);
 
 	/* Allocate or find a client reference we can use */
 	clp = nfs_get_client(&cl_init);
-	if (IS_ERR(clp)) {
-		error = PTR_ERR(clp);
-		goto error;
-	}
+	if (IS_ERR(clp))
+		return PTR_ERR(clp);
 
-	if (server->nfs_client == clp) {
-		error = -ELOOP;
-		goto error;
-	}
+	if (server->nfs_client == clp)
+		return -ELOOP;
 
 	/*
 	 * Query for the lease time on clientid setup or renewal
@@ -947,11 +874,7 @@ static int nfs4_set_client(struct nfs_server *server,
 	set_bit(NFS_CS_CHECK_LEASE_TIME, &clp->cl_res_state);
 
 	server->nfs_client = clp;
-	dprintk("<-- nfs4_set_client() = 0 [new %p]\n", clp);
 	return 0;
-error:
-	dprintk("<-- nfs4_set_client() = xerror %d\n", error);
-	return error;
 }
 
 /*
@@ -982,7 +905,6 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 		.net = mds_clp->cl_net,
 		.timeparms = &ds_timeout,
 	};
-	struct nfs_client *clp;
 	char buf[INET6_ADDRSTRLEN + 1];
 
 	if (rpc_ntop(ds_addr, buf, sizeof(buf)) <= 0)
@@ -998,10 +920,7 @@ struct nfs_client *nfs4_set_ds_client(struct nfs_server *mds_srv,
 	 * (section 13.1 RFC 5661).
 	 */
 	nfs_init_timeout_values(&ds_timeout, ds_proto, ds_timeo, ds_retrans);
-	clp = nfs_get_client(&cl_init);
-
-	dprintk("<-- %s %p\n", __func__, clp);
-	return clp;
+	return nfs_get_client(&cl_init);
 }
 EXPORT_SYMBOL_GPL(nfs4_set_ds_client);
 
@@ -1023,9 +942,9 @@ static void nfs4_session_set_rwsize(struct nfs_server *server)
 	server_resp_sz = sess->fc_attrs.max_resp_sz - nfs41_maxread_overhead;
 	server_rqst_sz = sess->fc_attrs.max_rqst_sz - nfs41_maxwrite_overhead;
 
-	if (server->rsize > server_resp_sz)
+	if (!server->rsize || server->rsize > server_resp_sz)
 		server->rsize = server_resp_sz;
-	if (server->wsize > server_rqst_sz)
+	if (!server->wsize || server->wsize > server_rqst_sz)
 		server->wsize = server_rqst_sz;
 #endif /* CONFIG_NFS_V4_1 */
 }
@@ -1098,8 +1017,6 @@ static int nfs4_init_server(struct nfs_server *server,
 	struct rpc_timeout timeparms;
 	int error;
 
-	dprintk("--> nfs4_init_server()\n");
-
 	nfs_init_timeout_values(&timeparms, data->nfs_server.protocol,
 			data->timeo, data->retrans);
 
@@ -1127,7 +1044,7 @@ static int nfs4_init_server(struct nfs_server *server,
 			data->minorversion,
 			data->net);
 	if (error < 0)
-		goto error;
+		return error;
 
 	if (data->rsize)
 		server->rsize = nfs_block_size(data->rsize, NULL);
@@ -1138,16 +1055,10 @@ static int nfs4_init_server(struct nfs_server *server,
 	server->acregmax = data->acregmax * HZ;
 	server->acdirmin = data->acdirmin * HZ;
 	server->acdirmax = data->acdirmax * HZ;
+	server->port     = data->nfs_server.port;
 
-	server->port = data->nfs_server.port;
-
-	error = nfs_init_server_rpcclient(server, &timeparms,
-					  data->selected_flavor);
-
-error:
-	/* Done */
-	dprintk("<-- nfs4_init_server() = %d\n", error);
-	return error;
+	return nfs_init_server_rpcclient(server, &timeparms,
+					 data->selected_flavor);
 }
 
 /*
@@ -1163,8 +1074,6 @@ struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info,
 	bool auth_probe;
 	int error;
 
-	dprintk("--> nfs4_create_server()\n");
-
 	server = nfs_alloc_server();
 	if (!server)
 		return ERR_PTR(-ENOMEM);
@@ -1180,12 +1089,10 @@ struct nfs_server *nfs4_create_server(struct nfs_mount_info *mount_info,
 	if (error < 0)
 		goto error;
 
-	dprintk("<-- nfs4_create_server() = %p\n", server);
 	return server;
 
 error:
 	nfs_free_server(server);
-	dprintk("<-- nfs4_create_server() = error %d\n", error);
 	return ERR_PTR(error);
 }
 
@@ -1200,8 +1107,6 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 	bool auth_probe;
 	int error;
 
-	dprintk("--> nfs4_create_referral_server()\n");
-
 	server = nfs_alloc_server();
 	if (!server)
 		return ERR_PTR(-ENOMEM);
@@ -1235,12 +1140,10 @@ struct nfs_server *nfs4_create_referral_server(struct nfs_clone_mount *data,
 	if (error < 0)
 		goto error;
 
-	dprintk("<-- nfs_create_referral_server() = %p\n", server);
 	return server;
 
 error:
 	nfs_free_server(server);
-	dprintk("<-- nfs4_create_referral_server() = error %d\n", error);
 	return ERR_PTR(error);
 }
 
@@ -1300,54 +1203,32 @@ int nfs4_update_server(struct nfs_server *server, const char *hostname,
 	struct sockaddr *localaddr = (struct sockaddr *)&address;
 	int error;
 
-	dprintk("--> %s: move FSID %llx:%llx to \"%s\")\n", __func__,
-			(unsigned long long)server->fsid.major,
-			(unsigned long long)server->fsid.minor,
-			hostname);
-
 	error = rpc_switch_client_transport(clnt, &xargs, clnt->cl_timeout);
-	if (error != 0) {
-		dprintk("<-- %s(): rpc_switch_client_transport returned %d\n",
-			__func__, error);
-		goto out;
-	}
+	if (error != 0)
+		return error;
 
 	error = rpc_localaddr(clnt, localaddr, sizeof(address));
-	if (error != 0) {
-		dprintk("<-- %s(): rpc_localaddr returned %d\n",
-			__func__, error);
-		goto out;
-	}
+	if (error != 0)
+		return error;
 
-	error = -EAFNOSUPPORT;
-	if (rpc_ntop(localaddr, buf, sizeof(buf)) == 0) {
-		dprintk("<-- %s(): rpc_ntop returned %d\n",
-			__func__, error);
-		goto out;
-	}
+	if (rpc_ntop(localaddr, buf, sizeof(buf)) == 0)
+		return -EAFNOSUPPORT;
 
 	nfs_server_remove_lists(server);
+	set_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status);
 	error = nfs4_set_client(server, hostname, sap, salen, buf,
 				clp->cl_proto, clnt->cl_timeout,
 				clp->cl_minorversion, net);
+	clear_bit(NFS_MIG_TSM_POSSIBLE, &server->mig_status);
 	nfs_put_client(clp);
 	if (error != 0) {
 		nfs_server_insert_lists(server);
-		dprintk("<-- %s(): nfs4_set_client returned %d\n",
-			__func__, error);
-		goto out;
+		return error;
 	}
 
 	if (server->nfs_client->cl_hostname == NULL)
 		server->nfs_client->cl_hostname = kstrdup(hostname, GFP_KERNEL);
 	nfs_server_insert_lists(server);
 
-	error = nfs_probe_destination(server);
-	if (error < 0)
-		goto out;
-
-	dprintk("<-- %s() succeeded\n", __func__);
-
-out:
-	return error;
+	return nfs_probe_destination(server);
 }
diff --git a/fs/nfs/nfs4getroot.c b/fs/nfs/nfs4getroot.c
index 039b3eb6d834..ac8406018962 100644
--- a/fs/nfs/nfs4getroot.c
+++ b/fs/nfs/nfs4getroot.c
@@ -14,8 +14,6 @@ int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool auth_p
 	struct nfs_fsinfo fsinfo;
 	int ret = -ENOMEM;
 
-	dprintk("--> nfs4_get_rootfh()\n");
-
 	fsinfo.fattr = nfs_alloc_fattr();
 	if (fsinfo.fattr == NULL)
 		goto out;
@@ -38,6 +36,5 @@ int nfs4_get_rootfh(struct nfs_server *server, struct nfs_fh *mntfh, bool auth_p
 	memcpy(&server->fsid, &fsinfo.fattr->fsid, sizeof(server->fsid));
 out:
 	nfs_free_fattr(fsinfo.fattr);
-	dprintk("<-- nfs4_get_rootfh() = %d\n", ret);
 	return ret;
 }
diff --git a/fs/nfs/nfs4idmap.c b/fs/nfs/nfs4idmap.c
index c444285bb1b1..dd5d27da8c0c 100644
--- a/fs/nfs/nfs4idmap.c
+++ b/fs/nfs/nfs4idmap.c
@@ -316,7 +316,7 @@ static ssize_t nfs_idmap_get_key(const char *name, size_t namelen,
 	if (ret < 0)
 		goto out_up;
 
-	payload = user_key_payload(rkey);
+	payload = user_key_payload_rcu(rkey);
 	if (IS_ERR_OR_NULL(payload)) {
 		ret = PTR_ERR(payload);
 		goto out_up;
@@ -364,7 +364,8 @@ static int nfs_idmap_lookup_id(const char *name, size_t namelen, const char *typ
 		ret = -EINVAL;
 	} else {
 		ret = kstrtol(id_str, 10, &id_long);
-		*id = (__u32)id_long;
+		if (!ret)
+			*id = (__u32)id_long;
 	}
 	return ret;
 }
diff --git a/fs/nfs/nfs4namespace.c b/fs/nfs/nfs4namespace.c
index d21104912676..7d531da1bae3 100644
--- a/fs/nfs/nfs4namespace.c
+++ b/fs/nfs/nfs4namespace.c
@@ -279,7 +279,7 @@ static struct vfsmount *try_location(struct nfs_clone_mount *mountdata,
 				mountdata->hostname,
 				mountdata->mnt_path);
 
-		mnt = vfs_kern_mount(&nfs4_referral_fs_type, 0, page, mountdata);
+		mnt = vfs_submount(mountdata->dentry, &nfs4_referral_fs_type, page, mountdata);
 		if (!IS_ERR(mnt))
 			break;
 	}
@@ -340,7 +340,6 @@ static struct vfsmount *nfs_follow_referral(struct dentry *dentry,
 out:
 	free_page((unsigned long) page);
 	free_page((unsigned long) page2);
-	dprintk("%s: done\n", __func__);
 	return mnt;
 }
 
@@ -358,11 +357,9 @@ static struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *
 	int err;
 
 	/* BUG_ON(IS_ROOT(dentry)); */
-	dprintk("%s: enter\n", __func__);
-
 	page = alloc_page(GFP_KERNEL);
 	if (page == NULL)
-		goto out;
+		return mnt;
 
 	fs_locations = kmalloc(sizeof(struct nfs4_fs_locations), GFP_KERNEL);
 	if (fs_locations == NULL)
@@ -386,8 +383,6 @@ static struct vfsmount *nfs_do_refmount(struct rpc_clnt *client, struct dentry *
 out_free:
 	__free_page(page);
 	kfree(fs_locations);
-out:
-	dprintk("%s: done\n", __func__);
 	return mnt;
 }
 
diff --git a/fs/nfs/nfs4proc.c b/fs/nfs/nfs4proc.c
index 0a0eaecf9676..a0b4e1091340 100644
--- a/fs/nfs/nfs4proc.c
+++ b/fs/nfs/nfs4proc.c
@@ -275,6 +275,7 @@ const u32 nfs4_fs_locations_bitmap[3] = {
 static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dentry,
 		struct nfs4_readdir_arg *readdir)
 {
+	unsigned int attrs = FATTR4_WORD0_FILEID | FATTR4_WORD0_TYPE;
 	__be32 *start, *p;
 
 	if (cookie > 2) {
@@ -305,8 +306,9 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent
 		memcpy(p, ".\0\0\0", 4);                        /* entry */
 		p++;
 		*p++ = xdr_one;                         /* bitmap length */
-		*p++ = htonl(FATTR4_WORD0_FILEID);             /* bitmap */
-		*p++ = htonl(8);              /* attribute buffer length */
+		*p++ = htonl(attrs);                           /* bitmap */
+		*p++ = htonl(12);             /* attribute buffer length */
+		*p++ = htonl(NF4DIR);
 		p = xdr_encode_hyper(p, NFS_FILEID(d_inode(dentry)));
 	}
 	
@@ -317,8 +319,9 @@ static void nfs4_setup_readdir(u64 cookie, __be32 *verifier, struct dentry *dent
 	memcpy(p, "..\0\0", 4);                         /* entry */
 	p++;
 	*p++ = xdr_one;                         /* bitmap length */
-	*p++ = htonl(FATTR4_WORD0_FILEID);             /* bitmap */
-	*p++ = htonl(8);              /* attribute buffer length */
+	*p++ = htonl(attrs);                           /* bitmap */
+	*p++ = htonl(12);             /* attribute buffer length */
+	*p++ = htonl(NF4DIR);
 	p = xdr_encode_hyper(p, NFS_FILEID(d_inode(dentry->d_parent)));
 
 	readdir->pgbase = (char *)p - (char *)start;
@@ -577,12 +580,7 @@ nfs4_async_handle_error(struct rpc_task *task, struct nfs_server *server,
 static bool _nfs4_is_integrity_protected(struct nfs_client *clp)
 {
 	rpc_authflavor_t flavor = clp->cl_rpcclient->cl_auth->au_flavor;
-
-	if (flavor == RPC_AUTH_GSS_KRB5I ||
-	    flavor == RPC_AUTH_GSS_KRB5P)
-		return true;
-
-	return false;
+	return (flavor == RPC_AUTH_GSS_KRB5I) || (flavor == RPC_AUTH_GSS_KRB5P);
 }
 
 static void do_renew_lease(struct nfs_client *clp, unsigned long timestamp)
@@ -622,48 +620,6 @@ static void nfs4_set_sequence_privileged(struct nfs4_sequence_args *args)
 	args->sa_privileged = 1;
 }
 
-int nfs40_setup_sequence(struct nfs4_slot_table *tbl,
-			 struct nfs4_sequence_args *args,
-			 struct nfs4_sequence_res *res,
-			 struct rpc_task *task)
-{
-	struct nfs4_slot *slot;
-
-	/* slot already allocated? */
-	if (res->sr_slot != NULL)
-		goto out_start;
-
-	spin_lock(&tbl->slot_tbl_lock);
-	if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged)
-		goto out_sleep;
-
-	slot = nfs4_alloc_slot(tbl);
-	if (IS_ERR(slot)) {
-		if (slot == ERR_PTR(-ENOMEM))
-			task->tk_timeout = HZ >> 2;
-		goto out_sleep;
-	}
-	spin_unlock(&tbl->slot_tbl_lock);
-
-	slot->privileged = args->sa_privileged ? 1 : 0;
-	args->sa_slot = slot;
-	res->sr_slot = slot;
-
-out_start:
-	rpc_call_start(task);
-	return 0;
-
-out_sleep:
-	if (args->sa_privileged)
-		rpc_sleep_on_priority(&tbl->slot_tbl_waitq, task,
-				NULL, RPC_PRIORITY_PRIVILEGED);
-	else
-		rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
-	spin_unlock(&tbl->slot_tbl_lock);
-	return -EAGAIN;
-}
-EXPORT_SYMBOL_GPL(nfs40_setup_sequence);
-
 static void nfs40_sequence_free_slot(struct nfs4_sequence_res *res)
 {
 	struct nfs4_slot *slot = res->sr_slot;
@@ -745,7 +701,8 @@ static int nfs41_sequence_process(struct rpc_task *task,
 	session = slot->table->session;
 
 	if (slot->interrupted) {
-		slot->interrupted = 0;
+		if (res->sr_status != -NFS4ERR_DELAY)
+			slot->interrupted = 0;
 		interrupted = true;
 	}
 
@@ -815,10 +772,6 @@ static int nfs41_sequence_process(struct rpc_task *task,
 	case -NFS4ERR_SEQ_FALSE_RETRY:
 		++slot->seq_nr;
 		goto retry_nowait;
-	case -NFS4ERR_DEADSESSION:
-	case -NFS4ERR_BADSESSION:
-		nfs4_schedule_session_recovery(session, res->sr_status);
-		goto retry_nowait;
 	default:
 		/* Just update the slot sequence no. */
 		slot->seq_done = 1;
@@ -882,101 +835,14 @@ int nfs4_sequence_done(struct rpc_task *task, struct nfs4_sequence_res *res)
 }
 EXPORT_SYMBOL_GPL(nfs4_sequence_done);
 
-int nfs41_setup_sequence(struct nfs4_session *session,
-				struct nfs4_sequence_args *args,
-				struct nfs4_sequence_res *res,
-				struct rpc_task *task)
-{
-	struct nfs4_slot *slot;
-	struct nfs4_slot_table *tbl;
-
-	dprintk("--> %s\n", __func__);
-	/* slot already allocated? */
-	if (res->sr_slot != NULL)
-		goto out_success;
-
-	tbl = &session->fc_slot_table;
-
-	task->tk_timeout = 0;
-
-	spin_lock(&tbl->slot_tbl_lock);
-	if (test_bit(NFS4_SLOT_TBL_DRAINING, &tbl->slot_tbl_state) &&
-	    !args->sa_privileged) {
-		/* The state manager will wait until the slot table is empty */
-		dprintk("%s session is draining\n", __func__);
-		goto out_sleep;
-	}
-
-	slot = nfs4_alloc_slot(tbl);
-	if (IS_ERR(slot)) {
-		/* If out of memory, try again in 1/4 second */
-		if (slot == ERR_PTR(-ENOMEM))
-			task->tk_timeout = HZ >> 2;
-		dprintk("<-- %s: no free slots\n", __func__);
-		goto out_sleep;
-	}
-	spin_unlock(&tbl->slot_tbl_lock);
-
-	slot->privileged = args->sa_privileged ? 1 : 0;
-	args->sa_slot = slot;
-
-	dprintk("<-- %s slotid=%u seqid=%u\n", __func__,
-			slot->slot_nr, slot->seq_nr);
-
-	res->sr_slot = slot;
-	res->sr_timestamp = jiffies;
-	res->sr_status_flags = 0;
-	/*
-	 * sr_status is only set in decode_sequence, and so will remain
-	 * set to 1 if an rpc level failure occurs.
-	 */
-	res->sr_status = 1;
-	trace_nfs4_setup_sequence(session, args);
-out_success:
-	rpc_call_start(task);
-	return 0;
-out_sleep:
-	/* Privileged tasks are queued with top priority */
-	if (args->sa_privileged)
-		rpc_sleep_on_priority(&tbl->slot_tbl_waitq, task,
-				NULL, RPC_PRIORITY_PRIVILEGED);
-	else
-		rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
-	spin_unlock(&tbl->slot_tbl_lock);
-	return -EAGAIN;
-}
-EXPORT_SYMBOL_GPL(nfs41_setup_sequence);
-
-static int nfs4_setup_sequence(const struct nfs_server *server,
-			       struct nfs4_sequence_args *args,
-			       struct nfs4_sequence_res *res,
-			       struct rpc_task *task)
-{
-	struct nfs4_session *session = nfs4_get_session(server);
-	int ret = 0;
-
-	if (!session)
-		return nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
-					    args, res, task);
-
-	dprintk("--> %s clp %p session %p sr_slot %u\n",
-		__func__, session->clp, session, res->sr_slot ?
-			res->sr_slot->slot_nr : NFS4_NO_SLOT);
-
-	ret = nfs41_setup_sequence(session, args, res, task);
-
-	dprintk("<-- %s status=%d\n", __func__, ret);
-	return ret;
-}
-
 static void nfs41_call_sync_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_call_sync_data *data = calldata;
-	struct nfs4_session *session = nfs4_get_session(data->seq_server);
 
 	dprintk("--> %s data->seq_server %p\n", __func__, data->seq_server);
 
-	nfs41_setup_sequence(session, data->seq_args, data->seq_res, task);
+	nfs4_setup_sequence(data->seq_server->nfs_client,
+			    data->seq_args, data->seq_res, task);
 }
 
 static void nfs41_call_sync_done(struct rpc_task *task, void *calldata)
@@ -993,15 +859,6 @@ static const struct rpc_call_ops nfs41_call_sync_ops = {
 
 #else	/* !CONFIG_NFS_V4_1 */
 
-static int nfs4_setup_sequence(const struct nfs_server *server,
-			       struct nfs4_sequence_args *args,
-			       struct nfs4_sequence_res *res,
-			       struct rpc_task *task)
-{
-	return nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
-				    args, res, task);
-}
-
 static int nfs4_sequence_process(struct rpc_task *task, struct nfs4_sequence_res *res)
 {
 	return nfs40_sequence_done(task, res);
@@ -1022,10 +879,68 @@ EXPORT_SYMBOL_GPL(nfs4_sequence_done);
 
 #endif	/* !CONFIG_NFS_V4_1 */
 
+int nfs4_setup_sequence(const struct nfs_client *client,
+			struct nfs4_sequence_args *args,
+			struct nfs4_sequence_res *res,
+			struct rpc_task *task)
+{
+	struct nfs4_session *session = nfs4_get_session(client);
+	struct nfs4_slot_table *tbl  = client->cl_slot_tbl;
+	struct nfs4_slot *slot;
+
+	/* slot already allocated? */
+	if (res->sr_slot != NULL)
+		goto out_start;
+
+	if (session) {
+		tbl = &session->fc_slot_table;
+		task->tk_timeout = 0;
+	}
+
+	spin_lock(&tbl->slot_tbl_lock);
+	/* The state manager will wait until the slot table is empty */
+	if (nfs4_slot_tbl_draining(tbl) && !args->sa_privileged)
+		goto out_sleep;
+
+	slot = nfs4_alloc_slot(tbl);
+	if (IS_ERR(slot)) {
+		/* Try again in 1/4 second */
+		if (slot == ERR_PTR(-ENOMEM))
+			task->tk_timeout = HZ >> 2;
+		goto out_sleep;
+	}
+	spin_unlock(&tbl->slot_tbl_lock);
+
+	slot->privileged = args->sa_privileged ? 1 : 0;
+	args->sa_slot = slot;
+
+	res->sr_slot = slot;
+	if (session) {
+		res->sr_timestamp = jiffies;
+		res->sr_status_flags = 0;
+		res->sr_status = 1;
+	}
+
+	trace_nfs4_setup_sequence(session, args);
+out_start:
+	rpc_call_start(task);
+	return 0;
+
+out_sleep:
+	if (args->sa_privileged)
+		rpc_sleep_on_priority(&tbl->slot_tbl_waitq, task,
+				NULL, RPC_PRIORITY_PRIVILEGED);
+	else
+		rpc_sleep_on(&tbl->slot_tbl_waitq, task, NULL);
+	spin_unlock(&tbl->slot_tbl_lock);
+	return -EAGAIN;
+}
+EXPORT_SYMBOL_GPL(nfs4_setup_sequence);
+
 static void nfs40_call_sync_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_call_sync_data *data = calldata;
-	nfs4_setup_sequence(data->seq_server,
+	nfs4_setup_sequence(data->seq_server->nfs_client,
 				data->seq_args, data->seq_res, task);
 }
 
@@ -1122,11 +1037,11 @@ struct nfs4_opendata {
 	struct nfs4_state *state;
 	struct iattr attrs;
 	unsigned long timestamp;
-	unsigned int rpc_done : 1;
-	unsigned int file_created : 1;
-	unsigned int is_recover : 1;
+	bool rpc_done;
+	bool file_created;
+	bool is_recover;
+	bool cancelled;
 	int rpc_status;
-	int cancelled;
 };
 
 static bool nfs4_clear_cap_atomic_open_v1(struct nfs_server *server,
@@ -1330,14 +1245,6 @@ static void nfs4_opendata_put(struct nfs4_opendata *p)
 		kref_put(&p->kref, nfs4_opendata_free);
 }
 
-static int nfs4_wait_for_completion_rpc_task(struct rpc_task *task)
-{
-	int ret;
-
-	ret = rpc_wait_for_completion_task(task);
-	return ret;
-}
-
 static bool nfs4_mode_match_open_stateid(struct nfs4_state *state,
 		fmode_t fmode)
 {
@@ -1732,17 +1639,15 @@ _nfs4_opendata_reclaim_to_nfs4_state(struct nfs4_opendata *data)
 	int ret;
 
 	if (!data->rpc_done) {
-		if (data->rpc_status) {
-			ret = data->rpc_status;
-			goto err;
-		}
+		if (data->rpc_status)
+			return ERR_PTR(data->rpc_status);
 		/* cached opens have already been processed */
 		goto update;
 	}
 
 	ret = nfs_refresh_inode(inode, &data->f_attr);
 	if (ret)
-		goto err;
+		return ERR_PTR(ret);
 
 	if (data->o_res.delegation_type != 0)
 		nfs4_opendata_check_deleg(data, state);
@@ -1752,9 +1657,6 @@ update:
 	atomic_inc(&state->count);
 
 	return state;
-err:
-	return ERR_PTR(ret);
-
 }
 
 static struct nfs4_state *
@@ -2048,8 +1950,8 @@ static void nfs4_open_confirm_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_opendata *data = calldata;
 
-	nfs40_setup_sequence(data->o_arg.server->nfs_client->cl_slot_tbl,
-			     &data->c_arg.seq_args, &data->c_res.seq_res, task);
+	nfs4_setup_sequence(data->o_arg.server->nfs_client,
+			   &data->c_arg.seq_args, &data->c_res.seq_res, task);
 }
 
 static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
@@ -2063,7 +1965,7 @@ static void nfs4_open_confirm_done(struct rpc_task *task, void *calldata)
 		nfs4_stateid_copy(&data->o_res.stateid, &data->c_res.stateid);
 		nfs_confirm_seqid(&data->owner->so_seqid, 0);
 		renew_lease(data->o_res.server, data->timestamp);
-		data->rpc_done = 1;
+		data->rpc_done = true;
 	}
 }
 
@@ -2073,7 +1975,7 @@ static void nfs4_open_confirm_release(void *calldata)
 	struct nfs4_state *state = NULL;
 
 	/* If this request hasn't been cancelled, do nothing */
-	if (data->cancelled == 0)
+	if (!data->cancelled)
 		goto out_free;
 	/* In case of error, no cleanup! */
 	if (!data->rpc_done)
@@ -2116,7 +2018,7 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data)
 
 	nfs4_init_sequence(&data->c_arg.seq_args, &data->c_res.seq_res, 1);
 	kref_get(&data->kref);
-	data->rpc_done = 0;
+	data->rpc_done = false;
 	data->rpc_status = 0;
 	data->timestamp = jiffies;
 	if (data->is_recover)
@@ -2124,9 +2026,9 @@ static int _nfs4_proc_open_confirm(struct nfs4_opendata *data)
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
-	status = nfs4_wait_for_completion_rpc_task(task);
+	status = rpc_wait_for_completion_task(task);
 	if (status != 0) {
-		data->cancelled = 1;
+		data->cancelled = true;
 		smp_wmb();
 	} else
 		status = data->rpc_status;
@@ -2172,7 +2074,7 @@ static void nfs4_open_prepare(struct rpc_task *task, void *calldata)
 		nfs_copy_fh(&data->o_res.fh, data->o_arg.fh);
 	}
 	data->timestamp = jiffies;
-	if (nfs4_setup_sequence(data->o_arg.server,
+	if (nfs4_setup_sequence(data->o_arg.server->nfs_client,
 				&data->o_arg.seq_args,
 				&data->o_res.seq_res,
 				task) != 0)
@@ -2225,7 +2127,7 @@ static void nfs4_open_done(struct rpc_task *task, void *calldata)
 		if (!(data->o_res.rflags & NFS4_OPEN_RESULT_CONFIRM))
 			nfs_confirm_seqid(&data->owner->so_seqid, 0);
 	}
-	data->rpc_done = 1;
+	data->rpc_done = true;
 }
 
 static void nfs4_open_release(void *calldata)
@@ -2234,7 +2136,7 @@ static void nfs4_open_release(void *calldata)
 	struct nfs4_state *state = NULL;
 
 	/* If this request hasn't been cancelled, do nothing */
-	if (data->cancelled == 0)
+	if (!data->cancelled)
 		goto out_free;
 	/* In case of error, no cleanup! */
 	if (data->rpc_status != 0 || !data->rpc_done)
@@ -2280,24 +2182,24 @@ static int nfs4_run_open_task(struct nfs4_opendata *data, int isrecover)
 
 	nfs4_init_sequence(&o_arg->seq_args, &o_res->seq_res, 1);
 	kref_get(&data->kref);
-	data->rpc_done = 0;
+	data->rpc_done = false;
 	data->rpc_status = 0;
-	data->cancelled = 0;
-	data->is_recover = 0;
+	data->cancelled = false;
+	data->is_recover = false;
 	if (isrecover) {
 		nfs4_set_sequence_privileged(&o_arg->seq_args);
-		data->is_recover = 1;
+		data->is_recover = true;
 	}
 	task = rpc_run_task(&task_setup_data);
-        if (IS_ERR(task))
-                return PTR_ERR(task);
-        status = nfs4_wait_for_completion_rpc_task(task);
-        if (status != 0) {
-                data->cancelled = 1;
-                smp_wmb();
-        } else
-                status = data->rpc_status;
-        rpc_put_task(task);
+	if (IS_ERR(task))
+		return PTR_ERR(task);
+	status = rpc_wait_for_completion_task(task);
+	if (status != 0) {
+		data->cancelled = true;
+		smp_wmb();
+	} else
+		status = data->rpc_status;
+	rpc_put_task(task);
 
 	return status;
 }
@@ -2306,7 +2208,7 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data)
 {
 	struct inode *dir = d_inode(data->dir);
 	struct nfs_openres *o_res = &data->o_res;
-        int status;
+	int status;
 
 	status = nfs4_run_open_task(data, 1);
 	if (status != 0 || !data->rpc_done)
@@ -2314,11 +2216,8 @@ static int _nfs4_recover_proc_open(struct nfs4_opendata *data)
 
 	nfs_fattr_map_and_free_names(NFS_SERVER(dir), &data->f_attr);
 
-	if (o_res->rflags & NFS4_OPEN_RESULT_CONFIRM) {
+	if (o_res->rflags & NFS4_OPEN_RESULT_CONFIRM)
 		status = _nfs4_proc_open_confirm(data);
-		if (status != 0)
-			return status;
-	}
 
 	return status;
 }
@@ -2363,8 +2262,6 @@ static int nfs4_opendata_access(struct rpc_cred *cred,
 	if ((mask & ~cache.mask & (MAY_READ | MAY_EXEC)) == 0)
 		return 0;
 
-	/* even though OPEN succeeded, access is denied. Close the file */
-	nfs4_close_state(state, fmode);
 	return -EACCES;
 }
 
@@ -2393,9 +2290,9 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 
 	if (o_arg->open_flags & O_CREAT) {
 		if (o_arg->open_flags & O_EXCL)
-			data->file_created = 1;
+			data->file_created = true;
 		else if (o_res->cinfo.before != o_res->cinfo.after)
-			data->file_created = 1;
+			data->file_created = true;
 		if (data->file_created || dir->i_version != o_res->cinfo.after)
 			update_changeattr(dir, &o_res->cinfo,
 					o_res->f_attr->time_start);
@@ -2407,16 +2304,13 @@ static int _nfs4_proc_open(struct nfs4_opendata *data)
 		if (status != 0)
 			return status;
 	}
-	if (!(o_res->f_attr->valid & NFS_ATTR_FATTR))
+	if (!(o_res->f_attr->valid & NFS_ATTR_FATTR)) {
+		nfs4_sequence_free_slot(&o_res->seq_res);
 		nfs4_proc_getattr(server, &o_res->fh, o_res->f_attr, o_res->f_label);
+	}
 	return 0;
 }
 
-static int nfs4_recover_expired_lease(struct nfs_server *server)
-{
-	return nfs4_client_recover_expired_lease(server->nfs_client);
-}
-
 /*
  * OPEN_EXPIRED:
  * 	reclaim state on the server after a network partition.
@@ -2554,17 +2448,14 @@ static void nfs41_check_delegation_stateid(struct nfs4_state *state)
 	}
 
 	nfs4_stateid_copy(&stateid, &delegation->stateid);
-	if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags)) {
+	if (test_bit(NFS_DELEGATION_REVOKED, &delegation->flags) ||
+		!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED,
+			&delegation->flags)) {
 		rcu_read_unlock();
 		nfs_finish_clear_delegation_stateid(state, &stateid);
 		return;
 	}
 
-	if (!test_and_clear_bit(NFS_DELEGATION_TEST_EXPIRED, &delegation->flags)) {
-		rcu_read_unlock();
-		return;
-	}
-
 	cred = get_rpccred(delegation->cred);
 	rcu_read_unlock();
 	status = nfs41_test_and_free_expired_stateid(server, &stateid, cred);
@@ -2701,7 +2592,8 @@ static inline void nfs4_exclusive_attrset(struct nfs4_opendata *opendata,
 
 	/* Except MODE, it seems harmless of setting twice. */
 	if (opendata->o_arg.createmode != NFS4_CREATE_EXCLUSIVE &&
-		attrset[1] & FATTR4_WORD1_MODE)
+		(attrset[1] & FATTR4_WORD1_MODE ||
+		 attrset[2] & FATTR4_WORD2_MODE_UMASK))
 		sattr->ia_valid &= ~ATTR_MODE;
 
 	if (attrset[2] & FATTR4_WORD2_SECURITY_LABEL)
@@ -2730,6 +2622,7 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	ret = PTR_ERR(state);
 	if (IS_ERR(state))
 		goto out;
+	ctx->state = state;
 	if (server->caps & NFS_CAP_POSIX_LOCK)
 		set_bit(NFS_STATE_POSIX_LOCKS, &state->flags);
 	if (opendata->o_res.rflags & NFS4_OPEN_RESULT_MAY_NOTIFY_LOCK)
@@ -2755,7 +2648,6 @@ static int _nfs4_open_and_get_state(struct nfs4_opendata *opendata,
 	if (ret != 0)
 		goto out;
 
-	ctx->state = state;
 	if (d_inode(dentry) == state->inode) {
 		nfs_inode_attach_open_context(ctx);
 		if (read_seqcount_retry(&sp->so_reclaim_seqcount, seq))
@@ -2794,7 +2686,7 @@ static int _nfs4_do_open(struct inode *dir,
 		dprintk("nfs4_do_open: nfs4_get_state_owner failed!\n");
 		goto out_err;
 	}
-	status = nfs4_recover_expired_lease(server);
+	status = nfs4_client_recover_expired_lease(server->nfs_client);
 	if (status != 0)
 		goto err_put_state_owner;
 	if (d_really_is_positive(dentry))
@@ -2940,12 +2832,12 @@ static int _nfs4_do_setattr(struct inode *inode,
 			    struct nfs_open_context *ctx)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
-        struct rpc_message msg = {
+	struct rpc_message msg = {
 		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_SETATTR],
 		.rpc_argp	= arg,
 		.rpc_resp	= res,
 		.rpc_cred	= cred,
-        };
+	};
 	struct rpc_cred *delegation_cred = NULL;
 	unsigned long timestamp = jiffies;
 	fmode_t fmode;
@@ -2993,18 +2885,18 @@ static int nfs4_do_setattr(struct inode *inode, struct rpc_cred *cred,
 {
 	struct nfs_server *server = NFS_SERVER(inode);
 	struct nfs4_state *state = ctx ? ctx->state : NULL;
-        struct nfs_setattrargs  arg = {
-                .fh             = NFS_FH(inode),
-                .iap            = sattr,
+	struct nfs_setattrargs	arg = {
+		.fh		= NFS_FH(inode),
+		.iap		= sattr,
 		.server		= server,
 		.bitmask = server->attr_bitmask,
 		.label		= ilabel,
-        };
-        struct nfs_setattrres  res = {
+	};
+	struct nfs_setattrres  res = {
 		.fattr		= fattr,
 		.label		= olabel,
 		.server		= server,
-        };
+	};
 	struct nfs4_exception exception = {
 		.state = state,
 		.inode = inode,
@@ -3118,7 +3010,7 @@ static void nfs4_close_done(struct rpc_task *task, void *data)
 		}
 	}
 
-        /* hmm. we are done with the inode, and in the process of freeing
+	/* hmm. we are done with the inode, and in the process of freeing
 	 * the state_owner. we keep this around to process errors
 	 */
 	switch (task->tk_status) {
@@ -3234,7 +3126,7 @@ static void nfs4_close_prepare(struct rpc_task *task, void *data)
 	else if (calldata->arg.bitmask == NULL)
 		calldata->res.fattr = NULL;
 	calldata->timestamp = jiffies;
-	if (nfs4_setup_sequence(NFS_SERVER(inode),
+	if (nfs4_setup_sequence(NFS_SERVER(inode)->nfs_client,
 				&calldata->arg.seq_args,
 				&calldata->res.seq_res,
 				task) != 0)
@@ -3380,6 +3272,7 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 		.rpc_resp = &res,
 	};
 	int status;
+	int i;
 
 	bitmask[0] = FATTR4_WORD0_SUPPORTED_ATTRS |
 		     FATTR4_WORD0_FH_EXPIRE_TYPE |
@@ -3445,8 +3338,13 @@ static int _nfs4_server_capabilities(struct nfs_server *server, struct nfs_fh *f
 		server->cache_consistency_bitmask[0] &= FATTR4_WORD0_CHANGE|FATTR4_WORD0_SIZE;
 		server->cache_consistency_bitmask[1] &= FATTR4_WORD1_TIME_METADATA|FATTR4_WORD1_TIME_MODIFY;
 		server->cache_consistency_bitmask[2] = 0;
+
+		/* Avoid a regression due to buggy server */
+		for (i = 0; i < ARRAY_SIZE(res.exclcreat_bitmask); i++)
+			res.exclcreat_bitmask[i] &= res.attr_bitmask[i];
 		memcpy(server->exclcreat_bitmask, res.exclcreat_bitmask,
 			sizeof(server->exclcreat_bitmask));
+
 		server->acl_bitmask = res.acl_bitmask;
 		server->fh_expire_type = res.fh_expire_type;
 	}
@@ -3522,16 +3420,11 @@ static int nfs4_lookup_root_sec(struct nfs_server *server, struct nfs_fh *fhandl
 		.pseudoflavor = flavor,
 	};
 	struct rpc_auth *auth;
-	int ret;
 
 	auth = rpcauth_create(&auth_args, server->client);
-	if (IS_ERR(auth)) {
-		ret = -EACCES;
-		goto out;
-	}
-	ret = nfs4_lookup_root(server, fhandle, info);
-out:
-	return ret;
+	if (IS_ERR(auth))
+		return -EACCES;
+	return nfs4_lookup_root(server, fhandle, info);
 }
 
 /*
@@ -3913,6 +3806,54 @@ nfs4_proc_lookup_mountpoint(struct inode *dir, const struct qstr *name,
 	return (client == NFS_CLIENT(dir)) ? rpc_clone_client(client) : client;
 }
 
+static int _nfs4_proc_lookupp(struct inode *inode,
+		struct nfs_fh *fhandle, struct nfs_fattr *fattr,
+		struct nfs4_label *label)
+{
+	struct rpc_clnt *clnt = NFS_CLIENT(inode);
+	struct nfs_server *server = NFS_SERVER(inode);
+	int		       status;
+	struct nfs4_lookupp_arg args = {
+		.bitmask = server->attr_bitmask,
+		.fh = NFS_FH(inode),
+	};
+	struct nfs4_lookupp_res res = {
+		.server = server,
+		.fattr = fattr,
+		.label = label,
+		.fh = fhandle,
+	};
+	struct rpc_message msg = {
+		.rpc_proc = &nfs4_procedures[NFSPROC4_CLNT_LOOKUPP],
+		.rpc_argp = &args,
+		.rpc_resp = &res,
+	};
+
+	args.bitmask = nfs4_bitmask(server, label);
+
+	nfs_fattr_init(fattr);
+
+	dprintk("NFS call  lookupp ino=0x%lx\n", inode->i_ino);
+	status = nfs4_call_sync(clnt, server, &msg, &args.seq_args,
+				&res.seq_res, 0);
+	dprintk("NFS reply lookupp: %d\n", status);
+	return status;
+}
+
+static int nfs4_proc_lookupp(struct inode *inode, struct nfs_fh *fhandle,
+			     struct nfs_fattr *fattr, struct nfs4_label *label)
+{
+	struct nfs4_exception exception = { };
+	int err;
+	do {
+		err = _nfs4_proc_lookupp(inode, fhandle, fattr, label);
+		trace_nfs4_lookupp(inode, err);
+		err = nfs4_handle_exception(NFS_SERVER(inode), err,
+				&exception);
+	} while (exception.retry);
+	return err;
+}
+
 static int _nfs4_proc_access(struct inode *inode, struct nfs_access_entry *entry)
 {
 	struct nfs_server *server = NFS_SERVER(inode);
@@ -4114,7 +4055,7 @@ static void nfs4_proc_unlink_setup(struct rpc_message *msg, struct inode *dir)
 
 static void nfs4_proc_unlink_rpc_prepare(struct rpc_task *task, struct nfs_unlinkdata *data)
 {
-	nfs4_setup_sequence(NFS_SB(data->dentry->d_sb),
+	nfs4_setup_sequence(NFS_SB(data->dentry->d_sb)->nfs_client,
 			&data->args.seq_args,
 			&data->res.seq_res,
 			task);
@@ -4148,7 +4089,7 @@ static void nfs4_proc_rename_setup(struct rpc_message *msg, struct inode *dir)
 
 static void nfs4_proc_rename_rpc_prepare(struct rpc_task *task, struct nfs_renamedata *data)
 {
-	nfs4_setup_sequence(NFS_SERVER(data->old_dir),
+	nfs4_setup_sequence(NFS_SERVER(data->old_dir)->nfs_client,
 			&data->args.seq_args,
 			&data->res.seq_res,
 			task);
@@ -4383,7 +4324,7 @@ static int nfs4_proc_mkdir(struct inode *dir, struct dentry *dentry,
 }
 
 static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-		u64 cookie, struct page **pages, unsigned int count, int plus)
+		u64 cookie, struct page **pages, unsigned int count, bool plus)
 {
 	struct inode		*dir = d_inode(dentry);
 	struct nfs4_readdir_arg args = {
@@ -4421,7 +4362,7 @@ static int _nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
 }
 
 static int nfs4_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-		u64 cookie, struct page **pages, unsigned int count, int plus)
+		u64 cookie, struct page **pages, unsigned int count, bool plus)
 {
 	struct nfs4_exception exception = { };
 	int err;
@@ -4723,14 +4664,14 @@ static void nfs4_proc_read_setup(struct nfs_pgio_header *hdr,
 static int nfs4_proc_pgio_rpc_prepare(struct rpc_task *task,
 				      struct nfs_pgio_header *hdr)
 {
-	if (nfs4_setup_sequence(NFS_SERVER(hdr->inode),
+	if (nfs4_setup_sequence(NFS_SERVER(hdr->inode)->nfs_client,
 			&hdr->args.seq_args,
 			&hdr->res.seq_res,
 			task))
 		return 0;
 	if (nfs4_set_rw_stateid(&hdr->args.stateid, hdr->args.context,
 				hdr->args.lock_context,
-				hdr->rw_ops->rw_mode) == -EIO)
+				hdr->rw_mode) == -EIO)
 		return -EIO;
 	if (unlikely(test_bit(NFS_CONTEXT_BAD, &hdr->args.context->flags)))
 		return -EIO;
@@ -4822,7 +4763,7 @@ static void nfs4_proc_write_setup(struct nfs_pgio_header *hdr,
 
 static void nfs4_proc_commit_rpc_prepare(struct rpc_task *task, struct nfs_commit_data *data)
 {
-	nfs4_setup_sequence(NFS_SERVER(data->inode),
+	nfs4_setup_sequence(NFS_SERVER(data->inode)->nfs_client,
 			&data->args.seq_args,
 			&data->res.seq_res,
 			task);
@@ -4924,8 +4865,10 @@ static int nfs4_proc_async_renew(struct nfs_client *clp, struct rpc_cred *cred,
 	if (!atomic_inc_not_zero(&clp->cl_count))
 		return -EIO;
 	data = kmalloc(sizeof(*data), GFP_NOFS);
-	if (data == NULL)
+	if (data == NULL) {
+		nfs_put_client(clp);
 		return -ENOMEM;
+	}
 	data->client = clp;
 	data->timestamp = jiffies;
 	return rpc_call_async(clp->cl_rpcclient, &msg, RPC_TASK_TIMEOUT,
@@ -4975,8 +4918,8 @@ static int buf_to_pages_noslab(const void *buf, size_t buflen,
 		if (newpage == NULL)
 			goto unwind;
 		memcpy(page_address(newpage), buf, len);
-                buf += len;
-                buflen -= len;
+		buf += len;
+		buflen -= len;
 		*pages++ = newpage;
 		rc++;
 	} while (buflen != 0);
@@ -5069,7 +5012,7 @@ out:
  */
 static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t buflen)
 {
-	struct page *pages[NFS4ACL_MAXPAGES] = {NULL, };
+	struct page *pages[NFS4ACL_MAXPAGES + 1] = {NULL, };
 	struct nfs_getaclargs args = {
 		.fh = NFS_FH(inode),
 		.acl_pages = pages,
@@ -5083,13 +5026,9 @@ static ssize_t __nfs4_get_acl_uncached(struct inode *inode, void *buf, size_t bu
 		.rpc_argp = &args,
 		.rpc_resp = &res,
 	};
-	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE);
+	unsigned int npages = DIV_ROUND_UP(buflen, PAGE_SIZE) + 1;
 	int ret = -ENOMEM, i;
 
-	/* As long as we're doing a round trip to the server anyway,
-	 * let's be prepared for a page of acl data. */
-	if (npages == 0)
-		npages = 1;
 	if (npages > ARRAY_SIZE(pages))
 		return -ERANGE;
 
@@ -5299,8 +5238,8 @@ static int _nfs4_do_set_security_label(struct inode *inode,
 	struct nfs_server *server = NFS_SERVER(inode);
 	const u32 bitmask[3] = { 0, 0, FATTR4_WORD2_SECURITY_LABEL };
 	struct nfs_setattrargs arg = {
-		.fh             = NFS_FH(inode),
-		.iap            = &sattr,
+		.fh		= NFS_FH(inode),
+		.iap		= &sattr,
 		.server		= server,
 		.bitmask	= bitmask,
 		.label		= ilabel,
@@ -5311,9 +5250,9 @@ static int _nfs4_do_set_security_label(struct inode *inode,
 		.server		= server,
 	};
 	struct rpc_message msg = {
-		.rpc_proc       = &nfs4_procedures[NFSPROC4_CLNT_SETATTR],
-		.rpc_argp       = &arg,
-		.rpc_resp       = &res,
+		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_SETATTR],
+		.rpc_argp	= &arg,
+		.rpc_resp	= &res,
 	};
 	int status;
 
@@ -5747,7 +5686,7 @@ static void nfs4_delegreturn_prepare(struct rpc_task *task, void *data)
 	if (!d_data->lr.roc && nfs4_wait_on_layoutreturn(d_data->inode, task))
 		return;
 
-	nfs4_setup_sequence(d_data->res.server,
+	nfs4_setup_sequence(d_data->res.server->nfs_client,
 			&d_data->args.seq_args,
 			&d_data->res.seq_res,
 			task);
@@ -5817,7 +5756,7 @@ static int _nfs4_proc_delegreturn(struct inode *inode, struct rpc_cred *cred, co
 		return PTR_ERR(task);
 	if (!issync)
 		goto out;
-	status = nfs4_wait_for_completion_rpc_task(task);
+	status = rpc_wait_for_completion_task(task);
 	if (status != 0)
 		goto out;
 	status = data->rpc_status;
@@ -5859,8 +5798,8 @@ static int _nfs4_proc_getlk(struct nfs4_state *state, int cmd, struct file_lock
 	};
 	struct rpc_message msg = {
 		.rpc_proc	= &nfs4_procedures[NFSPROC4_CLNT_LOCKT],
-		.rpc_argp       = &arg,
-		.rpc_resp       = &res,
+		.rpc_argp	= &arg,
+		.rpc_resp	= &res,
 		.rpc_cred	= state->owner->so_cred,
 	};
 	struct nfs4_lock_state *lsp;
@@ -5906,6 +5845,7 @@ struct nfs4_unlockdata {
 	struct nfs_locku_res res;
 	struct nfs4_lock_state *lsp;
 	struct nfs_open_context *ctx;
+	struct nfs_lock_context *l_ctx;
 	struct file_lock fl;
 	struct nfs_server *server;
 	unsigned long timestamp;
@@ -5930,6 +5870,7 @@ static struct nfs4_unlockdata *nfs4_alloc_unlockdata(struct file_lock *fl,
 	atomic_inc(&lsp->ls_count);
 	/* Ensure we don't close file until we're done freeing locks! */
 	p->ctx = get_nfs_open_context(ctx);
+	p->l_ctx = nfs_get_lock_context(ctx);
 	memcpy(&p->fl, fl, sizeof(p->fl));
 	p->server = NFS_SERVER(inode);
 	return p;
@@ -5940,6 +5881,7 @@ static void nfs4_locku_release_calldata(void *data)
 	struct nfs4_unlockdata *calldata = data;
 	nfs_free_seqid(calldata->arg.seqid);
 	nfs4_put_lock_state(calldata->lsp);
+	nfs_put_lock_context(calldata->l_ctx);
 	put_nfs_open_context(calldata->ctx);
 	kfree(calldata);
 }
@@ -5981,6 +5923,10 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data)
 {
 	struct nfs4_unlockdata *calldata = data;
 
+	if (test_bit(NFS_CONTEXT_UNLOCK, &calldata->l_ctx->open_context->flags) &&
+		nfs_async_iocounter_wait(task, calldata->l_ctx))
+		return;
+
 	if (nfs_wait_on_sequence(calldata->arg.seqid, task) != 0)
 		goto out_wait;
 	nfs4_stateid_copy(&calldata->arg.stateid, &calldata->lsp->ls_stateid);
@@ -5989,7 +5935,7 @@ static void nfs4_locku_prepare(struct rpc_task *task, void *data)
 		goto out_no_action;
 	}
 	calldata->timestamp = jiffies;
-	if (nfs4_setup_sequence(calldata->server,
+	if (nfs4_setup_sequence(calldata->server->nfs_client,
 				&calldata->arg.seq_args,
 				&calldata->res.seq_res,
 				task) != 0)
@@ -6032,6 +5978,8 @@ static struct rpc_task *nfs4_do_unlck(struct file_lock *fl,
 	 * canceled lock is passed in, and it won't be an unlock.
 	 */
 	fl->fl_type = F_UNLCK;
+	if (fl->fl_flags & FL_CLOSE)
+		set_bit(NFS_CONTEXT_UNLOCK, &ctx->flags);
 
 	data = nfs4_alloc_unlockdata(fl, ctx, lsp, seqid);
 	if (data == NULL) {
@@ -6087,7 +6035,7 @@ static int nfs4_proc_unlck(struct nfs4_state *state, int cmd, struct file_lock *
 	status = PTR_ERR(task);
 	if (IS_ERR(task))
 		goto out;
-	status = nfs4_wait_for_completion_rpc_task(task);
+	status = rpc_wait_for_completion_task(task);
 	rpc_put_task(task);
 out:
 	request->fl_flags = fl_flags;
@@ -6174,7 +6122,7 @@ static void nfs4_lock_prepare(struct rpc_task *task, void *calldata)
 		goto out_release_open_seqid;
 	}
 	data->timestamp = jiffies;
-	if (nfs4_setup_sequence(data->server,
+	if (nfs4_setup_sequence(data->server->nfs_client,
 				&data->arg.seq_args,
 				&data->res.seq_res,
 				task) == 0)
@@ -6238,7 +6186,7 @@ static void nfs4_lock_release(void *calldata)
 
 	dprintk("%s: begin!\n", __func__);
 	nfs_free_seqid(data->arg.open_seqid);
-	if (data->cancelled != 0) {
+	if (data->cancelled) {
 		struct rpc_task *task;
 		task = nfs4_do_unlck(&data->fl, data->ctx, data->lsp,
 				data->arg.lock_seqid);
@@ -6314,14 +6262,14 @@ static int _nfs4_do_setlk(struct nfs4_state *state, int cmd, struct file_lock *f
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return PTR_ERR(task);
-	ret = nfs4_wait_for_completion_rpc_task(task);
+	ret = rpc_wait_for_completion_task(task);
 	if (ret == 0) {
 		ret = data->rpc_status;
 		if (ret)
 			nfs4_handle_setlk_error(data->server, data->lsp,
 					data->arg.new_lock_owner, ret);
 	} else
-		data->cancelled = 1;
+		data->cancelled = true;
 	rpc_put_task(task);
 	dprintk("%s: done, ret = %d!\n", __func__, ret);
 	trace_nfs4_set_lock(fl, state, &data->res.stateid, cmd, ret);
@@ -6393,8 +6341,7 @@ static int nfs41_lock_expired(struct nfs4_state *state, struct file_lock *reques
 	if (test_bit(NFS_LOCK_INITIALIZED, &lsp->ls_flags) ||
 	    test_bit(NFS_LOCK_LOST, &lsp->ls_flags))
 		return 0;
-	status = nfs4_lock_expired(state, request);
-	return status;
+	return nfs4_lock_expired(state, request);
 }
 #endif
 
@@ -6477,7 +6424,7 @@ struct nfs4_lock_waiter {
 };
 
 static int
-nfs4_wake_lock_waiter(wait_queue_t *wait, unsigned int mode, int flags, void *key)
+nfs4_wake_lock_waiter(wait_queue_entry_t *wait, unsigned int mode, int flags, void *key)
 {
 	int ret;
 	struct cb_notify_lock_args *cbnl = key;
@@ -6520,7 +6467,7 @@ nfs4_retry_setlk(struct nfs4_state *state, int cmd, struct file_lock *request)
 					   .inode = state->inode,
 					   .owner = &owner,
 					   .notified = false };
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 
 	/* Don't bother with waitqueue if we don't expect a callback */
 	if (!test_bit(NFS_STATE_MAY_NOTIFY_LOCK, &state->flags))
@@ -6570,9 +6517,6 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
 	ctx = nfs_file_open_context(filp);
 	state = ctx->state;
 
-	if (request->fl_start < 0 || request->fl_end < 0)
-		return -EINVAL;
-
 	if (IS_GETLK(cmd)) {
 		if (state != NULL)
 			return nfs4_proc_getlk(state, F_GETLK, request);
@@ -6595,20 +6539,6 @@ nfs4_proc_lock(struct file *filp, int cmd, struct file_lock *request)
 	    !test_bit(NFS_STATE_POSIX_LOCKS, &state->flags))
 		return -ENOLCK;
 
-	/*
-	 * Don't rely on the VFS having checked the file open mode,
-	 * since it won't do this for flock() locks.
-	 */
-	switch (request->fl_type) {
-	case F_RDLCK:
-		if (!(filp->f_mode & FMODE_READ))
-			return -EBADF;
-		break;
-	case F_WRLCK:
-		if (!(filp->f_mode & FMODE_WRITE))
-			return -EBADF;
-	}
-
 	status = nfs4_set_lock_state(state, request);
 	if (status != 0)
 		return status;
@@ -6640,8 +6570,8 @@ static void nfs4_release_lockowner_prepare(struct rpc_task *task, void *calldata
 {
 	struct nfs_release_lockowner_data *data = calldata;
 	struct nfs_server *server = data->server;
-	nfs40_setup_sequence(server->nfs_client->cl_slot_tbl,
-			     &data->args.seq_args, &data->res.seq_res, task);
+	nfs4_setup_sequence(server->nfs_client, &data->args.seq_args,
+			   &data->res.seq_res, task);
 	data->args.lock_owner.clientid = server->nfs_client->cl_clientid;
 	data->timestamp = jiffies;
 }
@@ -7232,11 +7162,9 @@ static bool
 nfs41_same_server_scope(struct nfs41_server_scope *a,
 			struct nfs41_server_scope *b)
 {
-	if (a->server_scope_sz == b->server_scope_sz &&
-	    memcmp(a->server_scope, b->server_scope, a->server_scope_sz) == 0)
-		return true;
-
-	return false;
+	if (a->server_scope_sz != b->server_scope_sz)
+		return false;
+	return memcmp(a->server_scope, b->server_scope, a->server_scope_sz) == 0;
 }
 
 static void
@@ -7282,8 +7210,6 @@ int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt,
 	};
 	struct rpc_task *task;
 
-	dprintk("--> %s\n", __func__);
-
 	nfs4_copy_sessionid(&args.sessionid, &clp->cl_session->sess_id);
 	if (!(clp->cl_session->flags & SESSION4_BACK_CHAN))
 		args.dir = NFS4_CDFC4_FORE;
@@ -7303,24 +7229,20 @@ int nfs4_proc_bind_one_conn_to_session(struct rpc_clnt *clnt,
 		if (memcmp(res.sessionid.data,
 		    clp->cl_session->sess_id.data, NFS4_MAX_SESSIONID_LEN)) {
 			dprintk("NFS: %s: Session ID mismatch\n", __func__);
-			status = -EIO;
-			goto out;
+			return -EIO;
 		}
 		if ((res.dir & args.dir) != res.dir || res.dir == 0) {
 			dprintk("NFS: %s: Unexpected direction from server\n",
 				__func__);
-			status = -EIO;
-			goto out;
+			return -EIO;
 		}
 		if (res.use_conn_in_rdma_mode != args.use_conn_in_rdma_mode) {
 			dprintk("NFS: %s: Server returned RDMA mode = true\n",
 				__func__);
-			status = -EIO;
-			goto out;
+			return -EIO;
 		}
 	}
-out:
-	dprintk("<-- %s status= %d\n", __func__, status);
+
 	return status;
 }
 
@@ -7505,12 +7427,11 @@ static void nfs4_exchange_id_done(struct rpc_task *task, void *data)
 	if (status == 0) {
 		clp->cl_clientid = cdata->res.clientid;
 		clp->cl_exchange_flags = cdata->res.flags;
+		clp->cl_seqid = cdata->res.seqid;
 		/* Client ID is not confirmed */
-		if (!(cdata->res.flags & EXCHGID4_FLAG_CONFIRMED_R)) {
+		if (!(cdata->res.flags & EXCHGID4_FLAG_CONFIRMED_R))
 			clear_bit(NFS4_SESSION_ESTABLISHED,
-			&clp->cl_session->session_state);
-			clp->cl_seqid = cdata->res.seqid;
-		}
+				  &clp->cl_session->session_state);
 
 		kfree(clp->cl_serverowner);
 		clp->cl_serverowner = cdata->res.server_owner;
@@ -7549,11 +7470,11 @@ static void nfs4_exchange_id_release(void *data)
 	struct nfs41_exchange_id_data *cdata =
 					(struct nfs41_exchange_id_data *)data;
 
-	nfs_put_client(cdata->args.client);
 	if (cdata->xprt) {
 		xprt_put(cdata->xprt);
 		rpc_clnt_xprt_switch_put(cdata->args.client->cl_rpcclient);
 	}
+	nfs_put_client(cdata->args.client);
 	kfree(cdata->res.impl_id);
 	kfree(cdata->res.server_scope);
 	kfree(cdata->res.server_owner);
@@ -7586,15 +7507,16 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 	};
 	struct nfs41_exchange_id_data *calldata;
 	struct rpc_task *task;
-	int status = -EIO;
+	int status;
 
 	if (!atomic_inc_not_zero(&clp->cl_count))
-		goto out;
+		return -EIO;
 
-	status = -ENOMEM;
 	calldata = kzalloc(sizeof(*calldata), GFP_NOFS);
-	if (!calldata)
-		goto out;
+	if (!calldata) {
+		nfs_put_client(clp);
+		return -ENOMEM;
+	}
 
 	if (!xprt)
 		nfs4_init_boot_verifier(clp, &verifier);
@@ -7603,10 +7525,6 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 	if (status)
 		goto out_calldata;
 
-	dprintk("NFS call  exchange_id auth=%s, '%s'\n",
-		clp->cl_rpcclient->cl_auth->au_ops->au_name,
-		clp->cl_owner_id);
-
 	calldata->res.server_owner = kzalloc(sizeof(struct nfs41_server_owner),
 						GFP_NOFS);
 	status = -ENOMEM;
@@ -7660,10 +7578,8 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 	task_setup_data.callback_data = calldata;
 
 	task = rpc_run_task(&task_setup_data);
-	if (IS_ERR(task)) {
-	status = PTR_ERR(task);
-		goto out_impl_id;
-	}
+	if (IS_ERR(task))
+		return PTR_ERR(task);
 
 	if (!xprt) {
 		status = rpc_wait_for_completion_task(task);
@@ -7674,13 +7590,6 @@ static int _nfs4_proc_exchange_id(struct nfs_client *clp, struct rpc_cred *cred,
 
 	rpc_put_task(task);
 out:
-	if (clp->cl_implid != NULL)
-		dprintk("NFS reply exchange_id: Server Implementation ID: "
-			"domain: %s, name: %s, date: %llu,%u\n",
-			clp->cl_implid->domain, clp->cl_implid->name,
-			clp->cl_implid->date.seconds,
-			clp->cl_implid->date.nseconds);
-	dprintk("NFS reply exchange_id: %d\n", status);
 	return status;
 
 out_impl_id:
@@ -7691,6 +7600,7 @@ out_server_owner:
 	kfree(calldata->res.server_owner);
 out_calldata:
 	kfree(calldata);
+	nfs_put_client(clp);
 	goto out;
 }
 
@@ -7831,7 +7741,7 @@ static void nfs4_get_lease_time_prepare(struct rpc_task *task,
 	dprintk("--> %s\n", __func__);
 	/* just setup sequence, do not trigger session recovery
 	   since we're invoked within one */
-	nfs41_setup_sequence(data->clp->cl_session,
+	nfs4_setup_sequence(data->clp,
 			&data->args->la_seq_args,
 			&data->res->lr_seq_res,
 			task);
@@ -7897,17 +7807,13 @@ int nfs4_proc_get_lease_time(struct nfs_client *clp, struct nfs_fsinfo *fsinfo)
 
 	nfs4_init_sequence(&args.la_seq_args, &res.lr_seq_res, 0);
 	nfs4_set_sequence_privileged(&args.la_seq_args);
-	dprintk("--> %s\n", __func__);
 	task = rpc_run_task(&task_setup);
 
 	if (IS_ERR(task))
-		status = PTR_ERR(task);
-	else {
-		status = task->tk_status;
-		rpc_put_task(task);
-	}
-	dprintk("<-- %s return %d\n", __func__, status);
+		return PTR_ERR(task);
 
+	status = task->tk_status;
+	rpc_put_task(task);
 	return status;
 }
 
@@ -8202,7 +8108,7 @@ static void nfs41_sequence_prepare(struct rpc_task *task, void *data)
 	args = task->tk_msg.rpc_argp;
 	res = task->tk_msg.rpc_resp;
 
-	nfs41_setup_sequence(clp->cl_session, args, res, task);
+	nfs4_setup_sequence(clp, args, res, task);
 }
 
 static const struct rpc_call_ops nfs41_sequence_ops = {
@@ -8290,7 +8196,7 @@ static void nfs4_reclaim_complete_prepare(struct rpc_task *task, void *data)
 {
 	struct nfs4_reclaim_complete_data *calldata = data;
 
-	nfs41_setup_sequence(calldata->clp->cl_session,
+	nfs4_setup_sequence(calldata->clp,
 			&calldata->arg.seq_args,
 			&calldata->res.seq_res,
 			task);
@@ -8308,6 +8214,12 @@ static int nfs41_reclaim_complete_handle_errors(struct rpc_task *task, struct nf
 		/* fall through */
 	case -NFS4ERR_RETRY_UNCACHED_REP:
 		return -EAGAIN;
+	case -NFS4ERR_BADSESSION:
+	case -NFS4ERR_DEADSESSION:
+	case -NFS4ERR_CONN_NOT_BOUND_TO_SESSION:
+		nfs4_schedule_session_recovery(clp->cl_session,
+				task->tk_status);
+		break;
 	default:
 		nfs4_schedule_lease_recovery(clp);
 	}
@@ -8382,11 +8294,10 @@ static int nfs41_proc_reclaim_complete(struct nfs_client *clp,
 		status = PTR_ERR(task);
 		goto out;
 	}
-	status = nfs4_wait_for_completion_rpc_task(task);
+	status = rpc_wait_for_completion_task(task);
 	if (status == 0)
 		status = task->tk_status;
 	rpc_put_task(task);
-	return 0;
 out:
 	dprintk("<-- %s status=%d\n", __func__, status);
 	return status;
@@ -8397,10 +8308,9 @@ nfs4_layoutget_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_layoutget *lgp = calldata;
 	struct nfs_server *server = NFS_SERVER(lgp->args.inode);
-	struct nfs4_session *session = nfs4_get_session(server);
 
 	dprintk("--> %s\n", __func__);
-	nfs41_setup_sequence(session, &lgp->args.seq_args,
+	nfs4_setup_sequence(server->nfs_client, &lgp->args.seq_args,
 				&lgp->res.seq_res, task);
 	dprintk("<-- %s\n", __func__);
 }
@@ -8486,6 +8396,7 @@ nfs4_layoutget_handle_exception(struct rpc_task *task,
 		 */
 		pnfs_mark_layout_stateid_invalid(lo, &head);
 		spin_unlock(&inode->i_lock);
+		nfs_commit_inode(inode, 0);
 		pnfs_free_lseg_list(&head);
 		status = -EAGAIN;
 		goto out;
@@ -8556,6 +8467,7 @@ static void nfs4_layoutget_release(void *calldata)
 	size_t max_pages = max_response_pages(server);
 
 	dprintk("--> %s\n", __func__);
+	nfs4_sequence_free_slot(&lgp->res.seq_res);
 	nfs4_free_pages(lgp->args.layout.pages, max_pages);
 	pnfs_put_layout_hdr(NFS_I(inode)->layout);
 	put_nfs_open_context(lgp->args.ctx);
@@ -8615,7 +8527,7 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags)
 	task = rpc_run_task(&task_setup_data);
 	if (IS_ERR(task))
 		return ERR_CAST(task);
-	status = nfs4_wait_for_completion_rpc_task(task);
+	status = rpc_wait_for_completion_task(task);
 	if (status == 0) {
 		status = nfs4_layoutget_handle_exception(task, lgp, &exception);
 		*timeout = exception.timeout;
@@ -8630,7 +8542,6 @@ nfs4_proc_layoutget(struct nfs4_layoutget *lgp, long *timeout, gfp_t gfp_flags)
 	/* if layoutp->len is 0, nfs4_layoutget_prepare called rpc_exit */
 	if (status == 0 && lgp->res.layoutp->len)
 		lseg = pnfs_layout_process(lgp);
-	nfs4_sequence_free_slot(&lgp->res.seq_res);
 	rpc_put_task(task);
 	dprintk("<-- %s status=%d\n", __func__, status);
 	if (status)
@@ -8644,7 +8555,7 @@ nfs4_layoutreturn_prepare(struct rpc_task *task, void *calldata)
 	struct nfs4_layoutreturn *lrp = calldata;
 
 	dprintk("--> %s\n", __func__);
-	nfs41_setup_sequence(lrp->clp->cl_session,
+	nfs4_setup_sequence(lrp->clp,
 			&lrp->args.seq_args,
 			&lrp->res.seq_res,
 			task);
@@ -8794,9 +8705,8 @@ static void nfs4_layoutcommit_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs4_layoutcommit_data *data = calldata;
 	struct nfs_server *server = NFS_SERVER(data->args.inode);
-	struct nfs4_session *session = nfs4_get_session(server);
 
-	nfs41_setup_sequence(session,
+	nfs4_setup_sequence(server->nfs_client,
 			&data->args.seq_args,
 			&data->res.seq_res,
 			task);
@@ -9120,7 +9030,7 @@ struct nfs_free_stateid_data {
 static void nfs41_free_stateid_prepare(struct rpc_task *task, void *calldata)
 {
 	struct nfs_free_stateid_data *data = calldata;
-	nfs41_setup_sequence(nfs4_get_session(data->server),
+	nfs4_setup_sequence(data->server->nfs_client,
 			&data->args.seq_args,
 			&data->res.seq_res,
 			task);
@@ -9232,10 +9142,8 @@ static bool nfs41_match_stateid(const nfs4_stateid *s1,
 
 	if (s1->seqid == s2->seqid)
 		return true;
-	if (s1->seqid == 0 || s2->seqid == 0)
-		return true;
 
-	return false;
+	return s1->seqid == 0 || s2->seqid == 0;
 }
 
 #endif /* CONFIG_NFS_V4_1 */
@@ -9455,6 +9363,7 @@ const struct nfs_rpc_ops nfs_v4_clientops = {
 	.getattr	= nfs4_proc_getattr,
 	.setattr	= nfs4_proc_setattr,
 	.lookup		= nfs4_proc_lookup,
+	.lookupp	= nfs4_proc_lookupp,
 	.access		= nfs4_proc_access,
 	.readlink	= nfs4_proc_readlink,
 	.create		= nfs4_proc_create,
diff --git a/fs/nfs/nfs4renewd.c b/fs/nfs/nfs4renewd.c
index 82e77198d17e..1f8c2ae43a8d 100644
--- a/fs/nfs/nfs4renewd.c
+++ b/fs/nfs/nfs4renewd.c
@@ -153,7 +153,7 @@ void nfs4_set_lease_period(struct nfs_client *clp,
 	spin_unlock(&clp->cl_lock);
 
 	/* Cap maximum reconnect timeout at 1/2 lease period */
-	rpc_cap_max_reconnect_timeout(clp->cl_rpcclient, lease >> 1);
+	rpc_set_connect_timeout(clp->cl_rpcclient, lease, lease >> 1);
 }
 
 /*
diff --git a/fs/nfs/nfs4session.h b/fs/nfs/nfs4session.h
index dae385500005..dfae4880eacb 100644
--- a/fs/nfs/nfs4session.h
+++ b/fs/nfs/nfs4session.h
@@ -103,6 +103,11 @@ static inline bool nfs4_test_locked_slot(const struct nfs4_slot_table *tbl,
 	return !!test_bit(slotid, tbl->used_slots);
 }
 
+static inline struct nfs4_session *nfs4_get_session(const struct nfs_client *clp)
+{
+	return clp->cl_session;
+}
+
 #if defined(CONFIG_NFS_V4_1)
 extern void nfs41_set_target_slotid(struct nfs4_slot_table *tbl,
 		u32 target_highest_slotid);
@@ -170,6 +175,8 @@ static inline int nfs4_has_persistent_session(const struct nfs_client *clp)
 	return 0;
 }
 
+#define nfs_session_id_hash(session) (0)
+
 #endif /* defined(CONFIG_NFS_V4_1) */
 #endif /* IS_ENABLED(CONFIG_NFS_V4) */
 #endif /* __LINUX_FS_NFS_NFS4SESSION_H */
diff --git a/fs/nfs/nfs4state.c b/fs/nfs/nfs4state.c
index daeb94e3acd4..0378e2257ca7 100644
--- a/fs/nfs/nfs4state.c
+++ b/fs/nfs/nfs4state.c
@@ -352,11 +352,17 @@ int nfs41_discover_server_trunking(struct nfs_client *clp,
 	if (clp != *result)
 		return 0;
 
-	/* Purge state if the client id was established in a prior instance */
-	if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R)
-		set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
-	else
-		set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+	/*
+	 * Purge state if the client id was established in a prior
+	 * instance and the client id could not have arrived on the
+	 * server via Transparent State Migration.
+	 */
+	if (clp->cl_exchange_flags & EXCHGID4_FLAG_CONFIRMED_R) {
+		if (!test_bit(NFS_CS_TSM_POSSIBLE, &clp->cl_flags))
+			set_bit(NFS4CLNT_PURGE_STATE, &clp->cl_state);
+		else
+			set_bit(NFS4CLNT_LEASE_CONFIRM, &clp->cl_state);
+	}
 	nfs4_schedule_state_manager(clp);
 	status = nfs_wait_client_init_complete(clp);
 	if (status < 0)
@@ -868,7 +874,7 @@ static struct nfs4_lock_state *nfs4_get_lock_state(struct nfs4_state *state, fl_
 	
 	for(;;) {
 		spin_lock(&state->state_lock);
-		lsp = __nfs4_find_lock_state(state, owner, 0);
+		lsp = __nfs4_find_lock_state(state, owner, NULL);
 		if (lsp != NULL)
 			break;
 		if (new != NULL) {
@@ -1649,13 +1655,14 @@ static void nfs4_state_start_reclaim_reboot(struct nfs_client *clp)
 	nfs4_state_mark_reclaim_helper(clp, nfs4_state_mark_reclaim_reboot);
 }
 
-static void nfs4_reclaim_complete(struct nfs_client *clp,
+static int nfs4_reclaim_complete(struct nfs_client *clp,
 				 const struct nfs4_state_recovery_ops *ops,
 				 struct rpc_cred *cred)
 {
 	/* Notify the server we're done reclaiming our state */
 	if (ops->reclaim_complete)
-		(void)ops->reclaim_complete(clp, cred);
+		return ops->reclaim_complete(clp, cred);
+	return 0;
 }
 
 static void nfs4_clear_reclaim_server(struct nfs_server *server)
@@ -1702,13 +1709,16 @@ static void nfs4_state_end_reclaim_reboot(struct nfs_client *clp)
 {
 	const struct nfs4_state_recovery_ops *ops;
 	struct rpc_cred *cred;
+	int err;
 
 	if (!nfs4_state_clear_reclaim_reboot(clp))
 		return;
 	ops = clp->cl_mvops->reboot_recovery_ops;
 	cred = nfs4_get_clid_cred(clp);
-	nfs4_reclaim_complete(clp, ops, cred);
+	err = nfs4_reclaim_complete(clp, ops, cred);
 	put_rpccred(cred);
+	if (err == -NFS4ERR_CONN_NOT_BOUND_TO_SESSION)
+		set_bit(NFS4CLNT_RECLAIM_REBOOT, &clp->cl_state);
 }
 
 static void nfs4_state_start_reclaim_nograce(struct nfs_client *clp)
@@ -2130,6 +2140,8 @@ again:
 	put_rpccred(cred);
 	switch (status) {
 	case 0:
+	case -EINTR:
+	case -ERESTARTSYS:
 		break;
 	case -ETIMEDOUT:
 		if (clnt->cl_softrtry)
diff --git a/fs/nfs/nfs4trace.h b/fs/nfs/nfs4trace.h
index cfb8f7ce5cf6..be1da19c65d6 100644
--- a/fs/nfs/nfs4trace.h
+++ b/fs/nfs/nfs4trace.h
@@ -241,38 +241,6 @@ DEFINE_NFS4_CLIENTID_EVENT(nfs4_bind_conn_to_session);
 DEFINE_NFS4_CLIENTID_EVENT(nfs4_sequence);
 DEFINE_NFS4_CLIENTID_EVENT(nfs4_reclaim_complete);
 
-TRACE_EVENT(nfs4_setup_sequence,
-		TP_PROTO(
-			const struct nfs4_session *session,
-			const struct nfs4_sequence_args *args
-		),
-		TP_ARGS(session, args),
-
-		TP_STRUCT__entry(
-			__field(unsigned int, session)
-			__field(unsigned int, slot_nr)
-			__field(unsigned int, seq_nr)
-			__field(unsigned int, highest_used_slotid)
-		),
-
-		TP_fast_assign(
-			const struct nfs4_slot *sa_slot = args->sa_slot;
-			__entry->session = nfs_session_id_hash(&session->sess_id);
-			__entry->slot_nr = sa_slot->slot_nr;
-			__entry->seq_nr = sa_slot->seq_nr;
-			__entry->highest_used_slotid =
-					sa_slot->table->highest_used_slotid;
-		),
-		TP_printk(
-			"session=0x%08x slot_nr=%u seq_nr=%u "
-			"highest_used_slotid=%u",
-			__entry->session,
-			__entry->slot_nr,
-			__entry->seq_nr,
-			__entry->highest_used_slotid
-		)
-);
-
 #define show_nfs4_sequence_status_flags(status) \
 	__print_flags((unsigned long)status, "|", \
 		{ SEQ4_STATUS_CB_PATH_DOWN, "CB_PATH_DOWN" }, \
@@ -382,6 +350,38 @@ TRACE_EVENT(nfs4_cb_sequence,
 );
 #endif /* CONFIG_NFS_V4_1 */
 
+TRACE_EVENT(nfs4_setup_sequence,
+		TP_PROTO(
+			const struct nfs4_session *session,
+			const struct nfs4_sequence_args *args
+		),
+		TP_ARGS(session, args),
+
+		TP_STRUCT__entry(
+			__field(unsigned int, session)
+			__field(unsigned int, slot_nr)
+			__field(unsigned int, seq_nr)
+			__field(unsigned int, highest_used_slotid)
+		),
+
+		TP_fast_assign(
+			const struct nfs4_slot *sa_slot = args->sa_slot;
+			__entry->session = session ? nfs_session_id_hash(&session->sess_id) : 0;
+			__entry->slot_nr = sa_slot->slot_nr;
+			__entry->seq_nr = sa_slot->seq_nr;
+			__entry->highest_used_slotid =
+					sa_slot->table->highest_used_slotid;
+		),
+		TP_printk(
+			"session=0x%08x slot_nr=%u seq_nr=%u "
+			"highest_used_slotid=%u",
+			__entry->session,
+			__entry->slot_nr,
+			__entry->seq_nr,
+			__entry->highest_used_slotid
+		)
+);
+
 DECLARE_EVENT_CLASS(nfs4_open_event,
 		TP_PROTO(
 			const struct nfs_open_context *ctx,
@@ -891,6 +891,35 @@ DEFINE_NFS4_LOOKUP_EVENT(nfs4_remove);
 DEFINE_NFS4_LOOKUP_EVENT(nfs4_get_fs_locations);
 DEFINE_NFS4_LOOKUP_EVENT(nfs4_secinfo);
 
+TRACE_EVENT(nfs4_lookupp,
+		TP_PROTO(
+			const struct inode *inode,
+			int error
+		),
+
+		TP_ARGS(inode, error),
+
+		TP_STRUCT__entry(
+			__field(dev_t, dev)
+			__field(u64, ino)
+			__field(int, error)
+		),
+
+		TP_fast_assign(
+			__entry->dev = inode->i_sb->s_dev;
+			__entry->ino = NFS_FILEID(inode);
+			__entry->error = error;
+		),
+
+		TP_printk(
+			"error=%d (%s) inode=%02x:%02x:%llu",
+			__entry->error,
+			show_nfsv4_errors(__entry->error),
+			MAJOR(__entry->dev), MINOR(__entry->dev),
+			(unsigned long long)__entry->ino
+		)
+);
+
 TRACE_EVENT(nfs4_rename,
 		TP_PROTO(
 			const struct inode *olddir,
diff --git a/fs/nfs/nfs4xdr.c b/fs/nfs/nfs4xdr.c
index e9255cb453e6..fa3eb361d4f8 100644
--- a/fs/nfs/nfs4xdr.c
+++ b/fs/nfs/nfs4xdr.c
@@ -159,6 +159,8 @@ static int nfs4_stat_to_errno(int);
 				(op_decode_hdr_maxsz)
 #define encode_lookup_maxsz	(op_encode_hdr_maxsz + nfs4_name_maxsz)
 #define decode_lookup_maxsz	(op_decode_hdr_maxsz)
+#define encode_lookupp_maxsz	(op_encode_hdr_maxsz)
+#define decode_lookupp_maxsz	(op_decode_hdr_maxsz)
 #define encode_share_access_maxsz \
 				(2)
 #define encode_createmode_maxsz	(1 + encode_attrs_maxsz + encode_verifier_maxsz)
@@ -169,8 +171,10 @@ static int nfs4_stat_to_errno(int);
 				open_owner_id_maxsz + \
 				encode_opentype_maxsz + \
 				encode_claim_null_maxsz)
+#define decode_space_limit_maxsz	(3)
 #define decode_ace_maxsz	(3 + nfs4_owner_maxsz)
 #define decode_delegation_maxsz	(1 + decode_stateid_maxsz + 1 + \
+				decode_space_limit_maxsz + \
 				decode_ace_maxsz)
 #define decode_change_info_maxsz	(5)
 #define decode_open_maxsz	(op_decode_hdr_maxsz + \
@@ -616,6 +620,18 @@ static int nfs4_stat_to_errno(int);
 				decode_lookup_maxsz + \
 				decode_getattr_maxsz + \
 				decode_getfh_maxsz)
+#define NFS4_enc_lookupp_sz	(compound_encode_hdr_maxsz + \
+				encode_sequence_maxsz + \
+				encode_putfh_maxsz + \
+				encode_lookupp_maxsz + \
+				encode_getattr_maxsz + \
+				encode_getfh_maxsz)
+#define NFS4_dec_lookupp_sz	(compound_decode_hdr_maxsz + \
+				decode_sequence_maxsz + \
+				decode_putfh_maxsz + \
+				decode_lookupp_maxsz + \
+				decode_getattr_maxsz + \
+				decode_getfh_maxsz)
 #define NFS4_enc_lookup_root_sz (compound_encode_hdr_maxsz + \
 				encode_sequence_maxsz + \
 				encode_putrootfh_maxsz + \
@@ -924,34 +940,22 @@ static __be32 *reserve_space(struct xdr_stream *xdr, size_t nbytes)
 
 static void encode_opaque_fixed(struct xdr_stream *xdr, const void *buf, size_t len)
 {
-	__be32 *p;
-
-	p = xdr_reserve_space(xdr, len);
-	xdr_encode_opaque_fixed(p, buf, len);
+	WARN_ON_ONCE(xdr_stream_encode_opaque_fixed(xdr, buf, len) < 0);
 }
 
 static void encode_string(struct xdr_stream *xdr, unsigned int len, const char *str)
 {
-	__be32 *p;
-
-	p = reserve_space(xdr, 4 + len);
-	xdr_encode_opaque(p, str, len);
+	WARN_ON_ONCE(xdr_stream_encode_opaque(xdr, str, len) < 0);
 }
 
 static void encode_uint32(struct xdr_stream *xdr, u32 n)
 {
-	__be32 *p;
-
-	p = reserve_space(xdr, 4);
-	*p = cpu_to_be32(n);
+	WARN_ON_ONCE(xdr_stream_encode_u32(xdr, n) < 0);
 }
 
 static void encode_uint64(struct xdr_stream *xdr, u64 n)
 {
-	__be32 *p;
-
-	p = reserve_space(xdr, 8);
-	xdr_encode_hyper(p, n);
+	WARN_ON_ONCE(xdr_stream_encode_u64(xdr, n) < 0);
 }
 
 static void encode_nfs4_seqid(struct xdr_stream *xdr,
@@ -1010,8 +1014,9 @@ static void encode_nfs4_verifier(struct xdr_stream *xdr, const nfs4_verifier *ve
 
 static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap,
 				const struct nfs4_label *label,
+				const umode_t *umask,
 				const struct nfs_server *server,
-				bool excl_check, const umode_t *umask)
+				const uint32_t attrmask[])
 {
 	char owner_name[IDMAP_NAMESZ];
 	char owner_group[IDMAP_NAMESZ];
@@ -1026,22 +1031,20 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap,
 	/*
 	 * We reserve enough space to write the entire attribute buffer at once.
 	 */
-	if (iap->ia_valid & ATTR_SIZE) {
+	if ((iap->ia_valid & ATTR_SIZE) && (attrmask[0] & FATTR4_WORD0_SIZE)) {
 		bmval[0] |= FATTR4_WORD0_SIZE;
 		len += 8;
 	}
-	if (!(server->attr_bitmask[2] & FATTR4_WORD2_MODE_UMASK))
-		umask = NULL;
 	if (iap->ia_valid & ATTR_MODE) {
-		if (umask) {
+		if (umask && (attrmask[2] & FATTR4_WORD2_MODE_UMASK)) {
 			bmval[2] |= FATTR4_WORD2_MODE_UMASK;
 			len += 8;
-		} else {
+		} else if (attrmask[1] & FATTR4_WORD1_MODE) {
 			bmval[1] |= FATTR4_WORD1_MODE;
 			len += 4;
 		}
 	}
-	if (iap->ia_valid & ATTR_UID) {
+	if ((iap->ia_valid & ATTR_UID) && (attrmask[1] & FATTR4_WORD1_OWNER)) {
 		owner_namelen = nfs_map_uid_to_name(server, iap->ia_uid, owner_name, IDMAP_NAMESZ);
 		if (owner_namelen < 0) {
 			dprintk("nfs: couldn't resolve uid %d to string\n",
@@ -1054,7 +1057,8 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap,
 		bmval[1] |= FATTR4_WORD1_OWNER;
 		len += 4 + (XDR_QUADLEN(owner_namelen) << 2);
 	}
-	if (iap->ia_valid & ATTR_GID) {
+	if ((iap->ia_valid & ATTR_GID) &&
+	   (attrmask[1] & FATTR4_WORD1_OWNER_GROUP)) {
 		owner_grouplen = nfs_map_gid_to_group(server, iap->ia_gid, owner_group, IDMAP_NAMESZ);
 		if (owner_grouplen < 0) {
 			dprintk("nfs: couldn't resolve gid %d to string\n",
@@ -1066,32 +1070,26 @@ static void encode_attrs(struct xdr_stream *xdr, const struct iattr *iap,
 		bmval[1] |= FATTR4_WORD1_OWNER_GROUP;
 		len += 4 + (XDR_QUADLEN(owner_grouplen) << 2);
 	}
-	if (iap->ia_valid & ATTR_ATIME_SET) {
-		bmval[1] |= FATTR4_WORD1_TIME_ACCESS_SET;
-		len += 16;
-	} else if (iap->ia_valid & ATTR_ATIME) {
-		bmval[1] |= FATTR4_WORD1_TIME_ACCESS_SET;
-		len += 4;
-	}
-	if (iap->ia_valid & ATTR_MTIME_SET) {
-		bmval[1] |= FATTR4_WORD1_TIME_MODIFY_SET;
-		len += 16;
-	} else if (iap->ia_valid & ATTR_MTIME) {
-		bmval[1] |= FATTR4_WORD1_TIME_MODIFY_SET;
-		len += 4;
+	if (attrmask[1] & FATTR4_WORD1_TIME_ACCESS_SET) {
+		if (iap->ia_valid & ATTR_ATIME_SET) {
+			bmval[1] |= FATTR4_WORD1_TIME_ACCESS_SET;
+			len += 16;
+		} else if (iap->ia_valid & ATTR_ATIME) {
+			bmval[1] |= FATTR4_WORD1_TIME_ACCESS_SET;
+			len += 4;
+		}
 	}
-
-	if (excl_check) {
-		const u32 *excl_bmval = server->exclcreat_bitmask;
-		bmval[0] &= excl_bmval[0];
-		bmval[1] &= excl_bmval[1];
-		bmval[2] &= excl_bmval[2];
-
-		if (!(excl_bmval[2] & FATTR4_WORD2_SECURITY_LABEL))
-			label = NULL;
+	if (attrmask[1] & FATTR4_WORD1_TIME_MODIFY_SET) {
+		if (iap->ia_valid & ATTR_MTIME_SET) {
+			bmval[1] |= FATTR4_WORD1_TIME_MODIFY_SET;
+			len += 16;
+		} else if (iap->ia_valid & ATTR_MTIME) {
+			bmval[1] |= FATTR4_WORD1_TIME_MODIFY_SET;
+			len += 4;
+		}
 	}
 
-	if (label) {
+	if (label && (attrmask[2] & FATTR4_WORD2_SECURITY_LABEL)) {
 		len += 4 + 4 + 4 + (XDR_QUADLEN(label->len) << 2);
 		bmval[2] |= FATTR4_WORD2_SECURITY_LABEL;
 	}
@@ -1198,8 +1196,8 @@ static void encode_create(struct xdr_stream *xdr, const struct nfs4_create_arg *
 	}
 
 	encode_string(xdr, create->name->len, create->name->name);
-	encode_attrs(xdr, create->attrs, create->label, create->server, false,
-		     &create->umask);
+	encode_attrs(xdr, create->attrs, create->label, &create->umask,
+			create->server, create->server->attr_bitmask);
 }
 
 static void encode_getattr_one(struct xdr_stream *xdr, uint32_t bitmap, struct compound_hdr *hdr)
@@ -1384,6 +1382,11 @@ static void encode_lookup(struct xdr_stream *xdr, const struct qstr *name, struc
 	encode_string(xdr, name->len, name->name);
 }
 
+static void encode_lookupp(struct xdr_stream *xdr, struct compound_hdr *hdr)
+{
+	encode_op_hdr(xdr, OP_LOOKUPP, decode_lookupp_maxsz, hdr);
+}
+
 static void encode_share_access(struct xdr_stream *xdr, u32 share_access)
 {
 	__be32 *p;
@@ -1419,13 +1422,13 @@ static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_op
 	switch(arg->createmode) {
 	case NFS4_CREATE_UNCHECKED:
 		*p = cpu_to_be32(NFS4_CREATE_UNCHECKED);
-		encode_attrs(xdr, arg->u.attrs, arg->label, arg->server, false,
-			     &arg->umask);
+		encode_attrs(xdr, arg->u.attrs, arg->label, &arg->umask,
+				arg->server, arg->server->attr_bitmask);
 		break;
 	case NFS4_CREATE_GUARDED:
 		*p = cpu_to_be32(NFS4_CREATE_GUARDED);
-		encode_attrs(xdr, arg->u.attrs, arg->label, arg->server, false,
-			     &arg->umask);
+		encode_attrs(xdr, arg->u.attrs, arg->label, &arg->umask,
+				arg->server, arg->server->attr_bitmask);
 		break;
 	case NFS4_CREATE_EXCLUSIVE:
 		*p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE);
@@ -1434,8 +1437,8 @@ static inline void encode_createmode(struct xdr_stream *xdr, const struct nfs_op
 	case NFS4_CREATE_EXCLUSIVE4_1:
 		*p = cpu_to_be32(NFS4_CREATE_EXCLUSIVE4_1);
 		encode_nfs4_verifier(xdr, &arg->u.verifier);
-		encode_attrs(xdr, arg->u.attrs, arg->label, arg->server, true,
-			     &arg->umask);
+		encode_attrs(xdr, arg->u.attrs, arg->label, &arg->umask,
+				arg->server, arg->server->exclcreat_bitmask);
 	}
 }
 
@@ -1667,7 +1670,8 @@ encode_restorefh(struct xdr_stream *xdr, struct compound_hdr *hdr)
 }
 
 static void
-encode_setacl(struct xdr_stream *xdr, struct nfs_setaclargs *arg, struct compound_hdr *hdr)
+encode_setacl(struct xdr_stream *xdr, const struct nfs_setaclargs *arg,
+		struct compound_hdr *hdr)
 {
 	__be32 *p;
 
@@ -1691,7 +1695,8 @@ static void encode_setattr(struct xdr_stream *xdr, const struct nfs_setattrargs
 {
 	encode_op_hdr(xdr, OP_SETATTR, decode_setattr_maxsz, hdr);
 	encode_nfs4_stateid(xdr, &arg->stateid);
-	encode_attrs(xdr, arg->iap, arg->label, server, false, NULL);
+	encode_attrs(xdr, arg->iap, arg->label, NULL, server,
+			server->attr_bitmask);
 }
 
 static void encode_setclientid(struct xdr_stream *xdr, const struct nfs4_setclientid *setclientid, struct compound_hdr *hdr)
@@ -1750,7 +1755,7 @@ static void encode_secinfo(struct xdr_stream *xdr, const struct qstr *name, stru
 #if defined(CONFIG_NFS_V4_1)
 /* NFSv4.1 operations */
 static void encode_bind_conn_to_session(struct xdr_stream *xdr,
-				   struct nfs41_bind_conn_to_session_args *args,
+				   const struct nfs41_bind_conn_to_session_args *args,
 				   struct compound_hdr *hdr)
 {
 	__be32 *p;
@@ -1763,7 +1768,7 @@ static void encode_bind_conn_to_session(struct xdr_stream *xdr,
 	*p = (args->use_conn_in_rdma_mode) ? cpu_to_be32(1) : cpu_to_be32(0);
 }
 
-static void encode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map)
+static void encode_op_map(struct xdr_stream *xdr, const struct nfs4_op_map *op_map)
 {
 	unsigned int i;
 	encode_uint32(xdr, NFS4_OP_MAP_NUM_WORDS);
@@ -1772,7 +1777,7 @@ static void encode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map)
 }
 
 static void encode_exchange_id(struct xdr_stream *xdr,
-			       struct nfs41_exchange_id_args *args,
+			       const struct nfs41_exchange_id_args *args,
 			       struct compound_hdr *hdr)
 {
 	__be32 *p;
@@ -1824,7 +1829,7 @@ static void encode_exchange_id(struct xdr_stream *xdr,
 }
 
 static void encode_create_session(struct xdr_stream *xdr,
-				  struct nfs41_create_session_args *args,
+				  const struct nfs41_create_session_args *args,
 				  struct compound_hdr *hdr)
 {
 	__be32 *p;
@@ -1877,7 +1882,7 @@ static void encode_create_session(struct xdr_stream *xdr,
 }
 
 static void encode_destroy_session(struct xdr_stream *xdr,
-				   struct nfs4_session *session,
+				   const struct nfs4_session *session,
 				   struct compound_hdr *hdr)
 {
 	encode_op_hdr(xdr, OP_DESTROY_SESSION, decode_destroy_session_maxsz, hdr);
@@ -1893,7 +1898,7 @@ static void encode_destroy_clientid(struct xdr_stream *xdr,
 }
 
 static void encode_reclaim_complete(struct xdr_stream *xdr,
-				    struct nfs41_reclaim_complete_args *args,
+				    const struct nfs41_reclaim_complete_args *args,
 				    struct compound_hdr *hdr)
 {
 	encode_op_hdr(xdr, OP_RECLAIM_COMPLETE, decode_reclaim_complete_maxsz, hdr);
@@ -1989,7 +1994,7 @@ encode_layoutget(struct xdr_stream *xdr,
 static int
 encode_layoutcommit(struct xdr_stream *xdr,
 		    struct inode *inode,
-		    struct nfs4_layoutcommit_args *args,
+		    const struct nfs4_layoutcommit_args *args,
 		    struct compound_hdr *hdr)
 {
 	__be32 *p;
@@ -2015,16 +2020,10 @@ encode_layoutcommit(struct xdr_stream *xdr,
 	*p++ = cpu_to_be32(0); /* Never send time_modify_changed */
 	*p++ = cpu_to_be32(NFS_SERVER(args->inode)->pnfs_curr_ld->id);/* type */
 
-	if (NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit) {
-		NFS_SERVER(inode)->pnfs_curr_ld->encode_layoutcommit(
-			NFS_I(inode)->layout, xdr, args);
-	} else {
-		encode_uint32(xdr, args->layoutupdate_len);
-		if (args->layoutupdate_pages) {
-			xdr_write_pages(xdr, args->layoutupdate_pages, 0,
-					args->layoutupdate_len);
-		}
-	}
+	encode_uint32(xdr, args->layoutupdate_len);
+	if (args->layoutupdate_pages)
+		xdr_write_pages(xdr, args->layoutupdate_pages, 0,
+				args->layoutupdate_len);
 
 	return 0;
 }
@@ -2034,7 +2033,6 @@ encode_layoutreturn(struct xdr_stream *xdr,
 		    const struct nfs4_layoutreturn_args *args,
 		    struct compound_hdr *hdr)
 {
-	const struct pnfs_layoutdriver_type *lr_ops = NFS_SERVER(args->inode)->pnfs_curr_ld;
 	__be32 *p;
 
 	encode_op_hdr(xdr, OP_LAYOUTRETURN, decode_layoutreturn_maxsz, hdr);
@@ -2051,8 +2049,6 @@ encode_layoutreturn(struct xdr_stream *xdr,
 	spin_unlock(&args->inode->i_lock);
 	if (args->ld_private->ops && args->ld_private->ops->encode)
 		args->ld_private->ops->encode(xdr, args, args->ld_private);
-	else if (lr_ops->encode_layoutreturn)
-		lr_ops->encode_layoutreturn(xdr, args);
 	else
 		encode_uint32(xdr, 0);
 }
@@ -2068,7 +2064,7 @@ encode_secinfo_no_name(struct xdr_stream *xdr,
 }
 
 static void encode_test_stateid(struct xdr_stream *xdr,
-				struct nfs41_test_stateid_args *args,
+				const struct nfs41_test_stateid_args *args,
 				struct compound_hdr *hdr)
 {
 	encode_op_hdr(xdr, OP_TEST_STATEID, decode_test_stateid_maxsz, hdr);
@@ -2077,7 +2073,7 @@ static void encode_test_stateid(struct xdr_stream *xdr,
 }
 
 static void encode_free_stateid(struct xdr_stream *xdr,
-				struct nfs41_free_stateid_args *args,
+				const struct nfs41_free_stateid_args *args,
 				struct compound_hdr *hdr)
 {
 	encode_op_hdr(xdr, OP_FREE_STATEID, decode_free_stateid_maxsz, hdr);
@@ -2110,8 +2106,9 @@ static u32 nfs4_xdr_minorversion(const struct nfs4_sequence_args *args)
  * Encode an ACCESS request
  */
 static void nfs4_xdr_enc_access(struct rpc_rqst *req, struct xdr_stream *xdr,
-				const struct nfs4_accessargs *args)
+				const void *data)
 {
+	const struct nfs4_accessargs *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2128,8 +2125,9 @@ static void nfs4_xdr_enc_access(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode LOOKUP request
  */
 static void nfs4_xdr_enc_lookup(struct rpc_rqst *req, struct xdr_stream *xdr,
-				const struct nfs4_lookup_arg *args)
+				const void *data)
 {
+	const struct nfs4_lookup_arg *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2144,12 +2142,33 @@ static void nfs4_xdr_enc_lookup(struct rpc_rqst *req, struct xdr_stream *xdr,
 }
 
 /*
+ * Encode LOOKUPP request
+ */
+static void nfs4_xdr_enc_lookupp(struct rpc_rqst *req, struct xdr_stream *xdr,
+		const void *data)
+{
+	const struct nfs4_lookupp_arg *args = data;
+	struct compound_hdr hdr = {
+		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
+	};
+
+	encode_compound_hdr(xdr, req, &hdr);
+	encode_sequence(xdr, &args->seq_args, &hdr);
+	encode_putfh(xdr, args->fh, &hdr);
+	encode_lookupp(xdr, &hdr);
+	encode_getfh(xdr, &hdr);
+	encode_getfattr(xdr, args->bitmask, &hdr);
+	encode_nops(&hdr);
+}
+
+/*
  * Encode LOOKUP_ROOT request
  */
 static void nfs4_xdr_enc_lookup_root(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs4_lookup_root_arg *args)
+				     const void *data)
 {
+	const struct nfs4_lookup_root_arg *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2166,8 +2185,9 @@ static void nfs4_xdr_enc_lookup_root(struct rpc_rqst *req,
  * Encode REMOVE request
  */
 static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr,
-				const struct nfs_removeargs *args)
+				const void *data)
 {
+	const struct nfs_removeargs *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2183,8 +2203,9 @@ static void nfs4_xdr_enc_remove(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode RENAME request
  */
 static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr,
-				const struct nfs_renameargs *args)
+				const void *data)
 {
+	const struct nfs_renameargs *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2202,8 +2223,9 @@ static void nfs4_xdr_enc_rename(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode LINK request
  */
 static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr,
-			     const struct nfs4_link_arg *args)
+			      const void *data)
 {
+	const struct nfs4_link_arg *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2223,8 +2245,9 @@ static void nfs4_xdr_enc_link(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode CREATE request
  */
 static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr,
-				const struct nfs4_create_arg *args)
+				const void *data)
 {
+	const struct nfs4_create_arg *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2242,8 +2265,10 @@ static void nfs4_xdr_enc_create(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode SYMLINK request
  */
 static void nfs4_xdr_enc_symlink(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 const struct nfs4_create_arg *args)
+				 const void *data)
 {
+	const struct nfs4_create_arg *args = data;
+
 	nfs4_xdr_enc_create(req, xdr, args);
 }
 
@@ -2251,8 +2276,9 @@ static void nfs4_xdr_enc_symlink(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode GETATTR request
  */
 static void nfs4_xdr_enc_getattr(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 const struct nfs4_getattr_arg *args)
+				 const void *data)
 {
+	const struct nfs4_getattr_arg *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2268,8 +2294,9 @@ static void nfs4_xdr_enc_getattr(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode a CLOSE request
  */
 static void nfs4_xdr_enc_close(struct rpc_rqst *req, struct xdr_stream *xdr,
-			       struct nfs_closeargs *args)
+			       const void *data)
 {
+	const struct nfs_closeargs *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2289,8 +2316,9 @@ static void nfs4_xdr_enc_close(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode an OPEN request
  */
 static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr,
-			      struct nfs_openargs *args)
+			      const void *data)
 {
+	const struct nfs_openargs *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2311,8 +2339,9 @@ static void nfs4_xdr_enc_open(struct rpc_rqst *req, struct xdr_stream *xdr,
  */
 static void nfs4_xdr_enc_open_confirm(struct rpc_rqst *req,
 				      struct xdr_stream *xdr,
-				      struct nfs_open_confirmargs *args)
+				      const void *data)
 {
+	const struct nfs_open_confirmargs *args = data;
 	struct compound_hdr hdr = {
 		.nops   = 0,
 	};
@@ -2328,8 +2357,9 @@ static void nfs4_xdr_enc_open_confirm(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     struct nfs_openargs *args)
+				     const void *data)
 {
+	const struct nfs_openargs *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2349,8 +2379,9 @@ static void nfs4_xdr_enc_open_noattr(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req,
 					struct xdr_stream *xdr,
-					struct nfs_closeargs *args)
+					const void *data)
 {
+	const struct nfs_closeargs *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2368,8 +2399,9 @@ static void nfs4_xdr_enc_open_downgrade(struct rpc_rqst *req,
  * Encode a LOCK request
  */
 static void nfs4_xdr_enc_lock(struct rpc_rqst *req, struct xdr_stream *xdr,
-			      struct nfs_lock_args *args)
+			      const void *data)
 {
+	const struct nfs_lock_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2385,8 +2417,9 @@ static void nfs4_xdr_enc_lock(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode a LOCKT request
  */
 static void nfs4_xdr_enc_lockt(struct rpc_rqst *req, struct xdr_stream *xdr,
-			       struct nfs_lockt_args *args)
+			       const void *data)
 {
+	const struct nfs_lockt_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2402,8 +2435,9 @@ static void nfs4_xdr_enc_lockt(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode a LOCKU request
  */
 static void nfs4_xdr_enc_locku(struct rpc_rqst *req, struct xdr_stream *xdr,
-			       struct nfs_locku_args *args)
+			       const void *data)
 {
+	const struct nfs_locku_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2417,8 +2451,9 @@ static void nfs4_xdr_enc_locku(struct rpc_rqst *req, struct xdr_stream *xdr,
 
 static void nfs4_xdr_enc_release_lockowner(struct rpc_rqst *req,
 					   struct xdr_stream *xdr,
-					struct nfs_release_lockowner_args *args)
+					   const void *data)
 {
+	const struct nfs_release_lockowner_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = 0,
 	};
@@ -2432,8 +2467,9 @@ static void nfs4_xdr_enc_release_lockowner(struct rpc_rqst *req,
  * Encode a READLINK request
  */
 static void nfs4_xdr_enc_readlink(struct rpc_rqst *req, struct xdr_stream *xdr,
-				  const struct nfs4_readlink *args)
+				  const void *data)
 {
+	const struct nfs4_readlink *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2452,8 +2488,9 @@ static void nfs4_xdr_enc_readlink(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode a READDIR request
  */
 static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 const struct nfs4_readdir_arg *args)
+				 const void *data)
 {
+	const struct nfs4_readdir_arg *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2475,8 +2512,9 @@ static void nfs4_xdr_enc_readdir(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode a READ request
  */
 static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr,
-			      struct nfs_pgio_args *args)
+			      const void *data)
 {
+	const struct nfs_pgio_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2496,8 +2534,9 @@ static void nfs4_xdr_enc_read(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode an SETATTR request
  */
 static void nfs4_xdr_enc_setattr(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 struct nfs_setattrargs *args)
+				 const void *data)
 {
+	const struct nfs_setattrargs *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2514,8 +2553,9 @@ static void nfs4_xdr_enc_setattr(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode a GETACL request
  */
 static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
-				struct nfs_getaclargs *args)
+				const void *data)
 {
+	const struct nfs_getaclargs *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2524,7 +2564,7 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
 	encode_compound_hdr(xdr, req, &hdr);
 	encode_sequence(xdr, &args->seq_args, &hdr);
 	encode_putfh(xdr, args->fh, &hdr);
-	replen = hdr.replen + op_decode_hdr_maxsz + 1;
+	replen = hdr.replen + op_decode_hdr_maxsz;
 	encode_getattr_two(xdr, FATTR4_WORD0_ACL, 0, &hdr);
 
 	xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
@@ -2537,8 +2577,9 @@ static void nfs4_xdr_enc_getacl(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Encode a WRITE request
  */
 static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr,
-			       struct nfs_pgio_args *args)
+			       const void *data)
 {
+	const struct nfs_pgio_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2557,8 +2598,9 @@ static void nfs4_xdr_enc_write(struct rpc_rqst *req, struct xdr_stream *xdr,
  *  a COMMIT request
  */
 static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr,
-				struct nfs_commitargs *args)
+				const void *data)
 {
+	const struct nfs_commitargs *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2574,8 +2616,9 @@ static void nfs4_xdr_enc_commit(struct rpc_rqst *req, struct xdr_stream *xdr,
  * FSINFO request
  */
 static void nfs4_xdr_enc_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr,
-				struct nfs4_fsinfo_arg *args)
+				const void *data)
 {
+	const struct nfs4_fsinfo_arg *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2591,8 +2634,9 @@ static void nfs4_xdr_enc_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr,
  * a PATHCONF request
  */
 static void nfs4_xdr_enc_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr,
-				  const struct nfs4_pathconf_arg *args)
+				  const void *data)
 {
+	const struct nfs4_pathconf_arg *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2609,8 +2653,9 @@ static void nfs4_xdr_enc_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr,
  * a STATFS request
  */
 static void nfs4_xdr_enc_statfs(struct rpc_rqst *req, struct xdr_stream *xdr,
-				const struct nfs4_statfs_arg *args)
+				const void *data)
 {
+	const struct nfs4_statfs_arg *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2628,8 +2673,9 @@ static void nfs4_xdr_enc_statfs(struct rpc_rqst *req, struct xdr_stream *xdr,
  */
 static void nfs4_xdr_enc_server_caps(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     struct nfs4_server_caps_arg *args)
+				     const void *data)
 {
+	const struct nfs4_server_caps_arg *args = data;
 	const u32 *bitmask = args->bitmask;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
@@ -2646,8 +2692,10 @@ static void nfs4_xdr_enc_server_caps(struct rpc_rqst *req,
  * a RENEW request
  */
 static void nfs4_xdr_enc_renew(struct rpc_rqst *req, struct xdr_stream *xdr,
-			       struct nfs_client *clp)
+			       const void *data)
+
 {
+	const struct nfs_client *clp = data;
 	struct compound_hdr hdr = {
 		.nops	= 0,
 	};
@@ -2662,8 +2710,9 @@ static void nfs4_xdr_enc_renew(struct rpc_rqst *req, struct xdr_stream *xdr,
  */
 static void nfs4_xdr_enc_setclientid(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     struct nfs4_setclientid *sc)
+				     const void *data)
 {
+	const struct nfs4_setclientid *sc = data;
 	struct compound_hdr hdr = {
 		.nops	= 0,
 	};
@@ -2678,8 +2727,9 @@ static void nfs4_xdr_enc_setclientid(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req,
 					     struct xdr_stream *xdr,
-					     struct nfs4_setclientid_res *arg)
+					     const void *data)
 {
+	const struct nfs4_setclientid_res *arg = data;
 	struct compound_hdr hdr = {
 		.nops	= 0,
 	};
@@ -2694,8 +2744,9 @@ static void nfs4_xdr_enc_setclientid_confirm(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     const struct nfs4_delegreturnargs *args)
+				     const void *data)
 {
+	const struct nfs4_delegreturnargs *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2716,8 +2767,9 @@ static void nfs4_xdr_enc_delegreturn(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req,
 				      struct xdr_stream *xdr,
-				      struct nfs4_fs_locations_arg *args)
+				      const void *data)
 {
+	const struct nfs4_fs_locations_arg *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2739,8 +2791,8 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req,
 	}
 
 	/* Set up reply kvec to capture returned fs_locations array. */
-	xdr_inline_pages(&req->rq_rcv_buf, replen << 2, &args->page,
-			0, PAGE_SIZE);
+	xdr_inline_pages(&req->rq_rcv_buf, replen << 2,
+			 (struct page **)&args->page, 0, PAGE_SIZE);
 	encode_nops(&hdr);
 }
 
@@ -2749,8 +2801,9 @@ static void nfs4_xdr_enc_fs_locations(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req,
 				struct xdr_stream *xdr,
-				struct nfs4_secinfo_arg *args)
+				const void *data)
 {
+	const struct nfs4_secinfo_arg *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2767,8 +2820,9 @@ static void nfs4_xdr_enc_secinfo(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req,
 				      struct xdr_stream *xdr,
-				      struct nfs4_fsid_present_arg *args)
+				      const void *data)
 {
+	const struct nfs4_fsid_present_arg *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2788,8 +2842,9 @@ static void nfs4_xdr_enc_fsid_present(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req,
 				struct xdr_stream *xdr,
-				struct nfs41_bind_conn_to_session_args *args)
+				const void *data)
 {
+	const struct nfs41_bind_conn_to_session_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = args->client->cl_mvops->minor_version,
 	};
@@ -2804,8 +2859,9 @@ static void nfs4_xdr_enc_bind_conn_to_session(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_exchange_id(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     struct nfs41_exchange_id_args *args)
+				     const void *data)
 {
+	const struct nfs41_exchange_id_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = args->client->cl_mvops->minor_version,
 	};
@@ -2820,8 +2876,9 @@ static void nfs4_xdr_enc_exchange_id(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_create_session(struct rpc_rqst *req,
 					struct xdr_stream *xdr,
-					struct nfs41_create_session_args *args)
+					const void *data)
 {
+	const struct nfs41_create_session_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = args->client->cl_mvops->minor_version,
 	};
@@ -2836,8 +2893,9 @@ static void nfs4_xdr_enc_create_session(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req,
 					 struct xdr_stream *xdr,
-					 struct nfs4_session *session)
+					 const void *data)
 {
+	const struct nfs4_session *session = data;
 	struct compound_hdr hdr = {
 		.minorversion = session->clp->cl_mvops->minor_version,
 	};
@@ -2852,8 +2910,9 @@ static void nfs4_xdr_enc_destroy_session(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req,
 					 struct xdr_stream *xdr,
-					 struct nfs_client *clp)
+					 const void *data)
 {
+	const struct nfs_client *clp = data;
 	struct compound_hdr hdr = {
 		.minorversion = clp->cl_mvops->minor_version,
 	};
@@ -2867,8 +2926,9 @@ static void nfs4_xdr_enc_destroy_clientid(struct rpc_rqst *req,
  * a SEQUENCE request
  */
 static void nfs4_xdr_enc_sequence(struct rpc_rqst *req, struct xdr_stream *xdr,
-				  struct nfs4_sequence_args *args)
+				  const void *data)
 {
+	const struct nfs4_sequence_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(args),
 	};
@@ -2883,8 +2943,9 @@ static void nfs4_xdr_enc_sequence(struct rpc_rqst *req, struct xdr_stream *xdr,
  */
 static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req,
 					struct xdr_stream *xdr,
-					struct nfs4_get_lease_time_args *args)
+					const void *data)
 {
+	const struct nfs4_get_lease_time_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->la_seq_args),
 	};
@@ -2902,8 +2963,9 @@ static void nfs4_xdr_enc_get_lease_time(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req,
 					  struct xdr_stream *xdr,
-				struct nfs41_reclaim_complete_args *args)
+					  const void *data)
 {
+	const struct nfs41_reclaim_complete_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args)
 	};
@@ -2919,8 +2981,9 @@ static void nfs4_xdr_enc_reclaim_complete(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req,
 				       struct xdr_stream *xdr,
-				       struct nfs4_getdeviceinfo_args *args)
+				       const void *data)
 {
+	const struct nfs4_getdeviceinfo_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2943,8 +3006,9 @@ static void nfs4_xdr_enc_getdeviceinfo(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   struct nfs4_layoutget_args *args)
+				   const void *data)
 {
+	const struct nfs4_layoutget_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -2965,8 +3029,9 @@ static void nfs4_xdr_enc_layoutget(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req,
 				      struct xdr_stream *xdr,
-				      struct nfs4_layoutcommit_args *args)
+				      const void *priv)
 {
+	const struct nfs4_layoutcommit_args *args = priv;
 	struct nfs4_layoutcommit_data *data =
 		container_of(args, struct nfs4_layoutcommit_data, args);
 	struct compound_hdr hdr = {
@@ -2986,8 +3051,9 @@ static void nfs4_xdr_enc_layoutcommit(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req,
 				      struct xdr_stream *xdr,
-				      struct nfs4_layoutreturn_args *args)
+				      const void *data)
 {
+	const struct nfs4_layoutreturn_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -3002,10 +3068,11 @@ static void nfs4_xdr_enc_layoutreturn(struct rpc_rqst *req,
 /*
  * Encode SECINFO_NO_NAME request
  */
-static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req,
+static void nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req,
 					struct xdr_stream *xdr,
-					struct nfs41_secinfo_no_name_args *args)
+					const void *data)
 {
+	const struct nfs41_secinfo_no_name_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -3015,7 +3082,6 @@ static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req,
 	encode_putrootfh(xdr, &hdr);
 	encode_secinfo_no_name(xdr, args, &hdr);
 	encode_nops(&hdr);
-	return 0;
 }
 
 /*
@@ -3023,8 +3089,9 @@ static int nfs4_xdr_enc_secinfo_no_name(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_test_stateid(struct rpc_rqst *req,
 				      struct xdr_stream *xdr,
-				      struct nfs41_test_stateid_args *args)
+				      const void *data)
 {
+	const struct nfs41_test_stateid_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -3040,8 +3107,9 @@ static void nfs4_xdr_enc_test_stateid(struct rpc_rqst *req,
  */
 static void nfs4_xdr_enc_free_stateid(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     struct nfs41_free_stateid_args *args)
+				     const void *data)
 {
+	const struct nfs41_free_stateid_args *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -3062,20 +3130,15 @@ static void print_overflow_msg(const char *func, const struct xdr_stream *xdr)
 
 static int decode_opaque_inline(struct xdr_stream *xdr, unsigned int *len, char **string)
 {
-	__be32 *p;
-
-	p = xdr_inline_decode(xdr, 4);
-	if (unlikely(!p))
-		goto out_overflow;
-	*len = be32_to_cpup(p);
-	p = xdr_inline_decode(xdr, *len);
-	if (unlikely(!p))
-		goto out_overflow;
-	*string = (char *)p;
+	ssize_t ret = xdr_stream_decode_opaque_inline(xdr, (void **)string,
+			NFS4_OPAQUE_LIMIT);
+	if (unlikely(ret < 0)) {
+		if (ret == -EBADMSG)
+			print_overflow_msg(__func__, xdr);
+		return -EIO;
+	}
+	*len = ret;
 	return 0;
-out_overflow:
-	print_overflow_msg(__func__, xdr);
-	return -EIO;
 }
 
 static int decode_compound_hdr(struct xdr_stream *xdr, struct compound_hdr *hdr)
@@ -3142,7 +3205,7 @@ static int decode_op_hdr(struct xdr_stream *xdr, enum nfs_opnum4 expected)
 }
 
 /* Dummy routine */
-static int decode_ace(struct xdr_stream *xdr, void *ace, struct nfs_client *clp)
+static int decode_ace(struct xdr_stream *xdr, void *ace)
 {
 	__be32 *p;
 	unsigned int strlen;
@@ -3890,45 +3953,50 @@ out_overflow:
 	return -EIO;
 }
 
+static ssize_t decode_nfs4_string(struct xdr_stream *xdr,
+		struct nfs4_string *name, gfp_t gfp_flags)
+{
+	ssize_t ret;
+
+	ret = xdr_stream_decode_string_dup(xdr, &name->data,
+			XDR_MAX_NETOBJ, gfp_flags);
+	name->len = 0;
+	if (ret > 0)
+		name->len = ret;
+	return ret;
+}
+
 static int decode_attr_owner(struct xdr_stream *xdr, uint32_t *bitmap,
 		const struct nfs_server *server, kuid_t *uid,
 		struct nfs4_string *owner_name)
 {
-	uint32_t len;
-	__be32 *p;
-	int ret = 0;
+	ssize_t len;
+	char *p;
 
 	*uid = make_kuid(&init_user_ns, -2);
 	if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER - 1U)))
 		return -EIO;
-	if (likely(bitmap[1] & FATTR4_WORD1_OWNER)) {
-		p = xdr_inline_decode(xdr, 4);
-		if (unlikely(!p))
-			goto out_overflow;
-		len = be32_to_cpup(p);
-		p = xdr_inline_decode(xdr, len);
-		if (unlikely(!p))
-			goto out_overflow;
-		if (owner_name != NULL) {
-			owner_name->data = kmemdup(p, len, GFP_NOWAIT);
-			if (owner_name->data != NULL) {
-				owner_name->len = len;
-				ret = NFS_ATTR_FATTR_OWNER_NAME;
-			}
-		} else if (len < XDR_MAX_NETOBJ) {
-			if (nfs_map_name_to_uid(server, (char *)p, len, uid) == 0)
-				ret = NFS_ATTR_FATTR_OWNER;
-			else
-				dprintk("%s: nfs_map_name_to_uid failed!\n",
-						__func__);
-		} else
-			dprintk("%s: name too long (%u)!\n",
-					__func__, len);
-		bitmap[1] &= ~FATTR4_WORD1_OWNER;
+	if (!(bitmap[1] & FATTR4_WORD1_OWNER))
+		return 0;
+	bitmap[1] &= ~FATTR4_WORD1_OWNER;
+
+	if (owner_name != NULL) {
+		len = decode_nfs4_string(xdr, owner_name, GFP_NOWAIT);
+		if (len <= 0)
+			goto out;
+		dprintk("%s: name=%s\n", __func__, owner_name->data);
+		return NFS_ATTR_FATTR_OWNER_NAME;
+	} else {
+		len = xdr_stream_decode_opaque_inline(xdr, (void **)&p,
+				XDR_MAX_NETOBJ);
+		if (len <= 0 || nfs_map_name_to_uid(server, p, len, uid) != 0)
+			goto out;
+		dprintk("%s: uid=%d\n", __func__, (int)from_kuid(&init_user_ns, *uid));
+		return NFS_ATTR_FATTR_OWNER;
 	}
-	dprintk("%s: uid=%d\n", __func__, (int)from_kuid(&init_user_ns, *uid));
-	return ret;
-out_overflow:
+out:
+	if (len != -EBADMSG)
+		return 0;
 	print_overflow_msg(__func__, xdr);
 	return -EIO;
 }
@@ -3937,41 +4005,33 @@ static int decode_attr_group(struct xdr_stream *xdr, uint32_t *bitmap,
 		const struct nfs_server *server, kgid_t *gid,
 		struct nfs4_string *group_name)
 {
-	uint32_t len;
-	__be32 *p;
-	int ret = 0;
+	ssize_t len;
+	char *p;
 
 	*gid = make_kgid(&init_user_ns, -2);
 	if (unlikely(bitmap[1] & (FATTR4_WORD1_OWNER_GROUP - 1U)))
 		return -EIO;
-	if (likely(bitmap[1] & FATTR4_WORD1_OWNER_GROUP)) {
-		p = xdr_inline_decode(xdr, 4);
-		if (unlikely(!p))
-			goto out_overflow;
-		len = be32_to_cpup(p);
-		p = xdr_inline_decode(xdr, len);
-		if (unlikely(!p))
-			goto out_overflow;
-		if (group_name != NULL) {
-			group_name->data = kmemdup(p, len, GFP_NOWAIT);
-			if (group_name->data != NULL) {
-				group_name->len = len;
-				ret = NFS_ATTR_FATTR_GROUP_NAME;
-			}
-		} else if (len < XDR_MAX_NETOBJ) {
-			if (nfs_map_group_to_gid(server, (char *)p, len, gid) == 0)
-				ret = NFS_ATTR_FATTR_GROUP;
-			else
-				dprintk("%s: nfs_map_group_to_gid failed!\n",
-						__func__);
-		} else
-			dprintk("%s: name too long (%u)!\n",
-					__func__, len);
-		bitmap[1] &= ~FATTR4_WORD1_OWNER_GROUP;
+	if (!(bitmap[1] & FATTR4_WORD1_OWNER_GROUP))
+		return 0;
+	bitmap[1] &= ~FATTR4_WORD1_OWNER_GROUP;
+
+	if (group_name != NULL) {
+		len = decode_nfs4_string(xdr, group_name, GFP_NOWAIT);
+		if (len <= 0)
+			goto out;
+		dprintk("%s: name=%s\n", __func__, group_name->data);
+		return NFS_ATTR_FATTR_GROUP_NAME;
+	} else {
+		len = xdr_stream_decode_opaque_inline(xdr, (void **)&p,
+				XDR_MAX_NETOBJ);
+		if (len <= 0 || nfs_map_group_to_gid(server, p, len, gid) != 0)
+			goto out;
+		dprintk("%s: gid=%d\n", __func__, (int)from_kgid(&init_user_ns, *gid));
+		return NFS_ATTR_FATTR_GROUP;
 	}
-	dprintk("%s: gid=%d\n", __func__, (int)from_kgid(&init_user_ns, *gid));
-	return ret;
-out_overflow:
+out:
+	if (len != -EBADMSG)
+		return 0;
 	print_overflow_msg(__func__, xdr);
 	return -EIO;
 }
@@ -4294,15 +4354,12 @@ out_overflow:
 
 static int decode_opaque_fixed(struct xdr_stream *xdr, void *buf, size_t len)
 {
-	__be32 *p;
-
-	p = xdr_inline_decode(xdr, len);
-	if (likely(p)) {
-		memcpy(buf, p, len);
-		return 0;
+	ssize_t ret = xdr_stream_decode_opaque_fixed(xdr, buf, len);
+	if (unlikely(ret < 0)) {
+		print_overflow_msg(__func__, xdr);
+		return -EIO;
 	}
-	print_overflow_msg(__func__, xdr);
-	return -EIO;
+	return 0;
 }
 
 static int decode_stateid(struct xdr_stream *xdr, nfs4_stateid *stateid)
@@ -5040,6 +5097,11 @@ static int decode_lookup(struct xdr_stream *xdr)
 	return decode_op_hdr(xdr, OP_LOOKUP);
 }
 
+static int decode_lookupp(struct xdr_stream *xdr)
+{
+	return decode_op_hdr(xdr, OP_LOOKUPP);
+}
+
 /* This is too sick! */
 static int decode_space_limit(struct xdr_stream *xdr,
 		unsigned long *pagemod_limit)
@@ -5093,7 +5155,7 @@ static int decode_rw_delegation(struct xdr_stream *xdr,
 		if (decode_space_limit(xdr, &res->pagemod_limit) < 0)
 				return -EIO;
 	}
-	return decode_ace(xdr, NULL, res->server->nfs_client);
+	return decode_ace(xdr, NULL);
 out_overflow:
 	print_overflow_msg(__func__, xdr);
 	return -EIO;
@@ -5600,6 +5662,8 @@ static int decode_op_map(struct xdr_stream *xdr, struct nfs4_op_map *op_map)
 	unsigned int i;
 
 	p = xdr_inline_decode(xdr, 4);
+	if (!p)
+		return -EIO;
 	bitmap_words = be32_to_cpup(p++);
 	if (bitmap_words > NFS4_OP_MAP_NUM_WORDS)
 		return -EIO;
@@ -5660,8 +5724,6 @@ static int decode_exchange_id(struct xdr_stream *xdr,
 	status = decode_opaque_inline(xdr, &dummy, &dummy_str);
 	if (unlikely(status))
 		return status;
-	if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
-		return -EIO;
 	memcpy(res->server_owner->major_id, dummy_str, dummy);
 	res->server_owner->major_id_sz = dummy;
 
@@ -5669,8 +5731,6 @@ static int decode_exchange_id(struct xdr_stream *xdr,
 	status = decode_opaque_inline(xdr, &dummy, &dummy_str);
 	if (unlikely(status))
 		return status;
-	if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
-		return -EIO;
 	memcpy(res->server_scope->server_scope, dummy_str, dummy);
 	res->server_scope->server_scope_sz = dummy;
 
@@ -5685,16 +5745,12 @@ static int decode_exchange_id(struct xdr_stream *xdr,
 		status = decode_opaque_inline(xdr, &dummy, &dummy_str);
 		if (unlikely(status))
 			return status;
-		if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
-			return -EIO;
 		memcpy(res->impl_id->domain, dummy_str, dummy);
 
 		/* nii_name */
 		status = decode_opaque_inline(xdr, &dummy, &dummy_str);
 		if (unlikely(status))
 			return status;
-		if (unlikely(dummy > NFS4_OPAQUE_LIMIT))
-			return -EIO;
 		memcpy(res->impl_id->name, dummy_str, dummy);
 
 		/* nii_date */
@@ -6142,8 +6198,9 @@ int decode_layoutreturn(struct xdr_stream *xdr,
  */
 static int nfs4_xdr_dec_open_downgrade(struct rpc_rqst *rqstp,
 				       struct xdr_stream *xdr,
-				       struct nfs_closeres *res)
+				       void *data)
 {
+	struct nfs_closeres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6171,8 +6228,9 @@ out:
  * Decode ACCESS response
  */
 static int nfs4_xdr_dec_access(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			       struct nfs4_accessres *res)
+			       void *data)
 {
+	struct nfs4_accessres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6197,8 +6255,9 @@ out:
  * Decode LOOKUP response
  */
 static int nfs4_xdr_dec_lookup(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			       struct nfs4_lookup_res *res)
+			       void *data)
 {
+	struct nfs4_lookup_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6223,12 +6282,43 @@ out:
 }
 
 /*
+ * Decode LOOKUPP response
+ */
+static int nfs4_xdr_dec_lookupp(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
+		void *data)
+{
+	struct nfs4_lookupp_res *res = data;
+	struct compound_hdr hdr;
+	int status;
+
+	status = decode_compound_hdr(xdr, &hdr);
+	if (status)
+		goto out;
+	status = decode_sequence(xdr, &res->seq_res, rqstp);
+	if (status)
+		goto out;
+	status = decode_putfh(xdr);
+	if (status)
+		goto out;
+	status = decode_lookupp(xdr);
+	if (status)
+		goto out;
+	status = decode_getfh(xdr, res->fh);
+	if (status)
+		goto out;
+	status = decode_getfattr_label(xdr, res->fattr, res->label, res->server);
+out:
+	return status;
+}
+
+/*
  * Decode LOOKUP_ROOT response
  */
 static int nfs4_xdr_dec_lookup_root(struct rpc_rqst *rqstp,
 				    struct xdr_stream *xdr,
-				    struct nfs4_lookup_res *res)
+				    void *data)
 {
+	struct nfs4_lookup_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6253,8 +6343,9 @@ out:
  * Decode REMOVE response
  */
 static int nfs4_xdr_dec_remove(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			       struct nfs_removeres *res)
+			       void *data)
 {
+	struct nfs_removeres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6276,8 +6367,9 @@ out:
  * Decode RENAME response
  */
 static int nfs4_xdr_dec_rename(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			       struct nfs_renameres *res)
+			       void *data)
 {
+	struct nfs_renameres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6305,8 +6397,9 @@ out:
  * Decode LINK response
  */
 static int nfs4_xdr_dec_link(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			     struct nfs4_link_res *res)
+			     void *data)
 {
+	struct nfs4_link_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6344,8 +6437,9 @@ out:
  * Decode CREATE response
  */
 static int nfs4_xdr_dec_create(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			       struct nfs4_create_res *res)
+			       void *data)
 {
+	struct nfs4_create_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6373,7 +6467,7 @@ out:
  * Decode SYMLINK response
  */
 static int nfs4_xdr_dec_symlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-				struct nfs4_create_res *res)
+				void *res)
 {
 	return nfs4_xdr_dec_create(rqstp, xdr, res);
 }
@@ -6382,8 +6476,9 @@ static int nfs4_xdr_dec_symlink(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
  * Decode GETATTR response
  */
 static int nfs4_xdr_dec_getattr(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-				struct nfs4_getattr_res *res)
+				void *data)
 {
+	struct nfs4_getattr_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6405,8 +6500,9 @@ out:
  * Encode an SETACL request
  */
 static void nfs4_xdr_enc_setacl(struct rpc_rqst *req, struct xdr_stream *xdr,
-				struct nfs_setaclargs *args)
+				const void *data)
 {
+	const struct nfs_setaclargs *args = data;
 	struct compound_hdr hdr = {
 		.minorversion = nfs4_xdr_minorversion(&args->seq_args),
 	};
@@ -6423,8 +6519,9 @@ static void nfs4_xdr_enc_setacl(struct rpc_rqst *req, struct xdr_stream *xdr,
  */
 static int
 nfs4_xdr_dec_setacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-		    struct nfs_setaclres *res)
+		    void *data)
 {
+	struct nfs_setaclres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6447,8 +6544,9 @@ out:
  */
 static int
 nfs4_xdr_dec_getacl(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-		    struct nfs_getaclres *res)
+		    void *data)
 {
+	struct nfs_getaclres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6475,8 +6573,9 @@ out:
  * Decode CLOSE response
  */
 static int nfs4_xdr_dec_close(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			      struct nfs_closeres *res)
+			      void *data)
 {
+	struct nfs_closeres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6509,8 +6608,9 @@ out:
  * Decode OPEN response
  */
 static int nfs4_xdr_dec_open(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			     struct nfs_openres *res)
+			     void *data)
 {
+	struct nfs_openres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6541,8 +6641,9 @@ out:
  */
 static int nfs4_xdr_dec_open_confirm(struct rpc_rqst *rqstp,
 				     struct xdr_stream *xdr,
-				     struct nfs_open_confirmres *res)
+				     void *data)
 {
+	struct nfs_open_confirmres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6562,8 +6663,9 @@ out:
  */
 static int nfs4_xdr_dec_open_noattr(struct rpc_rqst *rqstp,
 				    struct xdr_stream *xdr,
-				    struct nfs_openres *res)
+				    void *data)
 {
+	struct nfs_openres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6591,8 +6693,9 @@ out:
  */
 static int nfs4_xdr_dec_setattr(struct rpc_rqst *rqstp,
 				struct xdr_stream *xdr,
-				struct nfs_setattrres *res)
+				void *data)
 {
+	struct nfs_setattrres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6617,8 +6720,9 @@ out:
  * Decode LOCK response
  */
 static int nfs4_xdr_dec_lock(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			     struct nfs_lock_res *res)
+			     void *data)
 {
+	struct nfs_lock_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6640,8 +6744,9 @@ out:
  * Decode LOCKT response
  */
 static int nfs4_xdr_dec_lockt(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			      struct nfs_lockt_res *res)
+			      void *data)
 {
+	struct nfs_lockt_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6663,8 +6768,9 @@ out:
  * Decode LOCKU response
  */
 static int nfs4_xdr_dec_locku(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			      struct nfs_locku_res *res)
+			      void *data)
 {
+	struct nfs_locku_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6699,8 +6805,9 @@ static int nfs4_xdr_dec_release_lockowner(struct rpc_rqst *rqstp,
  */
 static int nfs4_xdr_dec_readlink(struct rpc_rqst *rqstp,
 				 struct xdr_stream *xdr,
-				 struct nfs4_readlink_res *res)
+				 void *data)
 {
+	struct nfs4_readlink_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6722,8 +6829,9 @@ out:
  * Decode READDIR response
  */
 static int nfs4_xdr_dec_readdir(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-				struct nfs4_readdir_res *res)
+				void *data)
 {
+	struct nfs4_readdir_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6745,8 +6853,9 @@ out:
  * Decode Read response
  */
 static int nfs4_xdr_dec_read(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			     struct nfs_pgio_res *res)
+			     void *data)
 {
+	struct nfs_pgio_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6771,8 +6880,9 @@ out:
  * Decode WRITE response
  */
 static int nfs4_xdr_dec_write(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			      struct nfs_pgio_res *res)
+			      void *data)
 {
+	struct nfs_pgio_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6801,8 +6911,9 @@ out:
  * Decode COMMIT response
  */
 static int nfs4_xdr_dec_commit(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
-			       struct nfs_commitres *res)
+			       void *data)
 {
+	struct nfs_commitres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6825,8 +6936,9 @@ out:
  * Decode FSINFO response
  */
 static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr,
-			       struct nfs4_fsinfo_res *res)
+			       void *data)
 {
+	struct nfs4_fsinfo_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6844,8 +6956,9 @@ static int nfs4_xdr_dec_fsinfo(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Decode PATHCONF response
  */
 static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 struct nfs4_pathconf_res *res)
+				 void *data)
 {
+	struct nfs4_pathconf_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6863,8 +6976,9 @@ static int nfs4_xdr_dec_pathconf(struct rpc_rqst *req, struct xdr_stream *xdr,
  * Decode STATFS response
  */
 static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, struct xdr_stream *xdr,
-			       struct nfs4_statfs_res *res)
+			       void *data)
 {
+	struct nfs4_statfs_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6883,8 +6997,9 @@ static int nfs4_xdr_dec_statfs(struct rpc_rqst *req, struct xdr_stream *xdr,
  */
 static int nfs4_xdr_dec_server_caps(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    struct nfs4_server_caps_res *res)
+				    void *data)
 {
+	struct nfs4_server_caps_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6922,8 +7037,9 @@ static int nfs4_xdr_dec_renew(struct rpc_rqst *rqstp, struct xdr_stream *xdr,
  */
 static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req,
 				    struct xdr_stream *xdr,
-				    struct nfs4_setclientid_res *res)
+				    void *data)
 {
+	struct nfs4_setclientid_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6937,7 +7053,8 @@ static int nfs4_xdr_dec_setclientid(struct rpc_rqst *req,
  * Decode SETCLIENTID_CONFIRM response
  */
 static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req,
-					    struct xdr_stream *xdr)
+					    struct xdr_stream *xdr,
+					    void *data)
 {
 	struct compound_hdr hdr;
 	int status;
@@ -6953,8 +7070,9 @@ static int nfs4_xdr_dec_setclientid_confirm(struct rpc_rqst *req,
  */
 static int nfs4_xdr_dec_delegreturn(struct rpc_rqst *rqstp,
 				    struct xdr_stream *xdr,
-				    struct nfs4_delegreturnres *res)
+				    void *data)
 {
+	struct nfs4_delegreturnres *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -6988,8 +7106,9 @@ out:
  */
 static int nfs4_xdr_dec_fs_locations(struct rpc_rqst *req,
 				     struct xdr_stream *xdr,
-				     struct nfs4_fs_locations_res *res)
+				     void *data)
 {
+	struct nfs4_fs_locations_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -7031,8 +7150,9 @@ out:
  */
 static int nfs4_xdr_dec_secinfo(struct rpc_rqst *rqstp,
 				struct xdr_stream *xdr,
-				struct nfs4_secinfo_res *res)
+				void *data)
 {
+	struct nfs4_secinfo_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -7055,8 +7175,9 @@ out:
  */
 static int nfs4_xdr_dec_fsid_present(struct rpc_rqst *rqstp,
 				     struct xdr_stream *xdr,
-				     struct nfs4_fsid_present_res *res)
+				     void *data)
 {
+	struct nfs4_fsid_present_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -7116,7 +7237,7 @@ static int nfs4_xdr_dec_exchange_id(struct rpc_rqst *rqstp,
  */
 static int nfs4_xdr_dec_create_session(struct rpc_rqst *rqstp,
 				       struct xdr_stream *xdr,
-				       struct nfs41_create_session_res *res)
+				       void *res)
 {
 	struct compound_hdr hdr;
 	int status;
@@ -7164,7 +7285,7 @@ static int nfs4_xdr_dec_destroy_clientid(struct rpc_rqst *rqstp,
  */
 static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp,
 				 struct xdr_stream *xdr,
-				 struct nfs4_sequence_res *res)
+				 void *res)
 {
 	struct compound_hdr hdr;
 	int status;
@@ -7180,8 +7301,9 @@ static int nfs4_xdr_dec_sequence(struct rpc_rqst *rqstp,
  */
 static int nfs4_xdr_dec_get_lease_time(struct rpc_rqst *rqstp,
 				       struct xdr_stream *xdr,
-				       struct nfs4_get_lease_time_res *res)
+				       void *data)
 {
+	struct nfs4_get_lease_time_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -7200,8 +7322,9 @@ static int nfs4_xdr_dec_get_lease_time(struct rpc_rqst *rqstp,
  */
 static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp,
 					 struct xdr_stream *xdr,
-					 struct nfs41_reclaim_complete_res *res)
+					 void *data)
 {
+	struct nfs41_reclaim_complete_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -7218,8 +7341,9 @@ static int nfs4_xdr_dec_reclaim_complete(struct rpc_rqst *rqstp,
  */
 static int nfs4_xdr_dec_getdeviceinfo(struct rpc_rqst *rqstp,
 				      struct xdr_stream *xdr,
-				      struct nfs4_getdeviceinfo_res *res)
+				      void *data)
 {
+	struct nfs4_getdeviceinfo_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -7239,8 +7363,9 @@ out:
  */
 static int nfs4_xdr_dec_layoutget(struct rpc_rqst *rqstp,
 				  struct xdr_stream *xdr,
-				  struct nfs4_layoutget_res *res)
+				  void *data)
 {
+	struct nfs4_layoutget_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -7263,8 +7388,9 @@ out:
  */
 static int nfs4_xdr_dec_layoutreturn(struct rpc_rqst *rqstp,
 				     struct xdr_stream *xdr,
-				     struct nfs4_layoutreturn_res *res)
+				     void *data)
 {
+	struct nfs4_layoutreturn_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -7287,8 +7413,9 @@ out:
  */
 static int nfs4_xdr_dec_layoutcommit(struct rpc_rqst *rqstp,
 				     struct xdr_stream *xdr,
-				     struct nfs4_layoutcommit_res *res)
+				     void *data)
 {
+	struct nfs4_layoutcommit_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -7314,8 +7441,9 @@ out:
  */
 static int nfs4_xdr_dec_secinfo_no_name(struct rpc_rqst *rqstp,
 					struct xdr_stream *xdr,
-					struct nfs4_secinfo_res *res)
+					void *data)
 {
+	struct nfs4_secinfo_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -7338,8 +7466,9 @@ out:
  */
 static int nfs4_xdr_dec_test_stateid(struct rpc_rqst *rqstp,
 				     struct xdr_stream *xdr,
-				     struct nfs41_test_stateid_res *res)
+				     void *data)
 {
+	struct nfs41_test_stateid_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -7359,8 +7488,9 @@ out:
  */
 static int nfs4_xdr_dec_free_stateid(struct rpc_rqst *rqstp,
 				     struct xdr_stream *xdr,
-				     struct nfs41_free_stateid_res *res)
+				     void *data)
 {
+	struct nfs41_free_stateid_res *res = data;
 	struct compound_hdr hdr;
 	int status;
 
@@ -7391,7 +7521,7 @@ out:
  * on a directory already in our cache.
  */
 int nfs4_decode_dirent(struct xdr_stream *xdr, struct nfs_entry *entry,
-		       int plus)
+		       bool plus)
 {
 	unsigned int savep;
 	uint32_t bitmap[3] = {0};
@@ -7525,8 +7655,8 @@ nfs4_stat_to_errno(int stat)
 #define PROC(proc, argtype, restype)				\
 [NFSPROC4_CLNT_##proc] = {					\
 	.p_proc   = NFSPROC4_COMPOUND,				\
-	.p_encode = (kxdreproc_t)nfs4_xdr_##argtype,		\
-	.p_decode = (kxdrdproc_t)nfs4_xdr_##restype,		\
+	.p_encode = nfs4_xdr_##argtype,				\
+	.p_decode = nfs4_xdr_##restype,				\
 	.p_arglen = NFS4_##argtype##_sz,			\
 	.p_replen = NFS4_##restype##_sz,			\
 	.p_statidx = NFSPROC4_CLNT_##proc,			\
@@ -7538,7 +7668,7 @@ nfs4_stat_to_errno(int stat)
 	.p_name = #proc,	\
 }
 
-struct rpc_procinfo	nfs4_procedures[] = {
+const struct rpc_procinfo nfs4_procedures[] = {
 	PROC(READ,		enc_read,		dec_read),
 	PROC(WRITE,		enc_write,		dec_write),
 	PROC(COMMIT,		enc_commit,		dec_commit),
@@ -7558,6 +7688,7 @@ struct rpc_procinfo	nfs4_procedures[] = {
 	PROC(ACCESS,		enc_access,		dec_access),
 	PROC(GETATTR,		enc_getattr,		dec_getattr),
 	PROC(LOOKUP,		enc_lookup,		dec_lookup),
+	PROC(LOOKUPP,		enc_lookupp,		dec_lookupp),
 	PROC(LOOKUP_ROOT,	enc_lookup_root,	dec_lookup_root),
 	PROC(REMOVE,		enc_remove,		dec_remove),
 	PROC(RENAME,		enc_rename,		dec_rename),
@@ -7605,10 +7736,12 @@ struct rpc_procinfo	nfs4_procedures[] = {
 #endif /* CONFIG_NFS_V4_2 */
 };
 
+static unsigned int nfs_version4_counts[ARRAY_SIZE(nfs4_procedures)];
 const struct rpc_version nfs_version4 = {
 	.number			= 4,
 	.nrprocs		= ARRAY_SIZE(nfs4_procedures),
-	.procs			= nfs4_procedures
+	.procs			= nfs4_procedures,
+	.counts			= nfs_version4_counts,
 };
 
 /*
diff --git a/fs/nfs/objlayout/Kbuild b/fs/nfs/objlayout/Kbuild
deleted file mode 100644
index ed30ea072bb8..000000000000
--- a/fs/nfs/objlayout/Kbuild
+++ /dev/null
@@ -1,5 +0,0 @@
-#
-# Makefile for the pNFS Objects Layout Driver kernel module
-#
-objlayoutdriver-y := objio_osd.o pnfs_osd_xdr_cli.o objlayout.o
-obj-$(CONFIG_PNFS_OBJLAYOUT) += objlayoutdriver.o
diff --git a/fs/nfs/objlayout/objio_osd.c b/fs/nfs/objlayout/objio_osd.c
deleted file mode 100644
index 049c1b1f2932..000000000000
--- a/fs/nfs/objlayout/objio_osd.c
+++ /dev/null
@@ -1,675 +0,0 @@
-/*
- *  pNFS Objects layout implementation over open-osd initiator library
- *
- *  Copyright (C) 2009 Panasas Inc. [year of first publication]
- *  All rights reserved.
- *
- *  Benny Halevy <bhalevy@panasas.com>
- *  Boaz Harrosh <ooo@electrozaur.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2
- *  See the file COPYING included with this distribution for more details.
- *
- *  Redistribution and use in source and binary forms, with or without
- *  modification, are permitted provided that the following conditions
- *  are met:
- *
- *  1. Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *  2. Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in the
- *     documentation and/or other materials provided with the distribution.
- *  3. Neither the name of the Panasas company nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/module.h>
-#include <scsi/osd_ore.h>
-
-#include "objlayout.h"
-#include "../internal.h"
-
-#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
-
-struct objio_dev_ent {
-	struct nfs4_deviceid_node id_node;
-	struct ore_dev od;
-};
-
-static void
-objio_free_deviceid_node(struct nfs4_deviceid_node *d)
-{
-	struct objio_dev_ent *de = container_of(d, struct objio_dev_ent, id_node);
-
-	dprintk("%s: free od=%p\n", __func__, de->od.od);
-	osduld_put_device(de->od.od);
-	kfree_rcu(d, rcu);
-}
-
-struct objio_segment {
-	struct pnfs_layout_segment lseg;
-
-	struct ore_layout layout;
-	struct ore_components oc;
-};
-
-static inline struct objio_segment *
-OBJIO_LSEG(struct pnfs_layout_segment *lseg)
-{
-	return container_of(lseg, struct objio_segment, lseg);
-}
-
-struct objio_state {
-	/* Generic layer */
-	struct objlayout_io_res oir;
-
-	bool sync;
-	/*FIXME: Support for extra_bytes at ore_get_rw_state() */
-	struct ore_io_state *ios;
-};
-
-/* Send and wait for a get_device_info of devices in the layout,
-   then look them up with the osd_initiator library */
-struct nfs4_deviceid_node *
-objio_alloc_deviceid_node(struct nfs_server *server, struct pnfs_device *pdev,
-			gfp_t gfp_flags)
-{
-	struct pnfs_osd_deviceaddr *deviceaddr;
-	struct objio_dev_ent *ode = NULL;
-	struct osd_dev *od;
-	struct osd_dev_info odi;
-	bool retry_flag = true;
-	__be32 *p;
-	int err;
-
-	deviceaddr = kzalloc(sizeof(*deviceaddr), gfp_flags);
-	if (!deviceaddr)
-		return NULL;
-
-	p = page_address(pdev->pages[0]);
-	pnfs_osd_xdr_decode_deviceaddr(deviceaddr, p);
-
-	odi.systemid_len = deviceaddr->oda_systemid.len;
-	if (odi.systemid_len > sizeof(odi.systemid)) {
-		dprintk("%s: odi.systemid_len > sizeof(systemid=%zd)\n",
-			__func__, sizeof(odi.systemid));
-		err = -EINVAL;
-		goto out;
-	} else if (odi.systemid_len)
-		memcpy(odi.systemid, deviceaddr->oda_systemid.data,
-		       odi.systemid_len);
-	odi.osdname_len	 = deviceaddr->oda_osdname.len;
-	odi.osdname	 = (u8 *)deviceaddr->oda_osdname.data;
-
-	if (!odi.osdname_len && !odi.systemid_len) {
-		dprintk("%s: !odi.osdname_len && !odi.systemid_len\n",
-			__func__);
-		err = -ENODEV;
-		goto out;
-	}
-
-retry_lookup:
-	od = osduld_info_lookup(&odi);
-	if (IS_ERR(od)) {
-		err = PTR_ERR(od);
-		dprintk("%s: osduld_info_lookup => %d\n", __func__, err);
-		if (err == -ENODEV && retry_flag) {
-			err = objlayout_autologin(deviceaddr);
-			if (likely(!err)) {
-				retry_flag = false;
-				goto retry_lookup;
-			}
-		}
-		goto out;
-	}
-
-	dprintk("Adding new dev_id(%llx:%llx)\n",
-		_DEVID_LO(&pdev->dev_id), _DEVID_HI(&pdev->dev_id));
-
-	ode = kzalloc(sizeof(*ode), gfp_flags);
-	if (!ode) {
-		dprintk("%s: -ENOMEM od=%p\n", __func__, od);
-		goto out;
-	}
-
-	nfs4_init_deviceid_node(&ode->id_node, server, &pdev->dev_id);
-	kfree(deviceaddr);
-
-	ode->od.od = od;
-	return &ode->id_node;
-
-out:
-	kfree(deviceaddr);
-	return NULL;
-}
-
-static void copy_single_comp(struct ore_components *oc, unsigned c,
-			     struct pnfs_osd_object_cred *src_comp)
-{
-	struct ore_comp *ocomp = &oc->comps[c];
-
-	WARN_ON(src_comp->oc_cap_key.cred_len > 0); /* libosd is NO_SEC only */
-	WARN_ON(src_comp->oc_cap.cred_len > sizeof(ocomp->cred));
-
-	ocomp->obj.partition = src_comp->oc_object_id.oid_partition_id;
-	ocomp->obj.id = src_comp->oc_object_id.oid_object_id;
-
-	memcpy(ocomp->cred, src_comp->oc_cap.cred, sizeof(ocomp->cred));
-}
-
-static int __alloc_objio_seg(unsigned numdevs, gfp_t gfp_flags,
-		       struct objio_segment **pseg)
-{
-/*	This is the in memory structure of the objio_segment
- *
- *	struct __alloc_objio_segment {
- *		struct objio_segment olseg;
- *		struct ore_dev *ods[numdevs];
- *		struct ore_comp	comps[numdevs];
- *	} *aolseg;
- *	NOTE: The code as above compiles and runs perfectly. It is elegant,
- *	type safe and compact. At some Past time Linus has decided he does not
- *	like variable length arrays, For the sake of this principal we uglify
- *	the code as below.
- */
-	struct objio_segment *lseg;
-	size_t lseg_size = sizeof(*lseg) +
-			numdevs * sizeof(lseg->oc.ods[0]) +
-			numdevs * sizeof(*lseg->oc.comps);
-
-	lseg = kzalloc(lseg_size, gfp_flags);
-	if (unlikely(!lseg)) {
-		dprintk("%s: Failed allocation numdevs=%d size=%zd\n", __func__,
-			numdevs, lseg_size);
-		return -ENOMEM;
-	}
-
-	lseg->oc.numdevs = numdevs;
-	lseg->oc.single_comp = EC_MULTPLE_COMPS;
-	lseg->oc.ods = (void *)(lseg + 1);
-	lseg->oc.comps = (void *)(lseg->oc.ods + numdevs);
-
-	*pseg = lseg;
-	return 0;
-}
-
-int objio_alloc_lseg(struct pnfs_layout_segment **outp,
-	struct pnfs_layout_hdr *pnfslay,
-	struct pnfs_layout_range *range,
-	struct xdr_stream *xdr,
-	gfp_t gfp_flags)
-{
-	struct nfs_server *server = NFS_SERVER(pnfslay->plh_inode);
-	struct objio_segment *objio_seg;
-	struct pnfs_osd_xdr_decode_layout_iter iter;
-	struct pnfs_osd_layout layout;
-	struct pnfs_osd_object_cred src_comp;
-	unsigned cur_comp;
-	int err;
-
-	err = pnfs_osd_xdr_decode_layout_map(&layout, &iter, xdr);
-	if (unlikely(err))
-		return err;
-
-	err = __alloc_objio_seg(layout.olo_num_comps, gfp_flags, &objio_seg);
-	if (unlikely(err))
-		return err;
-
-	objio_seg->layout.stripe_unit = layout.olo_map.odm_stripe_unit;
-	objio_seg->layout.group_width = layout.olo_map.odm_group_width;
-	objio_seg->layout.group_depth = layout.olo_map.odm_group_depth;
-	objio_seg->layout.mirrors_p1 = layout.olo_map.odm_mirror_cnt + 1;
-	objio_seg->layout.raid_algorithm = layout.olo_map.odm_raid_algorithm;
-
-	err = ore_verify_layout(layout.olo_map.odm_num_comps,
-					  &objio_seg->layout);
-	if (unlikely(err))
-		goto err;
-
-	objio_seg->oc.first_dev = layout.olo_comps_index;
-	cur_comp = 0;
-	while (pnfs_osd_xdr_decode_layout_comp(&src_comp, &iter, xdr, &err)) {
-		struct nfs4_deviceid_node *d;
-		struct objio_dev_ent *ode;
-
-		copy_single_comp(&objio_seg->oc, cur_comp, &src_comp);
-
-		d = nfs4_find_get_deviceid(server,
-				&src_comp.oc_object_id.oid_device_id,
-				pnfslay->plh_lc_cred, gfp_flags);
-		if (!d) {
-			err = -ENXIO;
-			goto err;
-		}
-
-		ode = container_of(d, struct objio_dev_ent, id_node);
-		objio_seg->oc.ods[cur_comp++] = &ode->od;
-	}
-	/* pnfs_osd_xdr_decode_layout_comp returns false on error */
-	if (unlikely(err))
-		goto err;
-
-	*outp = &objio_seg->lseg;
-	return 0;
-
-err:
-	kfree(objio_seg);
-	dprintk("%s: Error: return %d\n", __func__, err);
-	*outp = NULL;
-	return err;
-}
-
-void objio_free_lseg(struct pnfs_layout_segment *lseg)
-{
-	int i;
-	struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
-
-	for (i = 0; i < objio_seg->oc.numdevs; i++) {
-		struct ore_dev *od = objio_seg->oc.ods[i];
-		struct objio_dev_ent *ode;
-
-		if (!od)
-			break;
-		ode = container_of(od, typeof(*ode), od);
-		nfs4_put_deviceid_node(&ode->id_node);
-	}
-	kfree(objio_seg);
-}
-
-static int
-objio_alloc_io_state(struct pnfs_layout_hdr *pnfs_layout_type, bool is_reading,
-	struct pnfs_layout_segment *lseg, struct page **pages, unsigned pgbase,
-	loff_t offset, size_t count, void *rpcdata, gfp_t gfp_flags,
-	struct objio_state **outp)
-{
-	struct objio_segment *objio_seg = OBJIO_LSEG(lseg);
-	struct ore_io_state *ios;
-	int ret;
-	struct __alloc_objio_state {
-		struct objio_state objios;
-		struct pnfs_osd_ioerr ioerrs[objio_seg->oc.numdevs];
-	} *aos;
-
-	aos = kzalloc(sizeof(*aos), gfp_flags);
-	if (unlikely(!aos))
-		return -ENOMEM;
-
-	objlayout_init_ioerrs(&aos->objios.oir, objio_seg->oc.numdevs,
-			aos->ioerrs, rpcdata, pnfs_layout_type);
-
-	ret = ore_get_rw_state(&objio_seg->layout, &objio_seg->oc, is_reading,
-			       offset, count, &ios);
-	if (unlikely(ret)) {
-		kfree(aos);
-		return ret;
-	}
-
-	ios->pages = pages;
-	ios->pgbase = pgbase;
-	ios->private = aos;
-	BUG_ON(ios->nr_pages > (pgbase + count + PAGE_SIZE - 1) >> PAGE_SHIFT);
-
-	aos->objios.sync = 0;
-	aos->objios.ios = ios;
-	*outp = &aos->objios;
-	return 0;
-}
-
-void objio_free_result(struct objlayout_io_res *oir)
-{
-	struct objio_state *objios = container_of(oir, struct objio_state, oir);
-
-	ore_put_io_state(objios->ios);
-	kfree(objios);
-}
-
-static enum pnfs_osd_errno osd_pri_2_pnfs_err(enum osd_err_priority oep)
-{
-	switch (oep) {
-	case OSD_ERR_PRI_NO_ERROR:
-		return (enum pnfs_osd_errno)0;
-
-	case OSD_ERR_PRI_CLEAR_PAGES:
-		BUG_ON(1);
-		return 0;
-
-	case OSD_ERR_PRI_RESOURCE:
-		return PNFS_OSD_ERR_RESOURCE;
-	case OSD_ERR_PRI_BAD_CRED:
-		return PNFS_OSD_ERR_BAD_CRED;
-	case OSD_ERR_PRI_NO_ACCESS:
-		return PNFS_OSD_ERR_NO_ACCESS;
-	case OSD_ERR_PRI_UNREACHABLE:
-		return PNFS_OSD_ERR_UNREACHABLE;
-	case OSD_ERR_PRI_NOT_FOUND:
-		return PNFS_OSD_ERR_NOT_FOUND;
-	case OSD_ERR_PRI_NO_SPACE:
-		return PNFS_OSD_ERR_NO_SPACE;
-	default:
-		WARN_ON(1);
-		/* fallthrough */
-	case OSD_ERR_PRI_EIO:
-		return PNFS_OSD_ERR_EIO;
-	}
-}
-
-static void __on_dev_error(struct ore_io_state *ios,
-	struct ore_dev *od, unsigned dev_index, enum osd_err_priority oep,
-	u64 dev_offset, u64  dev_len)
-{
-	struct objio_state *objios = ios->private;
-	struct pnfs_osd_objid pooid;
-	struct objio_dev_ent *ode = container_of(od, typeof(*ode), od);
-	/* FIXME: what to do with more-then-one-group layouts. We need to
-	 * translate from ore_io_state index to oc->comps index
-	 */
-	unsigned comp = dev_index;
-
-	pooid.oid_device_id = ode->id_node.deviceid;
-	pooid.oid_partition_id = ios->oc->comps[comp].obj.partition;
-	pooid.oid_object_id = ios->oc->comps[comp].obj.id;
-
-	objlayout_io_set_result(&objios->oir, comp,
-				&pooid, osd_pri_2_pnfs_err(oep),
-				dev_offset, dev_len, !ios->reading);
-}
-
-/*
- * read
- */
-static void _read_done(struct ore_io_state *ios, void *private)
-{
-	struct objio_state *objios = private;
-	ssize_t status;
-	int ret = ore_check_io(ios, &__on_dev_error);
-
-	/* FIXME: _io_free(ios) can we dealocate the libosd resources; */
-
-	if (likely(!ret))
-		status = ios->length;
-	else
-		status = ret;
-
-	objlayout_read_done(&objios->oir, status, objios->sync);
-}
-
-int objio_read_pagelist(struct nfs_pgio_header *hdr)
-{
-	struct objio_state *objios;
-	int ret;
-
-	ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, true,
-			hdr->lseg, hdr->args.pages, hdr->args.pgbase,
-			hdr->args.offset, hdr->args.count, hdr,
-			GFP_KERNEL, &objios);
-	if (unlikely(ret))
-		return ret;
-
-	objios->ios->done = _read_done;
-	dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
-		hdr->args.offset, hdr->args.count);
-	ret = ore_read(objios->ios);
-	if (unlikely(ret))
-		objio_free_result(&objios->oir);
-	return ret;
-}
-
-/*
- * write
- */
-static void _write_done(struct ore_io_state *ios, void *private)
-{
-	struct objio_state *objios = private;
-	ssize_t status;
-	int ret = ore_check_io(ios, &__on_dev_error);
-
-	/* FIXME: _io_free(ios) can we dealocate the libosd resources; */
-
-	if (likely(!ret)) {
-		/* FIXME: should be based on the OSD's persistence model
-		 * See OSD2r05 Section 4.13 Data persistence model */
-		objios->oir.committed = NFS_FILE_SYNC;
-		status = ios->length;
-	} else {
-		status = ret;
-	}
-
-	objlayout_write_done(&objios->oir, status, objios->sync);
-}
-
-static struct page *__r4w_get_page(void *priv, u64 offset, bool *uptodate)
-{
-	struct objio_state *objios = priv;
-	struct nfs_pgio_header *hdr = objios->oir.rpcdata;
-	struct address_space *mapping = hdr->inode->i_mapping;
-	pgoff_t index = offset / PAGE_SIZE;
-	struct page *page;
-	loff_t i_size = i_size_read(hdr->inode);
-
-	if (offset >= i_size) {
-		*uptodate = true;
-		dprintk("%s: g_zero_page index=0x%lx\n", __func__, index);
-		return ZERO_PAGE(0);
-	}
-
-	page = find_get_page(mapping, index);
-	if (!page) {
-		page = find_or_create_page(mapping, index, GFP_NOFS);
-		if (unlikely(!page)) {
-			dprintk("%s: grab_cache_page Failed index=0x%lx\n",
-				__func__, index);
-			return NULL;
-		}
-		unlock_page(page);
-	}
-	*uptodate = PageUptodate(page);
-	dprintk("%s: index=0x%lx uptodate=%d\n", __func__, index, *uptodate);
-	return page;
-}
-
-static void __r4w_put_page(void *priv, struct page *page)
-{
-	dprintk("%s: index=0x%lx\n", __func__,
-		(page == ZERO_PAGE(0)) ? -1UL : page->index);
-	if (ZERO_PAGE(0) != page)
-		put_page(page);
-	return;
-}
-
-static const struct _ore_r4w_op _r4w_op = {
-	.get_page = &__r4w_get_page,
-	.put_page = &__r4w_put_page,
-};
-
-int objio_write_pagelist(struct nfs_pgio_header *hdr, int how)
-{
-	struct objio_state *objios;
-	int ret;
-
-	ret = objio_alloc_io_state(NFS_I(hdr->inode)->layout, false,
-			hdr->lseg, hdr->args.pages, hdr->args.pgbase,
-			hdr->args.offset, hdr->args.count, hdr, GFP_NOFS,
-			&objios);
-	if (unlikely(ret))
-		return ret;
-
-	objios->sync = 0 != (how & FLUSH_SYNC);
-	objios->ios->r4w = &_r4w_op;
-
-	if (!objios->sync)
-		objios->ios->done = _write_done;
-
-	dprintk("%s: offset=0x%llx length=0x%x\n", __func__,
-		hdr->args.offset, hdr->args.count);
-	ret = ore_write(objios->ios);
-	if (unlikely(ret)) {
-		objio_free_result(&objios->oir);
-		return ret;
-	}
-
-	if (objios->sync)
-		_write_done(objios->ios, objios);
-
-	return 0;
-}
-
-/*
- * Return 0 if @req cannot be coalesced into @pgio, otherwise return the number
- * of bytes (maximum @req->wb_bytes) that can be coalesced.
- */
-static size_t objio_pg_test(struct nfs_pageio_descriptor *pgio,
-			  struct nfs_page *prev, struct nfs_page *req)
-{
-	struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(pgio);
-	unsigned int size;
-
-	size = pnfs_generic_pg_test(pgio, prev, req);
-
-	if (!size || mirror->pg_count + req->wb_bytes >
-	    (unsigned long)pgio->pg_layout_private)
-		return 0;
-
-	return min(size, req->wb_bytes);
-}
-
-static void objio_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
-{
-	pnfs_generic_pg_init_read(pgio, req);
-	if (unlikely(pgio->pg_lseg == NULL))
-		return; /* Not pNFS */
-
-	pgio->pg_layout_private = (void *)
-				OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
-}
-
-static bool aligned_on_raid_stripe(u64 offset, struct ore_layout *layout,
-				   unsigned long *stripe_end)
-{
-	u32 stripe_off;
-	unsigned stripe_size;
-
-	if (layout->raid_algorithm == PNFS_OSD_RAID_0)
-		return true;
-
-	stripe_size = layout->stripe_unit *
-				(layout->group_width - layout->parity);
-
-	div_u64_rem(offset, stripe_size, &stripe_off);
-	if (!stripe_off)
-		return true;
-
-	*stripe_end = stripe_size - stripe_off;
-	return false;
-}
-
-static void objio_init_write(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
-{
-	unsigned long stripe_end = 0;
-	u64 wb_size;
-
-	if (pgio->pg_dreq == NULL)
-		wb_size = i_size_read(pgio->pg_inode) - req_offset(req);
-	else
-		wb_size = nfs_dreq_bytes_left(pgio->pg_dreq);
-
-	pnfs_generic_pg_init_write(pgio, req, wb_size);
-	if (unlikely(pgio->pg_lseg == NULL))
-		return; /* Not pNFS */
-
-	if (req->wb_offset ||
-	    !aligned_on_raid_stripe(req->wb_index * PAGE_SIZE,
-			       &OBJIO_LSEG(pgio->pg_lseg)->layout,
-			       &stripe_end)) {
-		pgio->pg_layout_private = (void *)stripe_end;
-	} else {
-		pgio->pg_layout_private = (void *)
-				OBJIO_LSEG(pgio->pg_lseg)->layout.max_io_length;
-	}
-}
-
-static const struct nfs_pageio_ops objio_pg_read_ops = {
-	.pg_init = objio_init_read,
-	.pg_test = objio_pg_test,
-	.pg_doio = pnfs_generic_pg_readpages,
-	.pg_cleanup = pnfs_generic_pg_cleanup,
-};
-
-static const struct nfs_pageio_ops objio_pg_write_ops = {
-	.pg_init = objio_init_write,
-	.pg_test = objio_pg_test,
-	.pg_doio = pnfs_generic_pg_writepages,
-	.pg_cleanup = pnfs_generic_pg_cleanup,
-};
-
-static struct pnfs_layoutdriver_type objlayout_type = {
-	.id = LAYOUT_OSD2_OBJECTS,
-	.name = "LAYOUT_OSD2_OBJECTS",
-	.flags                   = PNFS_LAYOUTRET_ON_SETATTR |
-				   PNFS_LAYOUTRET_ON_ERROR,
-
-	.max_deviceinfo_size	 = PAGE_SIZE,
-	.owner		       	 = THIS_MODULE,
-	.alloc_layout_hdr        = objlayout_alloc_layout_hdr,
-	.free_layout_hdr         = objlayout_free_layout_hdr,
-
-	.alloc_lseg              = objlayout_alloc_lseg,
-	.free_lseg               = objlayout_free_lseg,
-
-	.read_pagelist           = objlayout_read_pagelist,
-	.write_pagelist          = objlayout_write_pagelist,
-	.pg_read_ops             = &objio_pg_read_ops,
-	.pg_write_ops            = &objio_pg_write_ops,
-
-	.sync			 = pnfs_generic_sync,
-
-	.free_deviceid_node	 = objio_free_deviceid_node,
-
-	.encode_layoutcommit	 = objlayout_encode_layoutcommit,
-	.encode_layoutreturn     = objlayout_encode_layoutreturn,
-};
-
-MODULE_DESCRIPTION("pNFS Layout Driver for OSD2 objects");
-MODULE_AUTHOR("Benny Halevy <bhalevy@panasas.com>");
-MODULE_LICENSE("GPL");
-
-static int __init
-objlayout_init(void)
-{
-	int ret = pnfs_register_layoutdriver(&objlayout_type);
-
-	if (ret)
-		printk(KERN_INFO
-			"NFS: %s: Registering OSD pNFS Layout Driver failed: error=%d\n",
-			__func__, ret);
-	else
-		printk(KERN_INFO "NFS: %s: Registered OSD pNFS Layout Driver\n",
-			__func__);
-	return ret;
-}
-
-static void __exit
-objlayout_exit(void)
-{
-	pnfs_unregister_layoutdriver(&objlayout_type);
-	printk(KERN_INFO "NFS: %s: Unregistered OSD pNFS Layout Driver\n",
-	       __func__);
-}
-
-MODULE_ALIAS("nfs-layouttype4-2");
-
-module_init(objlayout_init);
-module_exit(objlayout_exit);
diff --git a/fs/nfs/objlayout/objlayout.c b/fs/nfs/objlayout/objlayout.c
deleted file mode 100644
index 2a4cdce939a0..000000000000
--- a/fs/nfs/objlayout/objlayout.c
+++ /dev/null
@@ -1,706 +0,0 @@
-/*
- *  pNFS Objects layout driver high level definitions
- *
- *  Copyright (C) 2007 Panasas Inc. [year of first publication]
- *  All rights reserved.
- *
- *  Benny Halevy <bhalevy@panasas.com>
- *  Boaz Harrosh <ooo@electrozaur.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2
- *  See the file COPYING included with this distribution for more details.
- *
- *  Redistribution and use in source and binary forms, with or without
- *  modification, are permitted provided that the following conditions
- *  are met:
- *
- *  1. Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *  2. Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in the
- *     documentation and/or other materials provided with the distribution.
- *  3. Neither the name of the Panasas company nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/kmod.h>
-#include <linux/moduleparam.h>
-#include <linux/ratelimit.h>
-#include <scsi/osd_initiator.h>
-#include "objlayout.h"
-
-#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
-/*
- * Create a objlayout layout structure for the given inode and return it.
- */
-struct pnfs_layout_hdr *
-objlayout_alloc_layout_hdr(struct inode *inode, gfp_t gfp_flags)
-{
-	struct objlayout *objlay;
-
-	objlay = kzalloc(sizeof(struct objlayout), gfp_flags);
-	if (!objlay)
-		return NULL;
-	spin_lock_init(&objlay->lock);
-	INIT_LIST_HEAD(&objlay->err_list);
-	dprintk("%s: Return %p\n", __func__, objlay);
-	return &objlay->pnfs_layout;
-}
-
-/*
- * Free an objlayout layout structure
- */
-void
-objlayout_free_layout_hdr(struct pnfs_layout_hdr *lo)
-{
-	struct objlayout *objlay = OBJLAYOUT(lo);
-
-	dprintk("%s: objlay %p\n", __func__, objlay);
-
-	WARN_ON(!list_empty(&objlay->err_list));
-	kfree(objlay);
-}
-
-/*
- * Unmarshall layout and store it in pnfslay.
- */
-struct pnfs_layout_segment *
-objlayout_alloc_lseg(struct pnfs_layout_hdr *pnfslay,
-		     struct nfs4_layoutget_res *lgr,
-		     gfp_t gfp_flags)
-{
-	int status = -ENOMEM;
-	struct xdr_stream stream;
-	struct xdr_buf buf = {
-		.pages =  lgr->layoutp->pages,
-		.page_len =  lgr->layoutp->len,
-		.buflen =  lgr->layoutp->len,
-		.len = lgr->layoutp->len,
-	};
-	struct page *scratch;
-	struct pnfs_layout_segment *lseg;
-
-	dprintk("%s: Begin pnfslay %p\n", __func__, pnfslay);
-
-	scratch = alloc_page(gfp_flags);
-	if (!scratch)
-		goto err_nofree;
-
-	xdr_init_decode(&stream, &buf, NULL);
-	xdr_set_scratch_buffer(&stream, page_address(scratch), PAGE_SIZE);
-
-	status = objio_alloc_lseg(&lseg, pnfslay, &lgr->range, &stream, gfp_flags);
-	if (unlikely(status)) {
-		dprintk("%s: objio_alloc_lseg Return err %d\n", __func__,
-			status);
-		goto err;
-	}
-
-	__free_page(scratch);
-
-	dprintk("%s: Return %p\n", __func__, lseg);
-	return lseg;
-
-err:
-	__free_page(scratch);
-err_nofree:
-	dprintk("%s: Err Return=>%d\n", __func__, status);
-	return ERR_PTR(status);
-}
-
-/*
- * Free a layout segement
- */
-void
-objlayout_free_lseg(struct pnfs_layout_segment *lseg)
-{
-	dprintk("%s: freeing layout segment %p\n", __func__, lseg);
-
-	if (unlikely(!lseg))
-		return;
-
-	objio_free_lseg(lseg);
-}
-
-/*
- * I/O Operations
- */
-static inline u64
-end_offset(u64 start, u64 len)
-{
-	u64 end;
-
-	end = start + len;
-	return end >= start ? end : NFS4_MAX_UINT64;
-}
-
-static void _fix_verify_io_params(struct pnfs_layout_segment *lseg,
-			   struct page ***p_pages, unsigned *p_pgbase,
-			   u64 offset, unsigned long count)
-{
-	u64 lseg_end_offset;
-
-	BUG_ON(offset < lseg->pls_range.offset);
-	lseg_end_offset = end_offset(lseg->pls_range.offset,
-				     lseg->pls_range.length);
-	BUG_ON(offset >= lseg_end_offset);
-	WARN_ON(offset + count > lseg_end_offset);
-
-	if (*p_pgbase > PAGE_SIZE) {
-		dprintk("%s: pgbase(0x%x) > PAGE_SIZE\n", __func__, *p_pgbase);
-		*p_pages += *p_pgbase >> PAGE_SHIFT;
-		*p_pgbase &= ~PAGE_MASK;
-	}
-}
-
-/*
- * I/O done common code
- */
-static void
-objlayout_iodone(struct objlayout_io_res *oir)
-{
-	if (likely(oir->status >= 0)) {
-		objio_free_result(oir);
-	} else {
-		struct objlayout *objlay = oir->objlay;
-
-		spin_lock(&objlay->lock);
-		objlay->delta_space_valid = OBJ_DSU_INVALID;
-		list_add(&objlay->err_list, &oir->err_list);
-		spin_unlock(&objlay->lock);
-	}
-}
-
-/*
- * objlayout_io_set_result - Set an osd_error code on a specific osd comp.
- *
- * The @index component IO failed (error returned from target). Register
- * the error for later reporting at layout-return.
- */
-void
-objlayout_io_set_result(struct objlayout_io_res *oir, unsigned index,
-			struct pnfs_osd_objid *pooid, int osd_error,
-			u64 offset, u64 length, bool is_write)
-{
-	struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[index];
-
-	BUG_ON(index >= oir->num_comps);
-	if (osd_error) {
-		ioerr->oer_component = *pooid;
-		ioerr->oer_comp_offset = offset;
-		ioerr->oer_comp_length = length;
-		ioerr->oer_iswrite = is_write;
-		ioerr->oer_errno = osd_error;
-
-		dprintk("%s: err[%d]: errno=%d is_write=%d dev(%llx:%llx) "
-			"par=0x%llx obj=0x%llx offset=0x%llx length=0x%llx\n",
-			__func__, index, ioerr->oer_errno,
-			ioerr->oer_iswrite,
-			_DEVID_LO(&ioerr->oer_component.oid_device_id),
-			_DEVID_HI(&ioerr->oer_component.oid_device_id),
-			ioerr->oer_component.oid_partition_id,
-			ioerr->oer_component.oid_object_id,
-			ioerr->oer_comp_offset,
-			ioerr->oer_comp_length);
-	} else {
-		/* User need not call if no error is reported */
-		ioerr->oer_errno = 0;
-	}
-}
-
-/* Function scheduled on rpc workqueue to call ->nfs_readlist_complete().
- * This is because the osd completion is called with ints-off from
- * the block layer
- */
-static void _rpc_read_complete(struct work_struct *work)
-{
-	struct rpc_task *task;
-	struct nfs_pgio_header *hdr;
-
-	dprintk("%s enter\n", __func__);
-	task = container_of(work, struct rpc_task, u.tk_work);
-	hdr = container_of(task, struct nfs_pgio_header, task);
-
-	pnfs_ld_read_done(hdr);
-}
-
-void
-objlayout_read_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
-{
-	struct nfs_pgio_header *hdr = oir->rpcdata;
-
-	oir->status = hdr->task.tk_status = status;
-	if (status >= 0)
-		hdr->res.count = status;
-	else
-		hdr->pnfs_error = status;
-	objlayout_iodone(oir);
-	/* must not use oir after this point */
-
-	dprintk("%s: Return status=%zd eof=%d sync=%d\n", __func__,
-		status, hdr->res.eof, sync);
-
-	if (sync)
-		pnfs_ld_read_done(hdr);
-	else {
-		INIT_WORK(&hdr->task.u.tk_work, _rpc_read_complete);
-		schedule_work(&hdr->task.u.tk_work);
-	}
-}
-
-/*
- * Perform sync or async reads.
- */
-enum pnfs_try_status
-objlayout_read_pagelist(struct nfs_pgio_header *hdr)
-{
-	struct inode *inode = hdr->inode;
-	loff_t offset = hdr->args.offset;
-	size_t count = hdr->args.count;
-	int err;
-	loff_t eof;
-
-	eof = i_size_read(inode);
-	if (unlikely(offset + count > eof)) {
-		if (offset >= eof) {
-			err = 0;
-			hdr->res.count = 0;
-			hdr->res.eof = 1;
-			/*FIXME: do we need to call pnfs_ld_read_done() */
-			goto out;
-		}
-		count = eof - offset;
-	}
-
-	hdr->res.eof = (offset + count) >= eof;
-	_fix_verify_io_params(hdr->lseg, &hdr->args.pages,
-			      &hdr->args.pgbase,
-			      hdr->args.offset, hdr->args.count);
-
-	dprintk("%s: inode(%lx) offset 0x%llx count 0x%Zx eof=%d\n",
-		__func__, inode->i_ino, offset, count, hdr->res.eof);
-
-	err = objio_read_pagelist(hdr);
- out:
-	if (unlikely(err)) {
-		hdr->pnfs_error = err;
-		dprintk("%s: Returned Error %d\n", __func__, err);
-		return PNFS_NOT_ATTEMPTED;
-	}
-	return PNFS_ATTEMPTED;
-}
-
-/* Function scheduled on rpc workqueue to call ->nfs_writelist_complete().
- * This is because the osd completion is called with ints-off from
- * the block layer
- */
-static void _rpc_write_complete(struct work_struct *work)
-{
-	struct rpc_task *task;
-	struct nfs_pgio_header *hdr;
-
-	dprintk("%s enter\n", __func__);
-	task = container_of(work, struct rpc_task, u.tk_work);
-	hdr = container_of(task, struct nfs_pgio_header, task);
-
-	pnfs_ld_write_done(hdr);
-}
-
-void
-objlayout_write_done(struct objlayout_io_res *oir, ssize_t status, bool sync)
-{
-	struct nfs_pgio_header *hdr = oir->rpcdata;
-
-	oir->status = hdr->task.tk_status = status;
-	if (status >= 0) {
-		hdr->res.count = status;
-		hdr->verf.committed = oir->committed;
-	} else {
-		hdr->pnfs_error = status;
-	}
-	objlayout_iodone(oir);
-	/* must not use oir after this point */
-
-	dprintk("%s: Return status %zd committed %d sync=%d\n", __func__,
-		status, hdr->verf.committed, sync);
-
-	if (sync)
-		pnfs_ld_write_done(hdr);
-	else {
-		INIT_WORK(&hdr->task.u.tk_work, _rpc_write_complete);
-		schedule_work(&hdr->task.u.tk_work);
-	}
-}
-
-/*
- * Perform sync or async writes.
- */
-enum pnfs_try_status
-objlayout_write_pagelist(struct nfs_pgio_header *hdr, int how)
-{
-	int err;
-
-	_fix_verify_io_params(hdr->lseg, &hdr->args.pages,
-			      &hdr->args.pgbase,
-			      hdr->args.offset, hdr->args.count);
-
-	err = objio_write_pagelist(hdr, how);
-	if (unlikely(err)) {
-		hdr->pnfs_error = err;
-		dprintk("%s: Returned Error %d\n", __func__, err);
-		return PNFS_NOT_ATTEMPTED;
-	}
-	return PNFS_ATTEMPTED;
-}
-
-void
-objlayout_encode_layoutcommit(struct pnfs_layout_hdr *pnfslay,
-			      struct xdr_stream *xdr,
-			      const struct nfs4_layoutcommit_args *args)
-{
-	struct objlayout *objlay = OBJLAYOUT(pnfslay);
-	struct pnfs_osd_layoutupdate lou;
-	__be32 *start;
-
-	dprintk("%s: Begin\n", __func__);
-
-	spin_lock(&objlay->lock);
-	lou.dsu_valid = (objlay->delta_space_valid == OBJ_DSU_VALID);
-	lou.dsu_delta = objlay->delta_space_used;
-	objlay->delta_space_used = 0;
-	objlay->delta_space_valid = OBJ_DSU_INIT;
-	lou.olu_ioerr_flag = !list_empty(&objlay->err_list);
-	spin_unlock(&objlay->lock);
-
-	start = xdr_reserve_space(xdr, 4);
-
-	BUG_ON(pnfs_osd_xdr_encode_layoutupdate(xdr, &lou));
-
-	*start = cpu_to_be32((xdr->p - start - 1) * 4);
-
-	dprintk("%s: Return delta_space_used %lld err %d\n", __func__,
-		lou.dsu_delta, lou.olu_ioerr_flag);
-}
-
-static int
-err_prio(u32 oer_errno)
-{
-	switch (oer_errno) {
-	case 0:
-		return 0;
-
-	case PNFS_OSD_ERR_RESOURCE:
-		return OSD_ERR_PRI_RESOURCE;
-	case PNFS_OSD_ERR_BAD_CRED:
-		return OSD_ERR_PRI_BAD_CRED;
-	case PNFS_OSD_ERR_NO_ACCESS:
-		return OSD_ERR_PRI_NO_ACCESS;
-	case PNFS_OSD_ERR_UNREACHABLE:
-		return OSD_ERR_PRI_UNREACHABLE;
-	case PNFS_OSD_ERR_NOT_FOUND:
-		return OSD_ERR_PRI_NOT_FOUND;
-	case PNFS_OSD_ERR_NO_SPACE:
-		return OSD_ERR_PRI_NO_SPACE;
-	default:
-		WARN_ON(1);
-		/* fallthrough */
-	case PNFS_OSD_ERR_EIO:
-		return OSD_ERR_PRI_EIO;
-	}
-}
-
-static void
-merge_ioerr(struct pnfs_osd_ioerr *dest_err,
-	    const struct pnfs_osd_ioerr *src_err)
-{
-	u64 dest_end, src_end;
-
-	if (!dest_err->oer_errno) {
-		*dest_err = *src_err;
-		/* accumulated device must be blank */
-		memset(&dest_err->oer_component.oid_device_id, 0,
-			sizeof(dest_err->oer_component.oid_device_id));
-
-		return;
-	}
-
-	if (dest_err->oer_component.oid_partition_id !=
-				src_err->oer_component.oid_partition_id)
-		dest_err->oer_component.oid_partition_id = 0;
-
-	if (dest_err->oer_component.oid_object_id !=
-				src_err->oer_component.oid_object_id)
-		dest_err->oer_component.oid_object_id = 0;
-
-	if (dest_err->oer_comp_offset > src_err->oer_comp_offset)
-		dest_err->oer_comp_offset = src_err->oer_comp_offset;
-
-	dest_end = end_offset(dest_err->oer_comp_offset,
-			      dest_err->oer_comp_length);
-	src_end =  end_offset(src_err->oer_comp_offset,
-			      src_err->oer_comp_length);
-	if (dest_end < src_end)
-		dest_end = src_end;
-
-	dest_err->oer_comp_length = dest_end - dest_err->oer_comp_offset;
-
-	if ((src_err->oer_iswrite == dest_err->oer_iswrite) &&
-	    (err_prio(src_err->oer_errno) > err_prio(dest_err->oer_errno))) {
-			dest_err->oer_errno = src_err->oer_errno;
-	} else if (src_err->oer_iswrite) {
-		dest_err->oer_iswrite = true;
-		dest_err->oer_errno = src_err->oer_errno;
-	}
-}
-
-static void
-encode_accumulated_error(struct objlayout *objlay, __be32 *p)
-{
-	struct objlayout_io_res *oir, *tmp;
-	struct pnfs_osd_ioerr accumulated_err = {.oer_errno = 0};
-
-	list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) {
-		unsigned i;
-
-		for (i = 0; i < oir->num_comps; i++) {
-			struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i];
-
-			if (!ioerr->oer_errno)
-				continue;
-
-			printk(KERN_ERR "NFS: %s: err[%d]: errno=%d "
-				"is_write=%d dev(%llx:%llx) par=0x%llx "
-				"obj=0x%llx offset=0x%llx length=0x%llx\n",
-				__func__, i, ioerr->oer_errno,
-				ioerr->oer_iswrite,
-				_DEVID_LO(&ioerr->oer_component.oid_device_id),
-				_DEVID_HI(&ioerr->oer_component.oid_device_id),
-				ioerr->oer_component.oid_partition_id,
-				ioerr->oer_component.oid_object_id,
-				ioerr->oer_comp_offset,
-				ioerr->oer_comp_length);
-
-			merge_ioerr(&accumulated_err, ioerr);
-		}
-		list_del(&oir->err_list);
-		objio_free_result(oir);
-	}
-
-	pnfs_osd_xdr_encode_ioerr(p, &accumulated_err);
-}
-
-void
-objlayout_encode_layoutreturn(struct xdr_stream *xdr,
-			      const struct nfs4_layoutreturn_args *args)
-{
-	struct pnfs_layout_hdr *pnfslay = args->layout;
-	struct objlayout *objlay = OBJLAYOUT(pnfslay);
-	struct objlayout_io_res *oir, *tmp;
-	__be32 *start;
-
-	dprintk("%s: Begin\n", __func__);
-	start = xdr_reserve_space(xdr, 4);
-	BUG_ON(!start);
-
-	spin_lock(&objlay->lock);
-
-	list_for_each_entry_safe(oir, tmp, &objlay->err_list, err_list) {
-		__be32 *last_xdr = NULL, *p;
-		unsigned i;
-		int res = 0;
-
-		for (i = 0; i < oir->num_comps; i++) {
-			struct pnfs_osd_ioerr *ioerr = &oir->ioerrs[i];
-
-			if (!ioerr->oer_errno)
-				continue;
-
-			dprintk("%s: err[%d]: errno=%d is_write=%d "
-				"dev(%llx:%llx) par=0x%llx obj=0x%llx "
-				"offset=0x%llx length=0x%llx\n",
-				__func__, i, ioerr->oer_errno,
-				ioerr->oer_iswrite,
-				_DEVID_LO(&ioerr->oer_component.oid_device_id),
-				_DEVID_HI(&ioerr->oer_component.oid_device_id),
-				ioerr->oer_component.oid_partition_id,
-				ioerr->oer_component.oid_object_id,
-				ioerr->oer_comp_offset,
-				ioerr->oer_comp_length);
-
-			p = pnfs_osd_xdr_ioerr_reserve_space(xdr);
-			if (unlikely(!p)) {
-				res = -E2BIG;
-				break; /* accumulated_error */
-			}
-
-			last_xdr = p;
-			pnfs_osd_xdr_encode_ioerr(p, &oir->ioerrs[i]);
-		}
-
-		/* TODO: use xdr_write_pages */
-		if (unlikely(res)) {
-			/* no space for even one error descriptor */
-			BUG_ON(!last_xdr);
-
-			/* we've encountered a situation with lots and lots of
-			 * errors and no space to encode them all. Use the last
-			 * available slot to report the union of all the
-			 * remaining errors.
-			 */
-			encode_accumulated_error(objlay, last_xdr);
-			goto loop_done;
-		}
-		list_del(&oir->err_list);
-		objio_free_result(oir);
-	}
-loop_done:
-	spin_unlock(&objlay->lock);
-
-	*start = cpu_to_be32((xdr->p - start - 1) * 4);
-	dprintk("%s: Return\n", __func__);
-}
-
-enum {
-	OBJLAYOUT_MAX_URI_LEN = 256, OBJLAYOUT_MAX_OSDNAME_LEN = 64,
-	OBJLAYOUT_MAX_SYSID_HEX_LEN = OSD_SYSTEMID_LEN * 2 + 1,
-	OSD_LOGIN_UPCALL_PATHLEN  = 256
-};
-
-static char osd_login_prog[OSD_LOGIN_UPCALL_PATHLEN] = "/sbin/osd_login";
-
-module_param_string(osd_login_prog, osd_login_prog, sizeof(osd_login_prog),
-		    0600);
-MODULE_PARM_DESC(osd_login_prog, "Path to the osd_login upcall program");
-
-struct __auto_login {
-	char uri[OBJLAYOUT_MAX_URI_LEN];
-	char osdname[OBJLAYOUT_MAX_OSDNAME_LEN];
-	char systemid_hex[OBJLAYOUT_MAX_SYSID_HEX_LEN];
-};
-
-static int __objlayout_upcall(struct __auto_login *login)
-{
-	static char *envp[] = { "HOME=/",
-		"TERM=linux",
-		"PATH=/sbin:/usr/sbin:/bin:/usr/bin",
-		NULL
-	};
-	char *argv[8];
-	int ret;
-
-	if (unlikely(!osd_login_prog[0])) {
-		dprintk("%s: osd_login_prog is disabled\n", __func__);
-		return -EACCES;
-	}
-
-	dprintk("%s uri: %s\n", __func__, login->uri);
-	dprintk("%s osdname %s\n", __func__, login->osdname);
-	dprintk("%s systemid_hex %s\n", __func__, login->systemid_hex);
-
-	argv[0] = (char *)osd_login_prog;
-	argv[1] = "-u";
-	argv[2] = login->uri;
-	argv[3] = "-o";
-	argv[4] = login->osdname;
-	argv[5] = "-s";
-	argv[6] = login->systemid_hex;
-	argv[7] = NULL;
-
-	ret = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
-	/*
-	 * Disable the upcall mechanism if we're getting an ENOENT or
-	 * EACCES error. The admin can re-enable it on the fly by using
-	 * sysfs to set the objlayoutdriver.osd_login_prog module parameter once
-	 * the problem has been fixed.
-	 */
-	if (ret == -ENOENT || ret == -EACCES) {
-		printk(KERN_ERR "PNFS-OBJ: %s was not found please set "
-			"objlayoutdriver.osd_login_prog kernel parameter!\n",
-			osd_login_prog);
-		osd_login_prog[0] = '\0';
-	}
-	dprintk("%s %s return value: %d\n", __func__, osd_login_prog, ret);
-
-	return ret;
-}
-
-/* Assume dest is all zeros */
-static void __copy_nfsS_and_zero_terminate(struct nfs4_string s,
-					   char *dest, int max_len,
-					   const char *var_name)
-{
-	if (!s.len)
-		return;
-
-	if (s.len >= max_len) {
-		pr_warn_ratelimited(
-			"objlayout_autologin: %s: s.len(%d) >= max_len(%d)",
-			var_name, s.len, max_len);
-		s.len = max_len - 1; /* space for null terminator */
-	}
-
-	memcpy(dest, s.data, s.len);
-}
-
-/* Assume sysid is all zeros */
-static void _sysid_2_hex(struct nfs4_string s,
-		  char sysid[OBJLAYOUT_MAX_SYSID_HEX_LEN])
-{
-	int i;
-	char *cur;
-
-	if (!s.len)
-		return;
-
-	if (s.len != OSD_SYSTEMID_LEN) {
-		pr_warn_ratelimited(
-		    "objlayout_autologin: systemid_len(%d) != OSD_SYSTEMID_LEN",
-		    s.len);
-		if (s.len > OSD_SYSTEMID_LEN)
-			s.len = OSD_SYSTEMID_LEN;
-	}
-
-	cur = sysid;
-	for (i = 0; i < s.len; i++)
-		cur = hex_byte_pack(cur, s.data[i]);
-}
-
-int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr)
-{
-	int rc;
-	struct __auto_login login;
-
-	if (!deviceaddr->oda_targetaddr.ota_netaddr.r_addr.len)
-		return -ENODEV;
-
-	memset(&login, 0, sizeof(login));
-	__copy_nfsS_and_zero_terminate(
-		deviceaddr->oda_targetaddr.ota_netaddr.r_addr,
-		login.uri, sizeof(login.uri), "URI");
-
-	__copy_nfsS_and_zero_terminate(
-		deviceaddr->oda_osdname,
-		login.osdname, sizeof(login.osdname), "OSDNAME");
-
-	_sysid_2_hex(deviceaddr->oda_systemid, login.systemid_hex);
-
-	rc = __objlayout_upcall(&login);
-	if (rc > 0) /* script returns positive values */
-		rc = -ENODEV;
-
-	return rc;
-}
diff --git a/fs/nfs/objlayout/objlayout.h b/fs/nfs/objlayout/objlayout.h
deleted file mode 100644
index fc94a5872ed4..000000000000
--- a/fs/nfs/objlayout/objlayout.h
+++ /dev/null
@@ -1,183 +0,0 @@
-/*
- *  Data types and function declerations for interfacing with the
- *  pNFS standard object layout driver.
- *
- *  Copyright (C) 2007 Panasas Inc. [year of first publication]
- *  All rights reserved.
- *
- *  Benny Halevy <bhalevy@panasas.com>
- *  Boaz Harrosh <ooo@electrozaur.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2
- *  See the file COPYING included with this distribution for more details.
- *
- *  Redistribution and use in source and binary forms, with or without
- *  modification, are permitted provided that the following conditions
- *  are met:
- *
- *  1. Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *  2. Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in the
- *     documentation and/or other materials provided with the distribution.
- *  3. Neither the name of the Panasas company nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#ifndef _OBJLAYOUT_H
-#define _OBJLAYOUT_H
-
-#include <linux/nfs_fs.h>
-#include <linux/pnfs_osd_xdr.h>
-#include "../pnfs.h"
-
-/*
- * per-inode layout
- */
-struct objlayout {
-	struct pnfs_layout_hdr pnfs_layout;
-
-	 /* for layout_commit */
-	enum osd_delta_space_valid_enum {
-		OBJ_DSU_INIT = 0,
-		OBJ_DSU_VALID,
-		OBJ_DSU_INVALID,
-	} delta_space_valid;
-	s64 delta_space_used;  /* consumed by write ops */
-
-	 /* for layout_return */
-	spinlock_t lock;
-	struct list_head err_list;
-};
-
-static inline struct objlayout *
-OBJLAYOUT(struct pnfs_layout_hdr *lo)
-{
-	return container_of(lo, struct objlayout, pnfs_layout);
-}
-
-/*
- * per-I/O operation state
- * embedded in objects provider io_state data structure
- */
-struct objlayout_io_res {
-	struct objlayout *objlay;
-
-	void *rpcdata;
-	int status;             /* res */
-	int committed;          /* res */
-
-	/* Error reporting (layout_return) */
-	struct list_head err_list;
-	unsigned num_comps;
-	/* Pointer to array of error descriptors of size num_comps.
-	 * It should contain as many entries as devices in the osd_layout
-	 * that participate in the I/O. It is up to the io_engine to allocate
-	 * needed space and set num_comps.
-	 */
-	struct pnfs_osd_ioerr *ioerrs;
-};
-
-static inline
-void objlayout_init_ioerrs(struct objlayout_io_res *oir, unsigned num_comps,
-			struct pnfs_osd_ioerr *ioerrs, void *rpcdata,
-			struct pnfs_layout_hdr *pnfs_layout_type)
-{
-	oir->objlay = OBJLAYOUT(pnfs_layout_type);
-	oir->rpcdata = rpcdata;
-	INIT_LIST_HEAD(&oir->err_list);
-	oir->num_comps = num_comps;
-	oir->ioerrs = ioerrs;
-}
-
-/*
- * Raid engine I/O API
- */
-extern int objio_alloc_lseg(struct pnfs_layout_segment **outp,
-	struct pnfs_layout_hdr *pnfslay,
-	struct pnfs_layout_range *range,
-	struct xdr_stream *xdr,
-	gfp_t gfp_flags);
-extern void objio_free_lseg(struct pnfs_layout_segment *lseg);
-
-/* objio_free_result will free these @oir structs received from
- * objlayout_{read,write}_done
- */
-extern void objio_free_result(struct objlayout_io_res *oir);
-
-extern int objio_read_pagelist(struct nfs_pgio_header *rdata);
-extern int objio_write_pagelist(struct nfs_pgio_header *wdata, int how);
-
-/*
- * callback API
- */
-extern void objlayout_io_set_result(struct objlayout_io_res *oir,
-			unsigned index, struct pnfs_osd_objid *pooid,
-			int osd_error, u64 offset, u64 length, bool is_write);
-
-static inline void
-objlayout_add_delta_space_used(struct objlayout *objlay, s64 space_used)
-{
-	/* If one of the I/Os errored out and the delta_space_used was
-	 * invalid we render the complete report as invalid. Protocol mandate
-	 * the DSU be accurate or not reported.
-	 */
-	spin_lock(&objlay->lock);
-	if (objlay->delta_space_valid != OBJ_DSU_INVALID) {
-		objlay->delta_space_valid = OBJ_DSU_VALID;
-		objlay->delta_space_used += space_used;
-	}
-	spin_unlock(&objlay->lock);
-}
-
-extern void objlayout_read_done(struct objlayout_io_res *oir,
-				ssize_t status, bool sync);
-extern void objlayout_write_done(struct objlayout_io_res *oir,
-				 ssize_t status, bool sync);
-
-/*
- * exported generic objects function vectors
- */
-
-extern struct pnfs_layout_hdr *objlayout_alloc_layout_hdr(struct inode *, gfp_t gfp_flags);
-extern void objlayout_free_layout_hdr(struct pnfs_layout_hdr *);
-
-extern struct pnfs_layout_segment *objlayout_alloc_lseg(
-	struct pnfs_layout_hdr *,
-	struct nfs4_layoutget_res *,
-	gfp_t gfp_flags);
-extern void objlayout_free_lseg(struct pnfs_layout_segment *);
-
-extern enum pnfs_try_status objlayout_read_pagelist(
-	struct nfs_pgio_header *);
-
-extern enum pnfs_try_status objlayout_write_pagelist(
-	struct nfs_pgio_header *,
-	int how);
-
-extern void objlayout_encode_layoutcommit(
-	struct pnfs_layout_hdr *,
-	struct xdr_stream *,
-	const struct nfs4_layoutcommit_args *);
-
-extern void objlayout_encode_layoutreturn(
-	struct xdr_stream *,
-	const struct nfs4_layoutreturn_args *);
-
-extern int objlayout_autologin(struct pnfs_osd_deviceaddr *deviceaddr);
-
-#endif /* _OBJLAYOUT_H */
diff --git a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c b/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
deleted file mode 100644
index f093c7ec983b..000000000000
--- a/fs/nfs/objlayout/pnfs_osd_xdr_cli.c
+++ /dev/null
@@ -1,415 +0,0 @@
-/*
- *  Object-Based pNFS Layout XDR layer
- *
- *  Copyright (C) 2007 Panasas Inc. [year of first publication]
- *  All rights reserved.
- *
- *  Benny Halevy <bhalevy@panasas.com>
- *  Boaz Harrosh <ooo@electrozaur.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License version 2
- *  See the file COPYING included with this distribution for more details.
- *
- *  Redistribution and use in source and binary forms, with or without
- *  modification, are permitted provided that the following conditions
- *  are met:
- *
- *  1. Redistributions of source code must retain the above copyright
- *     notice, this list of conditions and the following disclaimer.
- *  2. Redistributions in binary form must reproduce the above copyright
- *     notice, this list of conditions and the following disclaimer in the
- *     documentation and/or other materials provided with the distribution.
- *  3. Neither the name of the Panasas company nor the names of its
- *     contributors may be used to endorse or promote products derived
- *     from this software without specific prior written permission.
- *
- *  THIS SOFTWARE IS PROVIDED ``AS IS'' AND ANY EXPRESS OR IMPLIED
- *  WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF
- *  MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
- *  DISCLAIMED. IN NO EVENT SHALL THE REGENTS OR CONTRIBUTORS BE LIABLE
- *  FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
- *  CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
- *  SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR
- *  BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF
- *  LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING
- *  NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
- *  SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
- */
-
-#include <linux/pnfs_osd_xdr.h>
-
-#define NFSDBG_FACILITY         NFSDBG_PNFS_LD
-
-/*
- * The following implementation is based on RFC5664
- */
-
-/*
- * struct pnfs_osd_objid {
- *	struct nfs4_deviceid	oid_device_id;
- *	u64			oid_partition_id;
- *	u64			oid_object_id;
- * }; // xdr size 32 bytes
- */
-static __be32 *
-_osd_xdr_decode_objid(__be32 *p, struct pnfs_osd_objid *objid)
-{
-	p = xdr_decode_opaque_fixed(p, objid->oid_device_id.data,
-				    sizeof(objid->oid_device_id.data));
-
-	p = xdr_decode_hyper(p, &objid->oid_partition_id);
-	p = xdr_decode_hyper(p, &objid->oid_object_id);
-	return p;
-}
-/*
- * struct pnfs_osd_opaque_cred {
- *	u32 cred_len;
- *	void *cred;
- * }; // xdr size [variable]
- * The return pointers are from the xdr buffer
- */
-static int
-_osd_xdr_decode_opaque_cred(struct pnfs_osd_opaque_cred *opaque_cred,
-			    struct xdr_stream *xdr)
-{
-	__be32 *p = xdr_inline_decode(xdr, 1);
-
-	if (!p)
-		return -EINVAL;
-
-	opaque_cred->cred_len = be32_to_cpu(*p++);
-
-	p = xdr_inline_decode(xdr, opaque_cred->cred_len);
-	if (!p)
-		return -EINVAL;
-
-	opaque_cred->cred = p;
-	return 0;
-}
-
-/*
- * struct pnfs_osd_object_cred {
- *	struct pnfs_osd_objid		oc_object_id;
- *	u32				oc_osd_version;
- *	u32				oc_cap_key_sec;
- *	struct pnfs_osd_opaque_cred	oc_cap_key
- *	struct pnfs_osd_opaque_cred	oc_cap;
- * }; // xdr size 32 + 4 + 4 + [variable] + [variable]
- */
-static int
-_osd_xdr_decode_object_cred(struct pnfs_osd_object_cred *comp,
-			    struct xdr_stream *xdr)
-{
-	__be32 *p = xdr_inline_decode(xdr, 32 + 4 + 4);
-	int ret;
-
-	if (!p)
-		return -EIO;
-
-	p = _osd_xdr_decode_objid(p, &comp->oc_object_id);
-	comp->oc_osd_version = be32_to_cpup(p++);
-	comp->oc_cap_key_sec = be32_to_cpup(p);
-
-	ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap_key, xdr);
-	if (unlikely(ret))
-		return ret;
-
-	ret = _osd_xdr_decode_opaque_cred(&comp->oc_cap, xdr);
-	return ret;
-}
-
-/*
- * struct pnfs_osd_data_map {
- *	u32	odm_num_comps;
- *	u64	odm_stripe_unit;
- *	u32	odm_group_width;
- *	u32	odm_group_depth;
- *	u32	odm_mirror_cnt;
- *	u32	odm_raid_algorithm;
- * }; // xdr size 4 + 8 + 4 + 4 + 4 + 4
- */
-static inline int
-_osd_data_map_xdr_sz(void)
-{
-	return 4 + 8 + 4 + 4 + 4 + 4;
-}
-
-static __be32 *
-_osd_xdr_decode_data_map(__be32 *p, struct pnfs_osd_data_map *data_map)
-{
-	data_map->odm_num_comps = be32_to_cpup(p++);
-	p = xdr_decode_hyper(p, &data_map->odm_stripe_unit);
-	data_map->odm_group_width = be32_to_cpup(p++);
-	data_map->odm_group_depth = be32_to_cpup(p++);
-	data_map->odm_mirror_cnt = be32_to_cpup(p++);
-	data_map->odm_raid_algorithm = be32_to_cpup(p++);
-	dprintk("%s: odm_num_comps=%u odm_stripe_unit=%llu odm_group_width=%u "
-		"odm_group_depth=%u odm_mirror_cnt=%u odm_raid_algorithm=%u\n",
-		__func__,
-		data_map->odm_num_comps,
-		(unsigned long long)data_map->odm_stripe_unit,
-		data_map->odm_group_width,
-		data_map->odm_group_depth,
-		data_map->odm_mirror_cnt,
-		data_map->odm_raid_algorithm);
-	return p;
-}
-
-int pnfs_osd_xdr_decode_layout_map(struct pnfs_osd_layout *layout,
-	struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr)
-{
-	__be32 *p;
-
-	memset(iter, 0, sizeof(*iter));
-
-	p = xdr_inline_decode(xdr, _osd_data_map_xdr_sz() + 4 + 4);
-	if (unlikely(!p))
-		return -EINVAL;
-
-	p = _osd_xdr_decode_data_map(p, &layout->olo_map);
-	layout->olo_comps_index = be32_to_cpup(p++);
-	layout->olo_num_comps = be32_to_cpup(p++);
-	dprintk("%s: olo_comps_index=%d olo_num_comps=%d\n", __func__,
-		layout->olo_comps_index, layout->olo_num_comps);
-
-	iter->total_comps = layout->olo_num_comps;
-	return 0;
-}
-
-bool pnfs_osd_xdr_decode_layout_comp(struct pnfs_osd_object_cred *comp,
-	struct pnfs_osd_xdr_decode_layout_iter *iter, struct xdr_stream *xdr,
-	int *err)
-{
-	BUG_ON(iter->decoded_comps > iter->total_comps);
-	if (iter->decoded_comps == iter->total_comps)
-		return false;
-
-	*err = _osd_xdr_decode_object_cred(comp, xdr);
-	if (unlikely(*err)) {
-		dprintk("%s: _osd_xdr_decode_object_cred=>%d decoded_comps=%d "
-			"total_comps=%d\n", __func__, *err,
-			iter->decoded_comps, iter->total_comps);
-		return false; /* stop the loop */
-	}
-	dprintk("%s: dev(%llx:%llx) par=0x%llx obj=0x%llx "
-		"key_len=%u cap_len=%u\n",
-		__func__,
-		_DEVID_LO(&comp->oc_object_id.oid_device_id),
-		_DEVID_HI(&comp->oc_object_id.oid_device_id),
-		comp->oc_object_id.oid_partition_id,
-		comp->oc_object_id.oid_object_id,
-		comp->oc_cap_key.cred_len, comp->oc_cap.cred_len);
-
-	iter->decoded_comps++;
-	return true;
-}
-
-/*
- * Get Device Information Decoding
- *
- * Note: since Device Information is currently done synchronously, all
- *       variable strings fields are left inside the rpc buffer and are only
- *       pointed to by the pnfs_osd_deviceaddr members. So the read buffer
- *       should not be freed while the returned information is in use.
- */
-/*
- *struct nfs4_string {
- *	unsigned int len;
- *	char *data;
- *}; // size [variable]
- * NOTE: Returned string points to inside the XDR buffer
- */
-static __be32 *
-__read_u8_opaque(__be32 *p, struct nfs4_string *str)
-{
-	str->len = be32_to_cpup(p++);
-	str->data = (char *)p;
-
-	p += XDR_QUADLEN(str->len);
-	return p;
-}
-
-/*
- * struct pnfs_osd_targetid {
- *	u32			oti_type;
- *	struct nfs4_string	oti_scsi_device_id;
- * };// size 4 + [variable]
- */
-static __be32 *
-__read_targetid(__be32 *p, struct pnfs_osd_targetid* targetid)
-{
-	u32 oti_type;
-
-	oti_type = be32_to_cpup(p++);
-	targetid->oti_type = oti_type;
-
-	switch (oti_type) {
-	case OBJ_TARGET_SCSI_NAME:
-	case OBJ_TARGET_SCSI_DEVICE_ID:
-		p = __read_u8_opaque(p, &targetid->oti_scsi_device_id);
-	}
-
-	return p;
-}
-
-/*
- * struct pnfs_osd_net_addr {
- *	struct nfs4_string	r_netid;
- *	struct nfs4_string	r_addr;
- * };
- */
-static __be32 *
-__read_net_addr(__be32 *p, struct pnfs_osd_net_addr* netaddr)
-{
-	p = __read_u8_opaque(p, &netaddr->r_netid);
-	p = __read_u8_opaque(p, &netaddr->r_addr);
-
-	return p;
-}
-
-/*
- * struct pnfs_osd_targetaddr {
- *	u32				ota_available;
- *	struct pnfs_osd_net_addr	ota_netaddr;
- * };
- */
-static __be32 *
-__read_targetaddr(__be32 *p, struct pnfs_osd_targetaddr *targetaddr)
-{
-	u32 ota_available;
-
-	ota_available = be32_to_cpup(p++);
-	targetaddr->ota_available = ota_available;
-
-	if (ota_available)
-		p = __read_net_addr(p, &targetaddr->ota_netaddr);
-
-
-	return p;
-}
-
-/*
- * struct pnfs_osd_deviceaddr {
- *	struct pnfs_osd_targetid	oda_targetid;
- *	struct pnfs_osd_targetaddr	oda_targetaddr;
- *	u8				oda_lun[8];
- *	struct nfs4_string		oda_systemid;
- *	struct pnfs_osd_object_cred	oda_root_obj_cred;
- *	struct nfs4_string		oda_osdname;
- * };
- */
-
-/* We need this version for the pnfs_osd_xdr_decode_deviceaddr which does
- * not have an xdr_stream
- */
-static __be32 *
-__read_opaque_cred(__be32 *p,
-			      struct pnfs_osd_opaque_cred *opaque_cred)
-{
-	opaque_cred->cred_len = be32_to_cpu(*p++);
-	opaque_cred->cred = p;
-	return p + XDR_QUADLEN(opaque_cred->cred_len);
-}
-
-static __be32 *
-__read_object_cred(__be32 *p, struct pnfs_osd_object_cred *comp)
-{
-	p = _osd_xdr_decode_objid(p, &comp->oc_object_id);
-	comp->oc_osd_version = be32_to_cpup(p++);
-	comp->oc_cap_key_sec = be32_to_cpup(p++);
-
-	p = __read_opaque_cred(p, &comp->oc_cap_key);
-	p = __read_opaque_cred(p, &comp->oc_cap);
-	return p;
-}
-
-void pnfs_osd_xdr_decode_deviceaddr(
-	struct pnfs_osd_deviceaddr *deviceaddr, __be32 *p)
-{
-	p = __read_targetid(p, &deviceaddr->oda_targetid);
-
-	p = __read_targetaddr(p, &deviceaddr->oda_targetaddr);
-
-	p = xdr_decode_opaque_fixed(p, deviceaddr->oda_lun,
-				    sizeof(deviceaddr->oda_lun));
-
-	p = __read_u8_opaque(p, &deviceaddr->oda_systemid);
-
-	p = __read_object_cred(p, &deviceaddr->oda_root_obj_cred);
-
-	p = __read_u8_opaque(p, &deviceaddr->oda_osdname);
-
-	/* libosd likes this terminated in dbg. It's last, so no problems */
-	deviceaddr->oda_osdname.data[deviceaddr->oda_osdname.len] = 0;
-}
-
-/*
- * struct pnfs_osd_layoutupdate {
- *	u32	dsu_valid;
- *	s64	dsu_delta;
- *	u32	olu_ioerr_flag;
- * }; xdr size 4 + 8 + 4
- */
-int
-pnfs_osd_xdr_encode_layoutupdate(struct xdr_stream *xdr,
-				 struct pnfs_osd_layoutupdate *lou)
-{
-	__be32 *p = xdr_reserve_space(xdr,  4 + 8 + 4);
-
-	if (!p)
-		return -E2BIG;
-
-	*p++ = cpu_to_be32(lou->dsu_valid);
-	if (lou->dsu_valid)
-		p = xdr_encode_hyper(p, lou->dsu_delta);
-	*p++ = cpu_to_be32(lou->olu_ioerr_flag);
-	return 0;
-}
-
-/*
- * struct pnfs_osd_objid {
- *	struct nfs4_deviceid	oid_device_id;
- *	u64			oid_partition_id;
- *	u64			oid_object_id;
- * }; // xdr size 32 bytes
- */
-static inline __be32 *
-pnfs_osd_xdr_encode_objid(__be32 *p, struct pnfs_osd_objid *object_id)
-{
-	p = xdr_encode_opaque_fixed(p, &object_id->oid_device_id.data,
-				    sizeof(object_id->oid_device_id.data));
-	p = xdr_encode_hyper(p, object_id->oid_partition_id);
-	p = xdr_encode_hyper(p, object_id->oid_object_id);
-
-	return p;
-}
-
-/*
- * struct pnfs_osd_ioerr {
- *	struct pnfs_osd_objid	oer_component;
- *	u64			oer_comp_offset;
- *	u64			oer_comp_length;
- *	u32			oer_iswrite;
- *	u32			oer_errno;
- * }; // xdr size 32 + 24 bytes
- */
-void pnfs_osd_xdr_encode_ioerr(__be32 *p, struct pnfs_osd_ioerr *ioerr)
-{
-	p = pnfs_osd_xdr_encode_objid(p, &ioerr->oer_component);
-	p = xdr_encode_hyper(p, ioerr->oer_comp_offset);
-	p = xdr_encode_hyper(p, ioerr->oer_comp_length);
-	*p++ = cpu_to_be32(ioerr->oer_iswrite);
-	*p   = cpu_to_be32(ioerr->oer_errno);
-}
-
-__be32 *pnfs_osd_xdr_ioerr_reserve_space(struct xdr_stream *xdr)
-{
-	__be32 *p;
-
-	p = xdr_reserve_space(xdr, 32 + 24);
-	if (unlikely(!p))
-		dprintk("%s: out of xdr space\n", __func__);
-
-	return p;
-}
diff --git a/fs/nfs/pagelist.c b/fs/nfs/pagelist.c
index 6e629b856a00..de9066a92c0d 100644
--- a/fs/nfs/pagelist.c
+++ b/fs/nfs/pagelist.c
@@ -29,19 +29,6 @@
 static struct kmem_cache *nfs_page_cachep;
 static const struct rpc_call_ops nfs_pgio_common_ops;
 
-static bool nfs_pgarray_set(struct nfs_page_array *p, unsigned int pagecount)
-{
-	p->npages = pagecount;
-	if (pagecount <= ARRAY_SIZE(p->page_array))
-		p->pagevec = p->page_array;
-	else {
-		p->pagevec = kcalloc(pagecount, sizeof(struct page *), GFP_KERNEL);
-		if (!p->pagevec)
-			p->npages = 0;
-	}
-	return p->pagevec != NULL;
-}
-
 struct nfs_pgio_mirror *
 nfs_pgio_current_mirror(struct nfs_pageio_descriptor *desc)
 {
@@ -63,8 +50,8 @@ void nfs_pgheader_init(struct nfs_pageio_descriptor *desc,
 	hdr->cred = hdr->req->wb_context->cred;
 	hdr->io_start = req_offset(hdr->req);
 	hdr->good_bytes = mirror->pg_count;
+	hdr->io_completion = desc->pg_io_completion;
 	hdr->dreq = desc->pg_dreq;
-	hdr->layout_private = desc->pg_layout_private;
 	hdr->release = release;
 	hdr->completion_ops = desc->pg_completion_ops;
 	if (hdr->completion_ops->init_hdr)
@@ -115,6 +102,35 @@ nfs_iocounter_wait(struct nfs_lock_context *l_ctx)
 			TASK_KILLABLE);
 }
 
+/**
+ * nfs_async_iocounter_wait - wait on a rpc_waitqueue for I/O
+ * to complete
+ * @task: the rpc_task that should wait
+ * @l_ctx: nfs_lock_context with io_counter to check
+ *
+ * Returns true if there is outstanding I/O to wait on and the
+ * task has been put to sleep.
+ */
+bool
+nfs_async_iocounter_wait(struct rpc_task *task, struct nfs_lock_context *l_ctx)
+{
+	struct inode *inode = d_inode(l_ctx->open_context->dentry);
+	bool ret = false;
+
+	if (atomic_read(&l_ctx->io_count) > 0) {
+		rpc_sleep_on(&NFS_SERVER(inode)->uoc_rpcwaitq, task, NULL);
+		ret = true;
+	}
+
+	if (atomic_read(&l_ctx->io_count) == 0) {
+		rpc_wake_up_queued_task(&NFS_SERVER(inode)->uoc_rpcwaitq, task);
+		ret = false;
+	}
+
+	return ret;
+}
+EXPORT_SYMBOL_GPL(nfs_async_iocounter_wait);
+
 /*
  * nfs_page_group_lock - lock the head of the page group
  * @req - request in group that is to be locked
@@ -139,9 +155,12 @@ nfs_page_group_lock(struct nfs_page *req, bool nonblock)
 	if (!test_and_set_bit(PG_HEADLOCK, &head->wb_flags))
 		return 0;
 
-	if (!nonblock)
+	if (!nonblock) {
+		set_bit(PG_CONTENDED1, &head->wb_flags);
+		smp_mb__after_atomic();
 		return wait_on_bit_lock(&head->wb_flags, PG_HEADLOCK,
 				TASK_UNINTERRUPTIBLE);
+	}
 
 	return -EAGAIN;
 }
@@ -159,6 +178,10 @@ nfs_page_group_lock_wait(struct nfs_page *req)
 
 	WARN_ON_ONCE(head != head->wb_head);
 
+	if (!test_bit(PG_HEADLOCK, &head->wb_flags))
+		return;
+	set_bit(PG_CONTENDED1, &head->wb_flags);
+	smp_mb__after_atomic();
 	wait_on_bit(&head->wb_flags, PG_HEADLOCK,
 		TASK_UNINTERRUPTIBLE);
 }
@@ -177,6 +200,8 @@ nfs_page_group_unlock(struct nfs_page *req)
 	smp_mb__before_atomic();
 	clear_bit(PG_HEADLOCK, &head->wb_flags);
 	smp_mb__after_atomic();
+	if (!test_bit(PG_CONTENDED1, &head->wb_flags))
+		return;
 	wake_up_bit(&head->wb_flags, PG_HEADLOCK);
 }
 
@@ -367,6 +392,8 @@ void nfs_unlock_request(struct nfs_page *req)
 	smp_mb__before_atomic();
 	clear_bit(PG_BUSY, &req->wb_flags);
 	smp_mb__after_atomic();
+	if (!test_bit(PG_CONTENDED2, &req->wb_flags))
+		return;
 	wake_up_bit(&req->wb_flags, PG_BUSY);
 }
 
@@ -398,8 +425,11 @@ static void nfs_clear_request(struct nfs_page *req)
 		req->wb_page = NULL;
 	}
 	if (l_ctx != NULL) {
-		if (atomic_dec_and_test(&l_ctx->io_count))
+		if (atomic_dec_and_test(&l_ctx->io_count)) {
 			wake_up_atomic_t(&l_ctx->io_count);
+			if (test_bit(NFS_CONTEXT_UNLOCK, &ctx->flags))
+				rpc_wake_up(&NFS_SERVER(d_inode(ctx->dentry))->uoc_rpcwaitq);
+		}
 		nfs_put_lock_context(l_ctx);
 		req->wb_lock_context = NULL;
 	}
@@ -446,6 +476,10 @@ void nfs_release_request(struct nfs_page *req)
 int
 nfs_wait_on_request(struct nfs_page *req)
 {
+	if (!test_bit(PG_BUSY, &req->wb_flags))
+		return 0;
+	set_bit(PG_CONTENDED2, &req->wb_flags);
+	smp_mb__after_atomic();
 	return wait_on_bit_io(&req->wb_flags, PG_BUSY,
 			      TASK_UNINTERRUPTIBLE);
 }
@@ -677,7 +711,8 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 		     const struct nfs_pgio_completion_ops *compl_ops,
 		     const struct nfs_rw_ops *rw_ops,
 		     size_t bsize,
-		     int io_flags)
+		     int io_flags,
+		     gfp_t gfp_flags)
 {
 	struct nfs_pgio_mirror *new;
 	int i;
@@ -690,8 +725,8 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 	desc->pg_ioflags = io_flags;
 	desc->pg_error = 0;
 	desc->pg_lseg = NULL;
+	desc->pg_io_completion = NULL;
 	desc->pg_dreq = NULL;
-	desc->pg_layout_private = NULL;
 	desc->pg_bsize = bsize;
 
 	desc->pg_mirror_count = 1;
@@ -701,7 +736,7 @@ void nfs_pageio_init(struct nfs_pageio_descriptor *desc,
 		/* until we have a request, we don't have an lseg and no
 		 * idea how many mirrors there will be */
 		new = kcalloc(NFS_PAGEIO_DESCRIPTOR_MIRROR_MAX,
-			      sizeof(struct nfs_pgio_mirror), GFP_KERNEL);
+			      sizeof(struct nfs_pgio_mirror), gfp_flags);
 		desc->pg_mirrors_dynamic = new;
 		desc->pg_mirrors = new;
 
@@ -754,13 +789,25 @@ int nfs_generic_pgio(struct nfs_pageio_descriptor *desc,
 				*last_page;
 	struct list_head *head = &mirror->pg_list;
 	struct nfs_commit_info cinfo;
+	struct nfs_page_array *pg_array = &hdr->page_array;
 	unsigned int pagecount, pageused;
+	gfp_t gfp_flags = GFP_KERNEL;
 
 	pagecount = nfs_page_array_len(mirror->pg_base, mirror->pg_count);
-	if (!nfs_pgarray_set(&hdr->page_array, pagecount)) {
-		nfs_pgio_error(hdr);
-		desc->pg_error = -ENOMEM;
-		return desc->pg_error;
+	pg_array->npages = pagecount;
+
+	if (pagecount <= ARRAY_SIZE(pg_array->page_array))
+		pg_array->pagevec = pg_array->page_array;
+	else {
+		if (hdr->rw_mode == FMODE_WRITE)
+			gfp_flags = GFP_NOIO;
+		pg_array->pagevec = kcalloc(pagecount, sizeof(struct page *), gfp_flags);
+		if (!pg_array->pagevec) {
+			pg_array->npages = 0;
+			nfs_pgio_error(hdr);
+			desc->pg_error = -ENOMEM;
+			return desc->pg_error;
+		}
 	}
 
 	nfs_init_cinfo(&cinfo, desc->pg_inode, desc->pg_dreq);
@@ -1202,6 +1249,7 @@ int nfs_pageio_resend(struct nfs_pageio_descriptor *desc,
 {
 	LIST_HEAD(failed);
 
+	desc->pg_io_completion = hdr->io_completion;
 	desc->pg_dreq = hdr->dreq;
 	while (!list_empty(&hdr->pages)) {
 		struct nfs_page *req = nfs_list_entry(hdr->pages.next);
@@ -1256,8 +1304,10 @@ void nfs_pageio_cond_complete(struct nfs_pageio_descriptor *desc, pgoff_t index)
 		mirror = &desc->pg_mirrors[midx];
 		if (!list_empty(&mirror->pg_list)) {
 			prev = nfs_list_entry(mirror->pg_list.prev);
-			if (index != prev->wb_index + 1)
-				nfs_pageio_complete_mirror(desc, midx);
+			if (index != prev->wb_index + 1) {
+				nfs_pageio_complete(desc);
+				break;
+			}
 		}
 	}
 }
diff --git a/fs/nfs/pnfs.c b/fs/nfs/pnfs.c
index dd042498ce7c..c383d0913b54 100644
--- a/fs/nfs/pnfs.c
+++ b/fs/nfs/pnfs.c
@@ -322,9 +322,15 @@ pnfs_set_plh_return_info(struct pnfs_layout_hdr *lo, enum pnfs_iomode iomode,
 static void
 pnfs_clear_layoutreturn_info(struct pnfs_layout_hdr *lo)
 {
+	struct pnfs_layout_segment *lseg;
 	lo->plh_return_iomode = 0;
 	lo->plh_return_seq = 0;
 	clear_bit(NFS_LAYOUT_RETURN_REQUESTED, &lo->plh_flags);
+	list_for_each_entry(lseg, &lo->plh_segs, pls_list) {
+		if (!test_bit(NFS_LSEG_LAYOUTRETURN, &lseg->pls_flags))
+			continue;
+		pnfs_set_plh_return_info(lo, lseg->pls_range.iomode, 0);
+	}
 }
 
 static void pnfs_clear_layoutreturn_waitbit(struct pnfs_layout_hdr *lo)
@@ -367,9 +373,9 @@ pnfs_mark_layout_stateid_invalid(struct pnfs_layout_hdr *lo,
 	struct pnfs_layout_segment *lseg, *next;
 
 	set_bit(NFS_LAYOUT_INVALID_STID, &lo->plh_flags);
-	pnfs_clear_layoutreturn_info(lo);
 	list_for_each_entry_safe(lseg, next, &lo->plh_segs, pls_list)
 		pnfs_clear_lseg_state(lseg, lseg_list);
+	pnfs_clear_layoutreturn_info(lo);
 	pnfs_free_returned_lsegs(lo, lseg_list, &range, 0);
 	if (test_bit(NFS_LAYOUT_RETURN, &lo->plh_flags) &&
 	    !test_and_set_bit(NFS_LAYOUT_RETURN_LOCK, &lo->plh_flags))
@@ -563,7 +569,6 @@ pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg)
 		}
 	}
 }
-EXPORT_SYMBOL_GPL(pnfs_put_lseg_locked);
 
 /*
  * is l2 fully contained in l1?
@@ -728,6 +733,7 @@ pnfs_destroy_layout(struct nfs_inode *nfsi)
 		pnfs_layout_clear_fail_bit(lo, NFS_LAYOUT_RW_FAILED);
 		spin_unlock(&nfsi->vfs_inode.i_lock);
 		pnfs_free_lseg_list(&tmp_list);
+		nfs_commit_inode(&nfsi->vfs_inode, 0);
 		pnfs_put_layout_hdr(lo);
 	} else
 		spin_unlock(&nfsi->vfs_inode.i_lock);
@@ -1209,7 +1215,6 @@ out:
 	dprintk("<-- %s status: %d\n", __func__, status);
 	return status;
 }
-EXPORT_SYMBOL_GPL(_pnfs_return_layout);
 
 int
 pnfs_commit_and_return_layout(struct inode *inode)
@@ -1991,6 +1996,8 @@ out_forget:
 	spin_unlock(&ino->i_lock);
 	lseg->pls_layout = lo;
 	NFS_SERVER(ino)->pnfs_curr_ld->free_lseg(lseg);
+	if (!pnfs_layout_is_valid(lo))
+		nfs_commit_inode(ino, 0);
 	return ERR_PTR(-EAGAIN);
 }
 
@@ -2051,9 +2058,11 @@ void pnfs_error_mark_layout_for_return(struct inode *inode,
 	bool return_now = false;
 
 	spin_lock(&inode->i_lock);
+	if (!pnfs_layout_is_valid(lo)) {
+		spin_unlock(&inode->i_lock);
+		return;
+	}
 	pnfs_set_plh_return_info(lo, range.iomode, 0);
-	/* Block LAYOUTGET */
-	set_bit(NFS_LAYOUT_RETURN, &lo->plh_flags);
 	/*
 	 * mark all matching lsegs so that we are sure to have no live
 	 * segments at hand when sending layoutreturn. See pnfs_put_lseg()
@@ -2075,10 +2084,36 @@ void pnfs_error_mark_layout_for_return(struct inode *inode,
 EXPORT_SYMBOL_GPL(pnfs_error_mark_layout_for_return);
 
 void
+pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio)
+{
+	if (pgio->pg_lseg == NULL ||
+	    test_bit(NFS_LSEG_VALID, &pgio->pg_lseg->pls_flags))
+		return;
+	pnfs_put_lseg(pgio->pg_lseg);
+	pgio->pg_lseg = NULL;
+}
+EXPORT_SYMBOL_GPL(pnfs_generic_pg_check_layout);
+
+/*
+ * Check for any intersection between the request and the pgio->pg_lseg,
+ * and if none, put this pgio->pg_lseg away.
+ */
+static void
+pnfs_generic_pg_check_range(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
+{
+	if (pgio->pg_lseg && !pnfs_lseg_request_intersecting(pgio->pg_lseg, req)) {
+		pnfs_put_lseg(pgio->pg_lseg);
+		pgio->pg_lseg = NULL;
+	}
+}
+
+void
 pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *pgio, struct nfs_page *req)
 {
 	u64 rd_size = req->wb_bytes;
 
+	pnfs_generic_pg_check_layout(pgio);
+	pnfs_generic_pg_check_range(pgio, req);
 	if (pgio->pg_lseg == NULL) {
 		if (pgio->pg_dreq == NULL)
 			rd_size = i_size_read(pgio->pg_inode) - req_offset(req);
@@ -2109,6 +2144,8 @@ void
 pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
 			   struct nfs_page *req, u64 wb_size)
 {
+	pnfs_generic_pg_check_layout(pgio);
+	pnfs_generic_pg_check_range(pgio, req);
 	if (pgio->pg_lseg == NULL) {
 		pgio->pg_lseg = pnfs_update_layout(pgio->pg_inode,
 						   req->wb_context,
@@ -2169,16 +2206,10 @@ pnfs_generic_pg_test(struct nfs_pageio_descriptor *pgio,
 		seg_end = pnfs_end_offset(pgio->pg_lseg->pls_range.offset,
 				     pgio->pg_lseg->pls_range.length);
 		req_start = req_offset(req);
-		WARN_ON_ONCE(req_start >= seg_end);
+
 		/* start of request is past the last byte of this segment */
-		if (req_start >= seg_end) {
-			/* reference the new lseg */
-			if (pgio->pg_ops->pg_cleanup)
-				pgio->pg_ops->pg_cleanup(pgio);
-			if (pgio->pg_ops->pg_init)
-				pgio->pg_ops->pg_init(pgio, req);
+		if (req_start >= seg_end)
 			return 0;
-		}
 
 		/* adjust 'size' iff there are fewer bytes left in the
 		 * segment than what nfs_generic_pg_test returned */
@@ -2277,8 +2308,20 @@ pnfs_do_write(struct nfs_pageio_descriptor *desc,
 	enum pnfs_try_status trypnfs;
 
 	trypnfs = pnfs_try_to_write_data(hdr, call_ops, lseg, how);
-	if (trypnfs == PNFS_NOT_ATTEMPTED)
+	switch (trypnfs) {
+	case PNFS_NOT_ATTEMPTED:
 		pnfs_write_through_mds(desc, hdr);
+	case PNFS_ATTEMPTED:
+		break;
+	case PNFS_TRY_AGAIN:
+		/* cleanup hdr and prepare to redo pnfs */
+		if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+			struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+			list_splice_init(&hdr->pages, &mirror->pg_list);
+			mirror->pg_recoalesce = 1;
+		}
+		hdr->mds_ops->rpc_release(hdr);
+	}
 }
 
 static void pnfs_writehdr_free(struct nfs_pgio_header *hdr)
@@ -2408,10 +2451,20 @@ pnfs_do_read(struct nfs_pageio_descriptor *desc, struct nfs_pgio_header *hdr)
 	enum pnfs_try_status trypnfs;
 
 	trypnfs = pnfs_try_to_read_data(hdr, call_ops, lseg);
-	if (trypnfs == PNFS_TRY_AGAIN)
-		pnfs_read_resend_pnfs(hdr);
-	if (trypnfs == PNFS_NOT_ATTEMPTED || hdr->task.tk_status)
+	switch (trypnfs) {
+	case PNFS_NOT_ATTEMPTED:
 		pnfs_read_through_mds(desc, hdr);
+	case PNFS_ATTEMPTED:
+		break;
+	case PNFS_TRY_AGAIN:
+		/* cleanup hdr and prepare to redo pnfs */
+		if (!test_and_set_bit(NFS_IOHDR_REDO, &hdr->flags)) {
+			struct nfs_pgio_mirror *mirror = nfs_pgio_current_mirror(desc);
+			list_splice_init(&hdr->pages, &mirror->pg_list);
+			mirror->pg_recoalesce = 1;
+		}
+		hdr->mds_ops->rpc_release(hdr);
+	}
 }
 
 static void pnfs_readhdr_free(struct nfs_pgio_header *hdr)
diff --git a/fs/nfs/pnfs.h b/fs/nfs/pnfs.h
index 63f77b49a586..99731e3e332f 100644
--- a/fs/nfs/pnfs.h
+++ b/fs/nfs/pnfs.h
@@ -173,14 +173,9 @@ struct pnfs_layoutdriver_type {
 			gfp_t gfp_flags);
 
 	int (*prepare_layoutreturn) (struct nfs4_layoutreturn_args *);
-	void (*encode_layoutreturn) (struct xdr_stream *xdr,
-				     const struct nfs4_layoutreturn_args *args);
 
 	void (*cleanup_layoutcommit) (struct nfs4_layoutcommit_data *data);
 	int (*prepare_layoutcommit) (struct nfs4_layoutcommit_args *args);
-	void (*encode_layoutcommit) (struct pnfs_layout_hdr *lo,
-				     struct xdr_stream *xdr,
-				     const struct nfs4_layoutcommit_args *args);
 	int (*prepare_layoutstats) (struct nfs42_layoutstat_args *args);
 };
 
@@ -239,6 +234,7 @@ void pnfs_put_lseg_locked(struct pnfs_layout_segment *lseg);
 
 void set_pnfs_layoutdriver(struct nfs_server *, const struct nfs_fh *, struct nfs_fsinfo *);
 void unset_pnfs_layoutdriver(struct nfs_server *);
+void pnfs_generic_pg_check_layout(struct nfs_pageio_descriptor *pgio);
 void pnfs_generic_pg_init_read(struct nfs_pageio_descriptor *, struct nfs_page *);
 int pnfs_generic_pg_readpages(struct nfs_pageio_descriptor *desc);
 void pnfs_generic_pg_init_write(struct nfs_pageio_descriptor *pgio,
@@ -367,7 +363,7 @@ void nfs4_pnfs_ds_put(struct nfs4_pnfs_ds *ds);
 struct nfs4_pnfs_ds *nfs4_pnfs_ds_add(struct list_head *dsaddrs,
 				      gfp_t gfp_flags);
 void nfs4_pnfs_v3_ds_connect_unload(void);
-void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
+int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
 			  struct nfs4_deviceid_node *devid, unsigned int timeo,
 			  unsigned int retrans, u32 version, u32 minor_version);
 struct nfs4_pnfs_ds_addr *nfs4_decode_mp_ds_addr(struct net *net,
@@ -597,6 +593,16 @@ pnfs_lseg_range_intersecting(const struct pnfs_layout_range *l1,
 	return pnfs_is_range_intersecting(l1->offset, end1, l2->offset, end2);
 }
 
+static inline bool
+pnfs_lseg_request_intersecting(struct pnfs_layout_segment *lseg, struct nfs_page *req)
+{
+	u64 seg_last = pnfs_end_offset(lseg->pls_range.offset, lseg->pls_range.length);
+	u64 req_last = req_offset(req) + req->wb_bytes;
+
+	return pnfs_is_range_intersecting(lseg->pls_range.offset, seg_last,
+				req_offset(req), req_last);
+}
+
 extern unsigned int layoutstats_timer;
 
 #ifdef NFS_DEBUG
diff --git a/fs/nfs/pnfs_nfs.c b/fs/nfs/pnfs_nfs.c
index 9414b492439f..25f28fa64c57 100644
--- a/fs/nfs/pnfs_nfs.c
+++ b/fs/nfs/pnfs_nfs.c
@@ -159,13 +159,18 @@ void pnfs_generic_recover_commit_reqs(struct list_head *dst,
 {
 	struct pnfs_commit_bucket *b;
 	struct pnfs_layout_segment *freeme;
+	int nwritten;
 	int i;
 
 	lockdep_assert_held(&cinfo->inode->i_lock);
 restart:
 	for (i = 0, b = cinfo->ds->buckets; i < cinfo->ds->nbuckets; i++, b++) {
-		if (pnfs_generic_transfer_commit_list(&b->written, dst,
-						      cinfo, 0)) {
+		nwritten = pnfs_generic_transfer_commit_list(&b->written,
+				dst, cinfo, 0);
+		if (!nwritten)
+			continue;
+		cinfo->ds->nwritten -= nwritten;
+		if (list_empty(&b->written)) {
 			freeme = b->wlseg;
 			b->wlseg = NULL;
 			spin_unlock(&cinfo->inode->i_lock);
@@ -174,7 +179,6 @@ restart:
 			goto restart;
 		}
 	}
-	cinfo->ds->nwritten = 0;
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_recover_commit_reqs);
 
@@ -183,6 +187,7 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
 	struct pnfs_ds_commit_info *fl_cinfo = cinfo->ds;
 	struct pnfs_commit_bucket *bucket;
 	struct pnfs_layout_segment *freeme;
+	struct list_head *pos;
 	LIST_HEAD(pages);
 	int i;
 
@@ -193,6 +198,8 @@ static void pnfs_generic_retry_commit(struct nfs_commit_info *cinfo, int idx)
 			continue;
 		freeme = bucket->clseg;
 		bucket->clseg = NULL;
+		list_for_each(pos, &bucket->committing)
+			cinfo->ds->ncommitting--;
 		list_splice_init(&bucket->committing, &pages);
 		spin_unlock(&cinfo->inode->i_lock);
 		nfs_retry_commit(&pages, freeme, cinfo, i);
@@ -217,7 +224,7 @@ pnfs_generic_alloc_ds_commits(struct nfs_commit_info *cinfo,
 	for (i = 0; i < fl_cinfo->nbuckets; i++, bucket++) {
 		if (list_empty(&bucket->committing))
 			continue;
-		data = nfs_commitdata_alloc();
+		data = nfs_commitdata_alloc(false);
 		if (!data)
 			break;
 		data->ds_commit_index = i;
@@ -236,9 +243,12 @@ void pnfs_fetch_commit_bucket_list(struct list_head *pages,
 		struct nfs_commit_info *cinfo)
 {
 	struct pnfs_commit_bucket *bucket;
+	struct list_head *pos;
 
 	bucket = &cinfo->ds->buckets[data->ds_commit_index];
 	spin_lock(&cinfo->inode->i_lock);
+	list_for_each(pos, &bucket->committing)
+		cinfo->ds->ncommitting--;
 	list_splice_init(&bucket->committing, pages);
 	data->lseg = bucket->clseg;
 	bucket->clseg = NULL;
@@ -283,16 +293,10 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 	unsigned int nreq = 0;
 
 	if (!list_empty(mds_pages)) {
-		data = nfs_commitdata_alloc();
-		if (data != NULL) {
-			data->ds_commit_index = -1;
-			list_add(&data->pages, &list);
-			nreq++;
-		} else {
-			nfs_retry_commit(mds_pages, NULL, cinfo, 0);
-			pnfs_generic_retry_commit(cinfo, 0);
-			return -ENOMEM;
-		}
+		data = nfs_commitdata_alloc(true);
+		data->ds_commit_index = -1;
+		list_add(&data->pages, &list);
+		nreq++;
 	}
 
 	nreq += pnfs_generic_alloc_ds_commits(cinfo, &list);
@@ -329,7 +333,6 @@ pnfs_generic_commit_pagelist(struct inode *inode, struct list_head *mds_pages,
 		}
 	}
 out:
-	cinfo->ds->ncommitting = 0;
 	return PNFS_ATTEMPTED;
 }
 EXPORT_SYMBOL_GPL(pnfs_generic_commit_pagelist);
@@ -619,7 +622,6 @@ void nfs4_pnfs_v3_ds_connect_unload(void)
 		get_v3_ds_connect = NULL;
 	}
 }
-EXPORT_SYMBOL_GPL(nfs4_pnfs_v3_ds_connect_unload);
 
 static int _nfs4_pnfs_v3_ds_connect(struct nfs_server *mds_srv,
 				 struct nfs4_pnfs_ds *ds,
@@ -745,15 +747,17 @@ out:
 /*
  * Create an rpc connection to the nfs4_pnfs_ds data server.
  * Currently only supports IPv4 and IPv6 addresses.
- * If connection fails, make devid unavailable.
+ * If connection fails, make devid unavailable and return a -errno.
  */
-void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
+int nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
 			  struct nfs4_deviceid_node *devid, unsigned int timeo,
 			  unsigned int retrans, u32 version, u32 minor_version)
 {
-	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
-		int err = 0;
+	int err;
 
+again:
+	err = 0;
+	if (test_and_set_bit(NFS4DS_CONNECTING, &ds->ds_state) == 0) {
 		if (version == 3) {
 			err = _nfs4_pnfs_v3_ds_connect(mds_srv, ds, timeo,
 						       retrans);
@@ -766,12 +770,29 @@ void nfs4_pnfs_ds_connect(struct nfs_server *mds_srv, struct nfs4_pnfs_ds *ds,
 			err = -EPROTONOSUPPORT;
 		}
 
-		if (err)
-			nfs4_mark_deviceid_unavailable(devid);
 		nfs4_clear_ds_conn_bit(ds);
 	} else {
 		nfs4_wait_ds_connect(ds);
+
+		/* what was waited on didn't connect AND didn't mark unavail */
+		if (!ds->ds_clp && !nfs4_test_deviceid_unavailable(devid))
+			goto again;
 	}
+
+	/*
+	 * At this point the ds->ds_clp should be ready, but it might have
+	 * hit an error.
+	 */
+	if (!err) {
+		if (!ds->ds_clp || !nfs_client_init_is_complete(ds->ds_clp)) {
+			WARN_ON_ONCE(ds->ds_clp ||
+				!nfs4_test_deviceid_unavailable(devid));
+			return -EINVAL;
+		}
+		err = nfs_client_init_status(ds->ds_clp);
+	}
+
+	return err;
 }
 EXPORT_SYMBOL_GPL(nfs4_pnfs_ds_connect);
 
diff --git a/fs/nfs/proc.c b/fs/nfs/proc.c
index b7bca8303989..7962e49097c3 100644
--- a/fs/nfs/proc.c
+++ b/fs/nfs/proc.c
@@ -485,7 +485,7 @@ nfs_proc_rmdir(struct inode *dir, const struct qstr *name)
  */
 static int
 nfs_proc_readdir(struct dentry *dentry, struct rpc_cred *cred,
-		 u64 cookie, struct page **pages, unsigned int count, int plus)
+		 u64 cookie, struct page **pages, unsigned int count, bool plus)
 {
 	struct inode		*dir = d_inode(dentry);
 	struct nfs_readdirargs	arg = {
@@ -638,7 +638,7 @@ nfs_proc_lock(struct file *filp, int cmd, struct file_lock *fl)
 {
 	struct inode *inode = file_inode(filp);
 
-	return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl);
+	return nlmclnt_proc(NFS_SERVER(inode)->nlm_host, cmd, fl, NULL);
 }
 
 /* Helper functions for NFS lock bounds checking */
diff --git a/fs/nfs/read.c b/fs/nfs/read.c
index defc9233e985..a8421d9dab6a 100644
--- a/fs/nfs/read.c
+++ b/fs/nfs/read.c
@@ -35,7 +35,11 @@ static struct kmem_cache *nfs_rdata_cachep;
 
 static struct nfs_pgio_header *nfs_readhdr_alloc(void)
 {
-	return kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
+	struct nfs_pgio_header *p = kmem_cache_zalloc(nfs_rdata_cachep, GFP_KERNEL);
+
+	if (p)
+		p->rw_mode = FMODE_READ;
+	return p;
 }
 
 static void nfs_readhdr_free(struct nfs_pgio_header *rhdr)
@@ -64,7 +68,7 @@ void nfs_pageio_init_read(struct nfs_pageio_descriptor *pgio,
 		pg_ops = server->pnfs_curr_ld->pg_read_ops;
 #endif
 	nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_read_ops,
-			server->rsize, 0);
+			server->rsize, 0, GFP_KERNEL);
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_init_read);
 
@@ -451,7 +455,6 @@ void nfs_destroy_readpagecache(void)
 }
 
 static const struct nfs_rw_ops nfs_rw_read_ops = {
-	.rw_mode		= FMODE_READ,
 	.rw_alloc_header	= nfs_readhdr_alloc,
 	.rw_free_header		= nfs_readhdr_free,
 	.rw_done		= nfs_readpage_done,
diff --git a/fs/nfs/super.c b/fs/nfs/super.c
index 6bca17883b93..d828ef88e7db 100644
--- a/fs/nfs/super.c
+++ b/fs/nfs/super.c
@@ -531,39 +531,32 @@ static void nfs_show_mountd_netid(struct seq_file *m, struct nfs_server *nfss,
 				  int showdefaults)
 {
 	struct sockaddr *sap = (struct sockaddr *) &nfss->mountd_address;
+	char *proto = NULL;
 
-	seq_printf(m, ",mountproto=");
 	switch (sap->sa_family) {
 	case AF_INET:
 		switch (nfss->mountd_protocol) {
 		case IPPROTO_UDP:
-			seq_printf(m, RPCBIND_NETID_UDP);
+			proto = RPCBIND_NETID_UDP;
 			break;
 		case IPPROTO_TCP:
-			seq_printf(m, RPCBIND_NETID_TCP);
+			proto = RPCBIND_NETID_TCP;
 			break;
-		default:
-			if (showdefaults)
-				seq_printf(m, "auto");
 		}
 		break;
 	case AF_INET6:
 		switch (nfss->mountd_protocol) {
 		case IPPROTO_UDP:
-			seq_printf(m, RPCBIND_NETID_UDP6);
+			proto = RPCBIND_NETID_UDP6;
 			break;
 		case IPPROTO_TCP:
-			seq_printf(m, RPCBIND_NETID_TCP6);
+			proto = RPCBIND_NETID_TCP6;
 			break;
-		default:
-			if (showdefaults)
-				seq_printf(m, "auto");
 		}
 		break;
-	default:
-		if (showdefaults)
-			seq_printf(m, "auto");
 	}
+	if (proto || showdefaults)
+		seq_printf(m, ",mountproto=%s", proto ?: "auto");
 }
 
 static void nfs_show_mountd_options(struct seq_file *m, struct nfs_server *nfss,
@@ -886,7 +879,7 @@ int nfs_show_stats(struct seq_file *m, struct dentry *root)
 	if (nfss->options & NFS_OPTION_FSCACHE) {
 		seq_printf(m, "\n\tfsc:\t");
 		for (i = 0; i < __NFSIOS_FSCACHEMAX; i++)
-			seq_printf(m, "%Lu ", totals.bytes[i]);
+			seq_printf(m, "%Lu ", totals.fscache[i]);
 	}
 #endif
 	seq_printf(m, "\n");
@@ -2308,7 +2301,7 @@ EXPORT_SYMBOL_GPL(nfs_remount);
 /*
  * Initialise the common bits of the superblock
  */
-inline void nfs_initialise_sb(struct super_block *sb)
+static void nfs_initialise_sb(struct super_block *sb)
 {
 	struct nfs_server *server = NFS_SB(sb);
 
@@ -2322,8 +2315,6 @@ inline void nfs_initialise_sb(struct super_block *sb)
 		sb->s_blocksize = nfs_block_bits(server->wsize,
 						 &sb->s_blocksize_bits);
 
-	sb->s_bdi = &server->backing_dev_info;
-
 	nfs_super_set_maxbytes(sb, server->maxfilesize);
 }
 
@@ -2348,6 +2339,7 @@ void nfs_fill_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 		 */
 		sb->s_flags |= MS_POSIXACL;
 		sb->s_time_gran = 1;
+		sb->s_export_op = &nfs_export_ops;
 	}
 
  	nfs_initialise_sb(sb);
@@ -2357,7 +2349,8 @@ EXPORT_SYMBOL_GPL(nfs_fill_super);
 /*
  * Finish setting up a cloned NFS2/3/4 superblock
  */
-void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
+static void nfs_clone_super(struct super_block *sb,
+			    struct nfs_mount_info *mount_info)
 {
 	const struct super_block *old_sb = mount_info->cloned->sb;
 	struct nfs_server *server = NFS_SB(sb);
@@ -2368,6 +2361,7 @@ void nfs_clone_super(struct super_block *sb, struct nfs_mount_info *mount_info)
 	sb->s_xattr = old_sb->s_xattr;
 	sb->s_op = old_sb->s_op;
 	sb->s_time_gran = 1;
+	sb->s_export_op = old_sb->s_export_op;
 
 	if (server->nfs_client->rpc_ops->version != 2) {
 		/* The VFS shouldn't apply the umask to mode bits. We will do
@@ -2529,11 +2523,6 @@ static void nfs_get_cache_cookie(struct super_block *sb,
 }
 #endif
 
-static int nfs_bdi_register(struct nfs_server *server)
-{
-	return bdi_register_dev(&server->backing_dev_info, server->s_dev);
-}
-
 int nfs_set_sb_security(struct super_block *s, struct dentry *mntroot,
 			struct nfs_mount_info *mount_info)
 {
@@ -2558,10 +2547,25 @@ EXPORT_SYMBOL_GPL(nfs_set_sb_security);
 int nfs_clone_sb_security(struct super_block *s, struct dentry *mntroot,
 			  struct nfs_mount_info *mount_info)
 {
+	int error;
+	unsigned long kflags = 0, kflags_out = 0;
+
 	/* clone any lsm security options from the parent to the new sb */
 	if (d_inode(mntroot)->i_op != NFS_SB(s)->nfs_client->rpc_ops->dir_inode_ops)
 		return -ESTALE;
-	return security_sb_clone_mnt_opts(mount_info->cloned->sb, s);
+
+	if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL)
+		kflags |= SECURITY_LSM_NATIVE_LABELS;
+
+	error = security_sb_clone_mnt_opts(mount_info->cloned->sb, s, kflags,
+			&kflags_out);
+	if (error)
+		return error;
+
+	if (NFS_SB(s)->caps & NFS_CAP_SECURITY_LABEL &&
+		!(kflags_out & SECURITY_LSM_NATIVE_LABELS))
+		NFS_SB(s)->caps &= ~NFS_CAP_SECURITY_LABEL;
+	return 0;
 }
 EXPORT_SYMBOL_GPL(nfs_clone_sb_security);
 
@@ -2601,11 +2605,13 @@ struct dentry *nfs_fs_mount_common(struct nfs_server *server,
 		nfs_free_server(server);
 		server = NULL;
 	} else {
-		error = nfs_bdi_register(server);
+		error = super_setup_bdi_name(s, "%u:%u", MAJOR(server->s_dev),
+					     MINOR(server->s_dev));
 		if (error) {
 			mntroot = ERR_PTR(error);
 			goto error_splat_super;
 		}
+		s->s_bdi->ra_pages = server->rpages * NFS_MAX_READAHEAD;
 		server->super = s;
 	}
 
diff --git a/fs/nfs/unlink.c b/fs/nfs/unlink.c
index 191aa577dd1f..e3949d93085c 100644
--- a/fs/nfs/unlink.c
+++ b/fs/nfs/unlink.c
@@ -288,6 +288,19 @@ static void nfs_async_rename_release(void *calldata)
 	if (d_really_is_positive(data->old_dentry))
 		nfs_mark_for_revalidate(d_inode(data->old_dentry));
 
+	/* The result of the rename is unknown. Play it safe by
+	 * forcing a new lookup */
+	if (data->cancelled) {
+		spin_lock(&data->old_dir->i_lock);
+		nfs_force_lookup_revalidate(data->old_dir);
+		spin_unlock(&data->old_dir->i_lock);
+		if (data->new_dir != data->old_dir) {
+			spin_lock(&data->new_dir->i_lock);
+			nfs_force_lookup_revalidate(data->new_dir);
+			spin_unlock(&data->new_dir->i_lock);
+		}
+	}
+
 	dput(data->old_dentry);
 	dput(data->new_dentry);
 	iput(data->old_dir);
diff --git a/fs/nfs/write.c b/fs/nfs/write.c
index b00d53d13d47..b1af5dee5e0a 100644
--- a/fs/nfs/write.c
+++ b/fs/nfs/write.c
@@ -40,6 +40,12 @@
 #define MIN_POOL_WRITE		(32)
 #define MIN_POOL_COMMIT		(4)
 
+struct nfs_io_completion {
+	void (*complete)(void *data);
+	void *data;
+	struct kref refcount;
+};
+
 /*
  * Local function declarations
  */
@@ -60,14 +66,28 @@ static mempool_t *nfs_wdata_mempool;
 static struct kmem_cache *nfs_cdata_cachep;
 static mempool_t *nfs_commit_mempool;
 
-struct nfs_commit_data *nfs_commitdata_alloc(void)
+struct nfs_commit_data *nfs_commitdata_alloc(bool never_fail)
 {
-	struct nfs_commit_data *p = mempool_alloc(nfs_commit_mempool, GFP_NOIO);
+	struct nfs_commit_data *p;
 
-	if (p) {
-		memset(p, 0, sizeof(*p));
-		INIT_LIST_HEAD(&p->pages);
+	if (never_fail)
+		p = mempool_alloc(nfs_commit_mempool, GFP_NOIO);
+	else {
+		/* It is OK to do some reclaim, not no safe to wait
+		 * for anything to be returned to the pool.
+		 * mempool_alloc() cannot handle that particular combination,
+		 * so we need two separate attempts.
+		 */
+		p = mempool_alloc(nfs_commit_mempool, GFP_NOWAIT);
+		if (!p)
+			p = kmem_cache_alloc(nfs_cdata_cachep, GFP_NOIO |
+					     __GFP_NOWARN | __GFP_NORETRY);
+		if (!p)
+			return NULL;
 	}
+
+	memset(p, 0, sizeof(*p));
+	INIT_LIST_HEAD(&p->pages);
 	return p;
 }
 EXPORT_SYMBOL_GPL(nfs_commitdata_alloc);
@@ -82,8 +102,10 @@ static struct nfs_pgio_header *nfs_writehdr_alloc(void)
 {
 	struct nfs_pgio_header *p = mempool_alloc(nfs_wdata_mempool, GFP_NOIO);
 
-	if (p)
+	if (p) {
 		memset(p, 0, sizeof(*p));
+		p->rw_mode = FMODE_WRITE;
+	}
 	return p;
 }
 
@@ -92,6 +114,39 @@ static void nfs_writehdr_free(struct nfs_pgio_header *hdr)
 	mempool_free(hdr, nfs_wdata_mempool);
 }
 
+static struct nfs_io_completion *nfs_io_completion_alloc(gfp_t gfp_flags)
+{
+	return kmalloc(sizeof(struct nfs_io_completion), gfp_flags);
+}
+
+static void nfs_io_completion_init(struct nfs_io_completion *ioc,
+		void (*complete)(void *), void *data)
+{
+	ioc->complete = complete;
+	ioc->data = data;
+	kref_init(&ioc->refcount);
+}
+
+static void nfs_io_completion_release(struct kref *kref)
+{
+	struct nfs_io_completion *ioc = container_of(kref,
+			struct nfs_io_completion, refcount);
+	ioc->complete(ioc->data);
+	kfree(ioc);
+}
+
+static void nfs_io_completion_get(struct nfs_io_completion *ioc)
+{
+	if (ioc != NULL)
+		kref_get(&ioc->refcount);
+}
+
+static void nfs_io_completion_put(struct nfs_io_completion *ioc)
+{
+	if (ioc != NULL)
+		kref_put(&ioc->refcount, nfs_io_completion_release);
+}
+
 static void nfs_context_set_write_error(struct nfs_open_context *ctx, int error)
 {
 	ctx->error = error;
@@ -263,16 +318,15 @@ int nfs_congestion_kb;
 
 static void nfs_set_page_writeback(struct page *page)
 {
-	struct nfs_server *nfss = NFS_SERVER(page_file_mapping(page)->host);
+	struct inode *inode = page_file_mapping(page)->host;
+	struct nfs_server *nfss = NFS_SERVER(inode);
 	int ret = test_set_page_writeback(page);
 
 	WARN_ON_ONCE(ret != 0);
 
 	if (atomic_long_inc_return(&nfss->writeback) >
-			NFS_CONGESTION_ON_THRESH) {
-		set_bdi_congested(&nfss->backing_dev_info,
-					BLK_RW_ASYNC);
-	}
+			NFS_CONGESTION_ON_THRESH)
+		set_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
 }
 
 static void nfs_end_page_writeback(struct nfs_page *req)
@@ -285,7 +339,7 @@ static void nfs_end_page_writeback(struct nfs_page *req)
 
 	end_page_writeback(req->wb_page);
 	if (atomic_long_dec_return(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+		clear_bdi_congested(inode_to_bdi(inode), BLK_RW_ASYNC);
 }
 
 
@@ -548,9 +602,21 @@ static void nfs_write_error_remove_page(struct nfs_page *req)
 {
 	nfs_unlock_request(req);
 	nfs_end_page_writeback(req);
-	nfs_release_request(req);
 	generic_error_remove_page(page_file_mapping(req->wb_page),
 				  req->wb_page);
+	nfs_release_request(req);
+}
+
+static bool
+nfs_error_is_fatal_on_server(int err)
+{
+	switch (err) {
+	case 0:
+	case -ERESTARTSYS:
+	case -EINTR:
+		return false;
+	}
+	return nfs_error_is_fatal(err);
 }
 
 /*
@@ -558,8 +624,7 @@ static void nfs_write_error_remove_page(struct nfs_page *req)
  * May return an error if the user signalled nfs_wait_on_request().
  */
 static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
-				struct page *page, bool nonblock,
-				bool launder)
+				struct page *page, bool nonblock)
 {
 	struct nfs_page *req;
 	int ret = 0;
@@ -575,19 +640,19 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 	WARN_ON_ONCE(test_bit(PG_CLEAN, &req->wb_flags));
 
 	ret = 0;
+	/* If there is a fatal error that covers this write, just exit */
+	if (nfs_error_is_fatal_on_server(req->wb_context->error))
+		goto out_launder;
+
 	if (!nfs_pageio_add_request(pgio, req)) {
 		ret = pgio->pg_error;
 		/*
-		 * Remove the problematic req upon fatal errors
-		 * in launder case, while other dirty pages can
-		 * still be around until they get flushed.
+		 * Remove the problematic req upon fatal errors on the server
 		 */
 		if (nfs_error_is_fatal(ret)) {
 			nfs_context_set_write_error(req->wb_context, ret);
-			if (launder) {
-				nfs_write_error_remove_page(req);
-				goto out;
-			}
+			if (nfs_error_is_fatal_on_server(ret))
+				goto out_launder;
 		}
 		nfs_redirty_request(req);
 		ret = -EAGAIN;
@@ -596,16 +661,18 @@ static int nfs_page_async_flush(struct nfs_pageio_descriptor *pgio,
 				NFSIOS_WRITEPAGES, 1);
 out:
 	return ret;
+out_launder:
+	nfs_write_error_remove_page(req);
+	return ret;
 }
 
 static int nfs_do_writepage(struct page *page, struct writeback_control *wbc,
-			    struct nfs_pageio_descriptor *pgio, bool launder)
+			    struct nfs_pageio_descriptor *pgio)
 {
 	int ret;
 
 	nfs_pageio_cond_complete(pgio, page_index(page));
-	ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE,
-				   launder);
+	ret = nfs_page_async_flush(pgio, page, wbc->sync_mode == WB_SYNC_NONE);
 	if (ret == -EAGAIN) {
 		redirty_page_for_writepage(wbc, page);
 		ret = 0;
@@ -617,8 +684,7 @@ static int nfs_do_writepage(struct page *page, struct writeback_control *wbc,
  * Write an mmapped page to the server.
  */
 static int nfs_writepage_locked(struct page *page,
-				struct writeback_control *wbc,
-				bool launder)
+				struct writeback_control *wbc)
 {
 	struct nfs_pageio_descriptor pgio;
 	struct inode *inode = page_file_mapping(page)->host;
@@ -627,7 +693,7 @@ static int nfs_writepage_locked(struct page *page,
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGE);
 	nfs_pageio_init_write(&pgio, inode, 0,
 				false, &nfs_async_write_completion_ops);
-	err = nfs_do_writepage(page, wbc, &pgio, launder);
+	err = nfs_do_writepage(page, wbc, &pgio);
 	nfs_pageio_complete(&pgio);
 	if (err < 0)
 		return err;
@@ -640,7 +706,7 @@ int nfs_writepage(struct page *page, struct writeback_control *wbc)
 {
 	int ret;
 
-	ret = nfs_writepage_locked(page, wbc, false);
+	ret = nfs_writepage_locked(page, wbc);
 	unlock_page(page);
 	return ret;
 }
@@ -649,23 +715,34 @@ static int nfs_writepages_callback(struct page *page, struct writeback_control *
 {
 	int ret;
 
-	ret = nfs_do_writepage(page, wbc, data, false);
+	ret = nfs_do_writepage(page, wbc, data);
 	unlock_page(page);
 	return ret;
 }
 
+static void nfs_io_completion_commit(void *inode)
+{
+	nfs_commit_inode(inode, 0);
+}
+
 int nfs_writepages(struct address_space *mapping, struct writeback_control *wbc)
 {
 	struct inode *inode = mapping->host;
 	struct nfs_pageio_descriptor pgio;
+	struct nfs_io_completion *ioc = nfs_io_completion_alloc(GFP_NOFS);
 	int err;
 
 	nfs_inc_stats(inode, NFSIOS_VFSWRITEPAGES);
 
+	if (ioc)
+		nfs_io_completion_init(ioc, nfs_io_completion_commit, inode);
+
 	nfs_pageio_init_write(&pgio, inode, wb_priority(wbc), false,
 				&nfs_async_write_completion_ops);
+	pgio.pg_io_completion = ioc;
 	err = write_cache_pages(mapping, wbc, nfs_writepages_callback, &pgio);
 	nfs_pageio_complete(&pgio);
+	nfs_io_completion_put(ioc);
 
 	if (err < 0)
 		goto out_err;
@@ -728,8 +805,6 @@ static void nfs_inode_remove_request(struct nfs_page *req)
 		if (likely(head->wb_page && !PageSwapCache(head->wb_page))) {
 			set_page_private(head->wb_page, 0);
 			ClearPagePrivate(head->wb_page);
-			smp_mb__after_atomic();
-			wake_up_page(head->wb_page, PG_private);
 			clear_bit(PG_MAPPED, &head->wb_flags);
 		}
 		nfsi->nrequests--;
@@ -915,6 +990,11 @@ int nfs_write_need_commit(struct nfs_pgio_header *hdr)
 	return hdr->verf.committed != NFS_FILE_SYNC;
 }
 
+static void nfs_async_write_init(struct nfs_pgio_header *hdr)
+{
+	nfs_io_completion_get(hdr->io_completion);
+}
+
 static void nfs_write_completion(struct nfs_pgio_header *hdr)
 {
 	struct nfs_commit_info cinfo;
@@ -948,6 +1028,7 @@ next:
 		nfs_release_request(req);
 	}
 out:
+	nfs_io_completion_put(hdr->io_completion);
 	hdr->release(hdr);
 }
 
@@ -1353,6 +1434,7 @@ static void nfs_async_write_reschedule_io(struct nfs_pgio_header *hdr)
 }
 
 static const struct nfs_pgio_completion_ops nfs_async_write_completion_ops = {
+	.init_hdr = nfs_async_write_init,
 	.error_cleanup = nfs_async_write_error,
 	.completion = nfs_write_completion,
 	.reschedule_io = nfs_async_write_reschedule_io,
@@ -1370,7 +1452,7 @@ void nfs_pageio_init_write(struct nfs_pageio_descriptor *pgio,
 		pg_ops = server->pnfs_curr_ld->pg_write_ops;
 #endif
 	nfs_pageio_init(pgio, inode, pg_ops, compl_ops, &nfs_rw_write_ops,
-			server->wsize, ioflags);
+			server->wsize, ioflags, GFP_NOIO);
 }
 EXPORT_SYMBOL_GPL(nfs_pageio_init_write);
 
@@ -1707,50 +1789,14 @@ nfs_commit_list(struct inode *inode, struct list_head *head, int how,
 	if (list_empty(head))
 		return 0;
 
-	data = nfs_commitdata_alloc();
-
-	if (!data)
-		goto out_bad;
+	data = nfs_commitdata_alloc(true);
 
 	/* Set up the argument struct */
 	nfs_init_commit(data, head, NULL, cinfo);
 	atomic_inc(&cinfo->mds->rpcs_out);
 	return nfs_initiate_commit(NFS_CLIENT(inode), data, NFS_PROTO(inode),
 				   data->mds_ops, how, 0);
- out_bad:
-	nfs_retry_commit(head, NULL, cinfo, 0);
-	return -ENOMEM;
-}
-
-int nfs_commit_file(struct file *file, struct nfs_write_verifier *verf)
-{
-	struct inode *inode = file_inode(file);
-	struct nfs_open_context *open;
-	struct nfs_commit_info cinfo;
-	struct nfs_page *req;
-	int ret;
-
-	open = get_nfs_open_context(nfs_file_open_context(file));
-	req  = nfs_create_request(open, NULL, NULL, 0, i_size_read(inode));
-	if (IS_ERR(req)) {
-		ret = PTR_ERR(req);
-		goto out_put;
-	}
-
-	nfs_init_cinfo_from_inode(&cinfo, inode);
-
-	memcpy(&req->wb_verf, verf, sizeof(struct nfs_write_verifier));
-	nfs_request_add_commit_list(req, &cinfo);
-	ret = nfs_commit_inode(inode, FLUSH_SYNC);
-	if (ret > 0)
-		ret = 0;
-
-	nfs_free_request(req);
-out_put:
-	put_nfs_open_context(open);
-	return ret;
 }
-EXPORT_SYMBOL_GPL(nfs_commit_file);
 
 /*
  * COMMIT call returned
@@ -1786,8 +1832,9 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 			(long long)req_offset(req));
 		if (status < 0) {
 			nfs_context_set_write_error(req->wb_context, status);
-			nfs_inode_remove_request(req);
-			dprintk(", error = %d\n", status);
+			if (req->wb_page)
+				nfs_inode_remove_request(req);
+			dprintk_cont(", error = %d\n", status);
 			goto next;
 		}
 
@@ -1795,12 +1842,13 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 		 * returned by the server against all stored verfs. */
 		if (!nfs_write_verifier_cmp(&req->wb_verf, &data->verf.verifier)) {
 			/* We have a match */
-			nfs_inode_remove_request(req);
-			dprintk(" OK\n");
+			if (req->wb_page)
+				nfs_inode_remove_request(req);
+			dprintk_cont(" OK\n");
 			goto next;
 		}
 		/* We have a mismatch. Write the page again */
-		dprintk(" mismatch\n");
+		dprintk_cont(" mismatch\n");
 		nfs_mark_request_dirty(req);
 		set_bit(NFS_CONTEXT_RESEND_WRITES, &req->wb_context->flags);
 	next:
@@ -1808,7 +1856,7 @@ static void nfs_commit_release_pages(struct nfs_commit_data *data)
 	}
 	nfss = NFS_SERVER(data->inode);
 	if (atomic_long_read(&nfss->writeback) < NFS_CONGESTION_OFF_THRESH)
-		clear_bdi_congested(&nfss->backing_dev_info, BLK_RW_ASYNC);
+		clear_bdi_congested(inode_to_bdi(data->inode), BLK_RW_ASYNC);
 
 	nfs_init_cinfo(&cinfo, data->inode, data->dreq);
 	nfs_commit_end(cinfo.mds);
@@ -1893,7 +1941,7 @@ int nfs_write_inode(struct inode *inode, struct writeback_control *wbc)
 		/* Don't commit yet if this is a non-blocking flush and there
 		 * are a lot of outstanding writes for this mapping.
 		 */
-		if (nfsi->commit_info.ncommit <= (nfsi->nrequests >> 1))
+		if (mapping_tagged(inode->i_mapping, PAGECACHE_TAG_WRITEBACK))
 			goto out_mark_dirty;
 
 		/* don't wait for the COMMIT response */
@@ -1986,7 +2034,7 @@ int nfs_wb_page_cancel(struct inode *inode, struct page *page)
 /*
  * Write back all requests on one page - we do this before reading it.
  */
-int nfs_wb_single_page(struct inode *inode, struct page *page, bool launder)
+int nfs_wb_page(struct inode *inode, struct page *page)
 {
 	loff_t range_start = page_file_offset(page);
 	loff_t range_end = range_start + (loff_t)(PAGE_SIZE - 1);
@@ -2003,7 +2051,7 @@ int nfs_wb_single_page(struct inode *inode, struct page *page, bool launder)
 	for (;;) {
 		wait_on_page_writeback(page);
 		if (clear_page_dirty_for_io(page)) {
-			ret = nfs_writepage_locked(page, &wbc, launder);
+			ret = nfs_writepage_locked(page, &wbc);
 			if (ret < 0)
 				goto out_error;
 			continue;
@@ -2108,7 +2156,6 @@ void nfs_destroy_writepagecache(void)
 }
 
 static const struct nfs_rw_ops nfs_rw_write_ops = {
-	.rw_mode		= FMODE_WRITE,
 	.rw_alloc_header	= nfs_writehdr_alloc,
 	.rw_free_header		= nfs_writehdr_free,
 	.rw_done		= nfs_writeback_done,
diff --git a/fs/nfsd/Kconfig b/fs/nfsd/Kconfig
index 47febcf99185..20b1c17320d5 100644
--- a/fs/nfsd/Kconfig
+++ b/fs/nfsd/Kconfig
@@ -104,6 +104,7 @@ config NFSD_SCSILAYOUT
 	depends on NFSD_V4 && BLOCK
 	select NFSD_PNFS
 	select EXPORTFS_BLOCK_OPS
+	select BLK_SCSI_REQUEST
 	help
 	  This option enables support for the exporting pNFS SCSI layouts
 	  in the kernel's NFS server. The pNFS SCSI layout enables NFS
diff --git a/fs/nfsd/blocklayout.c b/fs/nfsd/blocklayout.c
index 0780ff864539..c862c2489df0 100644
--- a/fs/nfsd/blocklayout.c
+++ b/fs/nfsd/blocklayout.c
@@ -10,6 +10,7 @@
 #include <linux/nfsd/debug.h>
 #include <scsi/scsi_proto.h>
 #include <scsi/scsi_common.h>
+#include <scsi/scsi_request.h>
 
 #include "blocklayoutxdr.h"
 #include "pnfs.h"
@@ -23,7 +24,7 @@ nfsd4_block_proc_layoutget(struct inode *inode, const struct svc_fh *fhp,
 {
 	struct nfsd4_layout_seg *seg = &args->lg_seg;
 	struct super_block *sb = inode->i_sb;
-	u32 block_size = (1 << inode->i_blkbits);
+	u32 block_size = i_blocksize(inode);
 	struct pnfs_block_extent *bex;
 	struct iomap iomap;
 	u32 device_generation = 0;
@@ -180,7 +181,7 @@ nfsd4_block_proc_layoutcommit(struct inode *inode,
 	int nr_iomaps;
 
 	nr_iomaps = nfsd4_block_decode_layoutupdate(lcp->lc_up_layout,
-			lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
+			lcp->lc_up_len, &iomaps, i_blocksize(inode));
 	if (nr_iomaps < 0)
 		return nfserrno(nr_iomaps);
 
@@ -213,36 +214,41 @@ static int nfsd4_scsi_identify_device(struct block_device *bdev,
 {
 	struct request_queue *q = bdev->bd_disk->queue;
 	struct request *rq;
+	struct scsi_request *req;
 	size_t bufflen = 252, len, id_len;
 	u8 *buf, *d, type, assoc;
 	int error;
 
+	if (WARN_ON_ONCE(!blk_queue_scsi_passthrough(q)))
+		return -EINVAL;
+
 	buf = kzalloc(bufflen, GFP_KERNEL);
 	if (!buf)
 		return -ENOMEM;
 
-	rq = blk_get_request(q, READ, GFP_KERNEL);
+	rq = blk_get_request(q, REQ_OP_SCSI_IN, GFP_KERNEL);
 	if (IS_ERR(rq)) {
 		error = -ENOMEM;
 		goto out_free_buf;
 	}
-	blk_rq_set_block_pc(rq);
+	req = scsi_req(rq);
 
 	error = blk_rq_map_kern(q, rq, buf, bufflen, GFP_KERNEL);
 	if (error)
 		goto out_put_request;
 
-	rq->cmd[0] = INQUIRY;
-	rq->cmd[1] = 1;
-	rq->cmd[2] = 0x83;
-	rq->cmd[3] = bufflen >> 8;
-	rq->cmd[4] = bufflen & 0xff;
-	rq->cmd_len = COMMAND_SIZE(INQUIRY);
+	req->cmd[0] = INQUIRY;
+	req->cmd[1] = 1;
+	req->cmd[2] = 0x83;
+	req->cmd[3] = bufflen >> 8;
+	req->cmd[4] = bufflen & 0xff;
+	req->cmd_len = COMMAND_SIZE(INQUIRY);
 
-	error = blk_execute_rq(rq->q, NULL, rq, 1);
-	if (error) {
+	blk_execute_rq(rq->q, NULL, rq, 1);
+	if (req->result) {
 		pr_err("pNFS: INQUIRY 0x83 failed with: %x\n",
-			rq->errors);
+			req->result);
+		error = -EIO;
 		goto out_put_request;
 	}
 
@@ -372,7 +378,7 @@ nfsd4_scsi_proc_layoutcommit(struct inode *inode,
 	int nr_iomaps;
 
 	nr_iomaps = nfsd4_scsi_decode_layoutupdate(lcp->lc_up_layout,
-			lcp->lc_up_len, &iomaps, 1 << inode->i_blkbits);
+			lcp->lc_up_len, &iomaps, i_blocksize(inode));
 	if (nr_iomaps < 0)
 		return nfserrno(nr_iomaps);
 
diff --git a/fs/nfsd/current_stateid.h b/fs/nfsd/current_stateid.h
index 4123551208d8..34075cee573a 100644
--- a/fs/nfsd/current_stateid.h
+++ b/fs/nfsd/current_stateid.h
@@ -8,21 +8,33 @@ extern void clear_current_stateid(struct nfsd4_compound_state *cstate);
 /*
  * functions to set current state id
  */
-extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *);
-extern void nfsd4_set_openstateid(struct nfsd4_compound_state *, struct nfsd4_open *);
-extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *, struct nfsd4_lock *);
-extern void nfsd4_set_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *);
+extern void nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_set_openstateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_set_lockstateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_set_closestateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
 
 /*
  * functions to consume current state id
  */
-extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *);
-extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *, struct nfsd4_delegreturn *);
-extern void nfsd4_get_freestateid(struct nfsd4_compound_state *, struct nfsd4_free_stateid *);
-extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *, struct nfsd4_setattr *);
-extern void nfsd4_get_closestateid(struct nfsd4_compound_state *, struct nfsd4_close *);
-extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *, struct nfsd4_locku *);
-extern void nfsd4_get_readstateid(struct nfsd4_compound_state *, struct nfsd4_read *);
-extern void nfsd4_get_writestateid(struct nfsd4_compound_state *, struct nfsd4_write *);
+extern void nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_freestateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_setattrstateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_closestateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_lockustateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_readstateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
+extern void nfsd4_get_writestateid(struct nfsd4_compound_state *,
+		union nfsd4_op_u *);
 
 #endif   /* _NFSD4_CURRENT_STATE_H */
diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c
index 43e109cc0ccc..3bc08c394a3f 100644
--- a/fs/nfsd/export.c
+++ b/fs/nfsd/export.c
@@ -486,7 +486,7 @@ secinfo_parse(char **mesg, char *buf, struct svc_export *exp) { return 0; }
 #endif
 
 static inline int
-uuid_parse(char **mesg, char *buf, unsigned char **puuid)
+nfsd_uuid_parse(char **mesg, char *buf, unsigned char **puuid)
 {
 	int len;
 
@@ -586,7 +586,7 @@ static int svc_export_parse(struct cache_detail *cd, char *mesg, int mlen)
 			if (strcmp(buf, "fsloc") == 0)
 				err = fsloc_parse(&mesg, buf, &exp.ex_fslocs);
 			else if (strcmp(buf, "uuid") == 0)
-				err = uuid_parse(&mesg, buf, &exp.ex_uuid);
+				err = nfsd_uuid_parse(&mesg, buf, &exp.ex_uuid);
 			else if (strcmp(buf, "secinfo") == 0)
 				err = secinfo_parse(&mesg, buf, &exp);
 			else
@@ -1102,6 +1102,7 @@ static struct flags {
 	{ NFSEXP_NOAUTHNLM, {"insecure_locks", ""}},
 	{ NFSEXP_V4ROOT, {"v4root", ""}},
 	{ NFSEXP_PNFS, {"pnfs", ""}},
+	{ NFSEXP_SECURITY_LABEL, {"security_label", ""}},
 	{ 0, {"", ""}}
 };
 
diff --git a/fs/nfsd/nfs2acl.c b/fs/nfsd/nfs2acl.c
index d08cd88155c7..6276ec8608b0 100644
--- a/fs/nfsd/nfs2acl.c
+++ b/fs/nfsd/nfs2acl.c
@@ -19,7 +19,7 @@
  * NULL call.
  */
 static __be32
-nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsacld_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -27,9 +27,10 @@ nfsacld_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
 /*
  * Get the Access and/or Default ACL of a file.
  */
-static __be32 nfsacld_proc_getacl(struct svc_rqst * rqstp,
-		struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp)
+static __be32 nfsacld_proc_getacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_getaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct posix_acl *acl;
 	struct inode *inode;
 	svc_fh *fh;
@@ -87,10 +88,10 @@ fail:
 /*
  * Set the Access and/or Default ACL of a file.
  */
-static __be32 nfsacld_proc_setacl(struct svc_rqst * rqstp,
-		struct nfsd3_setaclargs *argp,
-		struct nfsd_attrstat *resp)
+static __be32 nfsacld_proc_setacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	struct inode *inode;
 	svc_fh *fh;
 	__be32 nfserr = 0;
@@ -141,9 +142,10 @@ out_errno:
 /*
  * Check file attributes
  */
-static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp,
-		struct nfsd_fhandle *argp, struct nfsd_attrstat *resp)
+static __be32 nfsacld_proc_getattr(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	__be32 nfserr;
 	dprintk("nfsd: GETATTR  %s\n", SVCFH_fmt(&argp->fh));
 
@@ -158,9 +160,10 @@ static __be32 nfsacld_proc_getattr(struct svc_rqst * rqstp,
 /*
  * Check file access
  */
-static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp,
-		struct nfsd3_accessres *resp)
+static __be32 nfsacld_proc_access(struct svc_rqst *rqstp)
 {
+	struct nfsd3_accessargs *argp = rqstp->rq_argp;
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
 	__be32 nfserr;
 
 	dprintk("nfsd: ACCESS(2acl)   %s 0x%x\n",
@@ -179,9 +182,10 @@ static __be32 nfsacld_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessarg
 /*
  * XDR decode functions
  */
-static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclargs *argp)
+static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_getaclargs *argp = rqstp->rq_argp;
+
 	p = nfs2svc_decode_fh(p, &argp->fh);
 	if (!p)
 		return 0;
@@ -191,9 +195,9 @@ static int nfsaclsvc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 
-static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_setaclargs *argp)
+static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
 	struct kvec *head = rqstp->rq_arg.head;
 	unsigned int base;
 	int n;
@@ -217,18 +221,20 @@ static int nfsaclsvc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
 	return (n > 0);
 }
 
-static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd_fhandle *argp)
+static int nfsaclsvc_decode_fhandleargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+
 	p = nfs2svc_decode_fh(p, &argp->fh);
 	if (!p)
 		return 0;
 	return xdr_argsize_check(rqstp, p);
 }
 
-static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_accessargs *argp)
+static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_accessargs *argp = rqstp->rq_argp;
+
 	p = nfs2svc_decode_fh(p, &argp->fh);
 	if (!p)
 		return 0;
@@ -245,15 +251,15 @@ static int nfsaclsvc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
  * There must be an encoding function for void results so svc_process
  * will work properly.
  */
-static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+static int nfsaclsvc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
 
 /* GETACL */
-static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclres *resp)
+static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct dentry *dentry = resp->fh.fh_dentry;
 	struct inode *inode;
 	struct kvec *head = rqstp->rq_res.head;
@@ -296,17 +302,19 @@ static int nfsaclsvc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
 	return (n > 0);
 }
 
-static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd_attrstat *resp)
+static int nfsaclsvc_encode_attrstatres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
 	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	return xdr_ressize_check(rqstp, p);
 }
 
 /* ACCESS */
-static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_accessres *resp)
+static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
+
 	p = nfs2svc_encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	*p++ = htonl(resp->access);
 	return xdr_ressize_check(rqstp, p);
@@ -315,27 +323,27 @@ static int nfsaclsvc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
 /*
  * XDR release functions
  */
-static int nfsaclsvc_release_getacl(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclres *resp)
+static void nfsaclsvc_release_getacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
 	posix_acl_release(resp->acl_access);
 	posix_acl_release(resp->acl_default);
-	return 1;
 }
 
-static int nfsaclsvc_release_attrstat(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd_attrstat *resp)
+static void nfsaclsvc_release_attrstat(struct svc_rqst *rqstp)
 {
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
-	return 1;
 }
 
-static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p,
-               struct nfsd3_accessres *resp)
+static void nfsaclsvc_release_access(struct svc_rqst *rqstp)
 {
-       fh_put(&resp->fh);
-       return 1;
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
+
+	fh_put(&resp->fh);
 }
 
 #define nfsaclsvc_decode_voidargs	NULL
@@ -345,24 +353,24 @@ static int nfsaclsvc_release_access(struct svc_rqst *rqstp, __be32 *p,
 #define nfsd3_voidres		nfsd3_voidargs
 struct nfsd3_voidargs { int dummy; };
 
-#define PROC(name, argt, rest, relt, cache, respsize)	\
- { (svc_procfunc) nfsacld_proc_##name,		\
-   (kxdrproc_t) nfsaclsvc_decode_##argt##args,	\
-   (kxdrproc_t) nfsaclsvc_encode_##rest##res,	\
-   (kxdrproc_t) nfsaclsvc_release_##relt,		\
-   sizeof(struct nfsd3_##argt##args),		\
-   sizeof(struct nfsd3_##rest##res),		\
-   0,						\
-   cache,					\
-   respsize,					\
- }
+#define PROC(name, argt, rest, relt, cache, respsize)			\
+{									\
+	.pc_func	= nfsacld_proc_##name,				\
+	.pc_decode	= nfsaclsvc_decode_##argt##args,		\
+	.pc_encode	= nfsaclsvc_encode_##rest##res,			\
+	.pc_release	= nfsaclsvc_release_##relt,	\
+	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
+	.pc_ressize	= sizeof(struct nfsd3_##rest##res),		\
+	.pc_cachetype	= cache,					\
+	.pc_xdrressize	= respsize,					\
+}
 
 #define ST 1		/* status*/
 #define AT 21		/* attributes */
 #define pAT (1+AT)	/* post attributes - conditional */
 #define ACL (1+NFS_ACL_MAX_ENTRIES*3)  /* Access Control List */
 
-static struct svc_procedure		nfsd_acl_procedures2[] = {
+static const struct svc_procedure nfsd_acl_procedures2[] = {
   PROC(null,	void,		void,		void,	  RC_NOCACHE, ST),
   PROC(getacl,	getacl,		getacl,		getacl,	  RC_NOCACHE, ST+1+2*(1+ACL)),
   PROC(setacl,	setacl,		attrstat,	attrstat, RC_NOCACHE, ST+AT),
@@ -370,11 +378,12 @@ static struct svc_procedure		nfsd_acl_procedures2[] = {
   PROC(access,	access,		access,		access,   RC_NOCACHE, ST+AT+1),
 };
 
-struct svc_version	nfsd_acl_version2 = {
-		.vs_vers	= 2,
-		.vs_nproc	= 5,
-		.vs_proc	= nfsd_acl_procedures2,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
-		.vs_hidden	= 0,
+static unsigned int nfsd_acl_count2[ARRAY_SIZE(nfsd_acl_procedures2)];
+const struct svc_version nfsd_acl_version2 = {
+	.vs_vers	= 2,
+	.vs_nproc	= 5,
+	.vs_proc	= nfsd_acl_procedures2,
+	.vs_count	= nfsd_acl_count2,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
diff --git a/fs/nfsd/nfs3acl.c b/fs/nfsd/nfs3acl.c
index 0c890347cde3..01976529f042 100644
--- a/fs/nfsd/nfs3acl.c
+++ b/fs/nfsd/nfs3acl.c
@@ -18,7 +18,7 @@
  * NULL call.
  */
 static __be32
-nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsd3_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -26,9 +26,10 @@ nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
 /*
  * Get the Access and/or Default ACL of a file.
  */
-static __be32 nfsd3_proc_getacl(struct svc_rqst * rqstp,
-		struct nfsd3_getaclargs *argp, struct nfsd3_getaclres *resp)
+static __be32 nfsd3_proc_getacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_getaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct posix_acl *acl;
 	struct inode *inode;
 	svc_fh *fh;
@@ -80,10 +81,10 @@ fail:
 /*
  * Set the Access and/or Default ACL of a file.
  */
-static __be32 nfsd3_proc_setacl(struct svc_rqst * rqstp,
-		struct nfsd3_setaclargs *argp,
-		struct nfsd3_attrstat *resp)
+static __be32 nfsd3_proc_setacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_setaclargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	struct inode *inode;
 	svc_fh *fh;
 	__be32 nfserr = 0;
@@ -123,9 +124,10 @@ out:
 /*
  * XDR decode functions
  */
-static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclargs *args)
+static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_getaclargs *args = rqstp->rq_argp;
+
 	p = nfs3svc_decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -135,9 +137,9 @@ static int nfs3svc_decode_getaclargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 
-static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_setaclargs *args)
+static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_setaclargs *args = rqstp->rq_argp;
 	struct kvec *head = rqstp->rq_arg.head;
 	unsigned int base;
 	int n;
@@ -166,9 +168,9 @@ static int nfs3svc_decode_setaclargs(struct svc_rqst *rqstp, __be32 *p,
  */
 
 /* GETACL */
-static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclres *resp)
+static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
 	struct dentry *dentry = resp->fh.fh_dentry;
 
 	p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
@@ -211,9 +213,10 @@ static int nfs3svc_encode_getaclres(struct svc_rqst *rqstp, __be32 *p,
 }
 
 /* SETACL */
-static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_attrstat *resp)
+static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
 	p = nfs3svc_encode_post_op_attr(rqstp, p, &resp->fh);
 
 	return xdr_ressize_check(rqstp, p);
@@ -222,13 +225,13 @@ static int nfs3svc_encode_setaclres(struct svc_rqst *rqstp, __be32 *p,
 /*
  * XDR release functions
  */
-static int nfs3svc_release_getacl(struct svc_rqst *rqstp, __be32 *p,
-		struct nfsd3_getaclres *resp)
+static void nfs3svc_release_getacl(struct svc_rqst *rqstp)
 {
+	struct nfsd3_getaclres *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
 	posix_acl_release(resp->acl_access);
 	posix_acl_release(resp->acl_default);
-	return 1;
 }
 
 #define nfs3svc_decode_voidargs		NULL
@@ -237,35 +240,36 @@ static int nfs3svc_release_getacl(struct svc_rqst *rqstp, __be32 *p,
 #define nfsd3_voidres			nfsd3_voidargs
 struct nfsd3_voidargs { int dummy; };
 
-#define PROC(name, argt, rest, relt, cache, respsize)	\
- { (svc_procfunc) nfsd3_proc_##name,		\
-   (kxdrproc_t) nfs3svc_decode_##argt##args,	\
-   (kxdrproc_t) nfs3svc_encode_##rest##res,	\
-   (kxdrproc_t) nfs3svc_release_##relt,		\
-   sizeof(struct nfsd3_##argt##args),		\
-   sizeof(struct nfsd3_##rest##res),		\
-   0,						\
-   cache,					\
-   respsize,					\
- }
+#define PROC(name, argt, rest, relt, cache, respsize)			\
+{									\
+	.pc_func	= nfsd3_proc_##name,				\
+	.pc_decode	= nfs3svc_decode_##argt##args,			\
+	.pc_encode	= nfs3svc_encode_##rest##res,			\
+	.pc_release	= nfs3svc_release_##relt,			\
+	.pc_argsize	= sizeof(struct nfsd3_##argt##args),		\
+	.pc_ressize	= sizeof(struct nfsd3_##rest##res),		\
+	.pc_cachetype	= cache,					\
+	.pc_xdrressize	= respsize,					\
+}
 
 #define ST 1		/* status*/
 #define AT 21		/* attributes */
 #define pAT (1+AT)	/* post attributes - conditional */
 #define ACL (1+NFS_ACL_MAX_ENTRIES*3)  /* Access Control List */
 
-static struct svc_procedure		nfsd_acl_procedures3[] = {
+static const struct svc_procedure nfsd_acl_procedures3[] = {
   PROC(null,	void,		void,		void,	  RC_NOCACHE, ST),
   PROC(getacl,	getacl,		getacl,		getacl,	  RC_NOCACHE, ST+1+2*(1+ACL)),
   PROC(setacl,	setacl,		setacl,		fhandle,  RC_NOCACHE, ST+pAT),
 };
 
-struct svc_version	nfsd_acl_version3 = {
-		.vs_vers	= 3,
-		.vs_nproc	= 3,
-		.vs_proc	= nfsd_acl_procedures3,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
-		.vs_hidden	= 0,
+static unsigned int nfsd_acl_count3[ARRAY_SIZE(nfsd_acl_procedures3)];
+const struct svc_version nfsd_acl_version3 = {
+	.vs_vers	= 3,
+	.vs_nproc	= 3,
+	.vs_proc	= nfsd_acl_procedures3,
+	.vs_count	= nfsd_acl_count3,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
 
diff --git a/fs/nfsd/nfs3proc.c b/fs/nfsd/nfs3proc.c
index d818e4ffd79f..2cb56a0d6625 100644
--- a/fs/nfsd/nfs3proc.c
+++ b/fs/nfsd/nfs3proc.c
@@ -31,7 +31,7 @@ static int	nfs3_ftypes[] = {
  * NULL call.
  */
 static __be32
-nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsd3_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -40,9 +40,10 @@ nfsd3_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
  * Get a file's attributes
  */
 static __be32
-nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
-					   struct nfsd3_attrstat *resp)
+nfsd3_proc_getattr(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: GETATTR(3)  %s\n",
@@ -63,9 +64,10 @@ nfsd3_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
  * Set a file's attributes
  */
 static __be32
-nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp,
-					   struct nfsd3_attrstat  *resp)
+nfsd3_proc_setattr(struct svc_rqst *rqstp)
 {
+	struct nfsd3_sattrargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: SETATTR(3)  %s\n",
@@ -81,9 +83,10 @@ nfsd3_proc_setattr(struct svc_rqst *rqstp, struct nfsd3_sattrargs *argp,
  * Look up a path name component
  */
 static __be32
-nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
-					  struct nfsd3_diropres  *resp)
+nfsd3_proc_lookup(struct svc_rqst *rqstp)
 {
+	struct nfsd3_diropargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres  *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: LOOKUP(3)   %s %.*s\n",
@@ -105,9 +108,10 @@ nfsd3_proc_lookup(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
  * Check file access
  */
 static __be32
-nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp,
-					  struct nfsd3_accessres *resp)
+nfsd3_proc_access(struct svc_rqst *rqstp)
 {
+	struct nfsd3_accessargs *argp = rqstp->rq_argp;
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: ACCESS(3)   %s 0x%x\n",
@@ -124,9 +128,10 @@ nfsd3_proc_access(struct svc_rqst *rqstp, struct nfsd3_accessargs *argp,
  * Read a symlink.
  */
 static __be32
-nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp,
-					   struct nfsd3_readlinkres *resp)
+nfsd3_proc_readlink(struct svc_rqst *rqstp)
 {
+	struct nfsd3_readlinkargs *argp = rqstp->rq_argp;
+	struct nfsd3_readlinkres *resp = rqstp->rq_resp;
 	__be32 nfserr;
 
 	dprintk("nfsd: READLINK(3) %s\n", SVCFH_fmt(&argp->fh));
@@ -142,9 +147,10 @@ nfsd3_proc_readlink(struct svc_rqst *rqstp, struct nfsd3_readlinkargs *argp,
  * Read a portion of a file.
  */
 static __be32
-nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
-				        struct nfsd3_readres  *resp)
+nfsd3_proc_read(struct svc_rqst *rqstp)
 {
+	struct nfsd3_readargs *argp = rqstp->rq_argp;
+	struct nfsd3_readres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	u32	max_blocksize = svc_max_payload(rqstp);
 	unsigned long cnt = min(argp->count, max_blocksize);
@@ -179,9 +185,10 @@ nfsd3_proc_read(struct svc_rqst *rqstp, struct nfsd3_readargs *argp,
  * Write data to a file
  */
 static __be32
-nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
-					 struct nfsd3_writeres  *resp)
+nfsd3_proc_write(struct svc_rqst *rqstp)
 {
+	struct nfsd3_writeargs *argp = rqstp->rq_argp;
+	struct nfsd3_writeres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	unsigned long cnt = argp->len;
 
@@ -193,11 +200,9 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
 
 	fh_copy(&resp->fh, &argp->fh);
 	resp->committed = argp->stable;
-	nfserr = nfsd_write(rqstp, &resp->fh, NULL,
-				   argp->offset,
-				   rqstp->rq_vec, argp->vlen,
-				   &cnt,
-				   &resp->committed);
+	nfserr = nfsd_write(rqstp, &resp->fh, argp->offset,
+				rqstp->rq_vec, argp->vlen,
+				&cnt, resp->committed);
 	resp->count = cnt;
 	RETURN_STATUS(nfserr);
 }
@@ -208,9 +213,10 @@ nfsd3_proc_write(struct svc_rqst *rqstp, struct nfsd3_writeargs *argp,
  * first reports about SunOS compatibility problems start to pour in...
  */
 static __be32
-nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
-					  struct nfsd3_diropres   *resp)
+nfsd3_proc_create(struct svc_rqst *rqstp)
 {
+	struct nfsd3_createargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
 	svc_fh		*dirfhp, *newfhp = NULL;
 	struct iattr	*attr;
 	__be32		nfserr;
@@ -245,9 +251,10 @@ nfsd3_proc_create(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
  * Make directory. This operation is not idempotent.
  */
 static __be32
-nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
-					 struct nfsd3_diropres   *resp)
+nfsd3_proc_mkdir(struct svc_rqst *rqstp)
 {
+	struct nfsd3_createargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: MKDIR(3)    %s %.*s\n",
@@ -265,9 +272,10 @@ nfsd3_proc_mkdir(struct svc_rqst *rqstp, struct nfsd3_createargs *argp,
 }
 
 static __be32
-nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp,
-					   struct nfsd3_diropres    *resp)
+nfsd3_proc_symlink(struct svc_rqst *rqstp)
 {
+	struct nfsd3_symlinkargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: SYMLINK(3)  %s %.*s -> %.*s\n",
@@ -286,9 +294,10 @@ nfsd3_proc_symlink(struct svc_rqst *rqstp, struct nfsd3_symlinkargs *argp,
  * Make socket/fifo/device.
  */
 static __be32
-nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp,
-					 struct nfsd3_diropres  *resp)
+nfsd3_proc_mknod(struct svc_rqst *rqstp)
 {
+	struct nfsd3_mknodargs *argp = rqstp->rq_argp;
+	struct nfsd3_diropres  *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	int type;
 	dev_t	rdev = 0;
@@ -323,9 +332,10 @@ nfsd3_proc_mknod(struct svc_rqst *rqstp, struct nfsd3_mknodargs *argp,
  * Remove file/fifo/socket etc.
  */
 static __be32
-nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
-					  struct nfsd3_attrstat  *resp)
+nfsd3_proc_remove(struct svc_rqst *rqstp)
 {
+	struct nfsd3_diropargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: REMOVE(3)   %s %.*s\n",
@@ -344,9 +354,10 @@ nfsd3_proc_remove(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
  * Remove a directory
  */
 static __be32
-nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
-					 struct nfsd3_attrstat  *resp)
+nfsd3_proc_rmdir(struct svc_rqst *rqstp)
 {
+	struct nfsd3_diropargs *argp = rqstp->rq_argp;
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: RMDIR(3)    %s %.*s\n",
@@ -361,9 +372,10 @@ nfsd3_proc_rmdir(struct svc_rqst *rqstp, struct nfsd3_diropargs *argp,
 }
 
 static __be32
-nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp,
-					  struct nfsd3_renameres  *resp)
+nfsd3_proc_rename(struct svc_rqst *rqstp)
 {
+	struct nfsd3_renameargs *argp = rqstp->rq_argp;
+	struct nfsd3_renameres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: RENAME(3)   %s %.*s ->\n",
@@ -383,9 +395,10 @@ nfsd3_proc_rename(struct svc_rqst *rqstp, struct nfsd3_renameargs *argp,
 }
 
 static __be32
-nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp,
-					struct nfsd3_linkres  *resp)
+nfsd3_proc_link(struct svc_rqst *rqstp)
 {
+	struct nfsd3_linkargs *argp = rqstp->rq_argp;
+	struct nfsd3_linkres  *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: LINK(3)     %s ->\n",
@@ -406,9 +419,10 @@ nfsd3_proc_link(struct svc_rqst *rqstp, struct nfsd3_linkargs *argp,
  * Read a portion of a directory.
  */
 static __be32
-nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
-					   struct nfsd3_readdirres  *resp)
+nfsd3_proc_readdir(struct svc_rqst *rqstp)
 {
+	struct nfsd3_readdirargs *argp = rqstp->rq_argp;
+	struct nfsd3_readdirres  *resp = rqstp->rq_resp;
 	__be32		nfserr;
 	int		count;
 
@@ -442,9 +456,10 @@ nfsd3_proc_readdir(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
  * For now, we choose to ignore the dircount parameter.
  */
 static __be32
-nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
-					       struct nfsd3_readdirres  *resp)
+nfsd3_proc_readdirplus(struct svc_rqst *rqstp)
 {
+	struct nfsd3_readdirargs *argp = rqstp->rq_argp;
+	struct nfsd3_readdirres  *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	int	count = 0;
 	loff_t	offset;
@@ -509,9 +524,10 @@ nfsd3_proc_readdirplus(struct svc_rqst *rqstp, struct nfsd3_readdirargs *argp,
  * Get file system stats
  */
 static __be32
-nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
-					   struct nfsd3_fsstatres *resp)
+nfsd3_proc_fsstat(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd3_fsstatres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: FSSTAT(3)   %s\n",
@@ -526,9 +542,10 @@ nfsd3_proc_fsstat(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
  * Get file system info
  */
 static __be32
-nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
-					   struct nfsd3_fsinfores *resp)
+nfsd3_proc_fsinfo(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd3_fsinfores *resp = rqstp->rq_resp;
 	__be32	nfserr;
 	u32	max_blocksize = svc_max_payload(rqstp);
 
@@ -569,9 +586,10 @@ nfsd3_proc_fsinfo(struct svc_rqst * rqstp, struct nfsd_fhandle    *argp,
  * Get pathconf info for the specified file
  */
 static __be32
-nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle      *argp,
-					     struct nfsd3_pathconfres *resp)
+nfsd3_proc_pathconf(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd3_pathconfres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: PATHCONF(3) %s\n",
@@ -612,9 +630,10 @@ nfsd3_proc_pathconf(struct svc_rqst * rqstp, struct nfsd_fhandle      *argp,
  * Commit a file (range) to stable storage.
  */
 static __be32
-nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp,
-					   struct nfsd3_commitres  *resp)
+nfsd3_proc_commit(struct svc_rqst *rqstp)
 {
+	struct nfsd3_commitargs *argp = rqstp->rq_argp;
+	struct nfsd3_commitres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: COMMIT(3)   %s %u@%Lu\n",
@@ -649,233 +668,221 @@ nfsd3_proc_commit(struct svc_rqst * rqstp, struct nfsd3_commitargs *argp,
 #define nfsd3_voidres			nfsd3_voidargs
 struct nfsd3_voidargs { int dummy; };
 
-#define PROC(name, argt, rest, relt, cache, respsize)	\
- { (svc_procfunc) nfsd3_proc_##name,		\
-   (kxdrproc_t) nfs3svc_decode_##argt##args,	\
-   (kxdrproc_t) nfs3svc_encode_##rest##res,	\
-   (kxdrproc_t) nfs3svc_release_##relt,		\
-   sizeof(struct nfsd3_##argt##args),		\
-   sizeof(struct nfsd3_##rest##res),		\
-   0,						\
-   cache,					\
-   respsize,					\
- }
-
 #define ST 1		/* status*/
 #define FH 17		/* filehandle with length */
 #define AT 21		/* attributes */
 #define pAT (1+AT)	/* post attributes - conditional */
 #define WC (7+pAT)	/* WCC attributes */
 
-static struct svc_procedure		nfsd_procedures3[22] = {
+static const struct svc_procedure nfsd_procedures3[22] = {
 	[NFS3PROC_NULL] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_null,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_voidres,
+		.pc_func = nfsd3_proc_null,
+		.pc_encode = nfs3svc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd3_voidargs),
 		.pc_ressize = sizeof(struct nfsd3_voidres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST,
 	},
 	[NFS3PROC_GETATTR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_getattr,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_attrstatres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_func = nfsd3_proc_getattr,
+		.pc_decode = nfs3svc_decode_fhandleargs,
+		.pc_encode = nfs3svc_encode_attrstatres,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_attrstatres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+AT,
 	},
 	[NFS3PROC_SETATTR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_setattr,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_sattrargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_func = nfsd3_proc_setattr,
+		.pc_decode = nfs3svc_decode_sattrargs,
+		.pc_encode = nfs3svc_encode_wccstatres,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_sattrargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+WC,
 	},
 	[NFS3PROC_LOOKUP] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_lookup,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_diropres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_func = nfsd3_proc_lookup,
+		.pc_decode = nfs3svc_decode_diropargs,
+		.pc_encode = nfs3svc_encode_diropres,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_diropres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+FH+pAT+pAT,
 	},
 	[NFS3PROC_ACCESS] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_access,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_accessargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_accessres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_func = nfsd3_proc_access,
+		.pc_decode = nfs3svc_decode_accessargs,
+		.pc_encode = nfs3svc_encode_accessres,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_accessargs),
 		.pc_ressize = sizeof(struct nfsd3_accessres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT+1,
 	},
 	[NFS3PROC_READLINK] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_readlink,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_readlinkargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_readlinkres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_func = nfsd3_proc_readlink,
+		.pc_decode = nfs3svc_decode_readlinkargs,
+		.pc_encode = nfs3svc_encode_readlinkres,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readlinkargs),
 		.pc_ressize = sizeof(struct nfsd3_readlinkres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT+1+NFS3_MAXPATHLEN/4,
 	},
 	[NFS3PROC_READ] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_read,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_readargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_readres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_func = nfsd3_proc_read,
+		.pc_decode = nfs3svc_decode_readargs,
+		.pc_encode = nfs3svc_encode_readres,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readargs),
 		.pc_ressize = sizeof(struct nfsd3_readres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT+4+NFSSVC_MAXBLKSIZE/4,
 	},
 	[NFS3PROC_WRITE] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_write,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_writeargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_writeres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_func = nfsd3_proc_write,
+		.pc_decode = nfs3svc_decode_writeargs,
+		.pc_encode = nfs3svc_encode_writeres,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_writeargs),
 		.pc_ressize = sizeof(struct nfsd3_writeres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+WC+4,
 	},
 	[NFS3PROC_CREATE] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_create,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_createargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_func = nfsd3_proc_create,
+		.pc_decode = nfs3svc_decode_createargs,
+		.pc_encode = nfs3svc_encode_createres,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_createargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
 	},
 	[NFS3PROC_MKDIR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_mkdir,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_mkdirargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_func = nfsd3_proc_mkdir,
+		.pc_decode = nfs3svc_decode_mkdirargs,
+		.pc_encode = nfs3svc_encode_createres,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mkdirargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
 	},
 	[NFS3PROC_SYMLINK] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_symlink,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_symlinkargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_func = nfsd3_proc_symlink,
+		.pc_decode = nfs3svc_decode_symlinkargs,
+		.pc_encode = nfs3svc_encode_createres,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_symlinkargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
 	},
 	[NFS3PROC_MKNOD] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_mknod,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_mknodargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_createres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_func = nfsd3_proc_mknod,
+		.pc_decode = nfs3svc_decode_mknodargs,
+		.pc_encode = nfs3svc_encode_createres,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_mknodargs),
 		.pc_ressize = sizeof(struct nfsd3_createres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+(1+FH+pAT)+WC,
 	},
 	[NFS3PROC_REMOVE] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_remove,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_func = nfsd3_proc_remove,
+		.pc_decode = nfs3svc_decode_diropargs,
+		.pc_encode = nfs3svc_encode_wccstatres,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+WC,
 	},
 	[NFS3PROC_RMDIR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_rmdir,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_wccstatres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_func = nfsd3_proc_rmdir,
+		.pc_decode = nfs3svc_decode_diropargs,
+		.pc_encode = nfs3svc_encode_wccstatres,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_diropargs),
 		.pc_ressize = sizeof(struct nfsd3_wccstatres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+WC,
 	},
 	[NFS3PROC_RENAME] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_rename,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_renameargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_renameres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_func = nfsd3_proc_rename,
+		.pc_decode = nfs3svc_decode_renameargs,
+		.pc_encode = nfs3svc_encode_renameres,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_renameargs),
 		.pc_ressize = sizeof(struct nfsd3_renameres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+WC+WC,
 	},
 	[NFS3PROC_LINK] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_link,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_linkargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_linkres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle2,
+		.pc_func = nfsd3_proc_link,
+		.pc_decode = nfs3svc_decode_linkargs,
+		.pc_encode = nfs3svc_encode_linkres,
+		.pc_release = nfs3svc_release_fhandle2,
 		.pc_argsize = sizeof(struct nfsd3_linkargs),
 		.pc_ressize = sizeof(struct nfsd3_linkres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+pAT+WC,
 	},
 	[NFS3PROC_READDIR] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_readdir,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_func = nfsd3_proc_readdir,
+		.pc_decode = nfs3svc_decode_readdirargs,
+		.pc_encode = nfs3svc_encode_readdirres,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirargs),
 		.pc_ressize = sizeof(struct nfsd3_readdirres),
 		.pc_cachetype = RC_NOCACHE,
 	},
 	[NFS3PROC_READDIRPLUS] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_readdirplus,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_readdirplusargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_readdirres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_func = nfsd3_proc_readdirplus,
+		.pc_decode = nfs3svc_decode_readdirplusargs,
+		.pc_encode = nfs3svc_encode_readdirres,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_readdirplusargs),
 		.pc_ressize = sizeof(struct nfsd3_readdirres),
 		.pc_cachetype = RC_NOCACHE,
 	},
 	[NFS3PROC_FSSTAT] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_fsstat,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsstatres,
+		.pc_func = nfsd3_proc_fsstat,
+		.pc_decode = nfs3svc_decode_fhandleargs,
+		.pc_encode = nfs3svc_encode_fsstatres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_fsstatres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT+2*6+1,
 	},
 	[NFS3PROC_FSINFO] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_fsinfo,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_fsinfores,
+		.pc_func = nfsd3_proc_fsinfo,
+		.pc_decode = nfs3svc_decode_fhandleargs,
+		.pc_encode = nfs3svc_encode_fsinfores,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_fsinfores),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT+12,
 	},
 	[NFS3PROC_PATHCONF] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_pathconf,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_fhandleargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_pathconfres,
+		.pc_func = nfsd3_proc_pathconf,
+		.pc_decode = nfs3svc_decode_fhandleargs,
+		.pc_encode = nfs3svc_encode_pathconfres,
 		.pc_argsize = sizeof(struct nfsd3_fhandleargs),
 		.pc_ressize = sizeof(struct nfsd3_pathconfres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+pAT+6,
 	},
 	[NFS3PROC_COMMIT] = {
-		.pc_func = (svc_procfunc) nfsd3_proc_commit,
-		.pc_decode = (kxdrproc_t) nfs3svc_decode_commitargs,
-		.pc_encode = (kxdrproc_t) nfs3svc_encode_commitres,
-		.pc_release = (kxdrproc_t) nfs3svc_release_fhandle,
+		.pc_func = nfsd3_proc_commit,
+		.pc_decode = nfs3svc_decode_commitargs,
+		.pc_encode = nfs3svc_encode_commitres,
+		.pc_release = nfs3svc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd3_commitargs),
 		.pc_ressize = sizeof(struct nfsd3_commitres),
 		.pc_cachetype = RC_NOCACHE,
@@ -883,10 +890,12 @@ static struct svc_procedure		nfsd_procedures3[22] = {
 	},
 };
 
-struct svc_version	nfsd_version3 = {
-		.vs_vers	= 3,
-		.vs_nproc	= 22,
-		.vs_proc	= nfsd_procedures3,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS3_SVC_XDRSIZE,
+static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures3)];
+const struct svc_version nfsd_version3 = {
+	.vs_vers	= 3,
+	.vs_nproc	= 22,
+	.vs_proc	= nfsd_procedures3,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_count	= nfsd_count3,
+	.vs_xdrsize	= NFS3_SVC_XDRSIZE,
 };
diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c
index dba2ff8eaa68..bf444b664011 100644
--- a/fs/nfsd/nfs3xdr.c
+++ b/fs/nfsd/nfs3xdr.c
@@ -260,7 +260,7 @@ void fill_post_wcc(struct svc_fh *fhp)
 		printk("nfsd: inode locked twice during operation.\n");
 
 	err = fh_getattr(fhp, &fhp->fh_post_attr);
-	fhp->fh_post_change = d_inode(fhp->fh_dentry)->i_version;
+	fhp->fh_post_change = nfsd4_change_attribute(d_inode(fhp->fh_dentry));
 	if (err) {
 		fhp->fh_post_saved = false;
 		/* Grab the ctime anyway - set_change_info might use it */
@@ -273,8 +273,10 @@ void fill_post_wcc(struct svc_fh *fhp)
  * XDR decode functions
  */
 int
-nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args)
+nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_fhandle *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -282,9 +284,10 @@ nfs3svc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *a
 }
 
 int
-nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_sattrargs *args)
+nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_sattrargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -300,9 +303,10 @@ nfs3svc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_diropargs *args)
+nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_diropargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh))
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -311,9 +315,10 @@ nfs3svc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_accessargs *args)
+nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_accessargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -323,9 +328,9 @@ nfs3svc_decode_accessargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readargs *args)
+nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readargs *args = rqstp->rq_argp;
 	unsigned int len;
 	int v;
 	u32 max_blocksize = svc_max_payload(rqstp);
@@ -353,11 +358,13 @@ nfs3svc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_writeargs *args)
+nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_writeargs *args = rqstp->rq_argp;
 	unsigned int len, v, hdr, dlen;
 	u32 max_blocksize = svc_max_payload(rqstp);
+	struct kvec *head = rqstp->rq_arg.head;
+	struct kvec *tail = rqstp->rq_arg.tail;
 
 	p = decode_fh(p, &args->fh);
 	if (!p)
@@ -367,6 +374,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	args->count = ntohl(*p++);
 	args->stable = ntohl(*p++);
 	len = args->len = ntohl(*p++);
+	if ((void *)p > head->iov_base + head->iov_len)
+		return 0;
 	/*
 	 * The count must equal the amount of data passed.
 	 */
@@ -377,9 +386,8 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	 * Check to make sure that we got the right number of
 	 * bytes.
 	 */
-	hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
-	dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
-		+ rqstp->rq_arg.tail[0].iov_len - hdr;
+	hdr = (void*)p - head->iov_base;
+	dlen = head->iov_len + rqstp->rq_arg.page_len + tail->iov_len - hdr;
 	/*
 	 * Round the length of the data which was specified up to
 	 * the next multiple of XDR units and then compare that
@@ -396,7 +404,7 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 		len = args->len = max_blocksize;
 	}
 	rqstp->rq_vec[0].iov_base = (void*)p;
-	rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+	rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
 	v = 0;
 	while (len > rqstp->rq_vec[v].iov_len) {
 		len -= rqstp->rq_vec[v].iov_len;
@@ -410,9 +418,10 @@ nfs3svc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_createargs *args)
+nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_createargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh))
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -432,10 +441,12 @@ nfs3svc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
 
 	return xdr_argsize_check(rqstp, p);
 }
+
 int
-nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_createargs *args)
+nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_createargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh)) ||
 	    !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -445,9 +456,9 @@ nfs3svc_decode_mkdirargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_symlinkargs *args)
+nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_symlinkargs *args = rqstp->rq_argp;
 	unsigned int len, avail;
 	char *old, *new;
 	struct kvec *vec;
@@ -471,6 +482,8 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
 	/* first copy and check from the first page */
 	old = (char*)p;
 	vec = &rqstp->rq_arg.head[0];
+	if ((void *)old > vec->iov_base + vec->iov_len)
+		return 0;
 	avail = vec->iov_len - (old - (char*)vec->iov_base);
 	while (len && avail && *old) {
 		*new++ = *old++;
@@ -495,9 +508,10 @@ nfs3svc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_mknodargs *args)
+nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_mknodargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh))
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -517,9 +531,10 @@ nfs3svc_decode_mknodargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_renameargs *args)
+nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_renameargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->ffh))
 	 || !(p = decode_filename(p, &args->fname, &args->flen))
 	 || !(p = decode_fh(p, &args->tfh))
@@ -530,9 +545,10 @@ nfs3svc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readlinkargs *args)
+nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readlinkargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -542,9 +558,10 @@ nfs3svc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_linkargs *args)
+nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_linkargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->ffh))
 	 || !(p = decode_fh(p, &args->tfh))
 	 || !(p = decode_filename(p, &args->tname, &args->tlen)))
@@ -554,9 +571,9 @@ nfs3svc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readdirargs *args)
+nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readdirargs *args = rqstp->rq_argp;
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -571,9 +588,9 @@ nfs3svc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readdirargs *args)
+nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readdirargs *args = rqstp->rq_argp;
 	int len;
 	u32 max_blocksize = svc_max_payload(rqstp);
 
@@ -597,9 +614,9 @@ nfs3svc_decode_readdirplusargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_commitargs *args)
+nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_commitargs *args = rqstp->rq_argp;
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -617,16 +634,17 @@ nfs3svc_decode_commitargs(struct svc_rqst *rqstp, __be32 *p,
  * will work properly.
  */
 int
-nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nfs3svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
 
 /* GETATTR */
 int
-nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_attrstat *resp)
+nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
 	if (resp->status == 0) {
 		lease_get_mtime(d_inode(resp->fh.fh_dentry),
 				&resp->stat.mtime);
@@ -637,18 +655,20 @@ nfs3svc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p,
 
 /* SETATTR, REMOVE, RMDIR */
 int
-nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_attrstat *resp)
+nfs3svc_encode_wccstat(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
 	p = encode_wcc_data(rqstp, p, &resp->fh);
 	return xdr_ressize_check(rqstp, p);
 }
 
 /* LOOKUP */
 int
-nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_diropres *resp)
+nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
+
 	if (resp->status == 0) {
 		p = encode_fh(p, &resp->fh);
 		p = encode_post_op_attr(rqstp, p, &resp->fh);
@@ -659,9 +679,10 @@ nfs3svc_encode_diropres(struct svc_rqst *rqstp, __be32 *p,
 
 /* ACCESS */
 int
-nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_accessres *resp)
+nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_accessres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 	if (resp->status == 0)
 		*p++ = htonl(resp->access);
@@ -670,9 +691,10 @@ nfs3svc_encode_accessres(struct svc_rqst *rqstp, __be32 *p,
 
 /* READLINK */
 int
-nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readlinkres *resp)
+nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readlinkres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 	if (resp->status == 0) {
 		*p++ = htonl(resp->len);
@@ -691,9 +713,10 @@ nfs3svc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
 
 /* READ */
 int
-nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readres *resp)
+nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 	if (resp->status == 0) {
 		*p++ = htonl(resp->count);
@@ -715,9 +738,9 @@ nfs3svc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
 
 /* WRITE */
 int
-nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_writeres *resp)
+nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_writeres *resp = rqstp->rq_resp;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
 	p = encode_wcc_data(rqstp, p, &resp->fh);
@@ -732,9 +755,10 @@ nfs3svc_encode_writeres(struct svc_rqst *rqstp, __be32 *p,
 
 /* CREATE, MKDIR, SYMLINK, MKNOD */
 int
-nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_diropres *resp)
+nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_diropres *resp = rqstp->rq_resp;
+
 	if (resp->status == 0) {
 		*p++ = xdr_one;
 		p = encode_fh(p, &resp->fh);
@@ -746,9 +770,10 @@ nfs3svc_encode_createres(struct svc_rqst *rqstp, __be32 *p,
 
 /* RENAME */
 int
-nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_renameres *resp)
+nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_renameres *resp = rqstp->rq_resp;
+
 	p = encode_wcc_data(rqstp, p, &resp->ffh);
 	p = encode_wcc_data(rqstp, p, &resp->tfh);
 	return xdr_ressize_check(rqstp, p);
@@ -756,9 +781,10 @@ nfs3svc_encode_renameres(struct svc_rqst *rqstp, __be32 *p,
 
 /* LINK */
 int
-nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_linkres *resp)
+nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_linkres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 	p = encode_wcc_data(rqstp, p, &resp->tfh);
 	return xdr_ressize_check(rqstp, p);
@@ -766,9 +792,10 @@ nfs3svc_encode_linkres(struct svc_rqst *rqstp, __be32 *p,
 
 /* READDIR */
 int
-nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_readdirres *resp)
+nfs3svc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_readdirres *resp = rqstp->rq_resp;
+
 	p = encode_post_op_attr(rqstp, p, &resp->fh);
 
 	if (resp->status == 0) {
@@ -1016,9 +1043,9 @@ nfs3svc_encode_entry_plus(void *cd, const char *name,
 
 /* FSSTAT */
 int
-nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_fsstatres *resp)
+nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_fsstatres *resp = rqstp->rq_resp;
 	struct kstatfs	*s = &resp->stats;
 	u64		bs = s->f_bsize;
 
@@ -1038,9 +1065,10 @@ nfs3svc_encode_fsstatres(struct svc_rqst *rqstp, __be32 *p,
 
 /* FSINFO */
 int
-nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_fsinfores *resp)
+nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_fsinfores *resp = rqstp->rq_resp;
+
 	*p++ = xdr_zero;	/* no post_op_attr */
 
 	if (resp->status == 0) {
@@ -1062,9 +1090,10 @@ nfs3svc_encode_fsinfores(struct svc_rqst *rqstp, __be32 *p,
 
 /* PATHCONF */
 int
-nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_pathconfres *resp)
+nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_pathconfres *resp = rqstp->rq_resp;
+
 	*p++ = xdr_zero;	/* no post_op_attr */
 
 	if (resp->status == 0) {
@@ -1081,9 +1110,9 @@ nfs3svc_encode_pathconfres(struct svc_rqst *rqstp, __be32 *p,
 
 /* COMMIT */
 int
-nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_commitres *resp)
+nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd3_commitres *resp = rqstp->rq_resp;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 
 	p = encode_wcc_data(rqstp, p, &resp->fh);
@@ -1098,19 +1127,19 @@ nfs3svc_encode_commitres(struct svc_rqst *rqstp, __be32 *p,
 /*
  * XDR release functions
  */
-int
-nfs3svc_release_fhandle(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_attrstat *resp)
+void
+nfs3svc_release_fhandle(struct svc_rqst *rqstp)
 {
+	struct nfsd3_attrstat *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
-	return 1;
 }
 
-int
-nfs3svc_release_fhandle2(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd3_fhandle_pair *resp)
+void
+nfs3svc_release_fhandle2(struct svc_rqst *rqstp)
 {
+	struct nfsd3_fhandle_pair *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh1);
 	fh_put(&resp->fh2);
-	return 1;
 }
diff --git a/fs/nfsd/nfs4callback.c b/fs/nfsd/nfs4callback.c
index eb78109d666c..49b0a9e7ff18 100644
--- a/fs/nfsd/nfs4callback.c
+++ b/fs/nfsd/nfs4callback.c
@@ -303,6 +303,7 @@ static int decode_cb_compound4res(struct xdr_stream *xdr,
 	p = xdr_inline_decode(xdr, length + 4);
 	if (unlikely(p == NULL))
 		goto out_overflow;
+	p += XDR_QUADLEN(length);
 	hdr->nops = be32_to_cpup(p);
 	return 0;
 out_overflow:
@@ -396,13 +397,10 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr,
 				    struct nfsd4_callback *cb)
 {
 	struct nfsd4_session *session = cb->cb_clp->cl_cb_session;
-	struct nfs4_sessionid id;
-	int status;
+	int status = -ESERVERFAULT;
 	__be32 *p;
 	u32 dummy;
 
-	status = -ESERVERFAULT;
-
 	/*
 	 * If the server returns different values for sessionID, slotID or
 	 * sequence number, the server is looney tunes.
@@ -410,9 +408,8 @@ static int decode_cb_sequence4resok(struct xdr_stream *xdr,
 	p = xdr_inline_decode(xdr, NFS4_MAX_SESSIONID_LEN + 4 + 4 + 4 + 4);
 	if (unlikely(p == NULL))
 		goto out_overflow;
-	memcpy(id.data, p, NFS4_MAX_SESSIONID_LEN);
-	if (memcmp(id.data, session->se_sessionid.data,
-					NFS4_MAX_SESSIONID_LEN) != 0) {
+
+	if (memcmp(p, session->se_sessionid.data, NFS4_MAX_SESSIONID_LEN)) {
 		dprintk("NFS: %s Invalid session id\n", __func__);
 		goto out;
 	}
@@ -471,7 +468,7 @@ static int decode_cb_sequence4res(struct xdr_stream *xdr,
  * NB: Without this zero space reservation, callbacks over krb5p fail
  */
 static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
-				 void *__unused)
+				 const void *__unused)
 {
 	xdr_reserve_space(xdr, 0);
 }
@@ -480,8 +477,9 @@ static void nfs4_xdr_enc_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
  * 20.2. Operation 4: CB_RECALL - Recall a Delegation
  */
 static void nfs4_xdr_enc_cb_recall(struct rpc_rqst *req, struct xdr_stream *xdr,
-				   const struct nfsd4_callback *cb)
+				   const void *data)
 {
+	const struct nfsd4_callback *cb = data;
 	const struct nfs4_delegation *dp = cb_to_delegation(cb);
 	struct nfs4_cb_compound_hdr hdr = {
 		.ident = cb->cb_clp->cl_cb_ident,
@@ -515,8 +513,9 @@ static int nfs4_xdr_dec_cb_null(struct rpc_rqst *req, struct xdr_stream *xdr,
  */
 static int nfs4_xdr_dec_cb_recall(struct rpc_rqst *rqstp,
 				  struct xdr_stream *xdr,
-				  struct nfsd4_callback *cb)
+				  void *data)
 {
+	struct nfsd4_callback *cb = data;
 	struct nfs4_cb_compound_hdr hdr;
 	int status;
 
@@ -588,8 +587,9 @@ static void encode_cb_layout4args(struct xdr_stream *xdr,
 
 static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req,
 				   struct xdr_stream *xdr,
-				   const struct nfsd4_callback *cb)
+				   const void *data)
 {
+	const struct nfsd4_callback *cb = data;
 	const struct nfs4_layout_stateid *ls =
 		container_of(cb, struct nfs4_layout_stateid, ls_recall);
 	struct nfs4_cb_compound_hdr hdr = {
@@ -605,8 +605,9 @@ static void nfs4_xdr_enc_cb_layout(struct rpc_rqst *req,
 
 static int nfs4_xdr_dec_cb_layout(struct rpc_rqst *rqstp,
 				  struct xdr_stream *xdr,
-				  struct nfsd4_callback *cb)
+				  void *data)
 {
+	struct nfsd4_callback *cb = data;
 	struct nfs4_cb_compound_hdr hdr;
 	int status;
 
@@ -634,8 +635,9 @@ static void encode_stateowner(struct xdr_stream *xdr, struct nfs4_stateowner *so
 
 static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req,
 					struct xdr_stream *xdr,
-					const struct nfsd4_callback *cb)
+					const void *data)
 {
+	const struct nfsd4_callback *cb = data;
 	const struct nfsd4_blocked_lock *nbl =
 		container_of(cb, struct nfsd4_blocked_lock, nbl_cb);
 	struct nfs4_lockowner *lo = (struct nfs4_lockowner *)nbl->nbl_lock.fl_owner;
@@ -662,8 +664,9 @@ static void nfs4_xdr_enc_cb_notify_lock(struct rpc_rqst *req,
 
 static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp,
 					struct xdr_stream *xdr,
-					struct nfsd4_callback *cb)
+					void *data)
 {
+	struct nfsd4_callback *cb = data;
 	struct nfs4_cb_compound_hdr hdr;
 	int status;
 
@@ -685,15 +688,15 @@ static int nfs4_xdr_dec_cb_notify_lock(struct rpc_rqst *rqstp,
 #define PROC(proc, call, argtype, restype)				\
 [NFSPROC4_CLNT_##proc] = {						\
 	.p_proc    = NFSPROC4_CB_##call,				\
-	.p_encode  = (kxdreproc_t)nfs4_xdr_enc_##argtype,		\
-	.p_decode  = (kxdrdproc_t)nfs4_xdr_dec_##restype,		\
+	.p_encode  = nfs4_xdr_enc_##argtype,		\
+	.p_decode  = nfs4_xdr_dec_##restype,				\
 	.p_arglen  = NFS4_enc_##argtype##_sz,				\
 	.p_replen  = NFS4_dec_##restype##_sz,				\
 	.p_statidx = NFSPROC4_CB_##call,				\
 	.p_name    = #proc,						\
 }
 
-static struct rpc_procinfo nfs4_cb_procedures[] = {
+static const struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NULL,	NULL,		cb_null,	cb_null),
 	PROC(CB_RECALL,	COMPOUND,	cb_recall,	cb_recall),
 #ifdef CONFIG_NFSD_PNFS
@@ -702,7 +705,8 @@ static struct rpc_procinfo nfs4_cb_procedures[] = {
 	PROC(CB_NOTIFY_LOCK,	COMPOUND,	cb_notify_lock,	cb_notify_lock),
 };
 
-static struct rpc_version nfs_cb_version4 = {
+static unsigned int nfs4_cb_counts[ARRAY_SIZE(nfs4_cb_procedures)];
+static const struct rpc_version nfs_cb_version4 = {
 /*
  * Note on the callback rpc program version number: despite language in rfc
  * 5661 section 18.36.3 requiring servers to use 4 in this field, the
@@ -712,11 +716,12 @@ static struct rpc_version nfs_cb_version4 = {
  */
 	.number			= 1,
 	.nrprocs		= ARRAY_SIZE(nfs4_cb_procedures),
-	.procs			= nfs4_cb_procedures
+	.procs			= nfs4_cb_procedures,
+	.counts			= nfs4_cb_counts,
 };
 
-static const struct rpc_version *nfs_cb_version[] = {
-	&nfs_cb_version4,
+static const struct rpc_version *nfs_cb_version[2] = {
+	[1] = &nfs_cb_version4,
 };
 
 static const struct rpc_program cb_program;
@@ -753,6 +758,14 @@ int set_callback_cred(void)
 	return 0;
 }
 
+void cleanup_callback_cred(void)
+{
+	if (callback_cred) {
+		put_rpccred(callback_cred);
+		callback_cred = NULL;
+	}
+}
+
 static struct rpc_cred *get_backchannel_cred(struct nfs4_client *clp, struct rpc_clnt *client, struct nfsd4_session *ses)
 {
 	if (clp->cl_minorversion == 0) {
@@ -782,7 +795,7 @@ static int setup_callback_client(struct nfs4_client *clp, struct nfs4_cb_conn *c
 		.saddress	= (struct sockaddr *) &conn->cb_saddr,
 		.timeout	= &timeparms,
 		.program	= &cb_program,
-		.version	= 0,
+		.version	= 1,
 		.flags		= (RPC_CLNT_CREATE_NOPING | RPC_CLNT_CREATE_QUIET),
 	};
 	struct rpc_clnt *client;
diff --git a/fs/nfsd/nfs4idmap.c b/fs/nfsd/nfs4idmap.c
index 5b20577dcdd2..6b9b6cca469f 100644
--- a/fs/nfsd/nfs4idmap.c
+++ b/fs/nfsd/nfs4idmap.c
@@ -628,6 +628,10 @@ nfsd_map_name_to_uid(struct svc_rqst *rqstp, const char *name, size_t namelen,
 {
 	__be32 status;
 	u32 id = -1;
+
+	if (name == NULL || namelen == 0)
+		return nfserr_inval;
+
 	status = do_name_to_id(rqstp, IDMAP_TYPE_USER, name, namelen, &id);
 	*uid = make_kuid(&init_user_ns, id);
 	if (!uid_valid(*uid))
@@ -641,6 +645,10 @@ nfsd_map_name_to_gid(struct svc_rqst *rqstp, const char *name, size_t namelen,
 {
 	__be32 status;
 	u32 id = -1;
+
+	if (name == NULL || namelen == 0)
+		return nfserr_inval;
+
 	status = do_name_to_id(rqstp, IDMAP_TYPE_GROUP, name, namelen, &id);
 	*gid = make_kgid(&init_user_ns, id);
 	if (!gid_valid(*gid))
diff --git a/fs/nfsd/nfs4layouts.c b/fs/nfsd/nfs4layouts.c
index 1fc07a9c70e9..e122da696f1b 100644
--- a/fs/nfsd/nfs4layouts.c
+++ b/fs/nfsd/nfs4layouts.c
@@ -614,6 +614,7 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
 {
 	struct nfs4_client *clp = ls->ls_stid.sc_client;
 	char addr_str[INET6_ADDRSTRLEN];
+	static char const nfsd_recall_failed[] = "/sbin/nfsd-recall-failed";
 	static char *envp[] = {
 		"HOME=/",
 		"TERM=linux",
@@ -629,12 +630,13 @@ nfsd4_cb_layout_fail(struct nfs4_layout_stateid *ls)
 		"nfsd: client %s failed to respond to layout recall. "
 		"  Fencing..\n", addr_str);
 
-	argv[0] = "/sbin/nfsd-recall-failed";
+	argv[0] = (char *)nfsd_recall_failed;
 	argv[1] = addr_str;
 	argv[2] = ls->ls_file->f_path.mnt->mnt_sb->s_id;
 	argv[3] = NULL;
 
-	error = call_usermodehelper(argv[0], argv, envp, UMH_WAIT_PROC);
+	error = call_usermodehelper(nfsd_recall_failed, argv, envp,
+				    UMH_WAIT_PROC);
 	if (error) {
 		printk(KERN_ERR "nfsd: fence failed for client %s: %d!\n",
 			addr_str, error);
diff --git a/fs/nfsd/nfs4proc.c b/fs/nfsd/nfs4proc.c
index 74a6e573e061..d27e75ad25e3 100644
--- a/fs/nfsd/nfs4proc.c
+++ b/fs/nfsd/nfs4proc.c
@@ -95,11 +95,15 @@ check_attr_support(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 		   u32 *bmval, u32 *writable)
 {
 	struct dentry *dentry = cstate->current_fh.fh_dentry;
+	struct svc_export *exp = cstate->current_fh.fh_export;
 
 	if (!nfsd_attrs_supported(cstate->minorversion, bmval))
 		return nfserr_attrnotsupp;
 	if ((bmval[0] & FATTR4_WORD0_ACL) && !IS_POSIXACL(d_inode(dentry)))
 		return nfserr_attrnotsupp;
+	if ((bmval[2] & FATTR4_WORD2_SECURITY_LABEL) &&
+			!(exp->ex_flags & NFSEXP_SECURITY_LABEL))
+		return nfserr_attrnotsupp;
 	if (writable && !bmval_is_subset(bmval, writable))
 		return nfserr_inval;
 	if (writable && (bmval[2] & FATTR4_WORD2_MODE_UMASK) &&
@@ -340,8 +344,9 @@ copy_clientid(clientid_t *clid, struct nfsd4_session *session)
 
 static __be32
 nfsd4_open(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	   struct nfsd4_open *open)
+	   union nfsd4_op_u *u)
 {
+	struct nfsd4_open *open = &u->open;
 	__be32 status;
 	struct svc_fh *resfh = NULL;
 	struct net *net = SVC_NET(rqstp);
@@ -463,14 +468,14 @@ out:
  */
 static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_op *op)
 {
-	struct nfsd4_open *open = (struct nfsd4_open *)&op->u;
+	struct nfsd4_open *open = &op->u.open;
 
 	if (!seqid_mutating_err(ntohl(op->status)))
 		return op->status;
 	if (nfsd4_has_session(cstate))
 		return op->status;
 	open->op_xdr_error = op->status;
-	return nfsd4_open(rqstp, cstate, open);
+	return nfsd4_open(rqstp, cstate, &op->u);
 }
 
 /*
@@ -478,19 +483,21 @@ static __be32 nfsd4_open_omfg(struct svc_rqst *rqstp, struct nfsd4_compound_stat
  */
 static __be32
 nfsd4_getfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	    struct svc_fh **getfh)
+	    union nfsd4_op_u *u)
 {
 	if (!cstate->current_fh.fh_dentry)
 		return nfserr_nofilehandle;
 
-	*getfh = &cstate->current_fh;
+	u->getfh = &cstate->current_fh;
 	return nfs_ok;
 }
 
 static __be32
 nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	    struct nfsd4_putfh *putfh)
+	    union nfsd4_op_u *u)
 {
+	struct nfsd4_putfh *putfh = &u->putfh;
+
 	fh_put(&cstate->current_fh);
 	cstate->current_fh.fh_handle.fh_size = putfh->pf_fhlen;
 	memcpy(&cstate->current_fh.fh_handle.fh_base, putfh->pf_fhval,
@@ -500,7 +507,7 @@ nfsd4_putfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static __be32
 nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		void *arg)
+		union nfsd4_op_u *u)
 {
 	__be32 status;
 
@@ -511,7 +518,7 @@ nfsd4_putrootfh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static __be32
 nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		void *arg)
+		union nfsd4_op_u *u)
 {
 	if (!cstate->save_fh.fh_dentry)
 		return nfserr_restorefh;
@@ -526,7 +533,7 @@ nfsd4_restorefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static __be32
 nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	     void *arg)
+	     union nfsd4_op_u *u)
 {
 	if (!cstate->current_fh.fh_dentry)
 		return nfserr_nofilehandle;
@@ -544,8 +551,10 @@ nfsd4_savefh(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
  */
 static __be32
 nfsd4_access(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	     struct nfsd4_access *access)
+	     union nfsd4_op_u *u)
 {
+	struct nfsd4_access *access = &u->access;
+
 	if (access->ac_req_access & ~NFS3_ACCESS_FULL)
 		return nfserr_inval;
 
@@ -570,8 +579,10 @@ static void gen_boot_verifier(nfs4_verifier *verifier, struct net *net)
 
 static __be32
 nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	     struct nfsd4_commit *commit)
+	     union nfsd4_op_u *u)
 {
+	struct nfsd4_commit *commit = &u->commit;
+
 	gen_boot_verifier(&commit->co_verf, SVC_NET(rqstp));
 	return nfsd_commit(rqstp, &cstate->current_fh, commit->co_offset,
 			     commit->co_count);
@@ -579,8 +590,9 @@ nfsd4_commit(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static __be32
 nfsd4_create(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	     struct nfsd4_create *create)
+	     union nfsd4_op_u *u)
 {
+	struct nfsd4_create *create = &u->create;
 	struct svc_fh resfh;
 	__be32 status;
 	dev_t rdev;
@@ -666,8 +678,9 @@ out:
 
 static __be32
 nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	      struct nfsd4_getattr *getattr)
+	      union nfsd4_op_u *u)
 {
+	struct nfsd4_getattr *getattr = &u->getattr;
 	__be32 status;
 
 	status = fh_verify(rqstp, &cstate->current_fh, 0, NFSD_MAY_NOP);
@@ -687,8 +700,9 @@ nfsd4_getattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static __be32
 nfsd4_link(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	   struct nfsd4_link *link)
+	   union nfsd4_op_u *u)
 {
+	struct nfsd4_link *link = &u->link;
 	__be32 status = nfserr_nofilehandle;
 
 	if (!cstate->save_fh.fh_dentry)
@@ -719,24 +733,25 @@ static __be32 nfsd4_do_lookupp(struct svc_rqst *rqstp, struct svc_fh *fh)
 
 static __be32
 nfsd4_lookupp(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	      void *arg)
+	      union nfsd4_op_u *u)
 {
 	return nfsd4_do_lookupp(rqstp, &cstate->current_fh);
 }
 
 static __be32
 nfsd4_lookup(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	     struct nfsd4_lookup *lookup)
+	     union nfsd4_op_u *u)
 {
 	return nfsd_lookup(rqstp, &cstate->current_fh,
-			   lookup->lo_name, lookup->lo_len,
+			   u->lookup.lo_name, u->lookup.lo_len,
 			   &cstate->current_fh);
 }
 
 static __be32
 nfsd4_read(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	   struct nfsd4_read *read)
+	   union nfsd4_op_u *u)
 {
+	struct nfsd4_read *read = &u->read;
 	__be32 status;
 
 	read->rd_filp = NULL;
@@ -771,8 +786,9 @@ out:
 
 static __be32
 nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	      struct nfsd4_readdir *readdir)
+	      union nfsd4_op_u *u)
 {
+	struct nfsd4_readdir *readdir = &u->readdir;
 	u64 cookie = readdir->rd_cookie;
 	static const nfs4_verifier zeroverf;
 
@@ -796,17 +812,18 @@ nfsd4_readdir(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static __be32
 nfsd4_readlink(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	       struct nfsd4_readlink *readlink)
+	       union nfsd4_op_u *u)
 {
-	readlink->rl_rqstp = rqstp;
-	readlink->rl_fhp = &cstate->current_fh;
+	u->readlink.rl_rqstp = rqstp;
+	u->readlink.rl_fhp = &cstate->current_fh;
 	return nfs_ok;
 }
 
 static __be32
 nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	     struct nfsd4_remove *remove)
+	     union nfsd4_op_u *u)
 {
+	struct nfsd4_remove *remove = &u->remove;
 	__be32 status;
 
 	if (opens_in_grace(SVC_NET(rqstp)))
@@ -822,8 +839,9 @@ nfsd4_remove(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static __be32
 nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	     struct nfsd4_rename *rename)
+	     union nfsd4_op_u *u)
 {
+	struct nfsd4_rename *rename = &u->rename;
 	__be32 status = nfserr_nofilehandle;
 
 	if (!cstate->save_fh.fh_dentry)
@@ -843,8 +861,9 @@ nfsd4_rename(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static __be32
 nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	      struct nfsd4_secinfo *secinfo)
+	      union nfsd4_op_u *u)
 {
+	struct nfsd4_secinfo *secinfo = &u->secinfo;
 	struct svc_export *exp;
 	struct dentry *dentry;
 	__be32 err;
@@ -872,11 +891,11 @@ nfsd4_secinfo(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static __be32
 nfsd4_secinfo_no_name(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	      struct nfsd4_secinfo_no_name *sin)
+		union nfsd4_op_u *u)
 {
 	__be32 err;
 
-	switch (sin->sin_style) {
+	switch (u->secinfo_no_name.sin_style) {
 	case NFS4_SECINFO_STYLE4_CURRENT_FH:
 		break;
 	case NFS4_SECINFO_STYLE4_PARENT:
@@ -888,15 +907,16 @@ nfsd4_secinfo_no_name(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstat
 		return nfserr_inval;
 	}
 
-	sin->sin_exp = exp_get(cstate->current_fh.fh_export);
+	u->secinfo_no_name.sin_exp = exp_get(cstate->current_fh.fh_export);
 	fh_put(&cstate->current_fh);
 	return nfs_ok;
 }
 
 static __be32
 nfsd4_setattr(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	      struct nfsd4_setattr *setattr)
+	      union nfsd4_op_u *u)
 {
+	struct nfsd4_setattr *setattr = &u->setattr;
 	__be32 status = nfs_ok;
 	int err;
 
@@ -956,8 +976,9 @@ static int fill_in_write_vector(struct kvec *vec, struct nfsd4_write *write)
 
 static __be32
 nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	    struct nfsd4_write *write)
+	    union nfsd4_op_u *u)
 {
+	struct nfsd4_write *write = &u->write;
 	stateid_t *stateid = &write->wr_stateid;
 	struct file *filp = NULL;
 	__be32 status = nfs_ok;
@@ -983,7 +1004,7 @@ nfsd4_write(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 	status = nfsd_vfs_write(rqstp, &cstate->current_fh, filp,
 				write->wr_offset, rqstp->rq_vec, nvecs, &cnt,
-				&write->wr_how_written);
+				write->wr_how_written);
 	fput(filp);
 
 	write->wr_bytes_written = cnt;
@@ -1030,8 +1051,9 @@ out_put_src:
 
 static __be32
 nfsd4_clone(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		struct nfsd4_clone *clone)
+		union nfsd4_op_u *u)
 {
+	struct nfsd4_clone *clone = &u->clone;
 	struct file *src, *dst;
 	__be32 status;
 
@@ -1051,8 +1073,9 @@ out:
 
 static __be32
 nfsd4_copy(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		struct nfsd4_copy *copy)
+		union nfsd4_op_u *u)
 {
+	struct nfsd4_copy *copy = &u->copy;
 	struct file *src, *dst;
 	__be32 status;
 	ssize_t bytes;
@@ -1107,23 +1130,24 @@ nfsd4_fallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
 
 static __be32
 nfsd4_allocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	       struct nfsd4_fallocate *fallocate)
+	       union nfsd4_op_u *u)
 {
-	return nfsd4_fallocate(rqstp, cstate, fallocate, 0);
+	return nfsd4_fallocate(rqstp, cstate, &u->allocate, 0);
 }
 
 static __be32
 nfsd4_deallocate(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		 struct nfsd4_fallocate *fallocate)
+		 union nfsd4_op_u *u)
 {
-	return nfsd4_fallocate(rqstp, cstate, fallocate,
+	return nfsd4_fallocate(rqstp, cstate, &u->deallocate,
 			       FALLOC_FL_PUNCH_HOLE | FALLOC_FL_KEEP_SIZE);
 }
 
 static __be32
 nfsd4_seek(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		struct nfsd4_seek *seek)
+	   union nfsd4_op_u *u)
 {
+	struct nfsd4_seek *seek = &u->seek;
 	int whence;
 	__be32 status;
 	struct file *file;
@@ -1228,21 +1252,21 @@ out_kfree:
 
 static __be32
 nfsd4_nverify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	      struct nfsd4_verify *verify)
+	      union nfsd4_op_u *u)
 {
 	__be32 status;
 
-	status = _nfsd4_verify(rqstp, cstate, verify);
+	status = _nfsd4_verify(rqstp, cstate, &u->verify);
 	return status == nfserr_not_same ? nfs_ok : status;
 }
 
 static __be32
 nfsd4_verify(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	     struct nfsd4_verify *verify)
+	     union nfsd4_op_u *u)
 {
 	__be32 status;
 
-	status = _nfsd4_verify(rqstp, cstate, verify);
+	status = _nfsd4_verify(rqstp, cstate, &u->nverify);
 	return status == nfserr_same ? nfs_ok : status;
 }
 
@@ -1255,7 +1279,8 @@ nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type)
 		return NULL;
 	}
 
-	if (!(exp->ex_layout_types & (1 << layout_type))) {
+	if (layout_type >= LAYOUT_TYPE_MAX ||
+	    !(exp->ex_layout_types & (1 << layout_type))) {
 		dprintk("%s: layout type %d not supported\n",
 			__func__, layout_type);
 		return NULL;
@@ -1266,9 +1291,9 @@ nfsd4_layout_verify(struct svc_export *exp, unsigned int layout_type)
 
 static __be32
 nfsd4_getdeviceinfo(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *cstate,
-		struct nfsd4_getdeviceinfo *gdp)
+		struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
 {
+	struct nfsd4_getdeviceinfo *gdp = &u->getdeviceinfo;
 	const struct nfsd4_layout_ops *ops;
 	struct nfsd4_deviceid_map *map;
 	struct svc_export *exp;
@@ -1312,9 +1337,9 @@ out:
 
 static __be32
 nfsd4_layoutget(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *cstate,
-		struct nfsd4_layoutget *lgp)
+		struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
 {
+	struct nfsd4_layoutget *lgp = &u->layoutget;
 	struct svc_fh *current_fh = &cstate->current_fh;
 	const struct nfsd4_layout_ops *ops;
 	struct nfs4_layout_stateid *ls;
@@ -1392,9 +1417,9 @@ out:
 
 static __be32
 nfsd4_layoutcommit(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *cstate,
-		struct nfsd4_layoutcommit *lcp)
+		struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
 {
+	struct nfsd4_layoutcommit *lcp = &u->layoutcommit;
 	const struct nfsd4_layout_seg *seg = &lcp->lc_seg;
 	struct svc_fh *current_fh = &cstate->current_fh;
 	const struct nfsd4_layout_ops *ops;
@@ -1456,9 +1481,9 @@ out:
 
 static __be32
 nfsd4_layoutreturn(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *cstate,
-		struct nfsd4_layoutreturn *lrp)
+		struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
 {
+	struct nfsd4_layoutreturn *lrp = &u->layoutreturn;
 	struct svc_fh *current_fh = &cstate->current_fh;
 	__be32 nfserr;
 
@@ -1505,7 +1530,7 @@ out:
  * NULL call.
  */
 static __be32
-nfsd4_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsd4_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -1516,12 +1541,6 @@ static inline void nfsd4_increment_op_stats(u32 opnum)
 		nfsdstats.nfs4_opcount[opnum]++;
 }
 
-typedef __be32(*nfsd4op_func)(struct svc_rqst *, struct nfsd4_compound_state *,
-			      void *);
-typedef u32(*nfsd4op_rsize)(struct svc_rqst *, struct nfsd4_op *op);
-typedef void(*stateid_setter)(struct nfsd4_compound_state *, void *);
-typedef void(*stateid_getter)(struct nfsd4_compound_state *, void *);
-
 enum nfsd4_op_flags {
 	ALLOWED_WITHOUT_FH = 1 << 0,	/* No current filehandle required */
 	ALLOWED_ON_ABSENT_FS = 1 << 1,	/* ops processed on absent fs */
@@ -1553,16 +1572,19 @@ enum nfsd4_op_flags {
 };
 
 struct nfsd4_operation {
-	nfsd4op_func op_func;
+	__be32 (*op_func)(struct svc_rqst *, struct nfsd4_compound_state *,
+			union nfsd4_op_u *);
 	u32 op_flags;
 	char *op_name;
 	/* Try to get response size before operation */
-	nfsd4op_rsize op_rsize_bop;
-	stateid_getter op_get_currentstateid;
-	stateid_setter op_set_currentstateid;
+	u32 (*op_rsize_bop)(struct svc_rqst *, struct nfsd4_op *);
+	void (*op_get_currentstateid)(struct nfsd4_compound_state *,
+			union nfsd4_op_u *);
+	void (*op_set_currentstateid)(struct nfsd4_compound_state *,
+			union nfsd4_op_u *);
 };
 
-static struct nfsd4_operation nfsd4_ops[];
+static const struct nfsd4_operation nfsd4_ops[];
 
 static const char *nfsd4_op_name(unsigned opnum);
 
@@ -1599,7 +1621,7 @@ static __be32 nfs41_check_op_ordering(struct nfsd4_compoundargs *args)
 	return nfs_ok;
 }
 
-static inline struct nfsd4_operation *OPDESC(struct nfsd4_op *op)
+static inline const struct nfsd4_operation *OPDESC(struct nfsd4_op *op)
 {
 	return &nfsd4_ops[op->opnum];
 }
@@ -1617,10 +1639,9 @@ static bool need_wrongsec_check(struct svc_rqst *rqstp)
 	struct nfsd4_compoundargs *argp = rqstp->rq_argp;
 	struct nfsd4_op *this = &argp->ops[resp->opcnt - 1];
 	struct nfsd4_op *next = &argp->ops[resp->opcnt];
-	struct nfsd4_operation *thisd;
-	struct nfsd4_operation *nextd;
+	const struct nfsd4_operation *thisd = OPDESC(this);
+	const struct nfsd4_operation *nextd;
 
-	thisd = OPDESC(this);
 	/*
 	 * Most ops check wronsec on our own; only the putfh-like ops
 	 * have special rules.
@@ -1668,12 +1689,12 @@ static void svcxdr_init_encode(struct svc_rqst *rqstp,
  * COMPOUND call.
  */
 static __be32
-nfsd4_proc_compound(struct svc_rqst *rqstp,
-		    struct nfsd4_compoundargs *args,
-		    struct nfsd4_compoundres *resp)
+nfsd4_proc_compound(struct svc_rqst *rqstp)
 {
+	struct nfsd4_compoundargs *args = rqstp->rq_argp;
+	struct nfsd4_compoundres *resp = rqstp->rq_resp;
 	struct nfsd4_op	*op;
-	struct nfsd4_operation *opdesc;
+	const struct nfsd4_operation *opdesc;
 	struct nfsd4_compound_state *cstate = &resp->cstate;
 	struct svc_fh *current_fh = &cstate->current_fh;
 	struct svc_fh *save_fh = &cstate->save_fh;
@@ -1764,6 +1785,12 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			opdesc->op_get_currentstateid(cstate, &op->u);
 		op->status = opdesc->op_func(rqstp, cstate, &op->u);
 
+		/* Only from SEQUENCE */
+		if (cstate->status == nfserr_replay_cache) {
+			dprintk("%s NFS4.1 replay from cache\n", __func__);
+			status = op->status;
+			goto out;
+		}
 		if (!op->status) {
 			if (opdesc->op_set_currentstateid)
 				opdesc->op_set_currentstateid(cstate, &op->u);
@@ -1774,14 +1801,7 @@ nfsd4_proc_compound(struct svc_rqst *rqstp,
 			if (need_wrongsec_check(rqstp))
 				op->status = check_nfsd_access(current_fh->fh_export, rqstp);
 		}
-
 encode_op:
-		/* Only from SEQUENCE */
-		if (cstate->status == nfserr_replay_cache) {
-			dprintk("%s NFS4.1 replay from cache\n", __func__);
-			status = op->status;
-			goto out;
-		}
 		if (op->status == nfserr_replay_me) {
 			op->replay = &cstate->replay_owner->so_replay;
 			nfsd4_encode_replay(&resp->xdr, op);
@@ -1838,6 +1858,12 @@ static inline u32 nfsd4_status_stateid_rsize(struct svc_rqst *rqstp, struct nfsd
 	return (op_encode_hdr_size + op_encode_stateid_maxsz)* sizeof(__be32);
 }
 
+static inline u32 nfsd4_access_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	/* ac_supported, ac_resp_access */
+	return (op_encode_hdr_size + 2)* sizeof(__be32);
+}
+
 static inline u32 nfsd4_commit_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_verifier_maxsz) * sizeof(__be32);
@@ -1892,6 +1918,11 @@ static inline u32 nfsd4_getattr_rsize(struct svc_rqst *rqstp,
 	return ret;
 }
 
+static inline u32 nfsd4_getfh_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size + 1) * sizeof(__be32) + NFS4_FHSIZE;
+}
+
 static inline u32 nfsd4_link_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_change_info_maxsz)
@@ -1933,6 +1964,11 @@ static inline u32 nfsd4_readdir_rsize(struct svc_rqst *rqstp, struct nfsd4_op *o
 		XDR_QUADLEN(rlen)) * sizeof(__be32);
 }
 
+static inline u32 nfsd4_readlink_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size + 1) * sizeof(__be32) + PAGE_SIZE;
+}
+
 static inline u32 nfsd4_remove_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + op_encode_change_info_maxsz)
@@ -1952,11 +1988,23 @@ static inline u32 nfsd4_sequence_rsize(struct svc_rqst *rqstp,
 		+ XDR_QUADLEN(NFS4_MAX_SESSIONID_LEN) + 5) * sizeof(__be32);
 }
 
+static inline u32 nfsd4_test_stateid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size + 1 + op->u.test_stateid.ts_num_ids)
+		* sizeof(__be32);
+}
+
 static inline u32 nfsd4_setattr_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + nfs4_fattr_bitmap_maxsz) * sizeof(__be32);
 }
 
+static inline u32 nfsd4_secinfo_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size + RPC_AUTH_MAXFLAVOR *
+		(4 + XDR_QUADLEN(GSS_OID_MAX_LEN))) * sizeof(__be32);
+}
+
 static inline u32 nfsd4_setclientid_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
 	return (op_encode_hdr_size + 2 + XDR_QUADLEN(NFS4_VERIFIER_SIZE)) *
@@ -2011,6 +2059,19 @@ static inline u32 nfsd4_copy_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
 }
 
 #ifdef CONFIG_NFSD_PNFS
+static inline u32 nfsd4_getdeviceinfo_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	u32 maxcount = 0, rlen = 0;
+
+	maxcount = svc_max_payload(rqstp);
+	rlen = min(op->u.getdeviceinfo.gd_maxcount, maxcount);
+
+	return (op_encode_hdr_size +
+		1 /* gd_layout_type*/ +
+		XDR_QUADLEN(rlen) +
+		2 /* gd_notify_types */) * sizeof(__be32);
+}
+
 /*
  * At this stage we don't really know what layout driver will handle the request,
  * so we need to define an arbitrary upper bound here.
@@ -2040,347 +2101,366 @@ static inline u32 nfsd4_layoutreturn_rsize(struct svc_rqst *rqstp, struct nfsd4_
 }
 #endif /* CONFIG_NFSD_PNFS */
 
-static struct nfsd4_operation nfsd4_ops[] = {
+
+static inline u32 nfsd4_seek_rsize(struct svc_rqst *rqstp, struct nfsd4_op *op)
+{
+	return (op_encode_hdr_size + 3) * sizeof(__be32);
+}
+
+static const struct nfsd4_operation nfsd4_ops[] = {
 	[OP_ACCESS] = {
-		.op_func = (nfsd4op_func)nfsd4_access,
+		.op_func = nfsd4_access,
 		.op_name = "OP_ACCESS",
+		.op_rsize_bop = nfsd4_access_rsize,
 	},
 	[OP_CLOSE] = {
-		.op_func = (nfsd4op_func)nfsd4_close,
+		.op_func = nfsd4_close,
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_CLOSE",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
-		.op_get_currentstateid = (stateid_getter)nfsd4_get_closestateid,
-		.op_set_currentstateid = (stateid_setter)nfsd4_set_closestateid,
+		.op_rsize_bop = nfsd4_status_stateid_rsize,
+		.op_get_currentstateid = nfsd4_get_closestateid,
+		.op_set_currentstateid = nfsd4_set_closestateid,
 	},
 	[OP_COMMIT] = {
-		.op_func = (nfsd4op_func)nfsd4_commit,
+		.op_func = nfsd4_commit,
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_COMMIT",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_commit_rsize,
+		.op_rsize_bop = nfsd4_commit_rsize,
 	},
 	[OP_CREATE] = {
-		.op_func = (nfsd4op_func)nfsd4_create,
+		.op_func = nfsd4_create,
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME | OP_CLEAR_STATEID,
 		.op_name = "OP_CREATE",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_create_rsize,
+		.op_rsize_bop = nfsd4_create_rsize,
 	},
 	[OP_DELEGRETURN] = {
-		.op_func = (nfsd4op_func)nfsd4_delegreturn,
+		.op_func = nfsd4_delegreturn,
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_DELEGRETURN",
 		.op_rsize_bop = nfsd4_only_status_rsize,
-		.op_get_currentstateid = (stateid_getter)nfsd4_get_delegreturnstateid,
+		.op_get_currentstateid = nfsd4_get_delegreturnstateid,
 	},
 	[OP_GETATTR] = {
-		.op_func = (nfsd4op_func)nfsd4_getattr,
+		.op_func = nfsd4_getattr,
 		.op_flags = ALLOWED_ON_ABSENT_FS,
 		.op_rsize_bop = nfsd4_getattr_rsize,
 		.op_name = "OP_GETATTR",
 	},
 	[OP_GETFH] = {
-		.op_func = (nfsd4op_func)nfsd4_getfh,
+		.op_func = nfsd4_getfh,
 		.op_name = "OP_GETFH",
+		.op_rsize_bop = nfsd4_getfh_rsize,
 	},
 	[OP_LINK] = {
-		.op_func = (nfsd4op_func)nfsd4_link,
+		.op_func = nfsd4_link,
 		.op_flags = ALLOWED_ON_ABSENT_FS | OP_MODIFIES_SOMETHING
 				| OP_CACHEME,
 		.op_name = "OP_LINK",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_link_rsize,
+		.op_rsize_bop = nfsd4_link_rsize,
 	},
 	[OP_LOCK] = {
-		.op_func = (nfsd4op_func)nfsd4_lock,
+		.op_func = nfsd4_lock,
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_LOCK",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_lock_rsize,
-		.op_set_currentstateid = (stateid_setter)nfsd4_set_lockstateid,
+		.op_rsize_bop = nfsd4_lock_rsize,
+		.op_set_currentstateid = nfsd4_set_lockstateid,
 	},
 	[OP_LOCKT] = {
-		.op_func = (nfsd4op_func)nfsd4_lockt,
+		.op_func = nfsd4_lockt,
 		.op_name = "OP_LOCKT",
+		.op_rsize_bop = nfsd4_lock_rsize,
 	},
 	[OP_LOCKU] = {
-		.op_func = (nfsd4op_func)nfsd4_locku,
+		.op_func = nfsd4_locku,
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_LOCKU",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
-		.op_get_currentstateid = (stateid_getter)nfsd4_get_lockustateid,
+		.op_rsize_bop = nfsd4_status_stateid_rsize,
+		.op_get_currentstateid = nfsd4_get_lockustateid,
 	},
 	[OP_LOOKUP] = {
-		.op_func = (nfsd4op_func)nfsd4_lookup,
+		.op_func = nfsd4_lookup,
 		.op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID,
 		.op_name = "OP_LOOKUP",
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_LOOKUPP] = {
-		.op_func = (nfsd4op_func)nfsd4_lookupp,
+		.op_func = nfsd4_lookupp,
 		.op_flags = OP_HANDLES_WRONGSEC | OP_CLEAR_STATEID,
 		.op_name = "OP_LOOKUPP",
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_NVERIFY] = {
-		.op_func = (nfsd4op_func)nfsd4_nverify,
+		.op_func = nfsd4_nverify,
 		.op_name = "OP_NVERIFY",
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_OPEN] = {
-		.op_func = (nfsd4op_func)nfsd4_open,
+		.op_func = nfsd4_open,
 		.op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING,
 		.op_name = "OP_OPEN",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_open_rsize,
-		.op_set_currentstateid = (stateid_setter)nfsd4_set_openstateid,
+		.op_rsize_bop = nfsd4_open_rsize,
+		.op_set_currentstateid = nfsd4_set_openstateid,
 	},
 	[OP_OPEN_CONFIRM] = {
-		.op_func = (nfsd4op_func)nfsd4_open_confirm,
+		.op_func = nfsd4_open_confirm,
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_OPEN_CONFIRM",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
+		.op_rsize_bop = nfsd4_status_stateid_rsize,
 	},
 	[OP_OPEN_DOWNGRADE] = {
-		.op_func = (nfsd4op_func)nfsd4_open_downgrade,
+		.op_func = nfsd4_open_downgrade,
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_OPEN_DOWNGRADE",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_status_stateid_rsize,
-		.op_get_currentstateid = (stateid_getter)nfsd4_get_opendowngradestateid,
-		.op_set_currentstateid = (stateid_setter)nfsd4_set_opendowngradestateid,
+		.op_rsize_bop = nfsd4_status_stateid_rsize,
+		.op_get_currentstateid = nfsd4_get_opendowngradestateid,
+		.op_set_currentstateid = nfsd4_set_opendowngradestateid,
 	},
 	[OP_PUTFH] = {
-		.op_func = (nfsd4op_func)nfsd4_putfh,
+		.op_func = nfsd4_putfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
 				| OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID,
 		.op_name = "OP_PUTFH",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_PUTPUBFH] = {
-		.op_func = (nfsd4op_func)nfsd4_putrootfh,
+		.op_func = nfsd4_putrootfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
 				| OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID,
 		.op_name = "OP_PUTPUBFH",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_PUTROOTFH] = {
-		.op_func = (nfsd4op_func)nfsd4_putrootfh,
+		.op_func = nfsd4_putrootfh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
 				| OP_IS_PUTFH_LIKE | OP_CLEAR_STATEID,
 		.op_name = "OP_PUTROOTFH",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_READ] = {
-		.op_func = (nfsd4op_func)nfsd4_read,
+		.op_func = nfsd4_read,
 		.op_name = "OP_READ",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_read_rsize,
-		.op_get_currentstateid = (stateid_getter)nfsd4_get_readstateid,
+		.op_rsize_bop = nfsd4_read_rsize,
+		.op_get_currentstateid = nfsd4_get_readstateid,
 	},
 	[OP_READDIR] = {
-		.op_func = (nfsd4op_func)nfsd4_readdir,
+		.op_func = nfsd4_readdir,
 		.op_name = "OP_READDIR",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_readdir_rsize,
+		.op_rsize_bop = nfsd4_readdir_rsize,
 	},
 	[OP_READLINK] = {
-		.op_func = (nfsd4op_func)nfsd4_readlink,
+		.op_func = nfsd4_readlink,
 		.op_name = "OP_READLINK",
+		.op_rsize_bop = nfsd4_readlink_rsize,
 	},
 	[OP_REMOVE] = {
-		.op_func = (nfsd4op_func)nfsd4_remove,
+		.op_func = nfsd4_remove,
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_name = "OP_REMOVE",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_remove_rsize,
+		.op_rsize_bop = nfsd4_remove_rsize,
 	},
 	[OP_RENAME] = {
-		.op_func = (nfsd4op_func)nfsd4_rename,
+		.op_func = nfsd4_rename,
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_name = "OP_RENAME",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_rename_rsize,
+		.op_rsize_bop = nfsd4_rename_rsize,
 	},
 	[OP_RENEW] = {
-		.op_func = (nfsd4op_func)nfsd4_renew,
+		.op_func = nfsd4_renew,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
 				| OP_MODIFIES_SOMETHING,
 		.op_name = "OP_RENEW",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 
 	},
 	[OP_RESTOREFH] = {
-		.op_func = (nfsd4op_func)nfsd4_restorefh,
+		.op_func = nfsd4_restorefh,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
 				| OP_IS_PUTFH_LIKE | OP_MODIFIES_SOMETHING,
 		.op_name = "OP_RESTOREFH",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_SAVEFH] = {
-		.op_func = (nfsd4op_func)nfsd4_savefh,
+		.op_func = nfsd4_savefh,
 		.op_flags = OP_HANDLES_WRONGSEC | OP_MODIFIES_SOMETHING,
 		.op_name = "OP_SAVEFH",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_SECINFO] = {
-		.op_func = (nfsd4op_func)nfsd4_secinfo,
+		.op_func = nfsd4_secinfo,
 		.op_flags = OP_HANDLES_WRONGSEC,
 		.op_name = "OP_SECINFO",
+		.op_rsize_bop = nfsd4_secinfo_rsize,
 	},
 	[OP_SETATTR] = {
-		.op_func = (nfsd4op_func)nfsd4_setattr,
+		.op_func = nfsd4_setattr,
 		.op_name = "OP_SETATTR",
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_setattr_rsize,
-		.op_get_currentstateid = (stateid_getter)nfsd4_get_setattrstateid,
+		.op_rsize_bop = nfsd4_setattr_rsize,
+		.op_get_currentstateid = nfsd4_get_setattrstateid,
 	},
 	[OP_SETCLIENTID] = {
-		.op_func = (nfsd4op_func)nfsd4_setclientid,
+		.op_func = nfsd4_setclientid,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
 				| OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_name = "OP_SETCLIENTID",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_setclientid_rsize,
+		.op_rsize_bop = nfsd4_setclientid_rsize,
 	},
 	[OP_SETCLIENTID_CONFIRM] = {
-		.op_func = (nfsd4op_func)nfsd4_setclientid_confirm,
+		.op_func = nfsd4_setclientid_confirm,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
 				| OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_name = "OP_SETCLIENTID_CONFIRM",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_VERIFY] = {
-		.op_func = (nfsd4op_func)nfsd4_verify,
+		.op_func = nfsd4_verify,
 		.op_name = "OP_VERIFY",
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_WRITE] = {
-		.op_func = (nfsd4op_func)nfsd4_write,
+		.op_func = nfsd4_write,
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_name = "OP_WRITE",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_write_rsize,
-		.op_get_currentstateid = (stateid_getter)nfsd4_get_writestateid,
+		.op_rsize_bop = nfsd4_write_rsize,
+		.op_get_currentstateid = nfsd4_get_writestateid,
 	},
 	[OP_RELEASE_LOCKOWNER] = {
-		.op_func = (nfsd4op_func)nfsd4_release_lockowner,
+		.op_func = nfsd4_release_lockowner,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_ON_ABSENT_FS
 				| OP_MODIFIES_SOMETHING,
 		.op_name = "OP_RELEASE_LOCKOWNER",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 
 	/* NFSv4.1 operations */
 	[OP_EXCHANGE_ID] = {
-		.op_func = (nfsd4op_func)nfsd4_exchange_id,
+		.op_func = nfsd4_exchange_id,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
 				| OP_MODIFIES_SOMETHING,
 		.op_name = "OP_EXCHANGE_ID",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_exchange_id_rsize,
+		.op_rsize_bop = nfsd4_exchange_id_rsize,
 	},
 	[OP_BACKCHANNEL_CTL] = {
-		.op_func = (nfsd4op_func)nfsd4_backchannel_ctl,
+		.op_func = nfsd4_backchannel_ctl,
 		.op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING,
 		.op_name = "OP_BACKCHANNEL_CTL",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_BIND_CONN_TO_SESSION] = {
-		.op_func = (nfsd4op_func)nfsd4_bind_conn_to_session,
+		.op_func = nfsd4_bind_conn_to_session,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
 				| OP_MODIFIES_SOMETHING,
 		.op_name = "OP_BIND_CONN_TO_SESSION",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_bind_conn_to_session_rsize,
+		.op_rsize_bop = nfsd4_bind_conn_to_session_rsize,
 	},
 	[OP_CREATE_SESSION] = {
-		.op_func = (nfsd4op_func)nfsd4_create_session,
+		.op_func = nfsd4_create_session,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
 				| OP_MODIFIES_SOMETHING,
 		.op_name = "OP_CREATE_SESSION",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_create_session_rsize,
+		.op_rsize_bop = nfsd4_create_session_rsize,
 	},
 	[OP_DESTROY_SESSION] = {
-		.op_func = (nfsd4op_func)nfsd4_destroy_session,
+		.op_func = nfsd4_destroy_session,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
 				| OP_MODIFIES_SOMETHING,
 		.op_name = "OP_DESTROY_SESSION",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_SEQUENCE] = {
-		.op_func = (nfsd4op_func)nfsd4_sequence,
+		.op_func = nfsd4_sequence,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP,
 		.op_name = "OP_SEQUENCE",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_sequence_rsize,
+		.op_rsize_bop = nfsd4_sequence_rsize,
 	},
 	[OP_DESTROY_CLIENTID] = {
-		.op_func = (nfsd4op_func)nfsd4_destroy_clientid,
+		.op_func = nfsd4_destroy_clientid,
 		.op_flags = ALLOWED_WITHOUT_FH | ALLOWED_AS_FIRST_OP
 				| OP_MODIFIES_SOMETHING,
 		.op_name = "OP_DESTROY_CLIENTID",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_RECLAIM_COMPLETE] = {
-		.op_func = (nfsd4op_func)nfsd4_reclaim_complete,
+		.op_func = nfsd4_reclaim_complete,
 		.op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING,
 		.op_name = "OP_RECLAIM_COMPLETE",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_SECINFO_NO_NAME] = {
-		.op_func = (nfsd4op_func)nfsd4_secinfo_no_name,
+		.op_func = nfsd4_secinfo_no_name,
 		.op_flags = OP_HANDLES_WRONGSEC,
 		.op_name = "OP_SECINFO_NO_NAME",
+		.op_rsize_bop = nfsd4_secinfo_rsize,
 	},
 	[OP_TEST_STATEID] = {
-		.op_func = (nfsd4op_func)nfsd4_test_stateid,
+		.op_func = nfsd4_test_stateid,
 		.op_flags = ALLOWED_WITHOUT_FH,
 		.op_name = "OP_TEST_STATEID",
+		.op_rsize_bop = nfsd4_test_stateid_rsize,
 	},
 	[OP_FREE_STATEID] = {
-		.op_func = (nfsd4op_func)nfsd4_free_stateid,
+		.op_func = nfsd4_free_stateid,
 		.op_flags = ALLOWED_WITHOUT_FH | OP_MODIFIES_SOMETHING,
 		.op_name = "OP_FREE_STATEID",
-		.op_get_currentstateid = (stateid_getter)nfsd4_get_freestateid,
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_get_currentstateid = nfsd4_get_freestateid,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 #ifdef CONFIG_NFSD_PNFS
 	[OP_GETDEVICEINFO] = {
-		.op_func = (nfsd4op_func)nfsd4_getdeviceinfo,
+		.op_func = nfsd4_getdeviceinfo,
 		.op_flags = ALLOWED_WITHOUT_FH,
 		.op_name = "OP_GETDEVICEINFO",
+		.op_rsize_bop = nfsd4_getdeviceinfo_rsize,
 	},
 	[OP_LAYOUTGET] = {
-		.op_func = (nfsd4op_func)nfsd4_layoutget,
+		.op_func = nfsd4_layoutget,
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_LAYOUTGET",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutget_rsize,
+		.op_rsize_bop = nfsd4_layoutget_rsize,
 	},
 	[OP_LAYOUTCOMMIT] = {
-		.op_func = (nfsd4op_func)nfsd4_layoutcommit,
+		.op_func = nfsd4_layoutcommit,
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_LAYOUTCOMMIT",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutcommit_rsize,
+		.op_rsize_bop = nfsd4_layoutcommit_rsize,
 	},
 	[OP_LAYOUTRETURN] = {
-		.op_func = (nfsd4op_func)nfsd4_layoutreturn,
+		.op_func = nfsd4_layoutreturn,
 		.op_flags = OP_MODIFIES_SOMETHING,
 		.op_name = "OP_LAYOUTRETURN",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_layoutreturn_rsize,
+		.op_rsize_bop = nfsd4_layoutreturn_rsize,
 	},
 #endif /* CONFIG_NFSD_PNFS */
 
 	/* NFSv4.2 operations */
 	[OP_ALLOCATE] = {
-		.op_func = (nfsd4op_func)nfsd4_allocate,
+		.op_func = nfsd4_allocate,
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_name = "OP_ALLOCATE",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_DEALLOCATE] = {
-		.op_func = (nfsd4op_func)nfsd4_deallocate,
+		.op_func = nfsd4_deallocate,
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_name = "OP_DEALLOCATE",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_CLONE] = {
-		.op_func = (nfsd4op_func)nfsd4_clone,
+		.op_func = nfsd4_clone,
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_name = "OP_CLONE",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_only_status_rsize,
+		.op_rsize_bop = nfsd4_only_status_rsize,
 	},
 	[OP_COPY] = {
-		.op_func = (nfsd4op_func)nfsd4_copy,
+		.op_func = nfsd4_copy,
 		.op_flags = OP_MODIFIES_SOMETHING | OP_CACHEME,
 		.op_name = "OP_COPY",
-		.op_rsize_bop = (nfsd4op_rsize)nfsd4_copy_rsize,
+		.op_rsize_bop = nfsd4_copy_rsize,
 	},
 	[OP_SEEK] = {
-		.op_func = (nfsd4op_func)nfsd4_seek,
+		.op_func = nfsd4_seek,
 		.op_name = "OP_SEEK",
+		.op_rsize_bop = nfsd4_seek_rsize,
 	},
 };
 
@@ -2425,14 +2505,11 @@ bool nfsd4_spo_must_allow(struct svc_rqst *rqstp)
 
 int nfsd4_max_reply(struct svc_rqst *rqstp, struct nfsd4_op *op)
 {
-	struct nfsd4_operation *opdesc;
-	nfsd4op_rsize estimator;
-
-	if (op->opnum == OP_ILLEGAL)
+	if (op->opnum == OP_ILLEGAL || op->status == nfserr_notsupp)
 		return op_encode_hdr_size * sizeof(__be32);
-	opdesc = OPDESC(op);
-	estimator = opdesc->op_rsize_bop;
-	return estimator ? estimator(rqstp, op) : PAGE_SIZE;
+
+	BUG_ON(OPDESC(op)->op_rsize_bop == NULL);
+	return OPDESC(op)->op_rsize_bop(rqstp, op);
 }
 
 void warn_on_nonidempotent_op(struct nfsd4_op *op)
@@ -2454,19 +2531,19 @@ static const char *nfsd4_op_name(unsigned opnum)
 #define nfsd4_voidres			nfsd4_voidargs
 struct nfsd4_voidargs { int dummy; };
 
-static struct svc_procedure		nfsd_procedures4[2] = {
+static const struct svc_procedure nfsd_procedures4[2] = {
 	[NFSPROC4_NULL] = {
-		.pc_func = (svc_procfunc) nfsd4_proc_null,
-		.pc_encode = (kxdrproc_t) nfs4svc_encode_voidres,
+		.pc_func = nfsd4_proc_null,
+		.pc_encode = nfs4svc_encode_voidres,
 		.pc_argsize = sizeof(struct nfsd4_voidargs),
 		.pc_ressize = sizeof(struct nfsd4_voidres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = 1,
 	},
 	[NFSPROC4_COMPOUND] = {
-		.pc_func = (svc_procfunc) nfsd4_proc_compound,
-		.pc_decode = (kxdrproc_t) nfs4svc_decode_compoundargs,
-		.pc_encode = (kxdrproc_t) nfs4svc_encode_compoundres,
+		.pc_func = nfsd4_proc_compound,
+		.pc_decode = nfs4svc_decode_compoundargs,
+		.pc_encode = nfs4svc_encode_compoundres,
 		.pc_argsize = sizeof(struct nfsd4_compoundargs),
 		.pc_ressize = sizeof(struct nfsd4_compoundres),
 		.pc_release = nfsd4_release_compoundargs,
@@ -2475,13 +2552,16 @@ static struct svc_procedure		nfsd_procedures4[2] = {
 	},
 };
 
-struct svc_version	nfsd_version4 = {
-		.vs_vers	= 4,
-		.vs_nproc	= 2,
-		.vs_proc	= nfsd_procedures4,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS4_SVC_XDRSIZE,
-		.vs_rpcb_optnl	= 1,
+static unsigned int nfsd_count3[ARRAY_SIZE(nfsd_procedures4)];
+const struct svc_version nfsd_version4 = {
+	.vs_vers		= 4,
+	.vs_nproc		= 2,
+	.vs_proc		= nfsd_procedures4,
+	.vs_count		= nfsd_count3,
+	.vs_dispatch		= nfsd_dispatch,
+	.vs_xdrsize		= NFS4_SVC_XDRSIZE,
+	.vs_rpcb_optnl		= true,
+	.vs_need_cong_ctrl	= true,
 };
 
 /*
diff --git a/fs/nfsd/nfs4state.c b/fs/nfsd/nfs4state.c
index a0dee8ae9f97..0c04f81aa63b 100644
--- a/fs/nfsd/nfs4state.c
+++ b/fs/nfsd/nfs4state.c
@@ -1912,28 +1912,15 @@ static void copy_clid(struct nfs4_client *target, struct nfs4_client *source)
 	target->cl_clientid.cl_id = source->cl_clientid.cl_id; 
 }
 
-int strdup_if_nonnull(char **target, char *source)
-{
-	if (source) {
-		*target = kstrdup(source, GFP_KERNEL);
-		if (!*target)
-			return -ENOMEM;
-	} else
-		*target = NULL;
-	return 0;
-}
-
 static int copy_cred(struct svc_cred *target, struct svc_cred *source)
 {
-	int ret;
+	target->cr_principal = kstrdup(source->cr_principal, GFP_KERNEL);
+	target->cr_raw_principal = kstrdup(source->cr_raw_principal,
+								GFP_KERNEL);
+	if ((source->cr_principal && ! target->cr_principal) ||
+	    (source->cr_raw_principal && ! target->cr_raw_principal))
+		return -ENOMEM;
 
-	ret = strdup_if_nonnull(&target->cr_principal, source->cr_principal);
-	if (ret)
-		return ret;
-	ret = strdup_if_nonnull(&target->cr_raw_principal,
-					source->cr_raw_principal);
-	if (ret)
-		return ret;
 	target->cr_flavor = source->cr_flavor;
 	target->cr_uid = source->cr_uid;
 	target->cr_gid = source->cr_gid;
@@ -2281,7 +2268,7 @@ gen_callback(struct nfs4_client *clp, struct nfsd4_setclientid *se, struct svc_r
 out_err:
 	conn->cb_addr.ss_family = AF_UNSPEC;
 	conn->cb_addrlen = 0;
-	dprintk(KERN_INFO "NFSD: this client (clientid %08x/%08x) "
+	dprintk("NFSD: this client (clientid %08x/%08x) "
 		"will not receive delegations\n",
 		clp->cl_clientid.cl_boot, clp->cl_clientid.cl_id);
 
@@ -2415,10 +2402,10 @@ static bool client_has_state(struct nfs4_client *clp)
 }
 
 __be32
-nfsd4_exchange_id(struct svc_rqst *rqstp,
-		  struct nfsd4_compound_state *cstate,
-		  struct nfsd4_exchange_id *exid)
+nfsd4_exchange_id(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
+	struct nfsd4_exchange_id *exid = &u->exchange_id;
 	struct nfs4_client *conf, *new;
 	struct nfs4_client *unconf = NULL;
 	__be32 status;
@@ -2711,9 +2698,9 @@ static __be32 nfsd4_check_cb_sec(struct nfsd4_cb_sec *cbs)
 
 __be32
 nfsd4_create_session(struct svc_rqst *rqstp,
-		     struct nfsd4_compound_state *cstate,
-		     struct nfsd4_create_session *cr_ses)
+		struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
 {
+	struct nfsd4_create_session *cr_ses = &u->create_session;
 	struct sockaddr *sa = svc_addr(rqstp);
 	struct nfs4_client *conf, *unconf;
 	struct nfs4_client *old = NULL;
@@ -2837,8 +2824,11 @@ static __be32 nfsd4_map_bcts_dir(u32 *dir)
 	return nfserr_inval;
 }
 
-__be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_backchannel_ctl *bc)
+__be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
+	struct nfsd4_backchannel_ctl *bc = &u->backchannel_ctl;
 	struct nfsd4_session *session = cstate->session;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
 	__be32 status;
@@ -2858,8 +2848,9 @@ __be32 nfsd4_backchannel_ctl(struct svc_rqst *rqstp, struct nfsd4_compound_state
 
 __be32 nfsd4_bind_conn_to_session(struct svc_rqst *rqstp,
 		     struct nfsd4_compound_state *cstate,
-		     struct nfsd4_bind_conn_to_session *bcts)
+		     union nfsd4_op_u *u)
 {
+	struct nfsd4_bind_conn_to_session *bcts = &u->bind_conn_to_session;
 	__be32 status;
 	struct nfsd4_conn *conn;
 	struct nfsd4_session *session;
@@ -2899,10 +2890,10 @@ static bool nfsd4_compound_in_session(struct nfsd4_session *session, struct nfs4
 }
 
 __be32
-nfsd4_destroy_session(struct svc_rqst *r,
-		      struct nfsd4_compound_state *cstate,
-		      struct nfsd4_destroy_session *sessionid)
+nfsd4_destroy_session(struct svc_rqst *r, struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
+	struct nfsd4_destroy_session *sessionid = &u->destroy_session;
 	struct nfsd4_session *ses;
 	__be32 status;
 	int ref_held_by_me = 0;
@@ -2996,10 +2987,10 @@ static bool nfsd4_request_too_big(struct svc_rqst *rqstp,
 }
 
 __be32
-nfsd4_sequence(struct svc_rqst *rqstp,
-	       struct nfsd4_compound_state *cstate,
-	       struct nfsd4_sequence *seq)
+nfsd4_sequence(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
+	struct nfsd4_sequence *seq = &u->sequence;
 	struct nfsd4_compoundres *resp = rqstp->rq_resp;
 	struct xdr_stream *xdr = &resp->xdr;
 	struct nfsd4_session *session;
@@ -3133,8 +3124,11 @@ nfsd4_sequence_done(struct nfsd4_compoundres *resp)
 }
 
 __be32
-nfsd4_destroy_clientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_destroy_clientid *dc)
+nfsd4_destroy_clientid(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
+	struct nfsd4_destroy_clientid *dc = &u->destroy_clientid;
 	struct nfs4_client *conf, *unconf;
 	struct nfs4_client *clp = NULL;
 	__be32 status = 0;
@@ -3174,8 +3168,10 @@ out:
 }
 
 __be32
-nfsd4_reclaim_complete(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate, struct nfsd4_reclaim_complete *rc)
+nfsd4_reclaim_complete(struct svc_rqst *rqstp,
+		struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
 {
+	struct nfsd4_reclaim_complete *rc = &u->reclaim_complete;
 	__be32 status = 0;
 
 	if (rc->rca_one_fs) {
@@ -3212,8 +3208,9 @@ out:
 
 __be32
 nfsd4_setclientid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		  struct nfsd4_setclientid *setclid)
+		  union nfsd4_op_u *u)
 {
+	struct nfsd4_setclientid *setclid = &u->setclientid;
 	struct xdr_netobj 	clname = setclid->se_name;
 	nfs4_verifier		clverifier = setclid->se_verf;
 	struct nfs4_client	*conf, *new;
@@ -3270,9 +3267,11 @@ out:
 
 __be32
 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
-			 struct nfsd4_compound_state *cstate,
-			 struct nfsd4_setclientid_confirm *setclientid_confirm)
+			struct nfsd4_compound_state *cstate,
+			union nfsd4_op_u *u)
 {
+	struct nfsd4_setclientid_confirm *setclientid_confirm =
+			&u->setclientid_confirm;
 	struct nfs4_client *conf, *unconf;
 	struct nfs4_client *old = NULL;
 	nfs4_verifier confirm = setclientid_confirm->sc_confirm; 
@@ -4519,8 +4518,9 @@ void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate,
 
 __be32
 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	    clientid_t *clid)
+	    union nfsd4_op_u *u)
 {
+	clientid_t *clid = &u->renew;
 	struct nfs4_client *clp;
 	__be32 status;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
@@ -5006,8 +5006,9 @@ out:
  */
 __be32
 nfsd4_test_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		   struct nfsd4_test_stateid *test_stateid)
+		   union nfsd4_op_u *u)
 {
+	struct nfsd4_test_stateid *test_stateid = &u->test_stateid;
 	struct nfsd4_test_stateid_id *stateid;
 	struct nfs4_client *cl = cstate->session->se_client;
 
@@ -5046,8 +5047,9 @@ out:
 
 __be32
 nfsd4_free_stateid(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		   struct nfsd4_free_stateid *free_stateid)
+		   union nfsd4_op_u *u)
 {
+	struct nfsd4_free_stateid *free_stateid = &u->free_stateid;
 	stateid_t *stateid = &free_stateid->fr_stateid;
 	struct nfs4_stid *s;
 	struct nfs4_delegation *dp;
@@ -5175,8 +5177,9 @@ static __be32 nfs4_preprocess_confirmed_seqid_op(struct nfsd4_compound_state *cs
 
 __be32
 nfsd4_open_confirm(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		   struct nfsd4_open_confirm *oc)
+		   union nfsd4_op_u *u)
 {
+	struct nfsd4_open_confirm *oc = &u->open_confirm;
 	__be32 status;
 	struct nfs4_openowner *oo;
 	struct nfs4_ol_stateid *stp;
@@ -5243,9 +5246,9 @@ static inline void nfs4_stateid_downgrade(struct nfs4_ol_stateid *stp, u32 to_ac
 
 __be32
 nfsd4_open_downgrade(struct svc_rqst *rqstp,
-		     struct nfsd4_compound_state *cstate,
-		     struct nfsd4_open_downgrade *od)
+		     struct nfsd4_compound_state *cstate, union nfsd4_op_u *u)
 {
+	struct nfsd4_open_downgrade *od = &u->open_downgrade;
 	__be32 status;
 	struct nfs4_ol_stateid *stp;
 	struct nfsd_net *nn = net_generic(SVC_NET(rqstp), nfsd_net_id);
@@ -5313,8 +5316,9 @@ static void nfsd4_close_open_stateid(struct nfs4_ol_stateid *s)
  */
 __be32
 nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	    struct nfsd4_close *close)
+		union nfsd4_op_u *u)
 {
+	struct nfsd4_close *close = &u->close;
 	__be32 status;
 	struct nfs4_ol_stateid *stp;
 	struct net *net = SVC_NET(rqstp);
@@ -5343,8 +5347,9 @@ out:
 
 __be32
 nfsd4_delegreturn(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-		  struct nfsd4_delegreturn *dr)
+		  union nfsd4_op_u *u)
 {
+	struct nfsd4_delegreturn *dr = &u->delegreturn;
 	struct nfs4_delegation *dp;
 	stateid_t *stateid = &dr->dr_stateid;
 	struct nfs4_stid *s;
@@ -5719,8 +5724,9 @@ out:
  */
 __be32
 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	   struct nfsd4_lock *lock)
+	   union nfsd4_op_u *u)
 {
+	struct nfsd4_lock *lock = &u->lock;
 	struct nfs4_openowner *open_sop = NULL;
 	struct nfs4_lockowner *lock_sop = NULL;
 	struct nfs4_ol_stateid *lock_stp = NULL;
@@ -5952,8 +5958,9 @@ static __be32 nfsd_test_lock(struct svc_rqst *rqstp, struct svc_fh *fhp, struct
  */
 __be32
 nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	    struct nfsd4_lockt *lockt)
+	    union nfsd4_op_u *u)
 {
+	struct nfsd4_lockt *lockt = &u->lockt;
 	struct file_lock *file_lock = NULL;
 	struct nfs4_lockowner *lo = NULL;
 	__be32 status;
@@ -6025,8 +6032,9 @@ out:
 
 __be32
 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *cstate,
-	    struct nfsd4_locku *locku)
+	    union nfsd4_op_u *u)
 {
+	struct nfsd4_locku *locku = &u->locku;
 	struct nfs4_ol_stateid *stp;
 	struct file *filp = NULL;
 	struct file_lock *file_lock = NULL;
@@ -6132,8 +6140,9 @@ check_for_locks(struct nfs4_file *fp, struct nfs4_lockowner *lowner)
 __be32
 nfsd4_release_lockowner(struct svc_rqst *rqstp,
 			struct nfsd4_compound_state *cstate,
-			struct nfsd4_release_lockowner *rlockowner)
+			union nfsd4_op_u *u)
 {
+	struct nfsd4_release_lockowner *rlockowner = &u->release_lockowner;
 	clientid_t *clid = &rlockowner->rl_clientid;
 	struct nfs4_stateowner *sop;
 	struct nfs4_lockowner *lo = NULL;
@@ -7012,23 +7021,24 @@ nfs4_state_start(void)
 
 	ret = set_callback_cred();
 	if (ret)
-		return -ENOMEM;
+		return ret;
+
 	laundry_wq = alloc_workqueue("%s", WQ_UNBOUND, 0, "nfsd4");
 	if (laundry_wq == NULL) {
 		ret = -ENOMEM;
-		goto out_recovery;
+		goto out_cleanup_cred;
 	}
 	ret = nfsd4_create_callback_queue();
 	if (ret)
 		goto out_free_laundry;
 
 	set_max_delegations();
-
 	return 0;
 
 out_free_laundry:
 	destroy_workqueue(laundry_wq);
-out_recovery:
+out_cleanup_cred:
+	cleanup_callback_cred();
 	return ret;
 }
 
@@ -7086,6 +7096,7 @@ nfs4_state_shutdown(void)
 {
 	destroy_workqueue(laundry_wq);
 	nfsd4_destroy_callback_queue();
+	cleanup_callback_cred();
 }
 
 static void
@@ -7114,27 +7125,31 @@ clear_current_stateid(struct nfsd4_compound_state *cstate)
  * functions to set current state id
  */
 void
-nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp)
+nfsd4_set_opendowngradestateid(struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
-	put_stateid(cstate, &odp->od_stateid);
+	put_stateid(cstate, &u->open_downgrade.od_stateid);
 }
 
 void
-nfsd4_set_openstateid(struct nfsd4_compound_state *cstate, struct nfsd4_open *open)
+nfsd4_set_openstateid(struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
-	put_stateid(cstate, &open->op_stateid);
+	put_stateid(cstate, &u->open.op_stateid);
 }
 
 void
-nfsd4_set_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close)
+nfsd4_set_closestateid(struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
-	put_stateid(cstate, &close->cl_stateid);
+	put_stateid(cstate, &u->close.cl_stateid);
 }
 
 void
-nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, struct nfsd4_lock *lock)
+nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
-	put_stateid(cstate, &lock->lk_resp_stateid);
+	put_stateid(cstate, &u->lock.lk_resp_stateid);
 }
 
 /*
@@ -7142,49 +7157,57 @@ nfsd4_set_lockstateid(struct nfsd4_compound_state *cstate, struct nfsd4_lock *lo
  */
 
 void
-nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate, struct nfsd4_open_downgrade *odp)
+nfsd4_get_opendowngradestateid(struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
-	get_stateid(cstate, &odp->od_stateid);
+	get_stateid(cstate, &u->open_downgrade.od_stateid);
 }
 
 void
-nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate, struct nfsd4_delegreturn *drp)
+nfsd4_get_delegreturnstateid(struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
-	get_stateid(cstate, &drp->dr_stateid);
+	get_stateid(cstate, &u->delegreturn.dr_stateid);
 }
 
 void
-nfsd4_get_freestateid(struct nfsd4_compound_state *cstate, struct nfsd4_free_stateid *fsp)
+nfsd4_get_freestateid(struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
-	get_stateid(cstate, &fsp->fr_stateid);
+	get_stateid(cstate, &u->free_stateid.fr_stateid);
 }
 
 void
-nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate, struct nfsd4_setattr *setattr)
+nfsd4_get_setattrstateid(struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
-	get_stateid(cstate, &setattr->sa_stateid);
+	get_stateid(cstate, &u->setattr.sa_stateid);
 }
 
 void
-nfsd4_get_closestateid(struct nfsd4_compound_state *cstate, struct nfsd4_close *close)
+nfsd4_get_closestateid(struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
-	get_stateid(cstate, &close->cl_stateid);
+	get_stateid(cstate, &u->close.cl_stateid);
 }
 
 void
-nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate, struct nfsd4_locku *locku)
+nfsd4_get_lockustateid(struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
-	get_stateid(cstate, &locku->lu_stateid);
+	get_stateid(cstate, &u->locku.lu_stateid);
 }
 
 void
-nfsd4_get_readstateid(struct nfsd4_compound_state *cstate, struct nfsd4_read *read)
+nfsd4_get_readstateid(struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
-	get_stateid(cstate, &read->rd_stateid);
+	get_stateid(cstate, &u->read.rd_stateid);
 }
 
 void
-nfsd4_get_writestateid(struct nfsd4_compound_state *cstate, struct nfsd4_write *write)
+nfsd4_get_writestateid(struct nfsd4_compound_state *cstate,
+		union nfsd4_op_u *u)
 {
-	get_stateid(cstate, &write->wr_stateid);
+	get_stateid(cstate, &u->write.wr_stateid);
 }
diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c
index 8fae53ce21d1..20fbcab97753 100644
--- a/fs/nfsd/nfs4xdr.c
+++ b/fs/nfsd/nfs4xdr.c
@@ -58,7 +58,7 @@
 
 #define NFSDDBG_FACILITY		NFSDDBG_XDR
 
-u32 nfsd_suppattrs[3][3] = {
+const u32 nfsd_suppattrs[3][3] = {
 	{NFSD4_SUPPORTED_ATTRS_WORD0,
 	 NFSD4_SUPPORTED_ATTRS_WORD1,
 	 NFSD4_SUPPORTED_ATTRS_WORD2},
@@ -1250,7 +1250,7 @@ nfsd4_decode_write(struct nfsd4_compoundargs *argp, struct nfsd4_write *write)
 	READ_BUF(16);
 	p = xdr_decode_hyper(p, &write->wr_offset);
 	write->wr_stable_how = be32_to_cpup(p++);
-	if (write->wr_stable_how > 2)
+	if (write->wr_stable_how > NFS_FILE_SYNC)
 		goto xdr_error;
 	write->wr_buflen = be32_to_cpup(p++);
 
@@ -1941,12 +1941,12 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 		} else
 			max_reply += nfsd4_max_reply(argp->rqstp, op);
 		/*
-		 * OP_LOCK may return a conflicting lock.  (Special case
-		 * because it will just skip encoding this if it runs
-		 * out of xdr buffer space, and it is the only operation
-		 * that behaves this way.)
+		 * OP_LOCK and OP_LOCKT may return a conflicting lock.
+		 * (Special case because it will just skip encoding this
+		 * if it runs out of xdr buffer space, and it is the only
+		 * operation that behaves this way.)
 		 */
-		if (op->opnum == OP_LOCK)
+		if (op->opnum == OP_LOCK || op->opnum == OP_LOCKT)
 			max_reply += NFS4_OPAQUE_LIMIT;
 
 		if (op->status) {
@@ -1966,10 +1966,14 @@ nfsd4_decode_compound(struct nfsd4_compoundargs *argp)
 	DECODE_TAIL;
 }
 
-static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode)
+static __be32 *encode_change(__be32 *p, struct kstat *stat, struct inode *inode,
+			     struct svc_export *exp)
 {
-	if (IS_I_VERSION(inode)) {
-		p = xdr_encode_hyper(p, inode->i_version);
+	if (exp->ex_flags & NFSEXP_V4ROOT) {
+		*p++ = cpu_to_be32(convert_to_wallclock(exp->cd->flush_time));
+		*p++ = 0;
+	} else if (IS_I_VERSION(inode)) {
+		p = xdr_encode_hyper(p, nfsd4_change_attribute(inode));
 	} else {
 		*p++ = cpu_to_be32(stat->ctime.tv_sec);
 		*p++ = cpu_to_be32(stat->ctime.tv_nsec);
@@ -2297,7 +2301,7 @@ static int get_parent_attributes(struct svc_export *exp, struct kstat *stat)
 		if (path.dentry != path.mnt->mnt_root)
 			break;
 	}
-	err = vfs_getattr(&path, stat);
+	err = vfs_getattr(&path, stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
 	path_put(&path);
 	return err;
 }
@@ -2381,7 +2385,7 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 			goto out;
 	}
 
-	err = vfs_getattr(&path, &stat);
+	err = vfs_getattr(&path, &stat, STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
 	if (err)
 		goto out_nfserr;
 	if ((bmval0 & (FATTR4_WORD0_FILES_AVAIL | FATTR4_WORD0_FILES_FREE |
@@ -2417,8 +2421,11 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 #ifdef CONFIG_NFSD_V4_SECURITY_LABEL
 	if ((bmval2 & FATTR4_WORD2_SECURITY_LABEL) ||
 	     bmval0 & FATTR4_WORD0_SUPPORTED_ATTRS) {
-		err = security_inode_getsecctx(d_inode(dentry),
+		if (exp->ex_flags & NFSEXP_SECURITY_LABEL)
+			err = security_inode_getsecctx(d_inode(dentry),
 						&context, &contextlen);
+		else
+			err = -EOPNOTSUPP;
 		contextsupport = (err == 0);
 		if (bmval2 & FATTR4_WORD2_SECURITY_LABEL) {
 			if (err == -EOPNOTSUPP)
@@ -2490,7 +2497,7 @@ nfsd4_encode_fattr(struct xdr_stream *xdr, struct svc_fh *fhp,
 		p = xdr_reserve_space(xdr, 8);
 		if (!p)
 			goto out_resource;
-		p = encode_change(p, &stat, d_inode(dentry));
+		p = encode_change(p, &stat, d_inode(dentry), exp);
 	}
 	if (bmval0 & FATTR4_WORD0_SIZE) {
 		p = xdr_reserve_space(xdr, 8);
@@ -2824,9 +2831,14 @@ out_acl:
 	}
 #endif /* CONFIG_NFSD_PNFS */
 	if (bmval2 & FATTR4_WORD2_SUPPATTR_EXCLCREAT) {
-		status = nfsd4_encode_bitmap(xdr, NFSD_SUPPATTR_EXCLCREAT_WORD0,
-						  NFSD_SUPPATTR_EXCLCREAT_WORD1,
-						  NFSD_SUPPATTR_EXCLCREAT_WORD2);
+		u32 supp[3];
+
+		memcpy(supp, nfsd_suppattrs[minorversion], sizeof(supp));
+		supp[0] &= NFSD_SUPPATTR_EXCLCREAT_WORD0;
+		supp[1] &= NFSD_SUPPATTR_EXCLCREAT_WORD1;
+		supp[2] &= NFSD_SUPPATTR_EXCLCREAT_WORD2;
+
+		status = nfsd4_encode_bitmap(xdr, supp[0], supp[1], supp[2]);
 		if (status)
 			goto out;
 	}
@@ -4112,8 +4124,7 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
 		struct nfsd4_getdeviceinfo *gdev)
 {
 	struct xdr_stream *xdr = &resp->xdr;
-	const struct nfsd4_layout_ops *ops =
-		nfsd4_layout_ops[gdev->gd_layout_type];
+	const struct nfsd4_layout_ops *ops;
 	u32 starting_len = xdr->buf->len, needed_len;
 	__be32 *p;
 
@@ -4130,6 +4141,7 @@ nfsd4_encode_getdeviceinfo(struct nfsd4_compoundres *resp, __be32 nfserr,
 
 	/* If maxcount is 0 then just update notifications */
 	if (gdev->gd_maxcount != 0) {
+		ops = nfsd4_layout_ops[gdev->gd_layout_type];
 		nfserr = ops->encode_getdeviceinfo(xdr, gdev);
 		if (nfserr) {
 			/*
@@ -4182,8 +4194,7 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
 		struct nfsd4_layoutget *lgp)
 {
 	struct xdr_stream *xdr = &resp->xdr;
-	const struct nfsd4_layout_ops *ops =
-		nfsd4_layout_ops[lgp->lg_layout_type];
+	const struct nfsd4_layout_ops *ops;
 	__be32 *p;
 
 	dprintk("%s: err %d\n", __func__, nfserr);
@@ -4206,6 +4217,7 @@ nfsd4_encode_layoutget(struct nfsd4_compoundres *resp, __be32 nfserr,
 	*p++ = cpu_to_be32(lgp->lg_seg.iomode);
 	*p++ = cpu_to_be32(lgp->lg_layout_type);
 
+	ops = nfsd4_layout_ops[lgp->lg_layout_type];
 	nfserr = ops->encode_layoutget(xdr, lgp);
 out:
 	kfree(lgp->lg_content);
@@ -4526,14 +4538,13 @@ nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op)
 }
 
 int
-nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nfs4svc_encode_voidres(struct svc_rqst *rqstp, __be32 *p)
 {
         return xdr_ressize_check(rqstp, p);
 }
 
-int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp)
+void nfsd4_release_compoundargs(struct svc_rqst *rqstp)
 {
-	struct svc_rqst *rqstp = rq;
 	struct nfsd4_compoundargs *args = rqstp->rq_argp;
 
 	if (args->ops != args->iops) {
@@ -4547,12 +4558,13 @@ int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp)
 		args->to_free = tb->next;
 		kfree(tb);
 	}
-	return 1;
 }
 
 int
-nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundargs *args)
+nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd4_compoundargs *args = rqstp->rq_argp;
+
 	if (rqstp->rq_arg.head[0].iov_len % 4) {
 		/* client is nuts */
 		dprintk("%s: compound not properly padded! (peeraddr=%pISc xid=0x%x)",
@@ -4572,11 +4584,12 @@ nfs4svc_decode_compoundargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_comp
 }
 
 int
-nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p, struct nfsd4_compoundres *resp)
+nfs4svc_encode_compoundres(struct svc_rqst *rqstp, __be32 *p)
 {
 	/*
 	 * All that remains is to write the tag and operation count...
 	 */
+	struct nfsd4_compoundres *resp = rqstp->rq_resp;
 	struct xdr_buf *buf = resp->xdr.buf;
 
 	WARN_ON_ONCE(buf->len != buf->head[0].iov_len + buf->page_len +
diff --git a/fs/nfsd/nfscache.c b/fs/nfsd/nfscache.c
index d6b97b424ad1..96fd15979cbd 100644
--- a/fs/nfsd/nfscache.c
+++ b/fs/nfsd/nfscache.c
@@ -578,7 +578,7 @@ nfsd_cache_append(struct svc_rqst *rqstp, struct kvec *data)
 	struct kvec	*vec = &rqstp->rq_res.head[0];
 
 	if (vec->iov_len + data->iov_len > PAGE_SIZE) {
-		printk(KERN_WARNING "nfsd: cached reply too large (%Zd).\n",
+		printk(KERN_WARNING "nfsd: cached reply too large (%zd).\n",
 				data->iov_len);
 		return 0;
 	}
diff --git a/fs/nfsd/nfsctl.c b/fs/nfsd/nfsctl.c
index f3b2f34b10a3..6493df6b1bd5 100644
--- a/fs/nfsd/nfsctl.c
+++ b/fs/nfsd/nfsctl.c
@@ -536,12 +536,32 @@ out_free:
 	return rv;
 }
 
+static ssize_t
+nfsd_print_version_support(char *buf, int remaining, const char *sep,
+		unsigned vers, int minor)
+{
+	const char *format = minor < 0 ? "%s%c%u" : "%s%c%u.%u";
+	bool supported = !!nfsd_vers(vers, NFSD_TEST);
+
+	if (vers == 4 && minor >= 0 &&
+	    !nfsd_minorversion(minor, NFSD_TEST))
+		supported = false;
+	if (minor == 0 && supported)
+		/*
+		 * special case for backward compatability.
+		 * +4.0 is never reported, it is implied by
+		 * +4, unless -4.0 is present.
+		 */
+		return 0;
+	return snprintf(buf, remaining, format, sep,
+			supported ? '+' : '-', vers, minor);
+}
+
 static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 {
 	char *mesg = buf;
 	char *vers, *minorp, sign;
 	int len, num, remaining;
-	unsigned minor;
 	ssize_t tlen = 0;
 	char *sep;
 	struct nfsd_net *nn = net_generic(netns(file), nfsd_net_id);
@@ -561,6 +581,8 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 		len = qword_get(&mesg, vers, size);
 		if (len <= 0) return -EINVAL;
 		do {
+			enum vers_op cmd;
+			unsigned minor;
 			sign = *vers;
 			if (sign == '+' || sign == '-')
 				num = simple_strtol((vers+1), &minorp, 0);
@@ -569,24 +591,34 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 			if (*minorp == '.') {
 				if (num != 4)
 					return -EINVAL;
-				minor = simple_strtoul(minorp+1, NULL, 0);
-				if (minor == 0)
-					return -EINVAL;
-				if (nfsd_minorversion(minor, sign == '-' ?
-						     NFSD_CLEAR : NFSD_SET) < 0)
+				if (kstrtouint(minorp+1, 0, &minor) < 0)
 					return -EINVAL;
-				goto next;
 			}
+
+			cmd = sign == '-' ? NFSD_CLEAR : NFSD_SET;
 			switch(num) {
 			case 2:
 			case 3:
+				nfsd_vers(num, cmd);
+				break;
 			case 4:
-				nfsd_vers(num, sign == '-' ? NFSD_CLEAR : NFSD_SET);
+				if (*minorp == '.') {
+					if (nfsd_minorversion(minor, cmd) < 0)
+						return -EINVAL;
+				} else if ((cmd == NFSD_SET) != nfsd_vers(num, NFSD_TEST)) {
+					/*
+					 * Either we have +4 and no minors are enabled,
+					 * or we have -4 and at least one minor is enabled.
+					 * In either case, propagate 'cmd' to all minors.
+					 */
+					minor = 0;
+					while (nfsd_minorversion(minor, cmd) >= 0)
+						minor++;
+				}
 				break;
 			default:
 				return -EINVAL;
 			}
-		next:
 			vers += len + 1;
 		} while ((len = qword_get(&mesg, vers, size)) > 0);
 		/* If all get turned off, turn them back on, as
@@ -599,35 +631,26 @@ static ssize_t __write_versions(struct file *file, char *buf, size_t size)
 	len = 0;
 	sep = "";
 	remaining = SIMPLE_TRANSACTION_LIMIT;
-	for (num=2 ; num <= 4 ; num++)
-		if (nfsd_vers(num, NFSD_AVAIL)) {
-			len = snprintf(buf, remaining, "%s%c%d", sep,
-				       nfsd_vers(num, NFSD_TEST)?'+':'-',
-				       num);
-			sep = " ";
-
-			if (len >= remaining)
-				break;
-			remaining -= len;
-			buf += len;
-			tlen += len;
-		}
-	if (nfsd_vers(4, NFSD_AVAIL))
-		for (minor = 1; minor <= NFSD_SUPPORTED_MINOR_VERSION;
-		     minor++) {
-			len = snprintf(buf, remaining, " %c4.%u",
-					(nfsd_vers(4, NFSD_TEST) &&
-					 nfsd_minorversion(minor, NFSD_TEST)) ?
-						'+' : '-',
-					minor);
+	for (num=2 ; num <= 4 ; num++) {
+		int minor;
+		if (!nfsd_vers(num, NFSD_AVAIL))
+			continue;
 
+		minor = -1;
+		do {
+			len = nfsd_print_version_support(buf, remaining,
+					sep, num, minor);
 			if (len >= remaining)
-				break;
+				goto out;
 			remaining -= len;
 			buf += len;
 			tlen += len;
-		}
-
+			minor++;
+			if (len)
+				sep = " ";
+		} while (num == 4 && minor <= NFSD_SUPPORTED_MINOR_VERSION);
+	}
+out:
 	len = snprintf(buf, remaining, "\n");
 	if (len >= remaining)
 		return -EINVAL;
@@ -1123,7 +1146,7 @@ static ssize_t write_v4_end_grace(struct file *file, char *buf, size_t size)
 
 static int nfsd_fill_super(struct super_block * sb, void * data, int silent)
 {
-	static struct tree_descr nfsd_files[] = {
+	static const struct tree_descr nfsd_files[] = {
 		[NFSD_List] = {"exports", &exports_nfsd_operations, S_IRUGO},
 		[NFSD_Export_features] = {"export_features",
 					&export_features_operations, S_IRUGO},
diff --git a/fs/nfsd/nfsd.h b/fs/nfsd/nfsd.h
index d74c8c44dc35..b9c538ab7a59 100644
--- a/fs/nfsd/nfsd.h
+++ b/fs/nfsd/nfsd.h
@@ -60,7 +60,7 @@ struct readdir_cd {
 
 
 extern struct svc_program	nfsd_program;
-extern struct svc_version	nfsd_version2, nfsd_version3,
+extern const struct svc_version	nfsd_version2, nfsd_version3,
 				nfsd_version4;
 extern struct mutex		nfsd_mutex;
 extern spinlock_t		nfsd_drc_lock;
@@ -86,12 +86,12 @@ void		nfsd_destroy(struct net *net);
 
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 #ifdef CONFIG_NFSD_V2_ACL
-extern struct svc_version nfsd_acl_version2;
+extern const struct svc_version nfsd_acl_version2;
 #else
 #define nfsd_acl_version2 NULL
 #endif
 #ifdef CONFIG_NFSD_V3_ACL
-extern struct svc_version nfsd_acl_version3;
+extern const struct svc_version nfsd_acl_version3;
 #else
 #define nfsd_acl_version3 NULL
 #endif
@@ -362,16 +362,16 @@ void		nfsd_lockd_shutdown(void);
 	FATTR4_WORD2_MODE_UMASK | \
 	NFSD4_2_SECURITY_ATTRS)
 
-extern u32 nfsd_suppattrs[3][3];
+extern const u32 nfsd_suppattrs[3][3];
 
-static inline bool bmval_is_subset(u32 *bm1, u32 *bm2)
+static inline bool bmval_is_subset(const u32 *bm1, const u32 *bm2)
 {
 	return !((bm1[0] & ~bm2[0]) ||
 	         (bm1[1] & ~bm2[1]) ||
 		 (bm1[2] & ~bm2[2]));
 }
 
-static inline bool nfsd_attrs_supported(u32 minorversion, u32 *bmval)
+static inline bool nfsd_attrs_supported(u32 minorversion, const u32 *bmval)
 {
 	return bmval_is_subset(bmval, nfsd_suppattrs[minorversion]);
 }
diff --git a/fs/nfsd/nfsfh.h b/fs/nfsd/nfsfh.h
index f84fe6bf9aee..e47cf6c2ac28 100644
--- a/fs/nfsd/nfsfh.h
+++ b/fs/nfsd/nfsfh.h
@@ -241,6 +241,28 @@ fh_clear_wcc(struct svc_fh *fhp)
 }
 
 /*
+ * We could use i_version alone as the change attribute.  However,
+ * i_version can go backwards after a reboot.  On its own that doesn't
+ * necessarily cause a problem, but if i_version goes backwards and then
+ * is incremented again it could reuse a value that was previously used
+ * before boot, and a client who queried the two values might
+ * incorrectly assume nothing changed.
+ *
+ * By using both ctime and the i_version counter we guarantee that as
+ * long as time doesn't go backwards we never reuse an old value.
+ */
+static inline u64 nfsd4_change_attribute(struct inode *inode)
+{
+	u64 chattr;
+
+	chattr =  inode->i_ctime.tv_sec;
+	chattr <<= 30;
+	chattr += inode->i_ctime.tv_nsec;
+	chattr += inode->i_version;
+	return chattr;
+}
+
+/*
  * Fill in the pre_op attr for the wcc data
  */
 static inline void
@@ -253,7 +275,7 @@ fill_pre_wcc(struct svc_fh *fhp)
 		fhp->fh_pre_mtime = inode->i_mtime;
 		fhp->fh_pre_ctime = inode->i_ctime;
 		fhp->fh_pre_size  = inode->i_size;
-		fhp->fh_pre_change = inode->i_version;
+		fhp->fh_pre_change = nfsd4_change_attribute(inode);
 		fhp->fh_pre_saved = true;
 	}
 }
diff --git a/fs/nfsd/nfsproc.c b/fs/nfsd/nfsproc.c
index 010aff5c5a79..5076ae2b8258 100644
--- a/fs/nfsd/nfsproc.c
+++ b/fs/nfsd/nfsproc.c
@@ -17,7 +17,7 @@ typedef struct svc_buf	svc_buf;
 
 
 static __be32
-nfsd_proc_null(struct svc_rqst *rqstp, void *argp, void *resp)
+nfsd_proc_null(struct svc_rqst *rqstp)
 {
 	return nfs_ok;
 }
@@ -39,9 +39,10 @@ nfsd_return_dirop(__be32 err, struct nfsd_diropres *resp)
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
-					  struct nfsd_attrstat *resp)
+nfsd_proc_getattr(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	__be32 nfserr;
 	dprintk("nfsd: GETATTR  %s\n", SVCFH_fmt(&argp->fh));
 
@@ -56,9 +57,10 @@ nfsd_proc_getattr(struct svc_rqst *rqstp, struct nfsd_fhandle  *argp,
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_setattr(struct svc_rqst *rqstp, struct nfsd_sattrargs *argp,
-					  struct nfsd_attrstat  *resp)
+nfsd_proc_setattr(struct svc_rqst *rqstp)
 {
+	struct nfsd_sattrargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	struct iattr *iap = &argp->attrs;
 	struct svc_fh *fhp;
 	__be32 nfserr;
@@ -122,9 +124,10 @@ done:
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
-					 struct nfsd_diropres  *resp)
+nfsd_proc_lookup(struct svc_rqst *rqstp)
 {
+	struct nfsd_diropargs *argp = rqstp->rq_argp;
+	struct nfsd_diropres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: LOOKUP   %s %.*s\n",
@@ -142,9 +145,10 @@ nfsd_proc_lookup(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
  * Read a symlink.
  */
 static __be32
-nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp,
-					   struct nfsd_readlinkres *resp)
+nfsd_proc_readlink(struct svc_rqst *rqstp)
 {
+	struct nfsd_readlinkargs *argp = rqstp->rq_argp;
+	struct nfsd_readlinkres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: READLINK %s\n", SVCFH_fmt(&argp->fh));
@@ -162,9 +166,10 @@ nfsd_proc_readlink(struct svc_rqst *rqstp, struct nfsd_readlinkargs *argp,
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp,
-				       struct nfsd_readres  *resp)
+nfsd_proc_read(struct svc_rqst *rqstp)
 {
+	struct nfsd_readargs *argp = rqstp->rq_argp;
+	struct nfsd_readres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: READ    %s %d bytes at %d\n",
@@ -200,22 +205,19 @@ nfsd_proc_read(struct svc_rqst *rqstp, struct nfsd_readargs *argp,
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp,
-					struct nfsd_attrstat  *resp)
+nfsd_proc_write(struct svc_rqst *rqstp)
 {
+	struct nfsd_writeargs *argp = rqstp->rq_argp;
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
 	__be32	nfserr;
-	int	stable = 1;
 	unsigned long cnt = argp->len;
 
 	dprintk("nfsd: WRITE    %s %d bytes at %d\n",
 		SVCFH_fmt(&argp->fh),
 		argp->len, argp->offset);
 
-	nfserr = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh), NULL,
-				   argp->offset,
-				   rqstp->rq_vec, argp->vlen,
-			           &cnt,
-				   &stable);
+	nfserr = nfsd_write(rqstp, fh_copy(&resp->fh, &argp->fh), argp->offset,
+				rqstp->rq_vec, argp->vlen, &cnt, NFS_DATA_SYNC);
 	return nfsd_return_attrs(nfserr, resp);
 }
 
@@ -226,9 +228,10 @@ nfsd_proc_write(struct svc_rqst *rqstp, struct nfsd_writeargs *argp,
  * N.B. After this call _both_ argp->fh and resp->fh need an fh_put
  */
 static __be32
-nfsd_proc_create(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
-					 struct nfsd_diropres   *resp)
+nfsd_proc_create(struct svc_rqst *rqstp)
 {
+	struct nfsd_createargs *argp = rqstp->rq_argp;
+	struct nfsd_diropres *resp = rqstp->rq_resp;
 	svc_fh		*dirfhp = &argp->fh;
 	svc_fh		*newfhp = &resp->fh;
 	struct iattr	*attr = &argp->attrs;
@@ -381,9 +384,9 @@ done:
 }
 
 static __be32
-nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
-					 void		       *resp)
+nfsd_proc_remove(struct svc_rqst *rqstp)
 {
+	struct nfsd_diropargs *argp = rqstp->rq_argp;
 	__be32	nfserr;
 
 	dprintk("nfsd: REMOVE   %s %.*s\n", SVCFH_fmt(&argp->fh),
@@ -396,9 +399,9 @@ nfsd_proc_remove(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
 }
 
 static __be32
-nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp,
-				  	 void		        *resp)
+nfsd_proc_rename(struct svc_rqst *rqstp)
 {
+	struct nfsd_renameargs *argp = rqstp->rq_argp;
 	__be32	nfserr;
 
 	dprintk("nfsd: RENAME   %s %.*s -> \n",
@@ -414,9 +417,9 @@ nfsd_proc_rename(struct svc_rqst *rqstp, struct nfsd_renameargs *argp,
 }
 
 static __be32
-nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp,
-				void			    *resp)
+nfsd_proc_link(struct svc_rqst *rqstp)
 {
+	struct nfsd_linkargs *argp = rqstp->rq_argp;
 	__be32	nfserr;
 
 	dprintk("nfsd: LINK     %s ->\n",
@@ -434,9 +437,9 @@ nfsd_proc_link(struct svc_rqst *rqstp, struct nfsd_linkargs *argp,
 }
 
 static __be32
-nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp,
-				          void			  *resp)
+nfsd_proc_symlink(struct svc_rqst *rqstp)
 {
+	struct nfsd_symlinkargs *argp = rqstp->rq_argp;
 	struct svc_fh	newfh;
 	__be32		nfserr;
 
@@ -464,9 +467,10 @@ nfsd_proc_symlink(struct svc_rqst *rqstp, struct nfsd_symlinkargs *argp,
  * N.B. After this call resp->fh needs an fh_put
  */
 static __be32
-nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
-					struct nfsd_diropres   *resp)
+nfsd_proc_mkdir(struct svc_rqst *rqstp)
 {
+	struct nfsd_createargs *argp = rqstp->rq_argp;
+	struct nfsd_diropres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: MKDIR    %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name);
@@ -488,9 +492,9 @@ nfsd_proc_mkdir(struct svc_rqst *rqstp, struct nfsd_createargs *argp,
  * Remove a directory
  */
 static __be32
-nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
-				 	void		      *resp)
+nfsd_proc_rmdir(struct svc_rqst *rqstp)
 {
+	struct nfsd_diropargs *argp = rqstp->rq_argp;
 	__be32	nfserr;
 
 	dprintk("nfsd: RMDIR    %s %.*s\n", SVCFH_fmt(&argp->fh), argp->len, argp->name);
@@ -504,9 +508,10 @@ nfsd_proc_rmdir(struct svc_rqst *rqstp, struct nfsd_diropargs *argp,
  * Read a portion of a directory.
  */
 static __be32
-nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp,
-					  struct nfsd_readdirres  *resp)
+nfsd_proc_readdir(struct svc_rqst *rqstp)
 {
+	struct nfsd_readdirargs *argp = rqstp->rq_argp;
+	struct nfsd_readdirres *resp = rqstp->rq_resp;
 	int		count;
 	__be32		nfserr;
 	loff_t		offset;
@@ -544,9 +549,10 @@ nfsd_proc_readdir(struct svc_rqst *rqstp, struct nfsd_readdirargs *argp,
  * Get file system info
  */
 static __be32
-nfsd_proc_statfs(struct svc_rqst * rqstp, struct nfsd_fhandle   *argp,
-					  struct nfsd_statfsres *resp)
+nfsd_proc_statfs(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *argp = rqstp->rq_argp;
+	struct nfsd_statfsres *resp = rqstp->rq_resp;
 	__be32	nfserr;
 
 	dprintk("nfsd: STATFS   %s\n", SVCFH_fmt(&argp->fh));
@@ -567,168 +573,168 @@ struct nfsd_void { int dummy; };
 #define FH 8		/* filehandle */
 #define	AT 18		/* attributes */
 
-static struct svc_procedure		nfsd_procedures2[18] = {
+static const struct svc_procedure nfsd_procedures2[18] = {
 	[NFSPROC_NULL] = {
-		.pc_func = (svc_procfunc) nfsd_proc_null,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_func = nfsd_proc_null,
+		.pc_decode = nfssvc_decode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_GETATTR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_getattr,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_func = nfsd_proc_getattr,
+		.pc_decode = nfssvc_decode_fhandle,
+		.pc_encode = nfssvc_encode_attrstat,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+AT,
 	},
 	[NFSPROC_SETATTR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_setattr,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_sattrargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_func = nfsd_proc_setattr,
+		.pc_decode = nfssvc_decode_sattrargs,
+		.pc_encode = nfssvc_encode_attrstat,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_sattrargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+AT,
 	},
 	[NFSPROC_ROOT] = {
-		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_decode = nfssvc_decode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_LOOKUP] = {
-		.pc_func = (svc_procfunc) nfsd_proc_lookup,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_func = nfsd_proc_lookup,
+		.pc_decode = nfssvc_decode_diropargs,
+		.pc_encode = nfssvc_encode_diropres,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+FH+AT,
 	},
 	[NFSPROC_READLINK] = {
-		.pc_func = (svc_procfunc) nfsd_proc_readlink,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_readlinkargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_readlinkres,
+		.pc_func = nfsd_proc_readlink,
+		.pc_decode = nfssvc_decode_readlinkargs,
+		.pc_encode = nfssvc_encode_readlinkres,
 		.pc_argsize = sizeof(struct nfsd_readlinkargs),
 		.pc_ressize = sizeof(struct nfsd_readlinkres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+1+NFS_MAXPATHLEN/4,
 	},
 	[NFSPROC_READ] = {
-		.pc_func = (svc_procfunc) nfsd_proc_read,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_readargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_readres,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_func = nfsd_proc_read,
+		.pc_decode = nfssvc_decode_readargs,
+		.pc_encode = nfssvc_encode_readres,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_readargs),
 		.pc_ressize = sizeof(struct nfsd_readres),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST+AT+1+NFSSVC_MAXBLKSIZE_V2/4,
 	},
 	[NFSPROC_WRITECACHE] = {
-		.pc_decode = (kxdrproc_t) nfssvc_decode_void,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_decode = nfssvc_decode_void,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_void),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_NOCACHE,
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_WRITE] = {
-		.pc_func = (svc_procfunc) nfsd_proc_write,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_writeargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_attrstat,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_func = nfsd_proc_write,
+		.pc_decode = nfssvc_decode_writeargs,
+		.pc_encode = nfssvc_encode_attrstat,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_writeargs),
 		.pc_ressize = sizeof(struct nfsd_attrstat),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+AT,
 	},
 	[NFSPROC_CREATE] = {
-		.pc_func = (svc_procfunc) nfsd_proc_create,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_func = nfsd_proc_create,
+		.pc_decode = nfssvc_decode_createargs,
+		.pc_encode = nfssvc_encode_diropres,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+FH+AT,
 	},
 	[NFSPROC_REMOVE] = {
-		.pc_func = (svc_procfunc) nfsd_proc_remove,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_func = nfsd_proc_remove,
+		.pc_decode = nfssvc_decode_diropargs,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_RENAME] = {
-		.pc_func = (svc_procfunc) nfsd_proc_rename,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_renameargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_func = nfsd_proc_rename,
+		.pc_decode = nfssvc_decode_renameargs,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_renameargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_LINK] = {
-		.pc_func = (svc_procfunc) nfsd_proc_link,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_linkargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_func = nfsd_proc_link,
+		.pc_decode = nfssvc_decode_linkargs,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_linkargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_SYMLINK] = {
-		.pc_func = (svc_procfunc) nfsd_proc_symlink,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_symlinkargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_func = nfsd_proc_symlink,
+		.pc_decode = nfssvc_decode_symlinkargs,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_symlinkargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_MKDIR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_mkdir,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_createargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_diropres,
-		.pc_release = (kxdrproc_t) nfssvc_release_fhandle,
+		.pc_func = nfsd_proc_mkdir,
+		.pc_decode = nfssvc_decode_createargs,
+		.pc_encode = nfssvc_encode_diropres,
+		.pc_release = nfssvc_release_fhandle,
 		.pc_argsize = sizeof(struct nfsd_createargs),
 		.pc_ressize = sizeof(struct nfsd_diropres),
 		.pc_cachetype = RC_REPLBUFF,
 		.pc_xdrressize = ST+FH+AT,
 	},
 	[NFSPROC_RMDIR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_rmdir,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_diropargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_void,
+		.pc_func = nfsd_proc_rmdir,
+		.pc_decode = nfssvc_decode_diropargs,
+		.pc_encode = nfssvc_encode_void,
 		.pc_argsize = sizeof(struct nfsd_diropargs),
 		.pc_ressize = sizeof(struct nfsd_void),
 		.pc_cachetype = RC_REPLSTAT,
 		.pc_xdrressize = ST,
 	},
 	[NFSPROC_READDIR] = {
-		.pc_func = (svc_procfunc) nfsd_proc_readdir,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_readdirargs,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_readdirres,
+		.pc_func = nfsd_proc_readdir,
+		.pc_decode = nfssvc_decode_readdirargs,
+		.pc_encode = nfssvc_encode_readdirres,
 		.pc_argsize = sizeof(struct nfsd_readdirargs),
 		.pc_ressize = sizeof(struct nfsd_readdirres),
 		.pc_cachetype = RC_NOCACHE,
 	},
 	[NFSPROC_STATFS] = {
-		.pc_func = (svc_procfunc) nfsd_proc_statfs,
-		.pc_decode = (kxdrproc_t) nfssvc_decode_fhandle,
-		.pc_encode = (kxdrproc_t) nfssvc_encode_statfsres,
+		.pc_func = nfsd_proc_statfs,
+		.pc_decode = nfssvc_decode_fhandle,
+		.pc_encode = nfssvc_encode_statfsres,
 		.pc_argsize = sizeof(struct nfsd_fhandle),
 		.pc_ressize = sizeof(struct nfsd_statfsres),
 		.pc_cachetype = RC_NOCACHE,
@@ -737,12 +743,14 @@ static struct svc_procedure		nfsd_procedures2[18] = {
 };
 
 
-struct svc_version	nfsd_version2 = {
-		.vs_vers	= 2,
-		.vs_nproc	= 18,
-		.vs_proc	= nfsd_procedures2,
-		.vs_dispatch	= nfsd_dispatch,
-		.vs_xdrsize	= NFS2_SVC_XDRSIZE,
+static unsigned int nfsd_count2[ARRAY_SIZE(nfsd_procedures2)];
+const struct svc_version nfsd_version2 = {
+	.vs_vers	= 2,
+	.vs_nproc	= 18,
+	.vs_proc	= nfsd_procedures2,
+	.vs_count	= nfsd_count2,
+	.vs_dispatch	= nfsd_dispatch,
+	.vs_xdrsize	= NFS2_SVC_XDRSIZE,
 };
 
 /*
@@ -790,6 +798,7 @@ nfserrno (int errno)
 		{ nfserr_serverfault, -ESERVERFAULT },
 		{ nfserr_serverfault, -ENFILE },
 		{ nfserr_io, -EUCLEAN },
+		{ nfserr_perm, -ENOKEY },
 	};
 	int	i;
 
diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c
index e6bfd96734c0..063ae7de2c12 100644
--- a/fs/nfsd/nfssvc.c
+++ b/fs/nfsd/nfssvc.c
@@ -6,7 +6,7 @@
  * Copyright (C) 1995, 1996, 1997 Olaf Kirch <okir@monad.swb.de>
  */
 
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/freezer.h>
 #include <linux/module.h>
 #include <linux/fs_struct.h>
@@ -68,14 +68,14 @@ unsigned long	nfsd_drc_mem_used;
 
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
 static struct svc_stat	nfsd_acl_svcstats;
-static struct svc_version *	nfsd_acl_version[] = {
+static const struct svc_version *nfsd_acl_version[] = {
 	[2] = &nfsd_acl_version2,
 	[3] = &nfsd_acl_version3,
 };
 
 #define NFSD_ACL_MINVERS            2
 #define NFSD_ACL_NRVERS		ARRAY_SIZE(nfsd_acl_version)
-static struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS];
+static const struct svc_version *nfsd_acl_versions[NFSD_ACL_NRVERS];
 
 static struct svc_program	nfsd_acl_program = {
 	.pg_prog		= NFS_ACL_PROGRAM,
@@ -92,7 +92,7 @@ static struct svc_stat	nfsd_acl_svcstats = {
 };
 #endif /* defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) */
 
-static struct svc_version *	nfsd_version[] = {
+static const struct svc_version *nfsd_version[] = {
 	[2] = &nfsd_version2,
 #if defined(CONFIG_NFSD_V3)
 	[3] = &nfsd_version3,
@@ -104,7 +104,7 @@ static struct svc_version *	nfsd_version[] = {
 
 #define NFSD_MINVERS    	2
 #define NFSD_NRVERS		ARRAY_SIZE(nfsd_version)
-static struct svc_version *nfsd_versions[NFSD_NRVERS];
+static const struct svc_version *nfsd_versions[NFSD_NRVERS];
 
 struct svc_program		nfsd_program = {
 #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
@@ -153,16 +153,31 @@ int nfsd_vers(int vers, enum vers_op change)
 	return 0;
 }
 
+static void
+nfsd_adjust_nfsd_versions4(void)
+{
+	unsigned i;
+
+	for (i = 0; i <= NFSD_SUPPORTED_MINOR_VERSION; i++) {
+		if (nfsd_supported_minorversions[i])
+			return;
+	}
+	nfsd_vers(4, NFSD_CLEAR);
+}
+
 int nfsd_minorversion(u32 minorversion, enum vers_op change)
 {
-	if (minorversion > NFSD_SUPPORTED_MINOR_VERSION)
+	if (minorversion > NFSD_SUPPORTED_MINOR_VERSION &&
+	    change != NFSD_AVAIL)
 		return -1;
 	switch(change) {
 	case NFSD_SET:
 		nfsd_supported_minorversions[minorversion] = true;
+		nfsd_vers(4, NFSD_SET);
 		break;
 	case NFSD_CLEAR:
 		nfsd_supported_minorversions[minorversion] = false;
+		nfsd_adjust_nfsd_versions4();
 		break;
 	case NFSD_TEST:
 		return nfsd_supported_minorversions[minorversion];
@@ -354,6 +369,8 @@ static int nfsd_inet6addr_event(struct notifier_block *this,
 		dprintk("nfsd_inet6addr_event: removed %pI6\n", &ifa->addr);
 		sin6.sin6_family = AF_INET6;
 		sin6.sin6_addr = ifa->addr;
+		if (ipv6_addr_type(&sin6.sin6_addr) & IPV6_ADDR_LINKLOCAL)
+			sin6.sin6_scope_id = ifa->idev->dev->ifindex;
 		svc_age_temp_xprts_now(nn->nfsd_serv, (struct sockaddr *)&sin6);
 	}
 
@@ -399,23 +416,20 @@ static void nfsd_last_thread(struct svc_serv *serv, struct net *net)
 
 void nfsd_reset_versions(void)
 {
-	int found_one = 0;
 	int i;
 
-	for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++) {
-		if (nfsd_program.pg_vers[i])
-			found_one = 1;
-	}
-
-	if (!found_one) {
-		for (i = NFSD_MINVERS; i < NFSD_NRVERS; i++)
-			nfsd_program.pg_vers[i] = nfsd_version[i];
-#if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL)
-		for (i = NFSD_ACL_MINVERS; i < NFSD_ACL_NRVERS; i++)
-			nfsd_acl_program.pg_vers[i] =
-				nfsd_acl_version[i];
-#endif
-	}
+	for (i = 0; i < NFSD_NRVERS; i++)
+		if (nfsd_vers(i, NFSD_TEST))
+			return;
+
+	for (i = 0; i < NFSD_NRVERS; i++)
+		if (i != 4)
+			nfsd_vers(i, NFSD_SET);
+		else {
+			int minor = 0;
+			while (nfsd_minorversion(minor, NFSD_SET) >= 0)
+				minor++;
+		}
 }
 
 /*
@@ -733,11 +747,41 @@ static __be32 map_new_errors(u32 vers, __be32 nfserr)
 	return nfserr;
 }
 
+/*
+ * A write procedure can have a large argument, and a read procedure can
+ * have a large reply, but no NFSv2 or NFSv3 procedure has argument and
+ * reply that can both be larger than a page.  The xdr code has taken
+ * advantage of this assumption to be a sloppy about bounds checking in
+ * some cases.  Pending a rewrite of the NFSv2/v3 xdr code to fix that
+ * problem, we enforce these assumptions here:
+ */
+static bool nfs_request_too_big(struct svc_rqst *rqstp,
+				const struct svc_procedure *proc)
+{
+	/*
+	 * The ACL code has more careful bounds-checking and is not
+	 * susceptible to this problem:
+	 */
+	if (rqstp->rq_prog != NFS_PROGRAM)
+		return false;
+	/*
+	 * Ditto NFSv4 (which can in theory have argument and reply both
+	 * more than a page):
+	 */
+	if (rqstp->rq_vers >= 4)
+		return false;
+	/* The reply will be small, we're OK: */
+	if (proc->pc_xdrressize > 0 &&
+	    proc->pc_xdrressize < XDR_QUADLEN(PAGE_SIZE))
+		return false;
+
+	return rqstp->rq_arg.len > PAGE_SIZE;
+}
+
 int
 nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 {
-	struct svc_procedure	*proc;
-	kxdrproc_t		xdr;
+	const struct svc_procedure *proc;
 	__be32			nfserr;
 	__be32			*nfserrp;
 
@@ -745,15 +789,19 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 				rqstp->rq_vers, rqstp->rq_proc);
 	proc = rqstp->rq_procinfo;
 
+	if (nfs_request_too_big(rqstp, proc)) {
+		dprintk("nfsd: NFSv%d argument too large\n", rqstp->rq_vers);
+		*statp = rpc_garbage_args;
+		return 1;
+	}
 	/*
 	 * Give the xdr decoder a chance to change this if it wants
 	 * (necessary in the NFSv4.0 compound case)
 	 */
 	rqstp->rq_cachetype = proc->pc_cachetype;
 	/* Decode arguments */
-	xdr = proc->pc_decode;
-	if (xdr && !xdr(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base,
-			rqstp->rq_argp)) {
+	if (proc->pc_decode &&
+	    !proc->pc_decode(rqstp, (__be32*)rqstp->rq_arg.head[0].iov_base)) {
 		dprintk("nfsd: failed to decode arguments!\n");
 		*statp = rpc_garbage_args;
 		return 1;
@@ -777,7 +825,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	rqstp->rq_res.head[0].iov_len += sizeof(__be32);
 
 	/* Now call the procedure handler, and encode NFS status. */
-	nfserr = proc->pc_func(rqstp, rqstp->rq_argp, rqstp->rq_resp);
+	nfserr = proc->pc_func(rqstp);
 	nfserr = map_new_errors(rqstp->rq_vers, nfserr);
 	if (nfserr == nfserr_dropit || test_bit(RQ_DROPME, &rqstp->rq_flags)) {
 		dprintk("nfsd: Dropping request; may be revisited later\n");
@@ -792,9 +840,7 @@ nfsd_dispatch(struct svc_rqst *rqstp, __be32 *statp)
 	 * For NFSv2, additional info is never returned in case of an error.
 	 */
 	if (!(nfserr && rqstp->rq_vers == 2)) {
-		xdr = proc->pc_encode;
-		if (xdr && !xdr(rqstp, nfserrp,
-				rqstp->rq_resp)) {
+		if (proc->pc_encode && !proc->pc_encode(rqstp, nfserrp)) {
 			/* Failed to encode result. Release cache entry */
 			dprintk("nfsd: failed to encode result!\n");
 			nfsd_cache_update(rqstp, RC_NOCACHE, NULL);
diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c
index 41b468a6a90f..e4da2717982d 100644
--- a/fs/nfsd/nfsxdr.c
+++ b/fs/nfsd/nfsxdr.c
@@ -206,14 +206,16 @@ __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *f
  * XDR decode functions
  */
 int
-nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nfssvc_decode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_argsize_check(rqstp, p);
 }
 
 int
-nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *args)
+nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_fhandle *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -221,9 +223,10 @@ nfssvc_decode_fhandle(struct svc_rqst *rqstp, __be32 *p, struct nfsd_fhandle *ar
 }
 
 int
-nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_sattrargs *args)
+nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_sattrargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -233,9 +236,10 @@ nfssvc_decode_sattrargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_diropargs *args)
+nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_diropargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->fh))
 	 || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -244,9 +248,9 @@ nfssvc_decode_diropargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readargs *args)
+nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readargs *args = rqstp->rq_argp;
 	unsigned int len;
 	int v;
 	p = decode_fh(p, &args->fh);
@@ -276,10 +280,11 @@ nfssvc_decode_readargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_writeargs *args)
+nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_writeargs *args = rqstp->rq_argp;
 	unsigned int len, hdr, dlen;
+	struct kvec *head = rqstp->rq_arg.head;
 	int v;
 
 	p = decode_fh(p, &args->fh);
@@ -300,9 +305,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 	 * Check to make sure that we got the right number of
 	 * bytes.
 	 */
-	hdr = (void*)p - rqstp->rq_arg.head[0].iov_base;
-	dlen = rqstp->rq_arg.head[0].iov_len + rqstp->rq_arg.page_len
-		- hdr;
+	hdr = (void*)p - head->iov_base;
+	if (hdr > head->iov_len)
+		return 0;
+	dlen = head->iov_len + rqstp->rq_arg.page_len - hdr;
 
 	/*
 	 * Round the length of the data which was specified up to
@@ -316,7 +322,7 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 		return 0;
 
 	rqstp->rq_vec[0].iov_base = (void*)p;
-	rqstp->rq_vec[0].iov_len = rqstp->rq_arg.head[0].iov_len - hdr;
+	rqstp->rq_vec[0].iov_len = head->iov_len - hdr;
 	v = 0;
 	while (len > rqstp->rq_vec[v].iov_len) {
 		len -= rqstp->rq_vec[v].iov_len;
@@ -330,9 +336,10 @@ nfssvc_decode_writeargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_createargs *args)
+nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_createargs *args = rqstp->rq_argp;
+
 	if (   !(p = decode_fh(p, &args->fh))
 	    || !(p = decode_filename(p, &args->name, &args->len)))
 		return 0;
@@ -342,9 +349,10 @@ nfssvc_decode_createargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_renameargs *args)
+nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_renameargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->ffh))
 	 || !(p = decode_filename(p, &args->fname, &args->flen))
 	 || !(p = decode_fh(p, &args->tfh))
@@ -355,8 +363,10 @@ nfssvc_decode_renameargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readlinkargs *args)
+nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readlinkargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -366,9 +376,10 @@ nfssvc_decode_readlinkargs(struct svc_rqst *rqstp, __be32 *p, struct nfsd_readli
 }
 
 int
-nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_linkargs *args)
+nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_linkargs *args = rqstp->rq_argp;
+
 	if (!(p = decode_fh(p, &args->ffh))
 	 || !(p = decode_fh(p, &args->tfh))
 	 || !(p = decode_filename(p, &args->tname, &args->tlen)))
@@ -378,9 +389,10 @@ nfssvc_decode_linkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_symlinkargs *args)
+nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_symlinkargs *args = rqstp->rq_argp;
+
 	if (   !(p = decode_fh(p, &args->ffh))
 	    || !(p = decode_filename(p, &args->fname, &args->flen))
 	    || !(p = decode_pathname(p, &args->tname, &args->tlen)))
@@ -391,9 +403,10 @@ nfssvc_decode_symlinkargs(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readdirargs *args)
+nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readdirargs *args = rqstp->rq_argp;
+
 	p = decode_fh(p, &args->fh);
 	if (!p)
 		return 0;
@@ -409,32 +422,35 @@ nfssvc_decode_readdirargs(struct svc_rqst *rqstp, __be32 *p,
  * XDR encode functions
  */
 int
-nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p, void *dummy)
+nfssvc_encode_void(struct svc_rqst *rqstp, __be32 *p)
 {
 	return xdr_ressize_check(rqstp, p);
 }
 
 int
-nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_attrstat *resp)
+nfssvc_encode_attrstat(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_attrstat *resp = rqstp->rq_resp;
+
 	p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	return xdr_ressize_check(rqstp, p);
 }
 
 int
-nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_diropres *resp)
+nfssvc_encode_diropres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_diropres *resp = rqstp->rq_resp;
+
 	p = encode_fh(p, &resp->fh);
 	p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	return xdr_ressize_check(rqstp, p);
 }
 
 int
-nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readlinkres *resp)
+nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readlinkres *resp = rqstp->rq_resp;
+
 	*p++ = htonl(resp->len);
 	xdr_ressize_check(rqstp, p);
 	rqstp->rq_res.page_len = resp->len;
@@ -448,9 +464,10 @@ nfssvc_encode_readlinkres(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readres *resp)
+nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readres *resp = rqstp->rq_resp;
+
 	p = encode_fattr(rqstp, p, &resp->fh, &resp->stat);
 	*p++ = htonl(resp->count);
 	xdr_ressize_check(rqstp, p);
@@ -467,9 +484,10 @@ nfssvc_encode_readres(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_readdirres *resp)
+nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_readdirres *resp = rqstp->rq_resp;
+
 	xdr_ressize_check(rqstp, p);
 	p = resp->buffer;
 	*p++ = 0;			/* no more entries */
@@ -480,9 +498,9 @@ nfssvc_encode_readdirres(struct svc_rqst *rqstp, __be32 *p,
 }
 
 int
-nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_statfsres *resp)
+nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p)
 {
+	struct nfsd_statfsres *resp = rqstp->rq_resp;
 	struct kstatfs	*stat = &resp->stats;
 
 	*p++ = htonl(NFSSVC_MAXBLKSIZE_V2);	/* max transfer size */
@@ -541,10 +559,10 @@ nfssvc_encode_entry(void *ccdv, const char *name,
 /*
  * XDR release functions
  */
-int
-nfssvc_release_fhandle(struct svc_rqst *rqstp, __be32 *p,
-					struct nfsd_fhandle *resp)
+void
+nfssvc_release_fhandle(struct svc_rqst *rqstp)
 {
+	struct nfsd_fhandle *resp = rqstp->rq_resp;
+
 	fh_put(&resp->fh);
-	return 1;
 }
diff --git a/fs/nfsd/state.h b/fs/nfsd/state.h
index 4516e8b7d776..005c911b34ac 100644
--- a/fs/nfsd/state.h
+++ b/fs/nfsd/state.h
@@ -615,6 +615,7 @@ extern struct nfs4_client_reclaim *nfsd4_find_reclaim_client(const char *recdir,
 extern __be32 nfs4_check_open_reclaim(clientid_t *clid,
 		struct nfsd4_compound_state *cstate, struct nfsd_net *nn);
 extern int set_callback_cred(void);
+extern void cleanup_callback_cred(void);
 extern void nfsd4_probe_callback(struct nfs4_client *clp);
 extern void nfsd4_probe_callback_sync(struct nfs4_client *clp);
 extern void nfsd4_change_callback(struct nfs4_client *clp, struct nfs4_cb_conn *);
diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c
index ca13236dbb1f..38d0383dc7f9 100644
--- a/fs/nfsd/vfs.c
+++ b/fs/nfsd/vfs.c
@@ -94,6 +94,12 @@ nfsd_cross_mnt(struct svc_rqst *rqstp, struct dentry **dpp,
 	err = follow_down(&path);
 	if (err < 0)
 		goto out;
+	if (path.mnt == exp->ex_path.mnt && path.dentry == dentry &&
+	    nfsd_mountpoint(dentry, exp) == 2) {
+		/* This is only a mountpoint in some other namespace */
+		path_put(&path);
+		goto out;
+	}
 
 	exp2 = rqst_exp_get_by_name(rqstp, &path);
 	if (IS_ERR(exp2)) {
@@ -167,16 +173,26 @@ static int nfsd_lookup_parent(struct svc_rqst *rqstp, struct dentry *dparent, st
 /*
  * For nfsd purposes, we treat V4ROOT exports as though there was an
  * export at *every* directory.
+ * We return:
+ * '1' if this dentry *must* be an export point,
+ * '2' if it might be, if there is really a mount here, and
+ * '0' if there is no chance of an export point here.
  */
 int nfsd_mountpoint(struct dentry *dentry, struct svc_export *exp)
 {
-	if (d_mountpoint(dentry))
+	if (!d_inode(dentry))
+		return 0;
+	if (exp->ex_flags & NFSEXP_V4ROOT)
 		return 1;
 	if (nfsd4_is_junction(dentry))
 		return 1;
-	if (!(exp->ex_flags & NFSEXP_V4ROOT))
-		return 0;
-	return d_inode(dentry) != NULL;
+	if (d_mountpoint(dentry))
+		/*
+		 * Might only be a mountpoint in a different namespace,
+		 * but we need to check.
+		 */
+		return 2;
+	return 0;
 }
 
 __be32
@@ -332,6 +348,37 @@ nfsd_sanitize_attrs(struct inode *inode, struct iattr *iap)
 	}
 }
 
+static __be32
+nfsd_get_write_access(struct svc_rqst *rqstp, struct svc_fh *fhp,
+		struct iattr *iap)
+{
+	struct inode *inode = d_inode(fhp->fh_dentry);
+	int host_err;
+
+	if (iap->ia_size < inode->i_size) {
+		__be32 err;
+
+		err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
+				NFSD_MAY_TRUNC | NFSD_MAY_OWNER_OVERRIDE);
+		if (err)
+			return err;
+	}
+
+	host_err = get_write_access(inode);
+	if (host_err)
+		goto out_nfserrno;
+
+	host_err = locks_verify_truncate(inode, NULL, iap->ia_size);
+	if (host_err)
+		goto out_put_write_access;
+	return 0;
+
+out_put_write_access:
+	put_write_access(inode);
+out_nfserrno:
+	return nfserrno(host_err);
+}
+
 /*
  * Set various file attributes.  After this call fhp needs an fh_put.
  */
@@ -346,6 +393,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	__be32		err;
 	int		host_err;
 	bool		get_write_count;
+	bool		size_change = (iap->ia_valid & ATTR_SIZE);
 
 	if (iap->ia_valid & (ATTR_ATIME | ATTR_MTIME | ATTR_SIZE))
 		accmode |= NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE;
@@ -362,7 +410,7 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	if (get_write_count) {
 		host_err = fh_want_write(fhp);
 		if (host_err)
-			goto out_host_err;
+			goto out;
 	}
 
 	dentry = fhp->fh_dentry;
@@ -384,47 +432,53 @@ nfsd_setattr(struct svc_rqst *rqstp, struct svc_fh *fhp, struct iattr *iap,
 	 * The size case is special, it changes the file in addition to the
 	 * attributes, and file systems don't expect it to be mixed with
 	 * "random" attribute changes.  We thus split out the size change
-	 * into a separate call for vfs_truncate, and do the rest as a
-	 * a separate setattr call.
+	 * into a separate call to ->setattr, and do the rest as a separate
+	 * setattr call.
 	 */
-	if (iap->ia_valid & ATTR_SIZE) {
-		struct path path = {
-			.mnt	= fhp->fh_export->ex_path.mnt,
-			.dentry	= dentry,
-		};
-		bool implicit_mtime = false;
+	if (size_change) {
+		err = nfsd_get_write_access(rqstp, fhp, iap);
+		if (err)
+			return err;
+	}
 
+	fh_lock(fhp);
+	if (size_change) {
 		/*
-		 * vfs_truncate implicity updates the mtime IFF the file size
-		 * actually changes.  Avoid the additional seattr call below if
-		 * the only other attribute that the client sends is the mtime.
+		 * RFC5661, Section 18.30.4:
+		 *   Changing the size of a file with SETATTR indirectly
+		 *   changes the time_modify and change attributes.
+		 *
+		 * (and similar for the older RFCs)
 		 */
-		if (iap->ia_size != i_size_read(inode) &&
-		    ((iap->ia_valid & ~(ATTR_SIZE | ATTR_MTIME)) == 0))
-			implicit_mtime = true;
+		struct iattr size_attr = {
+			.ia_valid	= ATTR_SIZE | ATTR_CTIME | ATTR_MTIME,
+			.ia_size	= iap->ia_size,
+		};
 
-		host_err = vfs_truncate(&path, iap->ia_size);
+		host_err = notify_change(dentry, &size_attr, NULL);
 		if (host_err)
-			goto out_host_err;
-
+			goto out_unlock;
 		iap->ia_valid &= ~ATTR_SIZE;
-		if (implicit_mtime)
-			iap->ia_valid &= ~ATTR_MTIME;
-		if (!iap->ia_valid)
-			goto done;
+
+		/*
+		 * Avoid the additional setattr call below if the only other
+		 * attribute that the client sends is the mtime, as we update
+		 * it as part of the size change above.
+		 */
+		if ((iap->ia_valid & ~ATTR_MTIME) == 0)
+			goto out_unlock;
 	}
 
 	iap->ia_valid |= ATTR_CTIME;
-
-	fh_lock(fhp);
 	host_err = notify_change(dentry, iap, NULL);
-	fh_unlock(fhp);
-	if (host_err)
-		goto out_host_err;
 
-done:
-	host_err = commit_metadata(fhp);
-out_host_err:
+out_unlock:
+	fh_unlock(fhp);
+	if (size_change)
+		put_write_access(inode);
+out:
+	if (!host_err)
+		host_err = commit_metadata(fhp);
 	return nfserrno(host_err);
 }
 
@@ -857,24 +911,13 @@ __be32 nfsd_splice_read(struct svc_rqst *rqstp,
 __be32 nfsd_readv(struct file *file, loff_t offset, struct kvec *vec, int vlen,
 		unsigned long *count)
 {
-	mm_segment_t oldfs;
+	struct iov_iter iter;
 	int host_err;
 
-	oldfs = get_fs();
-	set_fs(KERNEL_DS);
-	host_err = vfs_readv(file, (struct iovec __user *)vec, vlen, &offset, 0);
-	set_fs(oldfs);
-	return nfsd_finish_read(file, count, host_err);
-}
+	iov_iter_kvec(&iter, READ | ITER_KVEC, vec, vlen, *count);
+	host_err = vfs_iter_read(file, &iter, &offset, 0);
 
-static __be32
-nfsd_vfs_read(struct svc_rqst *rqstp, struct file *file,
-	      loff_t offset, struct kvec *vec, int vlen, unsigned long *count)
-{
-	if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags))
-		return nfsd_splice_read(rqstp, file, offset, count);
-	else
-		return nfsd_readv(file, offset, vec, vlen, count);
+	return nfsd_finish_read(file, count, host_err);
 }
 
 /*
@@ -917,14 +960,12 @@ static int wait_for_concurrent_writes(struct file *file)
 __be32
 nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 				loff_t offset, struct kvec *vec, int vlen,
-				unsigned long *cnt, int *stablep)
+				unsigned long *cnt, int stable)
 {
 	struct svc_export	*exp;
-	struct inode		*inode;
-	mm_segment_t		oldfs;
+	struct iov_iter		iter;
 	__be32			err = 0;
 	int			host_err;
-	int			stable = *stablep;
 	int			use_wgather;
 	loff_t			pos = offset;
 	unsigned int		pflags = current->flags;
@@ -939,21 +980,17 @@ nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
 		 */
 		current->flags |= PF_LESS_THROTTLE;
 
-	inode = file_inode(file);
-	exp   = fhp->fh_export;
-
+	exp = fhp->fh_export;
 	use_wgather = (rqstp->rq_vers == 2) && EX_WGATHER(exp);
 
 	if (!EX_ISSYNC(exp))
-		stable = 0;
+		stable = NFS_UNSTABLE;
 
 	if (stable && !use_wgather)
 		flags |= RWF_SYNC;
 
-	/* Write the data. */
-	oldfs = get_fs(); set_fs(KERNEL_DS);
-	host_err = vfs_writev(file, (struct iovec __user *)vec, vlen, &pos, flags);
-	set_fs(oldfs);
+	iov_iter_kvec(&iter, WRITE | ITER_KVEC, vec, vlen, *cnt);
+	host_err = vfs_iter_write(file, &iter, &pos, flags);
 	if (host_err < 0)
 		goto out_nfserr;
 	*cnt = host_err;
@@ -970,7 +1007,7 @@ out_nfserr:
 	else
 		err = nfserrno(host_err);
 	if (test_bit(RQ_LOCAL, &rqstp->rq_flags))
-		tsk_restore_flags(current, pflags, PF_LESS_THROTTLE);
+		current_restore_flags(pflags, PF_LESS_THROTTLE);
 	return err;
 }
 
@@ -994,7 +1031,12 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
 	ra = nfsd_init_raparms(file);
 
 	trace_read_opened(rqstp, fhp, offset, vlen);
-	err = nfsd_vfs_read(rqstp, file, offset, vec, vlen, count);
+
+	if (file->f_op->splice_read && test_bit(RQ_SPLICE_OK, &rqstp->rq_flags))
+		err = nfsd_splice_read(rqstp, file, offset, count);
+	else
+		err = nfsd_readv(file, offset, vec, vlen, count);
+
 	trace_read_io_done(rqstp, fhp, offset, vlen);
 
 	if (ra)
@@ -1012,35 +1054,22 @@ __be32 nfsd_read(struct svc_rqst *rqstp, struct svc_fh *fhp,
  * N.B. After this call fhp needs an fh_put
  */
 __be32
-nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, struct file *file,
-		loff_t offset, struct kvec *vec, int vlen, unsigned long *cnt,
-		int *stablep)
+nfsd_write(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t offset,
+	   struct kvec *vec, int vlen, unsigned long *cnt, int stable)
 {
-	__be32			err = 0;
+	struct file *file = NULL;
+	__be32 err = 0;
 
 	trace_write_start(rqstp, fhp, offset, vlen);
 
-	if (file) {
-		err = nfsd_permission(rqstp, fhp->fh_export, fhp->fh_dentry,
-				NFSD_MAY_WRITE|NFSD_MAY_OWNER_OVERRIDE);
-		if (err)
-			goto out;
-		trace_write_opened(rqstp, fhp, offset, vlen);
-		err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt,
-				stablep);
-		trace_write_io_done(rqstp, fhp, offset, vlen);
-	} else {
-		err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file);
-		if (err)
-			goto out;
+	err = nfsd_open(rqstp, fhp, S_IFREG, NFSD_MAY_WRITE, &file);
+	if (err)
+		goto out;
 
-		trace_write_opened(rqstp, fhp, offset, vlen);
-		if (cnt)
-			err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen,
-					     cnt, stablep);
-		trace_write_io_done(rqstp, fhp, offset, vlen);
-		fput(file);
-	}
+	trace_write_opened(rqstp, fhp, offset, vlen);
+	err = nfsd_vfs_write(rqstp, fhp, file, offset, vec, vlen, cnt, stable);
+	trace_write_io_done(rqstp, fhp, offset, vlen);
+	fput(file);
 out:
 	trace_write_done(rqstp, fhp, offset, vlen);
 	return err;
@@ -1427,41 +1456,34 @@ do_nfsd_create(struct svc_rqst *rqstp, struct svc_fh *fhp,
 __be32
 nfsd_readlink(struct svc_rqst *rqstp, struct svc_fh *fhp, char *buf, int *lenp)
 {
-	mm_segment_t	oldfs;
 	__be32		err;
-	int		host_err;
+	const char *link;
 	struct path path;
+	DEFINE_DELAYED_CALL(done);
+	int len;
 
 	err = fh_verify(rqstp, fhp, S_IFLNK, NFSD_MAY_NOP);
-	if (err)
-		goto out;
+	if (unlikely(err))
+		return err;
 
 	path.mnt = fhp->fh_export->ex_path.mnt;
 	path.dentry = fhp->fh_dentry;
 
-	err = nfserr_inval;
-	if (!d_is_symlink(path.dentry))
-		goto out;
+	if (unlikely(!d_is_symlink(path.dentry)))
+		return nfserr_inval;
 
 	touch_atime(&path);
-	/* N.B. Why does this call need a get_fs()??
-	 * Remove the set_fs and watch the fireworks:-) --okir
-	 */
 
-	oldfs = get_fs(); set_fs(KERNEL_DS);
-	host_err = vfs_readlink(path.dentry, (char __user *)buf, *lenp);
-	set_fs(oldfs);
+	link = vfs_get_link(path.dentry, &done);
+	if (IS_ERR(link))
+		return nfserrno(PTR_ERR(link));
 
-	if (host_err < 0)
-		goto out_nfserr;
-	*lenp = host_err;
-	err = 0;
-out:
-	return err;
-
-out_nfserr:
-	err = nfserrno(host_err);
-	goto out;
+	len = strlen(link);
+	if (len < *lenp)
+		*lenp = len;
+	memcpy(buf, link, *lenp);
+	do_delayed_call(&done);
+	return 0;
 }
 
 /*
diff --git a/fs/nfsd/vfs.h b/fs/nfsd/vfs.h
index 0bf9e7bf5800..1bbdccecbf3d 100644
--- a/fs/nfsd/vfs.h
+++ b/fs/nfsd/vfs.h
@@ -83,12 +83,12 @@ __be32		nfsd_readv(struct file *, loff_t, struct kvec *, int,
 				unsigned long *);
 __be32 		nfsd_read(struct svc_rqst *, struct svc_fh *,
 				loff_t, struct kvec *, int, unsigned long *);
-__be32 		nfsd_write(struct svc_rqst *, struct svc_fh *,struct file *,
-				loff_t, struct kvec *,int, unsigned long *, int *);
+__be32 		nfsd_write(struct svc_rqst *, struct svc_fh *, loff_t,
+				struct kvec *, int, unsigned long *, int);
 __be32		nfsd_vfs_write(struct svc_rqst *rqstp, struct svc_fh *fhp,
 				struct file *file, loff_t offset,
 				struct kvec *vec, int vlen, unsigned long *cnt,
-				int *stablep);
+				int stable);
 __be32		nfsd_readlink(struct svc_rqst *, struct svc_fh *,
 				char *, int *);
 __be32		nfsd_symlink(struct svc_rqst *, struct svc_fh *,
@@ -135,7 +135,8 @@ static inline __be32 fh_getattr(struct svc_fh *fh, struct kstat *stat)
 {
 	struct path p = {.mnt = fh->fh_export->ex_path.mnt,
 			 .dentry = fh->fh_dentry};
-	return nfserrno(vfs_getattr(&p, stat));
+	return nfserrno(vfs_getattr(&p, stat, STATX_BASIC_STATS,
+				    AT_STATX_SYNC_AS_STAT));
 }
 
 static inline int nfsd_create_is_exclusive(int createmode)
diff --git a/fs/nfsd/xdr.h b/fs/nfsd/xdr.h
index 4f0481d63804..457ce45e5084 100644
--- a/fs/nfsd/xdr.h
+++ b/fs/nfsd/xdr.h
@@ -131,40 +131,30 @@ union nfsd_xdrstore {
 #define NFS2_SVC_XDRSIZE	sizeof(union nfsd_xdrstore)
 
 
-int nfssvc_decode_void(struct svc_rqst *, __be32 *, void *);
-int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
-int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *,
-				struct nfsd_sattrargs *);
-int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *,
-				struct nfsd_diropargs *);
-int nfssvc_decode_readargs(struct svc_rqst *, __be32 *,
-				struct nfsd_readargs *);
-int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *,
-				struct nfsd_writeargs *);
-int nfssvc_decode_createargs(struct svc_rqst *, __be32 *,
-				struct nfsd_createargs *);
-int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *,
-				struct nfsd_renameargs *);
-int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *,
-				struct nfsd_readlinkargs *);
-int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *,
-				struct nfsd_linkargs *);
-int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *,
-				struct nfsd_symlinkargs *);
-int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *,
-				struct nfsd_readdirargs *);
-int nfssvc_encode_void(struct svc_rqst *, __be32 *, void *);
-int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *, struct nfsd_attrstat *);
-int nfssvc_encode_diropres(struct svc_rqst *, __be32 *, struct nfsd_diropres *);
-int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *, struct nfsd_readlinkres *);
-int nfssvc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd_readres *);
-int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *, struct nfsd_statfsres *);
-int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *, struct nfsd_readdirres *);
+int nfssvc_decode_void(struct svc_rqst *, __be32 *);
+int nfssvc_decode_fhandle(struct svc_rqst *, __be32 *);
+int nfssvc_decode_sattrargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_diropargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_readargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_writeargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_createargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_renameargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_readlinkargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_linkargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_symlinkargs(struct svc_rqst *, __be32 *);
+int nfssvc_decode_readdirargs(struct svc_rqst *, __be32 *);
+int nfssvc_encode_void(struct svc_rqst *, __be32 *);
+int nfssvc_encode_attrstat(struct svc_rqst *, __be32 *);
+int nfssvc_encode_diropres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_readlinkres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_readres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_statfsres(struct svc_rqst *, __be32 *);
+int nfssvc_encode_readdirres(struct svc_rqst *, __be32 *);
 
 int nfssvc_encode_entry(void *, const char *name,
 			int namlen, loff_t offset, u64 ino, unsigned int);
 
-int nfssvc_release_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
+void nfssvc_release_fhandle(struct svc_rqst *);
 
 /* Helper functions for NFSv2 ACL code */
 __be32 *nfs2svc_encode_fattr(struct svc_rqst *rqstp, __be32 *p, struct svc_fh *fhp, struct kstat *stat);
diff --git a/fs/nfsd/xdr3.h b/fs/nfsd/xdr3.h
index 335e04aaf7db..80d7da620e91 100644
--- a/fs/nfsd/xdr3.h
+++ b/fs/nfsd/xdr3.h
@@ -269,71 +269,41 @@ union nfsd3_xdrstore {
 
 #define NFS3_SVC_XDRSIZE		sizeof(union nfsd3_xdrstore)
 
-int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *, struct nfsd_fhandle *);
-int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_sattrargs *);
-int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_diropargs *);
-int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_accessargs *);
-int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_readargs *);
-int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_writeargs *);
-int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_createargs *);
-int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_createargs *);
-int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_mknodargs *);
-int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_renameargs *);
-int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_readlinkargs *);
-int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_linkargs *);
-int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_symlinkargs *);
-int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_readdirargs *);
-int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_readdirargs *);
-int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *,
-				struct nfsd3_commitargs *);
-int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
-int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *,
-				struct nfsd3_attrstat *);
-int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *,
-				struct nfsd3_attrstat *);
-int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *,
-				struct nfsd3_diropres *);
-int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *,
-				struct nfsd3_accessres *);
-int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *,
-				struct nfsd3_readlinkres *);
-int nfs3svc_encode_readres(struct svc_rqst *, __be32 *, struct nfsd3_readres *);
-int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *, struct nfsd3_writeres *);
-int nfs3svc_encode_createres(struct svc_rqst *, __be32 *,
-				struct nfsd3_diropres *);
-int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *,
-				struct nfsd3_renameres *);
-int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *,
-				struct nfsd3_linkres *);
-int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *,
-				struct nfsd3_readdirres *);
-int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *,
-				struct nfsd3_fsstatres *);
-int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *,
-				struct nfsd3_fsinfores *);
-int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *,
-				struct nfsd3_pathconfres *);
-int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *,
-				struct nfsd3_commitres *);
-
-int nfs3svc_release_fhandle(struct svc_rqst *, __be32 *,
-				struct nfsd3_attrstat *);
-int nfs3svc_release_fhandle2(struct svc_rqst *, __be32 *,
-				struct nfsd3_fhandle_pair *);
+int nfs3svc_decode_fhandle(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_sattrargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_diropargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_accessargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_readargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_writeargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_createargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_mkdirargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_mknodargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_renameargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_readlinkargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_linkargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_symlinkargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_readdirargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_readdirplusargs(struct svc_rqst *, __be32 *);
+int nfs3svc_decode_commitargs(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_voidres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_attrstat(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_wccstat(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_diropres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_accessres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_readlinkres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_readres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_writeres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_createres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_renameres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_linkres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_readdirres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_fsstatres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_fsinfores(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_pathconfres(struct svc_rqst *, __be32 *);
+int nfs3svc_encode_commitres(struct svc_rqst *, __be32 *);
+
+void nfs3svc_release_fhandle(struct svc_rqst *);
+void nfs3svc_release_fhandle2(struct svc_rqst *);
 int nfs3svc_encode_entry(void *, const char *name,
 				int namlen, loff_t offset, u64 ino,
 				unsigned int);
diff --git a/fs/nfsd/xdr4.h b/fs/nfsd/xdr4.h
index 8fda4abdf3b1..72c6ad136107 100644
--- a/fs/nfsd/xdr4.h
+++ b/fs/nfsd/xdr4.h
@@ -539,7 +539,7 @@ struct nfsd4_seek {
 struct nfsd4_op {
 	int					opnum;
 	__be32					status;
-	union {
+	union nfsd4_op_u {
 		struct nfsd4_access		access;
 		struct nfsd4_close		close;
 		struct nfsd4_commit		commit;
@@ -577,6 +577,7 @@ struct nfsd4_op {
 		struct nfsd4_bind_conn_to_session bind_conn_to_session;
 		struct nfsd4_create_session	create_session;
 		struct nfsd4_destroy_session	destroy_session;
+		struct nfsd4_destroy_clientid	destroy_clientid;
 		struct nfsd4_sequence		sequence;
 		struct nfsd4_reclaim_complete	reclaim_complete;
 		struct nfsd4_test_stateid	test_stateid;
@@ -585,6 +586,7 @@ struct nfsd4_op {
 		struct nfsd4_layoutget		layoutget;
 		struct nfsd4_layoutcommit	layoutcommit;
 		struct nfsd4_layoutreturn	layoutreturn;
+		struct nfsd4_secinfo_no_name	secinfo_no_name;
 
 		/* NFSv4.2 */
 		struct nfsd4_fallocate		allocate;
@@ -682,11 +684,9 @@ set_change_info(struct nfsd4_change_info *cinfo, struct svc_fh *fhp)
 
 
 bool nfsd4_mach_creds_match(struct nfs4_client *cl, struct svc_rqst *rqstp);
-int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *, void *);
-int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *,
-		struct nfsd4_compoundargs *);
-int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *,
-		struct nfsd4_compoundres *);
+int nfs4svc_encode_voidres(struct svc_rqst *, __be32 *);
+int nfs4svc_decode_compoundargs(struct svc_rqst *, __be32 *);
+int nfs4svc_encode_compoundres(struct svc_rqst *, __be32 *);
 __be32 nfsd4_check_resp_size(struct nfsd4_compoundres *, u32);
 void nfsd4_encode_operation(struct nfsd4_compoundres *, struct nfsd4_op *);
 void nfsd4_encode_replay(struct xdr_stream *xdr, struct nfsd4_op *op);
@@ -695,27 +695,26 @@ __be32 nfsd4_encode_fattr_to_buf(__be32 **p, int words,
 		struct dentry *dentry,
 		u32 *bmval, struct svc_rqst *, int ignore_crossmnt);
 extern __be32 nfsd4_setclientid(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *,
-		struct nfsd4_setclientid *setclid);
+		struct nfsd4_compound_state *, union nfsd4_op_u *u);
 extern __be32 nfsd4_setclientid_confirm(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *,
-		struct nfsd4_setclientid_confirm *setclientid_confirm);
+		struct nfsd4_compound_state *, union nfsd4_op_u *u);
 extern __be32 nfsd4_exchange_id(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *, struct nfsd4_exchange_id *);
-extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_backchannel_ctl *);
-extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_bind_conn_to_session *);
+		struct nfsd4_compound_state *, union nfsd4_op_u *u);
+extern __be32 nfsd4_backchannel_ctl(struct svc_rqst *,
+		struct nfsd4_compound_state *, union nfsd4_op_u *u);
+extern __be32 nfsd4_bind_conn_to_session(struct svc_rqst *,
+		struct nfsd4_compound_state *, union nfsd4_op_u *u);
 extern __be32 nfsd4_create_session(struct svc_rqst *,
-		struct nfsd4_compound_state *,
-		struct nfsd4_create_session *);
+		struct nfsd4_compound_state *, union nfsd4_op_u *u);
 extern __be32 nfsd4_sequence(struct svc_rqst *,
-		struct nfsd4_compound_state *,
-		struct nfsd4_sequence *);
+		struct nfsd4_compound_state *, union nfsd4_op_u *u);
 extern void nfsd4_sequence_done(struct nfsd4_compoundres *resp);
 extern __be32 nfsd4_destroy_session(struct svc_rqst *,
-		struct nfsd4_compound_state *,
-		struct nfsd4_destroy_session *);
-extern __be32 nfsd4_destroy_clientid(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_destroy_clientid *);
-__be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *, struct nfsd4_reclaim_complete *);
+		struct nfsd4_compound_state *, union nfsd4_op_u *u);
+extern __be32 nfsd4_destroy_clientid(struct svc_rqst *, struct nfsd4_compound_state *,
+		union nfsd4_op_u *u);
+__be32 nfsd4_reclaim_complete(struct svc_rqst *, struct nfsd4_compound_state *,
+		union nfsd4_op_u *u);
 extern __be32 nfsd4_process_open1(struct nfsd4_compound_state *,
 		struct nfsd4_open *open, struct nfsd_net *nn);
 extern __be32 nfsd4_process_open2(struct svc_rqst *rqstp,
@@ -724,34 +723,29 @@ extern void nfsd4_cstate_clear_replay(struct nfsd4_compound_state *cstate);
 extern void nfsd4_cleanup_open_state(struct nfsd4_compound_state *cstate,
 		struct nfsd4_open *open);
 extern __be32 nfsd4_open_confirm(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *, struct nfsd4_open_confirm *oc);
-extern __be32 nfsd4_close(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *,
-		struct nfsd4_close *close);
+		struct nfsd4_compound_state *, union nfsd4_op_u *u);
+extern __be32 nfsd4_close(struct svc_rqst *rqstp, struct nfsd4_compound_state *,
+		union nfsd4_op_u *u);
 extern __be32 nfsd4_open_downgrade(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *,
-		struct nfsd4_open_downgrade *od);
+		struct nfsd4_compound_state *, union nfsd4_op_u *u);
 extern __be32 nfsd4_lock(struct svc_rqst *rqstp, struct nfsd4_compound_state *,
-		struct nfsd4_lock *lock);
-extern __be32 nfsd4_lockt(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *,
-		struct nfsd4_lockt *lockt);
-extern __be32 nfsd4_locku(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *,
-		struct nfsd4_locku *locku);
+		union nfsd4_op_u *u);
+extern __be32 nfsd4_lockt(struct svc_rqst *rqstp, struct nfsd4_compound_state *,
+		union nfsd4_op_u *u);
+extern __be32 nfsd4_locku(struct svc_rqst *rqstp, struct nfsd4_compound_state *,
+		union nfsd4_op_u *u);
 extern __be32
 nfsd4_release_lockowner(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *,
-		struct nfsd4_release_lockowner *rlockowner);
-extern int nfsd4_release_compoundargs(void *rq, __be32 *p, void *resp);
+		struct nfsd4_compound_state *, union nfsd4_op_u *u);
+extern void nfsd4_release_compoundargs(struct svc_rqst *rqstp);
 extern __be32 nfsd4_delegreturn(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *, struct nfsd4_delegreturn *dr);
-extern __be32 nfsd4_renew(struct svc_rqst *rqstp,
-			  struct nfsd4_compound_state *, clientid_t *clid);
+		struct nfsd4_compound_state *, union nfsd4_op_u *u);
+extern __be32 nfsd4_renew(struct svc_rqst *rqstp, struct nfsd4_compound_state *,
+		union nfsd4_op_u *u);
 extern __be32 nfsd4_test_stateid(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *, struct nfsd4_test_stateid *test_stateid);
+		struct nfsd4_compound_state *, union nfsd4_op_u *);
 extern __be32 nfsd4_free_stateid(struct svc_rqst *rqstp,
-		struct nfsd4_compound_state *, struct nfsd4_free_stateid *free_stateid);
+		struct nfsd4_compound_state *, union nfsd4_op_u *);
 extern void nfsd4_bump_seqid(struct nfsd4_compound_state *, __be32 nfserr);
 
 #endif
diff --git a/fs/nilfs2/alloc.c b/fs/nilfs2/alloc.c
index 2c90e285d7c6..03b8ba933eb2 100644
--- a/fs/nilfs2/alloc.c
+++ b/fs/nilfs2/alloc.c
@@ -34,7 +34,7 @@
 static inline unsigned long
 nilfs_palloc_groups_per_desc_block(const struct inode *inode)
 {
-	return (1UL << inode->i_blkbits) /
+	return i_blocksize(inode) /
 		sizeof(struct nilfs_palloc_group_desc);
 }
 
diff --git a/fs/nilfs2/btnode.c b/fs/nilfs2/btnode.c
index d5c23da43513..c21e0b4454a6 100644
--- a/fs/nilfs2/btnode.c
+++ b/fs/nilfs2/btnode.c
@@ -50,7 +50,7 @@ nilfs_btnode_create_block(struct address_space *btnc, __u64 blocknr)
 		brelse(bh);
 		BUG();
 	}
-	memset(bh->b_data, 0, 1 << inode->i_blkbits);
+	memset(bh->b_data, 0, i_blocksize(inode));
 	bh->b_bdev = inode->i_sb->s_bdev;
 	bh->b_blocknr = blocknr;
 	set_buffer_mapped(bh);
diff --git a/fs/nilfs2/btree.c b/fs/nilfs2/btree.c
index 2e315f9f2e51..06ffa135dfa6 100644
--- a/fs/nilfs2/btree.c
+++ b/fs/nilfs2/btree.c
@@ -119,7 +119,7 @@ nilfs_btree_node_set_nchildren(struct nilfs_btree_node *node, int nchildren)
 
 static int nilfs_btree_node_size(const struct nilfs_bmap *btree)
 {
-	return 1 << btree->b_inode->i_blkbits;
+	return i_blocksize(btree->b_inode);
 }
 
 static int nilfs_btree_nchildren_per_block(const struct nilfs_bmap *btree)
@@ -1870,7 +1870,7 @@ int nilfs_btree_convert_and_insert(struct nilfs_bmap *btree,
 		di = &dreq;
 		ni = NULL;
 	} else if ((n + 1) <= NILFS_BTREE_NODE_NCHILDREN_MAX(
-			   1 << btree->b_inode->i_blkbits)) {
+			   nilfs_btree_node_size(btree))) {
 		di = &dreq;
 		ni = &nreq;
 	} else {
diff --git a/fs/nilfs2/file.c b/fs/nilfs2/file.c
index 547381f3ce13..c5fa3dee72fc 100644
--- a/fs/nilfs2/file.c
+++ b/fs/nilfs2/file.c
@@ -51,8 +51,9 @@ int nilfs_sync_file(struct file *file, loff_t start, loff_t end, int datasync)
 	return err;
 }
 
-static int nilfs_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int nilfs_page_mkwrite(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	struct page *page = vmf->page;
 	struct inode *inode = file_inode(vma->vm_file);
 	struct nilfs_transaction_info ti;
diff --git a/fs/nilfs2/inode.c b/fs/nilfs2/inode.c
index c7f4fef9ebf5..7ffe71a8dfb9 100644
--- a/fs/nilfs2/inode.c
+++ b/fs/nilfs2/inode.c
@@ -51,7 +51,7 @@ void nilfs_inode_add_blocks(struct inode *inode, int n)
 {
 	struct nilfs_root *root = NILFS_I(inode)->i_root;
 
-	inode_add_bytes(inode, (1 << inode->i_blkbits) * n);
+	inode_add_bytes(inode, i_blocksize(inode) * n);
 	if (root)
 		atomic64_add(n, &root->blocks_count);
 }
@@ -60,7 +60,7 @@ void nilfs_inode_sub_blocks(struct inode *inode, int n)
 {
 	struct nilfs_root *root = NILFS_I(inode)->i_root;
 
-	inode_sub_bytes(inode, (1 << inode->i_blkbits) * n);
+	inode_sub_bytes(inode, i_blocksize(inode) * n);
 	if (root)
 		atomic64_sub(n, &root->blocks_count);
 }
diff --git a/fs/nilfs2/mdt.c b/fs/nilfs2/mdt.c
index d56d3a5bea88..98835ed6bef4 100644
--- a/fs/nilfs2/mdt.c
+++ b/fs/nilfs2/mdt.c
@@ -57,7 +57,7 @@ nilfs_mdt_insert_new_block(struct inode *inode, unsigned long block,
 	set_buffer_mapped(bh);
 
 	kaddr = kmap_atomic(bh->b_page);
-	memset(kaddr + bh_offset(bh), 0, 1 << inode->i_blkbits);
+	memset(kaddr + bh_offset(bh), 0, i_blocksize(inode));
 	if (init_block)
 		init_block(inode, bh, kaddr);
 	flush_dcache_page(bh->b_page);
@@ -501,7 +501,7 @@ void nilfs_mdt_set_entry_size(struct inode *inode, unsigned int entry_size,
 	struct nilfs_mdt_info *mi = NILFS_MDT(inode);
 
 	mi->mi_entry_size = entry_size;
-	mi->mi_entries_per_block = (1 << inode->i_blkbits) / entry_size;
+	mi->mi_entries_per_block = i_blocksize(inode) / entry_size;
 	mi->mi_first_entry_offset = DIV_ROUND_UP(header_size, entry_size);
 }
 
diff --git a/fs/nilfs2/segbuf.c b/fs/nilfs2/segbuf.c
index 6f87b2ac1aeb..e73c86d9855c 100644
--- a/fs/nilfs2/segbuf.c
+++ b/fs/nilfs2/segbuf.c
@@ -338,7 +338,7 @@ static void nilfs_end_bio_write(struct bio *bio)
 {
 	struct nilfs_segment_buffer *segbuf = bio->bi_private;
 
-	if (bio->bi_error)
+	if (bio->bi_status)
 		atomic_inc(&segbuf->sb_err);
 
 	bio_put(bio);
diff --git a/fs/nilfs2/segment.c b/fs/nilfs2/segment.c
index bedcae2c28e6..70ded52dc1dd 100644
--- a/fs/nilfs2/segment.c
+++ b/fs/nilfs2/segment.c
@@ -30,6 +30,8 @@
 #include <linux/crc32.h>
 #include <linux/pagevec.h>
 #include <linux/slab.h>
+#include <linux/sched/signal.h>
+
 #include "nilfs.h"
 #include "btnode.h"
 #include "page.h"
@@ -723,7 +725,7 @@ static size_t nilfs_lookup_dirty_data_buffers(struct inode *inode,
 
 		lock_page(page);
 		if (!page_has_buffers(page))
-			create_empty_buffers(page, 1 << inode->i_blkbits, 0);
+			create_empty_buffers(page, i_blocksize(inode), 0);
 		unlock_page(page);
 
 		bh = head = page_buffers(page);
@@ -2159,7 +2161,7 @@ void nilfs_flush_segment(struct super_block *sb, ino_t ino)
 }
 
 struct nilfs_segctor_wait_request {
-	wait_queue_t	wq;
+	wait_queue_entry_t	wq;
 	__u32		seq;
 	int		err;
 	atomic_t	done;
@@ -2204,8 +2206,7 @@ static void nilfs_segctor_wakeup(struct nilfs_sc_info *sci, int err)
 	unsigned long flags;
 
 	spin_lock_irqsave(&sci->sc_wait_request.lock, flags);
-	list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.task_list,
-				 wq.task_list) {
+	list_for_each_entry_safe(wrq, n, &sci->sc_wait_request.head, wq.entry) {
 		if (!atomic_read(&wrq->done) &&
 		    nilfs_cnt32_ge(sci->sc_seq_done, wrq->seq)) {
 			wrq->err = err;
diff --git a/fs/nilfs2/super.c b/fs/nilfs2/super.c
index 12eeae62a2b1..926682981d61 100644
--- a/fs/nilfs2/super.c
+++ b/fs/nilfs2/super.c
@@ -1068,7 +1068,7 @@ nilfs_fill_super(struct super_block *sb, void *data, int silent)
 	sb->s_time_gran = 1;
 	sb->s_max_links = NILFS_LINK_MAX;
 
-	sb->s_bdi = &bdev_get_queue(sb->s_bdev)->backing_dev_info;
+	sb->s_bdi = bdi_get(sb->s_bdev->bd_bdi);
 
 	err = load_nilfs(nilfs, sb);
 	if (err)
diff --git a/fs/notify/Makefile b/fs/notify/Makefile
index 96d3420d0242..3e969ae91b60 100644
--- a/fs/notify/Makefile
+++ b/fs/notify/Makefile
@@ -1,5 +1,5 @@
-obj-$(CONFIG_FSNOTIFY)		+= fsnotify.o notification.o group.o inode_mark.o \
-				   mark.o vfsmount_mark.o fdinfo.o
+obj-$(CONFIG_FSNOTIFY)		+= fsnotify.o notification.o group.o mark.o \
+				   fdinfo.o
 
 obj-y			+= dnotify/
 obj-y			+= inotify/
diff --git a/fs/notify/dnotify/dnotify.c b/fs/notify/dnotify/dnotify.c
index 5a4ec309e283..2430a0415995 100644
--- a/fs/notify/dnotify/dnotify.c
+++ b/fs/notify/dnotify/dnotify.c
@@ -52,7 +52,7 @@ struct dnotify_mark {
  */
 static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
 {
-	__u32 new_mask, old_mask;
+	__u32 new_mask = 0;
 	struct dnotify_struct *dn;
 	struct dnotify_mark *dn_mark  = container_of(fsn_mark,
 						     struct dnotify_mark,
@@ -60,17 +60,13 @@ static void dnotify_recalc_inode_mask(struct fsnotify_mark *fsn_mark)
 
 	assert_spin_locked(&fsn_mark->lock);
 
-	old_mask = fsn_mark->mask;
-	new_mask = 0;
 	for (dn = dn_mark->dn; dn != NULL; dn = dn->dn_next)
 		new_mask |= (dn->dn_mask & ~FS_DN_MULTISHOT);
-	fsnotify_set_mark_mask_locked(fsn_mark, new_mask);
-
-	if (old_mask == new_mask)
+	if (fsn_mark->mask == new_mask)
 		return;
+	fsn_mark->mask = new_mask;
 
-	if (fsn_mark->inode)
-		fsnotify_recalc_inode_mask(fsn_mark->inode);
+	fsnotify_recalc_mask(fsn_mark->connector);
 }
 
 /*
@@ -86,7 +82,8 @@ static int dnotify_handle_event(struct fsnotify_group *group,
 				struct fsnotify_mark *inode_mark,
 				struct fsnotify_mark *vfsmount_mark,
 				u32 mask, const void *data, int data_type,
-				const unsigned char *file_name, u32 cookie)
+				const unsigned char *file_name, u32 cookie,
+				struct fsnotify_iter_info *iter_info)
 {
 	struct dnotify_mark *dn_mark;
 	struct dnotify_struct *dn;
@@ -138,6 +135,7 @@ static void dnotify_free_mark(struct fsnotify_mark *fsn_mark)
 
 static struct fsnotify_ops dnotify_fsnotify_ops = {
 	.handle_event = dnotify_handle_event,
+	.free_mark = dnotify_free_mark,
 };
 
 /*
@@ -160,7 +158,7 @@ void dnotify_flush(struct file *filp, fl_owner_t id)
 	if (!S_ISDIR(inode->i_mode))
 		return;
 
-	fsn_mark = fsnotify_find_inode_mark(dnotify_group, inode);
+	fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group);
 	if (!fsn_mark)
 		return;
 	dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
@@ -308,7 +306,7 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
 
 	/* set up the new_fsn_mark and new_dn_mark */
 	new_fsn_mark = &new_dn_mark->fsn_mark;
-	fsnotify_init_mark(new_fsn_mark, dnotify_free_mark);
+	fsnotify_init_mark(new_fsn_mark, dnotify_group);
 	new_fsn_mark->mask = mask;
 	new_dn_mark->dn = NULL;
 
@@ -316,13 +314,12 @@ int fcntl_dirnotify(int fd, struct file *filp, unsigned long arg)
 	mutex_lock(&dnotify_group->mark_mutex);
 
 	/* add the new_fsn_mark or find an old one. */
-	fsn_mark = fsnotify_find_inode_mark(dnotify_group, inode);
+	fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, dnotify_group);
 	if (fsn_mark) {
 		dn_mark = container_of(fsn_mark, struct dnotify_mark, fsn_mark);
 		spin_lock(&fsn_mark->lock);
 	} else {
-		fsnotify_add_mark_locked(new_fsn_mark, dnotify_group, inode,
-					 NULL, 0);
+		fsnotify_add_mark_locked(new_fsn_mark, inode, NULL, 0);
 		spin_lock(&new_fsn_mark->lock);
 		fsn_mark = new_fsn_mark;
 		dn_mark = new_dn_mark;
diff --git a/fs/notify/fanotify/fanotify.c b/fs/notify/fanotify/fanotify.c
index bbc175d4213d..2fa99aeaa095 100644
--- a/fs/notify/fanotify/fanotify.c
+++ b/fs/notify/fanotify/fanotify.c
@@ -6,6 +6,7 @@
 #include <linux/kernel.h> /* UINT_MAX */
 #include <linux/mount.h>
 #include <linux/sched.h>
+#include <linux/sched/user.h>
 #include <linux/types.h>
 #include <linux/wait.h>
 
@@ -31,7 +32,6 @@ static bool should_merge(struct fsnotify_event *old_fsn,
 static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
 {
 	struct fsnotify_event *test_event;
-	bool do_merge = false;
 
 	pr_debug("%s: list=%p event=%p\n", __func__, list, event);
 
@@ -47,28 +47,36 @@ static int fanotify_merge(struct list_head *list, struct fsnotify_event *event)
 
 	list_for_each_entry_reverse(test_event, list, list) {
 		if (should_merge(test_event, event)) {
-			do_merge = true;
-			break;
+			test_event->mask |= event->mask;
+			return 1;
 		}
 	}
 
-	if (!do_merge)
-		return 0;
-
-	test_event->mask |= event->mask;
-	return 1;
+	return 0;
 }
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 static int fanotify_get_response(struct fsnotify_group *group,
-				 struct fanotify_perm_event_info *event)
+				 struct fanotify_perm_event_info *event,
+				 struct fsnotify_iter_info *iter_info)
 {
 	int ret;
 
 	pr_debug("%s: group=%p event=%p\n", __func__, group, event);
 
+	/*
+	 * fsnotify_prepare_user_wait() fails if we race with mark deletion.
+	 * Just let the operation pass in that case.
+	 */
+	if (!fsnotify_prepare_user_wait(iter_info)) {
+		event->response = FAN_ALLOW;
+		goto out;
+	}
+
 	wait_event(group->fanotify_data.access_waitq, event->response);
 
+	fsnotify_finish_user_wait(iter_info);
+out:
 	/* userspace responded, convert to something usable */
 	switch (event->response) {
 	case FAN_ALLOW:
@@ -178,7 +186,8 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 				 struct fsnotify_mark *inode_mark,
 				 struct fsnotify_mark *fanotify_mark,
 				 u32 mask, const void *data, int data_type,
-				 const unsigned char *file_name, u32 cookie)
+				 const unsigned char *file_name, u32 cookie,
+				 struct fsnotify_iter_info *iter_info)
 {
 	int ret = 0;
 	struct fanotify_event_info *event;
@@ -219,7 +228,8 @@ static int fanotify_handle_event(struct fsnotify_group *group,
 
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
 	if (mask & FAN_ALL_PERM_EVENTS) {
-		ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event));
+		ret = fanotify_get_response(group, FANOTIFY_PE(fsn_event),
+					    iter_info);
 		fsnotify_destroy_event(group, fsn_event);
 	}
 #endif
@@ -252,8 +262,14 @@ static void fanotify_free_event(struct fsnotify_event *fsn_event)
 	kmem_cache_free(fanotify_event_cachep, event);
 }
 
+static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
+{
+	kmem_cache_free(fanotify_mark_cache, fsn_mark);
+}
+
 const struct fsnotify_ops fanotify_fsnotify_ops = {
 	.handle_event = fanotify_handle_event,
 	.free_group_priv = fanotify_free_group_priv,
 	.free_event = fanotify_free_event,
+	.free_mark = fanotify_free_mark,
 };
diff --git a/fs/notify/fanotify/fanotify.h b/fs/notify/fanotify/fanotify.h
index 4500a74f8d38..4eb6f5efa282 100644
--- a/fs/notify/fanotify/fanotify.h
+++ b/fs/notify/fanotify/fanotify.h
@@ -2,6 +2,7 @@
 #include <linux/path.h>
 #include <linux/slab.h>
 
+extern struct kmem_cache *fanotify_mark_cache;
 extern struct kmem_cache *fanotify_event_cachep;
 extern struct kmem_cache *fanotify_perm_event_cachep;
 
diff --git a/fs/notify/fanotify/fanotify_user.c b/fs/notify/fanotify/fanotify_user.c
index 7ebfca6a1427..907a481ac781 100644
--- a/fs/notify/fanotify/fanotify_user.c
+++ b/fs/notify/fanotify/fanotify_user.c
@@ -14,6 +14,7 @@
 #include <linux/types.h>
 #include <linux/uaccess.h>
 #include <linux/compat.h>
+#include <linux/sched/signal.h>
 
 #include <asm/ioctls.h>
 
@@ -40,7 +41,7 @@
 
 extern const struct fsnotify_ops fanotify_fsnotify_ops;
 
-static struct kmem_cache *fanotify_mark_cache __read_mostly;
+struct kmem_cache *fanotify_mark_cache __read_mostly;
 struct kmem_cache *fanotify_event_cachep __read_mostly;
 struct kmem_cache *fanotify_perm_event_cachep __read_mostly;
 
@@ -294,27 +295,37 @@ static ssize_t fanotify_read(struct file *file, char __user *buf,
 		}
 
 		ret = copy_event_to_user(group, kevent, buf);
+		if (unlikely(ret == -EOPENSTALE)) {
+			/*
+			 * We cannot report events with stale fd so drop it.
+			 * Setting ret to 0 will continue the event loop and
+			 * do the right thing if there are no more events to
+			 * read (i.e. return bytes read, -EAGAIN or wait).
+			 */
+			ret = 0;
+		}
+
 		/*
 		 * Permission events get queued to wait for response.  Other
 		 * events can be destroyed now.
 		 */
 		if (!(kevent->mask & FAN_ALL_PERM_EVENTS)) {
 			fsnotify_destroy_event(group, kevent);
-			if (ret < 0)
-				break;
 		} else {
 #ifdef CONFIG_FANOTIFY_ACCESS_PERMISSIONS
-			if (ret < 0) {
+			if (ret <= 0) {
 				FANOTIFY_PE(kevent)->response = FAN_DENY;
 				wake_up(&group->fanotify_data.access_waitq);
-				break;
+			} else {
+				spin_lock(&group->notification_lock);
+				list_add_tail(&kevent->list,
+					&group->fanotify_data.access_list);
+				spin_unlock(&group->notification_lock);
 			}
-			spin_lock(&group->notification_lock);
-			list_add_tail(&kevent->list,
-				      &group->fanotify_data.access_list);
-			spin_unlock(&group->notification_lock);
 #endif
 		}
+		if (ret < 0)
+			break;
 		buf += ret;
 		count -= ret;
 	}
@@ -444,11 +455,6 @@ static const struct file_operations fanotify_fops = {
 	.llseek		= noop_llseek,
 };
 
-static void fanotify_free_mark(struct fsnotify_mark *fsn_mark)
-{
-	kmem_cache_free(fanotify_mark_cache, fsn_mark);
-}
-
 static int fanotify_find_path(int dfd, const char __user *filename,
 			      struct path *path, unsigned int flags)
 {
@@ -510,13 +516,12 @@ static __u32 fanotify_mark_remove_from_mask(struct fsnotify_mark *fsn_mark,
 			tmask &= ~FAN_ONDIR;
 
 		oldmask = fsn_mark->mask;
-		fsnotify_set_mark_mask_locked(fsn_mark, tmask);
+		fsn_mark->mask = tmask;
 	} else {
 		__u32 tmask = fsn_mark->ignored_mask & ~mask;
 		if (flags & FAN_MARK_ONDIR)
 			tmask &= ~FAN_ONDIR;
-
-		fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
+		fsn_mark->ignored_mask = tmask;
 	}
 	*destroy = !(fsn_mark->mask | fsn_mark->ignored_mask);
 	spin_unlock(&fsn_mark->lock);
@@ -533,7 +538,8 @@ static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
 	int destroy_mark;
 
 	mutex_lock(&group->mark_mutex);
-	fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
+	fsn_mark = fsnotify_find_mark(&real_mount(mnt)->mnt_fsnotify_marks,
+				      group);
 	if (!fsn_mark) {
 		mutex_unlock(&group->mark_mutex);
 		return -ENOENT;
@@ -541,6 +547,8 @@ static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
 
 	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
 						 &destroy_mark);
+	if (removed & real_mount(mnt)->mnt_fsnotify_mask)
+		fsnotify_recalc_mask(real_mount(mnt)->mnt_fsnotify_marks);
 	if (destroy_mark)
 		fsnotify_detach_mark(fsn_mark);
 	mutex_unlock(&group->mark_mutex);
@@ -548,9 +556,6 @@ static int fanotify_remove_vfsmount_mark(struct fsnotify_group *group,
 		fsnotify_free_mark(fsn_mark);
 
 	fsnotify_put_mark(fsn_mark);
-	if (removed & real_mount(mnt)->mnt_fsnotify_mask)
-		fsnotify_recalc_vfsmount_mask(mnt);
-
 	return 0;
 }
 
@@ -563,7 +568,7 @@ static int fanotify_remove_inode_mark(struct fsnotify_group *group,
 	int destroy_mark;
 
 	mutex_lock(&group->mark_mutex);
-	fsn_mark = fsnotify_find_inode_mark(group, inode);
+	fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
 	if (!fsn_mark) {
 		mutex_unlock(&group->mark_mutex);
 		return -ENOENT;
@@ -571,16 +576,16 @@ static int fanotify_remove_inode_mark(struct fsnotify_group *group,
 
 	removed = fanotify_mark_remove_from_mask(fsn_mark, mask, flags,
 						 &destroy_mark);
+	if (removed & inode->i_fsnotify_mask)
+		fsnotify_recalc_mask(inode->i_fsnotify_marks);
 	if (destroy_mark)
 		fsnotify_detach_mark(fsn_mark);
 	mutex_unlock(&group->mark_mutex);
 	if (destroy_mark)
 		fsnotify_free_mark(fsn_mark);
 
-	/* matches the fsnotify_find_inode_mark() */
+	/* matches the fsnotify_find_mark() */
 	fsnotify_put_mark(fsn_mark);
-	if (removed & inode->i_fsnotify_mask)
-		fsnotify_recalc_inode_mask(inode);
 
 	return 0;
 }
@@ -599,13 +604,13 @@ static __u32 fanotify_mark_add_to_mask(struct fsnotify_mark *fsn_mark,
 			tmask |= FAN_ONDIR;
 
 		oldmask = fsn_mark->mask;
-		fsnotify_set_mark_mask_locked(fsn_mark, tmask);
+		fsn_mark->mask = tmask;
 	} else {
 		__u32 tmask = fsn_mark->ignored_mask | mask;
 		if (flags & FAN_MARK_ONDIR)
 			tmask |= FAN_ONDIR;
 
-		fsnotify_set_mark_ignored_mask_locked(fsn_mark, tmask);
+		fsn_mark->ignored_mask = tmask;
 		if (flags & FAN_MARK_IGNORED_SURV_MODIFY)
 			fsn_mark->flags |= FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY;
 	}
@@ -628,8 +633,8 @@ static struct fsnotify_mark *fanotify_add_new_mark(struct fsnotify_group *group,
 	if (!mark)
 		return ERR_PTR(-ENOMEM);
 
-	fsnotify_init_mark(mark, fanotify_free_mark);
-	ret = fsnotify_add_mark_locked(mark, group, inode, mnt, 0);
+	fsnotify_init_mark(mark, group);
+	ret = fsnotify_add_mark_locked(mark, inode, mnt, 0);
 	if (ret) {
 		fsnotify_put_mark(mark);
 		return ERR_PTR(ret);
@@ -647,7 +652,8 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
 	__u32 added;
 
 	mutex_lock(&group->mark_mutex);
-	fsn_mark = fsnotify_find_vfsmount_mark(group, mnt);
+	fsn_mark = fsnotify_find_mark(&real_mount(mnt)->mnt_fsnotify_marks,
+				      group);
 	if (!fsn_mark) {
 		fsn_mark = fanotify_add_new_mark(group, NULL, mnt);
 		if (IS_ERR(fsn_mark)) {
@@ -656,10 +662,9 @@ static int fanotify_add_vfsmount_mark(struct fsnotify_group *group,
 		}
 	}
 	added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
-	mutex_unlock(&group->mark_mutex);
-
 	if (added & ~real_mount(mnt)->mnt_fsnotify_mask)
-		fsnotify_recalc_vfsmount_mask(mnt);
+		fsnotify_recalc_mask(real_mount(mnt)->mnt_fsnotify_marks);
+	mutex_unlock(&group->mark_mutex);
 
 	fsnotify_put_mark(fsn_mark);
 	return 0;
@@ -685,7 +690,7 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
 		return 0;
 
 	mutex_lock(&group->mark_mutex);
-	fsn_mark = fsnotify_find_inode_mark(group, inode);
+	fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
 	if (!fsn_mark) {
 		fsn_mark = fanotify_add_new_mark(group, inode, NULL);
 		if (IS_ERR(fsn_mark)) {
@@ -694,10 +699,9 @@ static int fanotify_add_inode_mark(struct fsnotify_group *group,
 		}
 	}
 	added = fanotify_mark_add_to_mask(fsn_mark, mask, flags);
-	mutex_unlock(&group->mark_mutex);
-
 	if (added & ~inode->i_fsnotify_mask)
-		fsnotify_recalc_inode_mask(inode);
+		fsnotify_recalc_mask(inode->i_fsnotify_marks);
+	mutex_unlock(&group->mark_mutex);
 
 	fsnotify_put_mark(fsn_mark);
 	return 0;
diff --git a/fs/notify/fdinfo.c b/fs/notify/fdinfo.c
index fd98e5100cab..dd63aa9a6f9a 100644
--- a/fs/notify/fdinfo.c
+++ b/fs/notify/fdinfo.c
@@ -76,12 +76,11 @@ static void inotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 	struct inotify_inode_mark *inode_mark;
 	struct inode *inode;
 
-	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE) ||
-	    !(mark->flags & FSNOTIFY_MARK_FLAG_INODE))
+	if (!(mark->connector->flags & FSNOTIFY_OBJ_TYPE_INODE))
 		return;
 
 	inode_mark = container_of(mark, struct inotify_inode_mark, fsn_mark);
-	inode = igrab(mark->inode);
+	inode = igrab(mark->connector->inode);
 	if (inode) {
 		/*
 		 * IN_ALL_EVENTS represents all of the mask bits
@@ -113,14 +112,11 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 	unsigned int mflags = 0;
 	struct inode *inode;
 
-	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE))
-		return;
-
 	if (mark->flags & FSNOTIFY_MARK_FLAG_IGNORED_SURV_MODIFY)
 		mflags |= FAN_MARK_IGNORED_SURV_MODIFY;
 
-	if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {
-		inode = igrab(mark->inode);
+	if (mark->connector->flags & FSNOTIFY_OBJ_TYPE_INODE) {
+		inode = igrab(mark->connector->inode);
 		if (!inode)
 			return;
 		seq_printf(m, "fanotify ino:%lx sdev:%x mflags:%x mask:%x ignored_mask:%x ",
@@ -129,8 +125,8 @@ static void fanotify_fdinfo(struct seq_file *m, struct fsnotify_mark *mark)
 		show_mark_fhandle(m, inode);
 		seq_putc(m, '\n');
 		iput(inode);
-	} else if (mark->flags & FSNOTIFY_MARK_FLAG_VFSMOUNT) {
-		struct mount *mnt = real_mount(mark->mnt);
+	} else if (mark->connector->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+		struct mount *mnt = real_mount(mark->connector->mnt);
 
 		seq_printf(m, "fanotify mnt_id:%x mflags:%x mask:%x ignored_mask:%x\n",
 			   mnt->mnt_id, mflags, mark->mask, mark->ignored_mask);
diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c
index b41515d3f081..0c4583b61717 100644
--- a/fs/notify/fsnotify.c
+++ b/fs/notify/fsnotify.c
@@ -41,6 +41,63 @@ void __fsnotify_vfsmount_delete(struct vfsmount *mnt)
 	fsnotify_clear_marks_by_mount(mnt);
 }
 
+/**
+ * fsnotify_unmount_inodes - an sb is unmounting.  handle any watched inodes.
+ * @sb: superblock being unmounted.
+ *
+ * Called during unmount with no locks held, so needs to be safe against
+ * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
+ */
+void fsnotify_unmount_inodes(struct super_block *sb)
+{
+	struct inode *inode, *iput_inode = NULL;
+
+	spin_lock(&sb->s_inode_list_lock);
+	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
+		/*
+		 * We cannot __iget() an inode in state I_FREEING,
+		 * I_WILL_FREE, or I_NEW which is fine because by that point
+		 * the inode cannot have any associated watches.
+		 */
+		spin_lock(&inode->i_lock);
+		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+
+		/*
+		 * If i_count is zero, the inode cannot have any watches and
+		 * doing an __iget/iput with MS_ACTIVE clear would actually
+		 * evict all inodes with zero i_count from icache which is
+		 * unnecessarily violent and may in fact be illegal to do.
+		 */
+		if (!atomic_read(&inode->i_count)) {
+			spin_unlock(&inode->i_lock);
+			continue;
+		}
+
+		__iget(inode);
+		spin_unlock(&inode->i_lock);
+		spin_unlock(&sb->s_inode_list_lock);
+
+		if (iput_inode)
+			iput(iput_inode);
+
+		/* for each watch, send FS_UNMOUNT and then remove it */
+		fsnotify(inode, FS_UNMOUNT, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
+
+		fsnotify_inode_delete(inode);
+
+		iput_inode = inode;
+
+		spin_lock(&sb->s_inode_list_lock);
+	}
+	spin_unlock(&sb->s_inode_list_lock);
+
+	if (iput_inode)
+		iput(iput_inode);
+}
+
 /*
  * Given an inode, first check if we care what happens to our children.  Inotify
  * and dnotify both tell their parents about events.  If we care about any event
@@ -104,16 +161,20 @@ int __fsnotify_parent(const struct path *path, struct dentry *dentry, __u32 mask
 	if (unlikely(!fsnotify_inode_watches_children(p_inode)))
 		__fsnotify_update_child_dentry_flags(p_inode);
 	else if (p_inode->i_fsnotify_mask & mask) {
+		struct name_snapshot name;
+
 		/* we are notifying a parent so come up with the new mask which
 		 * specifies these are events which came from a child. */
 		mask |= FS_EVENT_ON_CHILD;
 
+		take_dentry_name_snapshot(&name, dentry);
 		if (path)
 			ret = fsnotify(p_inode, mask, path, FSNOTIFY_EVENT_PATH,
-				       dentry->d_name.name, 0);
+				       name.name, 0);
 		else
 			ret = fsnotify(p_inode, mask, dentry->d_inode, FSNOTIFY_EVENT_INODE,
-				       dentry->d_name.name, 0);
+				       name.name, 0);
+		release_dentry_name_snapshot(&name);
 	}
 
 	dput(parent);
@@ -127,7 +188,8 @@ static int send_to_group(struct inode *to_tell,
 			 struct fsnotify_mark *vfsmount_mark,
 			 __u32 mask, const void *data,
 			 int data_is, u32 cookie,
-			 const unsigned char *file_name)
+			 const unsigned char *file_name,
+			 struct fsnotify_iter_info *iter_info)
 {
 	struct fsnotify_group *group = NULL;
 	__u32 inode_test_mask = 0;
@@ -178,7 +240,7 @@ static int send_to_group(struct inode *to_tell,
 
 	return group->ops->handle_event(group, to_tell, inode_mark,
 					vfsmount_mark, mask, data, data_is,
-					file_name, cookie);
+					file_name, cookie, iter_info);
 }
 
 /*
@@ -193,8 +255,10 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 	struct hlist_node *inode_node = NULL, *vfsmount_node = NULL;
 	struct fsnotify_mark *inode_mark = NULL, *vfsmount_mark = NULL;
 	struct fsnotify_group *inode_group, *vfsmount_group;
+	struct fsnotify_mark_connector *inode_conn, *vfsmount_conn;
+	struct fsnotify_iter_info iter_info;
 	struct mount *mnt;
-	int idx, ret = 0;
+	int ret = 0;
 	/* global tests shouldn't care about events on child only the specific event */
 	__u32 test_mask = (mask & ~FS_EVENT_ON_CHILD);
 
@@ -210,8 +274,8 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 	 * SRCU because we have no references to any objects and do not
 	 * need SRCU to keep them "alive".
 	 */
-	if (hlist_empty(&to_tell->i_fsnotify_marks) &&
-	    (!mnt || hlist_empty(&mnt->mnt_fsnotify_marks)))
+	if (!to_tell->i_fsnotify_marks &&
+	    (!mnt || !mnt->mnt_fsnotify_marks))
 		return 0;
 	/*
 	 * if this is a modify event we may need to clear the ignored masks
@@ -223,19 +287,30 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 	    !(mnt && test_mask & mnt->mnt_fsnotify_mask))
 		return 0;
 
-	idx = srcu_read_lock(&fsnotify_mark_srcu);
+	iter_info.srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
 
 	if ((mask & FS_MODIFY) ||
-	    (test_mask & to_tell->i_fsnotify_mask))
-		inode_node = srcu_dereference(to_tell->i_fsnotify_marks.first,
+	    (test_mask & to_tell->i_fsnotify_mask)) {
+		inode_conn = srcu_dereference(to_tell->i_fsnotify_marks,
 					      &fsnotify_mark_srcu);
+		if (inode_conn)
+			inode_node = srcu_dereference(inode_conn->list.first,
+						      &fsnotify_mark_srcu);
+	}
 
 	if (mnt && ((mask & FS_MODIFY) ||
 		    (test_mask & mnt->mnt_fsnotify_mask))) {
-		vfsmount_node = srcu_dereference(mnt->mnt_fsnotify_marks.first,
-						 &fsnotify_mark_srcu);
-		inode_node = srcu_dereference(to_tell->i_fsnotify_marks.first,
+		inode_conn = srcu_dereference(to_tell->i_fsnotify_marks,
 					      &fsnotify_mark_srcu);
+		if (inode_conn)
+			inode_node = srcu_dereference(inode_conn->list.first,
+						      &fsnotify_mark_srcu);
+		vfsmount_conn = srcu_dereference(mnt->mnt_fsnotify_marks,
+					         &fsnotify_mark_srcu);
+		if (vfsmount_conn)
+			vfsmount_node = srcu_dereference(
+						vfsmount_conn->list.first,
+						&fsnotify_mark_srcu);
 	}
 
 	/*
@@ -272,8 +347,13 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 				vfsmount_mark = NULL;
 			}
 		}
+
+		iter_info.inode_mark = inode_mark;
+		iter_info.vfsmount_mark = vfsmount_mark;
+
 		ret = send_to_group(to_tell, inode_mark, vfsmount_mark, mask,
-				    data, data_is, cookie, file_name);
+				    data, data_is, cookie, file_name,
+				    &iter_info);
 
 		if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS))
 			goto out;
@@ -287,12 +367,14 @@ int fsnotify(struct inode *to_tell, __u32 mask, const void *data, int data_is,
 	}
 	ret = 0;
 out:
-	srcu_read_unlock(&fsnotify_mark_srcu, idx);
+	srcu_read_unlock(&fsnotify_mark_srcu, iter_info.srcu_idx);
 
 	return ret;
 }
 EXPORT_SYMBOL_GPL(fsnotify);
 
+extern struct kmem_cache *fsnotify_mark_connector_cachep;
+
 static __init int fsnotify_init(void)
 {
 	int ret;
@@ -303,6 +385,9 @@ static __init int fsnotify_init(void)
 	if (ret)
 		panic("initializing fsnotify_mark_srcu");
 
+	fsnotify_mark_connector_cachep = KMEM_CACHE(fsnotify_mark_connector,
+						    SLAB_PANIC);
+
 	return 0;
 }
 core_initcall(fsnotify_init);
diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h
index 0a3bc2cf192c..bf012e8ecd14 100644
--- a/fs/notify/fsnotify.h
+++ b/fs/notify/fsnotify.h
@@ -8,60 +8,36 @@
 
 #include "../mount.h"
 
+struct fsnotify_iter_info {
+	struct fsnotify_mark *inode_mark;
+	struct fsnotify_mark *vfsmount_mark;
+	int srcu_idx;
+};
+
 /* destroy all events sitting in this groups notification queue */
 extern void fsnotify_flush_notify(struct fsnotify_group *group);
 
 /* protects reads of inode and vfsmount marks list */
 extern struct srcu_struct fsnotify_mark_srcu;
 
-/* Calculate mask of events for a list of marks */
-extern u32 fsnotify_recalc_mask(struct hlist_head *head);
-
 /* compare two groups for sorting of marks lists */
 extern int fsnotify_compare_groups(struct fsnotify_group *a,
 				   struct fsnotify_group *b);
 
-extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark,
-						__u32 mask);
-/* Add mark to a proper place in mark list */
-extern int fsnotify_add_mark_list(struct hlist_head *head,
-				  struct fsnotify_mark *mark,
-				  int allow_dups);
-/* add a mark to an inode */
-extern int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
-				   struct fsnotify_group *group, struct inode *inode,
-				   int allow_dups);
-/* add a mark to a vfsmount */
-extern int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
-				      struct fsnotify_group *group, struct vfsmount *mnt,
-				      int allow_dups);
-
-/* vfsmount specific destruction of a mark */
-extern void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark);
-/* inode specific destruction of a mark */
-extern void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark);
-/* Find mark belonging to given group in the list of marks */
-extern struct fsnotify_mark *fsnotify_find_mark(struct hlist_head *head,
-						struct fsnotify_group *group);
-/* Destroy all marks in the given list protected by 'lock' */
-extern void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock);
+/* Destroy all marks connected via given connector */
+extern void fsnotify_destroy_marks(struct fsnotify_mark_connector __rcu **connp);
 /* run the list of all marks associated with inode and destroy them */
 static inline void fsnotify_clear_marks_by_inode(struct inode *inode)
 {
-	fsnotify_destroy_marks(&inode->i_fsnotify_marks, &inode->i_lock);
+	fsnotify_destroy_marks(&inode->i_fsnotify_marks);
 }
 /* run the list of all marks associated with vfsmount and destroy them */
 static inline void fsnotify_clear_marks_by_mount(struct vfsmount *mnt)
 {
-	fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks,
-			       &mnt->mnt_root->d_lock);
+	fsnotify_destroy_marks(&real_mount(mnt)->mnt_fsnotify_marks);
 }
-/* prepare for freeing all marks associated with given group */
-extern void fsnotify_detach_group_marks(struct fsnotify_group *group);
-/*
- * wait for fsnotify_mark_srcu period to end and free all marks in destroy_list
- */
-extern void fsnotify_mark_destroy_list(void);
+/* Wait until all marks queued for destruction are destroyed */
+extern void fsnotify_wait_marks_destroyed(void);
 
 /*
  * update the dentry->d_flags of all of inode's children to indicate if inode cares
diff --git a/fs/notify/group.c b/fs/notify/group.c
index fbe3cbebec16..32357534de18 100644
--- a/fs/notify/group.c
+++ b/fs/notify/group.c
@@ -66,14 +66,23 @@ void fsnotify_destroy_group(struct fsnotify_group *group)
 	 */
 	fsnotify_group_stop_queueing(group);
 
-	/* clear all inode marks for this group, attach them to destroy_list */
-	fsnotify_detach_group_marks(group);
+	/* Clear all marks for this group and queue them for destruction */
+	fsnotify_clear_marks_by_group(group, FSNOTIFY_OBJ_ALL_TYPES);
 
 	/*
-	 * Wait for fsnotify_mark_srcu period to end and free all marks in
-	 * destroy_list
+	 * Some marks can still be pinned when waiting for response from
+	 * userspace. Wait for those now. fsnotify_prepare_user_wait() will
+	 * not succeed now so this wait is race-free.
 	 */
-	fsnotify_mark_destroy_list();
+	wait_event(group->notification_waitq, !atomic_read(&group->user_waits));
+
+	/*
+	 * Wait until all marks get really destroyed. We could actually destroy
+	 * them ourselves instead of waiting for worker to do it, however that
+	 * would be racy as worker can already be processing some marks before
+	 * we even entered fsnotify_destroy_group().
+	 */
+	fsnotify_wait_marks_destroyed();
 
 	/*
 	 * Since we have waited for fsnotify_mark_srcu in
@@ -124,6 +133,7 @@ struct fsnotify_group *fsnotify_alloc_group(const struct fsnotify_ops *ops)
 	/* set to 0 when there a no external references to this group */
 	atomic_set(&group->refcnt, 1);
 	atomic_set(&group->num_marks, 0);
+	atomic_set(&group->user_waits, 0);
 
 	spin_lock_init(&group->notification_lock);
 	INIT_LIST_HEAD(&group->notification_list);
diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c
deleted file mode 100644
index a3645249f7ec..000000000000
--- a/fs/notify/inode_mark.c
+++ /dev/null
@@ -1,199 +0,0 @@
-/*
- *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2, or (at your option)
- *  any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; see the file COPYING.  If not, write to
- *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/fs.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mutex.h>
-#include <linux/spinlock.h>
-
-#include <linux/atomic.h>
-
-#include <linux/fsnotify_backend.h>
-#include "fsnotify.h"
-
-#include "../internal.h"
-
-/*
- * Recalculate the inode->i_fsnotify_mask, or the mask of all FS_* event types
- * any notifier is interested in hearing for this inode.
- */
-void fsnotify_recalc_inode_mask(struct inode *inode)
-{
-	spin_lock(&inode->i_lock);
-	inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
-	spin_unlock(&inode->i_lock);
-
-	__fsnotify_update_child_dentry_flags(inode);
-}
-
-void fsnotify_destroy_inode_mark(struct fsnotify_mark *mark)
-{
-	struct inode *inode = mark->inode;
-
-	BUG_ON(!mutex_is_locked(&mark->group->mark_mutex));
-	assert_spin_locked(&mark->lock);
-
-	spin_lock(&inode->i_lock);
-
-	hlist_del_init_rcu(&mark->obj_list);
-	mark->inode = NULL;
-
-	/*
-	 * this mark is now off the inode->i_fsnotify_marks list and we
-	 * hold the inode->i_lock, so this is the perfect time to update the
-	 * inode->i_fsnotify_mask
-	 */
-	inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
-	spin_unlock(&inode->i_lock);
-}
-
-/*
- * Given a group clear all of the inode marks associated with that group.
- */
-void fsnotify_clear_inode_marks_by_group(struct fsnotify_group *group)
-{
-	fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_MARK_FLAG_INODE);
-}
-
-/*
- * given a group and inode, find the mark associated with that combination.
- * if found take a reference to that mark and return it, else return NULL
- */
-struct fsnotify_mark *fsnotify_find_inode_mark(struct fsnotify_group *group,
-					       struct inode *inode)
-{
-	struct fsnotify_mark *mark;
-
-	spin_lock(&inode->i_lock);
-	mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
-	spin_unlock(&inode->i_lock);
-
-	return mark;
-}
-
-/*
- * If we are setting a mark mask on an inode mark we should pin the inode
- * in memory.
- */
-void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *mark,
-					 __u32 mask)
-{
-	struct inode *inode;
-
-	assert_spin_locked(&mark->lock);
-
-	if (mask &&
-	    mark->inode &&
-	    !(mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED)) {
-		mark->flags |= FSNOTIFY_MARK_FLAG_OBJECT_PINNED;
-		inode = igrab(mark->inode);
-		/*
-		 * we shouldn't be able to get here if the inode wasn't
-		 * already safely held in memory.  But bug in case it
-		 * ever is wrong.
-		 */
-		BUG_ON(!inode);
-	}
-}
-
-/*
- * Attach an initialized mark to a given inode.
- * These marks may be used for the fsnotify backend to determine which
- * event types should be delivered to which group and for which inodes.  These
- * marks are ordered according to priority, highest number first, and then by
- * the group's location in memory.
- */
-int fsnotify_add_inode_mark(struct fsnotify_mark *mark,
-			    struct fsnotify_group *group, struct inode *inode,
-			    int allow_dups)
-{
-	int ret;
-
-	mark->flags |= FSNOTIFY_MARK_FLAG_INODE;
-
-	BUG_ON(!mutex_is_locked(&group->mark_mutex));
-	assert_spin_locked(&mark->lock);
-
-	spin_lock(&inode->i_lock);
-	mark->inode = inode;
-	ret = fsnotify_add_mark_list(&inode->i_fsnotify_marks, mark,
-				     allow_dups);
-	inode->i_fsnotify_mask = fsnotify_recalc_mask(&inode->i_fsnotify_marks);
-	spin_unlock(&inode->i_lock);
-
-	return ret;
-}
-
-/**
- * fsnotify_unmount_inodes - an sb is unmounting.  handle any watched inodes.
- * @sb: superblock being unmounted.
- *
- * Called during unmount with no locks held, so needs to be safe against
- * concurrent modifiers. We temporarily drop sb->s_inode_list_lock and CAN block.
- */
-void fsnotify_unmount_inodes(struct super_block *sb)
-{
-	struct inode *inode, *iput_inode = NULL;
-
-	spin_lock(&sb->s_inode_list_lock);
-	list_for_each_entry(inode, &sb->s_inodes, i_sb_list) {
-		/*
-		 * We cannot __iget() an inode in state I_FREEING,
-		 * I_WILL_FREE, or I_NEW which is fine because by that point
-		 * the inode cannot have any associated watches.
-		 */
-		spin_lock(&inode->i_lock);
-		if (inode->i_state & (I_FREEING|I_WILL_FREE|I_NEW)) {
-			spin_unlock(&inode->i_lock);
-			continue;
-		}
-
-		/*
-		 * If i_count is zero, the inode cannot have any watches and
-		 * doing an __iget/iput with MS_ACTIVE clear would actually
-		 * evict all inodes with zero i_count from icache which is
-		 * unnecessarily violent and may in fact be illegal to do.
-		 */
-		if (!atomic_read(&inode->i_count)) {
-			spin_unlock(&inode->i_lock);
-			continue;
-		}
-
-		__iget(inode);
-		spin_unlock(&inode->i_lock);
-		spin_unlock(&sb->s_inode_list_lock);
-
-		if (iput_inode)
-			iput(iput_inode);
-
-		/* for each watch, send FS_UNMOUNT and then remove it */
-		fsnotify(inode, FS_UNMOUNT, inode, FSNOTIFY_EVENT_INODE, NULL, 0);
-
-		fsnotify_inode_delete(inode);
-
-		iput_inode = inode;
-
-		spin_lock(&sb->s_inode_list_lock);
-	}
-	spin_unlock(&sb->s_inode_list_lock);
-
-	if (iput_inode)
-		iput(iput_inode);
-}
diff --git a/fs/notify/inotify/inotify.h b/fs/notify/inotify/inotify.h
index a6f5907a3fee..9ff67b61da8a 100644
--- a/fs/notify/inotify/inotify.h
+++ b/fs/notify/inotify/inotify.h
@@ -27,6 +27,25 @@ extern int inotify_handle_event(struct fsnotify_group *group,
 				struct fsnotify_mark *inode_mark,
 				struct fsnotify_mark *vfsmount_mark,
 				u32 mask, const void *data, int data_type,
-				const unsigned char *file_name, u32 cookie);
+				const unsigned char *file_name, u32 cookie,
+				struct fsnotify_iter_info *iter_info);
 
 extern const struct fsnotify_ops inotify_fsnotify_ops;
+extern struct kmem_cache *inotify_inode_mark_cachep;
+
+#ifdef CONFIG_INOTIFY_USER
+static inline void dec_inotify_instances(struct ucounts *ucounts)
+{
+	dec_ucount(ucounts, UCOUNT_INOTIFY_INSTANCES);
+}
+
+static inline struct ucounts *inc_inotify_watches(struct ucounts *ucounts)
+{
+	return inc_ucount(ucounts->ns, ucounts->uid, UCOUNT_INOTIFY_WATCHES);
+}
+
+static inline void dec_inotify_watches(struct ucounts *ucounts)
+{
+	dec_ucount(ucounts, UCOUNT_INOTIFY_WATCHES);
+}
+#endif
diff --git a/fs/notify/inotify/inotify_fsnotify.c b/fs/notify/inotify/inotify_fsnotify.c
index 19e7ec109a75..8b73332735ba 100644
--- a/fs/notify/inotify/inotify_fsnotify.c
+++ b/fs/notify/inotify/inotify_fsnotify.c
@@ -30,6 +30,7 @@
 #include <linux/slab.h> /* kmem_* */
 #include <linux/types.h>
 #include <linux/sched.h>
+#include <linux/sched/user.h>
 
 #include "inotify.h"
 
@@ -67,7 +68,8 @@ int inotify_handle_event(struct fsnotify_group *group,
 			 struct fsnotify_mark *inode_mark,
 			 struct fsnotify_mark *vfsmount_mark,
 			 u32 mask, const void *data, int data_type,
-			 const unsigned char *file_name, u32 cookie)
+			 const unsigned char *file_name, u32 cookie,
+			 struct fsnotify_iter_info *iter_info)
 {
 	struct inotify_inode_mark *i_mark;
 	struct inotify_event_info *event;
@@ -155,8 +157,8 @@ static int idr_callback(int id, void *p, void *data)
 	 * BUG() that was here.
 	 */
 	if (fsn_mark)
-		printk(KERN_WARNING "fsn_mark->group=%p inode=%p wd=%d\n",
-			fsn_mark->group, fsn_mark->inode, i_mark->wd);
+		printk(KERN_WARNING "fsn_mark->group=%p wd=%d\n",
+			fsn_mark->group, i_mark->wd);
 	return 0;
 }
 
@@ -165,10 +167,8 @@ static void inotify_free_group_priv(struct fsnotify_group *group)
 	/* ideally the idr is empty and we won't hit the BUG in the callback */
 	idr_for_each(&group->inotify_data.idr, idr_callback, group);
 	idr_destroy(&group->inotify_data.idr);
-	if (group->inotify_data.user) {
-		atomic_dec(&group->inotify_data.user->inotify_devs);
-		free_uid(group->inotify_data.user);
-	}
+	if (group->inotify_data.ucounts)
+		dec_inotify_instances(group->inotify_data.ucounts);
 }
 
 static void inotify_free_event(struct fsnotify_event *fsn_event)
@@ -176,9 +176,20 @@ static void inotify_free_event(struct fsnotify_event *fsn_event)
 	kfree(INOTIFY_E(fsn_event));
 }
 
+/* ding dong the mark is dead */
+static void inotify_free_mark(struct fsnotify_mark *fsn_mark)
+{
+	struct inotify_inode_mark *i_mark;
+
+	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
+
+	kmem_cache_free(inotify_inode_mark_cachep, i_mark);
+}
+
 const struct fsnotify_ops inotify_fsnotify_ops = {
 	.handle_event = inotify_handle_event,
 	.free_group_priv = inotify_free_group_priv,
 	.free_event = inotify_free_event,
 	.freeing_mark = inotify_freeing_mark,
+	.free_mark = inotify_free_mark,
 };
diff --git a/fs/notify/inotify/inotify_user.c b/fs/notify/inotify/inotify_user.c
index 69d1ea3d292a..7cc7d3fb1862 100644
--- a/fs/notify/inotify/inotify_user.c
+++ b/fs/notify/inotify/inotify_user.c
@@ -30,7 +30,7 @@
 #include <linux/inotify.h>
 #include <linux/kernel.h> /* roundup() */
 #include <linux/namei.h> /* LOOKUP_FOLLOW */
-#include <linux/sched.h> /* struct user */
+#include <linux/sched/signal.h>
 #include <linux/slab.h> /* struct kmem_cache */
 #include <linux/syscalls.h>
 #include <linux/types.h>
@@ -44,12 +44,10 @@
 
 #include <asm/ioctls.h>
 
-/* these are configurable via /proc/sys/fs/inotify/ */
-static int inotify_max_user_instances __read_mostly;
+/* configurable via /proc/sys/fs/inotify/ */
 static int inotify_max_queued_events __read_mostly;
-static int inotify_max_user_watches __read_mostly;
 
-static struct kmem_cache *inotify_inode_mark_cachep __read_mostly;
+struct kmem_cache *inotify_inode_mark_cachep __read_mostly;
 
 #ifdef CONFIG_SYSCTL
 
@@ -60,7 +58,7 @@ static int zero;
 struct ctl_table inotify_table[] = {
 	{
 		.procname	= "max_user_instances",
-		.data		= &inotify_max_user_instances,
+		.data		= &init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES],
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
@@ -68,7 +66,7 @@ struct ctl_table inotify_table[] = {
 	},
 	{
 		.procname	= "max_user_watches",
-		.data		= &inotify_max_user_watches,
+		.data		= &init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES],
 		.maxlen		= sizeof(int),
 		.mode		= 0644,
 		.proc_handler	= proc_dointvec_minmax,
@@ -397,21 +395,6 @@ static struct inotify_inode_mark *inotify_idr_find(struct fsnotify_group *group,
 	return i_mark;
 }
 
-static void do_inotify_remove_from_idr(struct fsnotify_group *group,
-				       struct inotify_inode_mark *i_mark)
-{
-	struct idr *idr = &group->inotify_data.idr;
-	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
-	int wd = i_mark->wd;
-
-	assert_spin_locked(idr_lock);
-
-	idr_remove(idr, wd);
-
-	/* removed from the idr, drop that ref */
-	fsnotify_put_mark(&i_mark->fsn_mark);
-}
-
 /*
  * Remove the mark from the idr (if present) and drop the reference
  * on the mark because it was in the idr.
@@ -419,6 +402,7 @@ static void do_inotify_remove_from_idr(struct fsnotify_group *group,
 static void inotify_remove_from_idr(struct fsnotify_group *group,
 				    struct inotify_inode_mark *i_mark)
 {
+	struct idr *idr = &group->inotify_data.idr;
 	spinlock_t *idr_lock = &group->inotify_data.idr_lock;
 	struct inotify_inode_mark *found_i_mark = NULL;
 	int wd;
@@ -431,18 +415,16 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
 	 * if it wasn't....
 	 */
 	if (wd == -1) {
-		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p"
-			" i_mark->inode=%p\n", __func__, i_mark, i_mark->wd,
-			i_mark->fsn_mark.group, i_mark->fsn_mark.inode);
+		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
+			__func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
 		goto out;
 	}
 
 	/* Lets look in the idr to see if we find it */
 	found_i_mark = inotify_idr_find_locked(group, wd);
 	if (unlikely(!found_i_mark)) {
-		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p"
-			" i_mark->inode=%p\n", __func__, i_mark, i_mark->wd,
-			i_mark->fsn_mark.group, i_mark->fsn_mark.inode);
+		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
+			__func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
 		goto out;
 	}
 
@@ -453,35 +435,33 @@ static void inotify_remove_from_idr(struct fsnotify_group *group,
 	 */
 	if (unlikely(found_i_mark != i_mark)) {
 		WARN_ONCE(1, "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p "
-			"mark->inode=%p found_i_mark=%p found_i_mark->wd=%d "
-			"found_i_mark->group=%p found_i_mark->inode=%p\n",
-			__func__, i_mark, i_mark->wd, i_mark->fsn_mark.group,
-			i_mark->fsn_mark.inode, found_i_mark, found_i_mark->wd,
-			found_i_mark->fsn_mark.group,
-			found_i_mark->fsn_mark.inode);
+			"found_i_mark=%p found_i_mark->wd=%d "
+			"found_i_mark->group=%p\n", __func__, i_mark,
+			i_mark->wd, i_mark->fsn_mark.group, found_i_mark,
+			found_i_mark->wd, found_i_mark->fsn_mark.group);
 		goto out;
 	}
 
 	/*
 	 * One ref for being in the idr
-	 * one ref held by the caller trying to kill us
 	 * one ref grabbed by inotify_idr_find
 	 */
-	if (unlikely(atomic_read(&i_mark->fsn_mark.refcnt) < 3)) {
-		printk(KERN_ERR "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p"
-			" i_mark->inode=%p\n", __func__, i_mark, i_mark->wd,
-			i_mark->fsn_mark.group, i_mark->fsn_mark.inode);
+	if (unlikely(atomic_read(&i_mark->fsn_mark.refcnt) < 2)) {
+		printk(KERN_ERR "%s: i_mark=%p i_mark->wd=%d i_mark->group=%p\n",
+			 __func__, i_mark, i_mark->wd, i_mark->fsn_mark.group);
 		/* we can't really recover with bad ref cnting.. */
 		BUG();
 	}
 
-	do_inotify_remove_from_idr(group, i_mark);
+	idr_remove(idr, wd);
+	/* Removed from the idr, drop that ref. */
+	fsnotify_put_mark(&i_mark->fsn_mark);
 out:
+	i_mark->wd = -1;
+	spin_unlock(idr_lock);
 	/* match the ref taken by inotify_idr_find_locked() */
 	if (found_i_mark)
 		fsnotify_put_mark(&found_i_mark->fsn_mark);
-	i_mark->wd = -1;
-	spin_unlock(idr_lock);
 }
 
 /*
@@ -494,23 +474,13 @@ void inotify_ignored_and_remove_idr(struct fsnotify_mark *fsn_mark,
 
 	/* Queue ignore event for the watch */
 	inotify_handle_event(group, NULL, fsn_mark, NULL, FS_IN_IGNORED,
-			     NULL, FSNOTIFY_EVENT_NONE, NULL, 0);
+			     NULL, FSNOTIFY_EVENT_NONE, NULL, 0, NULL);
 
 	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
 	/* remove this mark from the idr */
 	inotify_remove_from_idr(group, i_mark);
 
-	atomic_dec(&group->inotify_data.user->inotify_watches);
-}
-
-/* ding dong the mark is dead */
-static void inotify_free_mark(struct fsnotify_mark *fsn_mark)
-{
-	struct inotify_inode_mark *i_mark;
-
-	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
-
-	kmem_cache_free(inotify_inode_mark_cachep, i_mark);
+	dec_inotify_watches(group->inotify_data.ucounts);
 }
 
 static int inotify_update_existing_watch(struct fsnotify_group *group,
@@ -526,21 +496,19 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
 
 	mask = inotify_arg_to_mask(arg);
 
-	fsn_mark = fsnotify_find_inode_mark(group, inode);
+	fsn_mark = fsnotify_find_mark(&inode->i_fsnotify_marks, group);
 	if (!fsn_mark)
 		return -ENOENT;
 
 	i_mark = container_of(fsn_mark, struct inotify_inode_mark, fsn_mark);
 
 	spin_lock(&fsn_mark->lock);
-
 	old_mask = fsn_mark->mask;
 	if (add)
-		fsnotify_set_mark_mask_locked(fsn_mark, (fsn_mark->mask | mask));
+		fsn_mark->mask |= mask;
 	else
-		fsnotify_set_mark_mask_locked(fsn_mark, mask);
+		fsn_mark->mask = mask;
 	new_mask = fsn_mark->mask;
-
 	spin_unlock(&fsn_mark->lock);
 
 	if (old_mask != new_mask) {
@@ -551,7 +519,7 @@ static int inotify_update_existing_watch(struct fsnotify_group *group,
 
 		/* update the inode with this new fsn_mark */
 		if (dropped || do_inode)
-			fsnotify_recalc_inode_mask(inode);
+			fsnotify_recalc_mask(inode->i_fsnotify_marks);
 
 	}
 
@@ -580,29 +548,29 @@ static int inotify_new_watch(struct fsnotify_group *group,
 	if (unlikely(!tmp_i_mark))
 		return -ENOMEM;
 
-	fsnotify_init_mark(&tmp_i_mark->fsn_mark, inotify_free_mark);
+	fsnotify_init_mark(&tmp_i_mark->fsn_mark, group);
 	tmp_i_mark->fsn_mark.mask = mask;
 	tmp_i_mark->wd = -1;
 
-	ret = -ENOSPC;
-	if (atomic_read(&group->inotify_data.user->inotify_watches) >= inotify_max_user_watches)
-		goto out_err;
-
 	ret = inotify_add_to_idr(idr, idr_lock, tmp_i_mark);
 	if (ret)
 		goto out_err;
 
+	/* increment the number of watches the user has */
+	if (!inc_inotify_watches(group->inotify_data.ucounts)) {
+		inotify_remove_from_idr(group, tmp_i_mark);
+		ret = -ENOSPC;
+		goto out_err;
+	}
+
 	/* we are on the idr, now get on the inode */
-	ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, group, inode,
-				       NULL, 0);
+	ret = fsnotify_add_mark_locked(&tmp_i_mark->fsn_mark, inode, NULL, 0);
 	if (ret) {
 		/* we failed to get on the inode, get off the idr */
 		inotify_remove_from_idr(group, tmp_i_mark);
 		goto out_err;
 	}
 
-	/* increment the number of watches the user has */
-	atomic_inc(&group->inotify_data.user->inotify_watches);
 
 	/* return the watch descriptor for this new mark */
 	ret = tmp_i_mark->wd;
@@ -653,10 +621,11 @@ static struct fsnotify_group *inotify_new_group(unsigned int max_events)
 
 	spin_lock_init(&group->inotify_data.idr_lock);
 	idr_init(&group->inotify_data.idr);
-	group->inotify_data.user = get_current_user();
+	group->inotify_data.ucounts = inc_ucount(current_user_ns(),
+						 current_euid(),
+						 UCOUNT_INOTIFY_INSTANCES);
 
-	if (atomic_inc_return(&group->inotify_data.user->inotify_devs) >
-	    inotify_max_user_instances) {
+	if (!group->inotify_data.ucounts) {
 		fsnotify_destroy_group(group);
 		return ERR_PTR(-EMFILE);
 	}
@@ -819,8 +788,8 @@ static int __init inotify_user_setup(void)
 	inotify_inode_mark_cachep = KMEM_CACHE(inotify_inode_mark, SLAB_PANIC);
 
 	inotify_max_queued_events = 16384;
-	inotify_max_user_instances = 128;
-	inotify_max_user_watches = 8192;
+	init_user_ns.ucount_max[UCOUNT_INOTIFY_INSTANCES] = 128;
+	init_user_ns.ucount_max[UCOUNT_INOTIFY_WATCHES] = 8192;
 
 	return 0;
 }
diff --git a/fs/notify/mark.c b/fs/notify/mark.c
index 6043306e8e21..9991f8826734 100644
--- a/fs/notify/mark.c
+++ b/fs/notify/mark.c
@@ -33,7 +33,7 @@
  *
  * group->mark_mutex
  * mark->lock
- * inode->i_lock
+ * mark->connector->lock
  *
  * group->mark_mutex protects the marks_list anchored inside a given group and
  * each mark is hooked via the g_list.  It also protects the groups private
@@ -44,14 +44,22 @@
  * is assigned to as well as the access to a reference of the inode/vfsmount
  * that is being watched by the mark.
  *
- * inode->i_lock protects the i_fsnotify_marks list anchored inside a
- * given inode and each mark is hooked via the i_list. (and sorta the
- * free_i_list)
+ * mark->connector->lock protects the list of marks anchored inside an
+ * inode / vfsmount and each mark is hooked via the i_list.
  *
+ * A list of notification marks relating to inode / mnt is contained in
+ * fsnotify_mark_connector. That structure is alive as long as there are any
+ * marks in the list and is also protected by fsnotify_mark_srcu. A mark gets
+ * detached from fsnotify_mark_connector when last reference to the mark is
+ * dropped.  Thus having mark reference is enough to protect mark->connector
+ * pointer and to make sure fsnotify_mark_connector cannot disappear. Also
+ * because we remove mark from g_list before dropping mark reference associated
+ * with that, any mark found through g_list is guaranteed to have
+ * mark->connector set until we drop group->mark_mutex.
  *
  * LIFETIME:
  * Inode marks survive between when they are added to an inode and when their
- * refcnt==0.
+ * refcnt==0. Marks are also protected by fsnotify_mark_srcu.
  *
  * The inode mark can be cleared for a number of different reasons including:
  * - The inode is unlinked for the last time.  (fsnotify_inode_remove)
@@ -61,17 +69,6 @@
  * - The fsnotify_group associated with the mark is going away and all such marks
  *   need to be cleaned up. (fsnotify_clear_marks_by_group)
  *
- * Worst case we are given an inode and need to clean up all the marks on that
- * inode.  We take i_lock and walk the i_fsnotify_marks safely.  For each
- * mark on the list we take a reference (so the mark can't disappear under us).
- * We remove that mark form the inode's list of marks and we add this mark to a
- * private list anchored on the stack using i_free_list; we walk i_free_list
- * and before we destroy the mark we make sure that we dont race with a
- * concurrent destroy_group by getting a ref to the marks group and taking the
- * groups mutex.
-
- * Very similarly for freeing by group, except we use free_g_list.
- *
  * This has the very interesting property of being able to run concurrently with
  * any (or all) other directions.
  */
@@ -94,94 +91,281 @@
 #define FSNOTIFY_REAPER_DELAY	(1)	/* 1 jiffy */
 
 struct srcu_struct fsnotify_mark_srcu;
+struct kmem_cache *fsnotify_mark_connector_cachep;
+
 static DEFINE_SPINLOCK(destroy_lock);
 static LIST_HEAD(destroy_list);
+static struct fsnotify_mark_connector *connector_destroy_list;
 
 static void fsnotify_mark_destroy_workfn(struct work_struct *work);
 static DECLARE_DELAYED_WORK(reaper_work, fsnotify_mark_destroy_workfn);
 
+static void fsnotify_connector_destroy_workfn(struct work_struct *work);
+static DECLARE_WORK(connector_reaper_work, fsnotify_connector_destroy_workfn);
+
 void fsnotify_get_mark(struct fsnotify_mark *mark)
 {
+	WARN_ON_ONCE(!atomic_read(&mark->refcnt));
 	atomic_inc(&mark->refcnt);
 }
 
-void fsnotify_put_mark(struct fsnotify_mark *mark)
+/*
+ * Get mark reference when we found the mark via lockless traversal of object
+ * list. Mark can be already removed from the list by now and on its way to be
+ * destroyed once SRCU period ends.
+ */
+static bool fsnotify_get_mark_safe(struct fsnotify_mark *mark)
 {
-	if (atomic_dec_and_test(&mark->refcnt)) {
-		if (mark->group)
-			fsnotify_put_group(mark->group);
-		mark->free_mark(mark);
-	}
+	return atomic_inc_not_zero(&mark->refcnt);
 }
 
-/* Calculate mask of events for a list of marks */
-u32 fsnotify_recalc_mask(struct hlist_head *head)
+static void __fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
 {
 	u32 new_mask = 0;
 	struct fsnotify_mark *mark;
 
-	hlist_for_each_entry(mark, head, obj_list)
-		new_mask |= mark->mask;
-	return new_mask;
+	assert_spin_locked(&conn->lock);
+	hlist_for_each_entry(mark, &conn->list, obj_list) {
+		if (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)
+			new_mask |= mark->mask;
+	}
+	if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE)
+		conn->inode->i_fsnotify_mask = new_mask;
+	else if (conn->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT)
+		real_mount(conn->mnt)->mnt_fsnotify_mask = new_mask;
 }
 
 /*
- * Remove mark from inode / vfsmount list, group list, drop inode reference
- * if we got one.
- *
- * Must be called with group->mark_mutex held.
+ * Calculate mask of events for a list of marks. The caller must make sure
+ * connector and connector->inode cannot disappear under us.  Callers achieve
+ * this by holding a mark->lock or mark->group->mark_mutex for a mark on this
+ * list.
  */
-void fsnotify_detach_mark(struct fsnotify_mark *mark)
+void fsnotify_recalc_mask(struct fsnotify_mark_connector *conn)
+{
+	if (!conn)
+		return;
+
+	spin_lock(&conn->lock);
+	__fsnotify_recalc_mask(conn);
+	spin_unlock(&conn->lock);
+	if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE)
+		__fsnotify_update_child_dentry_flags(conn->inode);
+}
+
+/* Free all connectors queued for freeing once SRCU period ends */
+static void fsnotify_connector_destroy_workfn(struct work_struct *work)
+{
+	struct fsnotify_mark_connector *conn, *free;
+
+	spin_lock(&destroy_lock);
+	conn = connector_destroy_list;
+	connector_destroy_list = NULL;
+	spin_unlock(&destroy_lock);
+
+	synchronize_srcu(&fsnotify_mark_srcu);
+	while (conn) {
+		free = conn;
+		conn = conn->destroy_next;
+		kmem_cache_free(fsnotify_mark_connector_cachep, free);
+	}
+}
+
+static struct inode *fsnotify_detach_connector_from_object(
+					struct fsnotify_mark_connector *conn)
 {
 	struct inode *inode = NULL;
+
+	if (conn->flags & FSNOTIFY_OBJ_TYPE_INODE) {
+		inode = conn->inode;
+		rcu_assign_pointer(inode->i_fsnotify_marks, NULL);
+		inode->i_fsnotify_mask = 0;
+		conn->inode = NULL;
+		conn->flags &= ~FSNOTIFY_OBJ_TYPE_INODE;
+	} else if (conn->flags & FSNOTIFY_OBJ_TYPE_VFSMOUNT) {
+		rcu_assign_pointer(real_mount(conn->mnt)->mnt_fsnotify_marks,
+				   NULL);
+		real_mount(conn->mnt)->mnt_fsnotify_mask = 0;
+		conn->mnt = NULL;
+		conn->flags &= ~FSNOTIFY_OBJ_TYPE_VFSMOUNT;
+	}
+
+	return inode;
+}
+
+static void fsnotify_final_mark_destroy(struct fsnotify_mark *mark)
+{
 	struct fsnotify_group *group = mark->group;
 
-	BUG_ON(!mutex_is_locked(&group->mark_mutex));
+	if (WARN_ON_ONCE(!group))
+		return;
+	group->ops->free_mark(mark);
+	fsnotify_put_group(group);
+}
 
-	spin_lock(&mark->lock);
+void fsnotify_put_mark(struct fsnotify_mark *mark)
+{
+	struct fsnotify_mark_connector *conn;
+	struct inode *inode = NULL;
+	bool free_conn = false;
 
-	/* something else already called this function on this mark */
-	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
-		spin_unlock(&mark->lock);
+	/* Catch marks that were actually never attached to object */
+	if (!mark->connector) {
+		if (atomic_dec_and_test(&mark->refcnt))
+			fsnotify_final_mark_destroy(mark);
 		return;
 	}
 
-	mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED;
+	/*
+	 * We have to be careful so that traversals of obj_list under lock can
+	 * safely grab mark reference.
+	 */
+	if (!atomic_dec_and_lock(&mark->refcnt, &mark->connector->lock))
+		return;
 
-	if (mark->flags & FSNOTIFY_MARK_FLAG_INODE) {
-		inode = mark->inode;
-		fsnotify_destroy_inode_mark(mark);
-	} else if (mark->flags & FSNOTIFY_MARK_FLAG_VFSMOUNT)
-		fsnotify_destroy_vfsmount_mark(mark);
-	else
-		BUG();
+	conn = mark->connector;
+	hlist_del_init_rcu(&mark->obj_list);
+	if (hlist_empty(&conn->list)) {
+		inode = fsnotify_detach_connector_from_object(conn);
+		free_conn = true;
+	} else {
+		__fsnotify_recalc_mask(conn);
+	}
+	mark->connector = NULL;
+	spin_unlock(&conn->lock);
+
+	iput(inode);
+
+	if (free_conn) {
+		spin_lock(&destroy_lock);
+		conn->destroy_next = connector_destroy_list;
+		connector_destroy_list = conn;
+		spin_unlock(&destroy_lock);
+		queue_work(system_unbound_wq, &connector_reaper_work);
+	}
 	/*
 	 * Note that we didn't update flags telling whether inode cares about
 	 * what's happening with children. We update these flags from
 	 * __fsnotify_parent() lazily when next event happens on one of our
 	 * children.
 	 */
+	spin_lock(&destroy_lock);
+	list_add(&mark->g_list, &destroy_list);
+	spin_unlock(&destroy_lock);
+	queue_delayed_work(system_unbound_wq, &reaper_work,
+			   FSNOTIFY_REAPER_DELAY);
+}
 
-	list_del_init(&mark->g_list);
+bool fsnotify_prepare_user_wait(struct fsnotify_iter_info *iter_info)
+{
+	struct fsnotify_group *group;
 
-	spin_unlock(&mark->lock);
+	if (WARN_ON_ONCE(!iter_info->inode_mark && !iter_info->vfsmount_mark))
+		return false;
+
+	if (iter_info->inode_mark)
+		group = iter_info->inode_mark->group;
+	else
+		group = iter_info->vfsmount_mark->group;
+
+	/*
+	 * Since acquisition of mark reference is an atomic op as well, we can
+	 * be sure this inc is seen before any effect of refcount increment.
+	 */
+	atomic_inc(&group->user_waits);
+
+	if (iter_info->inode_mark) {
+		/* This can fail if mark is being removed */
+		if (!fsnotify_get_mark_safe(iter_info->inode_mark))
+			goto out_wait;
+	}
+	if (iter_info->vfsmount_mark) {
+		if (!fsnotify_get_mark_safe(iter_info->vfsmount_mark))
+			goto out_inode;
+	}
 
-	if (inode && (mark->flags & FSNOTIFY_MARK_FLAG_OBJECT_PINNED))
-		iput(inode);
+	/*
+	 * Now that both marks are pinned by refcount in the inode / vfsmount
+	 * lists, we can drop SRCU lock, and safely resume the list iteration
+	 * once userspace returns.
+	 */
+	srcu_read_unlock(&fsnotify_mark_srcu, iter_info->srcu_idx);
+
+	return true;
+out_inode:
+	if (iter_info->inode_mark)
+		fsnotify_put_mark(iter_info->inode_mark);
+out_wait:
+	if (atomic_dec_and_test(&group->user_waits) && group->shutdown)
+		wake_up(&group->notification_waitq);
+	return false;
+}
+
+void fsnotify_finish_user_wait(struct fsnotify_iter_info *iter_info)
+{
+	struct fsnotify_group *group = NULL;
+
+	iter_info->srcu_idx = srcu_read_lock(&fsnotify_mark_srcu);
+	if (iter_info->inode_mark) {
+		group = iter_info->inode_mark->group;
+		fsnotify_put_mark(iter_info->inode_mark);
+	}
+	if (iter_info->vfsmount_mark) {
+		group = iter_info->vfsmount_mark->group;
+		fsnotify_put_mark(iter_info->vfsmount_mark);
+	}
+	/*
+	 * We abuse notification_waitq on group shutdown for waiting for all
+	 * marks pinned when waiting for userspace.
+	 */
+	if (atomic_dec_and_test(&group->user_waits) && group->shutdown)
+		wake_up(&group->notification_waitq);
+}
+
+/*
+ * Mark mark as detached, remove it from group list. Mark still stays in object
+ * list until its last reference is dropped. Note that we rely on mark being
+ * removed from group list before corresponding reference to it is dropped. In
+ * particular we rely on mark->connector being valid while we hold
+ * group->mark_mutex if we found the mark through g_list.
+ *
+ * Must be called with group->mark_mutex held. The caller must either hold
+ * reference to the mark or be protected by fsnotify_mark_srcu.
+ */
+void fsnotify_detach_mark(struct fsnotify_mark *mark)
+{
+	struct fsnotify_group *group = mark->group;
+
+	WARN_ON_ONCE(!mutex_is_locked(&group->mark_mutex));
+	WARN_ON_ONCE(!srcu_read_lock_held(&fsnotify_mark_srcu) &&
+		     atomic_read(&mark->refcnt) < 1 +
+			!!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED));
+
+	spin_lock(&mark->lock);
+	/* something else already called this function on this mark */
+	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
+		spin_unlock(&mark->lock);
+		return;
+	}
+	mark->flags &= ~FSNOTIFY_MARK_FLAG_ATTACHED;
+	list_del_init(&mark->g_list);
+	spin_unlock(&mark->lock);
 
 	atomic_dec(&group->num_marks);
+
+	/* Drop mark reference acquired in fsnotify_add_mark_locked() */
+	fsnotify_put_mark(mark);
 }
 
 /*
- * Prepare mark for freeing and add it to the list of marks prepared for
- * freeing. The actual freeing must happen after SRCU period ends and the
- * caller is responsible for this.
+ * Free fsnotify mark. The mark is actually only marked as being freed.  The
+ * freeing is actually happening only once last reference to the mark is
+ * dropped from a workqueue which first waits for srcu period end.
  *
- * The function returns true if the mark was added to the list of marks for
- * freeing. The function returns false if someone else has already called
- * __fsnotify_free_mark() for the mark.
+ * Caller must have a reference to the mark or be protected by
+ * fsnotify_mark_srcu.
  */
-static bool __fsnotify_free_mark(struct fsnotify_mark *mark)
+void fsnotify_free_mark(struct fsnotify_mark *mark)
 {
 	struct fsnotify_group *group = mark->group;
 
@@ -189,7 +373,7 @@ static bool __fsnotify_free_mark(struct fsnotify_mark *mark)
 	/* something else already called this function on this mark */
 	if (!(mark->flags & FSNOTIFY_MARK_FLAG_ALIVE)) {
 		spin_unlock(&mark->lock);
-		return false;
+		return;
 	}
 	mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
 	spin_unlock(&mark->lock);
@@ -201,25 +385,6 @@ static bool __fsnotify_free_mark(struct fsnotify_mark *mark)
 	 */
 	if (group->ops->freeing_mark)
 		group->ops->freeing_mark(mark, group);
-
-	spin_lock(&destroy_lock);
-	list_add(&mark->g_list, &destroy_list);
-	spin_unlock(&destroy_lock);
-
-	return true;
-}
-
-/*
- * Free fsnotify mark. The freeing is actually happening from a workqueue which
- * first waits for srcu period end. Caller must have a reference to the mark
- * or be protected by fsnotify_mark_srcu.
- */
-void fsnotify_free_mark(struct fsnotify_mark *mark)
-{
-	if (__fsnotify_free_mark(mark)) {
-		queue_delayed_work(system_unbound_wq, &reaper_work,
-				   FSNOTIFY_REAPER_DELAY);
-	}
 }
 
 void fsnotify_destroy_mark(struct fsnotify_mark *mark,
@@ -231,54 +396,6 @@ void fsnotify_destroy_mark(struct fsnotify_mark *mark,
 	fsnotify_free_mark(mark);
 }
 
-void fsnotify_destroy_marks(struct hlist_head *head, spinlock_t *lock)
-{
-	struct fsnotify_mark *mark;
-
-	while (1) {
-		/*
-		 * We have to be careful since we can race with e.g.
-		 * fsnotify_clear_marks_by_group() and once we drop 'lock',
-		 * mark can get removed from the obj_list and destroyed. But
-		 * we are holding mark reference so mark cannot be freed and
-		 * calling fsnotify_destroy_mark() more than once is fine.
-		 */
-		spin_lock(lock);
-		if (hlist_empty(head)) {
-			spin_unlock(lock);
-			break;
-		}
-		mark = hlist_entry(head->first, struct fsnotify_mark, obj_list);
-		/*
-		 * We don't update i_fsnotify_mask / mnt_fsnotify_mask here
-		 * since inode / mount is going away anyway. So just remove
-		 * mark from the list.
-		 */
-		hlist_del_init_rcu(&mark->obj_list);
-		fsnotify_get_mark(mark);
-		spin_unlock(lock);
-		fsnotify_destroy_mark(mark, mark->group);
-		fsnotify_put_mark(mark);
-	}
-}
-
-void fsnotify_set_mark_mask_locked(struct fsnotify_mark *mark, __u32 mask)
-{
-	assert_spin_locked(&mark->lock);
-
-	mark->mask = mask;
-
-	if (mark->flags & FSNOTIFY_MARK_FLAG_INODE)
-		fsnotify_set_inode_mark_mask_locked(mark, mask);
-}
-
-void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mask)
-{
-	assert_spin_locked(&mark->lock);
-
-	mark->ignored_mask = mask;
-}
-
 /*
  * Sorting function for lists of fsnotify marks.
  *
@@ -315,37 +432,133 @@ int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b)
 	return -1;
 }
 
-/* Add mark into proper place in given list of marks */
-int fsnotify_add_mark_list(struct hlist_head *head, struct fsnotify_mark *mark,
-			   int allow_dups)
+static int fsnotify_attach_connector_to_object(
+				struct fsnotify_mark_connector __rcu **connp,
+				struct inode *inode,
+				struct vfsmount *mnt)
+{
+	struct fsnotify_mark_connector *conn;
+
+	conn = kmem_cache_alloc(fsnotify_mark_connector_cachep, GFP_KERNEL);
+	if (!conn)
+		return -ENOMEM;
+	spin_lock_init(&conn->lock);
+	INIT_HLIST_HEAD(&conn->list);
+	if (inode) {
+		conn->flags = FSNOTIFY_OBJ_TYPE_INODE;
+		conn->inode = igrab(inode);
+	} else {
+		conn->flags = FSNOTIFY_OBJ_TYPE_VFSMOUNT;
+		conn->mnt = mnt;
+	}
+	/*
+	 * cmpxchg() provides the barrier so that readers of *connp can see
+	 * only initialized structure
+	 */
+	if (cmpxchg(connp, NULL, conn)) {
+		/* Someone else created list structure for us */
+		if (inode)
+			iput(inode);
+		kmem_cache_free(fsnotify_mark_connector_cachep, conn);
+	}
+
+	return 0;
+}
+
+/*
+ * Get mark connector, make sure it is alive and return with its lock held.
+ * This is for users that get connector pointer from inode or mount. Users that
+ * hold reference to a mark on the list may directly lock connector->lock as
+ * they are sure list cannot go away under them.
+ */
+static struct fsnotify_mark_connector *fsnotify_grab_connector(
+				struct fsnotify_mark_connector __rcu **connp)
+{
+	struct fsnotify_mark_connector *conn;
+	int idx;
+
+	idx = srcu_read_lock(&fsnotify_mark_srcu);
+	conn = srcu_dereference(*connp, &fsnotify_mark_srcu);
+	if (!conn)
+		goto out;
+	spin_lock(&conn->lock);
+	if (!(conn->flags & (FSNOTIFY_OBJ_TYPE_INODE |
+			     FSNOTIFY_OBJ_TYPE_VFSMOUNT))) {
+		spin_unlock(&conn->lock);
+		srcu_read_unlock(&fsnotify_mark_srcu, idx);
+		return NULL;
+	}
+out:
+	srcu_read_unlock(&fsnotify_mark_srcu, idx);
+	return conn;
+}
+
+/*
+ * Add mark into proper place in given list of marks. These marks may be used
+ * for the fsnotify backend to determine which event types should be delivered
+ * to which group and for which inodes. These marks are ordered according to
+ * priority, highest number first, and then by the group's location in memory.
+ */
+static int fsnotify_add_mark_list(struct fsnotify_mark *mark,
+				  struct inode *inode, struct vfsmount *mnt,
+				  int allow_dups)
 {
 	struct fsnotify_mark *lmark, *last = NULL;
+	struct fsnotify_mark_connector *conn;
+	struct fsnotify_mark_connector __rcu **connp;
 	int cmp;
+	int err = 0;
+
+	if (WARN_ON(!inode && !mnt))
+		return -EINVAL;
+	if (inode)
+		connp = &inode->i_fsnotify_marks;
+	else
+		connp = &real_mount(mnt)->mnt_fsnotify_marks;
+restart:
+	spin_lock(&mark->lock);
+	conn = fsnotify_grab_connector(connp);
+	if (!conn) {
+		spin_unlock(&mark->lock);
+		err = fsnotify_attach_connector_to_object(connp, inode, mnt);
+		if (err)
+			return err;
+		goto restart;
+	}
 
 	/* is mark the first mark? */
-	if (hlist_empty(head)) {
-		hlist_add_head_rcu(&mark->obj_list, head);
-		return 0;
+	if (hlist_empty(&conn->list)) {
+		hlist_add_head_rcu(&mark->obj_list, &conn->list);
+		goto added;
 	}
 
 	/* should mark be in the middle of the current list? */
-	hlist_for_each_entry(lmark, head, obj_list) {
+	hlist_for_each_entry(lmark, &conn->list, obj_list) {
 		last = lmark;
 
-		if ((lmark->group == mark->group) && !allow_dups)
-			return -EEXIST;
+		if ((lmark->group == mark->group) &&
+		    (lmark->flags & FSNOTIFY_MARK_FLAG_ATTACHED) &&
+		    !allow_dups) {
+			err = -EEXIST;
+			goto out_err;
+		}
 
 		cmp = fsnotify_compare_groups(lmark->group, mark->group);
 		if (cmp >= 0) {
 			hlist_add_before_rcu(&mark->obj_list, &lmark->obj_list);
-			return 0;
+			goto added;
 		}
 	}
 
 	BUG_ON(last == NULL);
 	/* mark should be the last entry.  last is the current last entry */
 	hlist_add_behind_rcu(&mark->obj_list, &last->obj_list);
-	return 0;
+added:
+	mark->connector = conn;
+out_err:
+	spin_unlock(&conn->lock);
+	spin_unlock(&mark->lock);
+	return err;
 }
 
 /*
@@ -353,10 +566,10 @@ int fsnotify_add_mark_list(struct hlist_head *head, struct fsnotify_mark *mark,
  * These marks may be used for the fsnotify backend to determine which
  * event types should be delivered to which group.
  */
-int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
-			     struct fsnotify_group *group, struct inode *inode,
+int fsnotify_add_mark_locked(struct fsnotify_mark *mark, struct inode *inode,
 			     struct vfsmount *mnt, int allow_dups)
 {
+	struct fsnotify_group *group = mark->group;
 	int ret = 0;
 
 	BUG_ON(inode && mnt);
@@ -367,61 +580,42 @@ int fsnotify_add_mark_locked(struct fsnotify_mark *mark,
 	 * LOCKING ORDER!!!!
 	 * group->mark_mutex
 	 * mark->lock
-	 * inode->i_lock
+	 * mark->connector->lock
 	 */
 	spin_lock(&mark->lock);
 	mark->flags |= FSNOTIFY_MARK_FLAG_ALIVE | FSNOTIFY_MARK_FLAG_ATTACHED;
 
-	fsnotify_get_group(group);
-	mark->group = group;
 	list_add(&mark->g_list, &group->marks_list);
 	atomic_inc(&group->num_marks);
-	fsnotify_get_mark(mark); /* for i_list and g_list */
-
-	if (inode) {
-		ret = fsnotify_add_inode_mark(mark, group, inode, allow_dups);
-		if (ret)
-			goto err;
-	} else if (mnt) {
-		ret = fsnotify_add_vfsmount_mark(mark, group, mnt, allow_dups);
-		if (ret)
-			goto err;
-	} else {
-		BUG();
-	}
-
-	/* this will pin the object if appropriate */
-	fsnotify_set_mark_mask_locked(mark, mark->mask);
+	fsnotify_get_mark(mark); /* for g_list */
 	spin_unlock(&mark->lock);
 
-	if (inode)
-		__fsnotify_update_child_dentry_flags(inode);
+	ret = fsnotify_add_mark_list(mark, inode, mnt, allow_dups);
+	if (ret)
+		goto err;
+
+	if (mark->mask)
+		fsnotify_recalc_mask(mark->connector);
 
 	return ret;
 err:
-	mark->flags &= ~FSNOTIFY_MARK_FLAG_ALIVE;
+	mark->flags &= ~(FSNOTIFY_MARK_FLAG_ALIVE |
+			 FSNOTIFY_MARK_FLAG_ATTACHED);
 	list_del_init(&mark->g_list);
-	fsnotify_put_group(group);
-	mark->group = NULL;
 	atomic_dec(&group->num_marks);
 
-	spin_unlock(&mark->lock);
-
-	spin_lock(&destroy_lock);
-	list_add(&mark->g_list, &destroy_list);
-	spin_unlock(&destroy_lock);
-	queue_delayed_work(system_unbound_wq, &reaper_work,
-				FSNOTIFY_REAPER_DELAY);
-
+	fsnotify_put_mark(mark);
 	return ret;
 }
 
-int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
-		      struct inode *inode, struct vfsmount *mnt, int allow_dups)
+int fsnotify_add_mark(struct fsnotify_mark *mark, struct inode *inode,
+		      struct vfsmount *mnt, int allow_dups)
 {
 	int ret;
+	struct fsnotify_group *group = mark->group;
+
 	mutex_lock(&group->mark_mutex);
-	ret = fsnotify_add_mark_locked(mark, group, inode, mnt, allow_dups);
+	ret = fsnotify_add_mark_locked(mark, inode, mnt, allow_dups);
 	mutex_unlock(&group->mark_mutex);
 	return ret;
 }
@@ -430,29 +624,42 @@ int fsnotify_add_mark(struct fsnotify_mark *mark, struct fsnotify_group *group,
  * Given a list of marks, find the mark associated with given group. If found
  * take a reference to that mark and return it, else return NULL.
  */
-struct fsnotify_mark *fsnotify_find_mark(struct hlist_head *head,
-					 struct fsnotify_group *group)
+struct fsnotify_mark *fsnotify_find_mark(
+				struct fsnotify_mark_connector __rcu **connp,
+				struct fsnotify_group *group)
 {
+	struct fsnotify_mark_connector *conn;
 	struct fsnotify_mark *mark;
 
-	hlist_for_each_entry(mark, head, obj_list) {
-		if (mark->group == group) {
+	conn = fsnotify_grab_connector(connp);
+	if (!conn)
+		return NULL;
+
+	hlist_for_each_entry(mark, &conn->list, obj_list) {
+		if (mark->group == group &&
+		    (mark->flags & FSNOTIFY_MARK_FLAG_ATTACHED)) {
 			fsnotify_get_mark(mark);
+			spin_unlock(&conn->lock);
 			return mark;
 		}
 	}
+	spin_unlock(&conn->lock);
 	return NULL;
 }
 
-/*
- * clear any marks in a group in which mark->flags & flags is true
- */
-void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
-					 unsigned int flags)
+/* Clear any marks in a group with given type */
+void fsnotify_clear_marks_by_group(struct fsnotify_group *group,
+				   unsigned int type)
 {
 	struct fsnotify_mark *lmark, *mark;
 	LIST_HEAD(to_free);
+	struct list_head *head = &to_free;
 
+	/* Skip selection step if we want to clear all marks. */
+	if (type == FSNOTIFY_OBJ_ALL_TYPES) {
+		head = &group->marks_list;
+		goto clear;
+	}
 	/*
 	 * We have to be really careful here. Anytime we drop mark_mutex, e.g.
 	 * fsnotify_clear_marks_by_inode() can come and free marks. Even in our
@@ -464,18 +671,19 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
 	 */
 	mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
 	list_for_each_entry_safe(mark, lmark, &group->marks_list, g_list) {
-		if (mark->flags & flags)
+		if (mark->connector->flags & type)
 			list_move(&mark->g_list, &to_free);
 	}
 	mutex_unlock(&group->mark_mutex);
 
+clear:
 	while (1) {
 		mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
-		if (list_empty(&to_free)) {
+		if (list_empty(head)) {
 			mutex_unlock(&group->mark_mutex);
 			break;
 		}
-		mark = list_first_entry(&to_free, struct fsnotify_mark, g_list);
+		mark = list_first_entry(head, struct fsnotify_mark, g_list);
 		fsnotify_get_mark(mark);
 		fsnotify_detach_mark(mark);
 		mutex_unlock(&group->mark_mutex);
@@ -484,49 +692,62 @@ void fsnotify_clear_marks_by_group_flags(struct fsnotify_group *group,
 	}
 }
 
-/*
- * Given a group, prepare for freeing all the marks associated with that group.
- * The marks are attached to the list of marks prepared for destruction, the
- * caller is responsible for freeing marks in that list after SRCU period has
- * ended.
- */
-void fsnotify_detach_group_marks(struct fsnotify_group *group)
+/* Destroy all marks attached to inode / vfsmount */
+void fsnotify_destroy_marks(struct fsnotify_mark_connector __rcu **connp)
 {
-	struct fsnotify_mark *mark;
+	struct fsnotify_mark_connector *conn;
+	struct fsnotify_mark *mark, *old_mark = NULL;
+	struct inode *inode;
 
-	while (1) {
-		mutex_lock_nested(&group->mark_mutex, SINGLE_DEPTH_NESTING);
-		if (list_empty(&group->marks_list)) {
-			mutex_unlock(&group->mark_mutex);
-			break;
-		}
-		mark = list_first_entry(&group->marks_list,
-					struct fsnotify_mark, g_list);
+	conn = fsnotify_grab_connector(connp);
+	if (!conn)
+		return;
+	/*
+	 * We have to be careful since we can race with e.g.
+	 * fsnotify_clear_marks_by_group() and once we drop the conn->lock, the
+	 * list can get modified. However we are holding mark reference and
+	 * thus our mark cannot be removed from obj_list so we can continue
+	 * iteration after regaining conn->lock.
+	 */
+	hlist_for_each_entry(mark, &conn->list, obj_list) {
 		fsnotify_get_mark(mark);
-		fsnotify_detach_mark(mark);
-		mutex_unlock(&group->mark_mutex);
-		__fsnotify_free_mark(mark);
-		fsnotify_put_mark(mark);
+		spin_unlock(&conn->lock);
+		if (old_mark)
+			fsnotify_put_mark(old_mark);
+		old_mark = mark;
+		fsnotify_destroy_mark(mark, mark->group);
+		spin_lock(&conn->lock);
 	}
+	/*
+	 * Detach list from object now so that we don't pin inode until all
+	 * mark references get dropped. It would lead to strange results such
+	 * as delaying inode deletion or blocking unmount.
+	 */
+	inode = fsnotify_detach_connector_from_object(conn);
+	spin_unlock(&conn->lock);
+	if (old_mark)
+		fsnotify_put_mark(old_mark);
+	iput(inode);
 }
 
 /*
  * Nothing fancy, just initialize lists and locks and counters.
  */
 void fsnotify_init_mark(struct fsnotify_mark *mark,
-			void (*free_mark)(struct fsnotify_mark *mark))
+			struct fsnotify_group *group)
 {
 	memset(mark, 0, sizeof(*mark));
 	spin_lock_init(&mark->lock);
 	atomic_set(&mark->refcnt, 1);
-	mark->free_mark = free_mark;
+	fsnotify_get_group(group);
+	mark->group = group;
 }
 
 /*
  * Destroy all marks in destroy_list, waits for SRCU period to finish before
  * actually freeing marks.
  */
-void fsnotify_mark_destroy_list(void)
+static void fsnotify_mark_destroy_workfn(struct work_struct *work)
 {
 	struct fsnotify_mark *mark, *next;
 	struct list_head private_destroy_list;
@@ -540,11 +761,12 @@ void fsnotify_mark_destroy_list(void)
 
 	list_for_each_entry_safe(mark, next, &private_destroy_list, g_list) {
 		list_del_init(&mark->g_list);
-		fsnotify_put_mark(mark);
+		fsnotify_final_mark_destroy(mark);
 	}
 }
 
-static void fsnotify_mark_destroy_workfn(struct work_struct *work)
+/* Wait for all marks queued for destruction to be actually destroyed */
+void fsnotify_wait_marks_destroyed(void)
 {
-	fsnotify_mark_destroy_list();
+	flush_delayed_work(&reaper_work);
 }
diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c
deleted file mode 100644
index a8fcab68faef..000000000000
--- a/fs/notify/vfsmount_mark.c
+++ /dev/null
@@ -1,108 +0,0 @@
-/*
- *  Copyright (C) 2008 Red Hat, Inc., Eric Paris <eparis@redhat.com>
- *
- *  This program is free software; you can redistribute it and/or modify
- *  it under the terms of the GNU General Public License as published by
- *  the Free Software Foundation; either version 2, or (at your option)
- *  any later version.
- *
- *  This program is distributed in the hope that it will be useful,
- *  but WITHOUT ANY WARRANTY; without even the implied warranty of
- *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- *  GNU General Public License for more details.
- *
- *  You should have received a copy of the GNU General Public License
- *  along with this program; see the file COPYING.  If not, write to
- *  the Free Software Foundation, 675 Mass Ave, Cambridge, MA 02139, USA.
- */
-
-#include <linux/fs.h>
-#include <linux/init.h>
-#include <linux/kernel.h>
-#include <linux/module.h>
-#include <linux/mount.h>
-#include <linux/mutex.h>
-#include <linux/spinlock.h>
-
-#include <linux/atomic.h>
-
-#include <linux/fsnotify_backend.h>
-#include "fsnotify.h"
-
-void fsnotify_clear_vfsmount_marks_by_group(struct fsnotify_group *group)
-{
-	fsnotify_clear_marks_by_group_flags(group, FSNOTIFY_MARK_FLAG_VFSMOUNT);
-}
-
-/*
- * Recalculate the mnt->mnt_fsnotify_mask, or the mask of all FS_* event types
- * any notifier is interested in hearing for this mount point
- */
-void fsnotify_recalc_vfsmount_mask(struct vfsmount *mnt)
-{
-	struct mount *m = real_mount(mnt);
-
-	spin_lock(&mnt->mnt_root->d_lock);
-	m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
-	spin_unlock(&mnt->mnt_root->d_lock);
-}
-
-void fsnotify_destroy_vfsmount_mark(struct fsnotify_mark *mark)
-{
-	struct vfsmount *mnt = mark->mnt;
-	struct mount *m = real_mount(mnt);
-
-	BUG_ON(!mutex_is_locked(&mark->group->mark_mutex));
-	assert_spin_locked(&mark->lock);
-
-	spin_lock(&mnt->mnt_root->d_lock);
-
-	hlist_del_init_rcu(&mark->obj_list);
-	mark->mnt = NULL;
-
-	m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
-	spin_unlock(&mnt->mnt_root->d_lock);
-}
-
-/*
- * given a group and vfsmount, find the mark associated with that combination.
- * if found take a reference to that mark and return it, else return NULL
- */
-struct fsnotify_mark *fsnotify_find_vfsmount_mark(struct fsnotify_group *group,
-						  struct vfsmount *mnt)
-{
-	struct mount *m = real_mount(mnt);
-	struct fsnotify_mark *mark;
-
-	spin_lock(&mnt->mnt_root->d_lock);
-	mark = fsnotify_find_mark(&m->mnt_fsnotify_marks, group);
-	spin_unlock(&mnt->mnt_root->d_lock);
-
-	return mark;
-}
-
-/*
- * Attach an initialized mark to a given group and vfsmount.
- * These marks may be used for the fsnotify backend to determine which
- * event types should be delivered to which groups.
- */
-int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark,
-			       struct fsnotify_group *group, struct vfsmount *mnt,
-			       int allow_dups)
-{
-	struct mount *m = real_mount(mnt);
-	int ret;
-
-	mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT;
-
-	BUG_ON(!mutex_is_locked(&group->mark_mutex));
-	assert_spin_locked(&mark->lock);
-
-	spin_lock(&mnt->mnt_root->d_lock);
-	mark->mnt = mnt;
-	ret = fsnotify_add_mark_list(&m->mnt_fsnotify_marks, mark, allow_dups);
-	m->mnt_fsnotify_mask = fsnotify_recalc_mask(&m->mnt_fsnotify_marks);
-	spin_unlock(&mnt->mnt_root->d_lock);
-
-	return ret;
-}
diff --git a/fs/nsfs.c b/fs/nsfs.c
index 8c9fb29c6673..08127a2b8559 100644
--- a/fs/nsfs.c
+++ b/fs/nsfs.c
@@ -7,6 +7,7 @@
 #include <linux/seq_file.h>
 #include <linux/user_namespace.h>
 #include <linux/nsfs.h>
+#include <linux/uaccess.h>
 
 static struct vfsmount *nsfs_mnt;
 
@@ -52,7 +53,6 @@ static void nsfs_evict(struct inode *inode)
 static void *__ns_get_path(struct path *path, struct ns_common *ns)
 {
 	struct vfsmount *mnt = nsfs_mnt;
-	struct qstr qname = { .name = "", };
 	struct dentry *dentry;
 	struct inode *inode;
 	unsigned long d;
@@ -84,12 +84,13 @@ slow:
 	inode->i_fop = &ns_file_operations;
 	inode->i_private = ns;
 
-	dentry = d_alloc_pseudo(mnt->mnt_sb, &qname);
+	dentry = d_alloc_pseudo(mnt->mnt_sb, &empty_name);
 	if (!dentry) {
 		iput(inode);
 		return ERR_PTR(-ENOMEM);
 	}
 	d_instantiate(dentry, inode);
+	dentry->d_flags |= DCACHE_RCUACCESS;
 	dentry->d_fsdata = (void *)ns->ops;
 	d = atomic_long_cmpxchg(&ns->stashed, 0, (unsigned long)dentry);
 	if (d) {
@@ -163,7 +164,10 @@ int open_related_ns(struct ns_common *ns,
 static long ns_ioctl(struct file *filp, unsigned int ioctl,
 			unsigned long arg)
 {
+	struct user_namespace *user_ns;
 	struct ns_common *ns = get_proc_ns(file_inode(filp));
+	uid_t __user *argp;
+	uid_t uid;
 
 	switch (ioctl) {
 	case NS_GET_USERNS:
@@ -172,6 +176,15 @@ static long ns_ioctl(struct file *filp, unsigned int ioctl,
 		if (!ns->ops->get_parent)
 			return -EINVAL;
 		return open_related_ns(ns, ns->ops->get_parent);
+	case NS_GET_NSTYPE:
+		return ns->ops->type;
+	case NS_GET_OWNER_UID:
+		if (ns->ops->type != CLONE_NEWUSER)
+			return -EINVAL;
+		user_ns = container_of(ns, struct user_namespace, ns);
+		argp = (uid_t __user *) arg;
+		uid = from_kuid_munged(current_user_ns(), user_ns->owner);
+		return put_user(uid, argp);
 	default:
 		return -ENOTTY;
 	}
@@ -182,9 +195,11 @@ int ns_get_name(char *buf, size_t size, struct task_struct *task,
 {
 	struct ns_common *ns;
 	int res = -ENOENT;
+	const char *name;
 	ns = ns_ops->get(task);
 	if (ns) {
-		res = snprintf(buf, size, "%s:[%u]", ns_ops->name, ns->inum);
+		name = ns_ops->real_ns_name ? : ns_ops->name;
+		res = snprintf(buf, size, "%s:[%u]", name, ns->inum);
 		ns_ops->put(ns);
 	}
 	return res;
diff --git a/fs/ntfs/file.c b/fs/ntfs/file.c
index 358ed7e1195a..c4f68c338735 100644
--- a/fs/ntfs/file.c
+++ b/fs/ntfs/file.c
@@ -24,7 +24,7 @@
 #include <linux/gfp.h>
 #include <linux/pagemap.h>
 #include <linux/pagevec.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/swap.h>
 #include <linux/uio.h>
 #include <linux/writeback.h>
diff --git a/fs/ntfs/namei.c b/fs/ntfs/namei.c
index 358258364616..4690cd75d8d7 100644
--- a/fs/ntfs/namei.c
+++ b/fs/ntfs/namei.c
@@ -159,7 +159,7 @@ static struct dentry *ntfs_lookup(struct inode *dir_ino, struct dentry *dent,
 					PTR_ERR(dent_inode));
 		kfree(name);
 		/* Return the error code. */
-		return (struct dentry *)dent_inode;
+		return ERR_CAST(dent_inode);
 	}
 	/* It is guaranteed that @name is no longer allocated at this point. */
 	if (MREF_ERR(mref) == -ENOENT) {
diff --git a/fs/ocfs2/acl.c b/fs/ocfs2/acl.c
index bed1fcb63088..dc22ba8c710f 100644
--- a/fs/ocfs2/acl.c
+++ b/fs/ocfs2/acl.c
@@ -283,16 +283,14 @@ int ocfs2_set_acl(handle_t *handle,
 int ocfs2_iop_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	struct buffer_head *bh = NULL;
-	int status = 0;
+	int status, had_lock;
+	struct ocfs2_lock_holder oh;
 
-	status = ocfs2_inode_lock(inode, &bh, 1);
-	if (status < 0) {
-		if (status != -ENOENT)
-			mlog_errno(status);
-		return status;
-	}
+	had_lock = ocfs2_inode_lock_tracker(inode, &bh, 1, &oh);
+	if (had_lock < 0)
+		return had_lock;
 	status = ocfs2_set_acl(NULL, inode, bh, type, acl, NULL, NULL);
-	ocfs2_inode_unlock(inode, 1);
+	ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);
 	brelse(bh);
 	return status;
 }
@@ -302,21 +300,20 @@ struct posix_acl *ocfs2_iop_get_acl(struct inode *inode, int type)
 	struct ocfs2_super *osb;
 	struct buffer_head *di_bh = NULL;
 	struct posix_acl *acl;
-	int ret;
+	int had_lock;
+	struct ocfs2_lock_holder oh;
 
 	osb = OCFS2_SB(inode->i_sb);
 	if (!(osb->s_mount_opt & OCFS2_MOUNT_POSIX_ACL))
 		return NULL;
-	ret = ocfs2_inode_lock(inode, &di_bh, 0);
-	if (ret < 0) {
-		if (ret != -ENOENT)
-			mlog_errno(ret);
-		return ERR_PTR(ret);
-	}
+
+	had_lock = ocfs2_inode_lock_tracker(inode, &di_bh, 0, &oh);
+	if (had_lock < 0)
+		return ERR_PTR(had_lock);
 
 	acl = ocfs2_get_acl_nolock(inode, type, di_bh);
 
-	ocfs2_inode_unlock(inode, 0);
+	ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock);
 	brelse(di_bh);
 	return acl;
 }
diff --git a/fs/ocfs2/alloc.c b/fs/ocfs2/alloc.c
index d4ec0d8961a6..fb15a96df0b6 100644
--- a/fs/ocfs2/alloc.c
+++ b/fs/ocfs2/alloc.c
@@ -30,6 +30,7 @@
 #include <linux/swap.h>
 #include <linux/quotaops.h>
 #include <linux/blkdev.h>
+#include <linux/sched/signal.h>
 
 #include <cluster/masklog.h>
 
diff --git a/fs/ocfs2/aops.c b/fs/ocfs2/aops.c
index 11556b7d93ec..88a31e9340a0 100644
--- a/fs/ocfs2/aops.c
+++ b/fs/ocfs2/aops.c
@@ -608,7 +608,7 @@ int ocfs2_map_page_blocks(struct page *page, u64 *p_blkno,
 	int ret = 0;
 	struct buffer_head *head, *bh, *wait[2], **wait_bh = wait;
 	unsigned int block_end, block_start;
-	unsigned int bsize = 1 << inode->i_blkbits;
+	unsigned int bsize = i_blocksize(inode);
 
 	if (!page_has_buffers(page))
 		create_empty_buffers(page, bsize, 0);
diff --git a/fs/ocfs2/cluster/heartbeat.c b/fs/ocfs2/cluster/heartbeat.c
index f6e871760f8d..ffe003982d95 100644
--- a/fs/ocfs2/cluster/heartbeat.c
+++ b/fs/ocfs2/cluster/heartbeat.c
@@ -516,9 +516,9 @@ static void o2hb_bio_end_io(struct bio *bio)
 {
 	struct o2hb_bio_wait_ctxt *wc = bio->bi_private;
 
-	if (bio->bi_error) {
-		mlog(ML_ERROR, "IO Error %d\n", bio->bi_error);
-		wc->wc_error = bio->bi_error;
+	if (bio->bi_status) {
+		mlog(ML_ERROR, "IO Error %d\n", bio->bi_status);
+		wc->wc_error = blk_status_to_errno(bio->bi_status);
 	}
 
 	o2hb_bio_wait_dec(wc, 1);
@@ -2242,13 +2242,13 @@ unlock:
 	spin_unlock(&o2hb_live_lock);
 }
 
-static ssize_t o2hb_heartbeat_group_threshold_show(struct config_item *item,
+static ssize_t o2hb_heartbeat_group_dead_threshold_show(struct config_item *item,
 		char *page)
 {
 	return sprintf(page, "%u\n", o2hb_dead_threshold);
 }
 
-static ssize_t o2hb_heartbeat_group_threshold_store(struct config_item *item,
+static ssize_t o2hb_heartbeat_group_dead_threshold_store(struct config_item *item,
 		const char *page, size_t count)
 {
 	unsigned long tmp;
@@ -2297,11 +2297,11 @@ static ssize_t o2hb_heartbeat_group_mode_store(struct config_item *item,
 
 }
 
-CONFIGFS_ATTR(o2hb_heartbeat_group_, threshold);
+CONFIGFS_ATTR(o2hb_heartbeat_group_, dead_threshold);
 CONFIGFS_ATTR(o2hb_heartbeat_group_, mode);
 
 static struct configfs_attribute *o2hb_heartbeat_group_attrs[] = {
-	&o2hb_heartbeat_group_attr_threshold,
+	&o2hb_heartbeat_group_attr_dead_threshold,
 	&o2hb_heartbeat_group_attr_mode,
 	NULL,
 };
diff --git a/fs/ocfs2/cluster/netdebug.c b/fs/ocfs2/cluster/netdebug.c
index 27d1242c8383..74a21f6695c8 100644
--- a/fs/ocfs2/cluster/netdebug.c
+++ b/fs/ocfs2/cluster/netdebug.c
@@ -349,7 +349,7 @@ static void sc_show_sock_container(struct seq_file *seq,
 		   "  func key:        0x%08x\n"
 		   "  func type:       %u\n",
 		   sc,
-		   atomic_read(&sc->sc_kref.refcount),
+		   kref_read(&sc->sc_kref),
 		   &saddr, inet ? ntohs(sport) : 0,
 		   &daddr, inet ? ntohs(dport) : 0,
 		   sc->sc_node->nd_name,
@@ -426,6 +426,7 @@ static int sc_fop_release(struct inode *inode, struct file *file)
 	struct o2net_sock_container *dummy_sc = sd->dbg_sock;
 
 	o2net_debug_del_sc(dummy_sc);
+	kfree(dummy_sc);
 	return seq_release_private(inode, file);
 }
 
diff --git a/fs/ocfs2/cluster/tcp.c b/fs/ocfs2/cluster/tcp.c
index d4b5c81f0445..8d779227370a 100644
--- a/fs/ocfs2/cluster/tcp.c
+++ b/fs/ocfs2/cluster/tcp.c
@@ -54,6 +54,7 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/sched/mm.h>
 #include <linux/jiffies.h>
 #include <linux/slab.h>
 #include <linux/idr.h>
@@ -97,7 +98,7 @@
 	typeof(sc) __sc = (sc);						\
 	mlog(ML_SOCKET, "[sc %p refs %d sock %p node %u page %p "	\
 	     "pg_off %zu] " fmt, __sc,					\
-	     atomic_read(&__sc->sc_kref.refcount), __sc->sc_sock,	\
+	     kref_read(&__sc->sc_kref), __sc->sc_sock,	\
 	    __sc->sc_node->nd_num, __sc->sc_page, __sc->sc_page_off ,	\
 	    ##args);							\
 } while (0)
@@ -449,9 +450,8 @@ static struct o2net_sock_container *sc_alloc(struct o2nm_node *node)
 	INIT_WORK(&sc->sc_shutdown_work, o2net_shutdown_sc);
 	INIT_DELAYED_WORK(&sc->sc_keepalive_work, o2net_sc_send_keep_req);
 
-	init_timer(&sc->sc_idle_timeout);
-	sc->sc_idle_timeout.function = o2net_idle_timer;
-	sc->sc_idle_timeout.data = (unsigned long)sc;
+	setup_timer(&sc->sc_idle_timeout, o2net_idle_timer,
+		    (unsigned long)sc);
 
 	sclog(sc, "alloced\n");
 
@@ -955,7 +955,7 @@ static void o2net_sendpage(struct o2net_sock_container *sc,
 		mutex_lock(&sc->sc_send_lock);
 		ret = sc->sc_sock->ops->sendpage(sc->sc_sock,
 						 virt_to_page(kmalloced_virt),
-						 (long)kmalloced_virt & ~PAGE_MASK,
+						 offset_in_page(kmalloced_virt),
 						 size, MSG_DONTWAIT);
 		mutex_unlock(&sc->sc_send_lock);
 		if (ret == size)
@@ -1459,27 +1459,10 @@ static void o2net_rx_until_empty(struct work_struct *work)
 
 static int o2net_set_nodelay(struct socket *sock)
 {
-	int ret, val = 1;
-	mm_segment_t oldfs;
+	int val = 1;
 
-	oldfs = get_fs();
-	set_fs(KERNEL_DS);
-
-	/*
-	 * Dear unsuspecting programmer,
-	 *
-	 * Don't use sock_setsockopt() for SOL_TCP.  It doesn't check its level
-	 * argument and assumes SOL_SOCKET so, say, your TCP_NODELAY will
-	 * silently turn into SO_DEBUG.
-	 *
-	 * Yours,
-	 * Keeper of hilariously fragile interfaces.
-	 */
-	ret = sock->ops->setsockopt(sock, SOL_TCP, TCP_NODELAY,
-				    (char __user *)&val, sizeof(val));
-
-	set_fs(oldfs);
-	return ret;
+	return kernel_setsockopt(sock, SOL_TCP, TCP_NODELAY,
+				    (void *)&val, sizeof(val));
 }
 
 static int o2net_set_usertimeout(struct socket *sock)
@@ -1487,7 +1470,7 @@ static int o2net_set_usertimeout(struct socket *sock)
 	int user_timeout = O2NET_TCP_USER_TIMEOUT;
 
 	return kernel_setsockopt(sock, SOL_TCP, TCP_USER_TIMEOUT,
-				(char *)&user_timeout, sizeof(user_timeout));
+				(void *)&user_timeout, sizeof(user_timeout));
 }
 
 static void o2net_initialize_handshake(void)
@@ -1862,7 +1845,7 @@ static int o2net_accept_one(struct socket *sock, int *more)
 
 	new_sock->type = sock->type;
 	new_sock->ops = sock->ops;
-	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK);
+	ret = sock->ops->accept(sock, new_sock, O_NONBLOCK, false);
 	if (ret < 0)
 		goto out;
 
diff --git a/fs/ocfs2/dlm/dlmdebug.c b/fs/ocfs2/dlm/dlmdebug.c
index e7b760deefae..9b984cae4c4e 100644
--- a/fs/ocfs2/dlm/dlmdebug.c
+++ b/fs/ocfs2/dlm/dlmdebug.c
@@ -81,7 +81,7 @@ static void __dlm_print_lock(struct dlm_lock *lock)
 	       lock->ml.type, lock->ml.convert_type, lock->ml.node,
 	       dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
 	       dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
-	       atomic_read(&lock->lock_refs.refcount),
+	       kref_read(&lock->lock_refs),
 	       (list_empty(&lock->ast_list) ? 'y' : 'n'),
 	       (lock->ast_pending ? 'y' : 'n'),
 	       (list_empty(&lock->bast_list) ? 'y' : 'n'),
@@ -106,7 +106,7 @@ void __dlm_print_one_lock_resource(struct dlm_lock_resource *res)
 	printk("lockres: %s, owner=%u, state=%u\n",
 	       buf, res->owner, res->state);
 	printk("  last used: %lu, refcnt: %u, on purge list: %s\n",
-	       res->last_used, atomic_read(&res->refs.refcount),
+	       res->last_used, kref_read(&res->refs),
 	       list_empty(&res->purge) ? "no" : "yes");
 	printk("  on dirty list: %s, on reco list: %s, "
 	       "migrating pending: %s\n",
@@ -298,7 +298,7 @@ static int dump_mle(struct dlm_master_list_entry *mle, char *buf, int len)
 			mle_type, mle->master, mle->new_master,
 			!list_empty(&mle->hb_events),
 			!!mle->inuse,
-			atomic_read(&mle->mle_refs.refcount));
+			kref_read(&mle->mle_refs));
 
 	out += snprintf(buf + out, len - out, "Maybe=");
 	out += stringify_nodemap(mle->maybe_map, O2NM_MAX_NODES,
@@ -494,7 +494,7 @@ static int dump_lock(struct dlm_lock *lock, int list_type, char *buf, int len)
 		       lock->ast_pending, lock->bast_pending,
 		       lock->convert_pending, lock->lock_pending,
 		       lock->cancel_pending, lock->unlock_pending,
-		       atomic_read(&lock->lock_refs.refcount));
+		       kref_read(&lock->lock_refs));
 	spin_unlock(&lock->spinlock);
 
 	return out;
@@ -521,7 +521,7 @@ static int dump_lockres(struct dlm_lock_resource *res, char *buf, int len)
 			!list_empty(&res->recovering),
 			res->inflight_locks, res->migration_pending,
 			atomic_read(&res->asts_reserved),
-			atomic_read(&res->refs.refcount));
+			kref_read(&res->refs));
 
 	/* refmap */
 	out += snprintf(buf + out, len - out, "RMAP:");
@@ -777,7 +777,7 @@ static int debug_state_print(struct dlm_ctxt *dlm, char *buf, int len)
 	/* Purge Count: xxx  Refs: xxx */
 	out += snprintf(buf + out, len - out,
 			"Purge Count: %d  Refs: %d\n", dlm->purge_count,
-			atomic_read(&dlm->dlm_refs.refcount));
+			kref_read(&dlm->dlm_refs));
 
 	/* Dead Node: xxx */
 	out += snprintf(buf + out, len - out,
diff --git a/fs/ocfs2/dlm/dlmdomain.c b/fs/ocfs2/dlm/dlmdomain.c
index 733e4e79c8e2..a2b19fbdcf46 100644
--- a/fs/ocfs2/dlm/dlmdomain.c
+++ b/fs/ocfs2/dlm/dlmdomain.c
@@ -33,6 +33,7 @@
 #include <linux/delay.h>
 #include <linux/err.h>
 #include <linux/debugfs.h>
+#include <linux/sched/signal.h>
 
 #include "cluster/heartbeat.h"
 #include "cluster/nodemanager.h"
@@ -2072,7 +2073,7 @@ static struct dlm_ctxt *dlm_alloc_ctxt(const char *domain,
 	INIT_LIST_HEAD(&dlm->dlm_eviction_callbacks);
 
 	mlog(0, "context init: refcount %u\n",
-		  atomic_read(&dlm->dlm_refs.refcount));
+		  kref_read(&dlm->dlm_refs));
 
 leave:
 	if (ret < 0 && dlm) {
diff --git a/fs/ocfs2/dlm/dlmmaster.c b/fs/ocfs2/dlm/dlmmaster.c
index a464c8088170..3e04279446e8 100644
--- a/fs/ocfs2/dlm/dlmmaster.c
+++ b/fs/ocfs2/dlm/dlmmaster.c
@@ -233,7 +233,7 @@ static void __dlm_put_mle(struct dlm_master_list_entry *mle)
 
 	assert_spin_locked(&dlm->spinlock);
 	assert_spin_locked(&dlm->master_lock);
-	if (!atomic_read(&mle->mle_refs.refcount)) {
+	if (!kref_read(&mle->mle_refs)) {
 		/* this may or may not crash, but who cares.
 		 * it's a BUG. */
 		mlog(ML_ERROR, "bad mle: %p\n", mle);
@@ -1124,9 +1124,9 @@ recheck:
 		unsigned long timeo = msecs_to_jiffies(DLM_MASTERY_TIMEOUT_MS);
 
 		/*
-		if (atomic_read(&mle->mle_refs.refcount) < 2)
+		if (kref_read(&mle->mle_refs) < 2)
 			mlog(ML_ERROR, "mle (%p) refs=%d, name=%.*s\n", mle,
-			atomic_read(&mle->mle_refs.refcount),
+			kref_read(&mle->mle_refs),
 			res->lockname.len, res->lockname.name);
 		*/
 		atomic_set(&mle->woken, 0);
@@ -1979,7 +1979,7 @@ ok:
 		 * on this mle. */
 		spin_lock(&dlm->master_lock);
 
-		rr = atomic_read(&mle->mle_refs.refcount);
+		rr = kref_read(&mle->mle_refs);
 		if (mle->inuse > 0) {
 			if (extra_ref && rr < 3)
 				err = 1;
@@ -2924,7 +2924,7 @@ again:
 	/*
 	 * if target is down, we need to clear DLM_LOCK_RES_BLOCK_DIRTY for
 	 * another try; otherwise, we are sure the MIGRATING state is there,
-	 * drop the unneded state which blocked threads trying to DIRTY
+	 * drop the unneeded state which blocked threads trying to DIRTY
 	 */
 	spin_lock(&res->spinlock);
 	BUG_ON(!(res->state & DLM_LOCK_RES_BLOCK_DIRTY));
diff --git a/fs/ocfs2/dlm/dlmunlock.c b/fs/ocfs2/dlm/dlmunlock.c
index 1082b2c3014b..63d701cd1e2e 100644
--- a/fs/ocfs2/dlm/dlmunlock.c
+++ b/fs/ocfs2/dlm/dlmunlock.c
@@ -251,7 +251,7 @@ leave:
 		mlog(0, "lock %u:%llu should be gone now! refs=%d\n",
 		     dlm_get_lock_cookie_node(be64_to_cpu(lock->ml.cookie)),
 		     dlm_get_lock_cookie_seq(be64_to_cpu(lock->ml.cookie)),
-		     atomic_read(&lock->lock_refs.refcount)-1);
+		     kref_read(&lock->lock_refs)-1);
 		dlm_lock_put(lock);
 	}
 	if (actions & DLM_UNLOCK_CALL_AST)
diff --git a/fs/ocfs2/dlmfs/userdlm.c b/fs/ocfs2/dlmfs/userdlm.c
index f70cda2f090d..9cecf4857195 100644
--- a/fs/ocfs2/dlmfs/userdlm.c
+++ b/fs/ocfs2/dlmfs/userdlm.c
@@ -28,6 +28,7 @@
  */
 
 #include <linux/signal.h>
+#include <linux/sched/signal.h>
 
 #include <linux/module.h>
 #include <linux/fs.h>
diff --git a/fs/ocfs2/dlmglue.c b/fs/ocfs2/dlmglue.c
index 77d1632e905d..4689940a953c 100644
--- a/fs/ocfs2/dlmglue.c
+++ b/fs/ocfs2/dlmglue.c
@@ -33,6 +33,7 @@
 #include <linux/seq_file.h>
 #include <linux/time.h>
 #include <linux/quotaops.h>
+#include <linux/sched/signal.h>
 
 #define MLOG_MASK_PREFIX ML_DLM_GLUE
 #include <cluster/masklog.h>
@@ -532,6 +533,7 @@ void ocfs2_lock_res_init_once(struct ocfs2_lock_res *res)
 	init_waitqueue_head(&res->l_event);
 	INIT_LIST_HEAD(&res->l_blocked_list);
 	INIT_LIST_HEAD(&res->l_mask_waiters);
+	INIT_LIST_HEAD(&res->l_holders);
 }
 
 void ocfs2_inode_lock_res_init(struct ocfs2_lock_res *res,
@@ -749,6 +751,50 @@ void ocfs2_lock_res_free(struct ocfs2_lock_res *res)
 	res->l_flags = 0UL;
 }
 
+/*
+ * Keep a list of processes who have interest in a lockres.
+ * Note: this is now only uesed for check recursive cluster locking.
+ */
+static inline void ocfs2_add_holder(struct ocfs2_lock_res *lockres,
+				   struct ocfs2_lock_holder *oh)
+{
+	INIT_LIST_HEAD(&oh->oh_list);
+	oh->oh_owner_pid = get_pid(task_pid(current));
+
+	spin_lock(&lockres->l_lock);
+	list_add_tail(&oh->oh_list, &lockres->l_holders);
+	spin_unlock(&lockres->l_lock);
+}
+
+static inline void ocfs2_remove_holder(struct ocfs2_lock_res *lockres,
+				       struct ocfs2_lock_holder *oh)
+{
+	spin_lock(&lockres->l_lock);
+	list_del(&oh->oh_list);
+	spin_unlock(&lockres->l_lock);
+
+	put_pid(oh->oh_owner_pid);
+}
+
+static inline int ocfs2_is_locked_by_me(struct ocfs2_lock_res *lockres)
+{
+	struct ocfs2_lock_holder *oh;
+	struct pid *pid;
+
+	/* look in the list of holders for one with the current task as owner */
+	spin_lock(&lockres->l_lock);
+	pid = task_pid(current);
+	list_for_each_entry(oh, &lockres->l_holders, oh_list) {
+		if (oh->oh_owner_pid == pid) {
+			spin_unlock(&lockres->l_lock);
+			return 1;
+		}
+	}
+	spin_unlock(&lockres->l_lock);
+
+	return 0;
+}
+
 static inline void ocfs2_inc_holders(struct ocfs2_lock_res *lockres,
 				     int level)
 {
@@ -2333,8 +2379,9 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
 		goto getbh;
 	}
 
-	if (ocfs2_mount_local(osb))
-		goto local;
+	if ((arg_flags & OCFS2_META_LOCK_GETBH) ||
+	    ocfs2_mount_local(osb))
+		goto update;
 
 	if (!(arg_flags & OCFS2_META_LOCK_RECOVERY))
 		ocfs2_wait_for_recovery(osb);
@@ -2363,7 +2410,7 @@ int ocfs2_inode_lock_full_nested(struct inode *inode,
 	if (!(arg_flags & OCFS2_META_LOCK_RECOVERY))
 		ocfs2_wait_for_recovery(osb);
 
-local:
+update:
 	/*
 	 * We only see this flag if we're being called from
 	 * ocfs2_read_locked_inode(). It means we're locking an inode
@@ -2497,6 +2544,63 @@ void ocfs2_inode_unlock(struct inode *inode,
 		ocfs2_cluster_unlock(OCFS2_SB(inode->i_sb), lockres, level);
 }
 
+/*
+ * This _tracker variantes are introduced to deal with the recursive cluster
+ * locking issue. The idea is to keep track of a lock holder on the stack of
+ * the current process. If there's a lock holder on the stack, we know the
+ * task context is already protected by cluster locking. Currently, they're
+ * used in some VFS entry routines.
+ *
+ * return < 0 on error, return == 0 if there's no lock holder on the stack
+ * before this call, return == 1 if this call would be a recursive locking.
+ */
+int ocfs2_inode_lock_tracker(struct inode *inode,
+			     struct buffer_head **ret_bh,
+			     int ex,
+			     struct ocfs2_lock_holder *oh)
+{
+	int status;
+	int arg_flags = 0, has_locked;
+	struct ocfs2_lock_res *lockres;
+
+	lockres = &OCFS2_I(inode)->ip_inode_lockres;
+	has_locked = ocfs2_is_locked_by_me(lockres);
+	/* Just get buffer head if the cluster lock has been taken */
+	if (has_locked)
+		arg_flags = OCFS2_META_LOCK_GETBH;
+
+	if (likely(!has_locked || ret_bh)) {
+		status = ocfs2_inode_lock_full(inode, ret_bh, ex, arg_flags);
+		if (status < 0) {
+			if (status != -ENOENT)
+				mlog_errno(status);
+			return status;
+		}
+	}
+	if (!has_locked)
+		ocfs2_add_holder(lockres, oh);
+
+	return has_locked;
+}
+
+void ocfs2_inode_unlock_tracker(struct inode *inode,
+				int ex,
+				struct ocfs2_lock_holder *oh,
+				int had_lock)
+{
+	struct ocfs2_lock_res *lockres;
+
+	lockres = &OCFS2_I(inode)->ip_inode_lockres;
+	/* had_lock means that the currect process already takes the cluster
+	 * lock previously. If had_lock is 1, we have nothing to do here, and
+	 * it will get unlocked where we got the lock.
+	 */
+	if (!had_lock) {
+		ocfs2_remove_holder(lockres, oh);
+		ocfs2_inode_unlock(inode, ex);
+	}
+}
+
 int ocfs2_orphan_scan_lock(struct ocfs2_super *osb, u32 *seqno)
 {
 	struct ocfs2_lock_res *lockres;
diff --git a/fs/ocfs2/dlmglue.h b/fs/ocfs2/dlmglue.h
index d293a22c32c5..a7fc18ba0dc1 100644
--- a/fs/ocfs2/dlmglue.h
+++ b/fs/ocfs2/dlmglue.h
@@ -70,6 +70,11 @@ struct ocfs2_orphan_scan_lvb {
 	__be32	lvb_os_seqno;
 };
 
+struct ocfs2_lock_holder {
+	struct list_head oh_list;
+	struct pid *oh_owner_pid;
+};
+
 /* ocfs2_inode_lock_full() 'arg_flags' flags */
 /* don't wait on recovery. */
 #define OCFS2_META_LOCK_RECOVERY	(0x01)
@@ -77,6 +82,8 @@ struct ocfs2_orphan_scan_lvb {
 #define OCFS2_META_LOCK_NOQUEUE		(0x02)
 /* don't block waiting for the downconvert thread, instead return -EAGAIN */
 #define OCFS2_LOCK_NONBLOCK		(0x04)
+/* just get back disk inode bh if we've got cluster lock. */
+#define OCFS2_META_LOCK_GETBH		(0x08)
 
 /* Locking subclasses of inode cluster lock */
 enum {
@@ -170,4 +177,15 @@ void ocfs2_put_dlm_debug(struct ocfs2_dlm_debug *dlm_debug);
 
 /* To set the locking protocol on module initialization */
 void ocfs2_set_locking_protocol(void);
+
+/* The _tracker pair is used to avoid cluster recursive locking */
+int ocfs2_inode_lock_tracker(struct inode *inode,
+			     struct buffer_head **ret_bh,
+			     int ex,
+			     struct ocfs2_lock_holder *oh);
+void ocfs2_inode_unlock_tracker(struct inode *inode,
+				int ex,
+				struct ocfs2_lock_holder *oh,
+				int had_lock);
+
 #endif	/* DLMGLUE_H */
diff --git a/fs/ocfs2/export.c b/fs/ocfs2/export.c
index 827fc9809bc2..9f88188060db 100644
--- a/fs/ocfs2/export.c
+++ b/fs/ocfs2/export.c
@@ -119,7 +119,7 @@ check_err:
 
 	if (IS_ERR(inode)) {
 		mlog_errno(PTR_ERR(inode));
-		result = (void *)inode;
+		result = ERR_CAST(inode);
 		goto bail;
 	}
 
diff --git a/fs/ocfs2/file.c b/fs/ocfs2/file.c
index c4889655d32b..bfeb647459d9 100644
--- a/fs/ocfs2/file.c
+++ b/fs/ocfs2/file.c
@@ -808,7 +808,7 @@ static int ocfs2_write_zero_page(struct inode *inode, u64 abs_from,
 	/* We know that zero_from is block aligned */
 	for (block_start = zero_from; block_start < zero_to;
 	     block_start = block_end) {
-		block_end = block_start + (1 << inode->i_blkbits);
+		block_end = block_start + i_blocksize(inode);
 
 		/*
 		 * block_start is block-aligned.  Bump it by one to force
@@ -1138,6 +1138,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 	handle_t *handle = NULL;
 	struct dquot *transfer_to[MAXQUOTAS] = { };
 	int qtype;
+	int had_lock;
+	struct ocfs2_lock_holder oh;
 
 	trace_ocfs2_setattr(inode, dentry,
 			    (unsigned long long)OCFS2_I(inode)->ip_blkno,
@@ -1173,11 +1175,30 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 		}
 	}
 
-	status = ocfs2_inode_lock(inode, &bh, 1);
-	if (status < 0) {
-		if (status != -ENOENT)
-			mlog_errno(status);
+	had_lock = ocfs2_inode_lock_tracker(inode, &bh, 1, &oh);
+	if (had_lock < 0) {
+		status = had_lock;
 		goto bail_unlock_rw;
+	} else if (had_lock) {
+		/*
+		 * As far as we know, ocfs2_setattr() could only be the first
+		 * VFS entry point in the call chain of recursive cluster
+		 * locking issue.
+		 *
+		 * For instance:
+		 * chmod_common()
+		 *  notify_change()
+		 *   ocfs2_setattr()
+		 *    posix_acl_chmod()
+		 *     ocfs2_iop_get_acl()
+		 *
+		 * But, we're not 100% sure if it's always true, because the
+		 * ordering of the VFS entry points in the call chain is out
+		 * of our control. So, we'd better dump the stack here to
+		 * catch the other cases of recursive locking.
+		 */
+		mlog(ML_ERROR, "Another case of recursive locking:\n");
+		dump_stack();
 	}
 	inode_locked = 1;
 
@@ -1260,8 +1281,8 @@ int ocfs2_setattr(struct dentry *dentry, struct iattr *attr)
 bail_commit:
 	ocfs2_commit_trans(osb, handle);
 bail_unlock:
-	if (status) {
-		ocfs2_inode_unlock(inode, 1);
+	if (status && inode_locked) {
+		ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);
 		inode_locked = 0;
 	}
 bail_unlock_rw:
@@ -1279,22 +1300,21 @@ bail:
 			mlog_errno(status);
 	}
 	if (inode_locked)
-		ocfs2_inode_unlock(inode, 1);
+		ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);
 
 	brelse(bh);
 	return status;
 }
 
-int ocfs2_getattr(struct vfsmount *mnt,
-		  struct dentry *dentry,
-		  struct kstat *stat)
+int ocfs2_getattr(const struct path *path, struct kstat *stat,
+		  u32 request_mask, unsigned int flags)
 {
-	struct inode *inode = d_inode(dentry);
-	struct super_block *sb = dentry->d_sb;
+	struct inode *inode = d_inode(path->dentry);
+	struct super_block *sb = path->dentry->d_sb;
 	struct ocfs2_super *osb = sb->s_fs_info;
 	int err;
 
-	err = ocfs2_inode_revalidate(dentry);
+	err = ocfs2_inode_revalidate(path->dentry);
 	if (err) {
 		if (err != -ENOENT)
 			mlog_errno(err);
@@ -1320,21 +1340,32 @@ bail:
 
 int ocfs2_permission(struct inode *inode, int mask)
 {
-	int ret;
+	int ret, had_lock;
+	struct ocfs2_lock_holder oh;
 
 	if (mask & MAY_NOT_BLOCK)
 		return -ECHILD;
 
-	ret = ocfs2_inode_lock(inode, NULL, 0);
-	if (ret) {
-		if (ret != -ENOENT)
-			mlog_errno(ret);
+	had_lock = ocfs2_inode_lock_tracker(inode, NULL, 0, &oh);
+	if (had_lock < 0) {
+		ret = had_lock;
 		goto out;
+	} else if (had_lock) {
+		/* See comments in ocfs2_setattr() for details.
+		 * The call chain of this case could be:
+		 * do_sys_open()
+		 *  may_open()
+		 *   inode_permission()
+		 *    ocfs2_permission()
+		 *     ocfs2_iop_get_acl()
+		 */
+		mlog(ML_ERROR, "Another case of recursive locking:\n");
+		dump_stack();
 	}
 
 	ret = generic_permission(inode, mask);
 
-	ocfs2_inode_unlock(inode, 0);
+	ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock);
 out:
 	return ret;
 }
diff --git a/fs/ocfs2/file.h b/fs/ocfs2/file.h
index 897fd9a2e51d..1fdc9839cd93 100644
--- a/fs/ocfs2/file.h
+++ b/fs/ocfs2/file.h
@@ -68,8 +68,8 @@ int ocfs2_zero_extend(struct inode *inode, struct buffer_head *di_bh,
 int ocfs2_extend_allocation(struct inode *inode, u32 logical_start,
 		u32 clusters_to_add, int mark_unwritten);
 int ocfs2_setattr(struct dentry *dentry, struct iattr *attr);
-int ocfs2_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		  struct kstat *stat);
+int ocfs2_getattr(const struct path *path, struct kstat *stat,
+		  u32 request_mask, unsigned int flags);
 int ocfs2_permission(struct inode *inode, int mask);
 
 int ocfs2_should_update_atime(struct inode *inode,
diff --git a/fs/ocfs2/inode.c b/fs/ocfs2/inode.c
index 382401d3e88f..1a1e0078ab38 100644
--- a/fs/ocfs2/inode.c
+++ b/fs/ocfs2/inode.c
@@ -136,7 +136,7 @@ struct inode *ocfs2_ilookup(struct super_block *sb, u64 blkno)
 struct inode *ocfs2_iget(struct ocfs2_super *osb, u64 blkno, unsigned flags,
 			 int sysfile_type)
 {
-	int rc = 0;
+	int rc = -ESTALE;
 	struct inode *inode = NULL;
 	struct super_block *sb = osb->sb;
 	struct ocfs2_find_inode_args args;
diff --git a/fs/ocfs2/mmap.c b/fs/ocfs2/mmap.c
index 429088786e93..098f5c712569 100644
--- a/fs/ocfs2/mmap.c
+++ b/fs/ocfs2/mmap.c
@@ -44,17 +44,18 @@
 #include "ocfs2_trace.h"
 
 
-static int ocfs2_fault(struct vm_area_struct *area, struct vm_fault *vmf)
+static int ocfs2_fault(struct vm_fault *vmf)
 {
+	struct vm_area_struct *vma = vmf->vma;
 	sigset_t oldset;
 	int ret;
 
 	ocfs2_block_signals(&oldset);
-	ret = filemap_fault(area, vmf);
+	ret = filemap_fault(vmf);
 	ocfs2_unblock_signals(&oldset);
 
-	trace_ocfs2_fault(OCFS2_I(area->vm_file->f_mapping->host)->ip_blkno,
-			  area, vmf->page, vmf->pgoff);
+	trace_ocfs2_fault(OCFS2_I(vma->vm_file->f_mapping->host)->ip_blkno,
+			  vma, vmf->page, vmf->pgoff);
 	return ret;
 }
 
@@ -127,10 +128,10 @@ out:
 	return ret;
 }
 
-static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int ocfs2_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct buffer_head *di_bh = NULL;
 	sigset_t oldset;
 	int ret;
@@ -160,7 +161,7 @@ static int ocfs2_page_mkwrite(struct vm_area_struct *vma, struct vm_fault *vmf)
 	 */
 	down_write(&OCFS2_I(inode)->ip_alloc_sem);
 
-	ret = __ocfs2_page_mkwrite(vma->vm_file, di_bh, page);
+	ret = __ocfs2_page_mkwrite(vmf->vma->vm_file, di_bh, page);
 
 	up_write(&OCFS2_I(inode)->ip_alloc_sem);
 
diff --git a/fs/ocfs2/ocfs2.h b/fs/ocfs2/ocfs2.h
index 7e5958b0be6b..0c39d71c67a1 100644
--- a/fs/ocfs2/ocfs2.h
+++ b/fs/ocfs2/ocfs2.h
@@ -172,6 +172,7 @@ struct ocfs2_lock_res {
 
 	struct list_head         l_blocked_list;
 	struct list_head         l_mask_waiters;
+	struct list_head	 l_holders;
 
 	unsigned long		 l_flags;
 	char                     l_name[OCFS2_LOCK_ID_MAX_LEN];
diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h
index 44d178b8d1aa..5bb4a89f9045 100644
--- a/fs/ocfs2/ocfs2_fs.h
+++ b/fs/ocfs2/ocfs2_fs.h
@@ -25,6 +25,8 @@
 #ifndef _OCFS2_FS_H
 #define _OCFS2_FS_H
 
+#include <linux/magic.h>
+
 /* Version */
 #define OCFS2_MAJOR_REV_LEVEL		0
 #define OCFS2_MINOR_REV_LEVEL          	90
@@ -56,9 +58,6 @@
 #define OCFS2_MIN_BLOCKSIZE		512
 #define OCFS2_MAX_BLOCKSIZE		OCFS2_MIN_CLUSTERSIZE
 
-/* Filesystem magic number */
-#define OCFS2_SUPER_MAGIC		0x7461636f
-
 /* Object signatures */
 #define OCFS2_SUPER_BLOCK_SIGNATURE	"OCFSV2"
 #define OCFS2_INODE_SIGNATURE		"INODE01"
diff --git a/fs/ocfs2/stackglue.c b/fs/ocfs2/stackglue.c
index 820359096c7a..d6c350ba25b9 100644
--- a/fs/ocfs2/stackglue.c
+++ b/fs/ocfs2/stackglue.c
@@ -631,7 +631,7 @@ static struct attribute *ocfs2_attrs[] = {
 	NULL,
 };
 
-static struct attribute_group ocfs2_attr_group = {
+static const struct attribute_group ocfs2_attr_group = {
 	.attrs = ocfs2_attrs,
 };
 
diff --git a/fs/ocfs2/super.c b/fs/ocfs2/super.c
index a24e42f95341..83005f486451 100644
--- a/fs/ocfs2/super.c
+++ b/fs/ocfs2/super.c
@@ -42,6 +42,7 @@
 #include <linux/seq_file.h>
 #include <linux/quotaops.h>
 #include <linux/cleancache.h>
+#include <linux/signal.h>
 
 #define CREATE_TRACE_POINTS
 #include "ocfs2_trace.h"
@@ -2061,7 +2062,7 @@ static int ocfs2_initialize_super(struct super_block *sb,
 	cbits = le32_to_cpu(di->id2.i_super.s_clustersize_bits);
 	bbits = le32_to_cpu(di->id2.i_super.s_blocksize_bits);
 	sb->s_maxbytes = ocfs2_max_file_offset(bbits, cbits);
-	memcpy(sb->s_uuid, di->id2.i_super.s_uuid,
+	memcpy(&sb->s_uuid, di->id2.i_super.s_uuid,
 	       sizeof(di->id2.i_super.s_uuid));
 
 	osb->osb_dx_mask = (1 << (cbits - bbits)) - 1;
diff --git a/fs/ocfs2/xattr.c b/fs/ocfs2/xattr.c
index 3c5384d9b3a5..f70c3778d600 100644
--- a/fs/ocfs2/xattr.c
+++ b/fs/ocfs2/xattr.c
@@ -1328,20 +1328,21 @@ static int ocfs2_xattr_get(struct inode *inode,
 			   void *buffer,
 			   size_t buffer_size)
 {
-	int ret;
+	int ret, had_lock;
 	struct buffer_head *di_bh = NULL;
+	struct ocfs2_lock_holder oh;
 
-	ret = ocfs2_inode_lock(inode, &di_bh, 0);
-	if (ret < 0) {
-		mlog_errno(ret);
-		return ret;
+	had_lock = ocfs2_inode_lock_tracker(inode, &di_bh, 0, &oh);
+	if (had_lock < 0) {
+		mlog_errno(had_lock);
+		return had_lock;
 	}
 	down_read(&OCFS2_I(inode)->ip_xattr_sem);
 	ret = ocfs2_xattr_get_nolock(inode, di_bh, name_index,
 				     name, buffer, buffer_size);
 	up_read(&OCFS2_I(inode)->ip_xattr_sem);
 
-	ocfs2_inode_unlock(inode, 0);
+	ocfs2_inode_unlock_tracker(inode, 0, &oh, had_lock);
 
 	brelse(di_bh);
 
@@ -3537,11 +3538,12 @@ int ocfs2_xattr_set(struct inode *inode,
 {
 	struct buffer_head *di_bh = NULL;
 	struct ocfs2_dinode *di;
-	int ret, credits, ref_meta = 0, ref_credits = 0;
+	int ret, credits, had_lock, ref_meta = 0, ref_credits = 0;
 	struct ocfs2_super *osb = OCFS2_SB(inode->i_sb);
 	struct inode *tl_inode = osb->osb_tl_inode;
 	struct ocfs2_xattr_set_ctxt ctxt = { NULL, NULL, NULL, };
 	struct ocfs2_refcount_tree *ref_tree = NULL;
+	struct ocfs2_lock_holder oh;
 
 	struct ocfs2_xattr_info xi = {
 		.xi_name_index = name_index,
@@ -3572,8 +3574,9 @@ int ocfs2_xattr_set(struct inode *inode,
 		return -ENOMEM;
 	}
 
-	ret = ocfs2_inode_lock(inode, &di_bh, 1);
-	if (ret < 0) {
+	had_lock = ocfs2_inode_lock_tracker(inode, &di_bh, 1, &oh);
+	if (had_lock < 0) {
+		ret = had_lock;
 		mlog_errno(ret);
 		goto cleanup_nolock;
 	}
@@ -3670,7 +3673,7 @@ cleanup:
 		if (ret)
 			mlog_errno(ret);
 	}
-	ocfs2_inode_unlock(inode, 1);
+	ocfs2_inode_unlock_tracker(inode, 1, &oh, had_lock);
 cleanup_nolock:
 	brelse(di_bh);
 	brelse(xbs.xattr_bh);
diff --git a/fs/omfs/inode.c b/fs/omfs/inode.c
index df7ea8543a2e..ee14af9e26f2 100644
--- a/fs/omfs/inode.c
+++ b/fs/omfs/inode.c
@@ -8,10 +8,12 @@
 #include <linux/slab.h>
 #include <linux/fs.h>
 #include <linux/vfs.h>
+#include <linux/cred.h>
 #include <linux/parser.h>
 #include <linux/buffer_head.h>
 #include <linux/vmalloc.h>
 #include <linux/writeback.h>
+#include <linux/seq_file.h>
 #include <linux/crc-itu-t.h>
 #include "omfs.h"
 
@@ -289,12 +291,40 @@ static int omfs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return 0;
 }
 
+/*
+ * Display the mount options in /proc/mounts.
+ */
+static int omfs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct omfs_sb_info *sbi = OMFS_SB(root->d_sb);
+	umode_t cur_umask = current_umask();
+
+	if (!uid_eq(sbi->s_uid, current_uid()))
+		seq_printf(m, ",uid=%u",
+			   from_kuid_munged(&init_user_ns, sbi->s_uid));
+	if (!gid_eq(sbi->s_gid, current_gid()))
+		seq_printf(m, ",gid=%u",
+			   from_kgid_munged(&init_user_ns, sbi->s_gid));
+
+	if (sbi->s_dmask == sbi->s_fmask) {
+		if (sbi->s_fmask != cur_umask)
+			seq_printf(m, ",umask=%o", sbi->s_fmask);
+	} else {
+		if (sbi->s_dmask != cur_umask)
+			seq_printf(m, ",dmask=%o", sbi->s_dmask);
+		if (sbi->s_fmask != cur_umask)
+			seq_printf(m, ",fmask=%o", sbi->s_fmask);
+	}
+
+	return 0;
+}
+
 static const struct super_operations omfs_sops = {
 	.write_inode	= omfs_write_inode,
 	.evict_inode	= omfs_evict_inode,
 	.put_super	= omfs_put_super,
 	.statfs		= omfs_statfs,
-	.show_options	= generic_show_options,
+	.show_options	= omfs_show_options,
 };
 
 /*
@@ -433,8 +463,6 @@ static int omfs_fill_super(struct super_block *sb, void *data, int silent)
 	struct inode *root;
 	int ret = -EINVAL;
 
-	save_mount_options(sb, (char *) data);
-
 	sbi = kzalloc(sizeof(struct omfs_sb_info), GFP_KERNEL);
 	if (!sbi)
 		return -ENOMEM;
diff --git a/fs/open.c b/fs/open.c
index 9921f70bc5ca..35bb784763a4 100644
--- a/fs/open.c
+++ b/fs/open.c
@@ -193,7 +193,8 @@ static long do_sys_ftruncate(unsigned int fd, loff_t length, int small)
 		goto out_putf;
 
 	error = -EPERM;
-	if (IS_APPEND(inode))
+	/* Check IS_APPEND on real upper inode */
+	if (IS_APPEND(file_inode(f.file)))
 		goto out_putf;
 
 	sb_start_write(inode->i_sb);
@@ -301,12 +302,10 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (S_ISFIFO(inode->i_mode))
 		return -ESPIPE;
 
-	/*
-	 * Let individual file system decide if it supports preallocation
-	 * for directories or not.
-	 */
-	if (!S_ISREG(inode->i_mode) && !S_ISDIR(inode->i_mode) &&
-	    !S_ISBLK(inode->i_mode))
+	if (S_ISDIR(inode->i_mode))
+		return -EISDIR;
+
+	if (!S_ISREG(inode->i_mode) && !S_ISBLK(inode->i_mode))
 		return -ENODEV;
 
 	/* Check for wrap through zero too */
@@ -316,7 +315,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (!file->f_op->fallocate)
 		return -EOPNOTSUPP;
 
-	sb_start_write(inode->i_sb);
+	file_start_write(file);
 	ret = file->f_op->fallocate(file, mode, offset, len);
 
 	/*
@@ -329,7 +328,7 @@ int vfs_fallocate(struct file *file, int mode, loff_t offset, loff_t len)
 	if (ret == 0)
 		fsnotify_modify(file);
 
-	sb_end_write(inode->i_sb);
+	file_end_write(file);
 	return ret;
 }
 EXPORT_SYMBOL_GPL(vfs_fallocate);
@@ -461,20 +460,17 @@ out:
 SYSCALL_DEFINE1(fchdir, unsigned int, fd)
 {
 	struct fd f = fdget_raw(fd);
-	struct inode *inode;
-	int error = -EBADF;
+	int error;
 
 	error = -EBADF;
 	if (!f.file)
 		goto out;
 
-	inode = file_inode(f.file);
-
 	error = -ENOTDIR;
-	if (!S_ISDIR(inode->i_mode))
+	if (!d_can_lookup(f.file->f_path.dentry))
 		goto out_putf;
 
-	error = inode_permission(inode, MAY_EXEC | MAY_CHDIR);
+	error = inode_permission(file_inode(f.file), MAY_EXEC | MAY_CHDIR);
 	if (!error)
 		set_fs_pwd(current->fs, &f.file->f_path);
 out_putf:
@@ -711,6 +707,9 @@ static int do_dentry_open(struct file *f,
 	f->f_inode = inode;
 	f->f_mapping = inode->i_mapping;
 
+	/* Ensure that we skip any errors that predate opening of the file */
+	f->f_wb_err = filemap_sample_wb_err(f->f_mapping);
+
 	if (unlikely(f->f_flags & O_PATH)) {
 		f->f_mode = FMODE_PATH;
 		f->f_op = &empty_fops;
@@ -763,6 +762,7 @@ static int do_dentry_open(struct file *f,
 	     likely(f->f_op->write || f->f_op->write_iter))
 		f->f_mode |= FMODE_CAN_WRITE;
 
+	f->f_write_hint = WRITE_LIFE_NOT_SET;
 	f->f_flags &= ~(O_CREAT | O_EXCL | O_NOCTTY | O_TRUNC);
 
 	file_ra_state_init(&f->f_ra, f->f_mapping->host->i_mapping);
@@ -902,6 +902,12 @@ static inline int build_open_flags(int flags, umode_t mode, struct open_flags *o
 	int lookup_flags = 0;
 	int acc_mode = ACC_MODE(flags);
 
+	/*
+	 * Clear out all open flags we don't know about so that we don't report
+	 * them in fcntl(F_GETFD) or similar interfaces.
+	 */
+	flags &= VALID_OPEN_FLAGS;
+
 	if (flags & (O_CREAT | __O_TMPFILE))
 		op->mode = (mode & S_IALLUGO) | S_IFREG;
 	else
@@ -1080,6 +1086,26 @@ SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags,
 	return do_sys_open(dfd, filename, flags, mode);
 }
 
+#ifdef CONFIG_COMPAT
+/*
+ * Exactly like sys_open(), except that it doesn't set the
+ * O_LARGEFILE flag.
+ */
+COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode)
+{
+	return do_sys_open(AT_FDCWD, filename, flags, mode);
+}
+
+/*
+ * Exactly like sys_openat(), except that it doesn't set the
+ * O_LARGEFILE flag.
+ */
+COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode)
+{
+	return do_sys_open(dfd, filename, flags, mode);
+}
+#endif
+
 #ifndef __alpha__
 
 /*
diff --git a/fs/orangefs/devorangefs-req.c b/fs/orangefs/devorangefs-req.c
index b0ced669427e..c19f0787c9c6 100644
--- a/fs/orangefs/devorangefs-req.c
+++ b/fs/orangefs/devorangefs-req.c
@@ -180,6 +180,10 @@ static ssize_t orangefs_devreq_read(struct file *file,
 		return -EINVAL;
 	}
 
+	/* Check for an empty list before locking. */
+	if (list_empty(&orangefs_request_list))
+		return -EAGAIN;
+
 restart:
 	/* Get next op (if any) from top of list. */
 	spin_lock(&orangefs_request_list_lock);
@@ -208,14 +212,19 @@ restart:
 				continue;
 			/*
 			 * Skip ops whose filesystem we don't know about unless
-			 * it is being mounted.
+			 * it is being mounted or unmounted.  It is possible for
+			 * a filesystem we don't know about to be unmounted if
+			 * it fails to mount in the kernel after userspace has
+			 * been sent the mount request.
 			 */
 			/* XXX: is there a better way to detect this? */
 			} else if (ret == -1 &&
 				   !(op->upcall.type ==
 					ORANGEFS_VFS_OP_FS_MOUNT ||
 				     op->upcall.type ==
-					ORANGEFS_VFS_OP_GETATTR)) {
+					ORANGEFS_VFS_OP_GETATTR ||
+				     op->upcall.type ==
+					ORANGEFS_VFS_OP_FS_UMOUNT)) {
 				gossip_debug(GOSSIP_DEV_DEBUG,
 				    "orangefs: skipping op tag %llu %s\n",
 				    llu(op->tag), get_opname_string(op));
@@ -400,8 +409,9 @@ static ssize_t orangefs_devreq_write_iter(struct kiocb *iocb,
 	/* remove the op from the in progress hash table */
 	op = orangefs_devreq_remove_op(head.tag);
 	if (!op) {
-		gossip_err("WARNING: No one's waiting for tag %llu\n",
-			   llu(head.tag));
+		gossip_debug(GOSSIP_DEV_DEBUG,
+			     "%s: No one's waiting for tag %llu\n",
+			     __func__, llu(head.tag));
 		return ret;
 	}
 
diff --git a/fs/orangefs/dir.c b/fs/orangefs/dir.c
index 284373a57a08..d327cbd17756 100644
--- a/fs/orangefs/dir.c
+++ b/fs/orangefs/dir.c
@@ -1,396 +1,404 @@
 /*
- * (C) 2001 Clemson University and The University of Chicago
- *
- * See COPYING in top-level directory.
+ * Copyright 2017 Omnibond Systems, L.L.C.
  */
 
 #include "protocol.h"
 #include "orangefs-kernel.h"
 #include "orangefs-bufmap.h"
 
+struct orangefs_dir_part {
+	struct orangefs_dir_part *next;
+	size_t len;
+};
+
+struct orangefs_dir {
+	__u64 token;
+	struct orangefs_dir_part *part;
+	loff_t end;
+	int error;
+};
+
+#define PART_SHIFT (24)
+#define PART_SIZE (1<<24)
+#define PART_MASK (~(PART_SIZE - 1))
+
 /*
- * decode routine used by kmod to deal with the blob sent from
- * userspace for readdirs. The blob contains zero or more of these
- * sub-blobs:
- *   __u32 - represents length of the character string that follows.
- *   string - between 1 and ORANGEFS_NAME_MAX bytes long.
- *   padding - (if needed) to cause the __u32 plus the string to be
- *             eight byte aligned.
- *   khandle - sizeof(khandle) bytes.
+ * There can be up to 512 directory entries.  Each entry is encoded as
+ * follows:
+ * 4 bytes: string size (n)
+ * n bytes: string
+ * 1 byte: trailing zero
+ * padding to 8 bytes
+ * 16 bytes: khandle
+ * padding to 8 bytes
+ *
+ * The trailer_buf starts with a struct orangefs_readdir_response_s
+ * which must be skipped to get to the directory data.
+ *
+ * The data which is received from the userspace daemon is termed a
+ * part and is stored in a linked list in case more than one part is
+ * needed for a large directory.
+ *
+ * The position pointer (ctx->pos) encodes the part and offset on which
+ * to begin reading at.  Bits above PART_SHIFT encode the part and bits
+ * below PART_SHIFT encode the offset.  Parts are stored in a linked
+ * list which grows as data is received from the server.  The overhead
+ * associated with managing the list is presumed to be small compared to
+ * the overhead of communicating with the server.
+ *
+ * As data is received from the server, it is placed at the end of the
+ * part list.  Data is parsed from the current position as it is needed.
+ * When data is determined to be corrupt, it is either because the
+ * userspace component has sent back corrupt data or because the file
+ * pointer has been moved to an invalid location.  Since the two cannot
+ * be differentiated, return EIO.
+ *
+ * Part zero is synthesized to contains `.' and `..'.  Part one is the
+ * first part of the part list.
  */
-static long decode_dirents(char *ptr, size_t size,
-                           struct orangefs_readdir_response_s *readdir)
+
+static int do_readdir(struct orangefs_inode_s *oi,
+    struct orangefs_dir *od, struct dentry *dentry,
+    struct orangefs_kernel_op_s *op)
 {
-	int i;
-	struct orangefs_readdir_response_s *rd =
-		(struct orangefs_readdir_response_s *) ptr;
-	char *buf = ptr;
-	int khandle_size = sizeof(struct orangefs_khandle);
-	size_t offset = offsetof(struct orangefs_readdir_response_s,
-				dirent_array);
-	/* 8 reflects eight byte alignment */
-	int smallest_blob = khandle_size + 8;
-	__u32 len;
-	int aligned_len;
-	int sizeof_u32 = sizeof(__u32);
-	long ret;
-
-	gossip_debug(GOSSIP_DIR_DEBUG, "%s: size:%zu:\n", __func__, size);
-
-	/* size is = offset on empty dirs, > offset on non-empty dirs... */
-	if (size < offset) {
-		gossip_err("%s: size:%zu: offset:%zu:\n",
-			   __func__,
-			   size,
-			   offset);
-		ret = -EINVAL;
-		goto out;
-	}
+	struct orangefs_readdir_response_s *resp;
+	int bufi, r;
 
-        if ((size == offset) && (readdir->orangefs_dirent_outcount != 0)) {
-		gossip_err("%s: size:%zu: dirent_outcount:%d:\n",
-			   __func__,
-			   size,
-			   readdir->orangefs_dirent_outcount);
-		ret = -EINVAL;
-		goto out;
-	}
+	/*
+	 * Despite the badly named field, readdir does not use shared
+	 * memory.  However, there are a limited number of readdir
+	 * slots, which must be allocated here.  This flag simply tells
+	 * the op scheduler to return the op here for retry.
+	 */
+	op->uses_shared_memory = 1;
+	op->upcall.req.readdir.refn = oi->refn;
+	op->upcall.req.readdir.token = od->token;
+	op->upcall.req.readdir.max_dirent_count =
+	    ORANGEFS_MAX_DIRENT_COUNT_READDIR;
 
-	readdir->token = rd->token;
-	readdir->orangefs_dirent_outcount = rd->orangefs_dirent_outcount;
-	readdir->dirent_array = kcalloc(readdir->orangefs_dirent_outcount,
-					sizeof(*readdir->dirent_array),
-					GFP_KERNEL);
-	if (readdir->dirent_array == NULL) {
-		gossip_err("%s: kcalloc failed.\n", __func__);
-		ret = -ENOMEM;
-		goto out;
+again:
+	bufi = orangefs_readdir_index_get();
+	if (bufi < 0) {
+		od->error = bufi;
+		return bufi;
 	}
 
-	buf += offset;
-	size -= offset;
-
-	for (i = 0; i < readdir->orangefs_dirent_outcount; i++) {
-		if (size < smallest_blob) {
-			gossip_err("%s: size:%zu: smallest_blob:%d:\n",
-				   __func__,
-				   size,
-				   smallest_blob);
-			ret = -EINVAL;
-			goto free;
-		}
+	op->upcall.req.readdir.buf_index = bufi;
 
-		len = *(__u32 *)buf;
-		if ((len < 1) || (len > ORANGEFS_NAME_MAX)) {
-			gossip_err("%s: len:%d:\n", __func__, len);
-			ret = -EINVAL;
-			goto free;
-		}
+	r = service_operation(op, "orangefs_readdir",
+	    get_interruptible_flag(dentry->d_inode));
 
-		gossip_debug(GOSSIP_DIR_DEBUG,
-			     "%s: size:%zu: len:%d:\n",
-			     __func__,
-			     size,
-			     len);
+	orangefs_readdir_index_put(bufi);
 
-		readdir->dirent_array[i].d_name = buf + sizeof_u32;
-		readdir->dirent_array[i].d_length = len;
+	if (op_state_purged(op)) {
+		if (r == -EAGAIN) {
+			vfree(op->downcall.trailer_buf);
+			goto again;
+		} else if (r == -EIO) {
+			vfree(op->downcall.trailer_buf);
+			od->error = r;
+			return r;
+		}
+	}
 
-		/*
-		 * Calculate "aligned" length of this string and its
-		 * associated __u32 descriptor.
-		 */
-		aligned_len = ((sizeof_u32 + len + 1) + 7) & ~7;
-		gossip_debug(GOSSIP_DIR_DEBUG,
-			     "%s: aligned_len:%d:\n",
-			     __func__,
-			     aligned_len);
+	if (r < 0) {
+		vfree(op->downcall.trailer_buf);
+		od->error = r;
+		return r;
+	} else if (op->downcall.status) {
+		vfree(op->downcall.trailer_buf);
+		od->error = op->downcall.status;
+		return op->downcall.status;
+	}
 
-		/*
-		 * The end of the blob should coincide with the end
-		 * of the last sub-blob.
-		 */
-		if (size < aligned_len + khandle_size) {
-			gossip_err("%s: ran off the end of the blob.\n",
-				   __func__);
-			ret = -EINVAL;
-			goto free;
-		}
-		size -= aligned_len + khandle_size;
+	/*
+	 * The maximum size is size per entry times the 512 entries plus
+	 * the header.  This is well under the limit.
+	 */
+	if (op->downcall.trailer_size > PART_SIZE) {
+		vfree(op->downcall.trailer_buf);
+		od->error = -EIO;
+		return -EIO;
+	}
 
-		buf += aligned_len;
+	resp = (struct orangefs_readdir_response_s *)
+	    op->downcall.trailer_buf;
+	od->token = resp->token;
+	return 0;
+}
 
-		readdir->dirent_array[i].khandle =
-			*(struct orangefs_khandle *) buf;
-		buf += khandle_size;
+static int parse_readdir(struct orangefs_dir *od,
+    struct orangefs_kernel_op_s *op)
+{
+	struct orangefs_dir_part *part, *new;
+	size_t count;
+
+	count = 1;
+	part = od->part;
+	while (part) {
+		count++;
+		if (part->next)
+			part = part->next;
+		else
+			break;
 	}
-	ret = buf - ptr;
-	gossip_debug(GOSSIP_DIR_DEBUG, "%s: returning:%ld:\n", __func__, ret);
-	goto out;
 
-free:
-	kfree(readdir->dirent_array);
-	readdir->dirent_array = NULL;
+	new = (void *)op->downcall.trailer_buf;
+	new->next = NULL;
+	new->len = op->downcall.trailer_size -
+	    sizeof(struct orangefs_readdir_response_s);
+	if (!od->part)
+		od->part = new;
+	else
+		part->next = new;
+	count++;
+	od->end = count << PART_SHIFT;
 
-out:
-	return ret;
+	return 0;
 }
 
-/*
- * Read directory entries from an instance of an open directory.
- */
-static int orangefs_readdir(struct file *file, struct dir_context *ctx)
+static int orangefs_dir_more(struct orangefs_inode_s *oi,
+    struct orangefs_dir *od, struct dentry *dentry)
 {
-	int ret = 0;
-	int buffer_index;
-	/*
-	 * ptoken supports Orangefs' distributed directory logic, added
-	 * in 2.9.2.
-	 */
-	__u64 *ptoken = file->private_data;
-	__u64 pos = 0;
-	ino_t ino = 0;
-	struct dentry *dentry = file->f_path.dentry;
-	struct orangefs_kernel_op_s *new_op = NULL;
-	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(dentry->d_inode);
-	struct orangefs_readdir_response_s readdir_response;
-	void *dents_buf;
-	int i = 0;
-	int len = 0;
-	ino_t current_ino = 0;
-	char *current_entry = NULL;
-	long bytes_decoded;
-
-	gossip_debug(GOSSIP_DIR_DEBUG,
-		     "%s: ctx->pos:%lld, ptoken = %llu\n",
-		     __func__,
-		     lld(ctx->pos),
-		     llu(*ptoken));
-
-	pos = (__u64) ctx->pos;
-
-	/* are we done? */
-	if (pos == ORANGEFS_READDIR_END) {
-		gossip_debug(GOSSIP_DIR_DEBUG,
-			     "Skipping to termination path\n");
-		return 0;
+	struct orangefs_kernel_op_s *op;
+	int r;
+
+	op = op_alloc(ORANGEFS_VFS_OP_READDIR);
+	if (!op) {
+		od->error = -ENOMEM;
+		return -ENOMEM;
+	}
+	r = do_readdir(oi, od, dentry, op);
+	if (r) {
+		od->error = r;
+		goto out;
+	}
+	r = parse_readdir(od, op);
+	if (r) {
+		od->error = r;
+		goto out;
 	}
 
-	gossip_debug(GOSSIP_DIR_DEBUG,
-		     "orangefs_readdir called on %pd (pos=%llu)\n",
-		     dentry, llu(pos));
+	od->error = 0;
+out:
+	op_release(op);
+	return od->error;
+}
 
-	memset(&readdir_response, 0, sizeof(readdir_response));
+static int fill_from_part(struct orangefs_dir_part *part,
+    struct dir_context *ctx)
+{
+	const int offset = sizeof(struct orangefs_readdir_response_s);
+	struct orangefs_khandle *khandle;
+	__u32 *len, padlen;
+	loff_t i;
+	char *s;
+	i = ctx->pos & ~PART_MASK;
 
-	new_op = op_alloc(ORANGEFS_VFS_OP_READDIR);
-	if (!new_op)
-		return -ENOMEM;
+	/* The file offset from userspace is too large. */
+	if (i > part->len)
+		return 1;
 
 	/*
-	 * Only the indices are shared. No memory is actually shared, but the
-	 * mechanism is used.
+	 * If the seek pointer is positioned just before an entry it
+	 * should find the next entry.
 	 */
-	new_op->uses_shared_memory = 1;
-	new_op->upcall.req.readdir.refn = orangefs_inode->refn;
-	new_op->upcall.req.readdir.max_dirent_count =
-	    ORANGEFS_MAX_DIRENT_COUNT_READDIR;
-
-	gossip_debug(GOSSIP_DIR_DEBUG,
-		     "%s: upcall.req.readdir.refn.khandle: %pU\n",
-		     __func__,
-		     &new_op->upcall.req.readdir.refn.khandle);
+	if (i % 8)
+		i = i + (8 - i%8)%8;
 
-	new_op->upcall.req.readdir.token = *ptoken;
-
-get_new_buffer_index:
-	buffer_index = orangefs_readdir_index_get();
-	if (buffer_index < 0) {
-		ret = buffer_index;
-		gossip_lerr("orangefs_readdir: orangefs_readdir_index_get() failure (%d)\n",
-			    ret);
-		goto out_free_op;
+	while (i < part->len) {
+		if (part->len < i + sizeof *len)
+			break;
+		len = (void *)part + offset + i;
+		/*
+		 * len is the size of the string itself.  padlen is the
+		 * total size of the encoded string.
+		 */
+		padlen = (sizeof *len + *len + 1) +
+		    (8 - (sizeof *len + *len + 1)%8)%8;
+		if (part->len < i + padlen + sizeof *khandle)
+			goto next;
+		s = (void *)part + offset + i + sizeof *len;
+		if (s[*len] != 0)
+			goto next;
+		khandle = (void *)part + offset + i + padlen;
+		if (!dir_emit(ctx, s, *len,
+		    orangefs_khandle_to_ino(khandle),
+		    DT_UNKNOWN))
+			return 0;
+		i += padlen + sizeof *khandle;
+		i = i + (8 - i%8)%8;
+		BUG_ON(i > part->len);
+		ctx->pos = (ctx->pos & PART_MASK) | i;
+		continue;
+next:
+		i += 8;
 	}
-	new_op->upcall.req.readdir.buf_index = buffer_index;
-
-	ret = service_operation(new_op,
-				"orangefs_readdir",
-				get_interruptible_flag(dentry->d_inode));
+	return 1;
+}
 
-	gossip_debug(GOSSIP_DIR_DEBUG,
-		     "Readdir downcall status is %d.  ret:%d\n",
-		     new_op->downcall.status,
-		     ret);
+static int orangefs_dir_fill(struct orangefs_inode_s *oi,
+    struct orangefs_dir *od, struct dentry *dentry,
+    struct dir_context *ctx)
+{
+	struct orangefs_dir_part *part;
+	size_t count;
 
-	orangefs_readdir_index_put(buffer_index);
+	count = ((ctx->pos & PART_MASK) >> PART_SHIFT) - 1;
 
-	if (ret == -EAGAIN && op_state_purged(new_op)) {
-		/* Client-core indices are invalid after it restarted. */
-		gossip_debug(GOSSIP_DIR_DEBUG,
-			"%s: Getting new buffer_index for retry of readdir..\n",
-			 __func__);
-		goto get_new_buffer_index;
+	part = od->part;
+	while (part->next && count) {
+		count--;
+		part = part->next;
 	}
-
-	if (ret == -EIO && op_state_purged(new_op)) {
-		gossip_err("%s: Client is down. Aborting readdir call.\n",
-			__func__);
-		goto out_free_op;
+	/* This means the userspace file offset is invalid. */
+	if (count) {
+		od->error = -EIO;
+		return -EIO;
 	}
 
-	if (ret < 0 || new_op->downcall.status != 0) {
-		gossip_debug(GOSSIP_DIR_DEBUG,
-			     "Readdir request failed.  Status:%d\n",
-			     new_op->downcall.status);
-		if (ret >= 0)
-			ret = new_op->downcall.status;
-		goto out_free_op;
+	while (part && part->len) {
+		int r;
+		r = fill_from_part(part, ctx);
+		if (r < 0) {
+			od->error = r;
+			return r;
+		} else if (r == 0) {
+			/* Userspace buffer is full. */
+			break;
+		} else {
+			/*
+			 * The part ran out of data.  Move to the next
+			 * part. */
+			ctx->pos = (ctx->pos & PART_MASK) +
+			    (1 << PART_SHIFT);
+			part = part->next;
+		}
 	}
+	return 0;
+}
 
-	dents_buf = new_op->downcall.trailer_buf;
-	if (dents_buf == NULL) {
-		gossip_err("Invalid NULL buffer in readdir response\n");
-		ret = -ENOMEM;
-		goto out_free_op;
+static loff_t orangefs_dir_llseek(struct file *file, loff_t offset,
+    int whence)
+{
+	struct orangefs_dir *od = file->private_data;
+	/*
+	 * Delete the stored data so userspace sees new directory
+	 * entries.
+	 */
+	if (!whence && offset < od->end) {
+		struct orangefs_dir_part *part = od->part;
+		while (part) {
+			struct orangefs_dir_part *next = part->next;
+			vfree(part);
+			part = next;
+		}
+		od->token = ORANGEFS_ITERATE_START;
+		od->part = NULL;
+		od->end = 1 << PART_SHIFT;
 	}
+	return default_llseek(file, offset, whence);
+}
 
-	bytes_decoded = decode_dirents(dents_buf, new_op->downcall.trailer_size,
-					&readdir_response);
-	if (bytes_decoded < 0) {
-		ret = bytes_decoded;
-		gossip_err("Could not decode readdir from buffer %d\n", ret);
-		goto out_vfree;
-	}
+static int orangefs_dir_iterate(struct file *file,
+    struct dir_context *ctx)
+{
+	struct orangefs_inode_s *oi;
+	struct orangefs_dir *od;
+	struct dentry *dentry;
+	int r;
 
-	if (bytes_decoded != new_op->downcall.trailer_size) {
-		gossip_err("orangefs_readdir: # bytes decoded (%ld) "
-			   "!= trailer size (%ld)\n",
-			   bytes_decoded,
-			   (long)new_op->downcall.trailer_size);
-		ret = -EINVAL;
-		goto out_destroy_handle;
-	}
+	dentry = file->f_path.dentry;
+	oi = ORANGEFS_I(dentry->d_inode);
+	od = file->private_data;
 
-	/*
-	 *  orangefs doesn't actually store dot and dot-dot, but
-	 *  we need to have them represented.
-	 */
-	if (pos == 0) {
-		ino = get_ino_from_khandle(dentry->d_inode);
-		gossip_debug(GOSSIP_DIR_DEBUG,
-			     "%s: calling dir_emit of \".\" with pos = %llu\n",
-			     __func__,
-			     llu(pos));
-		ret = dir_emit(ctx, ".", 1, ino, DT_DIR);
-		pos += 1;
-	}
+	if (od->error)
+		return od->error;
 
-	if (pos == 1) {
-		ino = get_parent_ino_from_dentry(dentry);
-		gossip_debug(GOSSIP_DIR_DEBUG,
-			     "%s: calling dir_emit of \"..\" with pos = %llu\n",
-			     __func__,
-			     llu(pos));
-		ret = dir_emit(ctx, "..", 2, ino, DT_DIR);
-		pos += 1;
+	if (ctx->pos == 0) {
+		if (!dir_emit_dot(file, ctx))
+			return 0;
+		ctx->pos++;
+	}
+	if (ctx->pos == 1) {
+		if (!dir_emit_dotdot(file, ctx))
+			return 0;
+		ctx->pos = 1 << PART_SHIFT;
 	}
 
 	/*
-	 * we stored ORANGEFS_ITERATE_NEXT in ctx->pos last time around
-	 * to prevent "finding" dot and dot-dot on any iteration
-	 * other than the first.
+	 * The seek position is in the first synthesized part but is not
+	 * valid.
 	 */
-	if (ctx->pos == ORANGEFS_ITERATE_NEXT)
-		ctx->pos = 0;
-
-	gossip_debug(GOSSIP_DIR_DEBUG,
-		     "%s: dirent_outcount:%d:\n",
-		     __func__,
-		     readdir_response.orangefs_dirent_outcount);
-	for (i = ctx->pos;
-	     i < readdir_response.orangefs_dirent_outcount;
-	     i++) {
-		len = readdir_response.dirent_array[i].d_length;
-		current_entry = readdir_response.dirent_array[i].d_name;
-		current_ino = orangefs_khandle_to_ino(
-			&readdir_response.dirent_array[i].khandle);
-
-		gossip_debug(GOSSIP_DIR_DEBUG,
-			     "calling dir_emit for %s with len %d"
-			     ", ctx->pos %ld\n",
-			     current_entry,
-			     len,
-			     (unsigned long)ctx->pos);
-		/*
-		 * type is unknown. We don't return object type
-		 * in the dirent_array. This leaves getdents
-		 * clueless about type.
-		 */
-		ret =
-		    dir_emit(ctx, current_entry, len, current_ino, DT_UNKNOWN);
-		if (!ret)
-			break;
-		ctx->pos++;
-		gossip_debug(GOSSIP_DIR_DEBUG,
-			      "%s: ctx->pos:%lld\n",
-			      __func__,
-			      lld(ctx->pos));
+	if ((ctx->pos & PART_MASK) == 0)
+		return -EIO;
 
-	}
+	r = 0;
 
 	/*
-	 * we ran all the way through the last batch, set up for
-	 * getting another batch...
+	 * Must read more if the user has sought past what has been read
+	 * so far.  Stop a user who has sought past the end.
 	 */
-	if (ret) {
-		*ptoken = readdir_response.token;
-		ctx->pos = ORANGEFS_ITERATE_NEXT;
+	while (od->token != ORANGEFS_ITERATE_END &&
+	    ctx->pos > od->end) {
+		r = orangefs_dir_more(oi, od, dentry);
+		if (r)
+			return r;
+	}
+	if (od->token == ORANGEFS_ITERATE_END && ctx->pos > od->end)
+		return -EIO;
+
+	/* Then try to fill if there's any left in the buffer. */
+	if (ctx->pos < od->end) {
+		r = orangefs_dir_fill(oi, od, dentry, ctx);
+		if (r)
+			return r;
 	}
 
-	/*
-	 * Did we hit the end of the directory?
-	 */
-	if (readdir_response.token == ORANGEFS_READDIR_END) {
-		gossip_debug(GOSSIP_DIR_DEBUG,
-		"End of dir detected; setting ctx->pos to ORANGEFS_READDIR_END.\n");
-		ctx->pos = ORANGEFS_READDIR_END;
+	/* Finally get some more and try to fill. */
+	if (od->token != ORANGEFS_ITERATE_END) {
+		r = orangefs_dir_more(oi, od, dentry);
+		if (r)
+			return r;
+		r = orangefs_dir_fill(oi, od, dentry, ctx);
 	}
 
-out_destroy_handle:
-	/* kfree(NULL) is safe */
-	kfree(readdir_response.dirent_array);
-out_vfree:
-	gossip_debug(GOSSIP_DIR_DEBUG, "vfree %p\n", dents_buf);
-	vfree(dents_buf);
-out_free_op:
-	op_release(new_op);
-	gossip_debug(GOSSIP_DIR_DEBUG, "orangefs_readdir returning %d\n", ret);
-	return ret;
+	return r;
 }
 
 static int orangefs_dir_open(struct inode *inode, struct file *file)
 {
-	__u64 *ptoken;
-
-	file->private_data = kmalloc(sizeof(__u64), GFP_KERNEL);
+	struct orangefs_dir *od;
+	file->private_data = kmalloc(sizeof(struct orangefs_dir),
+	    GFP_KERNEL);
 	if (!file->private_data)
 		return -ENOMEM;
-
-	ptoken = file->private_data;
-	*ptoken = ORANGEFS_READDIR_START;
+	od = file->private_data;
+	od->token = ORANGEFS_ITERATE_START;
+	od->part = NULL;
+	od->end = 1 << PART_SHIFT;
+	od->error = 0;
 	return 0;
 }
 
 static int orangefs_dir_release(struct inode *inode, struct file *file)
 {
+	struct orangefs_dir *od = file->private_data;
+	struct orangefs_dir_part *part = od->part;
 	orangefs_flush_inode(inode);
-	kfree(file->private_data);
+	while (part) {
+		struct orangefs_dir_part *next = part->next;
+		vfree(part);
+		part = next;
+	}
+	kfree(od);
 	return 0;
 }
 
-/** ORANGEFS implementation of VFS directory operations */
 const struct file_operations orangefs_dir_operations = {
+	.llseek = orangefs_dir_llseek,
 	.read = generic_read_dir,
-	.iterate = orangefs_readdir,
+	.iterate = orangefs_dir_iterate,
 	.open = orangefs_dir_open,
-	.release = orangefs_dir_release,
+	.release = orangefs_dir_release
 };
diff --git a/fs/orangefs/downcall.h b/fs/orangefs/downcall.h
index 3b8923f8bf21..163001c95501 100644
--- a/fs/orangefs/downcall.h
+++ b/fs/orangefs/downcall.h
@@ -40,16 +40,6 @@ struct orangefs_mkdir_response {
 	struct orangefs_object_kref refn;
 };
 
-/*
- * duplication of some system interface structures so that I don't have
- * to allocate extra memory
- */
-struct orangefs_dirent {
-	char *d_name;
-	int d_length;
-	struct orangefs_khandle khandle;
-};
-
 struct orangefs_statfs_response {
 	__s64 block_size;
 	__s64 blocks_total;
@@ -131,12 +121,16 @@ struct orangefs_downcall_s {
 	} resp;
 };
 
+/*
+ * The readdir response comes in the trailer.  It is followed by the
+ * directory entries as described in dir.c.
+ */
+
 struct orangefs_readdir_response_s {
 	__u64 token;
 	__u64 directory_version;
 	__u32 __pad2;
 	__u32 orangefs_dirent_outcount;
-	struct orangefs_dirent *dirent_array;
 };
 
 #endif /* __DOWNCALL_H */
diff --git a/fs/orangefs/file.c b/fs/orangefs/file.c
index e6bbc8083d77..28f38d813ad2 100644
--- a/fs/orangefs/file.c
+++ b/fs/orangefs/file.c
@@ -114,7 +114,6 @@ static ssize_t wait_for_direct_io(enum ORANGEFS_io_type type, struct inode *inod
 	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
 	struct orangefs_khandle *handle = &orangefs_inode->refn.khandle;
 	struct orangefs_kernel_op_s *new_op = NULL;
-	struct iov_iter saved = *iter;
 	int buffer_index = -1;
 	ssize_t ret;
 
@@ -193,7 +192,7 @@ populate_shared_memory:
 		orangefs_bufmap_put(buffer_index);
 		buffer_index = -1;
 		if (type == ORANGEFS_IO_WRITE)
-			*iter = saved;
+			iov_iter_revert(iter, total_size);
 		gossip_debug(GOSSIP_FILE_DEBUG,
 			     "%s:going to repopulate_shared_memory.\n",
 			     __func__);
@@ -475,7 +474,8 @@ static ssize_t orangefs_file_write_iter(struct kiocb *iocb, struct iov_iter *ite
 
 	/* Make sure generic_write_checks sees an up to date inode size. */
 	if (file->f_flags & O_APPEND) {
-		rc = orangefs_inode_getattr(file->f_mapping->host, 0, 1);
+		rc = orangefs_inode_getattr(file->f_mapping->host, 0, 1,
+		    STATX_SIZE);
 		if (rc == -ESTALE)
 			rc = -EIO;
 		if (rc) {
@@ -693,7 +693,8 @@ static loff_t orangefs_file_llseek(struct file *file, loff_t offset, int origin)
 		 * NOTE: We are only interested in file size here,
 		 * so we set mask accordingly.
 		 */
-		ret = orangefs_inode_getattr(file->f_mapping->host, 0, 1);
+		ret = orangefs_inode_getattr(file->f_mapping->host, 0, 1,
+		    STATX_SIZE);
 		if (ret == -ESTALE)
 			ret = -EIO;
 		if (ret) {
diff --git a/fs/orangefs/inode.c b/fs/orangefs/inode.c
index 551bc74ed2b8..9428ea0aac16 100644
--- a/fs/orangefs/inode.c
+++ b/fs/orangefs/inode.c
@@ -136,12 +136,6 @@ static ssize_t orangefs_direct_IO(struct kiocb *iocb,
 	return -EINVAL;
 }
 
-struct backing_dev_info orangefs_backing_dev_info = {
-	.name = "orangefs",
-	.ra_pages = 0,
-	.capabilities = BDI_CAP_NO_ACCT_DIRTY | BDI_CAP_NO_WRITEBACK,
-};
-
 /** ORANGEFS2 implementation of address space operations */
 const struct address_space_operations orangefs_address_operations = {
 	.readpage = orangefs_readpage,
@@ -167,7 +161,7 @@ static int orangefs_setattr_size(struct inode *inode, struct iattr *iattr)
 		     iattr->ia_size);
 
 	/* Ensure that we have a up to date size, so we know if it changed. */
-	ret = orangefs_inode_getattr(inode, 0, 1);
+	ret = orangefs_inode_getattr(inode, 0, 1, STATX_SIZE);
 	if (ret == -ESTALE)
 		ret = -EIO;
 	if (ret) {
@@ -224,8 +218,7 @@ int orangefs_setattr(struct dentry *dentry, struct iattr *iattr)
 	if (ret)
 		goto out;
 
-	if ((iattr->ia_valid & ATTR_SIZE) &&
-	    iattr->ia_size != i_size_read(inode)) {
+	if (iattr->ia_valid & ATTR_SIZE) {
 		ret = orangefs_setattr_size(inode, iattr);
 		if (ret)
 			goto out;
@@ -251,25 +244,30 @@ out:
 /*
  * Obtain attributes of an object given a dentry
  */
-int orangefs_getattr(struct vfsmount *mnt,
-		  struct dentry *dentry,
-		  struct kstat *kstat)
+int orangefs_getattr(const struct path *path, struct kstat *stat,
+		     u32 request_mask, unsigned int flags)
 {
 	int ret = -ENOENT;
-	struct inode *inode = dentry->d_inode;
+	struct inode *inode = path->dentry->d_inode;
 	struct orangefs_inode_s *orangefs_inode = NULL;
 
 	gossip_debug(GOSSIP_INODE_DEBUG,
 		     "orangefs_getattr: called on %pd\n",
-		     dentry);
+		     path->dentry);
 
-	ret = orangefs_inode_getattr(inode, 0, 0);
+	ret = orangefs_inode_getattr(inode, 0, 0, request_mask);
 	if (ret == 0) {
-		generic_fillattr(inode, kstat);
+		generic_fillattr(inode, stat);
 
 		/* override block size reported to stat */
 		orangefs_inode = ORANGEFS_I(inode);
-		kstat->blksize = orangefs_inode->blksize;
+		stat->blksize = orangefs_inode->blksize;
+
+		if (request_mask & STATX_SIZE)
+			stat->result_mask = STATX_BASIC_STATS;
+		else
+			stat->result_mask = STATX_BASIC_STATS &
+			    ~STATX_SIZE;
 	}
 	return ret;
 }
@@ -284,7 +282,7 @@ int orangefs_permission(struct inode *inode, int mask)
 	gossip_debug(GOSSIP_INODE_DEBUG, "%s: refreshing\n", __func__);
 
 	/* Make sure the permission (and other common attrs) are up to date. */
-	ret = orangefs_inode_getattr(inode, 0, 0);
+	ret = orangefs_inode_getattr(inode, 0, 0, STATX_MODE);
 	if (ret < 0)
 		return ret;
 
@@ -382,7 +380,7 @@ struct inode *orangefs_iget(struct super_block *sb, struct orangefs_object_kref
 	if (!inode || !(inode->i_state & I_NEW))
 		return inode;
 
-	error = orangefs_inode_getattr(inode, 1, 1);
+	error = orangefs_inode_getattr(inode, 1, 1, STATX_ALL);
 	if (error) {
 		iget_failed(inode);
 		return ERR_PTR(error);
@@ -427,7 +425,7 @@ struct inode *orangefs_new_inode(struct super_block *sb, struct inode *dir,
 	orangefs_set_inode(inode, ref);
 	inode->i_ino = hash;	/* needed for stat etc */
 
-	error = orangefs_inode_getattr(inode, 1, 1);
+	error = orangefs_inode_getattr(inode, 1, 1, STATX_ALL);
 	if (error)
 		goto out_iput;
 
diff --git a/fs/orangefs/namei.c b/fs/orangefs/namei.c
index a290ff6ec756..478e88bd7f9d 100644
--- a/fs/orangefs/namei.c
+++ b/fs/orangefs/namei.c
@@ -74,6 +74,7 @@ static int orangefs_create(struct inode *dir,
 	unlock_new_inode(inode);
 	orangefs_set_timeout(dentry);
 	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
+	ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
 
 	gossip_debug(GOSSIP_NAME_DEBUG,
 		     "%s: dentry instantiated for %pd\n",
@@ -193,8 +194,6 @@ static struct dentry *orangefs_lookup(struct inode *dir, struct dentry *dentry,
 		goto out;
 	}
 
-	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
-
 	gossip_debug(GOSSIP_NAME_DEBUG,
 		     "%s:%s:%d "
 		     "Found good inode [%lu] with count [%d]\n",
@@ -324,6 +323,7 @@ static int orangefs_symlink(struct inode *dir,
 	unlock_new_inode(inode);
 	orangefs_set_timeout(dentry);
 	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
+	ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
 
 	gossip_debug(GOSSIP_NAME_DEBUG,
 		     "Inode (Symlink) %pU -> %pd\n",
@@ -388,6 +388,7 @@ static int orangefs_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode
 	unlock_new_inode(inode);
 	orangefs_set_timeout(dentry);
 	ORANGEFS_I(inode)->getattr_time = jiffies - 1;
+	ORANGEFS_I(inode)->getattr_mask = STATX_BASIC_STATS;
 
 	gossip_debug(GOSSIP_NAME_DEBUG,
 		     "Inode (Directory) %pU -> %pd\n",
diff --git a/fs/orangefs/orangefs-bufmap.c b/fs/orangefs/orangefs-bufmap.c
index 75375e90a63f..038d67545d9f 100644
--- a/fs/orangefs/orangefs-bufmap.c
+++ b/fs/orangefs/orangefs-bufmap.c
@@ -46,8 +46,8 @@ static void run_down(struct slot_map *m)
 	spin_lock(&m->q.lock);
 	if (m->c != -1) {
 		for (;;) {
-			if (likely(list_empty(&wait.task_list)))
-				__add_wait_queue_tail(&m->q, &wait);
+			if (likely(list_empty(&wait.entry)))
+				__add_wait_queue_entry_tail(&m->q, &wait);
 			set_current_state(TASK_UNINTERRUPTIBLE);
 
 			if (m->c == -1)
@@ -84,8 +84,8 @@ static int wait_for_free(struct slot_map *m)
 
 	do {
 		long n = left, t;
-		if (likely(list_empty(&wait.task_list)))
-			__add_wait_queue_tail_exclusive(&m->q, &wait);
+		if (likely(list_empty(&wait.entry)))
+			__add_wait_queue_entry_tail_exclusive(&m->q, &wait);
 		set_current_state(TASK_INTERRUPTIBLE);
 
 		if (m->c > 0)
@@ -108,8 +108,8 @@ static int wait_for_free(struct slot_map *m)
 			left = -EINTR;
 	} while (left > 0);
 
-	if (!list_empty(&wait.task_list))
-		list_del(&wait.task_list);
+	if (!list_empty(&wait.entry))
+		list_del(&wait.entry);
 	else if (left <= 0 && waitqueue_active(&m->q))
 		__wake_up_locked_key(&m->q, TASK_INTERRUPTIBLE, NULL);
 	__set_current_state(TASK_RUNNING);
@@ -344,6 +344,11 @@ int orangefs_bufmap_initialize(struct ORANGEFS_dev_map_desc *user_desc)
 		     user_desc->size,
 		     user_desc->count);
 
+	if (user_desc->total_size < 0 ||
+	    user_desc->size < 0 ||
+	    user_desc->count < 0)
+		goto out;
+
 	/*
 	 * sanity check alignment and size of buffer that caller wants to
 	 * work with
@@ -516,13 +521,11 @@ int orangefs_bufmap_copy_from_iovec(struct iov_iter *iter,
 		size_t n = size;
 		if (n > PAGE_SIZE)
 			n = PAGE_SIZE;
-		n = copy_page_from_iter(page, 0, n, iter);
-		if (!n)
+		if (copy_page_from_iter(page, 0, n, iter) != n)
 			return -EFAULT;
 		size -= n;
 	}
 	return 0;
-
 }
 
 /*
diff --git a/fs/orangefs/orangefs-debugfs.c b/fs/orangefs/orangefs-debugfs.c
index 27e75cf28b3a..716ed337f166 100644
--- a/fs/orangefs/orangefs-debugfs.c
+++ b/fs/orangefs/orangefs-debugfs.c
@@ -440,6 +440,9 @@ static ssize_t orangefs_debug_write(struct file *file,
 		"orangefs_debug_write: %pD\n",
 		file);
 
+	if (count == 0)
+		return 0;
+
 	/*
 	 * Thwart users who try to jamb a ridiculous number
 	 * of bytes into the debug file...
@@ -967,13 +970,13 @@ int orangefs_debugfs_new_client_string(void __user *arg)
 	int ret;
 
 	ret = copy_from_user(&client_debug_array_string,
-                                     (void __user *)arg,
-                                     ORANGEFS_MAX_DEBUG_STRING_LEN);
+			     (void __user *)arg,
+			     ORANGEFS_MAX_DEBUG_STRING_LEN);
 
 	if (ret != 0) {
 		pr_info("%s: CLIENT_STRING: copy_from_user failed\n",
 			__func__);
-		return -EIO;
+		return -EFAULT;
 	}
 
 	/*
@@ -988,17 +991,18 @@ int orangefs_debugfs_new_client_string(void __user *arg)
 	 */
 	client_debug_array_string[ORANGEFS_MAX_DEBUG_STRING_LEN - 1] =
 		'\0';
-	
+
 	pr_info("%s: client debug array string has been received.\n",
 		__func__);
 
 	if (!help_string_initialized) {
 
 		/* Build a proper debug help string. */
-		if (orangefs_prepare_debugfs_help_string(0)) {
+		ret = orangefs_prepare_debugfs_help_string(0);
+		if (ret) {
 			gossip_err("%s: no debug help string \n",
 				   __func__);
-			return -EIO;
+			return ret;
 		}
 
 	}
@@ -1011,7 +1015,7 @@ int orangefs_debugfs_new_client_string(void __user *arg)
 
 	help_string_initialized++;
 
-	return ret;
+	return 0;
 }
 
 int orangefs_debugfs_new_debug(void __user *arg) 
diff --git a/fs/orangefs/orangefs-dev-proto.h b/fs/orangefs/orangefs-dev-proto.h
index a3d84ffee905..efe08c763e56 100644
--- a/fs/orangefs/orangefs-dev-proto.h
+++ b/fs/orangefs/orangefs-dev-proto.h
@@ -50,15 +50,9 @@
  * Misc constants. Please retain them as multiples of 8!
  * Otherwise 32-64 bit interactions will be messed up :)
  */
-#define ORANGEFS_MAX_DEBUG_STRING_LEN	0x00000400
-#define ORANGEFS_MAX_DEBUG_ARRAY_LEN	0x00000800
+#define ORANGEFS_MAX_DEBUG_STRING_LEN	0x00000800
 
-/*
- * The maximum number of directory entries in a single request is 96.
- * XXX: Why can this not be higher. The client-side code can handle up to 512.
- * XXX: What happens if we expect more than the client can return?
- */
-#define ORANGEFS_MAX_DIRENT_COUNT_READDIR 96
+#define ORANGEFS_MAX_DIRENT_COUNT_READDIR 512
 
 #include "upcall.h"
 #include "downcall.h"
diff --git a/fs/orangefs/orangefs-kernel.h b/fs/orangefs/orangefs-kernel.h
index 3bf803d732c5..ea0ce507a6ab 100644
--- a/fs/orangefs/orangefs-kernel.h
+++ b/fs/orangefs/orangefs-kernel.h
@@ -41,7 +41,7 @@
 #include <linux/uaccess.h>
 #include <linux/atomic.h>
 #include <linux/uio.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/mm.h>
 #include <linux/wait.h>
 #include <linux/dcache.h>
@@ -215,6 +215,7 @@ struct orangefs_inode_s {
 	unsigned long pinode_flags;
 
 	unsigned long getattr_time;
+	u32 getattr_mask;
 };
 
 #define P_ATIME_FLAG 0
@@ -249,6 +250,7 @@ struct orangefs_sb_info_s {
 	char devname[ORANGEFS_MAX_SERVER_ADDR_LEN];
 	struct super_block *sb;
 	int mount_pending;
+	int no_list;
 	struct list_head list;
 };
 
@@ -339,11 +341,6 @@ static inline struct orangefs_khandle *get_khandle_from_ino(struct inode *inode)
 	return &(ORANGEFS_I(inode)->refn.khandle);
 }
 
-static inline __s32 get_fsid_from_ino(struct inode *inode)
-{
-	return ORANGEFS_I(inode)->refn.fs_id;
-}
-
 static inline ino_t get_ino_from_khandle(struct inode *inode)
 {
 	struct orangefs_khandle *khandle;
@@ -439,9 +436,8 @@ struct inode *orangefs_new_inode(struct super_block *sb,
 
 int orangefs_setattr(struct dentry *dentry, struct iattr *iattr);
 
-int orangefs_getattr(struct vfsmount *mnt,
-		  struct dentry *dentry,
-		  struct kstat *kstat);
+int orangefs_getattr(const struct path *path, struct kstat *stat,
+		     u32 request_mask, unsigned int flags);
 
 int orangefs_permission(struct inode *inode, int mask);
 
@@ -500,7 +496,8 @@ int orangefs_inode_setxattr(struct inode *inode,
 			 size_t size,
 			 int flags);
 
-int orangefs_inode_getattr(struct inode *inode, int new, int bypass);
+int orangefs_inode_getattr(struct inode *inode, int new, int bypass,
+    u32 request_mask);
 
 int orangefs_inode_check_changed(struct inode *inode);
 
@@ -529,7 +526,6 @@ extern spinlock_t orangefs_htable_ops_in_progress_lock;
 extern int hash_table_size;
 
 extern const struct address_space_operations orangefs_address_operations;
-extern struct backing_dev_info orangefs_backing_dev_info;
 extern const struct inode_operations orangefs_file_inode_operations;
 extern const struct file_operations orangefs_file_operations;
 extern const struct inode_operations orangefs_symlink_inode_operations;
diff --git a/fs/orangefs/orangefs-mod.c b/fs/orangefs/orangefs-mod.c
index 4113eb0495bf..c1b5174cb5a9 100644
--- a/fs/orangefs/orangefs-mod.c
+++ b/fs/orangefs/orangefs-mod.c
@@ -80,11 +80,6 @@ static int __init orangefs_init(void)
 	int ret = -1;
 	__u32 i = 0;
 
-	ret = bdi_init(&orangefs_backing_dev_info);
-
-	if (ret)
-		return ret;
-
 	if (op_timeout_secs < 0)
 		op_timeout_secs = 0;
 
@@ -94,7 +89,7 @@ static int __init orangefs_init(void)
 	/* initialize global book keeping data structures */
 	ret = op_cache_initialize();
 	if (ret < 0)
-		goto err;
+		goto out;
 
 	ret = orangefs_inode_cache_initialize();
 	if (ret < 0)
@@ -181,9 +176,6 @@ cleanup_inode:
 cleanup_op:
 	op_cache_finalize();
 
-err:
-	bdi_destroy(&orangefs_backing_dev_info);
-
 out:
 	return ret;
 }
@@ -207,8 +199,6 @@ static void __exit orangefs_exit(void)
 
 	kfree(orangefs_htable_ops_in_progress);
 
-	bdi_destroy(&orangefs_backing_dev_info);
-
 	pr_info("orangefs: module version %s unloaded\n", ORANGEFS_VERSION);
 }
 
diff --git a/fs/orangefs/orangefs-sysfs.c b/fs/orangefs/orangefs-sysfs.c
index 084954448f18..afd2f523b283 100644
--- a/fs/orangefs/orangefs-sysfs.c
+++ b/fs/orangefs/orangefs-sysfs.c
@@ -91,6 +91,13 @@
  * Description:
  *			Readahead cache buffer count and size.
  *
+ * What:		/sys/fs/orangefs/readahead_readcnt
+ * Date:		Jan 2017
+ * Contact:		Martin Brandenburg <martin@omnibond.com>
+ * Description:
+ *			Number of buffers (in multiples of readahead_size)
+ *			which can be read ahead for a single file at once.
+ *
  * What:		/sys/fs/orangefs/acache/...
  * Date:		Jun 2015
  * Contact:		Martin Brandenburg <martin@omnibond.com>
@@ -329,7 +336,8 @@ static ssize_t sysfs_service_op_show(struct kobject *kobj,
 		if (!(orangefs_features & ORANGEFS_FEATURE_READAHEAD) &&
 		    (!strcmp(attr->attr.name, "readahead_count") ||
 		    !strcmp(attr->attr.name, "readahead_size") ||
-		    !strcmp(attr->attr.name, "readahead_count_size"))) {
+		    !strcmp(attr->attr.name, "readahead_count_size") ||
+		    !strcmp(attr->attr.name, "readahead_readcnt"))) {
 			rc = -EINVAL;
 			goto out;
 		}
@@ -360,6 +368,11 @@ static ssize_t sysfs_service_op_show(struct kobject *kobj,
 				 "readahead_count_size"))
 			new_op->upcall.req.param.op =
 				ORANGEFS_PARAM_REQUEST_OP_READAHEAD_COUNT_SIZE;
+
+		else if (!strcmp(attr->attr.name,
+				 "readahead_readcnt"))
+			new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_READAHEAD_READCNT;
 	} else if (!strcmp(kobj->name, ACACHE_KOBJ_ID)) {
 		if (!strcmp(attr->attr.name, "timeout_msecs"))
 			new_op->upcall.req.param.op =
@@ -542,7 +555,8 @@ static ssize_t sysfs_service_op_store(struct kobject *kobj,
 		if (!(orangefs_features & ORANGEFS_FEATURE_READAHEAD) &&
 		    (!strcmp(attr->attr.name, "readahead_count") ||
 		    !strcmp(attr->attr.name, "readahead_size") ||
-		    !strcmp(attr->attr.name, "readahead_count_size"))) {
+		    !strcmp(attr->attr.name, "readahead_count_size") ||
+		    !strcmp(attr->attr.name, "readahead_readcnt"))) {
 			rc = -EINVAL;
 			goto out;
 		}
@@ -609,6 +623,15 @@ static ssize_t sysfs_service_op_store(struct kobject *kobj,
 			new_op->upcall.req.param.u.value32[0] = val1;
 			new_op->upcall.req.param.u.value32[1] = val2;
 			goto value_set;
+		} else if (!strcmp(attr->attr.name,
+				   "readahead_readcnt")) {
+			if ((val >= 0)) {
+				new_op->upcall.req.param.op =
+				ORANGEFS_PARAM_REQUEST_OP_READAHEAD_READCNT;
+			} else {
+				rc = 0;
+				goto out;
+			}
 		}
 
 	} else if (!strcmp(kobj->name, ACACHE_KOBJ_ID)) {
@@ -812,6 +835,10 @@ static struct orangefs_attribute readahead_count_size_attribute =
 	__ATTR(readahead_count_size, 0664, sysfs_service_op_show,
 	       sysfs_service_op_store);
 
+static struct orangefs_attribute readahead_readcnt_attribute =
+	__ATTR(readahead_readcnt, 0664, sysfs_service_op_show,
+	       sysfs_service_op_store);
+
 static struct orangefs_attribute perf_counter_reset_attribute =
 	__ATTR(perf_counter_reset,
 	       0664,
@@ -838,6 +865,7 @@ static struct attribute *orangefs_default_attrs[] = {
 	&readahead_count_attribute.attr,
 	&readahead_size_attribute.attr,
 	&readahead_count_size_attribute.attr,
+	&readahead_readcnt_attribute.attr,
 	&perf_counter_reset_attribute.attr,
 	&perf_history_size_attribute.attr,
 	&perf_time_interval_secs_attribute.attr,
diff --git a/fs/orangefs/orangefs-utils.c b/fs/orangefs/orangefs-utils.c
index 06af81f71e10..aab6f1842963 100644
--- a/fs/orangefs/orangefs-utils.c
+++ b/fs/orangefs/orangefs-utils.c
@@ -251,7 +251,8 @@ static int orangefs_inode_is_stale(struct inode *inode, int new,
 	return 0;
 }
 
-int orangefs_inode_getattr(struct inode *inode, int new, int bypass)
+int orangefs_inode_getattr(struct inode *inode, int new, int bypass,
+    u32 request_mask)
 {
 	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
 	struct orangefs_kernel_op_s *new_op;
@@ -262,7 +263,13 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass)
 	    get_khandle_from_ino(inode));
 
 	if (!new && !bypass) {
-		if (time_before(jiffies, orangefs_inode->getattr_time))
+		/*
+		 * Must have all the attributes in the mask and be within cache
+		 * time.
+		 */
+		if ((request_mask & orangefs_inode->getattr_mask) ==
+		    request_mask &&
+		    time_before(jiffies, orangefs_inode->getattr_time))
 			return 0;
 	}
 
@@ -270,7 +277,15 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass)
 	if (!new_op)
 		return -ENOMEM;
 	new_op->upcall.req.getattr.refn = orangefs_inode->refn;
-	new_op->upcall.req.getattr.mask = ORANGEFS_ATTR_SYS_ALL_NOHINT;
+	/*
+	 * Size is the hardest attribute to get.  The incremental cost of any
+	 * other attribute is essentially zero.
+	 */
+	if (request_mask & STATX_SIZE || new)
+		new_op->upcall.req.getattr.mask = ORANGEFS_ATTR_SYS_ALL_NOHINT;
+	else
+		new_op->upcall.req.getattr.mask =
+		    ORANGEFS_ATTR_SYS_ALL_NOHINT & ~ORANGEFS_ATTR_SYS_SIZE;
 
 	ret = service_operation(new_op, __func__,
 	    get_interruptible_flag(inode));
@@ -291,32 +306,36 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass)
 	case S_IFREG:
 		inode->i_flags = orangefs_inode_flags(&new_op->
 		    downcall.resp.getattr.attributes);
-		inode_size = (loff_t)new_op->
-		    downcall.resp.getattr.attributes.size;
-		rounded_up_size =
-		    (inode_size + (4096 - (inode_size % 4096)));
-		inode->i_size = inode_size;
-		orangefs_inode->blksize =
-		    new_op->downcall.resp.getattr.attributes.blksize;
-		spin_lock(&inode->i_lock);
-		inode->i_bytes = inode_size;
-		inode->i_blocks =
-		    (unsigned long)(rounded_up_size / 512);
-		spin_unlock(&inode->i_lock);
+		if (request_mask & STATX_SIZE || new) {
+			inode_size = (loff_t)new_op->
+			    downcall.resp.getattr.attributes.size;
+			rounded_up_size =
+			    (inode_size + (4096 - (inode_size % 4096)));
+			inode->i_size = inode_size;
+			orangefs_inode->blksize =
+			    new_op->downcall.resp.getattr.attributes.blksize;
+			spin_lock(&inode->i_lock);
+			inode->i_bytes = inode_size;
+			inode->i_blocks =
+			    (unsigned long)(rounded_up_size / 512);
+			spin_unlock(&inode->i_lock);
+		}
 		break;
 	case S_IFDIR:
-		inode->i_size = PAGE_SIZE;
-		orangefs_inode->blksize = (1 << inode->i_blkbits);
-		spin_lock(&inode->i_lock);
-		inode_set_bytes(inode, inode->i_size);
-		spin_unlock(&inode->i_lock);
+		if (request_mask & STATX_SIZE || new) {
+			inode->i_size = PAGE_SIZE;
+			orangefs_inode->blksize = i_blocksize(inode);
+			spin_lock(&inode->i_lock);
+			inode_set_bytes(inode, inode->i_size);
+			spin_unlock(&inode->i_lock);
+		}
 		set_nlink(inode, 1);
 		break;
 	case S_IFLNK:
 		if (new) {
 			inode->i_size = (loff_t)strlen(new_op->
 			    downcall.resp.getattr.link_target);
-			orangefs_inode->blksize = (1 << inode->i_blkbits);
+			orangefs_inode->blksize = i_blocksize(inode);
 			ret = strscpy(orangefs_inode->link_target,
 			    new_op->downcall.resp.getattr.link_target,
 			    ORANGEFS_NAME_MAX);
@@ -349,6 +368,10 @@ int orangefs_inode_getattr(struct inode *inode, int new, int bypass)
 
 	orangefs_inode->getattr_time = jiffies +
 	    orangefs_getattr_timeout_msecs*HZ/1000;
+	if (request_mask & STATX_SIZE || new)
+		orangefs_inode->getattr_mask = STATX_BASIC_STATS;
+	else
+		orangefs_inode->getattr_mask = STATX_BASIC_STATS & ~STATX_SIZE;
 	ret = 0;
 out:
 	op_release(new_op);
@@ -500,41 +523,6 @@ int orangefs_flush_inode(struct inode *inode)
 	return ret;
 }
 
-int orangefs_unmount_sb(struct super_block *sb)
-{
-	int ret = -EINVAL;
-	struct orangefs_kernel_op_s *new_op = NULL;
-
-	gossip_debug(GOSSIP_UTILS_DEBUG,
-		     "orangefs_unmount_sb called on sb %p\n",
-		     sb);
-
-	new_op = op_alloc(ORANGEFS_VFS_OP_FS_UMOUNT);
-	if (!new_op)
-		return -ENOMEM;
-	new_op->upcall.req.fs_umount.id = ORANGEFS_SB(sb)->id;
-	new_op->upcall.req.fs_umount.fs_id = ORANGEFS_SB(sb)->fs_id;
-	strncpy(new_op->upcall.req.fs_umount.orangefs_config_server,
-		ORANGEFS_SB(sb)->devname,
-		ORANGEFS_MAX_SERVER_ADDR_LEN);
-
-	gossip_debug(GOSSIP_UTILS_DEBUG,
-		     "Attempting ORANGEFS Unmount via host %s\n",
-		     new_op->upcall.req.fs_umount.orangefs_config_server);
-
-	ret = service_operation(new_op, "orangefs_fs_umount", 0);
-
-	gossip_debug(GOSSIP_UTILS_DEBUG,
-		     "orangefs_unmount: got return value of %d\n", ret);
-	if (ret)
-		sb = ERR_PTR(ret);
-	else
-		ORANGEFS_SB(sb)->mount_pending = 1;
-
-	op_release(new_op);
-	return ret;
-}
-
 void orangefs_make_bad_inode(struct inode *inode)
 {
 	if (is_root_handle(inode)) {
diff --git a/fs/orangefs/protocol.h b/fs/orangefs/protocol.h
index 971307ad69be..48bcc1bbe415 100644
--- a/fs/orangefs/protocol.h
+++ b/fs/orangefs/protocol.h
@@ -138,13 +138,8 @@ typedef __s64 ORANGEFS_offset;
 #define ORANGEFS_G_SGID    (1 << 10)
 #define ORANGEFS_U_SUID    (1 << 11)
 
-/* definition taken from stdint.h */
-#define INT32_MAX (2147483647)
-#define ORANGEFS_ITERATE_START    (INT32_MAX - 1)
-#define ORANGEFS_ITERATE_END      (INT32_MAX - 2)
-#define ORANGEFS_ITERATE_NEXT     (INT32_MAX - 3)
-#define ORANGEFS_READDIR_START ORANGEFS_ITERATE_START
-#define ORANGEFS_READDIR_END   ORANGEFS_ITERATE_END
+#define ORANGEFS_ITERATE_START    2147483646
+#define ORANGEFS_ITERATE_END      2147483645
 #define ORANGEFS_IMMUTABLE_FL FS_IMMUTABLE_FL
 #define ORANGEFS_APPEND_FL    FS_APPEND_FL
 #define ORANGEFS_NOATIME_FL   FS_NOATIME_FL
diff --git a/fs/orangefs/super.c b/fs/orangefs/super.c
index c48859f16e7b..5a1bed6c8c6a 100644
--- a/fs/orangefs/super.c
+++ b/fs/orangefs/super.c
@@ -35,6 +35,19 @@ static const match_table_t tokens = {
 
 uint64_t orangefs_features;
 
+static int orangefs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct orangefs_sb_info_s *orangefs_sb = ORANGEFS_SB(root->d_sb);
+
+	if (root->d_sb->s_flags & MS_POSIXACL)
+		seq_puts(m, ",acl");
+	if (orangefs_sb->flags & ORANGEFS_OPT_INTR)
+		seq_puts(m, ",intr");
+	if (orangefs_sb->flags & ORANGEFS_OPT_LOCAL_LOCK)
+		seq_puts(m, ",local_lock");
+	return 0;
+}
+
 static int parse_mount_options(struct super_block *sb, char *options,
 		int silent)
 {
@@ -115,6 +128,13 @@ static struct inode *orangefs_alloc_inode(struct super_block *sb)
 	return &orangefs_inode->vfs_inode;
 }
 
+static void orangefs_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
+	kmem_cache_free(orangefs_inode_cache, orangefs_inode);
+}
+
 static void orangefs_destroy_inode(struct inode *inode)
 {
 	struct orangefs_inode_s *orangefs_inode = ORANGEFS_I(inode);
@@ -123,7 +143,7 @@ static void orangefs_destroy_inode(struct inode *inode)
 			"%s: deallocated %p destroying inode %pU\n",
 			__func__, orangefs_inode, get_khandle_from_ino(inode));
 
-	kmem_cache_free(orangefs_inode_cache, orangefs_inode);
+	call_rcu(&inode->i_rcu, orangefs_i_callback);
 }
 
 /*
@@ -256,8 +276,13 @@ int orangefs_remount(struct orangefs_sb_info_s *orangefs_sb)
 		if (!new_op)
 			return -ENOMEM;
 		new_op->upcall.req.features.features = 0;
-		ret = service_operation(new_op, "orangefs_features", 0);
-		orangefs_features = new_op->downcall.resp.features.features;
+		ret = service_operation(new_op, "orangefs_features",
+		    ORANGEFS_OP_PRIORITY | ORANGEFS_OP_NO_MUTEX);
+		if (!ret)
+			orangefs_features =
+			    new_op->downcall.resp.features.features;
+		else
+			orangefs_features = 0;
 		op_release(new_op);
 	} else {
 		orangefs_features = 0;
@@ -293,7 +318,7 @@ static const struct super_operations orangefs_s_ops = {
 	.drop_inode = generic_delete_inode,
 	.statfs = orangefs_statfs,
 	.remount_fs = orangefs_remount_fs,
-	.show_options = generic_show_options,
+	.show_options = orangefs_show_options,
 };
 
 static struct dentry *orangefs_fh_to_dentry(struct super_block *sb,
@@ -364,6 +389,25 @@ static const struct export_operations orangefs_export_ops = {
 	.fh_to_dentry = orangefs_fh_to_dentry,
 };
 
+static int orangefs_unmount(int id, __s32 fs_id, const char *devname)
+{
+	struct orangefs_kernel_op_s *op;
+	int r;
+	op = op_alloc(ORANGEFS_VFS_OP_FS_UMOUNT);
+	if (!op)
+		return -ENOMEM;
+	op->upcall.req.fs_umount.id = id;
+	op->upcall.req.fs_umount.fs_id = fs_id;
+	strncpy(op->upcall.req.fs_umount.orangefs_config_server,
+	    devname, ORANGEFS_MAX_SERVER_ADDR_LEN);
+	r = service_operation(op, "orangefs_fs_umount", 0);
+	/* Not much to do about an error here. */
+	if (r)
+		gossip_err("orangefs_unmount: service_operation %d\n", r);
+	op_release(op);
+	return r;
+}
+
 static int orangefs_fill_sb(struct super_block *sb,
 		struct orangefs_fs_mount_response *fs_mount,
 		void *data, int silent)
@@ -472,6 +516,8 @@ struct dentry *orangefs_mount(struct file_system_type *fst,
 
 	if (IS_ERR(sb)) {
 		d = ERR_CAST(sb);
+		orangefs_unmount(new_op->downcall.resp.fs_mount.id,
+		    new_op->downcall.resp.fs_mount.fs_id, devname);
 		goto free_op;
 	}
 
@@ -481,7 +527,7 @@ struct dentry *orangefs_mount(struct file_system_type *fst,
 
 	if (ret) {
 		d = ERR_PTR(ret);
-		goto free_op;
+		goto free_sb_and_op;
 	}
 
 	/*
@@ -507,6 +553,9 @@ struct dentry *orangefs_mount(struct file_system_type *fst,
 	spin_unlock(&orangefs_superblocks_lock);
 	op_release(new_op);
 
+	/* Must be removed from the list now. */
+	ORANGEFS_SB(sb)->no_list = 0;
+
 	if (orangefs_userspace_version >= 20906) {
 		new_op = op_alloc(ORANGEFS_VFS_OP_FEATURES);
 		if (!new_op)
@@ -521,6 +570,11 @@ struct dentry *orangefs_mount(struct file_system_type *fst,
 
 	return dget(sb->s_root);
 
+free_sb_and_op:
+	/* Will call orangefs_kill_sb with sb not in list. */
+	ORANGEFS_SB(sb)->no_list = 1;
+	/* ORANGEFS_VFS_OP_FS_UMOUNT is done by orangefs_kill_sb. */
+	deactivate_locked_super(sb);
 free_op:
 	gossip_err("orangefs_mount: mount request failed with %d\n", ret);
 	if (ret == -EINVAL) {
@@ -535,6 +589,7 @@ free_op:
 
 void orangefs_kill_sb(struct super_block *sb)
 {
+	int r;
 	gossip_debug(GOSSIP_SUPER_DEBUG, "orangefs_kill_sb: called\n");
 
 	/* provided sb cleanup */
@@ -544,14 +599,19 @@ void orangefs_kill_sb(struct super_block *sb)
 	 * issue the unmount to userspace to tell it to remove the
 	 * dynamic mount info it has for this superblock
 	 */
-	 orangefs_unmount_sb(sb);
-
-	/* remove the sb from our list of orangefs specific sb's */
-
-	spin_lock(&orangefs_superblocks_lock);
-	__list_del_entry(&ORANGEFS_SB(sb)->list);	/* not list_del_init */
-	ORANGEFS_SB(sb)->list.prev = NULL;
-	spin_unlock(&orangefs_superblocks_lock);
+	r = orangefs_unmount(ORANGEFS_SB(sb)->id, ORANGEFS_SB(sb)->fs_id,
+	    ORANGEFS_SB(sb)->devname);
+	if (!r)
+		ORANGEFS_SB(sb)->mount_pending = 1;
+
+	if (!ORANGEFS_SB(sb)->no_list) {
+		/* remove the sb from our list of orangefs specific sb's */
+		spin_lock(&orangefs_superblocks_lock);
+		/* not list_del_init */
+		__list_del_entry(&ORANGEFS_SB(sb)->list);
+		ORANGEFS_SB(sb)->list.prev = NULL;
+		spin_unlock(&orangefs_superblocks_lock);
+	}
 
 	/*
 	 * make sure that ORANGEFS_DEV_REMOUNT_ALL loop that might've seen us
diff --git a/fs/orangefs/upcall.h b/fs/orangefs/upcall.h
index af0b0e36d559..b8249f8fdd80 100644
--- a/fs/orangefs/upcall.h
+++ b/fs/orangefs/upcall.h
@@ -182,6 +182,7 @@ enum orangefs_param_request_op {
 	ORANGEFS_PARAM_REQUEST_OP_READAHEAD_SIZE = 26,
 	ORANGEFS_PARAM_REQUEST_OP_READAHEAD_COUNT = 27,
 	ORANGEFS_PARAM_REQUEST_OP_READAHEAD_COUNT_SIZE = 28,
+	ORANGEFS_PARAM_REQUEST_OP_READAHEAD_READCNT = 29,
 };
 
 struct orangefs_param_request_s {
diff --git a/fs/orangefs/waitqueue.c b/fs/orangefs/waitqueue.c
index abcfa3fa9992..61e2ca7fec55 100644
--- a/fs/orangefs/waitqueue.c
+++ b/fs/orangefs/waitqueue.c
@@ -124,7 +124,14 @@ retry_servicing:
 		gossip_debug(GOSSIP_WAIT_DEBUG,
 			     "%s:client core is NOT in service.\n",
 			     __func__);
-		timeout = op_timeout_secs * HZ;
+		/*
+		 * Don't wait for the userspace component to return if
+		 * the filesystem is being umounted anyway.
+		 */
+		if (op->upcall.type == ORANGEFS_VFS_OP_FS_UMOUNT)
+			timeout = 0;
+		else
+			timeout = op_timeout_secs * HZ;
 	}
 	spin_unlock(&orangefs_request_list_lock);
 
diff --git a/fs/orangefs/xattr.c b/fs/orangefs/xattr.c
index 74a81b1daaac..237c9c04dc3b 100644
--- a/fs/orangefs/xattr.c
+++ b/fs/orangefs/xattr.c
@@ -76,11 +76,8 @@ ssize_t orangefs_inode_getxattr(struct inode *inode, const char *name,
 	if (S_ISLNK(inode->i_mode))
 		return -EOPNOTSUPP;
 
-	if (strlen(name) >= ORANGEFS_MAX_XATTR_NAMELEN) {
-		gossip_err("Invalid key length (%d)\n",
-			   (int)strlen(name));
+	if (strlen(name) > ORANGEFS_MAX_XATTR_NAMELEN)
 		return -EINVAL;
-	}
 
 	fsuid = from_kuid(&init_user_ns, current_fsuid());
 	fsgid = from_kgid(&init_user_ns, current_fsgid());
@@ -172,6 +169,9 @@ static int orangefs_inode_removexattr(struct inode *inode, const char *name,
 	struct orangefs_kernel_op_s *new_op = NULL;
 	int ret = -ENOMEM;
 
+	if (strlen(name) > ORANGEFS_MAX_XATTR_NAMELEN)
+		return -EINVAL;
+
 	down_write(&orangefs_inode->xattr_sem);
 	new_op = op_alloc(ORANGEFS_VFS_OP_REMOVEXATTR);
 	if (!new_op)
@@ -231,23 +231,13 @@ int orangefs_inode_setxattr(struct inode *inode, const char *name,
 		     "%s: name %s, buffer_size %zd\n",
 		     __func__, name, size);
 
-	if (size >= ORANGEFS_MAX_XATTR_VALUELEN ||
-	    flags < 0) {
-		gossip_err("orangefs_inode_setxattr: bogus values of size(%d), flags(%d)\n",
-			   (int)size,
-			   flags);
+	if (size > ORANGEFS_MAX_XATTR_VALUELEN)
+		return -EINVAL;
+	if (strlen(name) > ORANGEFS_MAX_XATTR_NAMELEN)
 		return -EINVAL;
-	}
 
 	internal_flag = convert_to_internal_xattr_flags(flags);
 
-	if (strlen(name) >= ORANGEFS_MAX_XATTR_NAMELEN) {
-		gossip_err
-		    ("orangefs_inode_setxattr: bogus key size (%d)\n",
-		     (int)(strlen(name)));
-		return -EINVAL;
-	}
-
 	/* This is equivalent to a removexattr */
 	if (size == 0 && value == NULL) {
 		gossip_debug(GOSSIP_XATTR_DEBUG,
@@ -358,7 +348,7 @@ try_again:
 
 	returned_count = new_op->downcall.resp.listxattr.returned_count;
 	if (returned_count < 0 ||
-	    returned_count >= ORANGEFS_MAX_XATTR_LISTLEN) {
+	    returned_count > ORANGEFS_MAX_XATTR_LISTLEN) {
 		gossip_err("%s: impossible value for returned_count:%d:\n",
 		__func__,
 		returned_count);
diff --git a/fs/overlayfs/Kconfig b/fs/overlayfs/Kconfig
index 0daac5112f7a..cbfc196e5dc5 100644
--- a/fs/overlayfs/Kconfig
+++ b/fs/overlayfs/Kconfig
@@ -1,5 +1,6 @@
 config OVERLAY_FS
 	tristate "Overlay filesystem support"
+	select EXPORTFS
 	help
 	  An overlay filesystem combines two filesystems - an 'upper' filesystem
 	  and a 'lower' filesystem.  When a name exists in both filesystems, the
@@ -22,3 +23,23 @@ config OVERLAY_FS_REDIRECT_DIR
 	  Note, that redirects are not backward compatible.  That is, mounting
 	  an overlay which has redirects on a kernel that doesn't support this
 	  feature will have unexpected results.
+
+config OVERLAY_FS_INDEX
+	bool "Overlayfs: turn on inodes index feature by default"
+	depends on OVERLAY_FS
+	help
+	  If this config option is enabled then overlay filesystems will use
+	  the inodes index dir to map lower inodes to upper inodes by default.
+	  In this case it is still possible to turn off index globally with the
+	  "index=off" module option or on a filesystem instance basis with the
+	  "index=off" mount option.
+
+	  The inodes index feature prevents breaking of lower hardlinks on copy
+	  up.
+
+	  Note, that the inodes index feature is read-only backward compatible.
+	  That is, mounting an overlay which has an index dir on a kernel that
+	  doesn't support this feature read-only, will not have any negative
+	  outcomes.  However, mounting the same overlay with an old kernel
+	  read-write and then mounting it again with a new kernel, will have
+	  unexpected results.
diff --git a/fs/overlayfs/copy_up.c b/fs/overlayfs/copy_up.c
index f57043dace62..acb6f97deb97 100644
--- a/fs/overlayfs/copy_up.c
+++ b/fs/overlayfs/copy_up.c
@@ -15,11 +15,14 @@
 #include <linux/xattr.h>
 #include <linux/security.h>
 #include <linux/uaccess.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/cred.h>
 #include <linux/namei.h>
 #include <linux/fdtable.h>
 #include <linux/ratelimit.h>
+#include <linux/exportfs.h>
 #include "overlayfs.h"
+#include "ovl_entry.h"
 
 #define OVL_COPY_UP_CHUNK_SIZE (1 << 20)
 
@@ -230,91 +233,290 @@ int ovl_set_attr(struct dentry *upperdentry, struct kstat *stat)
 	return err;
 }
 
-static int ovl_copy_up_locked(struct dentry *workdir, struct dentry *upperdir,
-			      struct dentry *dentry, struct path *lowerpath,
-			      struct kstat *stat, const char *link)
+struct ovl_fh *ovl_encode_fh(struct dentry *lower, bool is_upper)
 {
-	struct inode *wdir = workdir->d_inode;
-	struct inode *udir = upperdir->d_inode;
-	struct dentry *newdentry = NULL;
-	struct dentry *upper = NULL;
+	struct ovl_fh *fh;
+	int fh_type, fh_len, dwords;
+	void *buf;
+	int buflen = MAX_HANDLE_SZ;
+	uuid_t *uuid = &lower->d_sb->s_uuid;
+
+	buf = kmalloc(buflen, GFP_TEMPORARY);
+	if (!buf)
+		return ERR_PTR(-ENOMEM);
+
+	/*
+	 * We encode a non-connectable file handle for non-dir, because we
+	 * only need to find the lower inode number and we don't want to pay
+	 * the price or reconnecting the dentry.
+	 */
+	dwords = buflen >> 2;
+	fh_type = exportfs_encode_fh(lower, buf, &dwords, 0);
+	buflen = (dwords << 2);
+
+	fh = ERR_PTR(-EIO);
+	if (WARN_ON(fh_type < 0) ||
+	    WARN_ON(buflen > MAX_HANDLE_SZ) ||
+	    WARN_ON(fh_type == FILEID_INVALID))
+		goto out;
+
+	BUILD_BUG_ON(MAX_HANDLE_SZ + offsetof(struct ovl_fh, fid) > 255);
+	fh_len = offsetof(struct ovl_fh, fid) + buflen;
+	fh = kmalloc(fh_len, GFP_KERNEL);
+	if (!fh) {
+		fh = ERR_PTR(-ENOMEM);
+		goto out;
+	}
+
+	fh->version = OVL_FH_VERSION;
+	fh->magic = OVL_FH_MAGIC;
+	fh->type = fh_type;
+	fh->flags = OVL_FH_FLAG_CPU_ENDIAN;
+	/*
+	 * When we will want to decode an overlay dentry from this handle
+	 * and all layers are on the same fs, if we get a disconncted real
+	 * dentry when we decode fid, the only way to tell if we should assign
+	 * it to upperdentry or to lowerstack is by checking this flag.
+	 */
+	if (is_upper)
+		fh->flags |= OVL_FH_FLAG_PATH_UPPER;
+	fh->len = fh_len;
+	fh->uuid = *uuid;
+	memcpy(fh->fid, buf, buflen);
+
+out:
+	kfree(buf);
+	return fh;
+}
+
+static int ovl_set_origin(struct dentry *dentry, struct dentry *lower,
+			  struct dentry *upper)
+{
+	const struct ovl_fh *fh = NULL;
 	int err;
+
+	/*
+	 * When lower layer doesn't support export operations store a 'null' fh,
+	 * so we can use the overlay.origin xattr to distignuish between a copy
+	 * up and a pure upper inode.
+	 */
+	if (ovl_can_decode_fh(lower->d_sb)) {
+		fh = ovl_encode_fh(lower, false);
+		if (IS_ERR(fh))
+			return PTR_ERR(fh);
+	}
+
+	/*
+	 * Do not fail when upper doesn't support xattrs.
+	 */
+	err = ovl_check_setxattr(dentry, upper, OVL_XATTR_ORIGIN, fh,
+				 fh ? fh->len : 0, 0);
+	kfree(fh);
+
+	return err;
+}
+
+struct ovl_copy_up_ctx {
+	struct dentry *parent;
+	struct dentry *dentry;
+	struct path lowerpath;
+	struct kstat stat;
+	struct kstat pstat;
+	const char *link;
+	struct dentry *destdir;
+	struct qstr destname;
+	struct dentry *workdir;
+	bool tmpfile;
+	bool origin;
+};
+
+static int ovl_link_up(struct ovl_copy_up_ctx *c)
+{
+	int err;
+	struct dentry *upper;
+	struct dentry *upperdir = ovl_dentry_upper(c->parent);
+	struct inode *udir = d_inode(upperdir);
+
+	/* Mark parent "impure" because it may now contain non-pure upper */
+	err = ovl_set_impure(c->parent, upperdir);
+	if (err)
+		return err;
+
+	err = ovl_set_nlink_lower(c->dentry);
+	if (err)
+		return err;
+
+	inode_lock_nested(udir, I_MUTEX_PARENT);
+	upper = lookup_one_len(c->dentry->d_name.name, upperdir,
+			       c->dentry->d_name.len);
+	err = PTR_ERR(upper);
+	if (!IS_ERR(upper)) {
+		err = ovl_do_link(ovl_dentry_upper(c->dentry), udir, upper,
+				  true);
+		dput(upper);
+
+		if (!err) {
+			/* Restore timestamps on parent (best effort) */
+			ovl_set_timestamps(upperdir, &c->pstat);
+			ovl_dentry_set_upper_alias(c->dentry);
+		}
+	}
+	inode_unlock(udir);
+	ovl_set_nlink_upper(c->dentry);
+
+	return err;
+}
+
+static int ovl_install_temp(struct ovl_copy_up_ctx *c, struct dentry *temp,
+			    struct dentry **newdentry)
+{
+	int err;
+	struct dentry *upper;
+	struct inode *udir = d_inode(c->destdir);
+
+	upper = lookup_one_len(c->destname.name, c->destdir, c->destname.len);
+	if (IS_ERR(upper))
+		return PTR_ERR(upper);
+
+	if (c->tmpfile)
+		err = ovl_do_link(temp, udir, upper, true);
+	else
+		err = ovl_do_rename(d_inode(c->workdir), temp, udir, upper, 0);
+
+	if (!err)
+		*newdentry = dget(c->tmpfile ? upper : temp);
+	dput(upper);
+
+	return err;
+}
+
+static int ovl_get_tmpfile(struct ovl_copy_up_ctx *c, struct dentry **tempp)
+{
+	int err;
+	struct dentry *temp;
 	const struct cred *old_creds = NULL;
 	struct cred *new_creds = NULL;
 	struct cattr cattr = {
 		/* Can't properly set mode on creation because of the umask */
-		.mode = stat->mode & S_IFMT,
-		.rdev = stat->rdev,
-		.link = link
+		.mode = c->stat.mode & S_IFMT,
+		.rdev = c->stat.rdev,
+		.link = c->link
 	};
 
-	newdentry = ovl_lookup_temp(workdir, dentry);
-	err = PTR_ERR(newdentry);
-	if (IS_ERR(newdentry))
-		goto out;
-
-	upper = lookup_one_len(dentry->d_name.name, upperdir,
-			       dentry->d_name.len);
-	err = PTR_ERR(upper);
-	if (IS_ERR(upper))
-		goto out1;
-
-	err = security_inode_copy_up(dentry, &new_creds);
+	err = security_inode_copy_up(c->dentry, &new_creds);
 	if (err < 0)
-		goto out2;
+		goto out;
 
 	if (new_creds)
 		old_creds = override_creds(new_creds);
 
-	err = ovl_create_real(wdir, newdentry, &cattr, NULL, true);
-
+	if (c->tmpfile) {
+		temp = ovl_do_tmpfile(c->workdir, c->stat.mode);
+		if (IS_ERR(temp))
+			goto temp_err;
+	} else {
+		temp = ovl_lookup_temp(c->workdir);
+		if (IS_ERR(temp))
+			goto temp_err;
+
+		err = ovl_create_real(d_inode(c->workdir), temp, &cattr,
+				      NULL, true);
+		if (err) {
+			dput(temp);
+			goto out;
+		}
+	}
+	err = 0;
+	*tempp = temp;
+out:
 	if (new_creds) {
 		revert_creds(old_creds);
 		put_cred(new_creds);
 	}
 
-	if (err)
-		goto out2;
+	return err;
+
+temp_err:
+	err = PTR_ERR(temp);
+	goto out;
+}
+
+static int ovl_copy_up_inode(struct ovl_copy_up_ctx *c, struct dentry *temp)
+{
+	int err;
 
-	if (S_ISREG(stat->mode)) {
+	if (S_ISREG(c->stat.mode)) {
 		struct path upperpath;
 
-		ovl_path_upper(dentry, &upperpath);
+		ovl_path_upper(c->dentry, &upperpath);
 		BUG_ON(upperpath.dentry != NULL);
-		upperpath.dentry = newdentry;
+		upperpath.dentry = temp;
 
-		err = ovl_copy_up_data(lowerpath, &upperpath, stat->size);
+		err = ovl_copy_up_data(&c->lowerpath, &upperpath, c->stat.size);
 		if (err)
-			goto out_cleanup;
+			return err;
 	}
 
-	err = ovl_copy_xattr(lowerpath->dentry, newdentry);
+	err = ovl_copy_xattr(c->lowerpath.dentry, temp);
 	if (err)
-		goto out_cleanup;
+		return err;
 
-	inode_lock(newdentry->d_inode);
-	err = ovl_set_attr(newdentry, stat);
-	inode_unlock(newdentry->d_inode);
+	inode_lock(temp->d_inode);
+	err = ovl_set_attr(temp, &c->stat);
+	inode_unlock(temp->d_inode);
+	if (err)
+		return err;
+
+	/*
+	 * Store identifier of lower inode in upper inode xattr to
+	 * allow lookup of the copy up origin inode.
+	 *
+	 * Don't set origin when we are breaking the association with a lower
+	 * hard link.
+	 */
+	if (c->origin) {
+		err = ovl_set_origin(c->dentry, c->lowerpath.dentry, temp);
+		if (err)
+			return err;
+	}
+
+	return 0;
+}
+
+static int ovl_copy_up_locked(struct ovl_copy_up_ctx *c)
+{
+	struct inode *udir = c->destdir->d_inode;
+	struct dentry *newdentry = NULL;
+	struct dentry *temp = NULL;
+	int err;
+
+	err = ovl_get_tmpfile(c, &temp);
+	if (err)
+		goto out;
+
+	err = ovl_copy_up_inode(c, temp);
 	if (err)
 		goto out_cleanup;
 
-	err = ovl_do_rename(wdir, newdentry, udir, upper, 0);
+	if (c->tmpfile) {
+		inode_lock_nested(udir, I_MUTEX_PARENT);
+		err = ovl_install_temp(c, temp, &newdentry);
+		inode_unlock(udir);
+	} else {
+		err = ovl_install_temp(c, temp, &newdentry);
+	}
 	if (err)
 		goto out_cleanup;
 
-	ovl_dentry_update(dentry, newdentry);
-	ovl_inode_update(d_inode(dentry), d_inode(newdentry));
-	newdentry = NULL;
-out2:
-	dput(upper);
-out1:
-	dput(newdentry);
+	ovl_inode_update(d_inode(c->dentry), newdentry);
 out:
+	dput(temp);
 	return err;
 
 out_cleanup:
-	ovl_cleanup(wdir, newdentry);
-	goto out2;
+	if (!c->tmpfile)
+		ovl_cleanup(d_inode(c->workdir), temp);
+	goto out;
 }
 
 /*
@@ -326,55 +528,119 @@ out_cleanup:
  * is possible that the copy up will lock the old parent.  At that point
  * the file will have already been copied up anyway.
  */
+static int ovl_do_copy_up(struct ovl_copy_up_ctx *c)
+{
+	int err;
+	struct ovl_fs *ofs = c->dentry->d_sb->s_fs_info;
+	bool indexed = false;
+
+	if (ovl_indexdir(c->dentry->d_sb) && !S_ISDIR(c->stat.mode) &&
+	    c->stat.nlink > 1)
+		indexed = true;
+
+	if (S_ISDIR(c->stat.mode) || c->stat.nlink == 1 || indexed)
+		c->origin = true;
+
+	if (indexed) {
+		c->destdir = ovl_indexdir(c->dentry->d_sb);
+		err = ovl_get_index_name(c->lowerpath.dentry, &c->destname);
+		if (err)
+			return err;
+	} else {
+		/*
+		 * Mark parent "impure" because it may now contain non-pure
+		 * upper
+		 */
+		err = ovl_set_impure(c->parent, c->destdir);
+		if (err)
+			return err;
+	}
+
+	/* Should we copyup with O_TMPFILE or with workdir? */
+	if (S_ISREG(c->stat.mode) && ofs->tmpfile) {
+		c->tmpfile = true;
+		err = ovl_copy_up_locked(c);
+	} else {
+		err = -EIO;
+		if (lock_rename(c->workdir, c->destdir) != NULL) {
+			pr_err("overlayfs: failed to lock workdir+upperdir\n");
+		} else {
+			err = ovl_copy_up_locked(c);
+			unlock_rename(c->workdir, c->destdir);
+		}
+	}
+
+	if (indexed) {
+		if (!err)
+			ovl_set_flag(OVL_INDEX, d_inode(c->dentry));
+		kfree(c->destname.name);
+	} else if (!err) {
+		struct inode *udir = d_inode(c->destdir);
+
+		/* Restore timestamps on parent (best effort) */
+		inode_lock(udir);
+		ovl_set_timestamps(c->destdir, &c->pstat);
+		inode_unlock(udir);
+
+		ovl_dentry_set_upper_alias(c->dentry);
+	}
+
+	return err;
+}
+
 static int ovl_copy_up_one(struct dentry *parent, struct dentry *dentry,
-			   struct path *lowerpath, struct kstat *stat)
+			   int flags)
 {
-	DEFINE_DELAYED_CALL(done);
-	struct dentry *workdir = ovl_workdir(dentry);
 	int err;
-	struct kstat pstat;
+	DEFINE_DELAYED_CALL(done);
 	struct path parentpath;
-	struct dentry *lowerdentry = lowerpath->dentry;
-	struct dentry *upperdir;
-	const char *link = NULL;
+	struct ovl_copy_up_ctx ctx = {
+		.parent = parent,
+		.dentry = dentry,
+		.workdir = ovl_workdir(dentry),
+	};
 
-	if (WARN_ON(!workdir))
+	if (WARN_ON(!ctx.workdir))
 		return -EROFS;
 
-	ovl_do_check_copy_up(lowerdentry);
+	ovl_path_lower(dentry, &ctx.lowerpath);
+	err = vfs_getattr(&ctx.lowerpath, &ctx.stat,
+			  STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
+	if (err)
+		return err;
 
 	ovl_path_upper(parent, &parentpath);
-	upperdir = parentpath.dentry;
+	ctx.destdir = parentpath.dentry;
+	ctx.destname = dentry->d_name;
 
-	err = vfs_getattr(&parentpath, &pstat);
+	err = vfs_getattr(&parentpath, &ctx.pstat,
+			  STATX_ATIME | STATX_MTIME, AT_STATX_SYNC_AS_STAT);
 	if (err)
 		return err;
 
-	if (S_ISLNK(stat->mode)) {
-		link = vfs_get_link(lowerdentry, &done);
-		if (IS_ERR(link))
-			return PTR_ERR(link);
-	}
+	/* maybe truncate regular file. this has no effect on dirs */
+	if (flags & O_TRUNC)
+		ctx.stat.size = 0;
 
-	err = -EIO;
-	if (lock_rename(workdir, upperdir) != NULL) {
-		pr_err("overlayfs: failed to lock workdir+upperdir\n");
-		goto out_unlock;
+	if (S_ISLNK(ctx.stat.mode)) {
+		ctx.link = vfs_get_link(ctx.lowerpath.dentry, &done);
+		if (IS_ERR(ctx.link))
+			return PTR_ERR(ctx.link);
 	}
-	if (ovl_dentry_upper(dentry)) {
-		/* Raced with another copy-up?  Nothing to do, then... */
-		err = 0;
-		goto out_unlock;
+	ovl_do_check_copy_up(ctx.lowerpath.dentry);
+
+	err = ovl_copy_up_start(dentry);
+	/* err < 0: interrupted, err > 0: raced with another copy-up */
+	if (unlikely(err)) {
+		if (err > 0)
+			err = 0;
+	} else {
+		if (!ovl_dentry_upper(dentry))
+			err = ovl_do_copy_up(&ctx);
+		if (!err && !ovl_dentry_has_upper_alias(dentry))
+			err = ovl_link_up(&ctx);
+		ovl_copy_up_end(dentry);
 	}
-
-	err = ovl_copy_up_locked(workdir, upperdir, dentry, lowerpath,
-				 stat, link);
-	if (!err) {
-		/* Restore timestamps on parent (best effort) */
-		ovl_set_timestamps(upperdir, &pstat);
-	}
-out_unlock:
-	unlock_rename(workdir, upperdir);
 	do_delayed_call(&done);
 
 	return err;
@@ -388,11 +654,22 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags)
 	while (!err) {
 		struct dentry *next;
 		struct dentry *parent;
-		struct path lowerpath;
-		struct kstat stat;
-		enum ovl_path_type type = ovl_path_type(dentry);
 
-		if (OVL_TYPE_UPPER(type))
+		/*
+		 * Check if copy-up has happened as well as for upper alias (in
+		 * case of hard links) is there.
+		 *
+		 * Both checks are lockless:
+		 *  - false negatives: will recheck under oi->lock
+		 *  - false positives:
+		 *    + ovl_dentry_upper() uses memory barriers to ensure the
+		 *      upper dentry is up-to-date
+		 *    + ovl_dentry_has_upper_alias() relies on locking of
+		 *      upper parent i_rwsem to prevent reordering copy-up
+		 *      with rename.
+		 */
+		if (ovl_dentry_upper(dentry) &&
+		    ovl_dentry_has_upper_alias(dentry))
 			break;
 
 		next = dget(dentry);
@@ -400,21 +677,14 @@ int ovl_copy_up_flags(struct dentry *dentry, int flags)
 		for (;;) {
 			parent = dget_parent(next);
 
-			type = ovl_path_type(parent);
-			if (OVL_TYPE_UPPER(type))
+			if (ovl_dentry_upper(parent))
 				break;
 
 			dput(next);
 			next = parent;
 		}
 
-		ovl_path_lower(next, &lowerpath);
-		err = vfs_getattr(&lowerpath, &stat);
-		/* maybe truncate regular file. this has no effect on dirs */
-		if (flags & O_TRUNC)
-			stat.size = 0;
-		if (!err)
-			err = ovl_copy_up_one(parent, next, &lowerpath, &stat);
+		err = ovl_copy_up_one(parent, next, flags);
 
 		dput(parent);
 		dput(next);
diff --git a/fs/overlayfs/dir.c b/fs/overlayfs/dir.c
index 16e06dd89457..48b70e6490f3 100644
--- a/fs/overlayfs/dir.c
+++ b/fs/overlayfs/dir.c
@@ -24,7 +24,7 @@ module_param_named(redirect_max, ovl_redirect_max, ushort, 0644);
 MODULE_PARM_DESC(ovl_redirect_max,
 		 "Maximum length of absolute redirect xattr value");
 
-void ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
+int ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
 {
 	int err;
 
@@ -39,9 +39,11 @@ void ovl_cleanup(struct inode *wdir, struct dentry *wdentry)
 		pr_err("overlayfs: cleanup of '%pd2' failed (%i)\n",
 		       wdentry, err);
 	}
+
+	return err;
 }
 
-struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry)
+struct dentry *ovl_lookup_temp(struct dentry *workdir)
 {
 	struct dentry *temp;
 	char name[20];
@@ -68,7 +70,7 @@ static struct dentry *ovl_whiteout(struct dentry *workdir,
 	struct dentry *whiteout;
 	struct inode *wdir = workdir->d_inode;
 
-	whiteout = ovl_lookup_temp(workdir, dentry);
+	whiteout = ovl_lookup_temp(workdir);
 	if (IS_ERR(whiteout))
 		return whiteout;
 
@@ -127,44 +129,26 @@ int ovl_create_real(struct inode *dir, struct dentry *newdentry,
 	return err;
 }
 
-static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry)
+static int ovl_set_opaque_xerr(struct dentry *dentry, struct dentry *upper,
+			       int xerr)
 {
 	int err;
 
-	err = ovl_do_setxattr(upperdentry, OVL_XATTR_OPAQUE, "y", 1, 0);
+	err = ovl_check_setxattr(dentry, upper, OVL_XATTR_OPAQUE, "y", 1, xerr);
 	if (!err)
 		ovl_dentry_set_opaque(dentry);
 
 	return err;
 }
 
-static int ovl_dir_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			 struct kstat *stat)
+static int ovl_set_opaque(struct dentry *dentry, struct dentry *upperdentry)
 {
-	int err;
-	enum ovl_path_type type;
-	struct path realpath;
-	const struct cred *old_cred;
-
-	type = ovl_path_real(dentry, &realpath);
-	old_cred = ovl_override_creds(dentry->d_sb);
-	err = vfs_getattr(&realpath, stat);
-	revert_creds(old_cred);
-	if (err)
-		return err;
-
-	stat->dev = dentry->d_sb->s_dev;
-	stat->ino = dentry->d_inode->i_ino;
-
 	/*
-	 * It's probably not worth it to count subdirs to get the
-	 * correct link count.  nlink=1 seems to pacify 'find' and
-	 * other utilities.
+	 * Fail with -EIO when trying to create opaque dir and upper doesn't
+	 * support xattrs. ovl_rename() calls ovl_set_opaque_xerr(-EXDEV) to
+	 * return a specific error for noxattr case.
 	 */
-	if (OVL_TYPE_MERGE(type))
-		stat->nlink = 1;
-
-	return 0;
+	return ovl_set_opaque_xerr(dentry, upperdentry, -EIO);
 }
 
 /* Common operations required to be done after creation of file on upper */
@@ -172,15 +156,19 @@ static void ovl_instantiate(struct dentry *dentry, struct inode *inode,
 			    struct dentry *newdentry, bool hardlink)
 {
 	ovl_dentry_version_inc(dentry->d_parent);
-	ovl_dentry_update(dentry, newdentry);
+	ovl_dentry_set_upper_alias(dentry);
 	if (!hardlink) {
-		ovl_inode_update(inode, d_inode(newdentry));
+		ovl_inode_update(inode, newdentry);
 		ovl_copyattr(newdentry->d_inode, inode);
 	} else {
-		WARN_ON(ovl_inode_real(inode, NULL) != d_inode(newdentry));
+		WARN_ON(ovl_inode_real(inode) != d_inode(newdentry));
+		dput(newdentry);
 		inc_nlink(inode);
 	}
 	d_instantiate(dentry, inode);
+	/* Force lookup of new upper hardlink to find its lower */
+	if (hardlink)
+		d_drop(dentry);
 }
 
 static bool ovl_type_merge(struct dentry *dentry)
@@ -188,6 +176,11 @@ static bool ovl_type_merge(struct dentry *dentry)
 	return OVL_TYPE_MERGE(ovl_path_type(dentry));
 }
 
+static bool ovl_type_origin(struct dentry *dentry)
+{
+	return OVL_TYPE_ORIGIN(ovl_path_type(dentry));
+}
+
 static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
 			    struct cattr *attr, struct dentry *hardlink)
 {
@@ -209,7 +202,7 @@ static int ovl_create_upper(struct dentry *dentry, struct inode *inode,
 	if (err)
 		goto out_dput;
 
-	if (ovl_type_merge(dentry->d_parent)) {
+	if (ovl_type_merge(dentry->d_parent) && d_is_dir(newdentry)) {
 		/* Setting opaque here is just an optimization, allow to fail */
 		ovl_set_opaque(dentry, newdentry);
 	}
@@ -264,7 +257,8 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry,
 		goto out;
 
 	ovl_path_upper(dentry, &upperpath);
-	err = vfs_getattr(&upperpath, &stat);
+	err = vfs_getattr(&upperpath, &stat,
+			  STATX_BASIC_STATS, AT_STATX_SYNC_AS_STAT);
 	if (err)
 		goto out_unlock;
 
@@ -275,7 +269,7 @@ static struct dentry *ovl_clear_empty(struct dentry *dentry,
 	if (upper->d_parent->d_inode != udir)
 		goto out_unlock;
 
-	opaquedir = ovl_lookup_temp(workdir, dentry);
+	opaquedir = ovl_lookup_temp(workdir);
 	err = PTR_ERR(opaquedir);
 	if (IS_ERR(opaquedir))
 		goto out_unlock;
@@ -407,7 +401,7 @@ static int ovl_create_over_whiteout(struct dentry *dentry, struct inode *inode,
 	if (err)
 		goto out;
 
-	newdentry = ovl_lookup_temp(workdir, dentry);
+	newdentry = ovl_lookup_temp(workdir);
 	err = PTR_ERR(newdentry);
 	if (IS_ERR(newdentry))
 		goto out_unlock;
@@ -487,17 +481,30 @@ out_cleanup:
 }
 
 static int ovl_create_or_link(struct dentry *dentry, struct inode *inode,
-			      struct cattr *attr, struct dentry *hardlink)
+			      struct cattr *attr, struct dentry *hardlink,
+			      bool origin)
 {
 	int err;
 	const struct cred *old_cred;
 	struct cred *override_cred;
+	struct dentry *parent = dentry->d_parent;
 
-	err = ovl_copy_up(dentry->d_parent);
+	err = ovl_copy_up(parent);
 	if (err)
 		return err;
 
 	old_cred = ovl_override_creds(dentry->d_sb);
+
+	/*
+	 * When linking a file with copy up origin into a new parent, mark the
+	 * new parent dir "impure".
+	 */
+	if (origin) {
+		err = ovl_set_impure(parent, ovl_dentry_upper(parent));
+		if (err)
+			goto out_revert_creds;
+	}
+
 	err = -ENOMEM;
 	override_cred = prepare_creds();
 	if (override_cred) {
@@ -556,7 +563,7 @@ static int ovl_create_object(struct dentry *dentry, int mode, dev_t rdev,
 	inode_init_owner(inode, dentry->d_parent->d_inode, mode);
 	attr.mode = inode->i_mode;
 
-	err = ovl_create_or_link(dentry, inode, &attr, NULL);
+	err = ovl_create_or_link(dentry, inode, &attr, NULL, false);
 	if (err)
 		iput(inode);
 
@@ -597,6 +604,7 @@ static int ovl_link(struct dentry *old, struct inode *newdir,
 		    struct dentry *new)
 {
 	int err;
+	bool locked = false;
 	struct inode *inode;
 
 	err = ovl_want_write(old);
@@ -607,19 +615,30 @@ static int ovl_link(struct dentry *old, struct inode *newdir,
 	if (err)
 		goto out_drop_write;
 
+	err = ovl_nlink_start(old, &locked);
+	if (err)
+		goto out_drop_write;
+
 	inode = d_inode(old);
 	ihold(inode);
 
-	err = ovl_create_or_link(new, inode, NULL, ovl_dentry_upper(old));
+	err = ovl_create_or_link(new, inode, NULL, ovl_dentry_upper(old),
+				 ovl_type_origin(old));
 	if (err)
 		iput(inode);
 
+	ovl_nlink_end(old, locked);
 out_drop_write:
 	ovl_drop_write(old);
 out:
 	return err;
 }
 
+static bool ovl_matches_upper(struct dentry *dentry, struct dentry *upper)
+{
+	return d_inode(ovl_dentry_upper(dentry)) == d_inode(upper);
+}
+
 static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
 {
 	struct dentry *workdir = ovl_workdir(dentry);
@@ -655,7 +674,7 @@ static int ovl_remove_and_whiteout(struct dentry *dentry, bool is_dir)
 	err = -ESTALE;
 	if ((opaquedir && upper != opaquedir) ||
 	    (!opaquedir && ovl_dentry_upper(dentry) &&
-	     upper != ovl_dentry_upper(dentry))) {
+	     !ovl_matches_upper(dentry, upper))) {
 		goto out_dput_upper;
 	}
 
@@ -716,7 +735,7 @@ static int ovl_remove_upper(struct dentry *dentry, bool is_dir)
 
 	err = -ESTALE;
 	if ((opaquedir && upper != opaquedir) ||
-	    (!opaquedir && upper != ovl_dentry_upper(dentry)))
+	    (!opaquedir && !ovl_matches_upper(dentry, upper)))
 		goto out_dput_upper;
 
 	if (is_dir)
@@ -744,8 +763,8 @@ out:
 
 static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 {
-	enum ovl_path_type type;
 	int err;
+	bool locked = false;
 	const struct cred *old_cred;
 
 	err = ovl_want_write(dentry);
@@ -756,7 +775,9 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 	if (err)
 		goto out_drop_write;
 
-	type = ovl_path_type(dentry);
+	err = ovl_nlink_start(dentry, &locked);
+	if (err)
+		goto out_drop_write;
 
 	old_cred = ovl_override_creds(dentry->d_sb);
 	if (!ovl_lower_positive(dentry))
@@ -770,6 +791,7 @@ static int ovl_do_remove(struct dentry *dentry, bool is_dir)
 		else
 			drop_nlink(dentry->d_inode);
 	}
+	ovl_nlink_end(dentry, locked);
 out_drop_write:
 	ovl_drop_write(dentry);
 out:
@@ -871,18 +893,16 @@ static int ovl_set_redirect(struct dentry *dentry, bool samedir)
 	if (IS_ERR(redirect))
 		return PTR_ERR(redirect);
 
-	err = ovl_do_setxattr(ovl_dentry_upper(dentry), OVL_XATTR_REDIRECT,
-			      redirect, strlen(redirect), 0);
+	err = ovl_check_setxattr(dentry, ovl_dentry_upper(dentry),
+				 OVL_XATTR_REDIRECT,
+				 redirect, strlen(redirect), -EXDEV);
 	if (!err) {
 		spin_lock(&dentry->d_lock);
 		ovl_dentry_set_redirect(dentry, redirect);
 		spin_unlock(&dentry->d_lock);
 	} else {
 		kfree(redirect);
-		if (err == -EOPNOTSUPP)
-			ovl_clear_redirect_dir(dentry->d_sb);
-		else
-			pr_warn_ratelimited("overlay: failed to set redirect (%i)\n", err);
+		pr_warn_ratelimited("overlay: failed to set redirect (%i)\n", err);
 		/* Fall back to userspace copy-up */
 		err = -EXDEV;
 	}
@@ -894,6 +914,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 		      unsigned int flags)
 {
 	int err;
+	bool locked = false;
 	struct dentry *old_upperdir;
 	struct dentry *new_upperdir;
 	struct dentry *olddentry;
@@ -937,6 +958,10 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 		err = ovl_copy_up(new);
 		if (err)
 			goto out_drop_write;
+	} else {
+		err = ovl_nlink_start(new, &locked);
+		if (err)
+			goto out_drop_write;
 	}
 
 	old_cred = ovl_override_creds(old->d_sb);
@@ -968,6 +993,25 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 	old_upperdir = ovl_dentry_upper(old->d_parent);
 	new_upperdir = ovl_dentry_upper(new->d_parent);
 
+	if (!samedir) {
+		/*
+		 * When moving a merge dir or non-dir with copy up origin into
+		 * a new parent, we are marking the new parent dir "impure".
+		 * When ovl_iterate() iterates an "impure" upper dir, it will
+		 * lookup the origin inodes of the entries to fill d_ino.
+		 */
+		if (ovl_type_origin(old)) {
+			err = ovl_set_impure(new->d_parent, new_upperdir);
+			if (err)
+				goto out_revert_creds;
+		}
+		if (!overwrite && ovl_type_origin(new)) {
+			err = ovl_set_impure(old->d_parent, old_upperdir);
+			if (err)
+				goto out_revert_creds;
+		}
+	}
+
 	trap = lock_rename(new_upperdir, old_upperdir);
 
 	olddentry = lookup_one_len(old->d_name.name, old_upperdir,
@@ -977,7 +1021,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 		goto out_unlock;
 
 	err = -ESTALE;
-	if (olddentry != ovl_dentry_upper(old))
+	if (!ovl_matches_upper(old, olddentry))
 		goto out_dput_old;
 
 	newdentry = lookup_one_len(new->d_name.name, new_upperdir,
@@ -990,12 +1034,12 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 	new_opaque = ovl_dentry_is_opaque(new);
 
 	err = -ESTALE;
-	if (ovl_dentry_upper(new)) {
+	if (d_inode(new) && ovl_dentry_upper(new)) {
 		if (opaquedir) {
 			if (newdentry != opaquedir)
 				goto out_dput;
 		} else {
-			if (newdentry != ovl_dentry_upper(new))
+			if (!ovl_matches_upper(new, newdentry))
 				goto out_dput;
 		}
 	} else {
@@ -1017,7 +1061,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 		if (ovl_type_merge_or_lower(old))
 			err = ovl_set_redirect(old, samedir);
 		else if (!old_opaque && ovl_type_merge(new->d_parent))
-			err = ovl_set_opaque(old, olddentry);
+			err = ovl_set_opaque_xerr(old, olddentry, -EXDEV);
 		if (err)
 			goto out_dput;
 	}
@@ -1025,7 +1069,7 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 		if (ovl_type_merge_or_lower(new))
 			err = ovl_set_redirect(new, samedir);
 		else if (!new_opaque && ovl_type_merge(old->d_parent))
-			err = ovl_set_opaque(new, newdentry);
+			err = ovl_set_opaque_xerr(new, newdentry, -EXDEV);
 		if (err)
 			goto out_dput;
 	}
@@ -1038,6 +1082,13 @@ static int ovl_rename(struct inode *olddir, struct dentry *old,
 	if (cleanup_whiteout)
 		ovl_cleanup(old_upperdir->d_inode, newdentry);
 
+	if (overwrite && d_inode(new)) {
+		if (new_is_dir)
+			clear_nlink(d_inode(new));
+		else
+			drop_nlink(d_inode(new));
+	}
+
 	ovl_dentry_version_inc(old->d_parent);
 	ovl_dentry_version_inc(new->d_parent);
 
@@ -1049,6 +1100,7 @@ out_unlock:
 	unlock_rename(new_upperdir, old_upperdir);
 out_revert_creds:
 	revert_creds(old_cred);
+	ovl_nlink_end(new, locked);
 out_drop_write:
 	ovl_drop_write(old);
 out:
@@ -1068,7 +1120,7 @@ const struct inode_operations ovl_dir_inode_operations = {
 	.create		= ovl_create,
 	.mknod		= ovl_mknod,
 	.permission	= ovl_permission,
-	.getattr	= ovl_dir_getattr,
+	.getattr	= ovl_getattr,
 	.listxattr	= ovl_listxattr,
 	.get_acl	= ovl_get_acl,
 	.update_time	= ovl_update_time,
diff --git a/fs/overlayfs/inode.c b/fs/overlayfs/inode.c
index 08643ac44a02..5bc71642b226 100644
--- a/fs/overlayfs/inode.c
+++ b/fs/overlayfs/inode.c
@@ -9,8 +9,10 @@
 
 #include <linux/fs.h>
 #include <linux/slab.h>
+#include <linux/cred.h>
 #include <linux/xattr.h>
 #include <linux/posix_acl.h>
+#include <linux/ratelimit.h>
 #include "overlayfs.h"
 
 int ovl_setattr(struct dentry *dentry, struct iattr *attr)
@@ -56,24 +58,98 @@ out:
 	return err;
 }
 
-static int ovl_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			 struct kstat *stat)
+int ovl_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int flags)
 {
+	struct dentry *dentry = path->dentry;
+	enum ovl_path_type type;
 	struct path realpath;
 	const struct cred *old_cred;
+	bool is_dir = S_ISDIR(dentry->d_inode->i_mode);
 	int err;
 
-	ovl_path_real(dentry, &realpath);
+	type = ovl_path_real(dentry, &realpath);
 	old_cred = ovl_override_creds(dentry->d_sb);
-	err = vfs_getattr(&realpath, stat);
+	err = vfs_getattr(&realpath, stat, request_mask, flags);
+	if (err)
+		goto out;
+
+	/*
+	 * When all layers are on the same fs, all real inode number are
+	 * unique, so we use the overlay st_dev, which is friendly to du -x.
+	 *
+	 * We also use st_ino of the copy up origin, if we know it.
+	 * This guaranties constant st_dev/st_ino across copy up.
+	 *
+	 * If filesystem supports NFS export ops, this also guaranties
+	 * persistent st_ino across mount cycle.
+	 */
+	if (ovl_same_sb(dentry->d_sb)) {
+		if (OVL_TYPE_ORIGIN(type)) {
+			struct kstat lowerstat;
+			u32 lowermask = STATX_INO | (!is_dir ? STATX_NLINK : 0);
+
+			ovl_path_lower(dentry, &realpath);
+			err = vfs_getattr(&realpath, &lowerstat,
+					  lowermask, flags);
+			if (err)
+				goto out;
+
+			WARN_ON_ONCE(stat->dev != lowerstat.dev);
+			/*
+			 * Lower hardlinks may be broken on copy up to different
+			 * upper files, so we cannot use the lower origin st_ino
+			 * for those different files, even for the same fs case.
+			 * With inodes index enabled, it is safe to use st_ino
+			 * of an indexed hardlinked origin. The index validates
+			 * that the upper hardlink is not broken.
+			 */
+			if (is_dir || lowerstat.nlink == 1 ||
+			    ovl_test_flag(OVL_INDEX, d_inode(dentry)))
+				stat->ino = lowerstat.ino;
+		}
+		stat->dev = dentry->d_sb->s_dev;
+	} else if (is_dir) {
+		/*
+		 * If not all layers are on the same fs the pair {real st_ino;
+		 * overlay st_dev} is not unique, so use the non persistent
+		 * overlay st_ino.
+		 *
+		 * Always use the overlay st_dev for directories, so 'find
+		 * -xdev' will scan the entire overlay mount and won't cross the
+		 * overlay mount boundaries.
+		 */
+		stat->dev = dentry->d_sb->s_dev;
+		stat->ino = dentry->d_inode->i_ino;
+	}
+
+	/*
+	 * It's probably not worth it to count subdirs to get the
+	 * correct link count.  nlink=1 seems to pacify 'find' and
+	 * other utilities.
+	 */
+	if (is_dir && OVL_TYPE_MERGE(type))
+		stat->nlink = 1;
+
+	/*
+	 * Return the overlay inode nlinks for indexed upper inodes.
+	 * Overlay inode nlink counts the union of the upper hardlinks
+	 * and non-covered lower hardlinks. It does not include the upper
+	 * index hardlink.
+	 */
+	if (!is_dir && ovl_test_flag(OVL_INDEX, d_inode(dentry)))
+		stat->nlink = dentry->d_inode->i_nlink;
+
+out:
 	revert_creds(old_cred);
+
 	return err;
 }
 
 int ovl_permission(struct inode *inode, int mask)
 {
-	bool is_upper;
-	struct inode *realinode = ovl_inode_real(inode, &is_upper);
+	struct inode *upperinode = ovl_inode_upper(inode);
+	struct inode *realinode = upperinode ?: ovl_inode_lower(inode);
 	const struct cred *old_cred;
 	int err;
 
@@ -92,7 +168,8 @@ int ovl_permission(struct inode *inode, int mask)
 		return err;
 
 	old_cred = ovl_override_creds(inode->i_sb);
-	if (!is_upper && !special_file(realinode->i_mode) && mask & MAY_WRITE) {
+	if (!upperinode &&
+	    !special_file(realinode->i_mode) && mask & MAY_WRITE) {
 		mask &= ~(MAY_WRITE | MAY_APPEND);
 		/* Make sure mounter can read file for copy up later */
 		mask |= MAY_READ;
@@ -125,37 +202,38 @@ bool ovl_is_private_xattr(const char *name)
 		       sizeof(OVL_XATTR_PREFIX) - 1) == 0;
 }
 
-int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value,
-		  size_t size, int flags)
+int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
+		  const void *value, size_t size, int flags)
 {
 	int err;
-	struct path realpath;
-	enum ovl_path_type type = ovl_path_real(dentry, &realpath);
+	struct dentry *upperdentry = ovl_i_dentry_upper(inode);
+	struct dentry *realdentry = upperdentry ?: ovl_dentry_lower(dentry);
 	const struct cred *old_cred;
 
 	err = ovl_want_write(dentry);
 	if (err)
 		goto out;
 
-	if (!value && !OVL_TYPE_UPPER(type)) {
-		err = vfs_getxattr(realpath.dentry, name, NULL, 0);
+	if (!value && !upperdentry) {
+		err = vfs_getxattr(realdentry, name, NULL, 0);
 		if (err < 0)
 			goto out_drop_write;
 	}
 
-	err = ovl_copy_up(dentry);
-	if (err)
-		goto out_drop_write;
+	if (!upperdentry) {
+		err = ovl_copy_up(dentry);
+		if (err)
+			goto out_drop_write;
 
-	if (!OVL_TYPE_UPPER(type))
-		ovl_path_upper(dentry, &realpath);
+		realdentry = ovl_dentry_upper(dentry);
+	}
 
 	old_cred = ovl_override_creds(dentry->d_sb);
 	if (value)
-		err = vfs_setxattr(realpath.dentry, name, value, size, flags);
+		err = vfs_setxattr(realdentry, name, value, size, flags);
 	else {
 		WARN_ON(flags != XATTR_REPLACE);
-		err = vfs_removexattr(realpath.dentry, name);
+		err = vfs_removexattr(realdentry, name);
 	}
 	revert_creds(old_cred);
 
@@ -165,12 +243,13 @@ out:
 	return err;
 }
 
-int ovl_xattr_get(struct dentry *dentry, const char *name,
+int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
 		  void *value, size_t size)
 {
-	struct dentry *realdentry = ovl_dentry_real(dentry);
 	ssize_t res;
 	const struct cred *old_cred;
+	struct dentry *realdentry =
+		ovl_i_dentry_upper(inode) ?: ovl_dentry_lower(dentry);
 
 	old_cred = ovl_override_creds(dentry->d_sb);
 	res = vfs_getxattr(realdentry, name, value, size);
@@ -178,6 +257,16 @@ int ovl_xattr_get(struct dentry *dentry, const char *name,
 	return res;
 }
 
+static bool ovl_can_list(const char *s)
+{
+	/* List all non-trusted xatts */
+	if (strncmp(s, XATTR_TRUSTED_PREFIX, XATTR_TRUSTED_PREFIX_LEN) != 0)
+		return true;
+
+	/* Never list trusted.overlay, list other trusted for superuser only */
+	return !ovl_is_private_xattr(s) && capable(CAP_SYS_ADMIN);
+}
+
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 {
 	struct dentry *realdentry = ovl_dentry_real(dentry);
@@ -201,7 +290,7 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 			return -EIO;
 
 		len -= slen;
-		if (ovl_is_private_xattr(s)) {
+		if (!ovl_can_list(s)) {
 			res -= slen;
 			memmove(s, s + slen, len);
 		} else {
@@ -214,7 +303,7 @@ ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size)
 
 struct posix_acl *ovl_get_acl(struct inode *inode, int type)
 {
-	struct inode *realinode = ovl_inode_real(inode, NULL);
+	struct inode *realinode = ovl_inode_real(inode);
 	const struct cred *old_cred;
 	struct posix_acl *acl;
 
@@ -228,13 +317,13 @@ struct posix_acl *ovl_get_acl(struct inode *inode, int type)
 	return acl;
 }
 
-static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type,
-				  struct dentry *realdentry)
+static bool ovl_open_need_copy_up(struct dentry *dentry, int flags)
 {
-	if (OVL_TYPE_UPPER(type))
+	if (ovl_dentry_upper(dentry) &&
+	    ovl_dentry_has_upper_alias(dentry))
 		return false;
 
-	if (special_file(realdentry->d_inode->i_mode))
+	if (special_file(d_inode(dentry)->i_mode))
 		return false;
 
 	if (!(OPEN_FMODE(flags) & FMODE_WRITE) && !(flags & O_TRUNC))
@@ -246,11 +335,8 @@ static bool ovl_open_need_copy_up(int flags, enum ovl_path_type type,
 int ovl_open_maybe_copy_up(struct dentry *dentry, unsigned int file_flags)
 {
 	int err = 0;
-	struct path realpath;
-	enum ovl_path_type type;
 
-	type = ovl_path_real(dentry, &realpath);
-	if (ovl_open_need_copy_up(file_flags, type, realpath.dentry)) {
+	if (ovl_open_need_copy_up(dentry, file_flags)) {
 		err = ovl_want_write(dentry);
 		if (!err) {
 			err = ovl_copy_up_flags(dentry, file_flags);
@@ -301,6 +387,41 @@ static const struct inode_operations ovl_symlink_inode_operations = {
 	.update_time	= ovl_update_time,
 };
 
+/*
+ * It is possible to stack overlayfs instance on top of another
+ * overlayfs instance as lower layer. We need to annonate the
+ * stackable i_mutex locks according to stack level of the super
+ * block instance. An overlayfs instance can never be in stack
+ * depth 0 (there is always a real fs below it).  An overlayfs
+ * inode lock will use the lockdep annotaion ovl_i_mutex_key[depth].
+ *
+ * For example, here is a snip from /proc/lockdep_chains after
+ * dir_iterate of nested overlayfs:
+ *
+ * [...] &ovl_i_mutex_dir_key[depth]   (stack_depth=2)
+ * [...] &ovl_i_mutex_dir_key[depth]#2 (stack_depth=1)
+ * [...] &type->i_mutex_dir_key        (stack_depth=0)
+ */
+#define OVL_MAX_NESTING FILESYSTEM_MAX_STACK_DEPTH
+
+static inline void ovl_lockdep_annotate_inode_mutex_key(struct inode *inode)
+{
+#ifdef CONFIG_LOCKDEP
+	static struct lock_class_key ovl_i_mutex_key[OVL_MAX_NESTING];
+	static struct lock_class_key ovl_i_mutex_dir_key[OVL_MAX_NESTING];
+
+	int depth = inode->i_sb->s_stack_depth - 1;
+
+	if (WARN_ON_ONCE(depth < 0 || depth >= OVL_MAX_NESTING))
+		depth = 0;
+
+	if (S_ISDIR(inode->i_mode))
+		lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_dir_key[depth]);
+	else
+		lockdep_set_class(&inode->i_rwsem, &ovl_i_mutex_key[depth]);
+#endif
+}
+
 static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev)
 {
 	inode->i_ino = get_next_ino();
@@ -310,6 +431,8 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev)
 	inode->i_acl = inode->i_default_acl = ACL_DONT_CACHE;
 #endif
 
+	ovl_lockdep_annotate_inode_mutex_key(inode);
+
 	switch (mode & S_IFMT) {
 	case S_IFREG:
 		inode->i_op = &ovl_file_inode_operations;
@@ -331,6 +454,103 @@ static void ovl_fill_inode(struct inode *inode, umode_t mode, dev_t rdev)
 	}
 }
 
+/*
+ * With inodes index enabled, an overlay inode nlink counts the union of upper
+ * hardlinks and non-covered lower hardlinks. During the lifetime of a non-pure
+ * upper inode, the following nlink modifying operations can happen:
+ *
+ * 1. Lower hardlink copy up
+ * 2. Upper hardlink created, unlinked or renamed over
+ * 3. Lower hardlink whiteout or renamed over
+ *
+ * For the first, copy up case, the union nlink does not change, whether the
+ * operation succeeds or fails, but the upper inode nlink may change.
+ * Therefore, before copy up, we store the union nlink value relative to the
+ * lower inode nlink in the index inode xattr trusted.overlay.nlink.
+ *
+ * For the second, upper hardlink case, the union nlink should be incremented
+ * or decremented IFF the operation succeeds, aligned with nlink change of the
+ * upper inode. Therefore, before link/unlink/rename, we store the union nlink
+ * value relative to the upper inode nlink in the index inode.
+ *
+ * For the last, lower cover up case, we simplify things by preceding the
+ * whiteout or cover up with copy up. This makes sure that there is an index
+ * upper inode where the nlink xattr can be stored before the copied up upper
+ * entry is unlink.
+ */
+#define OVL_NLINK_ADD_UPPER	(1 << 0)
+
+/*
+ * On-disk format for indexed nlink:
+ *
+ * nlink relative to the upper inode - "U[+-]NUM"
+ * nlink relative to the lower inode - "L[+-]NUM"
+ */
+
+static int ovl_set_nlink_common(struct dentry *dentry,
+				struct dentry *realdentry, const char *format)
+{
+	struct inode *inode = d_inode(dentry);
+	struct inode *realinode = d_inode(realdentry);
+	char buf[13];
+	int len;
+
+	len = snprintf(buf, sizeof(buf), format,
+		       (int) (inode->i_nlink - realinode->i_nlink));
+
+	return ovl_do_setxattr(ovl_dentry_upper(dentry),
+			       OVL_XATTR_NLINK, buf, len, 0);
+}
+
+int ovl_set_nlink_upper(struct dentry *dentry)
+{
+	return ovl_set_nlink_common(dentry, ovl_dentry_upper(dentry), "U%+i");
+}
+
+int ovl_set_nlink_lower(struct dentry *dentry)
+{
+	return ovl_set_nlink_common(dentry, ovl_dentry_lower(dentry), "L%+i");
+}
+
+unsigned int ovl_get_nlink(struct dentry *lowerdentry,
+			   struct dentry *upperdentry,
+			   unsigned int fallback)
+{
+	int nlink_diff;
+	int nlink;
+	char buf[13];
+	int err;
+
+	if (!lowerdentry || !upperdentry || d_inode(lowerdentry)->i_nlink == 1)
+		return fallback;
+
+	err = vfs_getxattr(upperdentry, OVL_XATTR_NLINK, &buf, sizeof(buf) - 1);
+	if (err < 0)
+		goto fail;
+
+	buf[err] = '\0';
+	if ((buf[0] != 'L' && buf[0] != 'U') ||
+	    (buf[1] != '+' && buf[1] != '-'))
+		goto fail;
+
+	err = kstrtoint(buf + 1, 10, &nlink_diff);
+	if (err < 0)
+		goto fail;
+
+	nlink = d_inode(buf[0] == 'L' ? lowerdentry : upperdentry)->i_nlink;
+	nlink += nlink_diff;
+
+	if (nlink <= 0)
+		goto fail;
+
+	return nlink;
+
+fail:
+	pr_warn_ratelimited("overlayfs: failed to get index nlink (%pd2, err=%i)\n",
+			    upperdentry, err);
+	return fallback;
+}
+
 struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev)
 {
 	struct inode *inode;
@@ -344,27 +564,87 @@ struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev)
 
 static int ovl_inode_test(struct inode *inode, void *data)
 {
-	return ovl_inode_real(inode, NULL) == data;
+	return inode->i_private == data;
 }
 
 static int ovl_inode_set(struct inode *inode, void *data)
 {
-	inode->i_private = (void *) (((unsigned long) data) | OVL_ISUPPER_MASK);
+	inode->i_private = data;
 	return 0;
 }
 
-struct inode *ovl_get_inode(struct super_block *sb, struct inode *realinode)
+static bool ovl_verify_inode(struct inode *inode, struct dentry *lowerdentry,
+			     struct dentry *upperdentry)
+{
+	struct inode *lowerinode = lowerdentry ? d_inode(lowerdentry) : NULL;
+
+	/* Lower (origin) inode must match, even if NULL */
+	if (ovl_inode_lower(inode) != lowerinode)
+		return false;
+
+	/*
+	 * Allow non-NULL __upperdentry in inode even if upperdentry is NULL.
+	 * This happens when finding a lower alias for a copied up hard link.
+	 */
+	if (upperdentry && ovl_inode_upper(inode) != d_inode(upperdentry))
+		return false;
+
+	return true;
+}
 
+struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry)
 {
+	struct dentry *lowerdentry = ovl_dentry_lower(dentry);
+	struct inode *realinode = upperdentry ? d_inode(upperdentry) : NULL;
 	struct inode *inode;
 
-	inode = iget5_locked(sb, (unsigned long) realinode,
-			     ovl_inode_test, ovl_inode_set, realinode);
-	if (inode && inode->i_state & I_NEW) {
-		ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev);
-		set_nlink(inode, realinode->i_nlink);
-		unlock_new_inode(inode);
+	if (!realinode)
+		realinode = d_inode(lowerdentry);
+
+	if (!S_ISDIR(realinode->i_mode) &&
+	    (upperdentry || (lowerdentry && ovl_indexdir(dentry->d_sb)))) {
+		struct inode *key = d_inode(lowerdentry ?: upperdentry);
+		unsigned int nlink;
+
+		inode = iget5_locked(dentry->d_sb, (unsigned long) key,
+				     ovl_inode_test, ovl_inode_set, key);
+		if (!inode)
+			goto out_nomem;
+		if (!(inode->i_state & I_NEW)) {
+			/*
+			 * Verify that the underlying files stored in the inode
+			 * match those in the dentry.
+			 */
+			if (!ovl_verify_inode(inode, lowerdentry, upperdentry)) {
+				iput(inode);
+				inode = ERR_PTR(-ESTALE);
+				goto out;
+			}
+
+			dput(upperdentry);
+			goto out;
+		}
+
+		nlink = ovl_get_nlink(lowerdentry, upperdentry,
+				      realinode->i_nlink);
+		set_nlink(inode, nlink);
+	} else {
+		inode = new_inode(dentry->d_sb);
+		if (!inode)
+			goto out_nomem;
 	}
+	ovl_fill_inode(inode, realinode->i_mode, realinode->i_rdev);
+	ovl_inode_init(inode, upperdentry, lowerdentry);
+
+	if (upperdentry && ovl_is_impuredir(upperdentry))
+		ovl_set_flag(OVL_IMPURE, inode);
 
+	if (inode->i_state & I_NEW)
+		unlock_new_inode(inode);
+out:
 	return inode;
+
+out_nomem:
+	inode = ERR_PTR(-ENOMEM);
+	goto out;
 }
diff --git a/fs/overlayfs/namei.c b/fs/overlayfs/namei.c
index 023bb0b03352..8aef2b304b2d 100644
--- a/fs/overlayfs/namei.c
+++ b/fs/overlayfs/namei.c
@@ -8,9 +8,12 @@
  */
 
 #include <linux/fs.h>
+#include <linux/cred.h>
 #include <linux/namei.h>
 #include <linux/xattr.h>
 #include <linux/ratelimit.h>
+#include <linux/mount.h>
+#include <linux/exportfs.h>
 #include "overlayfs.h"
 #include "ovl_entry.h"
 
@@ -80,19 +83,109 @@ invalid:
 	goto err_free;
 }
 
-static bool ovl_is_opaquedir(struct dentry *dentry)
+static int ovl_acceptable(void *ctx, struct dentry *dentry)
+{
+	return 1;
+}
+
+static struct ovl_fh *ovl_get_origin_fh(struct dentry *dentry)
 {
 	int res;
-	char val;
+	struct ovl_fh *fh = NULL;
+
+	res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, NULL, 0);
+	if (res < 0) {
+		if (res == -ENODATA || res == -EOPNOTSUPP)
+			return NULL;
+		goto fail;
+	}
+	/* Zero size value means "copied up but origin unknown" */
+	if (res == 0)
+		return NULL;
 
-	if (!d_is_dir(dentry))
-		return false;
+	fh = kzalloc(res, GFP_TEMPORARY);
+	if (!fh)
+		return ERR_PTR(-ENOMEM);
 
-	res = vfs_getxattr(dentry, OVL_XATTR_OPAQUE, &val, 1);
-	if (res == 1 && val == 'y')
-		return true;
+	res = vfs_getxattr(dentry, OVL_XATTR_ORIGIN, fh, res);
+	if (res < 0)
+		goto fail;
+
+	if (res < sizeof(struct ovl_fh) || res < fh->len)
+		goto invalid;
+
+	if (fh->magic != OVL_FH_MAGIC)
+		goto invalid;
+
+	/* Treat larger version and unknown flags as "origin unknown" */
+	if (fh->version > OVL_FH_VERSION || fh->flags & ~OVL_FH_FLAG_ALL)
+		goto out;
+
+	/* Treat endianness mismatch as "origin unknown" */
+	if (!(fh->flags & OVL_FH_FLAG_ANY_ENDIAN) &&
+	    (fh->flags & OVL_FH_FLAG_BIG_ENDIAN) != OVL_FH_FLAG_CPU_ENDIAN)
+		goto out;
+
+	return fh;
+
+out:
+	kfree(fh);
+	return NULL;
 
-	return false;
+fail:
+	pr_warn_ratelimited("overlayfs: failed to get origin (%i)\n", res);
+	goto out;
+invalid:
+	pr_warn_ratelimited("overlayfs: invalid origin (%*phN)\n", res, fh);
+	goto out;
+}
+
+static struct dentry *ovl_get_origin(struct dentry *dentry,
+				     struct vfsmount *mnt)
+{
+	struct dentry *origin = NULL;
+	struct ovl_fh *fh = ovl_get_origin_fh(dentry);
+	int bytes;
+
+	if (IS_ERR_OR_NULL(fh))
+		return (struct dentry *)fh;
+
+	/*
+	 * Make sure that the stored uuid matches the uuid of the lower
+	 * layer where file handle will be decoded.
+	 */
+	if (!uuid_equal(&fh->uuid, &mnt->mnt_sb->s_uuid))
+		goto out;
+
+	bytes = (fh->len - offsetof(struct ovl_fh, fid));
+	origin = exportfs_decode_fh(mnt, (struct fid *)fh->fid,
+				    bytes >> 2, (int)fh->type,
+				    ovl_acceptable, NULL);
+	if (IS_ERR(origin)) {
+		/* Treat stale file handle as "origin unknown" */
+		if (origin == ERR_PTR(-ESTALE))
+			origin = NULL;
+		goto out;
+	}
+
+	if (ovl_dentry_weird(origin) ||
+	    ((d_inode(origin)->i_mode ^ d_inode(dentry)->i_mode) & S_IFMT))
+		goto invalid;
+
+out:
+	kfree(fh);
+	return origin;
+
+invalid:
+	pr_warn_ratelimited("overlayfs: invalid origin (%pd2)\n", origin);
+	dput(origin);
+	origin = NULL;
+	goto out;
+}
+
+static bool ovl_is_opaquedir(struct dentry *dentry)
+{
+	return ovl_check_dir_xattr(dentry, OVL_XATTR_OPAQUE);
 }
 
 static int ovl_lookup_single(struct dentry *base, struct ovl_lookup_data *d,
@@ -191,6 +284,274 @@ static int ovl_lookup_layer(struct dentry *base, struct ovl_lookup_data *d,
 	return 0;
 }
 
+
+static int ovl_check_origin(struct dentry *upperdentry,
+			    struct path *lowerstack, unsigned int numlower,
+			    struct path **stackp, unsigned int *ctrp)
+{
+	struct vfsmount *mnt;
+	struct dentry *origin = NULL;
+	int i;
+
+
+	for (i = 0; i < numlower; i++) {
+		mnt = lowerstack[i].mnt;
+		origin = ovl_get_origin(upperdentry, mnt);
+		if (IS_ERR(origin))
+			return PTR_ERR(origin);
+
+		if (origin)
+			break;
+	}
+
+	if (!origin)
+		return 0;
+
+	BUG_ON(*ctrp);
+	if (!*stackp)
+		*stackp = kmalloc(sizeof(struct path), GFP_TEMPORARY);
+	if (!*stackp) {
+		dput(origin);
+		return -ENOMEM;
+	}
+	**stackp = (struct path) { .dentry = origin, .mnt = mnt };
+	*ctrp = 1;
+
+	return 0;
+}
+
+/*
+ * Verify that @fh matches the origin file handle stored in OVL_XATTR_ORIGIN.
+ * Return 0 on match, -ESTALE on mismatch, < 0 on error.
+ */
+static int ovl_verify_origin_fh(struct dentry *dentry, const struct ovl_fh *fh)
+{
+	struct ovl_fh *ofh = ovl_get_origin_fh(dentry);
+	int err = 0;
+
+	if (!ofh)
+		return -ENODATA;
+
+	if (IS_ERR(ofh))
+		return PTR_ERR(ofh);
+
+	if (fh->len != ofh->len || memcmp(fh, ofh, fh->len))
+		err = -ESTALE;
+
+	kfree(ofh);
+	return err;
+}
+
+/*
+ * Verify that an inode matches the origin file handle stored in upper inode.
+ *
+ * If @set is true and there is no stored file handle, encode and store origin
+ * file handle in OVL_XATTR_ORIGIN.
+ *
+ * Return 0 on match, -ESTALE on mismatch, < 0 on error.
+ */
+int ovl_verify_origin(struct dentry *dentry, struct vfsmount *mnt,
+		      struct dentry *origin, bool is_upper, bool set)
+{
+	struct inode *inode;
+	struct ovl_fh *fh;
+	int err;
+
+	fh = ovl_encode_fh(origin, is_upper);
+	err = PTR_ERR(fh);
+	if (IS_ERR(fh))
+		goto fail;
+
+	err = ovl_verify_origin_fh(dentry, fh);
+	if (set && err == -ENODATA)
+		err = ovl_do_setxattr(dentry, OVL_XATTR_ORIGIN, fh, fh->len, 0);
+	if (err)
+		goto fail;
+
+out:
+	kfree(fh);
+	return err;
+
+fail:
+	inode = d_inode(origin);
+	pr_warn_ratelimited("overlayfs: failed to verify origin (%pd2, ino=%lu, err=%i)\n",
+			    origin, inode ? inode->i_ino : 0, err);
+	goto out;
+}
+
+/*
+ * Verify that an index entry name matches the origin file handle stored in
+ * OVL_XATTR_ORIGIN and that origin file handle can be decoded to lower path.
+ * Return 0 on match, -ESTALE on mismatch or stale origin, < 0 on error.
+ */
+int ovl_verify_index(struct dentry *index, struct path *lowerstack,
+		     unsigned int numlower)
+{
+	struct ovl_fh *fh = NULL;
+	size_t len;
+	struct path origin = { };
+	struct path *stack = &origin;
+	unsigned int ctr = 0;
+	int err;
+
+	if (!d_inode(index))
+		return 0;
+
+	/*
+	 * Directory index entries are going to be used for looking up
+	 * redirected upper dirs by lower dir fh when decoding an overlay
+	 * file handle of a merge dir. Whiteout index entries are going to be
+	 * used as an indication that an exported overlay file handle should
+	 * be treated as stale (i.e. after unlink of the overlay inode).
+	 * We don't know the verification rules for directory and whiteout
+	 * index entries, because they have not been implemented yet, so return
+	 * EROFS if those entries are found to avoid corrupting an index that
+	 * was created by a newer kernel.
+	 */
+	err = -EROFS;
+	if (d_is_dir(index) || ovl_is_whiteout(index))
+		goto fail;
+
+	err = -EINVAL;
+	if (index->d_name.len < sizeof(struct ovl_fh)*2)
+		goto fail;
+
+	err = -ENOMEM;
+	len = index->d_name.len / 2;
+	fh = kzalloc(len, GFP_TEMPORARY);
+	if (!fh)
+		goto fail;
+
+	err = -EINVAL;
+	if (hex2bin((u8 *)fh, index->d_name.name, len) || len != fh->len)
+		goto fail;
+
+	err = ovl_verify_origin_fh(index, fh);
+	if (err)
+		goto fail;
+
+	err = ovl_check_origin(index, lowerstack, numlower, &stack, &ctr);
+	if (!err && !ctr)
+		err = -ESTALE;
+	if (err)
+		goto fail;
+
+	/* Check if index is orphan and don't warn before cleaning it */
+	if (d_inode(index)->i_nlink == 1 &&
+	    ovl_get_nlink(index, origin.dentry, 0) == 0)
+		err = -ENOENT;
+
+	dput(origin.dentry);
+out:
+	kfree(fh);
+	return err;
+
+fail:
+	pr_warn_ratelimited("overlayfs: failed to verify index (%pd2, ftype=%x, err=%i)\n",
+			    index, d_inode(index)->i_mode & S_IFMT, err);
+	goto out;
+}
+
+/*
+ * Lookup in indexdir for the index entry of a lower real inode or a copy up
+ * origin inode. The index entry name is the hex representation of the lower
+ * inode file handle.
+ *
+ * If the index dentry in negative, then either no lower aliases have been
+ * copied up yet, or aliases have been copied up in older kernels and are
+ * not indexed.
+ *
+ * If the index dentry for a copy up origin inode is positive, but points
+ * to an inode different than the upper inode, then either the upper inode
+ * has been copied up and not indexed or it was indexed, but since then
+ * index dir was cleared. Either way, that index cannot be used to indentify
+ * the overlay inode.
+ */
+int ovl_get_index_name(struct dentry *origin, struct qstr *name)
+{
+	int err;
+	struct ovl_fh *fh;
+	char *n, *s;
+
+	fh = ovl_encode_fh(origin, false);
+	if (IS_ERR(fh))
+		return PTR_ERR(fh);
+
+	err = -ENOMEM;
+	n = kzalloc(fh->len * 2, GFP_TEMPORARY);
+	if (n) {
+		s  = bin2hex(n, fh, fh->len);
+		*name = (struct qstr) QSTR_INIT(n, s - n);
+		err = 0;
+	}
+	kfree(fh);
+
+	return err;
+
+}
+
+static struct dentry *ovl_lookup_index(struct dentry *dentry,
+				       struct dentry *upper,
+				       struct dentry *origin)
+{
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+	struct dentry *index;
+	struct inode *inode;
+	struct qstr name;
+	int err;
+
+	err = ovl_get_index_name(origin, &name);
+	if (err)
+		return ERR_PTR(err);
+
+	index = lookup_one_len_unlocked(name.name, ofs->indexdir, name.len);
+	if (IS_ERR(index)) {
+		pr_warn_ratelimited("overlayfs: failed inode index lookup (ino=%lu, key=%*s, err=%i);\n"
+				    "overlayfs: mount with '-o index=off' to disable inodes index.\n",
+				    d_inode(origin)->i_ino, name.len, name.name,
+				    err);
+		goto out;
+	}
+
+	inode = d_inode(index);
+	if (d_is_negative(index)) {
+		if (upper && d_inode(origin)->i_nlink > 1) {
+			pr_warn_ratelimited("overlayfs: hard link with origin but no index (ino=%lu).\n",
+					    d_inode(origin)->i_ino);
+			goto fail;
+		}
+
+		dput(index);
+		index = NULL;
+	} else if (upper && d_inode(upper) != inode) {
+		pr_warn_ratelimited("overlayfs: wrong index found (index=%pd2, ino=%lu, upper ino=%lu).\n",
+				    index, inode->i_ino, d_inode(upper)->i_ino);
+		goto fail;
+	} else if (ovl_dentry_weird(index) || ovl_is_whiteout(index) ||
+		   ((inode->i_mode ^ d_inode(origin)->i_mode) & S_IFMT)) {
+		/*
+		 * Index should always be of the same file type as origin
+		 * except for the case of a whiteout index. A whiteout
+		 * index should only exist if all lower aliases have been
+		 * unlinked, which means that finding a lower origin on lookup
+		 * whose index is a whiteout should be treated as an error.
+		 */
+		pr_warn_ratelimited("overlayfs: bad index found (index=%pd2, ftype=%x, origin ftype=%x).\n",
+				    index, d_inode(index)->i_mode & S_IFMT,
+				    d_inode(origin)->i_mode & S_IFMT);
+		goto fail;
+	}
+
+out:
+	kfree(name.name);
+	return index;
+
+fail:
+	dput(index);
+	index = ERR_PTR(-EIO);
+	goto out;
+}
+
 /*
  * Returns next layer in stack starting from top.
  * Returns -1 if this is the last layer.
@@ -219,8 +580,10 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 	const struct cred *old_cred;
 	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
 	struct ovl_entry *poe = dentry->d_parent->d_fsdata;
+	struct ovl_entry *roe = dentry->d_sb->s_root->d_fsdata;
 	struct path *stack = NULL;
 	struct dentry *upperdir, *upperdentry = NULL;
+	struct dentry *index = NULL;
 	unsigned int ctr = 0;
 	struct inode *inode = NULL;
 	bool upperopaque = false;
@@ -241,7 +604,7 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 		return ERR_PTR(-ENAMETOOLONG);
 
 	old_cred = ovl_override_creds(dentry->d_sb);
-	upperdir = ovl_upperdentry_dereference(poe);
+	upperdir = ovl_dentry_upper(dentry->d_parent);
 	if (upperdir) {
 		err = ovl_lookup_layer(upperdir, &d, &upperdentry);
 		if (err)
@@ -252,13 +615,30 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 			err = -EREMOTE;
 			goto out;
 		}
+		if (upperdentry && !d.is_dir) {
+			BUG_ON(!d.stop || d.redirect);
+			/*
+			 * Lookup copy up origin by decoding origin file handle.
+			 * We may get a disconnected dentry, which is fine,
+			 * because we only need to hold the origin inode in
+			 * cache and use its inode number.  We may even get a
+			 * connected dentry, that is not under any of the lower
+			 * layers root.  That is also fine for using it's inode
+			 * number - it's the same as if we held a reference
+			 * to a dentry in lower layer that was moved under us.
+			 */
+			err = ovl_check_origin(upperdentry, roe->lowerstack,
+					       roe->numlower, &stack, &ctr);
+			if (err)
+				goto out;
+		}
 
 		if (d.redirect) {
 			upperredirect = kstrdup(d.redirect, GFP_KERNEL);
 			if (!upperredirect)
 				goto out_put_upper;
 			if (d.redirect[0] == '/')
-				poe = dentry->d_sb->s_root->d_fsdata;
+				poe = roe;
 		}
 		upperopaque = d.opaque;
 	}
@@ -289,10 +669,8 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 		if (d.stop)
 			break;
 
-		if (d.redirect &&
-		    d.redirect[0] == '/' &&
-		    poe != dentry->d_sb->s_root->d_fsdata) {
-			poe = dentry->d_sb->s_root->d_fsdata;
+		if (d.redirect && d.redirect[0] == '/' && poe != roe) {
+			poe = roe;
 
 			/* Find the current layer on the root dentry */
 			for (i = 0; i < poe->numlower; i++)
@@ -303,47 +681,56 @@ struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry,
 		}
 	}
 
+	/* Lookup index by lower inode and verify it matches upper inode */
+	if (ctr && !d.is_dir && ovl_indexdir(dentry->d_sb)) {
+		struct dentry *origin = stack[0].dentry;
+
+		index = ovl_lookup_index(dentry, upperdentry, origin);
+		if (IS_ERR(index)) {
+			err = PTR_ERR(index);
+			index = NULL;
+			goto out_put;
+		}
+	}
+
 	oe = ovl_alloc_entry(ctr);
 	err = -ENOMEM;
 	if (!oe)
 		goto out_put;
 
-	if (upperdentry || ctr) {
-		struct dentry *realdentry;
-		struct inode *realinode;
+	oe->opaque = upperopaque;
+	memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
+	dentry->d_fsdata = oe;
 
-		realdentry = upperdentry ? upperdentry : stack[0].dentry;
-		realinode = d_inode(realdentry);
+	if (upperdentry)
+		ovl_dentry_set_upper_alias(dentry);
+	else if (index)
+		upperdentry = dget(index);
 
-		err = -ENOMEM;
-		if (upperdentry && !d_is_dir(upperdentry)) {
-			inode = ovl_get_inode(dentry->d_sb, realinode);
-		} else {
-			inode = ovl_new_inode(dentry->d_sb, realinode->i_mode,
-					      realinode->i_rdev);
-			if (inode)
-				ovl_inode_init(inode, realinode, !!upperdentry);
-		}
-		if (!inode)
+	if (upperdentry || ctr) {
+		inode = ovl_get_inode(dentry, upperdentry);
+		err = PTR_ERR(inode);
+		if (IS_ERR(inode))
 			goto out_free_oe;
-		ovl_copyattr(realdentry->d_inode, inode);
+
+		OVL_I(inode)->redirect = upperredirect;
+		if (index)
+			ovl_set_flag(OVL_INDEX, inode);
 	}
 
 	revert_creds(old_cred);
-	oe->opaque = upperopaque;
-	oe->redirect = upperredirect;
-	oe->__upperdentry = upperdentry;
-	memcpy(oe->lowerstack, stack, sizeof(struct path) * ctr);
+	dput(index);
 	kfree(stack);
 	kfree(d.redirect);
-	dentry->d_fsdata = oe;
 	d_add(dentry, inode);
 
 	return NULL;
 
 out_free_oe:
+	dentry->d_fsdata = NULL;
 	kfree(oe);
 out_put:
+	dput(index);
 	for (i = 0; i < ctr; i++)
 		dput(stack[i].dentry);
 	kfree(stack);
@@ -373,7 +760,7 @@ bool ovl_lower_positive(struct dentry *dentry)
 		return oe->opaque;
 
 	/* Negative upper -> positive lower */
-	if (!oe->__upperdentry)
+	if (!ovl_dentry_upper(dentry))
 		return true;
 
 	/* Positive upper -> have to look up lower to see whether it exists */
diff --git a/fs/overlayfs/overlayfs.h b/fs/overlayfs/overlayfs.h
index 8af450b0e57a..e927a62c97ae 100644
--- a/fs/overlayfs/overlayfs.h
+++ b/fs/overlayfs/overlayfs.h
@@ -8,20 +8,66 @@
  */
 
 #include <linux/kernel.h>
+#include <linux/uuid.h>
 
 enum ovl_path_type {
 	__OVL_PATH_UPPER	= (1 << 0),
 	__OVL_PATH_MERGE	= (1 << 1),
+	__OVL_PATH_ORIGIN	= (1 << 2),
 };
 
 #define OVL_TYPE_UPPER(type)	((type) & __OVL_PATH_UPPER)
 #define OVL_TYPE_MERGE(type)	((type) & __OVL_PATH_MERGE)
+#define OVL_TYPE_ORIGIN(type)	((type) & __OVL_PATH_ORIGIN)
 
 #define OVL_XATTR_PREFIX XATTR_TRUSTED_PREFIX "overlay."
 #define OVL_XATTR_OPAQUE OVL_XATTR_PREFIX "opaque"
 #define OVL_XATTR_REDIRECT OVL_XATTR_PREFIX "redirect"
+#define OVL_XATTR_ORIGIN OVL_XATTR_PREFIX "origin"
+#define OVL_XATTR_IMPURE OVL_XATTR_PREFIX "impure"
+#define OVL_XATTR_NLINK OVL_XATTR_PREFIX "nlink"
 
-#define OVL_ISUPPER_MASK 1UL
+enum ovl_flag {
+	OVL_IMPURE,
+	OVL_INDEX,
+};
+
+/*
+ * The tuple (fh,uuid) is a universal unique identifier for a copy up origin,
+ * where:
+ * origin.fh	- exported file handle of the lower file
+ * origin.uuid	- uuid of the lower filesystem
+ */
+#define OVL_FH_VERSION	0
+#define OVL_FH_MAGIC	0xfb
+
+/* CPU byte order required for fid decoding:  */
+#define OVL_FH_FLAG_BIG_ENDIAN	(1 << 0)
+#define OVL_FH_FLAG_ANY_ENDIAN	(1 << 1)
+/* Is the real inode encoded in fid an upper inode? */
+#define OVL_FH_FLAG_PATH_UPPER	(1 << 2)
+
+#define OVL_FH_FLAG_ALL (OVL_FH_FLAG_BIG_ENDIAN | OVL_FH_FLAG_ANY_ENDIAN | \
+			 OVL_FH_FLAG_PATH_UPPER)
+
+#if defined(__LITTLE_ENDIAN)
+#define OVL_FH_FLAG_CPU_ENDIAN 0
+#elif defined(__BIG_ENDIAN)
+#define OVL_FH_FLAG_CPU_ENDIAN OVL_FH_FLAG_BIG_ENDIAN
+#else
+#error Endianness not defined
+#endif
+
+/* On-disk and in-memeory format for redirect by file handle */
+struct ovl_fh {
+	u8 version;	/* 0 */
+	u8 magic;	/* 0xfb */
+	u8 len;		/* size of this header + size of fid */
+	u8 flags;	/* OVL_FH_FLAG_* */
+	u8 type;	/* fid_type of fid */
+	uuid_t uuid;	/* uuid of filesystem */
+	u8 fid[0];	/* file identifier */
+} __packed;
 
 static inline int ovl_do_rmdir(struct inode *dir, struct dentry *dentry)
 {
@@ -127,14 +173,13 @@ static inline int ovl_do_whiteout(struct inode *dir, struct dentry *dentry)
 	return err;
 }
 
-static inline struct inode *ovl_inode_real(struct inode *inode, bool *is_upper)
+static inline struct dentry *ovl_do_tmpfile(struct dentry *dentry, umode_t mode)
 {
-	unsigned long x = (unsigned long) READ_ONCE(inode->i_private);
-
-	if (is_upper)
-		*is_upper = x & OVL_ISUPPER_MASK;
+	struct dentry *ret = vfs_tmpfile(dentry, mode, 0);
+	int err = IS_ERR(ret) ? PTR_ERR(ret) : 0;
 
-	return (struct inode *) (x & ~OVL_ISUPPER_MASK);
+	pr_debug("tmpfile(%pd2, 0%o) = %i\n", dentry, mode, err);
+	return ret;
 }
 
 /* util.c */
@@ -142,6 +187,9 @@ int ovl_want_write(struct dentry *dentry);
 void ovl_drop_write(struct dentry *dentry);
 struct dentry *ovl_workdir(struct dentry *dentry);
 const struct cred *ovl_override_creds(struct super_block *sb);
+struct super_block *ovl_same_sb(struct super_block *sb);
+bool ovl_can_decode_fh(struct super_block *sb);
+struct dentry *ovl_indexdir(struct super_block *sb);
 struct ovl_entry *ovl_alloc_entry(unsigned int numlower);
 bool ovl_dentry_remote(struct dentry *dentry);
 bool ovl_dentry_weird(struct dentry *dentry);
@@ -152,25 +200,53 @@ enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path);
 struct dentry *ovl_dentry_upper(struct dentry *dentry);
 struct dentry *ovl_dentry_lower(struct dentry *dentry);
 struct dentry *ovl_dentry_real(struct dentry *dentry);
+struct dentry *ovl_i_dentry_upper(struct inode *inode);
+struct inode *ovl_inode_upper(struct inode *inode);
+struct inode *ovl_inode_lower(struct inode *inode);
+struct inode *ovl_inode_real(struct inode *inode);
 struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry);
 void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache);
 bool ovl_dentry_is_opaque(struct dentry *dentry);
 bool ovl_dentry_is_whiteout(struct dentry *dentry);
 void ovl_dentry_set_opaque(struct dentry *dentry);
+bool ovl_dentry_has_upper_alias(struct dentry *dentry);
+void ovl_dentry_set_upper_alias(struct dentry *dentry);
 bool ovl_redirect_dir(struct super_block *sb);
-void ovl_clear_redirect_dir(struct super_block *sb);
 const char *ovl_dentry_get_redirect(struct dentry *dentry);
 void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect);
-void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry);
-void ovl_inode_init(struct inode *inode, struct inode *realinode,
-		    bool is_upper);
-void ovl_inode_update(struct inode *inode, struct inode *upperinode);
+void ovl_inode_init(struct inode *inode, struct dentry *upperdentry,
+		    struct dentry *lowerdentry);
+void ovl_inode_update(struct inode *inode, struct dentry *upperdentry);
 void ovl_dentry_version_inc(struct dentry *dentry);
 u64 ovl_dentry_version_get(struct dentry *dentry);
 bool ovl_is_whiteout(struct dentry *dentry);
 struct file *ovl_path_open(struct path *path, int flags);
+int ovl_copy_up_start(struct dentry *dentry);
+void ovl_copy_up_end(struct dentry *dentry);
+bool ovl_check_dir_xattr(struct dentry *dentry, const char *name);
+int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
+		       const char *name, const void *value, size_t size,
+		       int xerr);
+int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry);
+void ovl_set_flag(unsigned long flag, struct inode *inode);
+bool ovl_test_flag(unsigned long flag, struct inode *inode);
+bool ovl_inuse_trylock(struct dentry *dentry);
+void ovl_inuse_unlock(struct dentry *dentry);
+int ovl_nlink_start(struct dentry *dentry, bool *locked);
+void ovl_nlink_end(struct dentry *dentry, bool locked);
+
+static inline bool ovl_is_impuredir(struct dentry *dentry)
+{
+	return ovl_check_dir_xattr(dentry, OVL_XATTR_IMPURE);
+}
+
 
 /* namei.c */
+int ovl_verify_origin(struct dentry *dentry, struct vfsmount *mnt,
+		      struct dentry *origin, bool is_upper, bool set);
+int ovl_verify_index(struct dentry *index, struct path *lowerstack,
+		     unsigned int numlower);
+int ovl_get_index_name(struct dentry *origin, struct qstr *name);
 int ovl_path_next(int idx, struct dentry *dentry, struct path *path);
 struct dentry *ovl_lookup(struct inode *dir, struct dentry *dentry, unsigned int flags);
 bool ovl_lower_positive(struct dentry *dentry);
@@ -183,13 +259,22 @@ void ovl_cache_free(struct list_head *list);
 int ovl_check_d_type_supported(struct path *realpath);
 void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt,
 			 struct dentry *dentry, int level);
+int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
+			 struct path *lowerstack, unsigned int numlower);
 
 /* inode.c */
+int ovl_set_nlink_upper(struct dentry *dentry);
+int ovl_set_nlink_lower(struct dentry *dentry);
+unsigned int ovl_get_nlink(struct dentry *lowerdentry,
+			   struct dentry *upperdentry,
+			   unsigned int fallback);
 int ovl_setattr(struct dentry *dentry, struct iattr *attr);
+int ovl_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int flags);
 int ovl_permission(struct inode *inode, int mask);
-int ovl_xattr_set(struct dentry *dentry, const char *name, const void *value,
-		  size_t size, int flags);
-int ovl_xattr_get(struct dentry *dentry, const char *name,
+int ovl_xattr_set(struct dentry *dentry, struct inode *inode, const char *name,
+		  const void *value, size_t size, int flags);
+int ovl_xattr_get(struct dentry *dentry, struct inode *inode, const char *name,
 		  void *value, size_t size);
 ssize_t ovl_listxattr(struct dentry *dentry, char *list, size_t size);
 struct posix_acl *ovl_get_acl(struct inode *inode, int type);
@@ -198,7 +283,7 @@ int ovl_update_time(struct inode *inode, struct timespec *ts, int flags);
 bool ovl_is_private_xattr(const char *name);
 
 struct inode *ovl_new_inode(struct super_block *sb, umode_t mode, dev_t rdev);
-struct inode *ovl_get_inode(struct super_block *sb, struct inode *realinode);
+struct inode *ovl_get_inode(struct dentry *dentry, struct dentry *upperdentry);
 static inline void ovl_copyattr(struct inode *from, struct inode *to)
 {
 	to->i_uid = from->i_uid;
@@ -211,7 +296,7 @@ static inline void ovl_copyattr(struct inode *from, struct inode *to)
 
 /* dir.c */
 extern const struct inode_operations ovl_dir_inode_operations;
-struct dentry *ovl_lookup_temp(struct dentry *workdir, struct dentry *dentry);
+struct dentry *ovl_lookup_temp(struct dentry *workdir);
 struct cattr {
 	dev_t rdev;
 	umode_t mode;
@@ -220,10 +305,11 @@ struct cattr {
 int ovl_create_real(struct inode *dir, struct dentry *newdentry,
 		    struct cattr *attr,
 		    struct dentry *hardlink, bool debug);
-void ovl_cleanup(struct inode *dir, struct dentry *dentry);
+int ovl_cleanup(struct inode *dir, struct dentry *dentry);
 
 /* copy_up.c */
 int ovl_copy_up(struct dentry *dentry);
 int ovl_copy_up_flags(struct dentry *dentry, int flags);
 int ovl_copy_xattr(struct dentry *old, struct dentry *new);
 int ovl_set_attr(struct dentry *upper, struct kstat *stat);
+struct ovl_fh *ovl_encode_fh(struct dentry *lower, bool is_upper);
diff --git a/fs/overlayfs/ovl_entry.h b/fs/overlayfs/ovl_entry.h
index d14bca1850d9..878a750986dd 100644
--- a/fs/overlayfs/ovl_entry.h
+++ b/fs/overlayfs/ovl_entry.h
@@ -14,6 +14,7 @@ struct ovl_config {
 	char *workdir;
 	bool default_permissions;
 	bool redirect_dir;
+	bool index;
 };
 
 /* private information held for overlayfs's superblock */
@@ -21,22 +22,28 @@ struct ovl_fs {
 	struct vfsmount *upper_mnt;
 	unsigned numlower;
 	struct vfsmount **lower_mnt;
+	/* workbasedir is the path at workdir= mount option */
+	struct dentry *workbasedir;
+	/* workdir is the 'work' directory under workbasedir */
 	struct dentry *workdir;
+	/* index directory listing overlay inodes by origin file handle */
+	struct dentry *indexdir;
 	long namelen;
 	/* pathnames of lower and upper dirs, for show_options */
 	struct ovl_config config;
 	/* creds of process who forced instantiation of super block */
 	const struct cred *creator_cred;
+	bool tmpfile;
+	bool noxattr;
+	/* sb common to all layers */
+	struct super_block *same_sb;
 };
 
 /* private information held for every overlayfs dentry */
 struct ovl_entry {
-	struct dentry *__upperdentry;
-	struct ovl_dir_cache *cache;
 	union {
 		struct {
-			u64 version;
-			const char *redirect;
+			unsigned long has_upper;
 			bool opaque;
 		};
 		struct rcu_head rcu;
@@ -47,7 +54,25 @@ struct ovl_entry {
 
 struct ovl_entry *ovl_alloc_entry(unsigned int numlower);
 
-static inline struct dentry *ovl_upperdentry_dereference(struct ovl_entry *oe)
+struct ovl_inode {
+	struct ovl_dir_cache *cache;
+	const char *redirect;
+	u64 version;
+	unsigned long flags;
+	struct inode vfs_inode;
+	struct dentry *__upperdentry;
+	struct inode *lower;
+
+	/* synchronize copy up and more */
+	struct mutex lock;
+};
+
+static inline struct ovl_inode *OVL_I(struct inode *inode)
+{
+	return container_of(inode, struct ovl_inode, vfs_inode);
+}
+
+static inline struct dentry *ovl_upperdentry_dereference(struct ovl_inode *oi)
 {
-	return lockless_dereference(oe->__upperdentry);
+	return lockless_dereference(oi->__upperdentry);
 }
diff --git a/fs/overlayfs/readdir.c b/fs/overlayfs/readdir.c
index f241b4ee3d8a..3d424a51cabb 100644
--- a/fs/overlayfs/readdir.c
+++ b/fs/overlayfs/readdir.c
@@ -667,3 +667,56 @@ void ovl_workdir_cleanup(struct inode *dir, struct vfsmount *mnt,
 		ovl_cleanup(dir, dentry);
 	}
 }
+
+int ovl_indexdir_cleanup(struct dentry *dentry, struct vfsmount *mnt,
+			 struct path *lowerstack, unsigned int numlower)
+{
+	int err;
+	struct inode *dir = dentry->d_inode;
+	struct path path = { .mnt = mnt, .dentry = dentry };
+	LIST_HEAD(list);
+	struct ovl_cache_entry *p;
+	struct ovl_readdir_data rdd = {
+		.ctx.actor = ovl_fill_merge,
+		.dentry = NULL,
+		.list = &list,
+		.root = RB_ROOT,
+		.is_lowest = false,
+	};
+
+	err = ovl_dir_read(&path, &rdd);
+	if (err)
+		goto out;
+
+	inode_lock_nested(dir, I_MUTEX_PARENT);
+	list_for_each_entry(p, &list, l_node) {
+		struct dentry *index;
+
+		if (p->name[0] == '.') {
+			if (p->len == 1)
+				continue;
+			if (p->len == 2 && p->name[1] == '.')
+				continue;
+		}
+		index = lookup_one_len(p->name, dentry, p->len);
+		if (IS_ERR(index)) {
+			err = PTR_ERR(index);
+			break;
+		}
+		err = ovl_verify_index(index, lowerstack, numlower);
+		if (err) {
+			if (err == -EROFS)
+				break;
+			err = ovl_cleanup(dir, index);
+			if (err)
+				break;
+		}
+		dput(index);
+	}
+	inode_unlock(dir);
+out:
+	ovl_cache_free(&list);
+	if (err)
+		pr_err("overlayfs: failed index dir cleanup (%i)\n", err);
+	return err;
+}
diff --git a/fs/overlayfs/super.c b/fs/overlayfs/super.c
index 20f48abbb82f..d86e89f97201 100644
--- a/fs/overlayfs/super.c
+++ b/fs/overlayfs/super.c
@@ -7,6 +7,7 @@
  * the Free Software Foundation.
  */
 
+#include <uapi/linux/magic.h>
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include <linux/xattr.h>
@@ -33,6 +34,11 @@ module_param_named(redirect_dir, ovl_redirect_dir_def, bool, 0644);
 MODULE_PARM_DESC(ovl_redirect_dir_def,
 		 "Default to on or off for the redirect_dir feature");
 
+static bool ovl_index_def = IS_ENABLED(CONFIG_OVERLAY_FS_INDEX);
+module_param_named(index, ovl_index_def, bool, 0644);
+MODULE_PARM_DESC(ovl_index_def,
+		 "Default to on or off for the inodes index feature");
+
 static void ovl_dentry_release(struct dentry *dentry)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
@@ -40,19 +46,34 @@ static void ovl_dentry_release(struct dentry *dentry)
 	if (oe) {
 		unsigned int i;
 
-		dput(oe->__upperdentry);
-		kfree(oe->redirect);
 		for (i = 0; i < oe->numlower; i++)
 			dput(oe->lowerstack[i].dentry);
 		kfree_rcu(oe, rcu);
 	}
 }
 
+static int ovl_check_append_only(struct inode *inode, int flag)
+{
+	/*
+	 * This test was moot in vfs may_open() because overlay inode does
+	 * not have the S_APPEND flag, so re-check on real upper inode
+	 */
+	if (IS_APPEND(inode)) {
+		if  ((flag & O_ACCMODE) != O_RDONLY && !(flag & O_APPEND))
+			return -EPERM;
+		if (flag & O_TRUNC)
+			return -EPERM;
+	}
+
+	return 0;
+}
+
 static struct dentry *ovl_d_real(struct dentry *dentry,
 				 const struct inode *inode,
 				 unsigned int open_flags)
 {
 	struct dentry *real;
+	int err;
 
 	if (!d_is_reg(dentry)) {
 		if (!inode || inode == d_inode(dentry))
@@ -64,15 +85,20 @@ static struct dentry *ovl_d_real(struct dentry *dentry,
 		return dentry;
 
 	if (open_flags) {
-		int err = ovl_open_maybe_copy_up(dentry, open_flags);
-
+		err = ovl_open_maybe_copy_up(dentry, open_flags);
 		if (err)
 			return ERR_PTR(err);
 	}
 
 	real = ovl_dentry_upper(dentry);
-	if (real && (!inode || inode == d_inode(real)))
+	if (real && (!inode || inode == d_inode(real))) {
+		if (!inode) {
+			err = ovl_check_append_only(d_inode(real), open_flags);
+			if (err)
+				return ERR_PTR(err);
+		}
 		return real;
+	}
 
 	real = ovl_dentry_lower(dentry);
 	if (!real)
@@ -142,12 +168,52 @@ static const struct dentry_operations ovl_reval_dentry_operations = {
 	.d_weak_revalidate = ovl_dentry_weak_revalidate,
 };
 
+static struct kmem_cache *ovl_inode_cachep;
+
+static struct inode *ovl_alloc_inode(struct super_block *sb)
+{
+	struct ovl_inode *oi = kmem_cache_alloc(ovl_inode_cachep, GFP_KERNEL);
+
+	oi->cache = NULL;
+	oi->redirect = NULL;
+	oi->version = 0;
+	oi->flags = 0;
+	oi->__upperdentry = NULL;
+	oi->lower = NULL;
+	mutex_init(&oi->lock);
+
+	return &oi->vfs_inode;
+}
+
+static void ovl_i_callback(struct rcu_head *head)
+{
+	struct inode *inode = container_of(head, struct inode, i_rcu);
+
+	kmem_cache_free(ovl_inode_cachep, OVL_I(inode));
+}
+
+static void ovl_destroy_inode(struct inode *inode)
+{
+	struct ovl_inode *oi = OVL_I(inode);
+
+	dput(oi->__upperdentry);
+	kfree(oi->redirect);
+	mutex_destroy(&oi->lock);
+
+	call_rcu(&inode->i_rcu, ovl_i_callback);
+}
+
 static void ovl_put_super(struct super_block *sb)
 {
 	struct ovl_fs *ufs = sb->s_fs_info;
 	unsigned i;
 
+	dput(ufs->indexdir);
 	dput(ufs->workdir);
+	ovl_inuse_unlock(ufs->workbasedir);
+	dput(ufs->workbasedir);
+	if (ufs->upper_mnt)
+		ovl_inuse_unlock(ufs->upper_mnt->mnt_root);
 	mntput(ufs->upper_mnt);
 	for (i = 0; i < ufs->numlower; i++)
 		mntput(ufs->lower_mnt[i]);
@@ -160,6 +226,25 @@ static void ovl_put_super(struct super_block *sb)
 	kfree(ufs);
 }
 
+static int ovl_sync_fs(struct super_block *sb, int wait)
+{
+	struct ovl_fs *ufs = sb->s_fs_info;
+	struct super_block *upper_sb;
+	int ret;
+
+	if (!ufs->upper_mnt)
+		return 0;
+	upper_sb = ufs->upper_mnt->mnt_sb;
+	if (!upper_sb->s_op->sync_fs)
+		return 0;
+
+	/* real inodes have already been synced by sync_filesystem(ovl_sb) */
+	down_read(&upper_sb->s_umount);
+	ret = upper_sb->s_op->sync_fs(upper_sb, wait);
+	up_read(&upper_sb->s_umount);
+	return ret;
+}
+
 /**
  * ovl_statfs
  * @sb: The overlayfs super block
@@ -186,6 +271,12 @@ static int ovl_statfs(struct dentry *dentry, struct kstatfs *buf)
 	return err;
 }
 
+/* Will this overlay be forced to mount/remount ro? */
+static bool ovl_force_readonly(struct ovl_fs *ufs)
+{
+	return (!ufs->upper_mnt || !ufs->workdir);
+}
+
 /**
  * ovl_show_options
  *
@@ -207,6 +298,9 @@ static int ovl_show_options(struct seq_file *m, struct dentry *dentry)
 	if (ufs->config.redirect_dir != ovl_redirect_dir_def)
 		seq_printf(m, ",redirect_dir=%s",
 			   ufs->config.redirect_dir ? "on" : "off");
+	if (ufs->config.index != ovl_index_def)
+		seq_printf(m, ",index=%s",
+			   ufs->config.index ? "on" : "off");
 	return 0;
 }
 
@@ -214,18 +308,21 @@ static int ovl_remount(struct super_block *sb, int *flags, char *data)
 {
 	struct ovl_fs *ufs = sb->s_fs_info;
 
-	if (!(*flags & MS_RDONLY) && (!ufs->upper_mnt || !ufs->workdir))
+	if (!(*flags & MS_RDONLY) && ovl_force_readonly(ufs))
 		return -EROFS;
 
 	return 0;
 }
 
 static const struct super_operations ovl_super_operations = {
+	.alloc_inode	= ovl_alloc_inode,
+	.destroy_inode	= ovl_destroy_inode,
+	.drop_inode	= generic_delete_inode,
 	.put_super	= ovl_put_super,
+	.sync_fs	= ovl_sync_fs,
 	.statfs		= ovl_statfs,
 	.show_options	= ovl_show_options,
 	.remount_fs	= ovl_remount,
-	.drop_inode	= generic_delete_inode,
 };
 
 enum {
@@ -235,6 +332,8 @@ enum {
 	OPT_DEFAULT_PERMISSIONS,
 	OPT_REDIRECT_DIR_ON,
 	OPT_REDIRECT_DIR_OFF,
+	OPT_INDEX_ON,
+	OPT_INDEX_OFF,
 	OPT_ERR,
 };
 
@@ -245,6 +344,8 @@ static const match_table_t ovl_tokens = {
 	{OPT_DEFAULT_PERMISSIONS,	"default_permissions"},
 	{OPT_REDIRECT_DIR_ON,		"redirect_dir=on"},
 	{OPT_REDIRECT_DIR_OFF,		"redirect_dir=off"},
+	{OPT_INDEX_ON,			"index=on"},
+	{OPT_INDEX_OFF,			"index=off"},
 	{OPT_ERR,			NULL}
 };
 
@@ -317,6 +418,14 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 			config->redirect_dir = false;
 			break;
 
+		case OPT_INDEX_ON:
+			config->index = true;
+			break;
+
+		case OPT_INDEX_OFF:
+			config->index = false;
+			break;
+
 		default:
 			pr_err("overlayfs: unrecognized mount option \"%s\" or missing value\n", p);
 			return -EINVAL;
@@ -335,23 +444,29 @@ static int ovl_parse_opt(char *opt, struct ovl_config *config)
 }
 
 #define OVL_WORKDIR_NAME "work"
+#define OVL_INDEXDIR_NAME "index"
 
-static struct dentry *ovl_workdir_create(struct vfsmount *mnt,
-					 struct dentry *dentry)
+static struct dentry *ovl_workdir_create(struct super_block *sb,
+					 struct ovl_fs *ufs,
+					 struct dentry *dentry,
+					 const char *name, bool persist)
 {
 	struct inode *dir = dentry->d_inode;
+	struct vfsmount *mnt = ufs->upper_mnt;
 	struct dentry *work;
 	int err;
 	bool retried = false;
+	bool locked = false;
 
 	err = mnt_want_write(mnt);
 	if (err)
-		return ERR_PTR(err);
+		goto out_err;
 
 	inode_lock_nested(dir, I_MUTEX_PARENT);
+	locked = true;
+
 retry:
-	work = lookup_one_len(OVL_WORKDIR_NAME, dentry,
-			      strlen(OVL_WORKDIR_NAME));
+	work = lookup_one_len(name, dentry, strlen(name));
 
 	if (!IS_ERR(work)) {
 		struct iattr attr = {
@@ -364,6 +479,9 @@ retry:
 			if (retried)
 				goto out_dput;
 
+			if (persist)
+				goto out_unlock;
+
 			retried = true;
 			ovl_workdir_cleanup(dir, mnt, work, 0);
 			dput(work);
@@ -403,16 +521,24 @@ retry:
 		inode_unlock(work->d_inode);
 		if (err)
 			goto out_dput;
+	} else {
+		err = PTR_ERR(work);
+		goto out_err;
 	}
 out_unlock:
-	inode_unlock(dir);
 	mnt_drop_write(mnt);
+	if (locked)
+		inode_unlock(dir);
 
 	return work;
 
 out_dput:
 	dput(work);
-	work = ERR_PTR(err);
+out_err:
+	pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n",
+		ufs->config.workdir, name, -err);
+	sb->s_flags |= MS_RDONLY;
+	work = NULL;
 	goto out_unlock;
 }
 
@@ -512,6 +638,15 @@ static int ovl_lower_dir(const char *name, struct path *path,
 	if (ovl_dentry_remote(path->dentry))
 		*remote = true;
 
+	/*
+	 * The inodes index feature needs to encode and decode file
+	 * handles, so it requires that all layers support them.
+	 */
+	if (ofs->config.index && !ovl_can_decode_fh(path->dentry->d_sb)) {
+		ofs->config.index = false;
+		pr_warn("overlayfs: fs on '%s' does not support file handles, falling back to index=off.\n", name);
+	}
+
 	return 0;
 
 out_put:
@@ -557,7 +692,7 @@ ovl_posix_acl_xattr_get(const struct xattr_handler *handler,
 			struct dentry *dentry, struct inode *inode,
 			const char *name, void *buffer, size_t size)
 {
-	return ovl_xattr_get(dentry, handler->name, buffer, size);
+	return ovl_xattr_get(dentry, inode, handler->name, buffer, size);
 }
 
 static int __maybe_unused
@@ -567,7 +702,7 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
 			size_t size, int flags)
 {
 	struct dentry *workdir = ovl_workdir(dentry);
-	struct inode *realinode = ovl_inode_real(inode, NULL);
+	struct inode *realinode = ovl_inode_real(inode);
 	struct posix_acl *acl = NULL;
 	int err;
 
@@ -607,9 +742,9 @@ ovl_posix_acl_xattr_set(const struct xattr_handler *handler,
 			return err;
 	}
 
-	err = ovl_xattr_set(dentry, handler->name, value, size, flags);
+	err = ovl_xattr_set(dentry, inode, handler->name, value, size, flags);
 	if (!err)
-		ovl_copyattr(ovl_inode_real(inode, NULL), inode);
+		ovl_copyattr(ovl_inode_real(inode), inode);
 
 	return err;
 
@@ -637,7 +772,7 @@ static int ovl_other_xattr_get(const struct xattr_handler *handler,
 			       struct dentry *dentry, struct inode *inode,
 			       const char *name, void *buffer, size_t size)
 {
-	return ovl_xattr_get(dentry, name, buffer, size);
+	return ovl_xattr_get(dentry, inode, name, buffer, size);
 }
 
 static int ovl_other_xattr_set(const struct xattr_handler *handler,
@@ -645,7 +780,7 @@ static int ovl_other_xattr_set(const struct xattr_handler *handler,
 			       const char *name, const void *value,
 			       size_t size, int flags)
 {
-	return ovl_xattr_set(dentry, name, value, size, flags);
+	return ovl_xattr_set(dentry, inode, name, value, size, flags);
 }
 
 static const struct xattr_handler __maybe_unused
@@ -688,10 +823,9 @@ static const struct xattr_handler *ovl_xattr_handlers[] = {
 
 static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 {
-	struct path upperpath = { NULL, NULL };
-	struct path workpath = { NULL, NULL };
+	struct path upperpath = { };
+	struct path workpath = { };
 	struct dentry *root_dentry;
-	struct inode *realinode;
 	struct ovl_entry *oe;
 	struct ovl_fs *ufs;
 	struct path *stack = NULL;
@@ -701,6 +835,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	unsigned int stacklen = 0;
 	unsigned int i;
 	bool remote = false;
+	struct cred *cred;
 	int err;
 
 	err = -ENOMEM;
@@ -709,6 +844,7 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		goto out;
 
 	ufs->config.redirect_dir = ovl_redirect_dir_def;
+	ufs->config.index = ovl_index_def;
 	err = ovl_parse_opt((char *) data, &ufs->config);
 	if (err)
 		goto out_free_config;
@@ -743,9 +879,15 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		if (err)
 			goto out_put_upperpath;
 
+		err = -EBUSY;
+		if (!ovl_inuse_trylock(upperpath.dentry)) {
+			pr_err("overlayfs: upperdir is in-use by another mount\n");
+			goto out_put_upperpath;
+		}
+
 		err = ovl_mount_dir(ufs->config.workdir, &workpath);
 		if (err)
-			goto out_put_upperpath;
+			goto out_unlock_upperdentry;
 
 		err = -EINVAL;
 		if (upperpath.mnt != workpath.mnt) {
@@ -756,12 +898,20 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			pr_err("overlayfs: workdir and upperdir must be separate subtrees\n");
 			goto out_put_workpath;
 		}
+
+		err = -EBUSY;
+		if (!ovl_inuse_trylock(workpath.dentry)) {
+			pr_err("overlayfs: workdir is in-use by another mount\n");
+			goto out_put_workpath;
+		}
+
+		ufs->workbasedir = workpath.dentry;
 		sb->s_stack_depth = upperpath.mnt->mnt_sb->s_stack_depth;
 	}
 	err = -ENOMEM;
 	lowertmp = kstrdup(ufs->config.lowerdir, GFP_KERNEL);
 	if (!lowertmp)
-		goto out_put_workpath;
+		goto out_unlock_workdentry;
 
 	err = -EINVAL;
 	stacklen = ovl_split_lowerdirs(lowertmp);
@@ -804,20 +954,14 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			pr_err("overlayfs: failed to clone upperpath\n");
 			goto out_put_lowerpath;
 		}
+
 		/* Don't inherit atime flags */
 		ufs->upper_mnt->mnt_flags &= ~(MNT_NOATIME | MNT_NODIRATIME | MNT_RELATIME);
 
 		sb->s_time_gran = ufs->upper_mnt->mnt_sb->s_time_gran;
 
-		ufs->workdir = ovl_workdir_create(ufs->upper_mnt, workpath.dentry);
-		err = PTR_ERR(ufs->workdir);
-		if (IS_ERR(ufs->workdir)) {
-			pr_warn("overlayfs: failed to create directory %s/%s (errno: %i); mounting read-only\n",
-				ufs->config.workdir, OVL_WORKDIR_NAME, -err);
-			sb->s_flags |= MS_RDONLY;
-			ufs->workdir = NULL;
-		}
-
+		ufs->workdir = ovl_workdir_create(sb, ufs, workpath.dentry,
+						  OVL_WORKDIR_NAME, false);
 		/*
 		 * Upper should support d_type, else whiteouts are visible.
 		 * Given workdir and upper are on same fs, we can do
@@ -825,6 +969,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 		 * creation of workdir in previous step.
 		 */
 		if (ufs->workdir) {
+			struct dentry *temp;
+
 			err = ovl_check_d_type_supported(&workpath);
 			if (err < 0)
 				goto out_put_workdir;
@@ -836,6 +982,34 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 			 */
 			if (!err)
 				pr_warn("overlayfs: upper fs needs to support d_type.\n");
+
+			/* Check if upper/work fs supports O_TMPFILE */
+			temp = ovl_do_tmpfile(ufs->workdir, S_IFREG | 0);
+			ufs->tmpfile = !IS_ERR(temp);
+			if (ufs->tmpfile)
+				dput(temp);
+			else
+				pr_warn("overlayfs: upper fs does not support tmpfile.\n");
+
+			/*
+			 * Check if upper/work fs supports trusted.overlay.*
+			 * xattr
+			 */
+			err = ovl_do_setxattr(ufs->workdir, OVL_XATTR_OPAQUE,
+					      "0", 1, 0);
+			if (err) {
+				ufs->noxattr = true;
+				pr_warn("overlayfs: upper fs does not support xattr.\n");
+			} else {
+				vfs_removexattr(ufs->workdir, OVL_XATTR_OPAQUE);
+			}
+
+			/* Check if upper/work fs supports file handles */
+			if (ufs->config.index &&
+			    !ovl_can_decode_fh(ufs->workdir->d_sb)) {
+				ufs->config.index = false;
+				pr_warn("overlayfs: upper fs does not support file handles, falling back to index=off.\n");
+			}
 		}
 	}
 
@@ -859,20 +1033,66 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 
 		ufs->lower_mnt[ufs->numlower] = mnt;
 		ufs->numlower++;
+
+		/* Check if all lower layers are on same sb */
+		if (i == 0)
+			ufs->same_sb = mnt->mnt_sb;
+		else if (ufs->same_sb != mnt->mnt_sb)
+			ufs->same_sb = NULL;
 	}
 
 	/* If the upper fs is nonexistent, we mark overlayfs r/o too */
 	if (!ufs->upper_mnt)
 		sb->s_flags |= MS_RDONLY;
+	else if (ufs->upper_mnt->mnt_sb != ufs->same_sb)
+		ufs->same_sb = NULL;
+
+	if (!(ovl_force_readonly(ufs)) && ufs->config.index) {
+		/* Verify lower root is upper root origin */
+		err = ovl_verify_origin(upperpath.dentry, ufs->lower_mnt[0],
+					stack[0].dentry, false, true);
+		if (err) {
+			pr_err("overlayfs: failed to verify upper root origin\n");
+			goto out_put_lower_mnt;
+		}
+
+		ufs->indexdir = ovl_workdir_create(sb, ufs, workpath.dentry,
+						   OVL_INDEXDIR_NAME, true);
+		if (ufs->indexdir) {
+			/* Verify upper root is index dir origin */
+			err = ovl_verify_origin(ufs->indexdir, ufs->upper_mnt,
+						upperpath.dentry, true, true);
+			if (err)
+				pr_err("overlayfs: failed to verify index dir origin\n");
+
+			/* Cleanup bad/stale/orphan index entries */
+			if (!err)
+				err = ovl_indexdir_cleanup(ufs->indexdir,
+							   ufs->upper_mnt,
+							   stack, numlower);
+		}
+		if (err || !ufs->indexdir)
+			pr_warn("overlayfs: try deleting index dir or mounting with '-o index=off' to disable inodes index.\n");
+		if (err)
+			goto out_put_indexdir;
+	}
+
+	/* Show index=off/on in /proc/mounts for any of the reasons above */
+	if (!ufs->indexdir)
+		ufs->config.index = false;
 
 	if (remote)
 		sb->s_d_op = &ovl_reval_dentry_operations;
 	else
 		sb->s_d_op = &ovl_dentry_operations;
 
-	ufs->creator_cred = prepare_creds();
-	if (!ufs->creator_cred)
-		goto out_put_lower_mnt;
+	err = -ENOMEM;
+	ufs->creator_cred = cred = prepare_creds();
+	if (!cred)
+		goto out_put_indexdir;
+
+	/* Never override disk quota limits or use reserved space */
+	cap_lower(cred->cap_effective, CAP_SYS_RESOURCE);
 
 	err = -ENOMEM;
 	oe = ovl_alloc_entry(numlower);
@@ -892,10 +1112,14 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 	mntput(upperpath.mnt);
 	for (i = 0; i < numlower; i++)
 		mntput(stack[i].mnt);
-	path_put(&workpath);
+	mntput(workpath.mnt);
 	kfree(lowertmp);
 
-	oe->__upperdentry = upperpath.dentry;
+	if (upperpath.dentry) {
+		oe->has_upper = true;
+		if (ovl_is_impuredir(upperpath.dentry))
+			ovl_set_flag(OVL_IMPURE, d_inode(root_dentry));
+	}
 	for (i = 0; i < numlower; i++) {
 		oe->lowerstack[i].dentry = stack[i].dentry;
 		oe->lowerstack[i].mnt = ufs->lower_mnt[i];
@@ -904,9 +1128,8 @@ static int ovl_fill_super(struct super_block *sb, void *data, int silent)
 
 	root_dentry->d_fsdata = oe;
 
-	realinode = d_inode(ovl_dentry_real(root_dentry));
-	ovl_inode_init(d_inode(root_dentry), realinode, !!upperpath.dentry);
-	ovl_copyattr(realinode, d_inode(root_dentry));
+	ovl_inode_init(d_inode(root_dentry), upperpath.dentry,
+		       ovl_dentry_lower(root_dentry));
 
 	sb->s_root = root_dentry;
 
@@ -916,6 +1139,8 @@ out_free_oe:
 	kfree(oe);
 out_put_cred:
 	put_cred(ufs->creator_cred);
+out_put_indexdir:
+	dput(ufs->indexdir);
 out_put_lower_mnt:
 	for (i = 0; i < ufs->numlower; i++)
 		mntput(ufs->lower_mnt[i]);
@@ -929,8 +1154,12 @@ out_put_lowerpath:
 	kfree(stack);
 out_free_lowertmp:
 	kfree(lowertmp);
+out_unlock_workdentry:
+	ovl_inuse_unlock(workpath.dentry);
 out_put_workpath:
 	path_put(&workpath);
+out_unlock_upperdentry:
+	ovl_inuse_unlock(upperpath.dentry);
 out_put_upperpath:
 	path_put(&upperpath);
 out_free_config:
@@ -956,14 +1185,43 @@ static struct file_system_type ovl_fs_type = {
 };
 MODULE_ALIAS_FS("overlay");
 
+static void ovl_inode_init_once(void *foo)
+{
+	struct ovl_inode *oi = foo;
+
+	inode_init_once(&oi->vfs_inode);
+}
+
 static int __init ovl_init(void)
 {
-	return register_filesystem(&ovl_fs_type);
+	int err;
+
+	ovl_inode_cachep = kmem_cache_create("ovl_inode",
+					     sizeof(struct ovl_inode), 0,
+					     (SLAB_RECLAIM_ACCOUNT|
+					      SLAB_MEM_SPREAD|SLAB_ACCOUNT),
+					     ovl_inode_init_once);
+	if (ovl_inode_cachep == NULL)
+		return -ENOMEM;
+
+	err = register_filesystem(&ovl_fs_type);
+	if (err)
+		kmem_cache_destroy(ovl_inode_cachep);
+
+	return err;
 }
 
 static void __exit ovl_exit(void)
 {
 	unregister_filesystem(&ovl_fs_type);
+
+	/*
+	 * Make sure all delayed rcu free inodes are flushed before we
+	 * destroy cache.
+	 */
+	rcu_barrier();
+	kmem_cache_destroy(ovl_inode_cachep);
+
 }
 
 module_init(ovl_init);
diff --git a/fs/overlayfs/util.c b/fs/overlayfs/util.c
index 952286f4826c..f46ad75dc96a 100644
--- a/fs/overlayfs/util.c
+++ b/fs/overlayfs/util.c
@@ -10,7 +10,12 @@
 #include <linux/fs.h>
 #include <linux/mount.h>
 #include <linux/slab.h>
+#include <linux/cred.h>
 #include <linux/xattr.h>
+#include <linux/exportfs.h>
+#include <linux/uuid.h>
+#include <linux/namei.h>
+#include <linux/ratelimit.h>
 #include "overlayfs.h"
 #include "ovl_entry.h"
 
@@ -39,6 +44,26 @@ const struct cred *ovl_override_creds(struct super_block *sb)
 	return override_creds(ofs->creator_cred);
 }
 
+struct super_block *ovl_same_sb(struct super_block *sb)
+{
+	struct ovl_fs *ofs = sb->s_fs_info;
+
+	return ofs->same_sb;
+}
+
+bool ovl_can_decode_fh(struct super_block *sb)
+{
+	return (sb->s_export_op && sb->s_export_op->fh_to_dentry &&
+		!uuid_is_null(&sb->s_uuid));
+}
+
+struct dentry *ovl_indexdir(struct super_block *sb)
+{
+	struct ovl_fs *ofs = sb->s_fs_info;
+
+	return ofs->indexdir;
+}
+
 struct ovl_entry *ovl_alloc_entry(unsigned int numlower)
 {
 	size_t size = offsetof(struct ovl_entry, lowerstack[numlower]);
@@ -70,15 +95,17 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry)
 	struct ovl_entry *oe = dentry->d_fsdata;
 	enum ovl_path_type type = 0;
 
-	if (oe->__upperdentry) {
+	if (ovl_dentry_upper(dentry)) {
 		type = __OVL_PATH_UPPER;
 
 		/*
-		 * Non-dir dentry can hold lower dentry from previous
-		 * location.
+		 * Non-dir dentry can hold lower dentry of its copy up origin.
 		 */
-		if (oe->numlower && d_is_dir(dentry))
-			type |= __OVL_PATH_MERGE;
+		if (oe->numlower) {
+			type |= __OVL_PATH_ORIGIN;
+			if (d_is_dir(dentry))
+				type |= __OVL_PATH_MERGE;
+		}
 	} else {
 		if (oe->numlower > 1)
 			type |= __OVL_PATH_MERGE;
@@ -89,17 +116,16 @@ enum ovl_path_type ovl_path_type(struct dentry *dentry)
 void ovl_path_upper(struct dentry *dentry, struct path *path)
 {
 	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
-	struct ovl_entry *oe = dentry->d_fsdata;
 
 	path->mnt = ofs->upper_mnt;
-	path->dentry = ovl_upperdentry_dereference(oe);
+	path->dentry = ovl_dentry_upper(dentry);
 }
 
 void ovl_path_lower(struct dentry *dentry, struct path *path)
 {
 	struct ovl_entry *oe = dentry->d_fsdata;
 
-	*path = oe->numlower ? oe->lowerstack[0] : (struct path) { NULL, NULL };
+	*path = oe->numlower ? oe->lowerstack[0] : (struct path) { };
 }
 
 enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
@@ -116,47 +142,52 @@ enum ovl_path_type ovl_path_real(struct dentry *dentry, struct path *path)
 
 struct dentry *ovl_dentry_upper(struct dentry *dentry)
 {
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	return ovl_upperdentry_dereference(oe);
+	return ovl_upperdentry_dereference(OVL_I(d_inode(dentry)));
 }
 
-static struct dentry *__ovl_dentry_lower(struct ovl_entry *oe)
+struct dentry *ovl_dentry_lower(struct dentry *dentry)
 {
+	struct ovl_entry *oe = dentry->d_fsdata;
+
 	return oe->numlower ? oe->lowerstack[0].dentry : NULL;
 }
 
-struct dentry *ovl_dentry_lower(struct dentry *dentry)
+struct dentry *ovl_dentry_real(struct dentry *dentry)
 {
-	struct ovl_entry *oe = dentry->d_fsdata;
+	return ovl_dentry_upper(dentry) ?: ovl_dentry_lower(dentry);
+}
 
-	return __ovl_dentry_lower(oe);
+struct dentry *ovl_i_dentry_upper(struct inode *inode)
+{
+	return ovl_upperdentry_dereference(OVL_I(inode));
 }
 
-struct dentry *ovl_dentry_real(struct dentry *dentry)
+struct inode *ovl_inode_upper(struct inode *inode)
 {
-	struct ovl_entry *oe = dentry->d_fsdata;
-	struct dentry *realdentry;
+	struct dentry *upperdentry = ovl_i_dentry_upper(inode);
+
+	return upperdentry ? d_inode(upperdentry) : NULL;
+}
 
-	realdentry = ovl_upperdentry_dereference(oe);
-	if (!realdentry)
-		realdentry = __ovl_dentry_lower(oe);
+struct inode *ovl_inode_lower(struct inode *inode)
+{
+	return OVL_I(inode)->lower;
+}
 
-	return realdentry;
+struct inode *ovl_inode_real(struct inode *inode)
+{
+	return ovl_inode_upper(inode) ?: ovl_inode_lower(inode);
 }
 
+
 struct ovl_dir_cache *ovl_dir_cache(struct dentry *dentry)
 {
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	return oe->cache;
+	return OVL_I(d_inode(dentry))->cache;
 }
 
 void ovl_set_dir_cache(struct dentry *dentry, struct ovl_dir_cache *cache)
 {
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	oe->cache = cache;
+	OVL_I(d_inode(dentry))->cache = cache;
 }
 
 bool ovl_dentry_is_opaque(struct dentry *dentry)
@@ -177,79 +208,87 @@ void ovl_dentry_set_opaque(struct dentry *dentry)
 	oe->opaque = true;
 }
 
-bool ovl_redirect_dir(struct super_block *sb)
+/*
+ * For hard links it's possible for ovl_dentry_upper() to return positive, while
+ * there's no actual upper alias for the inode.  Copy up code needs to know
+ * about the existence of the upper alias, so it can't use ovl_dentry_upper().
+ */
+bool ovl_dentry_has_upper_alias(struct dentry *dentry)
 {
-	struct ovl_fs *ofs = sb->s_fs_info;
+	struct ovl_entry *oe = dentry->d_fsdata;
+
+	return oe->has_upper;
+}
+
+void ovl_dentry_set_upper_alias(struct dentry *dentry)
+{
+	struct ovl_entry *oe = dentry->d_fsdata;
 
-	return ofs->config.redirect_dir;
+	oe->has_upper = true;
 }
 
-void ovl_clear_redirect_dir(struct super_block *sb)
+bool ovl_redirect_dir(struct super_block *sb)
 {
 	struct ovl_fs *ofs = sb->s_fs_info;
 
-	ofs->config.redirect_dir = false;
+	return ofs->config.redirect_dir && !ofs->noxattr;
 }
 
 const char *ovl_dentry_get_redirect(struct dentry *dentry)
 {
-	struct ovl_entry *oe = dentry->d_fsdata;
-
-	return oe->redirect;
+	return OVL_I(d_inode(dentry))->redirect;
 }
 
 void ovl_dentry_set_redirect(struct dentry *dentry, const char *redirect)
 {
-	struct ovl_entry *oe = dentry->d_fsdata;
+	struct ovl_inode *oi = OVL_I(d_inode(dentry));
 
-	kfree(oe->redirect);
-	oe->redirect = redirect;
+	kfree(oi->redirect);
+	oi->redirect = redirect;
 }
 
-void ovl_dentry_update(struct dentry *dentry, struct dentry *upperdentry)
+void ovl_inode_init(struct inode *inode, struct dentry *upperdentry,
+		    struct dentry *lowerdentry)
 {
-	struct ovl_entry *oe = dentry->d_fsdata;
+	if (upperdentry)
+		OVL_I(inode)->__upperdentry = upperdentry;
+	if (lowerdentry)
+		OVL_I(inode)->lower = d_inode(lowerdentry);
 
-	WARN_ON(!inode_is_locked(upperdentry->d_parent->d_inode));
-	WARN_ON(oe->__upperdentry);
-	/*
-	 * Make sure upperdentry is consistent before making it visible to
-	 * ovl_upperdentry_dereference().
-	 */
-	smp_wmb();
-	oe->__upperdentry = upperdentry;
+	ovl_copyattr(d_inode(upperdentry ?: lowerdentry), inode);
 }
 
-void ovl_inode_init(struct inode *inode, struct inode *realinode, bool is_upper)
+void ovl_inode_update(struct inode *inode, struct dentry *upperdentry)
 {
-	WRITE_ONCE(inode->i_private, (unsigned long) realinode |
-		   (is_upper ? OVL_ISUPPER_MASK : 0));
-}
+	struct inode *upperinode = d_inode(upperdentry);
 
-void ovl_inode_update(struct inode *inode, struct inode *upperinode)
-{
-	WARN_ON(!upperinode);
-	WARN_ON(!inode_unhashed(inode));
-	WRITE_ONCE(inode->i_private,
-		   (unsigned long) upperinode | OVL_ISUPPER_MASK);
-	if (!S_ISDIR(upperinode->i_mode))
+	WARN_ON(OVL_I(inode)->__upperdentry);
+
+	/*
+	 * Make sure upperdentry is consistent before making it visible
+	 */
+	smp_wmb();
+	OVL_I(inode)->__upperdentry = upperdentry;
+	if (!S_ISDIR(upperinode->i_mode) && inode_unhashed(inode)) {
+		inode->i_private = upperinode;
 		__insert_inode_hash(inode, (unsigned long) upperinode);
+	}
 }
 
 void ovl_dentry_version_inc(struct dentry *dentry)
 {
-	struct ovl_entry *oe = dentry->d_fsdata;
+	struct inode *inode = d_inode(dentry);
 
-	WARN_ON(!inode_is_locked(dentry->d_inode));
-	oe->version++;
+	WARN_ON(!inode_is_locked(inode));
+	OVL_I(inode)->version++;
 }
 
 u64 ovl_dentry_version_get(struct dentry *dentry)
 {
-	struct ovl_entry *oe = dentry->d_fsdata;
+	struct inode *inode = d_inode(dentry);
 
-	WARN_ON(!inode_is_locked(dentry->d_inode));
-	return oe->version;
+	WARN_ON(!inode_is_locked(inode));
+	return OVL_I(inode)->version;
 }
 
 bool ovl_is_whiteout(struct dentry *dentry)
@@ -263,3 +302,246 @@ struct file *ovl_path_open(struct path *path, int flags)
 {
 	return dentry_open(path, flags | O_NOATIME, current_cred());
 }
+
+int ovl_copy_up_start(struct dentry *dentry)
+{
+	struct ovl_inode *oi = OVL_I(d_inode(dentry));
+	int err;
+
+	err = mutex_lock_interruptible(&oi->lock);
+	if (!err && ovl_dentry_has_upper_alias(dentry)) {
+		err = 1; /* Already copied up */
+		mutex_unlock(&oi->lock);
+	}
+
+	return err;
+}
+
+void ovl_copy_up_end(struct dentry *dentry)
+{
+	mutex_unlock(&OVL_I(d_inode(dentry))->lock);
+}
+
+bool ovl_check_dir_xattr(struct dentry *dentry, const char *name)
+{
+	int res;
+	char val;
+
+	if (!d_is_dir(dentry))
+		return false;
+
+	res = vfs_getxattr(dentry, name, &val, 1);
+	if (res == 1 && val == 'y')
+		return true;
+
+	return false;
+}
+
+int ovl_check_setxattr(struct dentry *dentry, struct dentry *upperdentry,
+		       const char *name, const void *value, size_t size,
+		       int xerr)
+{
+	int err;
+	struct ovl_fs *ofs = dentry->d_sb->s_fs_info;
+
+	if (ofs->noxattr)
+		return xerr;
+
+	err = ovl_do_setxattr(upperdentry, name, value, size, 0);
+
+	if (err == -EOPNOTSUPP) {
+		pr_warn("overlayfs: cannot set %s xattr on upper\n", name);
+		ofs->noxattr = true;
+		return xerr;
+	}
+
+	return err;
+}
+
+int ovl_set_impure(struct dentry *dentry, struct dentry *upperdentry)
+{
+	int err;
+
+	if (ovl_test_flag(OVL_IMPURE, d_inode(dentry)))
+		return 0;
+
+	/*
+	 * Do not fail when upper doesn't support xattrs.
+	 * Upper inodes won't have origin nor redirect xattr anyway.
+	 */
+	err = ovl_check_setxattr(dentry, upperdentry, OVL_XATTR_IMPURE,
+				 "y", 1, 0);
+	if (!err)
+		ovl_set_flag(OVL_IMPURE, d_inode(dentry));
+
+	return err;
+}
+
+void ovl_set_flag(unsigned long flag, struct inode *inode)
+{
+	set_bit(flag, &OVL_I(inode)->flags);
+}
+
+bool ovl_test_flag(unsigned long flag, struct inode *inode)
+{
+	return test_bit(flag, &OVL_I(inode)->flags);
+}
+
+/**
+ * Caller must hold a reference to inode to prevent it from being freed while
+ * it is marked inuse.
+ */
+bool ovl_inuse_trylock(struct dentry *dentry)
+{
+	struct inode *inode = d_inode(dentry);
+	bool locked = false;
+
+	spin_lock(&inode->i_lock);
+	if (!(inode->i_state & I_OVL_INUSE)) {
+		inode->i_state |= I_OVL_INUSE;
+		locked = true;
+	}
+	spin_unlock(&inode->i_lock);
+
+	return locked;
+}
+
+void ovl_inuse_unlock(struct dentry *dentry)
+{
+	if (dentry) {
+		struct inode *inode = d_inode(dentry);
+
+		spin_lock(&inode->i_lock);
+		WARN_ON(!(inode->i_state & I_OVL_INUSE));
+		inode->i_state &= ~I_OVL_INUSE;
+		spin_unlock(&inode->i_lock);
+	}
+}
+
+/* Called must hold OVL_I(inode)->oi_lock */
+static void ovl_cleanup_index(struct dentry *dentry)
+{
+	struct inode *dir = ovl_indexdir(dentry->d_sb)->d_inode;
+	struct dentry *lowerdentry = ovl_dentry_lower(dentry);
+	struct dentry *upperdentry = ovl_dentry_upper(dentry);
+	struct dentry *index = NULL;
+	struct inode *inode;
+	struct qstr name;
+	int err;
+
+	err = ovl_get_index_name(lowerdentry, &name);
+	if (err)
+		goto fail;
+
+	inode = d_inode(upperdentry);
+	if (inode->i_nlink != 1) {
+		pr_warn_ratelimited("overlayfs: cleanup linked index (%pd2, ino=%lu, nlink=%u)\n",
+				    upperdentry, inode->i_ino, inode->i_nlink);
+		/*
+		 * We either have a bug with persistent union nlink or a lower
+		 * hardlink was added while overlay is mounted. Adding a lower
+		 * hardlink and then unlinking all overlay hardlinks would drop
+		 * overlay nlink to zero before all upper inodes are unlinked.
+		 * As a safety measure, when that situation is detected, set
+		 * the overlay nlink to the index inode nlink minus one for the
+		 * index entry itself.
+		 */
+		set_nlink(d_inode(dentry), inode->i_nlink - 1);
+		ovl_set_nlink_upper(dentry);
+		goto out;
+	}
+
+	inode_lock_nested(dir, I_MUTEX_PARENT);
+	/* TODO: whiteout instead of cleanup to block future open by handle */
+	index = lookup_one_len(name.name, ovl_indexdir(dentry->d_sb), name.len);
+	err = PTR_ERR(index);
+	if (!IS_ERR(index))
+		err = ovl_cleanup(dir, index);
+	inode_unlock(dir);
+	if (err)
+		goto fail;
+
+out:
+	dput(index);
+	return;
+
+fail:
+	pr_err("overlayfs: cleanup index of '%pd2' failed (%i)\n", dentry, err);
+	goto out;
+}
+
+/*
+ * Operations that change overlay inode and upper inode nlink need to be
+ * synchronized with copy up for persistent nlink accounting.
+ */
+int ovl_nlink_start(struct dentry *dentry, bool *locked)
+{
+	struct ovl_inode *oi = OVL_I(d_inode(dentry));
+	const struct cred *old_cred;
+	int err;
+
+	if (!d_inode(dentry) || d_is_dir(dentry))
+		return 0;
+
+	/*
+	 * With inodes index is enabled, we store the union overlay nlink
+	 * in an xattr on the index inode. When whiting out lower hardlinks
+	 * we need to decrement the overlay persistent nlink, but before the
+	 * first copy up, we have no upper index inode to store the xattr.
+	 *
+	 * As a workaround, before whiteout/rename over of a lower hardlink,
+	 * copy up to create the upper index. Creating the upper index will
+	 * initialize the overlay nlink, so it could be dropped if unlink
+	 * or rename succeeds.
+	 *
+	 * TODO: implement metadata only index copy up when called with
+	 *       ovl_copy_up_flags(dentry, O_PATH).
+	 */
+	if (ovl_indexdir(dentry->d_sb) && !ovl_dentry_has_upper_alias(dentry) &&
+	    d_inode(ovl_dentry_lower(dentry))->i_nlink > 1) {
+		err = ovl_copy_up(dentry);
+		if (err)
+			return err;
+	}
+
+	err = mutex_lock_interruptible(&oi->lock);
+	if (err)
+		return err;
+
+	if (!ovl_test_flag(OVL_INDEX, d_inode(dentry)))
+		goto out;
+
+	old_cred = ovl_override_creds(dentry->d_sb);
+	/*
+	 * The overlay inode nlink should be incremented/decremented IFF the
+	 * upper operation succeeds, along with nlink change of upper inode.
+	 * Therefore, before link/unlink/rename, we store the union nlink
+	 * value relative to the upper inode nlink in an upper inode xattr.
+	 */
+	err = ovl_set_nlink_upper(dentry);
+	revert_creds(old_cred);
+
+out:
+	if (err)
+		mutex_unlock(&oi->lock);
+	else
+		*locked = true;
+
+	return err;
+}
+
+void ovl_nlink_end(struct dentry *dentry, bool locked)
+{
+	if (locked) {
+		if (ovl_test_flag(OVL_INDEX, d_inode(dentry)) &&
+		    d_inode(dentry)->i_nlink == 0) {
+			const struct cred *old_cred;
+
+			old_cred = ovl_override_creds(dentry->d_sb);
+			ovl_cleanup_index(dentry);
+			revert_creds(old_cred);
+		}
+
+		mutex_unlock(&OVL_I(d_inode(dentry))->lock);
+	}
+}
diff --git a/fs/pipe.c b/fs/pipe.c
index 73b84baf58f8..97e5be897753 100644
--- a/fs/pipe.c
+++ b/fs/pipe.c
@@ -739,13 +739,12 @@ int create_pipe_files(struct file **res, int flags)
 	struct inode *inode = get_pipe_inode();
 	struct file *f;
 	struct path path;
-	static struct qstr name = { .name = "" };
 
 	if (!inode)
 		return -ENFILE;
 
 	err = -ENOMEM;
-	path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &name);
+	path.dentry = d_alloc_pseudo(pipe_mnt->mnt_sb, &empty_name);
 	if (!path.dentry)
 		goto err_inode;
 	path.mnt = mntget(pipe_mnt);
diff --git a/fs/pnode.c b/fs/pnode.c
index 06a793f4ae38..53d411a371ce 100644
--- a/fs/pnode.c
+++ b/fs/pnode.c
@@ -24,6 +24,11 @@ static inline struct mount *first_slave(struct mount *p)
 	return list_entry(p->mnt_slave_list.next, struct mount, mnt_slave);
 }
 
+static inline struct mount *last_slave(struct mount *p)
+{
+	return list_entry(p->mnt_slave_list.prev, struct mount, mnt_slave);
+}
+
 static inline struct mount *next_slave(struct mount *p)
 {
 	return list_entry(p->mnt_slave.next, struct mount, mnt_slave);
@@ -162,6 +167,19 @@ static struct mount *propagation_next(struct mount *m,
 	}
 }
 
+static struct mount *skip_propagation_subtree(struct mount *m,
+						struct mount *origin)
+{
+	/*
+	 * Advance m such that propagation_next will not return
+	 * the slaves of m.
+	 */
+	if (!IS_MNT_NEW(m) && !list_empty(&m->mnt_slave_list))
+		m = last_slave(m);
+
+	return m;
+}
+
 static struct mount *next_group(struct mount *m, struct mount *origin)
 {
 	while (1) {
@@ -322,6 +340,21 @@ out:
 	return ret;
 }
 
+static struct mount *find_topper(struct mount *mnt)
+{
+	/* If there is exactly one mount covering mnt completely return it. */
+	struct mount *child;
+
+	if (!list_is_singular(&mnt->mnt_mounts))
+		return NULL;
+
+	child = list_first_entry(&mnt->mnt_mounts, struct mount, mnt_child);
+	if (child->mnt_mountpoint != mnt->mnt.mnt_root)
+		return NULL;
+
+	return child;
+}
+
 /*
  * return true if the refcount is greater than count
  */
@@ -342,9 +375,8 @@ static inline int do_refcount_check(struct mount *mnt, int count)
  */
 int propagate_mount_busy(struct mount *mnt, int refcnt)
 {
-	struct mount *m, *child;
+	struct mount *m, *child, *topper;
 	struct mount *parent = mnt->mnt_parent;
-	int ret = 0;
 
 	if (mnt == parent)
 		return do_refcount_check(mnt, refcnt);
@@ -359,12 +391,24 @@ int propagate_mount_busy(struct mount *mnt, int refcnt)
 
 	for (m = propagation_next(parent, parent); m;
 	     		m = propagation_next(m, parent)) {
-		child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint);
-		if (child && list_empty(&child->mnt_mounts) &&
-		    (ret = do_refcount_check(child, 1)))
-			break;
+		int count = 1;
+		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
+		if (!child)
+			continue;
+
+		/* Is there exactly one mount on the child that covers
+		 * it completely whose reference should be ignored?
+		 */
+		topper = find_topper(child);
+		if (topper)
+			count += 1;
+		else if (!list_empty(&child->mnt_mounts))
+			continue;
+
+		if (do_refcount_check(child, count))
+			return 1;
 	}
-	return ret;
+	return 0;
 }
 
 /*
@@ -381,60 +425,110 @@ void propagate_mount_unlock(struct mount *mnt)
 
 	for (m = propagation_next(parent, parent); m;
 			m = propagation_next(m, parent)) {
-		child = __lookup_mnt_last(&m->mnt, mnt->mnt_mountpoint);
+		child = __lookup_mnt(&m->mnt, mnt->mnt_mountpoint);
 		if (child)
 			child->mnt.mnt_flags &= ~MNT_LOCKED;
 	}
 }
 
-/*
- * Mark all mounts that the MNT_LOCKED logic will allow to be unmounted.
- */
-static void mark_umount_candidates(struct mount *mnt)
+static void umount_one(struct mount *mnt, struct list_head *to_umount)
 {
-	struct mount *parent = mnt->mnt_parent;
-	struct mount *m;
-
-	BUG_ON(parent == mnt);
-
-	for (m = propagation_next(parent, parent); m;
-			m = propagation_next(m, parent)) {
-		struct mount *child = __lookup_mnt_last(&m->mnt,
-						mnt->mnt_mountpoint);
-		if (child && (!IS_MNT_LOCKED(child) || IS_MNT_MARKED(m))) {
-			SET_MNT_MARK(child);
-		}
-	}
+	CLEAR_MNT_MARK(mnt);
+	mnt->mnt.mnt_flags |= MNT_UMOUNT;
+	list_del_init(&mnt->mnt_child);
+	list_del_init(&mnt->mnt_umounting);
+	list_move_tail(&mnt->mnt_list, to_umount);
 }
 
 /*
  * NOTE: unmounting 'mnt' naturally propagates to all other mounts its
  * parent propagates to.
  */
-static void __propagate_umount(struct mount *mnt)
+static bool __propagate_umount(struct mount *mnt,
+			       struct list_head *to_umount,
+			       struct list_head *to_restore)
 {
-	struct mount *parent = mnt->mnt_parent;
-	struct mount *m;
-
-	BUG_ON(parent == mnt);
+	bool progress = false;
+	struct mount *child;
 
-	for (m = propagation_next(parent, parent); m;
-			m = propagation_next(m, parent)) {
+	/*
+	 * The state of the parent won't change if this mount is
+	 * already unmounted or marked as without children.
+	 */
+	if (mnt->mnt.mnt_flags & (MNT_UMOUNT | MNT_MARKED))
+		goto out;
 
-		struct mount *child = __lookup_mnt_last(&m->mnt,
-						mnt->mnt_mountpoint);
-		/*
-		 * umount the child only if the child has no children
-		 * and the child is marked safe to unmount.
-		 */
-		if (!child || !IS_MNT_MARKED(child))
+	/* Verify topper is the only grandchild that has not been
+	 * speculatively unmounted.
+	 */
+	list_for_each_entry(child, &mnt->mnt_mounts, mnt_child) {
+		if (child->mnt_mountpoint == mnt->mnt.mnt_root)
+			continue;
+		if (!list_empty(&child->mnt_umounting) && IS_MNT_MARKED(child))
 			continue;
-		CLEAR_MNT_MARK(child);
-		if (list_empty(&child->mnt_mounts)) {
-			list_del_init(&child->mnt_child);
-			child->mnt.mnt_flags |= MNT_UMOUNT;
-			list_move_tail(&child->mnt_list, &mnt->mnt_list);
+		/* Found a mounted child */
+		goto children;
+	}
+
+	/* Mark mounts that can be unmounted if not locked */
+	SET_MNT_MARK(mnt);
+	progress = true;
+
+	/* If a mount is without children and not locked umount it. */
+	if (!IS_MNT_LOCKED(mnt)) {
+		umount_one(mnt, to_umount);
+	} else {
+children:
+		list_move_tail(&mnt->mnt_umounting, to_restore);
+	}
+out:
+	return progress;
+}
+
+static void umount_list(struct list_head *to_umount,
+			struct list_head *to_restore)
+{
+	struct mount *mnt, *child, *tmp;
+	list_for_each_entry(mnt, to_umount, mnt_list) {
+		list_for_each_entry_safe(child, tmp, &mnt->mnt_mounts, mnt_child) {
+			/* topper? */
+			if (child->mnt_mountpoint == mnt->mnt.mnt_root)
+				list_move_tail(&child->mnt_umounting, to_restore);
+			else
+				umount_one(child, to_umount);
+		}
+	}
+}
+
+static void restore_mounts(struct list_head *to_restore)
+{
+	/* Restore mounts to a clean working state */
+	while (!list_empty(to_restore)) {
+		struct mount *mnt, *parent;
+		struct mountpoint *mp;
+
+		mnt = list_first_entry(to_restore, struct mount, mnt_umounting);
+		CLEAR_MNT_MARK(mnt);
+		list_del_init(&mnt->mnt_umounting);
+
+		/* Should this mount be reparented? */
+		mp = mnt->mnt_mp;
+		parent = mnt->mnt_parent;
+		while (parent->mnt.mnt_flags & MNT_UMOUNT) {
+			mp = parent->mnt_mp;
+			parent = parent->mnt_parent;
 		}
+		if (parent != mnt->mnt_parent)
+			mnt_change_mountpoint(parent, mp, mnt);
+	}
+}
+
+static void cleanup_umount_visitations(struct list_head *visited)
+{
+	while (!list_empty(visited)) {
+		struct mount *mnt =
+			list_first_entry(visited, struct mount, mnt_umounting);
+		list_del_init(&mnt->mnt_umounting);
 	}
 }
 
@@ -448,11 +542,68 @@ static void __propagate_umount(struct mount *mnt)
 int propagate_umount(struct list_head *list)
 {
 	struct mount *mnt;
+	LIST_HEAD(to_restore);
+	LIST_HEAD(to_umount);
+	LIST_HEAD(visited);
+
+	/* Find candidates for unmounting */
+	list_for_each_entry_reverse(mnt, list, mnt_list) {
+		struct mount *parent = mnt->mnt_parent;
+		struct mount *m;
+
+		/*
+		 * If this mount has already been visited it is known that it's
+		 * entire peer group and all of their slaves in the propagation
+		 * tree for the mountpoint has already been visited and there is
+		 * no need to visit them again.
+		 */
+		if (!list_empty(&mnt->mnt_umounting))
+			continue;
+
+		list_add_tail(&mnt->mnt_umounting, &visited);
+		for (m = propagation_next(parent, parent); m;
+		     m = propagation_next(m, parent)) {
+			struct mount *child = __lookup_mnt(&m->mnt,
+							   mnt->mnt_mountpoint);
+			if (!child)
+				continue;
+
+			if (!list_empty(&child->mnt_umounting)) {
+				/*
+				 * If the child has already been visited it is
+				 * know that it's entire peer group and all of
+				 * their slaves in the propgation tree for the
+				 * mountpoint has already been visited and there
+				 * is no need to visit this subtree again.
+				 */
+				m = skip_propagation_subtree(m, parent);
+				continue;
+			} else if (child->mnt.mnt_flags & MNT_UMOUNT) {
+				/*
+				 * We have come accross an partially unmounted
+				 * mount in list that has not been visited yet.
+				 * Remember it has been visited and continue
+				 * about our merry way.
+				 */
+				list_add_tail(&child->mnt_umounting, &visited);
+				continue;
+			}
+
+			/* Check the child and parents while progress is made */
+			while (__propagate_umount(child,
+						  &to_umount, &to_restore)) {
+				/* Is the parent a umount candidate? */
+				child = child->mnt_parent;
+				if (list_empty(&child->mnt_umounting))
+					break;
+			}
+		}
+	}
 
-	list_for_each_entry_reverse(mnt, list, mnt_list)
-		mark_umount_candidates(mnt);
+	umount_list(&to_umount, &to_restore);
+	restore_mounts(&to_restore);
+	cleanup_umount_visitations(&visited);
+	list_splice_tail(&to_umount, list);
 
-	list_for_each_entry(mnt, list, mnt_list)
-		__propagate_umount(mnt);
 	return 0;
 }
diff --git a/fs/pnode.h b/fs/pnode.h
index 550f5a8b4fcf..dc87e65becd2 100644
--- a/fs/pnode.h
+++ b/fs/pnode.h
@@ -49,6 +49,8 @@ int get_dominating_id(struct mount *mnt, const struct path *root);
 unsigned int mnt_get_count(struct mount *mnt);
 void mnt_set_mountpoint(struct mount *, struct mountpoint *,
 			struct mount *);
+void mnt_change_mountpoint(struct mount *parent, struct mountpoint *mp,
+			   struct mount *mnt);
 struct mount *copy_tree(struct mount *, struct dentry *, int);
 bool is_path_reachable(struct mount *, struct dentry *,
 			 const struct path *root);
diff --git a/fs/posix_acl.c b/fs/posix_acl.c
index c9d48dc78495..eebf5f6cf6d5 100644
--- a/fs/posix_acl.c
+++ b/fs/posix_acl.c
@@ -15,6 +15,7 @@
 #include <linux/atomic.h>
 #include <linux/fs.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/posix_acl.h>
 #include <linux/posix_acl_xattr.h>
 #include <linux/xattr.h>
diff --git a/fs/proc/array.c b/fs/proc/array.c
index 51a4213afa2e..88c355574aa0 100644
--- a/fs/proc/array.c
+++ b/fs/proc/array.c
@@ -60,6 +60,10 @@
 #include <linux/tty.h>
 #include <linux/string.h>
 #include <linux/mman.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/numa_balancing.h>
+#include <linux/sched/task.h>
+#include <linux/sched/cputime.h>
 #include <linux/proc_fs.h>
 #include <linux/ioport.h>
 #include <linux/uaccess.h>
@@ -401,8 +405,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	unsigned long long start_time;
 	unsigned long cmin_flt = 0, cmaj_flt = 0;
 	unsigned long  min_flt = 0,  maj_flt = 0;
-	cputime_t cutime, cstime, utime, stime;
-	cputime_t cgtime, gtime;
+	u64 cutime, cstime, utime, stime;
+	u64 cgtime, gtime;
 	unsigned long rsslim = 0;
 	char tcomm[sizeof(task->comm)];
 	unsigned long flags;
@@ -497,10 +501,10 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	seq_put_decimal_ull(m, " ", cmin_flt);
 	seq_put_decimal_ull(m, " ", maj_flt);
 	seq_put_decimal_ull(m, " ", cmaj_flt);
-	seq_put_decimal_ull(m, " ", cputime_to_clock_t(utime));
-	seq_put_decimal_ull(m, " ", cputime_to_clock_t(stime));
-	seq_put_decimal_ll(m, " ", cputime_to_clock_t(cutime));
-	seq_put_decimal_ll(m, " ", cputime_to_clock_t(cstime));
+	seq_put_decimal_ull(m, " ", nsec_to_clock_t(utime));
+	seq_put_decimal_ull(m, " ", nsec_to_clock_t(stime));
+	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cutime));
+	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cstime));
 	seq_put_decimal_ll(m, " ", priority);
 	seq_put_decimal_ll(m, " ", nice);
 	seq_put_decimal_ll(m, " ", num_threads);
@@ -542,8 +546,8 @@ static int do_task_stat(struct seq_file *m, struct pid_namespace *ns,
 	seq_put_decimal_ull(m, " ", task->rt_priority);
 	seq_put_decimal_ull(m, " ", task->policy);
 	seq_put_decimal_ull(m, " ", delayacct_blkio_ticks(task));
-	seq_put_decimal_ull(m, " ", cputime_to_clock_t(gtime));
-	seq_put_decimal_ll(m, " ", cputime_to_clock_t(cgtime));
+	seq_put_decimal_ull(m, " ", nsec_to_clock_t(gtime));
+	seq_put_decimal_ll(m, " ", nsec_to_clock_t(cgtime));
 
 	if (mm && permitted) {
 		seq_put_decimal_ull(m, " ", mm->start_data);
diff --git a/fs/proc/base.c b/fs/proc/base.c
index 87c9a9aacda3..719c2e943ea1 100644
--- a/fs/proc/base.c
+++ b/fs/proc/base.c
@@ -85,6 +85,11 @@
 #include <linux/user_namespace.h>
 #include <linux/fs_struct.h>
 #include <linux/slab.h>
+#include <linux/sched/autogroup.h>
+#include <linux/sched/mm.h>
+#include <linux/sched/coredump.h>
+#include <linux/sched/debug.h>
+#include <linux/sched/stat.h>
 #include <linux/flex_array.h>
 #include <linux/posix-timers.h>
 #ifdef CONFIG_HARDWALL
@@ -292,101 +297,69 @@ static ssize_t proc_pid_cmdline_read(struct file *file, char __user *buf,
 		}
 	} else {
 		/*
-		 * Command line (1 string) occupies ARGV and maybe
-		 * extends into ENVP.
-		 */
-		if (len1 + len2 <= *pos)
-			goto skip_argv_envp;
-		if (len1 <= *pos)
-			goto skip_argv;
-
-		p = arg_start + *pos;
-		len = len1 - *pos;
-		while (count > 0 && len > 0) {
-			unsigned int _count, l;
-			int nr_read;
-			bool final;
-
-			_count = min3(count, len, PAGE_SIZE);
-			nr_read = access_remote_vm(mm, p, page, _count, 0);
-			if (nr_read < 0)
-				rv = nr_read;
-			if (nr_read <= 0)
-				goto out_free_page;
-
-			/*
-			 * Command line can be shorter than whole ARGV
-			 * even if last "marker" byte says it is not.
-			 */
-			final = false;
-			l = strnlen(page, nr_read);
-			if (l < nr_read) {
-				nr_read = l;
-				final = true;
-			}
-
-			if (copy_to_user(buf, page, nr_read)) {
-				rv = -EFAULT;
-				goto out_free_page;
-			}
-
-			p	+= nr_read;
-			len	-= nr_read;
-			buf	+= nr_read;
-			count	-= nr_read;
-			rv	+= nr_read;
-
-			if (final)
-				goto out_free_page;
-		}
-skip_argv:
-		/*
 		 * Command line (1 string) occupies ARGV and
 		 * extends into ENVP.
 		 */
-		if (len1 <= *pos) {
-			p = env_start + *pos - len1;
-			len = len1 + len2 - *pos;
-		} else {
-			p = env_start;
-			len = len2;
+		struct {
+			unsigned long p;
+			unsigned long len;
+		} cmdline[2] = {
+			{ .p = arg_start, .len = len1 },
+			{ .p = env_start, .len = len2 },
+		};
+		loff_t pos1 = *pos;
+		unsigned int i;
+
+		i = 0;
+		while (i < 2 && pos1 >= cmdline[i].len) {
+			pos1 -= cmdline[i].len;
+			i++;
 		}
-		while (count > 0 && len > 0) {
-			unsigned int _count, l;
-			int nr_read;
-			bool final;
-
-			_count = min3(count, len, PAGE_SIZE);
-			nr_read = access_remote_vm(mm, p, page, _count, 0);
-			if (nr_read < 0)
-				rv = nr_read;
-			if (nr_read <= 0)
-				goto out_free_page;
-
-			/* Find EOS. */
-			final = false;
-			l = strnlen(page, nr_read);
-			if (l < nr_read) {
-				nr_read = l;
-				final = true;
-			}
-
-			if (copy_to_user(buf, page, nr_read)) {
-				rv = -EFAULT;
-				goto out_free_page;
+		while (i < 2) {
+			p = cmdline[i].p + pos1;
+			len = cmdline[i].len - pos1;
+			while (count > 0 && len > 0) {
+				unsigned int _count, l;
+				int nr_read;
+				bool final;
+
+				_count = min3(count, len, PAGE_SIZE);
+				nr_read = access_remote_vm(mm, p, page, _count, 0);
+				if (nr_read < 0)
+					rv = nr_read;
+				if (nr_read <= 0)
+					goto out_free_page;
+
+				/*
+				 * Command line can be shorter than whole ARGV
+				 * even if last "marker" byte says it is not.
+				 */
+				final = false;
+				l = strnlen(page, nr_read);
+				if (l < nr_read) {
+					nr_read = l;
+					final = true;
+				}
+
+				if (copy_to_user(buf, page, nr_read)) {
+					rv = -EFAULT;
+					goto out_free_page;
+				}
+
+				p	+= nr_read;
+				len	-= nr_read;
+				buf	+= nr_read;
+				count	-= nr_read;
+				rv	+= nr_read;
+
+				if (final)
+					goto out_free_page;
 			}
 
-			p	+= nr_read;
-			len	-= nr_read;
-			buf	+= nr_read;
-			count	-= nr_read;
-			rv	+= nr_read;
-
-			if (final)
-				goto out_free_page;
+			/* Only first chunk can be read partially. */
+			pos1 = 0;
+			i++;
 		}
-skip_argv_envp:
-		;
 	}
 
 out_free_page:
@@ -729,11 +702,11 @@ static int proc_pid_permission(struct inode *inode, int mask)
 	task = get_proc_task(inode);
 	if (!task)
 		return -ESRCH;
-	has_perms = has_pid_permissions(pid, task, 1);
+	has_perms = has_pid_permissions(pid, task, HIDEPID_NO_ACCESS);
 	put_task_struct(task);
 
 	if (!has_perms) {
-		if (pid->hide_pid == 2) {
+		if (pid->hide_pid == HIDEPID_INVISIBLE) {
 			/*
 			 * Let's make getdents(), stat(), and open()
 			 * consistent with each other.  If a process
@@ -798,7 +771,7 @@ struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode)
 
 		if (!IS_ERR_OR_NULL(mm)) {
 			/* ensure this mm_struct can't be freed */
-			atomic_inc(&mm->mm_count);
+			mmgrab(mm);
 			/* but do not pin its memory */
 			mmput(mm);
 		}
@@ -845,13 +818,10 @@ static ssize_t mem_rw(struct file *file, char __user *buf,
 		return -ENOMEM;
 
 	copied = 0;
-	if (!atomic_inc_not_zero(&mm->mm_users))
+	if (!mmget_not_zero(mm))
 		goto free;
 
-	/* Maybe we should limit FOLL_FORCE to actual ptrace users? */
-	flags = FOLL_FORCE;
-	if (write)
-		flags |= FOLL_WRITE;
+	flags = FOLL_FORCE | (write ? FOLL_WRITE : 0);
 
 	while (count > 0) {
 		int this_len = min_t(int, count, PAGE_SIZE);
@@ -953,7 +923,7 @@ static ssize_t environ_read(struct file *file, char __user *buf,
 		return -ENOMEM;
 
 	ret = 0;
-	if (!atomic_inc_not_zero(&mm->mm_users))
+	if (!mmget_not_zero(mm))
 		goto free;
 
 	down_read(&mm->mmap_sem);
@@ -1096,7 +1066,7 @@ static int __set_oom_adj(struct file *file, int oom_adj, bool legacy)
 		if (p) {
 			if (atomic_read(&p->mm->mm_users) > 1) {
 				mm = p->mm;
-				atomic_inc(&mm->mm_count);
+				mmgrab(mm);
 			}
 			task_unlock(p);
 		}
@@ -1385,6 +1355,49 @@ static const struct file_operations proc_fault_inject_operations = {
 	.write		= proc_fault_inject_write,
 	.llseek		= generic_file_llseek,
 };
+
+static ssize_t proc_fail_nth_write(struct file *file, const char __user *buf,
+				   size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	int err;
+	unsigned int n;
+
+	err = kstrtouint_from_user(buf, count, 0, &n);
+	if (err)
+		return err;
+
+	task = get_proc_task(file_inode(file));
+	if (!task)
+		return -ESRCH;
+	WRITE_ONCE(task->fail_nth, n);
+	put_task_struct(task);
+
+	return count;
+}
+
+static ssize_t proc_fail_nth_read(struct file *file, char __user *buf,
+				  size_t count, loff_t *ppos)
+{
+	struct task_struct *task;
+	char numbuf[PROC_NUMBUF];
+	ssize_t len;
+
+	task = get_proc_task(file_inode(file));
+	if (!task)
+		return -ESRCH;
+	len = snprintf(numbuf, sizeof(numbuf), "%u\n",
+			READ_ONCE(task->fail_nth));
+	len = simple_read_from_buffer(buf, count, ppos, numbuf, len);
+	put_task_struct(task);
+
+	return len;
+}
+
+static const struct file_operations proc_fail_nth_operations = {
+	.read		= proc_fail_nth_read,
+	.write		= proc_fail_nth_write,
+};
 #endif
 
 
@@ -1667,12 +1680,63 @@ const struct inode_operations proc_pid_link_inode_operations = {
 
 /* building an inode */
 
+void task_dump_owner(struct task_struct *task, mode_t mode,
+		     kuid_t *ruid, kgid_t *rgid)
+{
+	/* Depending on the state of dumpable compute who should own a
+	 * proc file for a task.
+	 */
+	const struct cred *cred;
+	kuid_t uid;
+	kgid_t gid;
+
+	/* Default to the tasks effective ownership */
+	rcu_read_lock();
+	cred = __task_cred(task);
+	uid = cred->euid;
+	gid = cred->egid;
+	rcu_read_unlock();
+
+	/*
+	 * Before the /proc/pid/status file was created the only way to read
+	 * the effective uid of a /process was to stat /proc/pid.  Reading
+	 * /proc/pid/status is slow enough that procps and other packages
+	 * kept stating /proc/pid.  To keep the rules in /proc simple I have
+	 * made this apply to all per process world readable and executable
+	 * directories.
+	 */
+	if (mode != (S_IFDIR|S_IRUGO|S_IXUGO)) {
+		struct mm_struct *mm;
+		task_lock(task);
+		mm = task->mm;
+		/* Make non-dumpable tasks owned by some root */
+		if (mm) {
+			if (get_dumpable(mm) != SUID_DUMP_USER) {
+				struct user_namespace *user_ns = mm->user_ns;
+
+				uid = make_kuid(user_ns, 0);
+				if (!uid_valid(uid))
+					uid = GLOBAL_ROOT_UID;
+
+				gid = make_kgid(user_ns, 0);
+				if (!gid_valid(gid))
+					gid = GLOBAL_ROOT_GID;
+			}
+		} else {
+			uid = GLOBAL_ROOT_UID;
+			gid = GLOBAL_ROOT_GID;
+		}
+		task_unlock(task);
+	}
+	*ruid = uid;
+	*rgid = gid;
+}
+
 struct inode *proc_pid_make_inode(struct super_block * sb,
 				  struct task_struct *task, umode_t mode)
 {
 	struct inode * inode;
 	struct proc_inode *ei;
-	const struct cred *cred;
 
 	/* We need a new inode */
 
@@ -1694,13 +1758,7 @@ struct inode *proc_pid_make_inode(struct super_block * sb,
 	if (!ei->pid)
 		goto out_unlock;
 
-	if (task_dumpable(task)) {
-		rcu_read_lock();
-		cred = __task_cred(task);
-		inode->i_uid = cred->euid;
-		inode->i_gid = cred->egid;
-		rcu_read_unlock();
-	}
+	task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
 	security_task_to_inode(task, inode);
 
 out:
@@ -1711,12 +1769,12 @@ out_unlock:
 	return NULL;
 }
 
-int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int pid_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct task_struct *task;
-	const struct cred *cred;
-	struct pid_namespace *pid = dentry->d_sb->s_fs_info;
+	struct pid_namespace *pid = path->dentry->d_sb->s_fs_info;
 
 	generic_fillattr(inode, stat);
 
@@ -1725,7 +1783,7 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 	stat->gid = GLOBAL_ROOT_GID;
 	task = pid_task(proc_pid(inode), PIDTYPE_PID);
 	if (task) {
-		if (!has_pid_permissions(pid, task, 2)) {
+		if (!has_pid_permissions(pid, task, HIDEPID_INVISIBLE)) {
 			rcu_read_unlock();
 			/*
 			 * This doesn't prevent learning whether PID exists,
@@ -1733,12 +1791,7 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
 			 */
 			return -ENOENT;
 		}
-		if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
-		    task_dumpable(task)) {
-			cred = __task_cred(task);
-			stat->uid = cred->euid;
-			stat->gid = cred->egid;
-		}
+		task_dump_owner(task, inode->i_mode, &stat->uid, &stat->gid);
 	}
 	rcu_read_unlock();
 	return 0;
@@ -1754,18 +1807,11 @@ int pid_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
  * Rewrite the inode's ownerships here because the owning task may have
  * performed a setuid(), etc.
  *
- * Before the /proc/pid/status file was created the only way to read
- * the effective uid of a /process was to stat /proc/pid.  Reading
- * /proc/pid/status is slow enough that procps and other packages
- * kept stating /proc/pid.  To keep the rules in /proc simple I have
- * made this apply to all per process world readable and executable
- * directories.
  */
 int pid_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct inode *inode;
 	struct task_struct *task;
-	const struct cred *cred;
 
 	if (flags & LOOKUP_RCU)
 		return -ECHILD;
@@ -1774,17 +1820,8 @@ int pid_revalidate(struct dentry *dentry, unsigned int flags)
 	task = get_proc_task(inode);
 
 	if (task) {
-		if ((inode->i_mode == (S_IFDIR|S_IRUGO|S_IXUGO)) ||
-		    task_dumpable(task)) {
-			rcu_read_lock();
-			cred = __task_cred(task);
-			inode->i_uid = cred->euid;
-			inode->i_gid = cred->egid;
-			rcu_read_unlock();
-		} else {
-			inode->i_uid = GLOBAL_ROOT_UID;
-			inode->i_gid = GLOBAL_ROOT_GID;
-		}
+		task_dump_owner(task, inode->i_mode, &inode->i_uid, &inode->i_gid);
+
 		inode->i_mode &= ~(S_ISUID | S_ISGID);
 		security_task_to_inode(task, inode);
 		put_task_struct(task);
@@ -1881,7 +1918,6 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
 	bool exact_vma_exists = false;
 	struct mm_struct *mm = NULL;
 	struct task_struct *task;
-	const struct cred *cred;
 	struct inode *inode;
 	int status = 0;
 
@@ -1906,16 +1942,8 @@ static int map_files_d_revalidate(struct dentry *dentry, unsigned int flags)
 	mmput(mm);
 
 	if (exact_vma_exists) {
-		if (task_dumpable(task)) {
-			rcu_read_lock();
-			cred = __task_cred(task);
-			inode->i_uid = cred->euid;
-			inode->i_gid = cred->egid;
-			rcu_read_unlock();
-		} else {
-			inode->i_uid = GLOBAL_ROOT_UID;
-			inode->i_gid = GLOBAL_ROOT_GID;
-		}
+		task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
+
 		security_task_to_inode(task, inode);
 		status = 1;
 	}
@@ -2179,7 +2207,7 @@ static const struct file_operations proc_map_files_operations = {
 	.llseek		= generic_file_llseek,
 };
 
-#ifdef CONFIG_CHECKPOINT_RESTORE
+#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS)
 struct timers_private {
 	struct pid *pid;
 	struct task_struct *task;
@@ -2488,6 +2516,12 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
 	length = -ESRCH;
 	if (!task)
 		goto out_no_task;
+
+	/* A task may only write its own attributes. */
+	length = -EACCES;
+	if (current != task)
+		goto out;
+
 	if (count > PAGE_SIZE)
 		count = PAGE_SIZE;
 
@@ -2503,14 +2537,13 @@ static ssize_t proc_pid_attr_write(struct file * file, const char __user * buf,
 	}
 
 	/* Guard against adverse ptrace interaction */
-	length = mutex_lock_interruptible(&task->signal->cred_guard_mutex);
+	length = mutex_lock_interruptible(&current->signal->cred_guard_mutex);
 	if (length < 0)
 		goto out_free;
 
-	length = security_setprocattr(task,
-				      (char*)file->f_path.dentry->d_name.name,
+	length = security_setprocattr(file->f_path.dentry->d_name.name,
 				      page, count);
-	mutex_unlock(&task->signal->cred_guard_mutex);
+	mutex_unlock(&current->signal->cred_guard_mutex);
 out_free:
 	kfree(page);
 out:
@@ -2841,6 +2874,15 @@ static int proc_pid_personality(struct seq_file *m, struct pid_namespace *ns,
 	return err;
 }
 
+#ifdef CONFIG_LIVEPATCH
+static int proc_pid_patch_state(struct seq_file *m, struct pid_namespace *ns,
+				struct pid *pid, struct task_struct *task)
+{
+	seq_printf(m, "%d\n", task->patch_state);
+	return 0;
+}
+#endif /* CONFIG_LIVEPATCH */
+
 /*
  * Thread groups
  */
@@ -2920,6 +2962,7 @@ static const struct pid_entry tgid_base_stuff[] = {
 #endif
 #ifdef CONFIG_FAULT_INJECTION
 	REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
+	REG("fail-nth", 0644, proc_fail_nth_operations),
 #endif
 #ifdef CONFIG_ELF_CORE
 	REG("coredump_filter", S_IRUGO|S_IWUSR, proc_coredump_filter_operations),
@@ -2936,10 +2979,13 @@ static const struct pid_entry tgid_base_stuff[] = {
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
 	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
-#ifdef CONFIG_CHECKPOINT_RESTORE
+#if defined(CONFIG_CHECKPOINT_RESTORE) && defined(CONFIG_POSIX_TIMERS)
 	REG("timers",	  S_IRUGO, proc_timers_operations),
 #endif
 	REG("timerslack_ns", S_IRUGO|S_IWUGO, proc_pid_set_timerslack_ns_operations),
+#ifdef CONFIG_LIVEPATCH
+	ONE("patch_state",  S_IRUSR, proc_pid_patch_state),
+#endif
 };
 
 static int proc_tgid_base_readdir(struct file *file, struct dir_context *ctx)
@@ -3181,7 +3227,7 @@ int proc_pid_readdir(struct file *file, struct dir_context *ctx)
 		int len;
 
 		cond_resched();
-		if (!has_pid_permissions(ns, iter.task, 2))
+		if (!has_pid_permissions(ns, iter.task, HIDEPID_INVISIBLE))
 			continue;
 
 		len = snprintf(name, sizeof(name), "%d", iter.tgid);
@@ -3309,6 +3355,7 @@ static const struct pid_entry tid_base_stuff[] = {
 #endif
 #ifdef CONFIG_FAULT_INJECTION
 	REG("make-it-fail", S_IRUGO|S_IWUSR, proc_fault_inject_operations),
+	REG("fail-nth", 0644, proc_fail_nth_operations),
 #endif
 #ifdef CONFIG_TASK_IO_ACCOUNTING
 	ONE("io",	S_IRUSR, proc_tid_io_accounting),
@@ -3322,6 +3369,9 @@ static const struct pid_entry tid_base_stuff[] = {
 	REG("projid_map", S_IRUGO|S_IWUSR, proc_projid_map_operations),
 	REG("setgroups",  S_IRUGO|S_IWUSR, proc_setgroups_operations),
 #endif
+#ifdef CONFIG_LIVEPATCH
+	ONE("patch_state",  S_IRUSR, proc_pid_patch_state),
+#endif
 };
 
 static int proc_tid_base_readdir(struct file *file, struct dir_context *ctx)
@@ -3524,9 +3574,10 @@ static int proc_task_readdir(struct file *file, struct dir_context *ctx)
 	return 0;
 }
 
-static int proc_task_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+static int proc_task_getattr(const struct path *path, struct kstat *stat,
+			     u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct task_struct *p = get_proc_task(inode);
 	generic_fillattr(inode, stat);
 
diff --git a/fs/proc/fd.c b/fs/proc/fd.c
index 4274f83bf100..c330495c3115 100644
--- a/fs/proc/fd.c
+++ b/fs/proc/fd.c
@@ -1,4 +1,4 @@
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/errno.h>
 #include <linux/dcache.h>
 #include <linux/path.h>
@@ -84,7 +84,6 @@ static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
 {
 	struct files_struct *files;
 	struct task_struct *task;
-	const struct cred *cred;
 	struct inode *inode;
 	unsigned int fd;
 
@@ -108,16 +107,7 @@ static int tid_fd_revalidate(struct dentry *dentry, unsigned int flags)
 				rcu_read_unlock();
 				put_files_struct(files);
 
-				if (task_dumpable(task)) {
-					rcu_read_lock();
-					cred = __task_cred(task);
-					inode->i_uid = cred->euid;
-					inode->i_gid = cred->egid;
-					rcu_read_unlock();
-				} else {
-					inode->i_uid = GLOBAL_ROOT_UID;
-					inode->i_gid = GLOBAL_ROOT_GID;
-				}
+				task_dump_owner(task, 0, &inode->i_uid, &inode->i_gid);
 
 				if (S_ISLNK(inode->i_mode)) {
 					unsigned i_mode = S_IFLNK;
diff --git a/fs/proc/generic.c b/fs/proc/generic.c
index f6a01f09f79d..e3cda0b5968f 100644
--- a/fs/proc/generic.c
+++ b/fs/proc/generic.c
@@ -57,9 +57,9 @@ static struct proc_dir_entry *pde_subdir_find(struct proc_dir_entry *dir,
 	struct rb_node *node = dir->subdir.rb_node;
 
 	while (node) {
-		struct proc_dir_entry *de = container_of(node,
-							 struct proc_dir_entry,
-							 subdir_node);
+		struct proc_dir_entry *de = rb_entry(node,
+						     struct proc_dir_entry,
+						     subdir_node);
 		int result = proc_match(len, name, de);
 
 		if (result < 0)
@@ -80,8 +80,9 @@ static bool pde_subdir_insert(struct proc_dir_entry *dir,
 
 	/* Figure out where to put new node */
 	while (*new) {
-		struct proc_dir_entry *this =
-			container_of(*new, struct proc_dir_entry, subdir_node);
+		struct proc_dir_entry *this = rb_entry(*new,
+						       struct proc_dir_entry,
+						       subdir_node);
 		int result = proc_match(de->namelen, de->name, this);
 
 		parent = *new;
@@ -117,10 +118,10 @@ static int proc_notify_change(struct dentry *dentry, struct iattr *iattr)
 	return 0;
 }
 
-static int proc_getattr(struct vfsmount *mnt, struct dentry *dentry,
-			struct kstat *stat)
+static int proc_getattr(const struct path *path, struct kstat *stat,
+			u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct proc_dir_entry *de = PDE(inode);
 	if (de && de->nlink)
 		set_nlink(inode, de->nlink);
@@ -179,7 +180,6 @@ static int xlate_proc_name(const char *name, struct proc_dir_entry **ret,
 }
 
 static DEFINE_IDA(proc_inum_ida);
-static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */
 
 #define PROC_DYNAMIC_FIRST 0xF0000000U
 
@@ -189,37 +189,20 @@ static DEFINE_SPINLOCK(proc_inum_lock); /* protects the above */
  */
 int proc_alloc_inum(unsigned int *inum)
 {
-	unsigned int i;
-	int error;
+	int i;
 
-retry:
-	if (!ida_pre_get(&proc_inum_ida, GFP_KERNEL))
-		return -ENOMEM;
+	i = ida_simple_get(&proc_inum_ida, 0, UINT_MAX - PROC_DYNAMIC_FIRST + 1,
+			   GFP_KERNEL);
+	if (i < 0)
+		return i;
 
-	spin_lock_irq(&proc_inum_lock);
-	error = ida_get_new(&proc_inum_ida, &i);
-	spin_unlock_irq(&proc_inum_lock);
-	if (error == -EAGAIN)
-		goto retry;
-	else if (error)
-		return error;
-
-	if (i > UINT_MAX - PROC_DYNAMIC_FIRST) {
-		spin_lock_irq(&proc_inum_lock);
-		ida_remove(&proc_inum_ida, i);
-		spin_unlock_irq(&proc_inum_lock);
-		return -ENOSPC;
-	}
-	*inum = PROC_DYNAMIC_FIRST + i;
+	*inum = PROC_DYNAMIC_FIRST + (unsigned int)i;
 	return 0;
 }
 
 void proc_free_inum(unsigned int inum)
 {
-	unsigned long flags;
-	spin_lock_irqsave(&proc_inum_lock, flags);
-	ida_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
-	spin_unlock_irqrestore(&proc_inum_lock, flags);
+	ida_simple_remove(&proc_inum_ida, inum - PROC_DYNAMIC_FIRST);
 }
 
 /*
@@ -471,6 +454,7 @@ struct proc_dir_entry *proc_create_mount_point(const char *name)
 		ent->data = NULL;
 		ent->proc_fops = NULL;
 		ent->proc_iops = NULL;
+		parent->nlink++;
 		if (proc_register(parent, ent) < 0) {
 			kfree(ent);
 			parent->nlink--;
diff --git a/fs/proc/inode.c b/fs/proc/inode.c
index 842a5ff5b85c..e250910cffc8 100644
--- a/fs/proc/inode.c
+++ b/fs/proc/inode.c
@@ -43,10 +43,11 @@ static void proc_evict_inode(struct inode *inode)
 	de = PDE(inode);
 	if (de)
 		pde_put(de);
+
 	head = PROC_I(inode)->sysctl;
 	if (head) {
 		RCU_INIT_POINTER(PROC_I(inode)->sysctl, NULL);
-		sysctl_head_put(head);
+		proc_sys_evict_inode(inode, head);
 	}
 }
 
@@ -57,7 +58,7 @@ static struct inode *proc_alloc_inode(struct super_block *sb)
 	struct proc_inode *ei;
 	struct inode *inode;
 
-	ei = (struct proc_inode *)kmem_cache_alloc(proc_inode_cachep, GFP_KERNEL);
+	ei = kmem_cache_alloc(proc_inode_cachep, GFP_KERNEL);
 	if (!ei)
 		return NULL;
 	ei->pid = NULL;
@@ -106,7 +107,7 @@ static int proc_show_options(struct seq_file *seq, struct dentry *root)
 
 	if (!gid_eq(pid->pid_gid, GLOBAL_ROOT_GID))
 		seq_printf(seq, ",gid=%u", from_kgid_munged(&init_user_ns, pid->pid_gid));
-	if (pid->hide_pid != 0)
+	if (pid->hide_pid != HIDEPID_OFF)
 		seq_printf(seq, ",hidepid=%u", pid->hide_pid);
 
 	return 0;
diff --git a/fs/proc/internal.h b/fs/proc/internal.h
index 2de5194ba378..aa2b89071630 100644
--- a/fs/proc/internal.h
+++ b/fs/proc/internal.h
@@ -14,6 +14,8 @@
 #include <linux/spinlock.h>
 #include <linux/atomic.h>
 #include <linux/binfmts.h>
+#include <linux/sched/coredump.h>
+#include <linux/sched/task.h>
 
 struct ctl_table_header;
 struct mempolicy;
@@ -49,7 +51,7 @@ struct proc_dir_entry {
 	spinlock_t pde_unload_lock; /* proc_fops checks and pde_users bumps */
 	u8 namelen;
 	char name[];
-};
+} __randomize_layout;
 
 union proc_op {
 	int (*proc_get_link)(struct dentry *, struct path *);
@@ -65,9 +67,10 @@ struct proc_inode {
 	struct proc_dir_entry *pde;
 	struct ctl_table_header *sysctl;
 	struct ctl_table *sysctl_entry;
+	struct hlist_node sysctl_inodes;
 	const struct proc_ns_operations *ns_ops;
 	struct inode vfs_inode;
-};
+} __randomize_layout;
 
 /*
  * General functions
@@ -97,20 +100,8 @@ static inline struct task_struct *get_proc_task(struct inode *inode)
 	return get_pid_task(proc_pid(inode), PIDTYPE_PID);
 }
 
-static inline int task_dumpable(struct task_struct *task)
-{
-	int dumpable = 0;
-	struct mm_struct *mm;
-
-	task_lock(task);
-	mm = task->mm;
-	if (mm)
-		dumpable = get_dumpable(mm);
-	task_unlock(task);
-	if (dumpable == SUID_DUMP_USER)
-		return 1;
-	return 0;
-}
+void task_dump_owner(struct task_struct *task, mode_t mode,
+		     kuid_t *ruid, kgid_t *rgid);
 
 static inline unsigned name_to_int(const struct qstr *qstr)
 {
@@ -160,7 +151,7 @@ extern int proc_pid_statm(struct seq_file *, struct pid_namespace *,
  * base.c
  */
 extern const struct dentry_operations pid_dentry_operations;
-extern int pid_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int pid_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int proc_setattr(struct dentry *, struct iattr *);
 extern struct inode *proc_pid_make_inode(struct super_block *, struct task_struct *, umode_t);
 extern int pid_revalidate(struct dentry *, unsigned int);
@@ -249,10 +240,12 @@ extern void proc_thread_self_init(void);
  */
 #ifdef CONFIG_PROC_SYSCTL
 extern int proc_sys_init(void);
-extern void sysctl_head_put(struct ctl_table_header *);
+extern void proc_sys_evict_inode(struct inode *inode,
+				 struct ctl_table_header *head);
 #else
 static inline void proc_sys_init(void) { }
-static inline void sysctl_head_put(struct ctl_table_header *head) { }
+static inline void proc_sys_evict_inode(struct  inode *inode,
+					struct ctl_table_header *head) { }
 #endif
 
 /*
@@ -286,7 +279,7 @@ struct proc_maps_private {
 #ifdef CONFIG_NUMA
 	struct mempolicy *task_mempolicy;
 #endif
-};
+} __randomize_layout;
 
 struct mm_struct *proc_mem_open(struct inode *inode, unsigned int mode);
 
diff --git a/fs/proc/kcore.c b/fs/proc/kcore.c
index 0b80ad87b4d6..45629f4b5402 100644
--- a/fs/proc/kcore.c
+++ b/fs/proc/kcore.c
@@ -28,6 +28,7 @@
 #include <linux/list.h>
 #include <linux/ioport.h>
 #include <linux/memory.h>
+#include <linux/sched/task.h>
 #include <asm/sections.h>
 #include "internal.h"
 
@@ -373,7 +374,10 @@ static void elf_kcore_store_hdr(char *bufp, int nphdr, int dataoff)
 		phdr->p_flags	= PF_R|PF_W|PF_X;
 		phdr->p_offset	= kc_vaddr_to_offset(m->addr) + dataoff;
 		phdr->p_vaddr	= (size_t)m->addr;
-		phdr->p_paddr	= 0;
+		if (m->type == KCORE_RAM || m->type == KCORE_TEXT)
+			phdr->p_paddr	= __pa(m->addr);
+		else
+			phdr->p_paddr	= (elf_addr_t)-1;
 		phdr->p_filesz	= phdr->p_memsz	= m->size;
 		phdr->p_align	= PAGE_SIZE;
 	}
@@ -500,7 +504,7 @@ read_kcore(struct file *file, char __user *buffer, size_t buflen, loff_t *fpos)
 		if (&m->list == &kclist_head) {
 			if (clear_user(buffer, tsz))
 				return -EFAULT;
-		} else if (is_vmalloc_or_module_addr((void *)start)) {
+		} else if (m->type == KCORE_VMALLOC) {
 			vread(buf, (char *)start, tsz);
 			/* we have to zero-fill user buffer even if no read */
 			if (copy_to_user(buffer, buf, tsz))
diff --git a/fs/proc/loadavg.c b/fs/proc/loadavg.c
index aec66e6c2060..983fce5c2418 100644
--- a/fs/proc/loadavg.c
+++ b/fs/proc/loadavg.c
@@ -3,6 +3,8 @@
 #include <linux/pid_namespace.h>
 #include <linux/proc_fs.h>
 #include <linux/sched.h>
+#include <linux/sched/loadavg.h>
+#include <linux/sched/stat.h>
 #include <linux/seq_file.h>
 #include <linux/seqlock.h>
 #include <linux/time.h>
diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
index 766f0c637ad1..3803b24ca220 100644
--- a/fs/proc/namespaces.c
+++ b/fs/proc/namespaces.c
@@ -23,6 +23,7 @@ static const struct proc_ns_operations *ns_entries[] = {
 #endif
 #ifdef CONFIG_PID_NS
 	&pidns_operations,
+	&pidns_for_children_operations,
 #endif
 #ifdef CONFIG_USER_NS
 	&userns_operations,
diff --git a/fs/proc/proc_net.c b/fs/proc/proc_net.c
index ffd72a6c6e04..d72fc40241d9 100644
--- a/fs/proc/proc_net.c
+++ b/fs/proc/proc_net.c
@@ -17,6 +17,7 @@
 #include <linux/slab.h>
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/task.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/mount.h>
@@ -140,10 +141,10 @@ static struct dentry *proc_tgid_net_lookup(struct inode *dir,
 	return de;
 }
 
-static int proc_tgid_net_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		struct kstat *stat)
+static int proc_tgid_net_getattr(const struct path *path, struct kstat *stat,
+				 u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct net *net;
 
 	net = get_proc_task_net(inode);
diff --git a/fs/proc/proc_sysctl.c b/fs/proc/proc_sysctl.c
index d4e37acd4821..8f479229b349 100644
--- a/fs/proc/proc_sysctl.c
+++ b/fs/proc/proc_sysctl.c
@@ -8,6 +8,7 @@
 #include <linux/printk.h>
 #include <linux/security.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/namei.h>
 #include <linux/mm.h>
 #include <linux/module.h>
@@ -190,6 +191,7 @@ static void init_header(struct ctl_table_header *head,
 	head->set = set;
 	head->parent = NULL;
 	head->node = node;
+	INIT_HLIST_HEAD(&head->inodes);
 	if (node) {
 		struct ctl_table *entry;
 		for (entry = table; entry->procname; entry++, node++)
@@ -259,6 +261,44 @@ static void unuse_table(struct ctl_table_header *p)
 			complete(p->unregistering);
 }
 
+static void proc_sys_prune_dcache(struct ctl_table_header *head)
+{
+	struct inode *inode;
+	struct proc_inode *ei;
+	struct hlist_node *node;
+	struct super_block *sb;
+
+	rcu_read_lock();
+	for (;;) {
+		node = hlist_first_rcu(&head->inodes);
+		if (!node)
+			break;
+		ei = hlist_entry(node, struct proc_inode, sysctl_inodes);
+		spin_lock(&sysctl_lock);
+		hlist_del_init_rcu(&ei->sysctl_inodes);
+		spin_unlock(&sysctl_lock);
+
+		inode = &ei->vfs_inode;
+		sb = inode->i_sb;
+		if (!atomic_inc_not_zero(&sb->s_active))
+			continue;
+		inode = igrab(inode);
+		rcu_read_unlock();
+		if (unlikely(!inode)) {
+			deactivate_super(sb);
+			rcu_read_lock();
+			continue;
+		}
+
+		d_prune_aliases(inode);
+		iput(inode);
+		deactivate_super(sb);
+
+		rcu_read_lock();
+	}
+	rcu_read_unlock();
+}
+
 /* called under sysctl_lock, will reacquire if has to wait */
 static void start_unregistering(struct ctl_table_header *p)
 {
@@ -272,31 +312,22 @@ static void start_unregistering(struct ctl_table_header *p)
 		p->unregistering = &wait;
 		spin_unlock(&sysctl_lock);
 		wait_for_completion(&wait);
-		spin_lock(&sysctl_lock);
 	} else {
 		/* anything non-NULL; we'll never dereference it */
 		p->unregistering = ERR_PTR(-EINVAL);
+		spin_unlock(&sysctl_lock);
 	}
 	/*
+	 * Prune dentries for unregistered sysctls: namespaced sysctls
+	 * can have duplicate names and contaminate dcache very badly.
+	 */
+	proc_sys_prune_dcache(p);
+	/*
 	 * do not remove from the list until nobody holds it; walking the
 	 * list in do_sysctl() relies on that.
 	 */
-	erase_header(p);
-}
-
-static void sysctl_head_get(struct ctl_table_header *head)
-{
-	spin_lock(&sysctl_lock);
-	head->count++;
-	spin_unlock(&sysctl_lock);
-}
-
-void sysctl_head_put(struct ctl_table_header *head)
-{
 	spin_lock(&sysctl_lock);
-	if (!--head->count)
-		kfree_rcu(head, rcu);
-	spin_unlock(&sysctl_lock);
+	erase_header(p);
 }
 
 static struct ctl_table_header *sysctl_head_grab(struct ctl_table_header *head)
@@ -394,10 +425,6 @@ static void next_entry(struct ctl_table_header **phead, struct ctl_table **pentr
 	*pentry = entry;
 }
 
-void register_sysctl_root(struct ctl_table_root *root)
-{
-}
-
 /*
  * sysctl_perm does NOT grant the superuser all rights automatically, because
  * some sysctl variables are readonly even to root.
@@ -440,10 +467,20 @@ static struct inode *proc_sys_make_inode(struct super_block *sb,
 
 	inode->i_ino = get_next_ino();
 
-	sysctl_head_get(head);
 	ei = PROC_I(inode);
+
+	spin_lock(&sysctl_lock);
+	if (unlikely(head->unregistering)) {
+		spin_unlock(&sysctl_lock);
+		iput(inode);
+		inode = NULL;
+		goto out;
+	}
 	ei->sysctl = head;
 	ei->sysctl_entry = table;
+	hlist_add_head_rcu(&ei->sysctl_inodes, &head->inodes);
+	head->count++;
+	spin_unlock(&sysctl_lock);
 
 	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
 	inode->i_mode = table->mode;
@@ -466,6 +503,15 @@ out:
 	return inode;
 }
 
+void proc_sys_evict_inode(struct inode *inode, struct ctl_table_header *head)
+{
+	spin_lock(&sysctl_lock);
+	hlist_del_init_rcu(&PROC_I(inode)->sysctl_inodes);
+	if (!--head->count)
+		kfree_rcu(head, rcu);
+	spin_unlock(&sysctl_lock);
+}
+
 static struct ctl_table_header *grab_header(struct inode *inode)
 {
 	struct ctl_table_header *head = PROC_I(inode)->sysctl;
@@ -769,9 +815,10 @@ static int proc_sys_setattr(struct dentry *dentry, struct iattr *attr)
 	return 0;
 }
 
-static int proc_sys_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+static int proc_sys_getattr(const struct path *path, struct kstat *stat,
+			    u32 request_mask, unsigned int query_flags)
 {
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct ctl_table_header *head = grab_header(inode);
 	struct ctl_table *table = PROC_I(inode)->sysctl_entry;
 
@@ -1031,15 +1078,30 @@ static int sysctl_err(const char *path, struct ctl_table *table, char *fmt, ...)
 	return -EINVAL;
 }
 
+static int sysctl_check_table_array(const char *path, struct ctl_table *table)
+{
+	int err = 0;
+
+	if ((table->proc_handler == proc_douintvec) ||
+	    (table->proc_handler == proc_douintvec_minmax)) {
+		if (table->maxlen != sizeof(unsigned int))
+			err |= sysctl_err(path, table, "array now allowed");
+	}
+
+	return err;
+}
+
 static int sysctl_check_table(const char *path, struct ctl_table *table)
 {
 	int err = 0;
 	for (; table->procname; table++) {
 		if (table->child)
-			err = sysctl_err(path, table, "Not a file");
+			err |= sysctl_err(path, table, "Not a file");
 
 		if ((table->proc_handler == proc_dostring) ||
 		    (table->proc_handler == proc_dointvec) ||
+		    (table->proc_handler == proc_douintvec) ||
+		    (table->proc_handler == proc_douintvec_minmax) ||
 		    (table->proc_handler == proc_dointvec_minmax) ||
 		    (table->proc_handler == proc_dointvec_jiffies) ||
 		    (table->proc_handler == proc_dointvec_userhz_jiffies) ||
@@ -1047,15 +1109,17 @@ static int sysctl_check_table(const char *path, struct ctl_table *table)
 		    (table->proc_handler == proc_doulongvec_minmax) ||
 		    (table->proc_handler == proc_doulongvec_ms_jiffies_minmax)) {
 			if (!table->data)
-				err = sysctl_err(path, table, "No data");
+				err |= sysctl_err(path, table, "No data");
 			if (!table->maxlen)
-				err = sysctl_err(path, table, "No maxlen");
+				err |= sysctl_err(path, table, "No maxlen");
+			else
+				err |= sysctl_check_table_array(path, table);
 		}
 		if (!table->proc_handler)
-			err = sysctl_err(path, table, "No proc_handler");
+			err |= sysctl_err(path, table, "No proc_handler");
 
 		if ((table->mode & (S_IRUGO|S_IWUGO)) != table->mode)
-			err = sysctl_err(path, table, "bogus .mode 0%o",
+			err |= sysctl_err(path, table, "bogus .mode 0%o",
 				table->mode);
 	}
 	return err;
diff --git a/fs/proc/root.c b/fs/proc/root.c
index 1988440b2049..deecb397daa3 100644
--- a/fs/proc/root.c
+++ b/fs/proc/root.c
@@ -14,12 +14,14 @@
 #include <linux/stat.h>
 #include <linux/init.h>
 #include <linux/sched.h>
+#include <linux/sched/stat.h>
 #include <linux/module.h>
 #include <linux/bitops.h>
 #include <linux/user_namespace.h>
 #include <linux/mount.h>
 #include <linux/pid_namespace.h>
 #include <linux/parser.h>
+#include <linux/cred.h>
 
 #include "internal.h"
 
@@ -58,7 +60,8 @@ int proc_parse_options(char *options, struct pid_namespace *pid)
 		case Opt_hidepid:
 			if (match_int(&args[0], &option))
 				return 0;
-			if (option < 0 || option > 2) {
+			if (option < HIDEPID_OFF ||
+			    option > HIDEPID_INVISIBLE) {
 				pr_err("proc: hidepid value must be between 0 and 2.\n");
 				return 0;
 			}
@@ -148,10 +151,10 @@ void __init proc_root_init(void)
 	proc_sys_init();
 }
 
-static int proc_root_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat
-)
+static int proc_root_getattr(const struct path *path, struct kstat *stat,
+			     u32 request_mask, unsigned int query_flags)
 {
-	generic_fillattr(d_inode(dentry), stat);
+	generic_fillattr(d_inode(path->dentry), stat);
 	stat->nlink = proc_root.nlink + nr_processes();
 	return 0;
 }
diff --git a/fs/proc/stat.c b/fs/proc/stat.c
index d700c42b3572..bd4e55f4aa20 100644
--- a/fs/proc/stat.c
+++ b/fs/proc/stat.c
@@ -5,11 +5,12 @@
 #include <linux/kernel_stat.h>
 #include <linux/proc_fs.h>
 #include <linux/sched.h>
+#include <linux/sched/stat.h>
 #include <linux/seq_file.h>
 #include <linux/slab.h>
 #include <linux/time.h>
 #include <linux/irqnr.h>
-#include <linux/cputime.h>
+#include <linux/sched/cputime.h>
 #include <linux/tick.h>
 
 #ifndef arch_irq_stat_cpu
@@ -21,9 +22,9 @@
 
 #ifdef arch_idle_time
 
-static cputime64_t get_idle_time(int cpu)
+static u64 get_idle_time(int cpu)
 {
-	cputime64_t idle;
+	u64 idle;
 
 	idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
 	if (cpu_online(cpu) && !nr_iowait_cpu(cpu))
@@ -31,9 +32,9 @@ static cputime64_t get_idle_time(int cpu)
 	return idle;
 }
 
-static cputime64_t get_iowait_time(int cpu)
+static u64 get_iowait_time(int cpu)
 {
-	cputime64_t iowait;
+	u64 iowait;
 
 	iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
 	if (cpu_online(cpu) && nr_iowait_cpu(cpu))
@@ -45,32 +46,32 @@ static cputime64_t get_iowait_time(int cpu)
 
 static u64 get_idle_time(int cpu)
 {
-	u64 idle, idle_time = -1ULL;
+	u64 idle, idle_usecs = -1ULL;
 
 	if (cpu_online(cpu))
-		idle_time = get_cpu_idle_time_us(cpu, NULL);
+		idle_usecs = get_cpu_idle_time_us(cpu, NULL);
 
-	if (idle_time == -1ULL)
+	if (idle_usecs == -1ULL)
 		/* !NO_HZ or cpu offline so we can rely on cpustat.idle */
 		idle = kcpustat_cpu(cpu).cpustat[CPUTIME_IDLE];
 	else
-		idle = usecs_to_cputime64(idle_time);
+		idle = idle_usecs * NSEC_PER_USEC;
 
 	return idle;
 }
 
 static u64 get_iowait_time(int cpu)
 {
-	u64 iowait, iowait_time = -1ULL;
+	u64 iowait, iowait_usecs = -1ULL;
 
 	if (cpu_online(cpu))
-		iowait_time = get_cpu_iowait_time_us(cpu, NULL);
+		iowait_usecs = get_cpu_iowait_time_us(cpu, NULL);
 
-	if (iowait_time == -1ULL)
+	if (iowait_usecs == -1ULL)
 		/* !NO_HZ or cpu offline so we can rely on cpustat.iowait */
 		iowait = kcpustat_cpu(cpu).cpustat[CPUTIME_IOWAIT];
 	else
-		iowait = usecs_to_cputime64(iowait_time);
+		iowait = iowait_usecs * NSEC_PER_USEC;
 
 	return iowait;
 }
@@ -115,16 +116,16 @@ static int show_stat(struct seq_file *p, void *v)
 	}
 	sum += arch_irq_stat();
 
-	seq_put_decimal_ull(p, "cpu  ", cputime64_to_clock_t(user));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(nice));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(system));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(idle));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(iowait));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(irq));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(softirq));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(steal));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest));
-	seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest_nice));
+	seq_put_decimal_ull(p, "cpu  ", nsec_to_clock_t(user));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+	seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
 	seq_putc(p, '\n');
 
 	for_each_online_cpu(i) {
@@ -140,16 +141,16 @@ static int show_stat(struct seq_file *p, void *v)
 		guest = kcpustat_cpu(i).cpustat[CPUTIME_GUEST];
 		guest_nice = kcpustat_cpu(i).cpustat[CPUTIME_GUEST_NICE];
 		seq_printf(p, "cpu%d", i);
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(user));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(nice));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(system));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(idle));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(iowait));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(irq));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(softirq));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(steal));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest));
-		seq_put_decimal_ull(p, " ", cputime64_to_clock_t(guest_nice));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(user));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(nice));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(system));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(idle));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(iowait));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(irq));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(softirq));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(steal));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest));
+		seq_put_decimal_ull(p, " ", nsec_to_clock_t(guest_nice));
 		seq_putc(p, '\n');
 	}
 	seq_put_decimal_ull(p, "intr ", (unsigned long long)sum);
diff --git a/fs/proc/task_mmu.c b/fs/proc/task_mmu.c
index 8f96a49178d0..b836fd61ed87 100644
--- a/fs/proc/task_mmu.c
+++ b/fs/proc/task_mmu.c
@@ -11,6 +11,7 @@
 #include <linux/mempolicy.h>
 #include <linux/rmap.h>
 #include <linux/swap.h>
+#include <linux/sched/mm.h>
 #include <linux/swapops.h>
 #include <linux/mmu_notifier.h>
 #include <linux/page_idle.h>
@@ -167,7 +168,7 @@ static void *m_start(struct seq_file *m, loff_t *ppos)
 		return ERR_PTR(-ESRCH);
 
 	mm = priv->mm;
-	if (!mm || !atomic_inc_not_zero(&mm->mm_users))
+	if (!mm || !mmget_not_zero(mm))
 		return NULL;
 
 	down_read(&mm->mmap_sem);
@@ -297,13 +298,8 @@ show_map_vma(struct seq_file *m, struct vm_area_struct *vma, int is_pid)
 		pgoff = ((loff_t)vma->vm_pgoff) << PAGE_SHIFT;
 	}
 
-	/* We don't show the stack guard page in /proc/maps */
 	start = vma->vm_start;
-	if (stack_guard_page_start(vma, start))
-		start += PAGE_SIZE;
 	end = vma->vm_end;
-	if (stack_guard_page_end(vma, end))
-		end -= PAGE_SIZE;
 
 	seq_setwidth(m, 25 + sizeof(void *) * 6 - 1);
 	seq_printf(m, "%08lx-%08lx %c%c%c%c %08llx %02x:%02x %lu ",
@@ -440,6 +436,7 @@ struct mem_size_stats {
 	unsigned long private_dirty;
 	unsigned long referenced;
 	unsigned long anonymous;
+	unsigned long lazyfree;
 	unsigned long anonymous_thp;
 	unsigned long shmem_thp;
 	unsigned long swap;
@@ -456,8 +453,11 @@ static void smaps_account(struct mem_size_stats *mss, struct page *page,
 	int i, nr = compound ? 1 << compound_order(page) : 1;
 	unsigned long size = nr * PAGE_SIZE;
 
-	if (PageAnon(page))
+	if (PageAnon(page)) {
 		mss->anonymous += size;
+		if (!PageSwapBacked(page) && !dirty && !PageDirty(page))
+			mss->lazyfree += size;
+	}
 
 	mss->resident += size;
 	/* Accumulate the size in pages that have been accessed. */
@@ -770,6 +770,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   "Private_Dirty:  %8lu kB\n"
 		   "Referenced:     %8lu kB\n"
 		   "Anonymous:      %8lu kB\n"
+		   "LazyFree:       %8lu kB\n"
 		   "AnonHugePages:  %8lu kB\n"
 		   "ShmemPmdMapped: %8lu kB\n"
 		   "Shared_Hugetlb: %8lu kB\n"
@@ -788,6 +789,7 @@ static int show_smap(struct seq_file *m, void *v, int is_pid)
 		   mss.private_dirty >> 10,
 		   mss.referenced >> 10,
 		   mss.anonymous >> 10,
+		   mss.lazyfree >> 10,
 		   mss.anonymous_thp >> 10,
 		   mss.shmem_thp >> 10,
 		   mss.shared_hugetlb >> 10,
@@ -899,7 +901,14 @@ static inline void clear_soft_dirty(struct vm_area_struct *vma,
 static inline void clear_soft_dirty_pmd(struct vm_area_struct *vma,
 		unsigned long addr, pmd_t *pmdp)
 {
-	pmd_t pmd = pmdp_huge_get_and_clear(vma->vm_mm, addr, pmdp);
+	pmd_t pmd = *pmdp;
+
+	/* See comment in change_huge_pmd() */
+	pmdp_invalidate(vma, addr, pmdp);
+	if (pmd_dirty(*pmdp))
+		pmd = pmd_mkdirty(pmd);
+	if (pmd_young(*pmdp))
+		pmd = pmd_mkyoung(pmd);
 
 	pmd = pmd_wrprotect(pmd);
 	pmd = pmd_clear_soft_dirty(pmd);
@@ -1352,7 +1361,7 @@ static ssize_t pagemap_read(struct file *file, char __user *buf,
 	unsigned long end_vaddr;
 	int ret = 0, copied = 0;
 
-	if (!mm || !atomic_inc_not_zero(&mm->mm_users))
+	if (!mm || !mmget_not_zero(mm))
 		goto out;
 
 	ret = -EINVAL;
diff --git a/fs/proc/task_nommu.c b/fs/proc/task_nommu.c
index 37175621e890..23266694db11 100644
--- a/fs/proc/task_nommu.c
+++ b/fs/proc/task_nommu.c
@@ -7,6 +7,8 @@
 #include <linux/ptrace.h>
 #include <linux/slab.h>
 #include <linux/seq_file.h>
+#include <linux/sched/mm.h>
+
 #include "internal.h"
 
 /*
@@ -219,7 +221,7 @@ static void *m_start(struct seq_file *m, loff_t *pos)
 		return ERR_PTR(-ESRCH);
 
 	mm = priv->mm;
-	if (!mm || !atomic_inc_not_zero(&mm->mm_users))
+	if (!mm || !mmget_not_zero(mm))
 		return NULL;
 
 	down_read(&mm->mmap_sem);
diff --git a/fs/proc/uptime.c b/fs/proc/uptime.c
index 33de567c25af..7981c4ffe787 100644
--- a/fs/proc/uptime.c
+++ b/fs/proc/uptime.c
@@ -5,23 +5,20 @@
 #include <linux/seq_file.h>
 #include <linux/time.h>
 #include <linux/kernel_stat.h>
-#include <linux/cputime.h>
 
 static int uptime_proc_show(struct seq_file *m, void *v)
 {
 	struct timespec uptime;
 	struct timespec idle;
-	u64 idletime;
 	u64 nsec;
 	u32 rem;
 	int i;
 
-	idletime = 0;
+	nsec = 0;
 	for_each_possible_cpu(i)
-		idletime += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
+		nsec += (__force u64) kcpustat_cpu(i).cpustat[CPUTIME_IDLE];
 
 	get_monotonic_boottime(&uptime);
-	nsec = cputime64_to_jiffies64(idletime) * TICK_NSEC;
 	idle.tv_sec = div_u64_rem(nsec, NSEC_PER_SEC, &rem);
 	idle.tv_nsec = rem;
 	seq_printf(m, "%lu.%02lu %lu.%02lu\n",
diff --git a/fs/proc/vmcore.c b/fs/proc/vmcore.c
index 5105b1599981..885d445afa0d 100644
--- a/fs/proc/vmcore.c
+++ b/fs/proc/vmcore.c
@@ -265,10 +265,10 @@ static ssize_t read_vmcore(struct file *file, char __user *buffer,
  * On s390 the fault handler is used for memory regions that can't be mapped
  * directly with remap_pfn_range().
  */
-static int mmap_vmcore_fault(struct vm_area_struct *vma, struct vm_fault *vmf)
+static int mmap_vmcore_fault(struct vm_fault *vmf)
 {
 #ifdef CONFIG_S390
-	struct address_space *mapping = vma->vm_file->f_mapping;
+	struct address_space *mapping = vmf->vma->vm_file->f_mapping;
 	pgoff_t index = vmf->pgoff;
 	struct page *page;
 	loff_t offset;
@@ -388,7 +388,7 @@ static int remap_oldmem_pfn_checked(struct vm_area_struct *vma,
 	}
 	return 0;
 fail:
-	do_munmap(vma->vm_mm, from, len);
+	do_munmap(vma->vm_mm, from, len, NULL);
 	return -EAGAIN;
 }
 
@@ -481,7 +481,7 @@ static int mmap_vmcore(struct file *file, struct vm_area_struct *vma)
 
 	return 0;
 fail:
-	do_munmap(vma->vm_mm, vma->vm_start, len);
+	do_munmap(vma->vm_mm, vma->vm_start, len, NULL);
 	return -EAGAIN;
 }
 #else
diff --git a/fs/proc_namespace.c b/fs/proc_namespace.c
index 3f1190d18991..b5713fefb4c1 100644
--- a/fs/proc_namespace.c
+++ b/fs/proc_namespace.c
@@ -10,6 +10,8 @@
 #include <linux/nsproxy.h>
 #include <linux/security.h>
 #include <linux/fs_struct.h>
+#include <linux/sched/task.h>
+
 #include "proc/internal.h" /* only for get_proc_task() in ->open() */
 
 #include "pnode.h"
diff --git a/fs/pstore/ftrace.c b/fs/pstore/ftrace.c
index 899d0ba0bd6c..06aab07b6bb7 100644
--- a/fs/pstore/ftrace.c
+++ b/fs/pstore/ftrace.c
@@ -37,6 +37,12 @@ static void notrace pstore_ftrace_call(unsigned long ip,
 {
 	unsigned long flags;
 	struct pstore_ftrace_record rec = {};
+	struct pstore_record record = {
+		.type = PSTORE_TYPE_FTRACE,
+		.buf = (char *)&rec,
+		.size = sizeof(rec),
+		.psi = psinfo,
+	};
 
 	if (unlikely(oops_in_progress))
 		return;
@@ -47,8 +53,7 @@ static void notrace pstore_ftrace_call(unsigned long ip,
 	rec.parent_ip = parent_ip;
 	pstore_ftrace_write_timestamp(&rec, pstore_ftrace_stamp++);
 	pstore_ftrace_encode_cpu(&rec, raw_smp_processor_id());
-	psinfo->write_buf(PSTORE_TYPE_FTRACE, 0, NULL, 0, (void *)&rec,
-			  0, sizeof(rec), psinfo);
+	psinfo->write(&record);
 
 	local_irq_restore(flags);
 }
@@ -117,7 +122,7 @@ void pstore_register_ftrace(void)
 {
 	struct dentry *file;
 
-	if (!psinfo->write_buf)
+	if (!psinfo->write)
 		return;
 
 	pstore_ftrace_dir = debugfs_create_dir("pstore", NULL);
diff --git a/fs/pstore/inode.c b/fs/pstore/inode.c
index 57c0646479f5..fefd22611cf6 100644
--- a/fs/pstore/inode.c
+++ b/fs/pstore/inode.c
@@ -47,12 +47,8 @@ static LIST_HEAD(allpstore);
 
 struct pstore_private {
 	struct list_head list;
-	struct pstore_info *psi;
-	enum pstore_type_id type;
-	u64	id;
-	int	count;
-	ssize_t	size;
-	char	data[];
+	struct pstore_record *record;
+	size_t total_size;
 };
 
 struct pstore_ftrace_seq_data {
@@ -63,6 +59,17 @@ struct pstore_ftrace_seq_data {
 
 #define REC_SIZE sizeof(struct pstore_ftrace_record)
 
+static void free_pstore_private(struct pstore_private *private)
+{
+	if (!private)
+		return;
+	if (private->record) {
+		kfree(private->record->buf);
+		kfree(private->record);
+	}
+	kfree(private);
+}
+
 static void *pstore_ftrace_seq_start(struct seq_file *s, loff_t *pos)
 {
 	struct pstore_private *ps = s->private;
@@ -72,9 +79,9 @@ static void *pstore_ftrace_seq_start(struct seq_file *s, loff_t *pos)
 	if (!data)
 		return NULL;
 
-	data->off = ps->size % REC_SIZE;
+	data->off = ps->total_size % REC_SIZE;
 	data->off += *pos * REC_SIZE;
-	if (data->off + REC_SIZE > ps->size) {
+	if (data->off + REC_SIZE > ps->total_size) {
 		kfree(data);
 		return NULL;
 	}
@@ -94,7 +101,7 @@ static void *pstore_ftrace_seq_next(struct seq_file *s, void *v, loff_t *pos)
 	struct pstore_ftrace_seq_data *data = v;
 
 	data->off += REC_SIZE;
-	if (data->off + REC_SIZE > ps->size)
+	if (data->off + REC_SIZE > ps->total_size)
 		return NULL;
 
 	(*pos)++;
@@ -105,7 +112,9 @@ static int pstore_ftrace_seq_show(struct seq_file *s, void *v)
 {
 	struct pstore_private *ps = s->private;
 	struct pstore_ftrace_seq_data *data = v;
-	struct pstore_ftrace_record *rec = (void *)(ps->data + data->off);
+	struct pstore_ftrace_record *rec;
+
+	rec = (struct pstore_ftrace_record *)(ps->record->buf + data->off);
 
 	seq_printf(s, "CPU:%d ts:%llu %08lx  %08lx  %pf <- %pF\n",
 		   pstore_ftrace_decode_cpu(rec),
@@ -125,7 +134,7 @@ static const struct seq_operations pstore_ftrace_seq_ops = {
 
 static int pstore_check_syslog_permissions(struct pstore_private *ps)
 {
-	switch (ps->type) {
+	switch (ps->record->type) {
 	case PSTORE_TYPE_DMESG:
 	case PSTORE_TYPE_CONSOLE:
 		return check_syslog_permissions(SYSLOG_ACTION_READ_ALL,
@@ -141,9 +150,10 @@ static ssize_t pstore_file_read(struct file *file, char __user *userbuf,
 	struct seq_file *sf = file->private_data;
 	struct pstore_private *ps = sf->private;
 
-	if (ps->type == PSTORE_TYPE_FTRACE)
+	if (ps->record->type == PSTORE_TYPE_FTRACE)
 		return seq_read(file, userbuf, count, ppos);
-	return simple_read_from_buffer(userbuf, count, ppos, ps->data, ps->size);
+	return simple_read_from_buffer(userbuf, count, ppos,
+				       ps->record->buf, ps->total_size);
 }
 
 static int pstore_file_open(struct inode *inode, struct file *file)
@@ -157,7 +167,7 @@ static int pstore_file_open(struct inode *inode, struct file *file)
 	if (err)
 		return err;
 
-	if (ps->type == PSTORE_TYPE_FTRACE)
+	if (ps->record->type == PSTORE_TYPE_FTRACE)
 		sops = &pstore_ftrace_seq_ops;
 
 	err = seq_open(file, sops);
@@ -193,20 +203,19 @@ static const struct file_operations pstore_file_operations = {
 static int pstore_unlink(struct inode *dir, struct dentry *dentry)
 {
 	struct pstore_private *p = d_inode(dentry)->i_private;
+	struct pstore_record *record = p->record;
 	int err;
 
 	err = pstore_check_syslog_permissions(p);
 	if (err)
 		return err;
 
-	if (p->psi->erase) {
-		mutex_lock(&p->psi->read_mutex);
-		p->psi->erase(p->type, p->id, p->count,
-			      d_inode(dentry)->i_ctime, p->psi);
-		mutex_unlock(&p->psi->read_mutex);
-	} else {
+	if (!record->psi->erase)
 		return -EPERM;
-	}
+
+	mutex_lock(&record->psi->read_mutex);
+	record->psi->erase(record);
+	mutex_unlock(&record->psi->read_mutex);
 
 	return simple_unlink(dir, dentry);
 }
@@ -221,7 +230,7 @@ static void pstore_evict_inode(struct inode *inode)
 		spin_lock_irqsave(&allpstore_lock, flags);
 		list_del(&p->list);
 		spin_unlock_irqrestore(&allpstore_lock, flags);
-		kfree(p);
+		free_pstore_private(p);
 	}
 }
 
@@ -274,6 +283,16 @@ static void parse_options(char *options)
 	}
 }
 
+/*
+ * Display the mount options in /proc/mounts.
+ */
+static int pstore_show_options(struct seq_file *m, struct dentry *root)
+{
+	if (kmsg_bytes != PSTORE_DEFAULT_KMSG_BYTES)
+		seq_printf(m, ",kmsg_bytes=%lu", kmsg_bytes);
+	return 0;
+}
+
 static int pstore_remount(struct super_block *sb, int *flags, char *data)
 {
 	sync_filesystem(sb);
@@ -287,7 +306,7 @@ static const struct super_operations pstore_ops = {
 	.drop_inode	= generic_delete_inode,
 	.evict_inode	= pstore_evict_inode,
 	.remount_fs	= pstore_remount,
-	.show_options	= generic_show_options,
+	.show_options	= pstore_show_options,
 };
 
 static struct super_block *pstore_sb;
@@ -302,23 +321,23 @@ bool pstore_is_mounted(void)
  * Load it up with "size" bytes of data from "buf".
  * Set the mtime & ctime to the date that this record was originally stored.
  */
-int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
-		  char *data, bool compressed, size_t size,
-		  struct timespec time, struct pstore_info *psi)
+int pstore_mkfile(struct dentry *root, struct pstore_record *record)
 {
-	struct dentry		*root = pstore_sb->s_root;
 	struct dentry		*dentry;
 	struct inode		*inode;
 	int			rc = 0;
 	char			name[PSTORE_NAMELEN];
 	struct pstore_private	*private, *pos;
 	unsigned long		flags;
+	size_t			size = record->size + record->ecc_notice_size;
+
+	WARN_ON(!inode_is_locked(d_inode(root)));
 
 	spin_lock_irqsave(&allpstore_lock, flags);
 	list_for_each_entry(pos, &allpstore, list) {
-		if (pos->type == type &&
-		    pos->id == id &&
-		    pos->psi == psi) {
+		if (pos->record->type == record->type &&
+		    pos->record->id == record->id &&
+		    pos->record->psi == record->psi) {
 			rc = -EEXIST;
 			break;
 		}
@@ -328,72 +347,74 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 		return rc;
 
 	rc = -ENOMEM;
-	inode = pstore_get_inode(pstore_sb);
+	inode = pstore_get_inode(root->d_sb);
 	if (!inode)
 		goto fail;
 	inode->i_mode = S_IFREG | 0444;
 	inode->i_fop = &pstore_file_operations;
-	private = kmalloc(sizeof *private + size, GFP_KERNEL);
+	private = kzalloc(sizeof(*private), GFP_KERNEL);
 	if (!private)
 		goto fail_alloc;
-	private->type = type;
-	private->id = id;
-	private->count = count;
-	private->psi = psi;
+	private->record = record;
 
-	switch (type) {
+	switch (record->type) {
 	case PSTORE_TYPE_DMESG:
-		scnprintf(name, sizeof(name), "dmesg-%s-%lld%s",
-			  psname, id, compressed ? ".enc.z" : "");
+		scnprintf(name, sizeof(name), "dmesg-%s-%llu%s",
+			  record->psi->name, record->id,
+			  record->compressed ? ".enc.z" : "");
 		break;
 	case PSTORE_TYPE_CONSOLE:
-		scnprintf(name, sizeof(name), "console-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "console-%s-%llu",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_FTRACE:
-		scnprintf(name, sizeof(name), "ftrace-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "ftrace-%s-%llu",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_MCE:
-		scnprintf(name, sizeof(name), "mce-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "mce-%s-%llu",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_PPC_RTAS:
-		scnprintf(name, sizeof(name), "rtas-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "rtas-%s-%llu",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_PPC_OF:
-		scnprintf(name, sizeof(name), "powerpc-ofw-%s-%lld",
-			  psname, id);
+		scnprintf(name, sizeof(name), "powerpc-ofw-%s-%llu",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_PPC_COMMON:
-		scnprintf(name, sizeof(name), "powerpc-common-%s-%lld",
-			  psname, id);
+		scnprintf(name, sizeof(name), "powerpc-common-%s-%llu",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_PMSG:
-		scnprintf(name, sizeof(name), "pmsg-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "pmsg-%s-%llu",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_PPC_OPAL:
-		sprintf(name, "powerpc-opal-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "powerpc-opal-%s-%llu",
+			  record->psi->name, record->id);
 		break;
 	case PSTORE_TYPE_UNKNOWN:
-		scnprintf(name, sizeof(name), "unknown-%s-%lld", psname, id);
+		scnprintf(name, sizeof(name), "unknown-%s-%llu",
+			  record->psi->name, record->id);
 		break;
 	default:
-		scnprintf(name, sizeof(name), "type%d-%s-%lld",
-			  type, psname, id);
+		scnprintf(name, sizeof(name), "type%d-%s-%llu",
+			  record->type, record->psi->name, record->id);
 		break;
 	}
 
-	inode_lock(d_inode(root));
-
 	dentry = d_alloc_name(root, name);
 	if (!dentry)
-		goto fail_lockedalloc;
+		goto fail_private;
 
-	memcpy(private->data, data, size);
-	inode->i_size = private->size = size;
+	inode->i_size = private->total_size = size;
 
 	inode->i_private = private;
 
-	if (time.tv_sec)
-		inode->i_mtime = inode->i_ctime = time;
+	if (record->time.tv_sec)
+		inode->i_mtime = inode->i_ctime = record->time;
 
 	d_add(dentry, inode);
 
@@ -401,13 +422,10 @@ int pstore_mkfile(enum pstore_type_id type, char *psname, u64 id, int count,
 	list_add(&private->list, &allpstore);
 	spin_unlock_irqrestore(&allpstore_lock, flags);
 
-	inode_unlock(d_inode(root));
-
 	return 0;
 
-fail_lockedalloc:
-	inode_unlock(d_inode(root));
-	kfree(private);
+fail_private:
+	free_pstore_private(private);
 fail_alloc:
 	iput(inode);
 
@@ -415,12 +433,31 @@ fail:
 	return rc;
 }
 
+/*
+ * Read all the records from the persistent store. Create
+ * files in our filesystem.  Don't warn about -EEXIST errors
+ * when we are re-scanning the backing store looking to add new
+ * error records.
+ */
+void pstore_get_records(int quiet)
+{
+	struct pstore_info *psi = psinfo;
+	struct dentry *root;
+
+	if (!psi || !pstore_sb)
+		return;
+
+	root = pstore_sb->s_root;
+
+	inode_lock(d_inode(root));
+	pstore_get_backend_records(psi, root, quiet);
+	inode_unlock(d_inode(root));
+}
+
 static int pstore_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct inode *inode;
 
-	save_mount_options(sb, data);
-
 	pstore_sb = sb;
 
 	sb->s_maxbytes		= MAX_LFS_FILESIZE;
diff --git a/fs/pstore/internal.h b/fs/pstore/internal.h
index da416e6591c9..7f4e48c8d188 100644
--- a/fs/pstore/internal.h
+++ b/fs/pstore/internal.h
@@ -5,6 +5,9 @@
 #include <linux/time.h>
 #include <linux/pstore.h>
 
+#define PSTORE_DEFAULT_KMSG_BYTES 10240
+extern unsigned long kmsg_bytes;
+
 #ifdef CONFIG_PSTORE_FTRACE
 extern void pstore_register_ftrace(void);
 extern void pstore_unregister_ftrace(void);
@@ -25,10 +28,12 @@ extern struct pstore_info *psinfo;
 
 extern void	pstore_set_kmsg_bytes(int);
 extern void	pstore_get_records(int);
-extern int	pstore_mkfile(enum pstore_type_id, char *psname, u64 id,
-			      int count, char *data, bool compressed,
-			      size_t size, struct timespec time,
-			      struct pstore_info *psi);
+extern void	pstore_get_backend_records(struct pstore_info *psi,
+					   struct dentry *root, int quiet);
+extern int	pstore_mkfile(struct dentry *root,
+			      struct pstore_record *record);
 extern bool	pstore_is_mounted(void);
+extern void	pstore_record_init(struct pstore_record *record,
+				   struct pstore_info *psi);
 
 #endif
diff --git a/fs/pstore/platform.c b/fs/pstore/platform.c
index 729677e18e36..2b21d180157c 100644
--- a/fs/pstore/platform.c
+++ b/fs/pstore/platform.c
@@ -99,7 +99,7 @@ static char *big_oops_buf;
 static size_t big_oops_buf_sz;
 
 /* How much of the console log to snapshot */
-static unsigned long kmsg_bytes = 10240;
+unsigned long kmsg_bytes = PSTORE_DEFAULT_KMSG_BYTES;
 
 void pstore_set_kmsg_bytes(int bytes)
 {
@@ -267,7 +267,7 @@ static void free_zlib(void)
 	big_oops_buf_sz = 0;
 }
 
-static struct pstore_zbackend backend_zlib = {
+static const struct pstore_zbackend backend_zlib = {
 	.compress	= compress_zlib,
 	.decompress	= decompress_zlib,
 	.allocate	= allocate_zlib,
@@ -328,7 +328,7 @@ static void free_lzo(void)
 	big_oops_buf_sz = 0;
 }
 
-static struct pstore_zbackend backend_lzo = {
+static const struct pstore_zbackend backend_lzo = {
 	.compress	= compress_lzo,
 	.decompress	= decompress_lzo,
 	.allocate	= allocate_lzo,
@@ -342,31 +342,35 @@ static int compress_lz4(const void *in, void *out, size_t inlen, size_t outlen)
 {
 	int ret;
 
-	ret = lz4_compress(in, inlen, out, &outlen, workspace);
-	if (ret) {
-		pr_err("lz4_compress error, ret = %d!\n", ret);
+	ret = LZ4_compress_default(in, out, inlen, outlen, workspace);
+	if (!ret) {
+		pr_err("LZ4_compress_default error; compression failed!\n");
 		return -EIO;
 	}
 
-	return outlen;
+	return ret;
 }
 
 static int decompress_lz4(void *in, void *out, size_t inlen, size_t outlen)
 {
 	int ret;
 
-	ret = lz4_decompress_unknownoutputsize(in, inlen, out, &outlen);
-	if (ret) {
-		pr_err("lz4_decompress error, ret = %d!\n", ret);
+	ret = LZ4_decompress_safe(in, out, inlen, outlen);
+	if (ret < 0) {
+		/*
+		 * LZ4_decompress_safe will return an error code
+		 * (< 0) if decompression failed
+		 */
+		pr_err("LZ4_decompress_safe error, ret = %d!\n", ret);
 		return -EIO;
 	}
 
-	return outlen;
+	return ret;
 }
 
 static void allocate_lz4(void)
 {
-	big_oops_buf_sz = lz4_compressbound(psinfo->bufsize);
+	big_oops_buf_sz = LZ4_compressBound(psinfo->bufsize);
 	big_oops_buf = kmalloc(big_oops_buf_sz, GFP_KERNEL);
 	if (big_oops_buf) {
 		workspace = kmalloc(LZ4_MEM_COMPRESS, GFP_KERNEL);
@@ -389,7 +393,7 @@ static void free_lz4(void)
 	big_oops_buf_sz = 0;
 }
 
-static struct pstore_zbackend backend_lz4 = {
+static const struct pstore_zbackend backend_lz4 = {
 	.compress	= compress_lz4,
 	.decompress	= decompress_lz4,
 	.allocate	= allocate_lz4,
@@ -398,7 +402,7 @@ static struct pstore_zbackend backend_lz4 = {
 };
 #endif
 
-static struct pstore_zbackend *zbackend =
+static const struct pstore_zbackend *zbackend =
 #if defined(CONFIG_PSTORE_ZLIB_COMPRESS)
 	&backend_zlib;
 #elif defined(CONFIG_PSTORE_LZO_COMPRESS)
@@ -470,6 +474,20 @@ static size_t copy_kmsg_to_buffer(int hsize, size_t len)
 	return total_len;
 }
 
+void pstore_record_init(struct pstore_record *record,
+			struct pstore_info *psinfo)
+{
+	memset(record, 0, sizeof(*record));
+
+	record->psi = psinfo;
+
+	/* Report zeroed timestamp if called before timekeeping has resumed. */
+	if (__getnstimeofday(&record->time)) {
+		record->time.tv_sec = 0;
+		record->time.tv_nsec = 0;
+	}
+}
+
 /*
  * callback from kmsg_dump. (s2,l2) has the most recently
  * written bytes, older bytes are in (s1,l1). Save as much
@@ -480,7 +498,6 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 {
 	unsigned long	total = 0;
 	const char	*why;
-	u64		id;
 	unsigned int	part = 1;
 	unsigned long	flags = 0;
 	int		is_locked;
@@ -502,48 +519,58 @@ static void pstore_dump(struct kmsg_dumper *dumper,
 	oopscount++;
 	while (total < kmsg_bytes) {
 		char *dst;
-		unsigned long size;
-		int hsize;
+		size_t dst_size;
+		int header_size;
 		int zipped_len = -1;
-		size_t len;
-		bool compressed = false;
-		size_t total_len;
+		size_t dump_size;
+		struct pstore_record record;
+
+		pstore_record_init(&record, psinfo);
+		record.type = PSTORE_TYPE_DMESG;
+		record.count = oopscount;
+		record.reason = reason;
+		record.part = part;
+		record.buf = psinfo->buf;
 
 		if (big_oops_buf && is_locked) {
 			dst = big_oops_buf;
-			size = big_oops_buf_sz;
+			dst_size = big_oops_buf_sz;
 		} else {
 			dst = psinfo->buf;
-			size = psinfo->bufsize;
+			dst_size = psinfo->bufsize;
 		}
 
-		hsize = sprintf(dst, "%s#%d Part%u\n", why, oopscount, part);
-		size -= hsize;
+		/* Write dump header. */
+		header_size = snprintf(dst, dst_size, "%s#%d Part%u\n", why,
+				 oopscount, part);
+		dst_size -= header_size;
 
-		if (!kmsg_dump_get_buffer(dumper, true, dst + hsize,
-					  size, &len))
+		/* Write dump contents. */
+		if (!kmsg_dump_get_buffer(dumper, true, dst + header_size,
+					  dst_size, &dump_size))
 			break;
 
 		if (big_oops_buf && is_locked) {
 			zipped_len = pstore_compress(dst, psinfo->buf,
-						hsize + len, psinfo->bufsize);
+						header_size + dump_size,
+						psinfo->bufsize);
 
 			if (zipped_len > 0) {
-				compressed = true;
-				total_len = zipped_len;
+				record.compressed = true;
+				record.size = zipped_len;
 			} else {
-				total_len = copy_kmsg_to_buffer(hsize, len);
+				record.size = copy_kmsg_to_buffer(header_size,
+								  dump_size);
 			}
 		} else {
-			total_len = hsize + len;
+			record.size = header_size + dump_size;
 		}
 
-		ret = psinfo->write(PSTORE_TYPE_DMESG, reason, &id, part,
-				    oopscount, compressed, total_len, psinfo);
+		ret = psinfo->write(&record);
 		if (ret == 0 && reason == KMSG_DUMP_OOPS && pstore_is_mounted())
 			pstore_new_entry = 1;
 
-		total += total_len;
+		total += record.size;
 		part++;
 	}
 	if (is_locked)
@@ -573,8 +600,11 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c)
 	const char *e = s + c;
 
 	while (s < e) {
+		struct pstore_record record;
 		unsigned long flags;
-		u64 id;
+
+		pstore_record_init(&record, psinfo);
+		record.type = PSTORE_TYPE_CONSOLE;
 
 		if (c > psinfo->bufsize)
 			c = psinfo->bufsize;
@@ -585,8 +615,9 @@ static void pstore_console_write(struct console *con, const char *s, unsigned c)
 		} else {
 			spin_lock_irqsave(&psinfo->buf_lock, flags);
 		}
-		psinfo->write_buf(PSTORE_TYPE_CONSOLE, 0, &id, 0,
-				  s, 0, c, psinfo);
+		record.buf = (char *)s;
+		record.size = c;
+		psinfo->write(&record);
 		spin_unlock_irqrestore(&psinfo->buf_lock, flags);
 		s += c;
 		c = e - s;
@@ -614,48 +645,27 @@ static void pstore_register_console(void) {}
 static void pstore_unregister_console(void) {}
 #endif
 
-static int pstore_write_compat(enum pstore_type_id type,
-			       enum kmsg_dump_reason reason,
-			       u64 *id, unsigned int part, int count,
-			       bool compressed, size_t size,
-			       struct pstore_info *psi)
-{
-	return psi->write_buf(type, reason, id, part, psinfo->buf, compressed,
-			     size, psi);
-}
-
-static int pstore_write_buf_user_compat(enum pstore_type_id type,
-			       enum kmsg_dump_reason reason,
-			       u64 *id, unsigned int part,
-			       const char __user *buf,
-			       bool compressed, size_t size,
-			       struct pstore_info *psi)
-{
-	unsigned long flags = 0;
-	size_t i, bufsize = size;
-	long ret = 0;
-
-	if (unlikely(!access_ok(VERIFY_READ, buf, size)))
-		return -EFAULT;
-	if (bufsize > psinfo->bufsize)
-		bufsize = psinfo->bufsize;
-	spin_lock_irqsave(&psinfo->buf_lock, flags);
-	for (i = 0; i < size; ) {
-		size_t c = min(size - i, bufsize);
-
-		ret = __copy_from_user(psinfo->buf, buf + i, c);
-		if (unlikely(ret != 0)) {
-			ret = -EFAULT;
-			break;
-		}
-		ret = psi->write_buf(type, reason, id, part, psinfo->buf,
-				     compressed, c, psi);
-		if (unlikely(ret < 0))
-			break;
-		i += c;
+static int pstore_write_user_compat(struct pstore_record *record,
+				    const char __user *buf)
+{
+	int ret = 0;
+
+	if (record->buf)
+		return -EINVAL;
+
+	record->buf = memdup_user(buf, record->size);
+	if (unlikely(IS_ERR(record->buf))) {
+		ret = PTR_ERR(record->buf);
+		goto out;
 	}
-	spin_unlock_irqrestore(&psinfo->buf_lock, flags);
-	return unlikely(ret < 0) ? ret : size;
+
+	ret = record->psi->write(record);
+
+	kfree(record->buf);
+out:
+	record->buf = NULL;
+
+	return unlikely(ret < 0) ? ret : record->size;
 }
 
 /*
@@ -669,19 +679,35 @@ int pstore_register(struct pstore_info *psi)
 {
 	struct module *owner = psi->owner;
 
-	if (backend && strcmp(backend, psi->name))
+	if (backend && strcmp(backend, psi->name)) {
+		pr_warn("ignoring unexpected backend '%s'\n", psi->name);
 		return -EPERM;
+	}
+
+	/* Sanity check flags. */
+	if (!psi->flags) {
+		pr_warn("backend '%s' must support at least one frontend\n",
+			psi->name);
+		return -EINVAL;
+	}
+
+	/* Check for required functions. */
+	if (!psi->read || !psi->write) {
+		pr_warn("backend '%s' must implement read() and write()\n",
+			psi->name);
+		return -EINVAL;
+	}
 
 	spin_lock(&pstore_lock);
 	if (psinfo) {
+		pr_warn("backend '%s' already loaded: ignoring '%s'\n",
+			psinfo->name, psi->name);
 		spin_unlock(&pstore_lock);
 		return -EBUSY;
 	}
 
-	if (!psi->write)
-		psi->write = pstore_write_compat;
-	if (!psi->write_buf_user)
-		psi->write_buf_user = pstore_write_buf_user_compat;
+	if (!psi->write_user)
+		psi->write_user = pstore_write_user_compat;
 	psinfo = psi;
 	mutex_init(&psinfo->read_mutex);
 	spin_unlock(&pstore_lock);
@@ -705,6 +731,7 @@ int pstore_register(struct pstore_info *psi)
 	if (psi->flags & PSTORE_FLAGS_PMSG)
 		pstore_register_pmsg();
 
+	/* Start watching for new records, if desired. */
 	if (pstore_update_ms >= 0) {
 		pstore_timer.expires = jiffies +
 			msecs_to_jiffies(pstore_update_ms);
@@ -717,16 +744,21 @@ int pstore_register(struct pstore_info *psi)
 	 */
 	backend = psi->name;
 
-	module_put(owner);
-
 	pr_info("Registered %s as persistent store backend\n", psi->name);
 
+	module_put(owner);
+
 	return 0;
 }
 EXPORT_SYMBOL_GPL(pstore_register);
 
 void pstore_unregister(struct pstore_info *psi)
 {
+	/* Stop timer and make sure all work has finished. */
+	pstore_update_ms = -1;
+	del_timer_sync(&pstore_timer);
+	flush_work(&pstore_work);
+
 	if (psi->flags & PSTORE_FLAGS_PMSG)
 		pstore_unregister_pmsg();
 	if (psi->flags & PSTORE_FLAGS_FTRACE)
@@ -743,66 +775,105 @@ void pstore_unregister(struct pstore_info *psi)
 }
 EXPORT_SYMBOL_GPL(pstore_unregister);
 
+static void decompress_record(struct pstore_record *record)
+{
+	int unzipped_len;
+	char *decompressed;
+
+	if (!record->compressed)
+		return;
+
+	/* Only PSTORE_TYPE_DMESG support compression. */
+	if (record->type != PSTORE_TYPE_DMESG) {
+		pr_warn("ignored compressed record type %d\n", record->type);
+		return;
+	}
+
+	/* No compression method has created the common buffer. */
+	if (!big_oops_buf) {
+		pr_warn("no decompression buffer allocated\n");
+		return;
+	}
+
+	unzipped_len = pstore_decompress(record->buf, big_oops_buf,
+					 record->size, big_oops_buf_sz);
+	if (unzipped_len <= 0) {
+		pr_err("decompression failed: %d\n", unzipped_len);
+		return;
+	}
+
+	/* Build new buffer for decompressed contents. */
+	decompressed = kmalloc(unzipped_len + record->ecc_notice_size,
+			       GFP_KERNEL);
+	if (!decompressed) {
+		pr_err("decompression ran out of memory\n");
+		return;
+	}
+	memcpy(decompressed, big_oops_buf, unzipped_len);
+
+	/* Append ECC notice to decompressed buffer. */
+	memcpy(decompressed + unzipped_len, record->buf + record->size,
+	       record->ecc_notice_size);
+
+	/* Swap out compresed contents with decompressed contents. */
+	kfree(record->buf);
+	record->buf = decompressed;
+	record->size = unzipped_len;
+	record->compressed = false;
+}
+
 /*
- * Read all the records from the persistent store. Create
+ * Read all the records from one persistent store backend. Create
  * files in our filesystem.  Don't warn about -EEXIST errors
  * when we are re-scanning the backing store looking to add new
  * error records.
  */
-void pstore_get_records(int quiet)
-{
-	struct pstore_info *psi = psinfo;
-	char			*buf = NULL;
-	ssize_t			size;
-	u64			id;
-	int			count;
-	enum pstore_type_id	type;
-	struct timespec		time;
-	int			failed = 0, rc;
-	bool			compressed;
-	int			unzipped_len = -1;
-	ssize_t			ecc_notice_size = 0;
-
-	if (!psi)
+void pstore_get_backend_records(struct pstore_info *psi,
+				struct dentry *root, int quiet)
+{
+	int failed = 0;
+	unsigned int stop_loop = 65536;
+
+	if (!psi || !root)
 		return;
 
 	mutex_lock(&psi->read_mutex);
 	if (psi->open && psi->open(psi))
 		goto out;
 
-	while ((size = psi->read(&id, &type, &count, &time, &buf, &compressed,
-				 &ecc_notice_size, psi)) > 0) {
-		if (compressed && (type == PSTORE_TYPE_DMESG)) {
-			if (big_oops_buf)
-				unzipped_len = pstore_decompress(buf,
-							big_oops_buf, size,
-							big_oops_buf_sz);
-
-			if (unzipped_len > 0) {
-				if (ecc_notice_size)
-					memcpy(big_oops_buf + unzipped_len,
-					       buf + size, ecc_notice_size);
-				kfree(buf);
-				buf = big_oops_buf;
-				size = unzipped_len;
-				compressed = false;
-			} else {
-				pr_err("decompression failed;returned %d\n",
-				       unzipped_len);
-				compressed = true;
-			}
+	/*
+	 * Backend callback read() allocates record.buf. decompress_record()
+	 * may reallocate record.buf. On success, pstore_mkfile() will keep
+	 * the record.buf, so free it only on failure.
+	 */
+	for (; stop_loop; stop_loop--) {
+		struct pstore_record *record;
+		int rc;
+
+		record = kzalloc(sizeof(*record), GFP_KERNEL);
+		if (!record) {
+			pr_err("out of memory creating record\n");
+			break;
+		}
+		pstore_record_init(record, psi);
+
+		record->size = psi->read(record);
+
+		/* No more records left in backend? */
+		if (record->size <= 0) {
+			kfree(record);
+			break;
+		}
+
+		decompress_record(record);
+		rc = pstore_mkfile(root, record);
+		if (rc) {
+			/* pstore_mkfile() did not take record, so free it. */
+			kfree(record->buf);
+			kfree(record);
+			if (rc != -EEXIST || !quiet)
+				failed++;
 		}
-		rc = pstore_mkfile(type, psi->name, id, count, buf,
-				   compressed, size + ecc_notice_size,
-				   time, psi);
-		if (unzipped_len < 0) {
-			/* Free buffer other than big oops */
-			kfree(buf);
-			buf = NULL;
-		} else
-			unzipped_len = -1;
-		if (rc && (rc != -EEXIST || !quiet))
-			failed++;
 	}
 	if (psi->close)
 		psi->close(psi);
@@ -810,8 +881,11 @@ out:
 	mutex_unlock(&psi->read_mutex);
 
 	if (failed)
-		pr_warn("failed to load %d record(s) from '%s'\n",
+		pr_warn("failed to create %d record(s) from '%s'\n",
 			failed, psi->name);
+	if (!stop_loop)
+		pr_err("looping? Too many records seen from '%s'\n",
+			psi->name);
 }
 
 static void pstore_dowork(struct work_struct *work)
@@ -826,7 +900,9 @@ static void pstore_timefunc(unsigned long dummy)
 		schedule_work(&pstore_work);
 	}
 
-	mod_timer(&pstore_timer, jiffies + msecs_to_jiffies(pstore_update_ms));
+	if (pstore_update_ms >= 0)
+		mod_timer(&pstore_timer,
+			  jiffies + msecs_to_jiffies(pstore_update_ms));
 }
 
 module_param(backend, charp, 0444);
diff --git a/fs/pstore/pmsg.c b/fs/pstore/pmsg.c
index 78f6176c020f..24db02de1787 100644
--- a/fs/pstore/pmsg.c
+++ b/fs/pstore/pmsg.c
@@ -15,7 +15,6 @@
 #include <linux/device.h>
 #include <linux/fs.h>
 #include <linux/uaccess.h>
-#include <linux/vmalloc.h>
 #include "internal.h"
 
 static DEFINE_MUTEX(pmsg_lock);
@@ -23,19 +22,22 @@ static DEFINE_MUTEX(pmsg_lock);
 static ssize_t write_pmsg(struct file *file, const char __user *buf,
 			  size_t count, loff_t *ppos)
 {
-	u64 id;
+	struct pstore_record record;
 	int ret;
 
 	if (!count)
 		return 0;
 
-	/* check outside lock, page in any data. write_buf_user also checks */
+	pstore_record_init(&record, psinfo);
+	record.type = PSTORE_TYPE_PMSG;
+	record.size = count;
+
+	/* check outside lock, page in any data. write_user also checks */
 	if (!access_ok(VERIFY_READ, buf, count))
 		return -EFAULT;
 
 	mutex_lock(&pmsg_lock);
-	ret = psinfo->write_buf_user(PSTORE_TYPE_PMSG, 0, &id, 0, buf, 0, count,
-				     psinfo);
+	ret = psinfo->write_user(&record, buf);
 	mutex_unlock(&pmsg_lock);
 	return ret ? ret : count;
 }
diff --git a/fs/pstore/ram.c b/fs/pstore/ram.c
index 27c059e1760a..7125b398d312 100644
--- a/fs/pstore/ram.c
+++ b/fs/pstore/ram.c
@@ -27,7 +27,6 @@
 #include <linux/module.h>
 #include <linux/version.h>
 #include <linux/pstore.h>
-#include <linux/time.h>
 #include <linux/io.h>
 #include <linux/ioport.h>
 #include <linux/platform_device.h>
@@ -58,7 +57,7 @@ module_param_named(pmsg_size, ramoops_pmsg_size, ulong, 0400);
 MODULE_PARM_DESC(pmsg_size, "size of user space message log");
 
 static unsigned long long mem_address;
-module_param(mem_address, ullong, 0400);
+module_param_hw(mem_address, ullong, other, 0400);
 MODULE_PARM_DESC(mem_address,
 		"start of reserved RAM used to store oops/panic logs");
 
@@ -133,7 +132,8 @@ ramoops_get_next_prz(struct persistent_ram_zone *przs[], uint *c, uint max,
 	struct persistent_ram_zone *prz;
 	int i = (*c)++;
 
-	if (i >= max)
+	/* Give up if we never existed or have hit the end. */
+	if (!przs || i >= max)
 		return NULL;
 
 	prz = przs[i];
@@ -234,35 +234,34 @@ static ssize_t ftrace_log_combine(struct persistent_ram_zone *dest,
 	return 0;
 }
 
-static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
-				   int *count, struct timespec *time,
-				   char **buf, bool *compressed,
-				   ssize_t *ecc_notice_size,
-				   struct pstore_info *psi)
+static ssize_t ramoops_pstore_read(struct pstore_record *record)
 {
 	ssize_t size = 0;
-	struct ramoops_context *cxt = psi->data;
+	struct ramoops_context *cxt = record->psi->data;
 	struct persistent_ram_zone *prz = NULL;
 	int header_length = 0;
 	bool free_prz = false;
 
-	/* Ramoops headers provide time stamps for PSTORE_TYPE_DMESG, but
+	/*
+	 * Ramoops headers provide time stamps for PSTORE_TYPE_DMESG, but
 	 * PSTORE_TYPE_CONSOLE and PSTORE_TYPE_FTRACE don't currently have
 	 * valid time stamps, so it is initialized to zero.
 	 */
-	time->tv_sec = 0;
-	time->tv_nsec = 0;
-	*compressed = false;
+	record->time.tv_sec = 0;
+	record->time.tv_nsec = 0;
+	record->compressed = false;
 
 	/* Find the next valid persistent_ram_zone for DMESG */
 	while (cxt->dump_read_cnt < cxt->max_dump_cnt && !prz) {
 		prz = ramoops_get_next_prz(cxt->dprzs, &cxt->dump_read_cnt,
-					   cxt->max_dump_cnt, id, type,
+					   cxt->max_dump_cnt, &record->id,
+					   &record->type,
 					   PSTORE_TYPE_DMESG, 1);
 		if (!prz_ok(prz))
 			continue;
 		header_length = ramoops_read_kmsg_hdr(persistent_ram_old(prz),
-						      time, compressed);
+						      &record->time,
+						      &record->compressed);
 		/* Clear and skip this DMESG record if it has no valid header */
 		if (!header_length) {
 			persistent_ram_free_old(prz);
@@ -273,18 +272,20 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 
 	if (!prz_ok(prz))
 		prz = ramoops_get_next_prz(&cxt->cprz, &cxt->console_read_cnt,
-					   1, id, type, PSTORE_TYPE_CONSOLE, 0);
+					   1, &record->id, &record->type,
+					   PSTORE_TYPE_CONSOLE, 0);
 
 	if (!prz_ok(prz))
 		prz = ramoops_get_next_prz(&cxt->mprz, &cxt->pmsg_read_cnt,
-					   1, id, type, PSTORE_TYPE_PMSG, 0);
+					   1, &record->id, &record->type,
+					   PSTORE_TYPE_PMSG, 0);
 
 	/* ftrace is last since it may want to dynamically allocate memory. */
 	if (!prz_ok(prz)) {
 		if (!(cxt->flags & RAMOOPS_FLAG_FTRACE_PER_CPU)) {
 			prz = ramoops_get_next_prz(cxt->fprzs,
-					&cxt->ftrace_read_cnt, 1, id, type,
-					PSTORE_TYPE_FTRACE, 0);
+					&cxt->ftrace_read_cnt, 1, &record->id,
+					&record->type, PSTORE_TYPE_FTRACE, 0);
 		} else {
 			/*
 			 * Build a new dummy record which combines all the
@@ -301,8 +302,10 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 			while (cxt->ftrace_read_cnt < cxt->max_ftrace_cnt) {
 				prz_next = ramoops_get_next_prz(cxt->fprzs,
 						&cxt->ftrace_read_cnt,
-						cxt->max_ftrace_cnt, id,
-						type, PSTORE_TYPE_FTRACE, 0);
+						cxt->max_ftrace_cnt,
+						&record->id,
+						&record->type,
+						PSTORE_TYPE_FTRACE, 0);
 
 				if (!prz_ok(prz_next))
 					continue;
@@ -315,7 +318,7 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 				if (size)
 					goto out;
 			}
-			*id = 0;
+			record->id = 0;
 			prz = tmp_prz;
 		}
 	}
@@ -328,17 +331,19 @@ static ssize_t ramoops_pstore_read(u64 *id, enum pstore_type_id *type,
 	size = persistent_ram_old_size(prz) - header_length;
 
 	/* ECC correction notice */
-	*ecc_notice_size = persistent_ram_ecc_string(prz, NULL, 0);
+	record->ecc_notice_size = persistent_ram_ecc_string(prz, NULL, 0);
 
-	*buf = kmalloc(size + *ecc_notice_size + 1, GFP_KERNEL);
-	if (*buf == NULL) {
+	record->buf = kmalloc(size + record->ecc_notice_size + 1, GFP_KERNEL);
+	if (record->buf == NULL) {
 		size = -ENOMEM;
 		goto out;
 	}
 
-	memcpy(*buf, (char *)persistent_ram_old(prz) + header_length, size);
+	memcpy(record->buf, (char *)persistent_ram_old(prz) + header_length,
+	       size);
 
-	persistent_ram_ecc_string(prz, *buf + size, *ecc_notice_size + 1);
+	persistent_ram_ecc_string(prz, record->buf + size,
+				  record->ecc_notice_size + 1);
 
 out:
 	if (free_prz) {
@@ -350,20 +355,15 @@ out:
 }
 
 static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz,
-				     bool compressed)
+				     struct pstore_record *record)
 {
 	char *hdr;
-	struct timespec timestamp;
 	size_t len;
 
-	/* Report zeroed timestamp if called before timekeeping has resumed. */
-	if (__getnstimeofday(&timestamp)) {
-		timestamp.tv_sec = 0;
-		timestamp.tv_nsec = 0;
-	}
 	hdr = kasprintf(GFP_ATOMIC, RAMOOPS_KERNMSG_HDR "%lu.%lu-%c\n",
-		(long)timestamp.tv_sec, (long)(timestamp.tv_nsec / 1000),
-		compressed ? 'C' : 'D');
+		record->time.tv_sec,
+		record->time.tv_nsec / 1000,
+		record->compressed ? 'C' : 'D');
 	WARN_ON_ONCE(!hdr);
 	len = hdr ? strlen(hdr) : 0;
 	persistent_ram_write(prz, hdr, len);
@@ -372,23 +372,18 @@ static size_t ramoops_write_kmsg_hdr(struct persistent_ram_zone *prz,
 	return len;
 }
 
-static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
-					    enum kmsg_dump_reason reason,
-					    u64 *id, unsigned int part,
-					    const char *buf,
-					    bool compressed, size_t size,
-					    struct pstore_info *psi)
+static int notrace ramoops_pstore_write(struct pstore_record *record)
 {
-	struct ramoops_context *cxt = psi->data;
+	struct ramoops_context *cxt = record->psi->data;
 	struct persistent_ram_zone *prz;
-	size_t hlen;
+	size_t size, hlen;
 
-	if (type == PSTORE_TYPE_CONSOLE) {
+	if (record->type == PSTORE_TYPE_CONSOLE) {
 		if (!cxt->cprz)
 			return -ENOMEM;
-		persistent_ram_write(cxt->cprz, buf, size);
+		persistent_ram_write(cxt->cprz, record->buf, record->size);
 		return 0;
-	} else if (type == PSTORE_TYPE_FTRACE) {
+	} else if (record->type == PSTORE_TYPE_FTRACE) {
 		int zonenum;
 
 		if (!cxt->fprzs)
@@ -401,33 +396,36 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
 		else
 			zonenum = 0;
 
-		persistent_ram_write(cxt->fprzs[zonenum], buf, size);
+		persistent_ram_write(cxt->fprzs[zonenum], record->buf,
+				     record->size);
 		return 0;
-	} else if (type == PSTORE_TYPE_PMSG) {
+	} else if (record->type == PSTORE_TYPE_PMSG) {
 		pr_warn_ratelimited("PMSG shouldn't call %s\n", __func__);
 		return -EINVAL;
 	}
 
-	if (type != PSTORE_TYPE_DMESG)
+	if (record->type != PSTORE_TYPE_DMESG)
 		return -EINVAL;
 
-	/* Out of the various dmesg dump types, ramoops is currently designed
+	/*
+	 * Out of the various dmesg dump types, ramoops is currently designed
 	 * to only store crash logs, rather than storing general kernel logs.
 	 */
-	if (reason != KMSG_DUMP_OOPS &&
-	    reason != KMSG_DUMP_PANIC)
+	if (record->reason != KMSG_DUMP_OOPS &&
+	    record->reason != KMSG_DUMP_PANIC)
 		return -EINVAL;
 
 	/* Skip Oopes when configured to do so. */
-	if (reason == KMSG_DUMP_OOPS && !cxt->dump_oops)
+	if (record->reason == KMSG_DUMP_OOPS && !cxt->dump_oops)
 		return -EINVAL;
 
-	/* Explicitly only take the first part of any new crash.
+	/*
+	 * Explicitly only take the first part of any new crash.
 	 * If our buffer is larger than kmsg_bytes, this can never happen,
 	 * and if our buffer is smaller than kmsg_bytes, we don't want the
 	 * report split across multiple records.
 	 */
-	if (part != 1)
+	if (record->part != 1)
 		return -ENOSPC;
 
 	if (!cxt->dprzs)
@@ -435,53 +433,50 @@ static int notrace ramoops_pstore_write_buf(enum pstore_type_id type,
 
 	prz = cxt->dprzs[cxt->dump_write_cnt];
 
-	hlen = ramoops_write_kmsg_hdr(prz, compressed);
+	/* Build header and append record contents. */
+	hlen = ramoops_write_kmsg_hdr(prz, record);
+	size = record->size;
 	if (size + hlen > prz->buffer_size)
 		size = prz->buffer_size - hlen;
-	persistent_ram_write(prz, buf, size);
+	persistent_ram_write(prz, record->buf, size);
 
 	cxt->dump_write_cnt = (cxt->dump_write_cnt + 1) % cxt->max_dump_cnt;
 
 	return 0;
 }
 
-static int notrace ramoops_pstore_write_buf_user(enum pstore_type_id type,
-						 enum kmsg_dump_reason reason,
-						 u64 *id, unsigned int part,
-						 const char __user *buf,
-						 bool compressed, size_t size,
-						 struct pstore_info *psi)
+static int notrace ramoops_pstore_write_user(struct pstore_record *record,
+					     const char __user *buf)
 {
-	if (type == PSTORE_TYPE_PMSG) {
-		struct ramoops_context *cxt = psi->data;
+	if (record->type == PSTORE_TYPE_PMSG) {
+		struct ramoops_context *cxt = record->psi->data;
 
 		if (!cxt->mprz)
 			return -ENOMEM;
-		return persistent_ram_write_user(cxt->mprz, buf, size);
+		return persistent_ram_write_user(cxt->mprz, buf, record->size);
 	}
 
 	return -EINVAL;
 }
 
-static int ramoops_pstore_erase(enum pstore_type_id type, u64 id, int count,
-				struct timespec time, struct pstore_info *psi)
+static int ramoops_pstore_erase(struct pstore_record *record)
 {
-	struct ramoops_context *cxt = psi->data;
+	struct ramoops_context *cxt = record->psi->data;
 	struct persistent_ram_zone *prz;
 
-	switch (type) {
+	switch (record->type) {
 	case PSTORE_TYPE_DMESG:
-		if (id >= cxt->max_dump_cnt)
+		if (record->id >= cxt->max_dump_cnt)
 			return -EINVAL;
-		prz = cxt->dprzs[id];
+		prz = cxt->dprzs[record->id];
 		break;
 	case PSTORE_TYPE_CONSOLE:
 		prz = cxt->cprz;
 		break;
 	case PSTORE_TYPE_FTRACE:
-		if (id >= cxt->max_ftrace_cnt)
+		if (record->id >= cxt->max_ftrace_cnt)
 			return -EINVAL;
-		prz = cxt->fprzs[id];
+		prz = cxt->fprzs[record->id];
 		break;
 	case PSTORE_TYPE_PMSG:
 		prz = cxt->mprz;
@@ -502,8 +497,8 @@ static struct ramoops_context oops_cxt = {
 		.name	= "ramoops",
 		.open	= ramoops_pstore_open,
 		.read	= ramoops_pstore_read,
-		.write_buf	= ramoops_pstore_write_buf,
-		.write_buf_user	= ramoops_pstore_write_buf_user,
+		.write	= ramoops_pstore_write,
+		.write_user	= ramoops_pstore_write_user,
 		.erase	= ramoops_pstore_erase,
 	},
 };
diff --git a/fs/pstore/ram_core.c b/fs/pstore/ram_core.c
index a857338b7dab..e11672aa4575 100644
--- a/fs/pstore/ram_core.c
+++ b/fs/pstore/ram_core.c
@@ -467,8 +467,7 @@ static int persistent_ram_buffer_map(phys_addr_t start, phys_addr_t size,
 }
 
 static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig,
-				    struct persistent_ram_ecc_info *ecc_info,
-				    unsigned long flags)
+				    struct persistent_ram_ecc_info *ecc_info)
 {
 	int ret;
 
@@ -494,10 +493,9 @@ static int persistent_ram_post_init(struct persistent_ram_zone *prz, u32 sig,
 			 prz->buffer->sig);
 	}
 
+	/* Rewind missing or invalid memory area. */
 	prz->buffer->sig = sig;
 	persistent_ram_zap(prz);
-	prz->buffer_lock = __RAW_SPIN_LOCK_UNLOCKED(buffer_lock);
-	prz->flags = flags;
 
 	return 0;
 }
@@ -533,11 +531,15 @@ struct persistent_ram_zone *persistent_ram_new(phys_addr_t start, size_t size,
 		goto err;
 	}
 
+	/* Initialize general buffer state. */
+	raw_spin_lock_init(&prz->buffer_lock);
+	prz->flags = flags;
+
 	ret = persistent_ram_buffer_map(start, size, prz, memtype);
 	if (ret)
 		goto err;
 
-	ret = persistent_ram_post_init(prz, sig, ecc_info, flags);
+	ret = persistent_ram_post_init(prz, sig, ecc_info);
 	if (ret)
 		goto err;
 
diff --git a/fs/quota/dquot.c b/fs/quota/dquot.c
index 406fed92362a..53a17496c5c5 100644
--- a/fs/quota/dquot.c
+++ b/fs/quota/dquot.c
@@ -72,6 +72,7 @@
 #include <linux/proc_fs.h>
 #include <linux/security.h>
 #include <linux/sched.h>
+#include <linux/cred.h>
 #include <linux/kmod.h>
 #include <linux/namei.h>
 #include <linux/capability.h>
@@ -1511,6 +1512,22 @@ int dquot_initialize(struct inode *inode)
 }
 EXPORT_SYMBOL(dquot_initialize);
 
+bool dquot_initialize_needed(struct inode *inode)
+{
+	struct dquot **dquots;
+	int i;
+
+	if (!dquot_active(inode))
+		return false;
+
+	dquots = i_dquot(inode);
+	for (i = 0; i < MAXQUOTAS; i++)
+		if (!dquots[i] && sb_has_quota_active(inode->i_sb, i))
+			return true;
+	return false;
+}
+EXPORT_SYMBOL(dquot_initialize_needed);
+
 /*
  * Release all quotas referenced by inode.
  *
@@ -1893,6 +1910,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 {
 	qsize_t space, cur_space;
 	qsize_t rsv_space = 0;
+	qsize_t inode_usage = 1;
 	struct dquot *transfer_from[MAXQUOTAS] = {};
 	int cnt, ret = 0;
 	char is_valid[MAXQUOTAS] = {};
@@ -1902,6 +1920,13 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 
 	if (IS_NOQUOTA(inode))
 		return 0;
+
+	if (inode->i_sb->dq_op->get_inode_usage) {
+		ret = inode->i_sb->dq_op->get_inode_usage(inode, &inode_usage);
+		if (ret)
+			return ret;
+	}
+
 	/* Initialize the arrays */
 	for (cnt = 0; cnt < MAXQUOTAS; cnt++) {
 		warn_to[cnt].w_type = QUOTA_NL_NOWARN;
@@ -1929,7 +1954,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 			continue;
 		is_valid[cnt] = 1;
 		transfer_from[cnt] = i_dquot(inode)[cnt];
-		ret = check_idq(transfer_to[cnt], 1, &warn_to[cnt]);
+		ret = check_idq(transfer_to[cnt], inode_usage, &warn_to[cnt]);
 		if (ret)
 			goto over_quota;
 		ret = check_bdq(transfer_to[cnt], space, 0, &warn_to[cnt]);
@@ -1946,7 +1971,7 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 		/* Due to IO error we might not have transfer_from[] structure */
 		if (transfer_from[cnt]) {
 			int wtype;
-			wtype = info_idq_free(transfer_from[cnt], 1);
+			wtype = info_idq_free(transfer_from[cnt], inode_usage);
 			if (wtype != QUOTA_NL_NOWARN)
 				prepare_warning(&warn_from_inodes[cnt],
 						transfer_from[cnt], wtype);
@@ -1954,13 +1979,13 @@ int __dquot_transfer(struct inode *inode, struct dquot **transfer_to)
 			if (wtype != QUOTA_NL_NOWARN)
 				prepare_warning(&warn_from_space[cnt],
 						transfer_from[cnt], wtype);
-			dquot_decr_inodes(transfer_from[cnt], 1);
+			dquot_decr_inodes(transfer_from[cnt], inode_usage);
 			dquot_decr_space(transfer_from[cnt], cur_space);
 			dquot_free_reserved_space(transfer_from[cnt],
 						  rsv_space);
 		}
 
-		dquot_incr_inodes(transfer_to[cnt], 1);
+		dquot_incr_inodes(transfer_to[cnt], inode_usage);
 		dquot_incr_space(transfer_to[cnt], cur_space);
 		dquot_resv_space(transfer_to[cnt], rsv_space);
 
@@ -2187,8 +2212,7 @@ int dquot_disable(struct super_block *sb, int type, unsigned int flags)
 		/* This can happen when suspending quotas on remount-ro... */
 		if (toputinode[cnt] && !sb_has_quota_loaded(sb, cnt)) {
 			inode_lock(toputinode[cnt]);
-			toputinode[cnt]->i_flags &= ~(S_IMMUTABLE |
-				  S_NOATIME | S_NOQUOTA);
+			toputinode[cnt]->i_flags &= ~S_NOQUOTA;
 			truncate_inode_pages(&toputinode[cnt]->i_data, 0);
 			inode_unlock(toputinode[cnt]);
 			mark_inode_dirty_sync(toputinode[cnt]);
@@ -2236,7 +2260,6 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
 	struct super_block *sb = inode->i_sb;
 	struct quota_info *dqopt = sb_dqopt(sb);
 	int error;
-	int oldflags = -1;
 
 	if (!fmt)
 		return -ESRCH;
@@ -2284,9 +2307,7 @@ static int vfs_load_quota_inode(struct inode *inode, int type, int format_id,
 		 * possible) Also nobody should write to the file - we use
 		 * special IO operations which ignore the immutable bit. */
 		inode_lock(inode);
-		oldflags = inode->i_flags & (S_NOATIME | S_IMMUTABLE |
-					     S_NOQUOTA);
-		inode->i_flags |= S_NOQUOTA | S_NOATIME | S_IMMUTABLE;
+		inode->i_flags |= S_NOQUOTA;
 		inode_unlock(inode);
 		/*
 		 * When S_NOQUOTA is set, remove dquot references as no more
@@ -2328,14 +2349,9 @@ out_file_init:
 	dqopt->files[type] = NULL;
 	iput(inode);
 out_file_flags:
-	if (oldflags != -1) {
-		inode_lock(inode);
-		/* Set the flags back (in the case of accidental quotaon()
-		 * on a wrong file we don't want to mess up the flags) */
-		inode->i_flags &= ~(S_NOATIME | S_NOQUOTA | S_IMMUTABLE);
-		inode->i_flags |= oldflags;
-		inode_unlock(inode);
-	}
+	inode_lock(inode);
+	inode->i_flags &= ~S_NOQUOTA;
+	inode_unlock(inode);
 out_fmt:
 	put_quota_format(fmt);
 
@@ -2779,18 +2795,6 @@ int dquot_set_dqinfo(struct super_block *sb, int type, struct qc_info *ii)
 }
 EXPORT_SYMBOL(dquot_set_dqinfo);
 
-const struct quotactl_ops dquot_quotactl_ops = {
-	.quota_on	= dquot_quota_on,
-	.quota_off	= dquot_quota_off,
-	.quota_sync	= dquot_quota_sync,
-	.get_state	= dquot_get_state,
-	.set_info	= dquot_set_dqinfo,
-	.get_dqblk	= dquot_get_dqblk,
-	.get_nextdqblk	= dquot_get_next_dqblk,
-	.set_dqblk	= dquot_set_dqblk
-};
-EXPORT_SYMBOL(dquot_quotactl_ops);
-
 const struct quotactl_ops dquot_quotactl_sysfile_ops = {
 	.quota_enable	= dquot_quota_enable,
 	.quota_disable	= dquot_quota_disable,
diff --git a/fs/ramfs/inode.c b/fs/ramfs/inode.c
index 26e45863e499..11201b2d06b9 100644
--- a/fs/ramfs/inode.c
+++ b/fs/ramfs/inode.c
@@ -38,6 +38,14 @@
 #include <linux/uaccess.h>
 #include "internal.h"
 
+struct ramfs_mount_opts {
+	umode_t mode;
+};
+
+struct ramfs_fs_info {
+	struct ramfs_mount_opts mount_opts;
+};
+
 #define RAMFS_DEFAULT_MODE	0755
 
 static const struct super_operations ramfs_ops;
@@ -149,14 +157,22 @@ static const struct inode_operations ramfs_dir_inode_operations = {
 	.rename		= simple_rename,
 };
 
+/*
+ * Display the mount options in /proc/mounts.
+ */
+static int ramfs_show_options(struct seq_file *m, struct dentry *root)
+{
+	struct ramfs_fs_info *fsi = root->d_sb->s_fs_info;
+
+	if (fsi->mount_opts.mode != RAMFS_DEFAULT_MODE)
+		seq_printf(m, ",mode=%o", fsi->mount_opts.mode);
+	return 0;
+}
+
 static const struct super_operations ramfs_ops = {
 	.statfs		= simple_statfs,
 	.drop_inode	= generic_delete_inode,
-	.show_options	= generic_show_options,
-};
-
-struct ramfs_mount_opts {
-	umode_t mode;
+	.show_options	= ramfs_show_options,
 };
 
 enum {
@@ -169,10 +185,6 @@ static const match_table_t tokens = {
 	{Opt_err, NULL}
 };
 
-struct ramfs_fs_info {
-	struct ramfs_mount_opts mount_opts;
-};
-
 static int ramfs_parse_options(char *data, struct ramfs_mount_opts *opts)
 {
 	substring_t args[MAX_OPT_ARGS];
@@ -211,8 +223,6 @@ int ramfs_fill_super(struct super_block *sb, void *data, int silent)
 	struct inode *inode;
 	int err;
 
-	save_mount_options(sb, data);
-
 	fsi = kzalloc(sizeof(struct ramfs_fs_info), GFP_KERNEL);
 	sb->s_fs_info = fsi;
 	if (!fsi)
diff --git a/fs/read_write.c b/fs/read_write.c
index 5816d4c4cab0..0cc7033aa413 100644
--- a/fs/read_write.c
+++ b/fs/read_write.c
@@ -4,8 +4,9 @@
  *  Copyright (C) 1991, 1992  Linus Torvalds
  */
 
-#include <linux/slab.h> 
+#include <linux/slab.h>
 #include <linux/stat.h>
+#include <linux/sched/xacct.h>
 #include <linux/fcntl.h>
 #include <linux/file.h>
 #include <linux/uio.h>
@@ -23,9 +24,6 @@
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
 
-typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *);
-typedef ssize_t (*iter_fn_t)(struct kiocb *, struct iov_iter *);
-
 const struct file_operations generic_ro_fops = {
 	.llseek		= generic_file_llseek,
 	.read_iter	= generic_file_read_iter,
@@ -358,46 +356,6 @@ out_putf:
 }
 #endif
 
-ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos)
-{
-	struct kiocb kiocb;
-	ssize_t ret;
-
-	if (!file->f_op->read_iter)
-		return -EINVAL;
-
-	init_sync_kiocb(&kiocb, file);
-	kiocb.ki_pos = *ppos;
-
-	iter->type |= READ;
-	ret = file->f_op->read_iter(&kiocb, iter);
-	BUG_ON(ret == -EIOCBQUEUED);
-	if (ret > 0)
-		*ppos = kiocb.ki_pos;
-	return ret;
-}
-EXPORT_SYMBOL(vfs_iter_read);
-
-ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos)
-{
-	struct kiocb kiocb;
-	ssize_t ret;
-
-	if (!file->f_op->write_iter)
-		return -EINVAL;
-
-	init_sync_kiocb(&kiocb, file);
-	kiocb.ki_pos = *ppos;
-
-	iter->type |= WRITE;
-	ret = file->f_op->write_iter(&kiocb, iter);
-	BUG_ON(ret == -EIOCBQUEUED);
-	if (ret > 0)
-		*ppos = kiocb.ki_pos;
-	return ret;
-}
-EXPORT_SYMBOL(vfs_iter_write);
-
 int rw_verify_area(int read_write, struct file *file, const loff_t *ppos, size_t count)
 {
 	struct inode *inode;
@@ -439,7 +397,7 @@ static ssize_t new_sync_read(struct file *filp, char __user *buf, size_t len, lo
 	kiocb.ki_pos = *ppos;
 	iov_iter_init(&iter, READ, &iov, 1, len);
 
-	ret = filp->f_op->read_iter(&kiocb, &iter);
+	ret = call_read_iter(filp, &kiocb, &iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
@@ -496,7 +454,7 @@ static ssize_t new_sync_write(struct file *filp, const char __user *buf, size_t
 	kiocb.ki_pos = *ppos;
 	iov_iter_init(&iter, WRITE, &iov, 1, len);
 
-	ret = filp->f_op->write_iter(&kiocb, &iter);
+	ret = call_write_iter(filp, &kiocb, &iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	if (ret > 0)
 		*ppos = kiocb.ki_pos;
@@ -675,24 +633,21 @@ unsigned long iov_shorten(struct iovec *iov, unsigned long nr_segs, size_t to)
 EXPORT_SYMBOL(iov_shorten);
 
 static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
-		loff_t *ppos, iter_fn_t fn, int flags)
+		loff_t *ppos, int type, int flags)
 {
 	struct kiocb kiocb;
 	ssize_t ret;
 
-	if (flags & ~(RWF_HIPRI | RWF_DSYNC | RWF_SYNC))
-		return -EOPNOTSUPP;
-
 	init_sync_kiocb(&kiocb, filp);
-	if (flags & RWF_HIPRI)
-		kiocb.ki_flags |= IOCB_HIPRI;
-	if (flags & RWF_DSYNC)
-		kiocb.ki_flags |= IOCB_DSYNC;
-	if (flags & RWF_SYNC)
-		kiocb.ki_flags |= (IOCB_DSYNC | IOCB_SYNC);
+	ret = kiocb_set_rw_flags(&kiocb, flags);
+	if (ret)
+		return ret;
 	kiocb.ki_pos = *ppos;
 
-	ret = fn(&kiocb, iter);
+	if (type == READ)
+		ret = call_read_iter(filp, &kiocb, iter);
+	else
+		ret = call_write_iter(filp, &kiocb, iter);
 	BUG_ON(ret == -EIOCBQUEUED);
 	*ppos = kiocb.ki_pos;
 	return ret;
@@ -700,7 +655,7 @@ static ssize_t do_iter_readv_writev(struct file *filp, struct iov_iter *iter,
 
 /* Do it by hand, with file-ops */
 static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
-		loff_t *ppos, io_fn_t fn, int flags)
+		loff_t *ppos, int type, int flags)
 {
 	ssize_t ret = 0;
 
@@ -711,7 +666,13 @@ static ssize_t do_loop_readv_writev(struct file *filp, struct iov_iter *iter,
 		struct iovec iovec = iov_iter_iovec(iter);
 		ssize_t nr;
 
-		nr = fn(filp, iovec.iov_base, iovec.iov_len, ppos);
+		if (type == READ) {
+			nr = filp->f_op->read(filp, iovec.iov_base,
+					      iovec.iov_len, ppos);
+		} else {
+			nr = filp->f_op->write(filp, iovec.iov_base,
+					       iovec.iov_len, ppos);
+		}
 
 		if (nr < 0) {
 			if (!ret)
@@ -834,83 +795,189 @@ out:
 	return ret;
 }
 
-static ssize_t do_readv_writev(int type, struct file *file,
-			       const struct iovec __user * uvector,
-			       unsigned long nr_segs, loff_t *pos,
-			       int flags)
+#ifdef CONFIG_COMPAT
+ssize_t compat_rw_copy_check_uvector(int type,
+		const struct compat_iovec __user *uvector, unsigned long nr_segs,
+		unsigned long fast_segs, struct iovec *fast_pointer,
+		struct iovec **ret_pointer)
 {
-	size_t tot_len;
-	struct iovec iovstack[UIO_FASTIOV];
-	struct iovec *iov = iovstack;
-	struct iov_iter iter;
-	ssize_t ret;
-	io_fn_t fn;
-	iter_fn_t iter_fn;
-
-	ret = import_iovec(type, uvector, nr_segs,
-			   ARRAY_SIZE(iovstack), &iov, &iter);
-	if (ret < 0)
-		return ret;
+	compat_ssize_t tot_len;
+	struct iovec *iov = *ret_pointer = fast_pointer;
+	ssize_t ret = 0;
+	int seg;
 
-	tot_len = iov_iter_count(&iter);
-	if (!tot_len)
-		goto out;
-	ret = rw_verify_area(type, file, pos, tot_len);
-	if (ret < 0)
+	/*
+	 * SuS says "The readv() function *may* fail if the iovcnt argument
+	 * was less than or equal to 0, or greater than {IOV_MAX}.  Linux has
+	 * traditionally returned zero for zero segments, so...
+	 */
+	if (nr_segs == 0)
 		goto out;
 
-	if (type == READ) {
-		fn = file->f_op->read;
-		iter_fn = file->f_op->read_iter;
-	} else {
-		fn = (io_fn_t)file->f_op->write;
-		iter_fn = file->f_op->write_iter;
-		file_start_write(file);
+	ret = -EINVAL;
+	if (nr_segs > UIO_MAXIOV)
+		goto out;
+	if (nr_segs > fast_segs) {
+		ret = -ENOMEM;
+		iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL);
+		if (iov == NULL)
+			goto out;
 	}
+	*ret_pointer = iov;
 
-	if (iter_fn)
-		ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
-	else
-		ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
+	ret = -EFAULT;
+	if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector)))
+		goto out;
 
-	if (type != READ)
-		file_end_write(file);
+	/*
+	 * Single unix specification:
+	 * We should -EINVAL if an element length is not >= 0 and fitting an
+	 * ssize_t.
+	 *
+	 * In Linux, the total length is limited to MAX_RW_COUNT, there is
+	 * no overflow possibility.
+	 */
+	tot_len = 0;
+	ret = -EINVAL;
+	for (seg = 0; seg < nr_segs; seg++) {
+		compat_uptr_t buf;
+		compat_ssize_t len;
 
-out:
-	kfree(iov);
-	if ((ret + (type == READ)) > 0) {
-		if (type == READ)
-			fsnotify_access(file);
-		else
-			fsnotify_modify(file);
+		if (__get_user(len, &uvector->iov_len) ||
+		   __get_user(buf, &uvector->iov_base)) {
+			ret = -EFAULT;
+			goto out;
+		}
+		if (len < 0)	/* size_t not fitting in compat_ssize_t .. */
+			goto out;
+		if (type >= 0 &&
+		    !access_ok(vrfy_dir(type), compat_ptr(buf), len)) {
+			ret = -EFAULT;
+			goto out;
+		}
+		if (len > MAX_RW_COUNT - tot_len)
+			len = MAX_RW_COUNT - tot_len;
+		tot_len += len;
+		iov->iov_base = compat_ptr(buf);
+		iov->iov_len = (compat_size_t) len;
+		uvector++;
+		iov++;
 	}
+	ret = tot_len;
+
+out:
 	return ret;
 }
+#endif
 
-ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
-		  unsigned long vlen, loff_t *pos, int flags)
+static ssize_t do_iter_read(struct file *file, struct iov_iter *iter,
+		loff_t *pos, int flags)
 {
+	size_t tot_len;
+	ssize_t ret = 0;
+
 	if (!(file->f_mode & FMODE_READ))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_READ))
 		return -EINVAL;
 
-	return do_readv_writev(READ, file, vec, vlen, pos, flags);
+	tot_len = iov_iter_count(iter);
+	if (!tot_len)
+		goto out;
+	ret = rw_verify_area(READ, file, pos, tot_len);
+	if (ret < 0)
+		return ret;
+
+	if (file->f_op->read_iter)
+		ret = do_iter_readv_writev(file, iter, pos, READ, flags);
+	else
+		ret = do_loop_readv_writev(file, iter, pos, READ, flags);
+out:
+	if (ret >= 0)
+		fsnotify_access(file);
+	return ret;
 }
 
-EXPORT_SYMBOL(vfs_readv);
+ssize_t vfs_iter_read(struct file *file, struct iov_iter *iter, loff_t *ppos,
+		int flags)
+{
+	if (!file->f_op->read_iter)
+		return -EINVAL;
+	return do_iter_read(file, iter, ppos, flags);
+}
+EXPORT_SYMBOL(vfs_iter_read);
 
-ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
-		   unsigned long vlen, loff_t *pos, int flags)
+static ssize_t do_iter_write(struct file *file, struct iov_iter *iter,
+		loff_t *pos, int flags)
 {
+	size_t tot_len;
+	ssize_t ret = 0;
+
 	if (!(file->f_mode & FMODE_WRITE))
 		return -EBADF;
 	if (!(file->f_mode & FMODE_CAN_WRITE))
 		return -EINVAL;
 
-	return do_readv_writev(WRITE, file, vec, vlen, pos, flags);
+	tot_len = iov_iter_count(iter);
+	if (!tot_len)
+		return 0;
+	ret = rw_verify_area(WRITE, file, pos, tot_len);
+	if (ret < 0)
+		return ret;
+
+	if (file->f_op->write_iter)
+		ret = do_iter_readv_writev(file, iter, pos, WRITE, flags);
+	else
+		ret = do_loop_readv_writev(file, iter, pos, WRITE, flags);
+	if (ret > 0)
+		fsnotify_modify(file);
+	return ret;
+}
+
+ssize_t vfs_iter_write(struct file *file, struct iov_iter *iter, loff_t *ppos,
+		int flags)
+{
+	if (!file->f_op->write_iter)
+		return -EINVAL;
+	return do_iter_write(file, iter, ppos, flags);
+}
+EXPORT_SYMBOL(vfs_iter_write);
+
+ssize_t vfs_readv(struct file *file, const struct iovec __user *vec,
+		  unsigned long vlen, loff_t *pos, int flags)
+{
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	ssize_t ret;
+
+	ret = import_iovec(READ, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret >= 0) {
+		ret = do_iter_read(file, &iter, pos, flags);
+		kfree(iov);
+	}
+
+	return ret;
 }
+EXPORT_SYMBOL(vfs_readv);
+
+ssize_t vfs_writev(struct file *file, const struct iovec __user *vec,
+		   unsigned long vlen, loff_t *pos, int flags)
+{
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	ssize_t ret;
 
+	ret = import_iovec(WRITE, vec, vlen, ARRAY_SIZE(iovstack), &iov, &iter);
+	if (ret >= 0) {
+		file_start_write(file);
+		ret = do_iter_write(file, &iter, pos, flags);
+		file_end_write(file);
+		kfree(iov);
+	}
+	return ret;
+}
 EXPORT_SYMBOL(vfs_writev);
 
 static ssize_t do_readv(unsigned long fd, const struct iovec __user *vec,
@@ -1058,76 +1125,20 @@ SYSCALL_DEFINE6(pwritev2, unsigned long, fd, const struct iovec __user *, vec,
 }
 
 #ifdef CONFIG_COMPAT
-
-static ssize_t compat_do_readv_writev(int type, struct file *file,
-			       const struct compat_iovec __user *uvector,
-			       unsigned long nr_segs, loff_t *pos,
-			       int flags)
+static size_t compat_readv(struct file *file,
+			   const struct compat_iovec __user *vec,
+			   unsigned long vlen, loff_t *pos, int flags)
 {
-	compat_ssize_t tot_len;
 	struct iovec iovstack[UIO_FASTIOV];
 	struct iovec *iov = iovstack;
 	struct iov_iter iter;
 	ssize_t ret;
-	io_fn_t fn;
-	iter_fn_t iter_fn;
 
-	ret = compat_import_iovec(type, uvector, nr_segs,
-				  UIO_FASTIOV, &iov, &iter);
-	if (ret < 0)
-		return ret;
-
-	tot_len = iov_iter_count(&iter);
-	if (!tot_len)
-		goto out;
-	ret = rw_verify_area(type, file, pos, tot_len);
-	if (ret < 0)
-		goto out;
-
-	if (type == READ) {
-		fn = file->f_op->read;
-		iter_fn = file->f_op->read_iter;
-	} else {
-		fn = (io_fn_t)file->f_op->write;
-		iter_fn = file->f_op->write_iter;
-		file_start_write(file);
-	}
-
-	if (iter_fn)
-		ret = do_iter_readv_writev(file, &iter, pos, iter_fn, flags);
-	else
-		ret = do_loop_readv_writev(file, &iter, pos, fn, flags);
-
-	if (type != READ)
-		file_end_write(file);
-
-out:
-	kfree(iov);
-	if ((ret + (type == READ)) > 0) {
-		if (type == READ)
-			fsnotify_access(file);
-		else
-			fsnotify_modify(file);
+	ret = compat_import_iovec(READ, vec, vlen, UIO_FASTIOV, &iov, &iter);
+	if (ret >= 0) {
+		ret = do_iter_read(file, &iter, pos, flags);
+		kfree(iov);
 	}
-	return ret;
-}
-
-static size_t compat_readv(struct file *file,
-			   const struct compat_iovec __user *vec,
-			   unsigned long vlen, loff_t *pos, int flags)
-{
-	ssize_t ret = -EBADF;
-
-	if (!(file->f_mode & FMODE_READ))
-		goto out;
-
-	ret = -EINVAL;
-	if (!(file->f_mode & FMODE_CAN_READ))
-		goto out;
-
-	ret = compat_do_readv_writev(READ, file, vec, vlen, pos, flags);
-
-out:
 	if (ret > 0)
 		add_rchar(current, ret);
 	inc_syscr(current);
@@ -1223,18 +1234,18 @@ static size_t compat_writev(struct file *file,
 			    const struct compat_iovec __user *vec,
 			    unsigned long vlen, loff_t *pos, int flags)
 {
-	ssize_t ret = -EBADF;
-
-	if (!(file->f_mode & FMODE_WRITE))
-		goto out;
-
-	ret = -EINVAL;
-	if (!(file->f_mode & FMODE_CAN_WRITE))
-		goto out;
-
-	ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos, 0);
+	struct iovec iovstack[UIO_FASTIOV];
+	struct iovec *iov = iovstack;
+	struct iov_iter iter;
+	ssize_t ret;
 
-out:
+	ret = compat_import_iovec(WRITE, vec, vlen, UIO_FASTIOV, &iov, &iter);
+	if (ret >= 0) {
+		file_start_write(file);
+		ret = do_iter_write(file, &iter, pos, flags);
+		file_end_write(file);
+		kfree(iov);
+	}
 	if (ret > 0)
 		add_wchar(current, ret);
 	inc_syscw(current);
@@ -1518,6 +1529,11 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (flags != 0)
 		return -EINVAL;
 
+	if (S_ISDIR(inode_in->i_mode) || S_ISDIR(inode_out->i_mode))
+		return -EISDIR;
+	if (!S_ISREG(inode_in->i_mode) || !S_ISREG(inode_out->i_mode))
+		return -EINVAL;
+
 	ret = rw_verify_area(READ, file_in, &pos_in, len);
 	if (unlikely(ret))
 		return ret;
@@ -1538,7 +1554,7 @@ ssize_t vfs_copy_file_range(struct file *file_in, loff_t pos_in,
 	if (len == 0)
 		return 0;
 
-	sb_start_write(inode_out->i_sb);
+	file_start_write(file_out);
 
 	/*
 	 * Try cloning first, this is supported by more file systems, and
@@ -1574,7 +1590,7 @@ done:
 	inc_syscr(current);
 	inc_syscw(current);
 
-	sb_end_write(inode_out->i_sb);
+	file_end_write(file_out);
 
 	return ret;
 }
diff --git a/fs/readdir.c b/fs/readdir.c
index 0e8a7f355f7a..89659549c09d 100644
--- a/fs/readdir.c
+++ b/fs/readdir.c
@@ -18,6 +18,7 @@
 #include <linux/security.h>
 #include <linux/syscalls.h>
 #include <linux/unistd.h>
+#include <linux/compat.h>
 
 #include <linux/uaccess.h>
 
@@ -324,3 +325,167 @@ SYSCALL_DEFINE3(getdents64, unsigned int, fd,
 	fdput_pos(f);
 	return error;
 }
+
+#ifdef CONFIG_COMPAT
+struct compat_old_linux_dirent {
+	compat_ulong_t	d_ino;
+	compat_ulong_t	d_offset;
+	unsigned short	d_namlen;
+	char		d_name[1];
+};
+
+struct compat_readdir_callback {
+	struct dir_context ctx;
+	struct compat_old_linux_dirent __user *dirent;
+	int result;
+};
+
+static int compat_fillonedir(struct dir_context *ctx, const char *name,
+			     int namlen, loff_t offset, u64 ino,
+			     unsigned int d_type)
+{
+	struct compat_readdir_callback *buf =
+		container_of(ctx, struct compat_readdir_callback, ctx);
+	struct compat_old_linux_dirent __user *dirent;
+	compat_ulong_t d_ino;
+
+	if (buf->result)
+		return -EINVAL;
+	d_ino = ino;
+	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
+		buf->result = -EOVERFLOW;
+		return -EOVERFLOW;
+	}
+	buf->result++;
+	dirent = buf->dirent;
+	if (!access_ok(VERIFY_WRITE, dirent,
+			(unsigned long)(dirent->d_name + namlen + 1) -
+				(unsigned long)dirent))
+		goto efault;
+	if (	__put_user(d_ino, &dirent->d_ino) ||
+		__put_user(offset, &dirent->d_offset) ||
+		__put_user(namlen, &dirent->d_namlen) ||
+		__copy_to_user(dirent->d_name, name, namlen) ||
+		__put_user(0, dirent->d_name + namlen))
+		goto efault;
+	return 0;
+efault:
+	buf->result = -EFAULT;
+	return -EFAULT;
+}
+
+COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd,
+		struct compat_old_linux_dirent __user *, dirent, unsigned int, count)
+{
+	int error;
+	struct fd f = fdget_pos(fd);
+	struct compat_readdir_callback buf = {
+		.ctx.actor = compat_fillonedir,
+		.dirent = dirent
+	};
+
+	if (!f.file)
+		return -EBADF;
+
+	error = iterate_dir(f.file, &buf.ctx);
+	if (buf.result)
+		error = buf.result;
+
+	fdput_pos(f);
+	return error;
+}
+
+struct compat_linux_dirent {
+	compat_ulong_t	d_ino;
+	compat_ulong_t	d_off;
+	unsigned short	d_reclen;
+	char		d_name[1];
+};
+
+struct compat_getdents_callback {
+	struct dir_context ctx;
+	struct compat_linux_dirent __user *current_dir;
+	struct compat_linux_dirent __user *previous;
+	int count;
+	int error;
+};
+
+static int compat_filldir(struct dir_context *ctx, const char *name, int namlen,
+		loff_t offset, u64 ino, unsigned int d_type)
+{
+	struct compat_linux_dirent __user * dirent;
+	struct compat_getdents_callback *buf =
+		container_of(ctx, struct compat_getdents_callback, ctx);
+	compat_ulong_t d_ino;
+	int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) +
+		namlen + 2, sizeof(compat_long_t));
+
+	buf->error = -EINVAL;	/* only used if we fail.. */
+	if (reclen > buf->count)
+		return -EINVAL;
+	d_ino = ino;
+	if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) {
+		buf->error = -EOVERFLOW;
+		return -EOVERFLOW;
+	}
+	dirent = buf->previous;
+	if (dirent) {
+		if (signal_pending(current))
+			return -EINTR;
+		if (__put_user(offset, &dirent->d_off))
+			goto efault;
+	}
+	dirent = buf->current_dir;
+	if (__put_user(d_ino, &dirent->d_ino))
+		goto efault;
+	if (__put_user(reclen, &dirent->d_reclen))
+		goto efault;
+	if (copy_to_user(dirent->d_name, name, namlen))
+		goto efault;
+	if (__put_user(0, dirent->d_name + namlen))
+		goto efault;
+	if (__put_user(d_type, (char  __user *) dirent + reclen - 1))
+		goto efault;
+	buf->previous = dirent;
+	dirent = (void __user *)dirent + reclen;
+	buf->current_dir = dirent;
+	buf->count -= reclen;
+	return 0;
+efault:
+	buf->error = -EFAULT;
+	return -EFAULT;
+}
+
+COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd,
+		struct compat_linux_dirent __user *, dirent, unsigned int, count)
+{
+	struct fd f;
+	struct compat_linux_dirent __user * lastdirent;
+	struct compat_getdents_callback buf = {
+		.ctx.actor = compat_filldir,
+		.current_dir = dirent,
+		.count = count
+	};
+	int error;
+
+	if (!access_ok(VERIFY_WRITE, dirent, count))
+		return -EFAULT;
+
+	f = fdget_pos(fd);
+	if (!f.file)
+		return -EBADF;
+
+	error = iterate_dir(f.file, &buf.ctx);
+	if (error >= 0)
+		error = buf.error;
+	lastdirent = buf.previous;
+	if (lastdirent) {
+		if (put_user(buf.ctx.pos, &lastdirent->d_off))
+			error = -EFAULT;
+		else
+			error = count - buf.count;
+	}
+	fdput_pos(f);
+	return error;
+}
+#endif
diff --git a/fs/reiserfs/bitmap.c b/fs/reiserfs/bitmap.c
index dc198bc64c61..edc8ef78b63f 100644
--- a/fs/reiserfs/bitmap.c
+++ b/fs/reiserfs/bitmap.c
@@ -513,9 +513,17 @@ static void __discard_prealloc(struct reiserfs_transaction_handle *th,
 			       "inode has negative prealloc blocks count.");
 #endif
 	while (ei->i_prealloc_count > 0) {
-		reiserfs_free_prealloc_block(th, inode, ei->i_prealloc_block);
-		ei->i_prealloc_block++;
+		b_blocknr_t block_to_free;
+
+		/*
+		 * reiserfs_free_prealloc_block can drop the write lock,
+		 * which could allow another caller to free the same block.
+		 * We can protect against it by modifying the prealloc
+		 * state before calling it.
+		 */
+		block_to_free = ei->i_prealloc_block++;
 		ei->i_prealloc_count--;
+		reiserfs_free_prealloc_block(th, inode, block_to_free);
 		dirty = 1;
 	}
 	if (dirty)
@@ -1128,7 +1136,7 @@ static int determine_prealloc_size(reiserfs_blocknr_hint_t * hint)
 	hint->prealloc_size = 0;
 
 	if (!hint->formatted_node && hint->preallocate) {
-		if (S_ISREG(hint->inode->i_mode)
+		if (S_ISREG(hint->inode->i_mode) && !IS_PRIVATE(hint->inode)
 		    && hint->inode->i_size >=
 		    REISERFS_SB(hint->th->t_super)->s_alloc_options.
 		    preallocmin * hint->inode->i_sb->s_blocksize)
diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c
index 2f8c5c9bdaf6..b396eb09f288 100644
--- a/fs/reiserfs/file.c
+++ b/fs/reiserfs/file.c
@@ -189,7 +189,7 @@ int reiserfs_commit_page(struct inode *inode, struct page *page,
 	int ret = 0;
 
 	th.t_trans_id = 0;
-	blocksize = 1 << inode->i_blkbits;
+	blocksize = i_blocksize(inode);
 
 	if (logit) {
 		reiserfs_write_lock(s);
diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c
index cfeae9b0a2b7..873fc04e9403 100644
--- a/fs/reiserfs/inode.c
+++ b/fs/reiserfs/inode.c
@@ -525,7 +525,7 @@ static int reiserfs_get_blocks_direct_io(struct inode *inode,
 	 * referenced in convert_tail_for_hole() that may be called from
 	 * reiserfs_get_block()
 	 */
-	bh_result->b_size = (1 << inode->i_blkbits);
+	bh_result->b_size = i_blocksize(inode);
 
 	ret = reiserfs_get_block(inode, iblock, bh_result,
 				 create | GET_BLOCK_NO_DANGLE);
@@ -1375,7 +1375,6 @@ static void init_inode(struct inode *inode, struct treepath *path)
 static void inode2sd(void *sd, struct inode *inode, loff_t size)
 {
 	struct stat_data *sd_v2 = (struct stat_data *)sd;
-	__u16 flags;
 
 	set_sd_v2_mode(sd_v2, inode->i_mode);
 	set_sd_v2_nlink(sd_v2, inode->i_nlink);
@@ -1390,9 +1389,7 @@ static void inode2sd(void *sd, struct inode *inode, loff_t size)
 		set_sd_v2_rdev(sd_v2, new_encode_dev(inode->i_rdev));
 	else
 		set_sd_v2_generation(sd_v2, inode->i_generation);
-	flags = REISERFS_I(inode)->i_attrs;
-	i_attrs_to_sd_attrs(inode, &flags);
-	set_sd_v2_attrs(sd_v2, flags);
+	set_sd_v2_attrs(sd_v2, REISERFS_I(inode)->i_attrs);
 }
 
 /* used to copy inode's fields to old stat data */
@@ -2002,10 +1999,6 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th,
 
 	/* uid and gid must already be set by the caller for quota init */
 
-	/* symlink cannot be immutable or append only, right? */
-	if (S_ISLNK(inode->i_mode))
-		inode->i_flags &= ~(S_IMMUTABLE | S_APPEND);
-
 	inode->i_mtime = inode->i_atime = inode->i_ctime = current_time(inode);
 	inode->i_size = i_size;
 	inode->i_blocks = 0;
@@ -3095,28 +3088,6 @@ void sd_attrs_to_i_attrs(__u16 sd_attrs, struct inode *inode)
 	}
 }
 
-void i_attrs_to_sd_attrs(struct inode *inode, __u16 * sd_attrs)
-{
-	if (reiserfs_attrs(inode->i_sb)) {
-		if (inode->i_flags & S_IMMUTABLE)
-			*sd_attrs |= REISERFS_IMMUTABLE_FL;
-		else
-			*sd_attrs &= ~REISERFS_IMMUTABLE_FL;
-		if (inode->i_flags & S_SYNC)
-			*sd_attrs |= REISERFS_SYNC_FL;
-		else
-			*sd_attrs &= ~REISERFS_SYNC_FL;
-		if (inode->i_flags & S_NOATIME)
-			*sd_attrs |= REISERFS_NOATIME_FL;
-		else
-			*sd_attrs &= ~REISERFS_NOATIME_FL;
-		if (REISERFS_I(inode)->i_flags & i_nopack_mask)
-			*sd_attrs |= REISERFS_NOTAIL_FL;
-		else
-			*sd_attrs &= ~REISERFS_NOTAIL_FL;
-	}
-}
-
 /*
  * decide if this buffer needs to stay around for data logging or ordered
  * write purposes
diff --git a/fs/reiserfs/ioctl.c b/fs/reiserfs/ioctl.c
index 1f4692a505a0..acbbaf7a0bb2 100644
--- a/fs/reiserfs/ioctl.c
+++ b/fs/reiserfs/ioctl.c
@@ -47,7 +47,6 @@ long reiserfs_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 		}
 
 		flags = REISERFS_I(inode)->i_attrs;
-		i_attrs_to_sd_attrs(inode, (__u16 *) & flags);
 		err = put_user(flags, (int __user *)arg);
 		break;
 	case REISERFS_IOC_SETFLAGS:{
diff --git a/fs/reiserfs/item_ops.c b/fs/reiserfs/item_ops.c
index aca73dd73906..e3c558d1b78c 100644
--- a/fs/reiserfs/item_ops.c
+++ b/fs/reiserfs/item_ops.c
@@ -724,18 +724,18 @@ static void errcatch_print_vi(struct virtual_item *vi)
 }
 
 static struct item_operations errcatch_ops = {
-	errcatch_bytes_number,
-	errcatch_decrement_key,
-	errcatch_is_left_mergeable,
-	errcatch_print_item,
-	errcatch_check_item,
-
-	errcatch_create_vi,
-	errcatch_check_left,
-	errcatch_check_right,
-	errcatch_part_size,
-	errcatch_unit_num,
-	errcatch_print_vi
+	.bytes_number = errcatch_bytes_number,
+	.decrement_key = errcatch_decrement_key,
+	.is_left_mergeable = errcatch_is_left_mergeable,
+	.print_item = errcatch_print_item,
+	.check_item = errcatch_check_item,
+
+	.create_vi = errcatch_create_vi,
+	.check_left = errcatch_check_left,
+	.check_right = errcatch_check_right,
+	.part_size = errcatch_part_size,
+	.unit_num = errcatch_unit_num,
+	.print_vi = errcatch_print_vi
 };
 
 #if ! (TYPE_STAT_DATA == 0 && TYPE_INDIRECT == 1 && TYPE_DIRECT == 2 && TYPE_DIRENTRY == 3)
diff --git a/fs/reiserfs/journal.c b/fs/reiserfs/journal.c
index aa40c242f1db..a11d773e5ff3 100644
--- a/fs/reiserfs/journal.c
+++ b/fs/reiserfs/journal.c
@@ -1112,7 +1112,7 @@ static int flush_commit_list(struct super_block *s,
 		depth = reiserfs_write_unlock_nested(s);
 		if (reiserfs_barrier_flush(s))
 			__sync_dirty_buffer(jl->j_commit_bh,
-					REQ_PREFLUSH | REQ_FUA);
+					REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
 		else
 			sync_dirty_buffer(jl->j_commit_bh);
 		reiserfs_write_lock_nested(s, depth);
@@ -1271,7 +1271,7 @@ static int _update_journal_header_block(struct super_block *sb,
 
 		if (reiserfs_barrier_flush(sb))
 			__sync_dirty_buffer(journal->j_header_bh,
-					REQ_PREFLUSH | REQ_FUA);
+					REQ_SYNC | REQ_PREFLUSH | REQ_FUA);
 		else
 			sync_dirty_buffer(journal->j_header_bh);
 
@@ -1961,7 +1961,7 @@ static int do_journal_release(struct reiserfs_transaction_handle *th,
 	 * will be requeued because superblock is being shutdown and doesn't
 	 * have MS_ACTIVE set.
 	 */
-	cancel_delayed_work_sync(&REISERFS_SB(sb)->old_work);
+	reiserfs_cancel_old_flush(sb);
 	/* wait for all commits to finish */
 	cancel_delayed_work_sync(&SB_JOURNAL(sb)->j_work);
 
@@ -2956,7 +2956,7 @@ void reiserfs_wait_on_write_block(struct super_block *s)
 
 static void queue_log_writer(struct super_block *s)
 {
-	wait_queue_t wait;
+	wait_queue_entry_t wait;
 	struct reiserfs_journal *journal = SB_JOURNAL(s);
 	set_bit(J_WRITERS_QUEUED, &journal->j_state);
 
diff --git a/fs/reiserfs/lbalance.c b/fs/reiserfs/lbalance.c
index 249594a821e0..f5cebd70d903 100644
--- a/fs/reiserfs/lbalance.c
+++ b/fs/reiserfs/lbalance.c
@@ -475,7 +475,7 @@ static void leaf_item_bottle(struct buffer_info *dest_bi,
 			 * 'cpy_bytes'; create new item header;
 			 * n_ih = new item_header;
 			 */
-			memcpy(&n_ih, ih, SHORT_KEY_SIZE);
+			memcpy(&n_ih.ih_key, &ih->ih_key, KEY_SIZE);
 
 			/* Endian safe, both le */
 			n_ih.ih_version = ih->ih_version;
diff --git a/fs/reiserfs/reiserfs.h b/fs/reiserfs/reiserfs.h
index 2adcde137c3f..1d34377fef97 100644
--- a/fs/reiserfs/reiserfs.h
+++ b/fs/reiserfs/reiserfs.h
@@ -1326,7 +1326,6 @@ struct cpu_key {
 #define KEY_NOT_FOUND 0
 
 #define KEY_SIZE (sizeof(struct reiserfs_key))
-#define SHORT_KEY_SIZE (sizeof (__u32) + sizeof (__u32))
 
 /* return values for search_by_key and clones */
 #define ITEM_FOUND 1
@@ -2949,6 +2948,7 @@ int reiserfs_allocate_list_bitmaps(struct super_block *s,
 				   struct reiserfs_list_bitmap *, unsigned int);
 
 void reiserfs_schedule_old_flush(struct super_block *s);
+void reiserfs_cancel_old_flush(struct super_block *s);
 void add_save_link(struct reiserfs_transaction_handle *th,
 		   struct inode *inode, int truncate);
 int remove_save_link(struct inode *inode, int truncate);
@@ -3099,7 +3099,6 @@ static inline void reiserfs_update_sd(struct reiserfs_transaction_handle *th,
 }
 
 void sd_attrs_to_i_attrs(__u16 sd_attrs, struct inode *inode);
-void i_attrs_to_sd_attrs(struct inode *inode, __u16 * sd_attrs);
 int reiserfs_setattr(struct dentry *dentry, struct iattr *attr);
 
 int __reiserfs_write_begin(struct page *page, unsigned from, unsigned len);
diff --git a/fs/reiserfs/super.c b/fs/reiserfs/super.c
index e314cb30a181..306e4e9d172d 100644
--- a/fs/reiserfs/super.c
+++ b/fs/reiserfs/super.c
@@ -89,11 +89,27 @@ static void flush_old_commits(struct work_struct *work)
 	sbi = container_of(work, struct reiserfs_sb_info, old_work.work);
 	s = sbi->s_journal->j_work_sb;
 
+	/*
+	 * We need s_umount for protecting quota writeback. We have to use
+	 * trylock as reiserfs_cancel_old_flush() may be waiting for this work
+	 * to complete with s_umount held.
+	 */
+	if (!down_read_trylock(&s->s_umount)) {
+		/* Requeue work if we are not cancelling it */
+		spin_lock(&sbi->old_work_lock);
+		if (sbi->work_queued == 1)
+			queue_delayed_work(system_long_wq, &sbi->old_work, HZ);
+		spin_unlock(&sbi->old_work_lock);
+		return;
+	}
 	spin_lock(&sbi->old_work_lock);
-	sbi->work_queued = 0;
+	/* Avoid clobbering the cancel state... */
+	if (sbi->work_queued == 1)
+		sbi->work_queued = 0;
 	spin_unlock(&sbi->old_work_lock);
 
 	reiserfs_sync_fs(s, 1);
+	up_read(&s->s_umount);
 }
 
 void reiserfs_schedule_old_flush(struct super_block *s)
@@ -117,21 +133,22 @@ void reiserfs_schedule_old_flush(struct super_block *s)
 	spin_unlock(&sbi->old_work_lock);
 }
 
-static void cancel_old_flush(struct super_block *s)
+void reiserfs_cancel_old_flush(struct super_block *s)
 {
 	struct reiserfs_sb_info *sbi = REISERFS_SB(s);
 
-	cancel_delayed_work_sync(&REISERFS_SB(s)->old_work);
 	spin_lock(&sbi->old_work_lock);
-	sbi->work_queued = 0;
+	/* Make sure no new flushes will be queued */
+	sbi->work_queued = 2;
 	spin_unlock(&sbi->old_work_lock);
+	cancel_delayed_work_sync(&REISERFS_SB(s)->old_work);
 }
 
 static int reiserfs_freeze(struct super_block *s)
 {
 	struct reiserfs_transaction_handle th;
 
-	cancel_old_flush(s);
+	reiserfs_cancel_old_flush(s);
 
 	reiserfs_write_lock(s);
 	if (!(s->s_flags & MS_RDONLY)) {
@@ -152,7 +169,13 @@ static int reiserfs_freeze(struct super_block *s)
 
 static int reiserfs_unfreeze(struct super_block *s)
 {
+	struct reiserfs_sb_info *sbi = REISERFS_SB(s);
+
 	reiserfs_allow_writes(s);
+	spin_lock(&sbi->old_work_lock);
+	/* Allow old_work to run again */
+	sbi->work_queued = 0;
+	spin_unlock(&sbi->old_work_lock);
 	return 0;
 }
 
@@ -547,12 +570,28 @@ static void reiserfs_kill_sb(struct super_block *s)
 	kill_block_super(s);
 }
 
+#ifdef CONFIG_QUOTA
+static int reiserfs_quota_off(struct super_block *sb, int type);
+
+static void reiserfs_quota_off_umount(struct super_block *s)
+{
+	int type;
+
+	for (type = 0; type < REISERFS_MAXQUOTAS; type++)
+		reiserfs_quota_off(s, type);
+}
+#else
+static inline void reiserfs_quota_off_umount(struct super_block *s)
+{
+}
+#endif
+
 static void reiserfs_put_super(struct super_block *s)
 {
 	struct reiserfs_transaction_handle th;
 	th.t_trans_id = 0;
 
-	dquot_disable(s, -1, DQUOT_USAGE_ENABLED | DQUOT_LIMITS_ENABLED);
+	reiserfs_quota_off_umount(s);
 
 	reiserfs_write_lock(s);
 
@@ -817,7 +856,7 @@ static const struct dquot_operations reiserfs_quota_operations = {
 
 static const struct quotactl_ops reiserfs_qctl_operations = {
 	.quota_on = reiserfs_quota_on,
-	.quota_off = dquot_quota_off,
+	.quota_off = reiserfs_quota_off,
 	.quota_sync = dquot_quota_sync,
 	.get_state = dquot_get_state,
 	.set_info = dquot_set_dqinfo,
@@ -1166,7 +1205,7 @@ static int reiserfs_parse_options(struct super_block *s,
 			if (!strcmp(arg, "auto")) {
 				/* From JFS code, to auto-get the size. */
 				*blocks =
-				    s->s_bdev->bd_inode->i_size >> s->
+				    i_size_read(s->s_bdev->bd_inode) >> s->
 				    s_blocksize_bits;
 			} else {
 				*blocks = simple_strtoul(arg, &p, 0);
@@ -1560,8 +1599,6 @@ static int reiserfs_remount(struct super_block *s, int *mount_flags, char *arg)
 	}
 
 out_ok_unlocked:
-	if (new_opts)
-		replace_mount_options(s, new_opts);
 	return 0;
 
 out_err_unlock:
@@ -1877,8 +1914,6 @@ static int reiserfs_fill_super(struct super_block *s, void *data, int silent)
 	char *qf_names[REISERFS_MAXQUOTAS] = {};
 	unsigned int qfmt = 0;
 
-	save_mount_options(s, data);
-
 	sbi = kzalloc(sizeof(struct reiserfs_sb_info), GFP_KERNEL);
 	if (!sbi)
 		return -ENOMEM;
@@ -2194,7 +2229,7 @@ error_unlocked:
 	if (sbi->commit_wq)
 		destroy_workqueue(sbi->commit_wq);
 
-	cancel_delayed_work_sync(&REISERFS_SB(s)->old_work);
+	reiserfs_cancel_old_flush(s);
 
 	reiserfs_free_bitmap_cache(s);
 	if (SB_BUFFER_WITH_SB(s))
@@ -2405,12 +2440,47 @@ static int reiserfs_quota_on(struct super_block *sb, int type, int format_id,
 			goto out;
 	}
 	reiserfs_write_unlock(sb);
-	return dquot_quota_on(sb, type, format_id, path);
+	err = dquot_quota_on(sb, type, format_id, path);
+	if (!err) {
+		inode_lock(inode);
+		REISERFS_I(inode)->i_attrs |= REISERFS_IMMUTABLE_FL |
+					      REISERFS_NOATIME_FL;
+		inode_set_flags(inode, S_IMMUTABLE | S_NOATIME,
+				S_IMMUTABLE | S_NOATIME);
+		inode_unlock(inode);
+		mark_inode_dirty(inode);
+	}
+	return err;
 out:
 	reiserfs_write_unlock(sb);
 	return err;
 }
 
+static int reiserfs_quota_off(struct super_block *sb, int type)
+{
+	int err;
+	struct inode *inode = sb_dqopt(sb)->files[type];
+
+	if (!inode || !igrab(inode))
+		goto out;
+
+	err = dquot_quota_off(sb, type);
+	if (err)
+		goto out_put;
+
+	inode_lock(inode);
+	REISERFS_I(inode)->i_attrs &= ~(REISERFS_IMMUTABLE_FL |
+					REISERFS_NOATIME_FL);
+	inode_set_flags(inode, 0, S_IMMUTABLE | S_NOATIME);
+	inode_unlock(inode);
+	mark_inode_dirty(inode);
+out_put:
+	iput(inode);
+	return err;
+out:
+	return dquot_quota_off(sb, type);
+}
+
 /*
  * Read data from quotafile - avoid pagecache and such because we cannot afford
  * acquiring the locks... As quota files are never truncated and quota code
diff --git a/fs/reiserfs/xattr_acl.c b/fs/reiserfs/xattr_acl.c
index 3d2256a425ee..54415f0e3d18 100644
--- a/fs/reiserfs/xattr_acl.c
+++ b/fs/reiserfs/xattr_acl.c
@@ -23,7 +23,8 @@ reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	struct reiserfs_transaction_handle th;
 	size_t jcreate_blocks;
 	int size = acl ? posix_acl_xattr_size(acl->a_count) : 0;
-
+	int update_mode = 0;
+	umode_t mode = inode->i_mode;
 
 	/*
 	 * Pessimism: We can't assume that anything from the xattr root up
@@ -37,7 +38,16 @@ reiserfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	error = journal_begin(&th, inode->i_sb, jcreate_blocks);
 	reiserfs_write_unlock(inode->i_sb);
 	if (error == 0) {
+		if (type == ACL_TYPE_ACCESS && acl) {
+			error = posix_acl_update_mode(inode, &mode, &acl);
+			if (error)
+				goto unlock;
+			update_mode = 1;
+		}
 		error = __reiserfs_set_acl(&th, inode, type, acl);
+		if (!error && update_mode)
+			inode->i_mode = mode;
+unlock:
 		reiserfs_write_lock(inode->i_sb);
 		error2 = journal_end(&th);
 		reiserfs_write_unlock(inode->i_sb);
@@ -241,11 +251,6 @@ __reiserfs_set_acl(struct reiserfs_transaction_handle *th, struct inode *inode,
 	switch (type) {
 	case ACL_TYPE_ACCESS:
 		name = XATTR_NAME_POSIX_ACL_ACCESS;
-		if (acl) {
-			error = posix_acl_update_mode(inode, &inode->i_mode, &acl);
-			if (error)
-				return error;
-		}
 		break;
 	case ACL_TYPE_DEFAULT:
 		name = XATTR_NAME_POSIX_ACL_DEFAULT;
diff --git a/fs/select.c b/fs/select.c
index 305c0daf5d67..9d5f15ed87fe 100644
--- a/fs/select.c
+++ b/fs/select.c
@@ -15,7 +15,8 @@
  */
 
 #include <linux/kernel.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/rt.h>
 #include <linux/syscalls.h>
 #include <linux/export.h>
 #include <linux/slab.h>
@@ -26,7 +27,6 @@
 #include <linux/fs.h>
 #include <linux/rcupdate.h>
 #include <linux/hrtimer.h>
-#include <linux/sched/rt.h>
 #include <linux/freezer.h>
 #include <net/busy_poll.h>
 #include <linux/vmalloc.h>
@@ -180,7 +180,7 @@ static struct poll_table_entry *poll_get_entry(struct poll_wqueues *p)
 	return table->entry++;
 }
 
-static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int __pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	struct poll_wqueues *pwq = wait->private;
 	DECLARE_WAITQUEUE(dummy_wait, pwq->polling_task);
@@ -206,7 +206,7 @@ static int __pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
 	return default_wake_function(&dummy_wait, mode, sync, key);
 }
 
-static int pollwake(wait_queue_t *wait, unsigned mode, int sync, void *key)
+static int pollwake(wait_queue_entry_t *wait, unsigned mode, int sync, void *key)
 {
 	struct poll_table_entry *entry;
 
@@ -338,6 +338,53 @@ sticky:
 	return ret;
 }
 
+/*
+ * Scalable version of the fd_set.
+ */
+
+typedef struct {
+	unsigned long *in, *out, *ex;
+	unsigned long *res_in, *res_out, *res_ex;
+} fd_set_bits;
+
+/*
+ * How many longwords for "nr" bits?
+ */
+#define FDS_BITPERLONG	(8*sizeof(long))
+#define FDS_LONGS(nr)	(((nr)+FDS_BITPERLONG-1)/FDS_BITPERLONG)
+#define FDS_BYTES(nr)	(FDS_LONGS(nr)*sizeof(long))
+
+/*
+ * We do a VERIFY_WRITE here even though we are only reading this time:
+ * we'll write to it eventually..
+ *
+ * Use "unsigned long" accesses to let user-mode fd_set's be long-aligned.
+ */
+static inline
+int get_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
+{
+	nr = FDS_BYTES(nr);
+	if (ufdset)
+		return copy_from_user(fdset, ufdset, nr) ? -EFAULT : 0;
+
+	memset(fdset, 0, nr);
+	return 0;
+}
+
+static inline unsigned long __must_check
+set_fd_set(unsigned long nr, void __user *ufdset, unsigned long *fdset)
+{
+	if (ufdset)
+		return __copy_to_user(ufdset, fdset, FDS_BYTES(nr));
+	return 0;
+}
+
+static inline
+void zero_fd_set(unsigned long nr, unsigned long *fdset)
+{
+	memset(fdset, 0, FDS_BYTES(nr));
+}
+
 #define FDS_IN(fds, n)		(fds->in + n)
 #define FDS_OUT(fds, n)		(fds->out + n)
 #define FDS_EX(fds, n)		(fds->ex + n)
@@ -401,7 +448,7 @@ static inline void wait_key_set(poll_table *wait, unsigned long in,
 		wait->_key |= POLLOUT_SET;
 }
 
-int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
+static int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 {
 	ktime_t expire, *to = NULL;
 	struct poll_wqueues table;
@@ -409,7 +456,7 @@ int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 	int retval, i, timed_out = 0;
 	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
-	unsigned long busy_end = 0;
+	unsigned long busy_start = 0;
 
 	rcu_read_lock();
 	retval = max_select_fd(n, fds);
@@ -512,11 +559,11 @@ int do_select(int n, fd_set_bits *fds, struct timespec64 *end_time)
 
 		/* only if found POLL_BUSY_LOOP sockets && not out of time */
 		if (can_busy_loop && !need_resched()) {
-			if (!busy_end) {
-				busy_end = busy_loop_end_time();
+			if (!busy_start) {
+				busy_start = busy_loop_current_time();
 				continue;
 			}
-			if (!busy_loop_timeout(busy_end))
+			if (!busy_loop_timeout(busy_start))
 				continue;
 		}
 		busy_flag = 0;
@@ -586,10 +633,7 @@ int core_sys_select(int n, fd_set __user *inp, fd_set __user *outp,
 			goto out_nofds;
 
 		alloc_size = 6 * size;
-		bits = kmalloc(alloc_size, GFP_KERNEL|__GFP_NOWARN);
-		if (!bits && alloc_size > PAGE_SIZE)
-			bits = vmalloc(alloc_size);
-
+		bits = kvmalloc(alloc_size, GFP_KERNEL);
 		if (!bits)
 			goto out_nofds;
 	}
@@ -800,7 +844,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 	int timed_out = 0, count = 0;
 	u64 slack = 0;
 	unsigned int busy_flag = net_busy_loop_on() ? POLL_BUSY_LOOP : 0;
-	unsigned long busy_end = 0;
+	unsigned long busy_start = 0;
 
 	/* Optimise the no-wait case */
 	if (end_time && !end_time->tv_sec && !end_time->tv_nsec) {
@@ -853,11 +897,11 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 
 		/* only if found POLL_BUSY_LOOP sockets && not out of time */
 		if (can_busy_loop && !need_resched()) {
-			if (!busy_end) {
-				busy_end = busy_loop_end_time();
+			if (!busy_start) {
+				busy_start = busy_loop_current_time();
 				continue;
 			}
-			if (!busy_loop_timeout(busy_end))
+			if (!busy_loop_timeout(busy_start))
 				continue;
 		}
 		busy_flag = 0;
@@ -881,7 +925,7 @@ static int do_poll(struct poll_list *list, struct poll_wqueues *wait,
 #define N_STACK_PPS ((sizeof(stack_pps) - sizeof(struct poll_list))  / \
 			sizeof(struct pollfd))
 
-int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
+static int do_sys_poll(struct pollfd __user *ufds, unsigned int nfds,
 		struct timespec64 *end_time)
 {
 	struct poll_wqueues table;
@@ -1053,3 +1097,339 @@ SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, unsigned int, nfds,
 
 	return ret;
 }
+
+#ifdef CONFIG_COMPAT
+#define __COMPAT_NFDBITS       (8 * sizeof(compat_ulong_t))
+
+static
+int compat_poll_select_copy_remaining(struct timespec *end_time, void __user *p,
+				      int timeval, int ret)
+{
+	struct timespec ts;
+
+	if (!p)
+		return ret;
+
+	if (current->personality & STICKY_TIMEOUTS)
+		goto sticky;
+
+	/* No update for zero timeout */
+	if (!end_time->tv_sec && !end_time->tv_nsec)
+		return ret;
+
+	ktime_get_ts(&ts);
+	ts = timespec_sub(*end_time, ts);
+	if (ts.tv_sec < 0)
+		ts.tv_sec = ts.tv_nsec = 0;
+
+	if (timeval) {
+		struct compat_timeval rtv;
+
+		rtv.tv_sec = ts.tv_sec;
+		rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC;
+
+		if (!copy_to_user(p, &rtv, sizeof(rtv)))
+			return ret;
+	} else {
+		struct compat_timespec rts;
+
+		rts.tv_sec = ts.tv_sec;
+		rts.tv_nsec = ts.tv_nsec;
+
+		if (!copy_to_user(p, &rts, sizeof(rts)))
+			return ret;
+	}
+	/*
+	 * If an application puts its timeval in read-only memory, we
+	 * don't want the Linux-specific update to the timeval to
+	 * cause a fault after the select has completed
+	 * successfully. However, because we're not updating the
+	 * timeval, we can't restart the system call.
+	 */
+
+sticky:
+	if (ret == -ERESTARTNOHAND)
+		ret = -EINTR;
+	return ret;
+}
+
+/*
+ * Ooo, nasty.  We need here to frob 32-bit unsigned longs to
+ * 64-bit unsigned longs.
+ */
+static
+int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
+			unsigned long *fdset)
+{
+	if (ufdset) {
+		return compat_get_bitmap(fdset, ufdset, nr);
+	} else {
+		/* Tricky, must clear full unsigned long in the
+		 * kernel fdset at the end, ALIGN makes sure that
+		 * actually happens.
+		 */
+		memset(fdset, 0, ALIGN(nr, BITS_PER_LONG));
+		return 0;
+	}
+}
+
+static
+int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset,
+		      unsigned long *fdset)
+{
+	if (!ufdset)
+		return 0;
+	return compat_put_bitmap(ufdset, fdset, nr);
+}
+
+
+/*
+ * This is a virtual copy of sys_select from fs/select.c and probably
+ * should be compared to it from time to time
+ */
+
+/*
+ * We can actually return ERESTARTSYS instead of EINTR, but I'd
+ * like to be certain this leads to no problems. So I return
+ * EINTR just for safety.
+ *
+ * Update: ERESTARTSYS breaks at least the xview clock binary, so
+ * I'm trying ERESTARTNOHAND which restart only when you want to.
+ */
+static int compat_core_sys_select(int n, compat_ulong_t __user *inp,
+	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
+	struct timespec *end_time)
+{
+	fd_set_bits fds;
+	void *bits;
+	int size, max_fds, ret = -EINVAL;
+	struct fdtable *fdt;
+	long stack_fds[SELECT_STACK_ALLOC/sizeof(long)];
+
+	if (n < 0)
+		goto out_nofds;
+
+	/* max_fds can increase, so grab it once to avoid race */
+	rcu_read_lock();
+	fdt = files_fdtable(current->files);
+	max_fds = fdt->max_fds;
+	rcu_read_unlock();
+	if (n > max_fds)
+		n = max_fds;
+
+	/*
+	 * We need 6 bitmaps (in/out/ex for both incoming and outgoing),
+	 * since we used fdset we need to allocate memory in units of
+	 * long-words.
+	 */
+	size = FDS_BYTES(n);
+	bits = stack_fds;
+	if (size > sizeof(stack_fds) / 6) {
+		bits = kmalloc(6 * size, GFP_KERNEL);
+		ret = -ENOMEM;
+		if (!bits)
+			goto out_nofds;
+	}
+	fds.in      = (unsigned long *)  bits;
+	fds.out     = (unsigned long *) (bits +   size);
+	fds.ex      = (unsigned long *) (bits + 2*size);
+	fds.res_in  = (unsigned long *) (bits + 3*size);
+	fds.res_out = (unsigned long *) (bits + 4*size);
+	fds.res_ex  = (unsigned long *) (bits + 5*size);
+
+	if ((ret = compat_get_fd_set(n, inp, fds.in)) ||
+	    (ret = compat_get_fd_set(n, outp, fds.out)) ||
+	    (ret = compat_get_fd_set(n, exp, fds.ex)))
+		goto out;
+	zero_fd_set(n, fds.res_in);
+	zero_fd_set(n, fds.res_out);
+	zero_fd_set(n, fds.res_ex);
+
+	ret = do_select(n, &fds, end_time);
+
+	if (ret < 0)
+		goto out;
+	if (!ret) {
+		ret = -ERESTARTNOHAND;
+		if (signal_pending(current))
+			goto out;
+		ret = 0;
+	}
+
+	if (compat_set_fd_set(n, inp, fds.res_in) ||
+	    compat_set_fd_set(n, outp, fds.res_out) ||
+	    compat_set_fd_set(n, exp, fds.res_ex))
+		ret = -EFAULT;
+out:
+	if (bits != stack_fds)
+		kfree(bits);
+out_nofds:
+	return ret;
+}
+
+COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp,
+	compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
+	struct compat_timeval __user *, tvp)
+{
+	struct timespec end_time, *to = NULL;
+	struct compat_timeval tv;
+	int ret;
+
+	if (tvp) {
+		if (copy_from_user(&tv, tvp, sizeof(tv)))
+			return -EFAULT;
+
+		to = &end_time;
+		if (poll_select_set_timeout(to,
+				tv.tv_sec + (tv.tv_usec / USEC_PER_SEC),
+				(tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC))
+			return -EINVAL;
+	}
+
+	ret = compat_core_sys_select(n, inp, outp, exp, to);
+	ret = compat_poll_select_copy_remaining(&end_time, tvp, 1, ret);
+
+	return ret;
+}
+
+struct compat_sel_arg_struct {
+	compat_ulong_t n;
+	compat_uptr_t inp;
+	compat_uptr_t outp;
+	compat_uptr_t exp;
+	compat_uptr_t tvp;
+};
+
+COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg)
+{
+	struct compat_sel_arg_struct a;
+
+	if (copy_from_user(&a, arg, sizeof(a)))
+		return -EFAULT;
+	return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp),
+				 compat_ptr(a.exp), compat_ptr(a.tvp));
+}
+
+static long do_compat_pselect(int n, compat_ulong_t __user *inp,
+	compat_ulong_t __user *outp, compat_ulong_t __user *exp,
+	struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask,
+	compat_size_t sigsetsize)
+{
+	compat_sigset_t ss32;
+	sigset_t ksigmask, sigsaved;
+	struct compat_timespec ts;
+	struct timespec end_time, *to = NULL;
+	int ret;
+
+	if (tsp) {
+		if (copy_from_user(&ts, tsp, sizeof(ts)))
+			return -EFAULT;
+
+		to = &end_time;
+		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
+			return -EINVAL;
+	}
+
+	if (sigmask) {
+		if (sigsetsize != sizeof(compat_sigset_t))
+			return -EINVAL;
+		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
+			return -EFAULT;
+		sigset_from_compat(&ksigmask, &ss32);
+
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
+
+	ret = compat_core_sys_select(n, inp, outp, exp, to);
+	ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret);
+
+	if (ret == -ERESTARTNOHAND) {
+		/*
+		 * Don't restore the signal mask yet. Let do_signal() deliver
+		 * the signal on the way back to userspace, before the signal
+		 * mask is restored.
+		 */
+		if (sigmask) {
+			memcpy(&current->saved_sigmask, &sigsaved,
+					sizeof(sigsaved));
+			set_restore_sigmask();
+		}
+	} else if (sigmask)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+	return ret;
+}
+
+COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp,
+	compat_ulong_t __user *, outp, compat_ulong_t __user *, exp,
+	struct compat_timespec __user *, tsp, void __user *, sig)
+{
+	compat_size_t sigsetsize = 0;
+	compat_uptr_t up = 0;
+
+	if (sig) {
+		if (!access_ok(VERIFY_READ, sig,
+				sizeof(compat_uptr_t)+sizeof(compat_size_t)) ||
+		    	__get_user(up, (compat_uptr_t __user *)sig) ||
+		    	__get_user(sigsetsize,
+				(compat_size_t __user *)(sig+sizeof(up))))
+			return -EFAULT;
+	}
+	return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(up),
+				 sigsetsize);
+}
+
+COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds,
+	unsigned int,  nfds, struct compat_timespec __user *, tsp,
+	const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize)
+{
+	compat_sigset_t ss32;
+	sigset_t ksigmask, sigsaved;
+	struct compat_timespec ts;
+	struct timespec end_time, *to = NULL;
+	int ret;
+
+	if (tsp) {
+		if (copy_from_user(&ts, tsp, sizeof(ts)))
+			return -EFAULT;
+
+		to = &end_time;
+		if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec))
+			return -EINVAL;
+	}
+
+	if (sigmask) {
+		if (sigsetsize != sizeof(compat_sigset_t))
+			return -EINVAL;
+		if (copy_from_user(&ss32, sigmask, sizeof(ss32)))
+			return -EFAULT;
+		sigset_from_compat(&ksigmask, &ss32);
+
+		sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP));
+		sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved);
+	}
+
+	ret = do_sys_poll(ufds, nfds, to);
+
+	/* We can restart this syscall, usually */
+	if (ret == -EINTR) {
+		/*
+		 * Don't restore the signal mask yet. Let do_signal() deliver
+		 * the signal on the way back to userspace, before the signal
+		 * mask is restored.
+		 */
+		if (sigmask) {
+			memcpy(&current->saved_sigmask, &sigsaved,
+				sizeof(sigsaved));
+			set_restore_sigmask();
+		}
+		ret = -ERESTARTNOHAND;
+	} else if (sigmask)
+		sigprocmask(SIG_SETMASK, &sigsaved, NULL);
+
+	ret = compat_poll_select_copy_remaining(&end_time, tsp, 0, ret);
+
+	return ret;
+}
+#endif
diff --git a/fs/seq_file.c b/fs/seq_file.c
index ca69fb99e41a..dc7c2be963ed 100644
--- a/fs/seq_file.c
+++ b/fs/seq_file.c
@@ -25,21 +25,7 @@ static void seq_set_overflow(struct seq_file *m)
 
 static void *seq_buf_alloc(unsigned long size)
 {
-	void *buf;
-	gfp_t gfp = GFP_KERNEL;
-
-	/*
-	 * For high order allocations, use __GFP_NORETRY to avoid oom-killing -
-	 * it's better to fall back to vmalloc() than to kill things.  For small
-	 * allocations, just use GFP_KERNEL which will oom kill, thus no need
-	 * for vmalloc fallback.
-	 */
-	if (size > PAGE_SIZE)
-		gfp |= __GFP_NORETRY | __GFP_NOWARN;
-	buf = kmalloc(size, gfp);
-	if (!buf && size > PAGE_SIZE)
-		buf = vmalloc(size);
-	return buf;
+	return kvmalloc(size, GFP_KERNEL);
 }
 
 /**
diff --git a/fs/signalfd.c b/fs/signalfd.c
index 270221fcef42..593b022ac11b 100644
--- a/fs/signalfd.c
+++ b/fs/signalfd.c
@@ -38,12 +38,12 @@ void signalfd_cleanup(struct sighand_struct *sighand)
 	/*
 	 * The lockless check can race with remove_wait_queue() in progress,
 	 * but in this case its caller should run under rcu_read_lock() and
-	 * sighand_cachep is SLAB_DESTROY_BY_RCU, we can safely return.
+	 * sighand_cachep is SLAB_TYPESAFE_BY_RCU, we can safely return.
 	 */
 	if (likely(!waitqueue_active(wqh)))
 		return;
 
-	/* wait_queue_t->func(POLLFREE) should do remove_wait_queue() */
+	/* wait_queue_entry_t->func(POLLFREE) should do remove_wait_queue() */
 	wake_up_poll(wqh, POLLHUP | POLLFREE);
 }
 
diff --git a/fs/splice.c b/fs/splice.c
index 873d83104e79..ae41201d0325 100644
--- a/fs/splice.c
+++ b/fs/splice.c
@@ -33,6 +33,8 @@
 #include <linux/gfp.h>
 #include <linux/socket.h>
 #include <linux/compat.h>
+#include <linux/sched/signal.h>
+
 #include "internal.h"
 
 /*
@@ -204,6 +206,7 @@ ssize_t splice_to_pipe(struct pipe_inode_info *pipe,
 		buf->len = spd->partial[page_nr].len;
 		buf->private = spd->partial[page_nr].private;
 		buf->ops = spd->ops;
+		buf->flags = 0;
 
 		pipe->nrbufs++;
 		page_nr++;
@@ -244,11 +247,6 @@ ssize_t add_to_pipe(struct pipe_inode_info *pipe, struct pipe_buffer *buf)
 }
 EXPORT_SYMBOL(add_to_pipe);
 
-void spd_release_page(struct splice_pipe_desc *spd, unsigned int i)
-{
-	put_page(spd->pages[i]);
-}
-
 /*
  * Check if we need to grow the arrays holding pages and partial page
  * descriptions.
@@ -306,7 +304,7 @@ ssize_t generic_file_splice_read(struct file *in, loff_t *ppos,
 	idx = to.idx;
 	init_sync_kiocb(&kiocb, in);
 	kiocb.ki_pos = *ppos;
-	ret = in->f_op->read_iter(&kiocb, &to);
+	ret = call_read_iter(in, &kiocb, &to);
 	if (ret > 0) {
 		*ppos = kiocb.ki_pos;
 		file_accessed(in);
@@ -390,7 +388,7 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 	struct iov_iter to;
 	struct page **pages;
 	unsigned int nr_pages;
-	size_t offset, dummy, copied = 0;
+	size_t offset, base, copied = 0;
 	ssize_t res;
 	int i;
 
@@ -405,12 +403,11 @@ static ssize_t default_file_splice_read(struct file *in, loff_t *ppos,
 
 	iov_iter_pipe(&to, ITER_PIPE | READ, pipe, len + offset);
 
-	res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &dummy);
+	res = iov_iter_get_pages_alloc(&to, &pages, len + offset, &base);
 	if (res <= 0)
 		return -ENOMEM;
 
-	BUG_ON(dummy);
-	nr_pages = DIV_ROUND_UP(res, PAGE_SIZE);
+	nr_pages = DIV_ROUND_UP(res + base, PAGE_SIZE);
 
 	vec = __vec;
 	if (nr_pages > PIPE_DEF_BUFFERS) {
@@ -765,7 +762,7 @@ iter_file_splice_write(struct pipe_inode_info *pipe, struct file *out,
 
 		iov_iter_bvec(&from, ITER_BVEC | WRITE, array, n,
 			      sd.total_len - left);
-		ret = vfs_iter_write(out, &from, &sd.pos);
+		ret = vfs_iter_write(out, &from, &sd.pos, 0);
 		if (ret <= 0)
 			break;
 
@@ -1356,6 +1353,8 @@ SYSCALL_DEFINE4(vmsplice, int, fd, const struct iovec __user *, iov,
 	struct fd f;
 	long error;
 
+	if (unlikely(flags & ~SPLICE_F_ALL))
+		return -EINVAL;
 	if (unlikely(nr_segs > UIO_MAXIOV))
 		return -EINVAL;
 	else if (unlikely(!nr_segs))
@@ -1406,6 +1405,9 @@ SYSCALL_DEFINE6(splice, int, fd_in, loff_t __user *, off_in,
 	if (unlikely(!len))
 		return 0;
 
+	if (unlikely(flags & ~SPLICE_F_ALL))
+		return -EINVAL;
+
 	error = -EBADF;
 	in = fdget(fd_in);
 	if (in.file) {
@@ -1734,6 +1736,9 @@ SYSCALL_DEFINE4(tee, int, fdin, int, fdout, size_t, len, unsigned int, flags)
 	struct fd in;
 	int error;
 
+	if (unlikely(flags & ~SPLICE_F_ALL))
+		return -EINVAL;
+
 	if (unlikely(!len))
 		return 0;
 
diff --git a/fs/squashfs/lz4_wrapper.c b/fs/squashfs/lz4_wrapper.c
index ff4468bd18b0..95da65366548 100644
--- a/fs/squashfs/lz4_wrapper.c
+++ b/fs/squashfs/lz4_wrapper.c
@@ -97,7 +97,6 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	struct squashfs_lz4 *stream = strm;
 	void *buff = stream->input, *data;
 	int avail, i, bytes = length, res;
-	size_t dest_len = output->length;
 
 	for (i = 0; i < b; i++) {
 		avail = min(bytes, msblk->devblksize - offset);
@@ -108,12 +107,13 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
 		put_bh(bh[i]);
 	}
 
-	res = lz4_decompress_unknownoutputsize(stream->input, length,
-					stream->output, &dest_len);
-	if (res)
+	res = LZ4_decompress_safe(stream->input, stream->output,
+		length, output->length);
+
+	if (res < 0)
 		return -EIO;
 
-	bytes = dest_len;
+	bytes = res;
 	data = squashfs_first_page(output);
 	buff = stream->output;
 	while (data) {
@@ -128,7 +128,7 @@ static int lz4_uncompress(struct squashfs_sb_info *msblk, void *strm,
 	}
 	squashfs_finish_page(output);
 
-	return dest_len;
+	return res;
 }
 
 const struct squashfs_decompressor squashfs_lz4_comp_ops = {
diff --git a/fs/stat.c b/fs/stat.c
index a268b7f27adf..c35610845ab1 100644
--- a/fs/stat.c
+++ b/fs/stat.c
@@ -12,12 +12,23 @@
 #include <linux/fs.h>
 #include <linux/namei.h>
 #include <linux/security.h>
+#include <linux/cred.h>
 #include <linux/syscalls.h>
 #include <linux/pagemap.h>
+#include <linux/compat.h>
 
 #include <linux/uaccess.h>
 #include <asm/unistd.h>
 
+/**
+ * generic_fillattr - Fill in the basic attributes from the inode struct
+ * @inode: Inode to use as the source
+ * @stat: Where to fill in the attributes
+ *
+ * Fill in the basic attributes in the kstat structure from data that's to be
+ * found on the VFS inode structure.  This is the default if no getattr inode
+ * operation is supplied.
+ */
 void generic_fillattr(struct inode *inode, struct kstat *stat)
 {
 	stat->dev = inode->i_sb->s_dev;
@@ -31,83 +42,150 @@ void generic_fillattr(struct inode *inode, struct kstat *stat)
 	stat->atime = inode->i_atime;
 	stat->mtime = inode->i_mtime;
 	stat->ctime = inode->i_ctime;
-	stat->blksize = (1 << inode->i_blkbits);
+	stat->blksize = i_blocksize(inode);
 	stat->blocks = inode->i_blocks;
-}
 
+	if (IS_NOATIME(inode))
+		stat->result_mask &= ~STATX_ATIME;
+	if (IS_AUTOMOUNT(inode))
+		stat->attributes |= STATX_ATTR_AUTOMOUNT;
+}
 EXPORT_SYMBOL(generic_fillattr);
 
 /**
  * vfs_getattr_nosec - getattr without security checks
  * @path: file to get attributes from
  * @stat: structure to return attributes in
+ * @request_mask: STATX_xxx flags indicating what the caller wants
+ * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
  *
  * Get attributes without calling security_inode_getattr.
  *
  * Currently the only caller other than vfs_getattr is internal to the
- * filehandle lookup code, which uses only the inode number and returns
- * no attributes to any user.  Any other code probably wants
- * vfs_getattr.
+ * filehandle lookup code, which uses only the inode number and returns no
+ * attributes to any user.  Any other code probably wants vfs_getattr.
  */
-int vfs_getattr_nosec(struct path *path, struct kstat *stat)
+int vfs_getattr_nosec(const struct path *path, struct kstat *stat,
+		      u32 request_mask, unsigned int query_flags)
 {
 	struct inode *inode = d_backing_inode(path->dentry);
 
+	memset(stat, 0, sizeof(*stat));
+	stat->result_mask |= STATX_BASIC_STATS;
+	request_mask &= STATX_ALL;
+	query_flags &= KSTAT_QUERY_FLAGS;
 	if (inode->i_op->getattr)
-		return inode->i_op->getattr(path->mnt, path->dentry, stat);
+		return inode->i_op->getattr(path, stat, request_mask,
+					    query_flags);
 
 	generic_fillattr(inode, stat);
 	return 0;
 }
-
 EXPORT_SYMBOL(vfs_getattr_nosec);
 
-int vfs_getattr(struct path *path, struct kstat *stat)
+/*
+ * vfs_getattr - Get the enhanced basic attributes of a file
+ * @path: The file of interest
+ * @stat: Where to return the statistics
+ * @request_mask: STATX_xxx flags indicating what the caller wants
+ * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
+ *
+ * Ask the filesystem for a file's attributes.  The caller must indicate in
+ * request_mask and query_flags to indicate what they want.
+ *
+ * If the file is remote, the filesystem can be forced to update the attributes
+ * from the backing store by passing AT_STATX_FORCE_SYNC in query_flags or can
+ * suppress the update by passing AT_STATX_DONT_SYNC.
+ *
+ * Bits must have been set in request_mask to indicate which attributes the
+ * caller wants retrieving.  Any such attribute not requested may be returned
+ * anyway, but the value may be approximate, and, if remote, may not have been
+ * synchronised with the server.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_getattr(const struct path *path, struct kstat *stat,
+		u32 request_mask, unsigned int query_flags)
 {
 	int retval;
 
 	retval = security_inode_getattr(path);
 	if (retval)
 		return retval;
-	return vfs_getattr_nosec(path, stat);
+	return vfs_getattr_nosec(path, stat, request_mask, query_flags);
 }
-
 EXPORT_SYMBOL(vfs_getattr);
 
-int vfs_fstat(unsigned int fd, struct kstat *stat)
+/**
+ * vfs_statx_fd - Get the enhanced basic attributes by file descriptor
+ * @fd: The file descriptor referring to the file of interest
+ * @stat: The result structure to fill in.
+ * @request_mask: STATX_xxx flags indicating what the caller wants
+ * @query_flags: Query mode (KSTAT_QUERY_FLAGS)
+ *
+ * This function is a wrapper around vfs_getattr().  The main difference is
+ * that it uses a file descriptor to determine the file location.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_statx_fd(unsigned int fd, struct kstat *stat,
+		 u32 request_mask, unsigned int query_flags)
 {
-	struct fd f = fdget_raw(fd);
+	struct fd f;
 	int error = -EBADF;
 
+	if (query_flags & ~KSTAT_QUERY_FLAGS)
+		return -EINVAL;
+
+	f = fdget_raw(fd);
 	if (f.file) {
-		error = vfs_getattr(&f.file->f_path, stat);
+		error = vfs_getattr(&f.file->f_path, stat,
+				    request_mask, query_flags);
 		fdput(f);
 	}
 	return error;
 }
-EXPORT_SYMBOL(vfs_fstat);
+EXPORT_SYMBOL(vfs_statx_fd);
 
-int vfs_fstatat(int dfd, const char __user *filename, struct kstat *stat,
-		int flag)
+/**
+ * vfs_statx - Get basic and extra attributes by filename
+ * @dfd: A file descriptor representing the base dir for a relative filename
+ * @filename: The name of the file of interest
+ * @flags: Flags to control the query
+ * @stat: The result structure to fill in.
+ * @request_mask: STATX_xxx flags indicating what the caller wants
+ *
+ * This function is a wrapper around vfs_getattr().  The main difference is
+ * that it uses a filename and base directory to determine the file location.
+ * Additionally, the use of AT_SYMLINK_NOFOLLOW in flags will prevent a symlink
+ * at the given name from being referenced.
+ *
+ * 0 will be returned on success, and a -ve error code if unsuccessful.
+ */
+int vfs_statx(int dfd, const char __user *filename, int flags,
+	      struct kstat *stat, u32 request_mask)
 {
 	struct path path;
 	int error = -EINVAL;
-	unsigned int lookup_flags = 0;
+	unsigned int lookup_flags = LOOKUP_FOLLOW | LOOKUP_AUTOMOUNT;
 
-	if ((flag & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
-		      AT_EMPTY_PATH)) != 0)
-		goto out;
+	if ((flags & ~(AT_SYMLINK_NOFOLLOW | AT_NO_AUTOMOUNT |
+		       AT_EMPTY_PATH | KSTAT_QUERY_FLAGS)) != 0)
+		return -EINVAL;
 
-	if (!(flag & AT_SYMLINK_NOFOLLOW))
-		lookup_flags |= LOOKUP_FOLLOW;
-	if (flag & AT_EMPTY_PATH)
+	if (flags & AT_SYMLINK_NOFOLLOW)
+		lookup_flags &= ~LOOKUP_FOLLOW;
+	if (flags & AT_NO_AUTOMOUNT)
+		lookup_flags &= ~LOOKUP_AUTOMOUNT;
+	if (flags & AT_EMPTY_PATH)
 		lookup_flags |= LOOKUP_EMPTY;
+
 retry:
 	error = user_path_at(dfd, filename, lookup_flags, &path);
 	if (error)
 		goto out;
 
-	error = vfs_getattr(&path, stat);
+	error = vfs_getattr(&path, stat, request_mask, flags);
 	path_put(&path);
 	if (retry_estale(error, lookup_flags)) {
 		lookup_flags |= LOOKUP_REVAL;
@@ -116,19 +194,7 @@ retry:
 out:
 	return error;
 }
-EXPORT_SYMBOL(vfs_fstatat);
-
-int vfs_stat(const char __user *name, struct kstat *stat)
-{
-	return vfs_fstatat(AT_FDCWD, name, stat, 0);
-}
-EXPORT_SYMBOL(vfs_stat);
-
-int vfs_lstat(const char __user *name, struct kstat *stat)
-{
-	return vfs_fstatat(AT_FDCWD, name, stat, AT_SYMLINK_NOFOLLOW);
-}
-EXPORT_SYMBOL(vfs_lstat);
+EXPORT_SYMBOL(vfs_statx);
 
 
 #ifdef __ARCH_WANT_OLD_STAT
@@ -141,7 +207,7 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta
 {
 	static int warncount = 5;
 	struct __old_kernel_stat tmp;
-	
+
 	if (warncount > 0) {
 		warncount--;
 		printk(KERN_WARNING "VFS: Warning: %s using old stat() call. Recompile your binary.\n",
@@ -166,7 +232,7 @@ static int cp_old_stat(struct kstat *stat, struct __old_kernel_stat __user * sta
 #if BITS_PER_LONG == 32
 	if (stat->size > MAX_NON_LFS)
 		return -EOVERFLOW;
-#endif	
+#endif
 	tmp.st_size = stat->size;
 	tmp.st_atime = stat->atime.tv_sec;
 	tmp.st_mtime = stat->mtime.tv_sec;
@@ -445,6 +511,156 @@ SYSCALL_DEFINE4(fstatat64, int, dfd, const char __user *, filename,
 }
 #endif /* __ARCH_WANT_STAT64 || __ARCH_WANT_COMPAT_STAT64 */
 
+static noinline_for_stack int
+cp_statx(const struct kstat *stat, struct statx __user *buffer)
+{
+	struct statx tmp;
+
+	memset(&tmp, 0, sizeof(tmp));
+
+	tmp.stx_mask = stat->result_mask;
+	tmp.stx_blksize = stat->blksize;
+	tmp.stx_attributes = stat->attributes;
+	tmp.stx_nlink = stat->nlink;
+	tmp.stx_uid = from_kuid_munged(current_user_ns(), stat->uid);
+	tmp.stx_gid = from_kgid_munged(current_user_ns(), stat->gid);
+	tmp.stx_mode = stat->mode;
+	tmp.stx_ino = stat->ino;
+	tmp.stx_size = stat->size;
+	tmp.stx_blocks = stat->blocks;
+	tmp.stx_attributes_mask = stat->attributes_mask;
+	tmp.stx_atime.tv_sec = stat->atime.tv_sec;
+	tmp.stx_atime.tv_nsec = stat->atime.tv_nsec;
+	tmp.stx_btime.tv_sec = stat->btime.tv_sec;
+	tmp.stx_btime.tv_nsec = stat->btime.tv_nsec;
+	tmp.stx_ctime.tv_sec = stat->ctime.tv_sec;
+	tmp.stx_ctime.tv_nsec = stat->ctime.tv_nsec;
+	tmp.stx_mtime.tv_sec = stat->mtime.tv_sec;
+	tmp.stx_mtime.tv_nsec = stat->mtime.tv_nsec;
+	tmp.stx_rdev_major = MAJOR(stat->rdev);
+	tmp.stx_rdev_minor = MINOR(stat->rdev);
+	tmp.stx_dev_major = MAJOR(stat->dev);
+	tmp.stx_dev_minor = MINOR(stat->dev);
+
+	return copy_to_user(buffer, &tmp, sizeof(tmp)) ? -EFAULT : 0;
+}
+
+/**
+ * sys_statx - System call to get enhanced stats
+ * @dfd: Base directory to pathwalk from *or* fd to stat.
+ * @filename: File to stat or "" with AT_EMPTY_PATH
+ * @flags: AT_* flags to control pathwalk.
+ * @mask: Parts of statx struct actually required.
+ * @buffer: Result buffer.
+ *
+ * Note that fstat() can be emulated by setting dfd to the fd of interest,
+ * supplying "" as the filename and setting AT_EMPTY_PATH in the flags.
+ */
+SYSCALL_DEFINE5(statx,
+		int, dfd, const char __user *, filename, unsigned, flags,
+		unsigned int, mask,
+		struct statx __user *, buffer)
+{
+	struct kstat stat;
+	int error;
+
+	if (mask & STATX__RESERVED)
+		return -EINVAL;
+	if ((flags & AT_STATX_SYNC_TYPE) == AT_STATX_SYNC_TYPE)
+		return -EINVAL;
+
+	error = vfs_statx(dfd, filename, flags, &stat, mask);
+	if (error)
+		return error;
+
+	return cp_statx(&stat, buffer);
+}
+
+#ifdef CONFIG_COMPAT
+static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf)
+{
+	struct compat_stat tmp;
+
+	if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev))
+		return -EOVERFLOW;
+
+	memset(&tmp, 0, sizeof(tmp));
+	tmp.st_dev = old_encode_dev(stat->dev);
+	tmp.st_ino = stat->ino;
+	if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino)
+		return -EOVERFLOW;
+	tmp.st_mode = stat->mode;
+	tmp.st_nlink = stat->nlink;
+	if (tmp.st_nlink != stat->nlink)
+		return -EOVERFLOW;
+	SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid));
+	SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid));
+	tmp.st_rdev = old_encode_dev(stat->rdev);
+	if ((u64) stat->size > MAX_NON_LFS)
+		return -EOVERFLOW;
+	tmp.st_size = stat->size;
+	tmp.st_atime = stat->atime.tv_sec;
+	tmp.st_atime_nsec = stat->atime.tv_nsec;
+	tmp.st_mtime = stat->mtime.tv_sec;
+	tmp.st_mtime_nsec = stat->mtime.tv_nsec;
+	tmp.st_ctime = stat->ctime.tv_sec;
+	tmp.st_ctime_nsec = stat->ctime.tv_nsec;
+	tmp.st_blocks = stat->blocks;
+	tmp.st_blksize = stat->blksize;
+	return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0;
+}
+
+COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename,
+		       struct compat_stat __user *, statbuf)
+{
+	struct kstat stat;
+	int error;
+
+	error = vfs_stat(filename, &stat);
+	if (error)
+		return error;
+	return cp_compat_stat(&stat, statbuf);
+}
+
+COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename,
+		       struct compat_stat __user *, statbuf)
+{
+	struct kstat stat;
+	int error;
+
+	error = vfs_lstat(filename, &stat);
+	if (error)
+		return error;
+	return cp_compat_stat(&stat, statbuf);
+}
+
+#ifndef __ARCH_WANT_STAT64
+COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd,
+		       const char __user *, filename,
+		       struct compat_stat __user *, statbuf, int, flag)
+{
+	struct kstat stat;
+	int error;
+
+	error = vfs_fstatat(dfd, filename, &stat, flag);
+	if (error)
+		return error;
+	return cp_compat_stat(&stat, statbuf);
+}
+#endif
+
+COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd,
+		       struct compat_stat __user *, statbuf)
+{
+	struct kstat stat;
+	int error = vfs_fstat(fd, &stat);
+
+	if (!error)
+		error = cp_compat_stat(&stat, statbuf);
+	return error;
+}
+#endif
+
 /* Caller is here responsible for sufficient locking (ie. inode->i_lock) */
 void __inode_add_bytes(struct inode *inode, loff_t bytes)
 {
@@ -456,6 +672,7 @@ void __inode_add_bytes(struct inode *inode, loff_t bytes)
 		inode->i_bytes -= 512;
 	}
 }
+EXPORT_SYMBOL(__inode_add_bytes);
 
 void inode_add_bytes(struct inode *inode, loff_t bytes)
 {
diff --git a/fs/statfs.c b/fs/statfs.c
index 13ae259d4879..fab9b6a3c116 100644
--- a/fs/statfs.c
+++ b/fs/statfs.c
@@ -7,6 +7,7 @@
 #include <linux/statfs.h>
 #include <linux/security.h>
 #include <linux/uaccess.h>
+#include <linux/compat.h>
 #include "internal.h"
 
 static int flags_by_mnt(int mnt_flags)
@@ -37,6 +38,8 @@ static int flags_by_sb(int s_flags)
 		flags |= ST_SYNCHRONOUS;
 	if (s_flags & MS_MANDLOCK)
 		flags |= ST_MANDLOCK;
+	if (s_flags & MS_RDONLY)
+		flags |= ST_RDONLY;
 	return flags;
 }
 
@@ -239,3 +242,144 @@ SYSCALL_DEFINE2(ustat, unsigned, dev, struct ustat __user *, ubuf)
 
 	return copy_to_user(ubuf, &tmp, sizeof(struct ustat)) ? -EFAULT : 0;
 }
+
+#ifdef CONFIG_COMPAT
+static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs *kbuf)
+{
+	struct compat_statfs buf;
+	if (sizeof ubuf->f_blocks == 4) {
+		if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail |
+		     kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL)
+			return -EOVERFLOW;
+		/* f_files and f_ffree may be -1; it's okay
+		 * to stuff that into 32 bits */
+		if (kbuf->f_files != 0xffffffffffffffffULL
+		 && (kbuf->f_files & 0xffffffff00000000ULL))
+			return -EOVERFLOW;
+		if (kbuf->f_ffree != 0xffffffffffffffffULL
+		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
+			return -EOVERFLOW;
+	}
+	memset(&buf, 0, sizeof(struct compat_statfs));
+	buf.f_type = kbuf->f_type;
+	buf.f_bsize = kbuf->f_bsize;
+	buf.f_blocks = kbuf->f_blocks;
+	buf.f_bfree = kbuf->f_bfree;
+	buf.f_bavail = kbuf->f_bavail;
+	buf.f_files = kbuf->f_files;
+	buf.f_ffree = kbuf->f_ffree;
+	buf.f_namelen = kbuf->f_namelen;
+	buf.f_fsid.val[0] = kbuf->f_fsid.val[0];
+	buf.f_fsid.val[1] = kbuf->f_fsid.val[1];
+	buf.f_frsize = kbuf->f_frsize;
+	buf.f_flags = kbuf->f_flags;
+	if (copy_to_user(ubuf, &buf, sizeof(struct compat_statfs)))
+		return -EFAULT;
+	return 0;
+}
+
+/*
+ * The following statfs calls are copies of code from fs/statfs.c and
+ * should be checked against those from time to time
+ */
+COMPAT_SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct compat_statfs __user *, buf)
+{
+	struct kstatfs tmp;
+	int error = user_statfs(pathname, &tmp);
+	if (!error)
+		error = put_compat_statfs(buf, &tmp);
+	return error;
+}
+
+COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, buf)
+{
+	struct kstatfs tmp;
+	int error = fd_statfs(fd, &tmp);
+	if (!error)
+		error = put_compat_statfs(buf, &tmp);
+	return error;
+}
+
+static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf)
+{
+	struct compat_statfs64 buf;
+	if (sizeof(ubuf->f_bsize) == 4) {
+		if ((kbuf->f_type | kbuf->f_bsize | kbuf->f_namelen |
+		     kbuf->f_frsize | kbuf->f_flags) & 0xffffffff00000000ULL)
+			return -EOVERFLOW;
+		/* f_files and f_ffree may be -1; it's okay
+		 * to stuff that into 32 bits */
+		if (kbuf->f_files != 0xffffffffffffffffULL
+		 && (kbuf->f_files & 0xffffffff00000000ULL))
+			return -EOVERFLOW;
+		if (kbuf->f_ffree != 0xffffffffffffffffULL
+		 && (kbuf->f_ffree & 0xffffffff00000000ULL))
+			return -EOVERFLOW;
+	}
+	memset(&buf, 0, sizeof(struct compat_statfs64));
+	buf.f_type = kbuf->f_type;
+	buf.f_bsize = kbuf->f_bsize;
+	buf.f_blocks = kbuf->f_blocks;
+	buf.f_bfree = kbuf->f_bfree;
+	buf.f_bavail = kbuf->f_bavail;
+	buf.f_files = kbuf->f_files;
+	buf.f_ffree = kbuf->f_ffree;
+	buf.f_namelen = kbuf->f_namelen;
+	buf.f_fsid.val[0] = kbuf->f_fsid.val[0];
+	buf.f_fsid.val[1] = kbuf->f_fsid.val[1];
+	buf.f_frsize = kbuf->f_frsize;
+	buf.f_flags = kbuf->f_flags;
+	if (copy_to_user(ubuf, &buf, sizeof(struct compat_statfs64)))
+		return -EFAULT;
+	return 0;
+}
+
+COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf)
+{
+	struct kstatfs tmp;
+	int error;
+
+	if (sz != sizeof(*buf))
+		return -EINVAL;
+
+	error = user_statfs(pathname, &tmp);
+	if (!error)
+		error = put_compat_statfs64(buf, &tmp);
+	return error;
+}
+
+COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf)
+{
+	struct kstatfs tmp;
+	int error;
+
+	if (sz != sizeof(*buf))
+		return -EINVAL;
+
+	error = fd_statfs(fd, &tmp);
+	if (!error)
+		error = put_compat_statfs64(buf, &tmp);
+	return error;
+}
+
+/*
+ * This is a copy of sys_ustat, just dealing with a structure layout.
+ * Given how simple this syscall is that apporach is more maintainable
+ * than the various conversion hacks.
+ */
+COMPAT_SYSCALL_DEFINE2(ustat, unsigned, dev, struct compat_ustat __user *, u)
+{
+	struct compat_ustat tmp;
+	struct kstatfs sbuf;
+	int err = vfs_ustat(new_decode_dev(dev), &sbuf);
+	if (err)
+		return err;
+
+	memset(&tmp, 0, sizeof(struct compat_ustat));
+	tmp.f_tfree = sbuf.f_bfree;
+	tmp.f_tinode = sbuf.f_ffree;
+	if (copy_to_user(u, &tmp, sizeof(struct compat_ustat)))
+		return -EFAULT;
+	return 0;
+}
+#endif
diff --git a/fs/super.c b/fs/super.c
index 1709ed029a2c..6bc3352adcf3 100644
--- a/fs/super.c
+++ b/fs/super.c
@@ -168,7 +168,6 @@ static void destroy_super(struct super_block *s)
 	WARN_ON(!list_empty(&s->s_mounts));
 	put_user_ns(s->s_user_ns);
 	kfree(s->s_subtype);
-	kfree(s->s_options);
 	call_rcu(&s->rcu, destroy_super_rcu);
 }
 
@@ -446,6 +445,10 @@ void generic_shutdown_super(struct super_block *sb)
 	hlist_del_init(&sb->s_instances);
 	spin_unlock(&sb_lock);
 	up_write(&sb->s_umount);
+	if (sb->s_bdi != &noop_backing_dev_info) {
+		bdi_put(sb->s_bdi);
+		sb->s_bdi = &noop_backing_dev_info;
+	}
 }
 
 EXPORT_SYMBOL(generic_shutdown_super);
@@ -469,7 +472,7 @@ struct super_block *sget_userns(struct file_system_type *type,
 	struct super_block *old;
 	int err;
 
-	if (!(flags & MS_KERNMOUNT) &&
+	if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) &&
 	    !(type->fs_flags & FS_USERNS_MOUNT) &&
 	    !capable(CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
@@ -499,12 +502,12 @@ retry:
 	}
 	if (!s) {
 		spin_unlock(&sb_lock);
-		s = alloc_super(type, flags, user_ns);
+		s = alloc_super(type, (flags & ~MS_SUBMOUNT), user_ns);
 		if (!s)
 			return ERR_PTR(-ENOMEM);
 		goto retry;
 	}
-		
+
 	err = set(s, data);
 	if (err) {
 		spin_unlock(&sb_lock);
@@ -540,8 +543,15 @@ struct super_block *sget(struct file_system_type *type,
 {
 	struct user_namespace *user_ns = current_user_ns();
 
+	/* We don't yet pass the user namespace of the parent
+	 * mount through to here so always use &init_user_ns
+	 * until that changes.
+	 */
+	if (flags & MS_SUBMOUNT)
+		user_ns = &init_user_ns;
+
 	/* Ensure the requestor has permissions over the target filesystem */
-	if (!(flags & MS_KERNMOUNT) && !ns_capable(user_ns, CAP_SYS_ADMIN))
+	if (!(flags & (MS_KERNMOUNT|MS_SUBMOUNT)) && !ns_capable(user_ns, CAP_SYS_ADMIN))
 		return ERR_PTR(-EPERM);
 
 	return sget_userns(type, test, set, flags, user_ns, data);
@@ -760,7 +770,7 @@ restart:
 	spin_unlock(&sb_lock);
 	return NULL;
 }
- 
+
 struct super_block *user_get_super(dev_t dev)
 {
 	struct super_block *sb;
@@ -1042,12 +1052,8 @@ static int set_bdev_super(struct super_block *s, void *data)
 {
 	s->s_bdev = data;
 	s->s_dev = s->s_bdev->bd_dev;
+	s->s_bdi = bdi_get(s->s_bdev->bd_bdi);
 
-	/*
-	 * We set the bdi here to the queue backing, file systems can
-	 * overwrite this in ->fill_super()
-	 */
-	s->s_bdi = &bdev_get_queue(s->s_bdev)->backing_dev_info;
 	return 0;
 }
 
@@ -1249,6 +1255,49 @@ out:
 }
 
 /*
+ * Setup private BDI for given superblock. It gets automatically cleaned up
+ * in generic_shutdown_super().
+ */
+int super_setup_bdi_name(struct super_block *sb, char *fmt, ...)
+{
+	struct backing_dev_info *bdi;
+	int err;
+	va_list args;
+
+	bdi = bdi_alloc(GFP_KERNEL);
+	if (!bdi)
+		return -ENOMEM;
+
+	bdi->name = sb->s_type->name;
+
+	va_start(args, fmt);
+	err = bdi_register_va(bdi, fmt, args);
+	va_end(args);
+	if (err) {
+		bdi_put(bdi);
+		return err;
+	}
+	WARN_ON(sb->s_bdi != &noop_backing_dev_info);
+	sb->s_bdi = bdi;
+
+	return 0;
+}
+EXPORT_SYMBOL(super_setup_bdi_name);
+
+/*
+ * Setup private BDI for given superblock. I gets automatically cleaned up
+ * in generic_shutdown_super().
+ */
+int super_setup_bdi(struct super_block *sb)
+{
+	static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0);
+
+	return super_setup_bdi_name(sb, "%.28s-%ld", sb->s_type->name,
+				    atomic_long_inc_return(&bdi_seq));
+}
+EXPORT_SYMBOL(super_setup_bdi);
+
+/*
  * This is an internal function, please use sb_end_{write,pagefault,intwrite}
  * instead.
  */
diff --git a/fs/sysfs/file.c b/fs/sysfs/file.c
index b803213d1307..39c75a86c67f 100644
--- a/fs/sysfs/file.c
+++ b/fs/sysfs/file.c
@@ -108,7 +108,7 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
 {
 	const struct sysfs_ops *ops = sysfs_file_ops(of->kn);
 	struct kobject *kobj = of->kn->parent->priv;
-	size_t len;
+	ssize_t len;
 
 	/*
 	 * If buf != of->prealloc_buf, we don't know how
@@ -117,13 +117,15 @@ static ssize_t sysfs_kf_read(struct kernfs_open_file *of, char *buf,
 	if (WARN_ON_ONCE(buf != of->prealloc_buf))
 		return 0;
 	len = ops->show(kobj, of->kn->priv, buf);
+	if (len < 0)
+		return len;
 	if (pos) {
 		if (len <= pos)
 			return 0;
 		len -= pos;
 		memmove(buf, buf + pos, len);
 	}
-	return min(count, len);
+	return min_t(ssize_t, count, len);
 }
 
 /* kernfs write callback for regular sysfs files */
diff --git a/fs/sysv/dir.c b/fs/sysv/dir.c
index 5bdae85ceef7..f5191cb2c947 100644
--- a/fs/sysv/dir.c
+++ b/fs/sysv/dir.c
@@ -45,7 +45,7 @@ static int dir_commit_chunk(struct page *page, loff_t pos, unsigned len)
 		mark_inode_dirty(dir);
 	}
 	if (IS_DIRSYNC(dir))
-		err = write_one_page(page, 1);
+		err = write_one_page(page);
 	else
 		unlock_page(page);
 	return err;
diff --git a/fs/sysv/itree.c b/fs/sysv/itree.c
index 08d3e630b49c..83809f5b5eca 100644
--- a/fs/sysv/itree.c
+++ b/fs/sysv/itree.c
@@ -440,10 +440,11 @@ static unsigned sysv_nblocks(struct super_block *s, loff_t size)
 	return blocks;
 }
 
-int sysv_getattr(struct vfsmount *mnt, struct dentry *dentry, struct kstat *stat)
+int sysv_getattr(const struct path *path, struct kstat *stat,
+		 u32 request_mask, unsigned int flags)
 {
-	struct super_block *s = dentry->d_sb;
-	generic_fillattr(d_inode(dentry), stat);
+	struct super_block *s = path->dentry->d_sb;
+	generic_fillattr(d_inode(path->dentry), stat);
 	stat->blocks = (s->s_blocksize / 512) * sysv_nblocks(s, stat->size);
 	stat->blksize = s->s_blocksize;
 	return 0;
diff --git a/fs/sysv/sysv.h b/fs/sysv/sysv.h
index 6c212288adcb..1e7e27c729af 100644
--- a/fs/sysv/sysv.h
+++ b/fs/sysv/sysv.h
@@ -142,7 +142,7 @@ extern struct inode *sysv_iget(struct super_block *, unsigned int);
 extern int sysv_write_inode(struct inode *, struct writeback_control *wbc);
 extern int sysv_sync_inode(struct inode *);
 extern void sysv_set_inode(struct inode *, dev_t);
-extern int sysv_getattr(struct vfsmount *, struct dentry *, struct kstat *);
+extern int sysv_getattr(const struct path *, struct kstat *, u32, unsigned int);
 extern int sysv_init_icache(void);
 extern void sysv_destroy_icache(void);
 
diff --git a/fs/timerfd.c b/fs/timerfd.c
index c173cc196175..ece0c02d7e63 100644
--- a/fs/timerfd.c
+++ b/fs/timerfd.c
@@ -40,6 +40,7 @@ struct timerfd_ctx {
 	short unsigned settime_flags;	/* to show in fdinfo */
 	struct rcu_head rcu;
 	struct list_head clist;
+	spinlock_t cancel_lock;
 	bool might_cancel;
 };
 
@@ -112,7 +113,7 @@ void timerfd_clock_was_set(void)
 	rcu_read_unlock();
 }
 
-static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
+static void __timerfd_remove_cancel(struct timerfd_ctx *ctx)
 {
 	if (ctx->might_cancel) {
 		ctx->might_cancel = false;
@@ -122,6 +123,13 @@ static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
 	}
 }
 
+static void timerfd_remove_cancel(struct timerfd_ctx *ctx)
+{
+	spin_lock(&ctx->cancel_lock);
+	__timerfd_remove_cancel(ctx);
+	spin_unlock(&ctx->cancel_lock);
+}
+
 static bool timerfd_canceled(struct timerfd_ctx *ctx)
 {
 	if (!ctx->might_cancel || ctx->moffs != KTIME_MAX)
@@ -132,6 +140,7 @@ static bool timerfd_canceled(struct timerfd_ctx *ctx)
 
 static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
 {
+	spin_lock(&ctx->cancel_lock);
 	if ((ctx->clockid == CLOCK_REALTIME ||
 	     ctx->clockid == CLOCK_REALTIME_ALARM) &&
 	    (flags & TFD_TIMER_ABSTIME) && (flags & TFD_TIMER_CANCEL_ON_SET)) {
@@ -141,9 +150,10 @@ static void timerfd_setup_cancel(struct timerfd_ctx *ctx, int flags)
 			list_add_rcu(&ctx->clist, &cancel_list);
 			spin_unlock(&cancel_lock);
 		}
-	} else if (ctx->might_cancel) {
-		timerfd_remove_cancel(ctx);
+	} else {
+		__timerfd_remove_cancel(ctx);
 	}
+	spin_unlock(&ctx->cancel_lock);
 }
 
 static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
@@ -159,7 +169,7 @@ static ktime_t timerfd_get_remaining(struct timerfd_ctx *ctx)
 }
 
 static int timerfd_setup(struct timerfd_ctx *ctx, int flags,
-			 const struct itimerspec *ktmr)
+			 const struct itimerspec64 *ktmr)
 {
 	enum hrtimer_mode htmode;
 	ktime_t texp;
@@ -168,10 +178,10 @@ static int timerfd_setup(struct timerfd_ctx *ctx, int flags,
 	htmode = (flags & TFD_TIMER_ABSTIME) ?
 		HRTIMER_MODE_ABS: HRTIMER_MODE_REL;
 
-	texp = timespec_to_ktime(ktmr->it_value);
+	texp = timespec64_to_ktime(ktmr->it_value);
 	ctx->expired = 0;
 	ctx->ticks = 0;
-	ctx->tintv = timespec_to_ktime(ktmr->it_interval);
+	ctx->tintv = timespec64_to_ktime(ktmr->it_interval);
 
 	if (isalarm(ctx)) {
 		alarm_init(&ctx->t.alarm,
@@ -390,9 +400,9 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 	     clockid != CLOCK_BOOTTIME_ALARM))
 		return -EINVAL;
 
-	if (!capable(CAP_WAKE_ALARM) &&
-	    (clockid == CLOCK_REALTIME_ALARM ||
-	     clockid == CLOCK_BOOTTIME_ALARM))
+	if ((clockid == CLOCK_REALTIME_ALARM ||
+	     clockid == CLOCK_BOOTTIME_ALARM) &&
+	    !capable(CAP_WAKE_ALARM))
 		return -EPERM;
 
 	ctx = kzalloc(sizeof(*ctx), GFP_KERNEL);
@@ -400,6 +410,7 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 		return -ENOMEM;
 
 	init_waitqueue_head(&ctx->wqh);
+	spin_lock_init(&ctx->cancel_lock);
 	ctx->clockid = clockid;
 
 	if (isalarm(ctx))
@@ -421,16 +432,15 @@ SYSCALL_DEFINE2(timerfd_create, int, clockid, int, flags)
 }
 
 static int do_timerfd_settime(int ufd, int flags, 
-		const struct itimerspec *new,
-		struct itimerspec *old)
+		const struct itimerspec64 *new,
+		struct itimerspec64 *old)
 {
 	struct fd f;
 	struct timerfd_ctx *ctx;
 	int ret;
 
 	if ((flags & ~TFD_SETTIME_FLAGS) ||
-	    !timespec_valid(&new->it_value) ||
-	    !timespec_valid(&new->it_interval))
+		 !itimerspec64_valid(new))
 		return -EINVAL;
 
 	ret = timerfd_fget(ufd, &f);
@@ -438,7 +448,7 @@ static int do_timerfd_settime(int ufd, int flags,
 		return ret;
 	ctx = f.file->private_data;
 
-	if (!capable(CAP_WAKE_ALARM) && isalarm(ctx)) {
+	if (isalarm(ctx) && !capable(CAP_WAKE_ALARM)) {
 		fdput(f);
 		return -EPERM;
 	}
@@ -476,8 +486,8 @@ static int do_timerfd_settime(int ufd, int flags,
 			hrtimer_forward_now(&ctx->t.tmr, ctx->tintv);
 	}
 
-	old->it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
-	old->it_interval = ktime_to_timespec(ctx->tintv);
+	old->it_value = ktime_to_timespec64(timerfd_get_remaining(ctx));
+	old->it_interval = ktime_to_timespec64(ctx->tintv);
 
 	/*
 	 * Re-program the timer to the new value ...
@@ -489,7 +499,7 @@ static int do_timerfd_settime(int ufd, int flags,
 	return ret;
 }
 
-static int do_timerfd_gettime(int ufd, struct itimerspec *t)
+static int do_timerfd_gettime(int ufd, struct itimerspec64 *t)
 {
 	struct fd f;
 	struct timerfd_ctx *ctx;
@@ -514,8 +524,8 @@ static int do_timerfd_gettime(int ufd, struct itimerspec *t)
 			hrtimer_restart(&ctx->t.tmr);
 		}
 	}
-	t->it_value = ktime_to_timespec(timerfd_get_remaining(ctx));
-	t->it_interval = ktime_to_timespec(ctx->tintv);
+	t->it_value = ktime_to_timespec64(timerfd_get_remaining(ctx));
+	t->it_interval = ktime_to_timespec64(ctx->tintv);
 	spin_unlock_irq(&ctx->wqh.lock);
 	fdput(f);
 	return 0;
@@ -525,15 +535,15 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
 		const struct itimerspec __user *, utmr,
 		struct itimerspec __user *, otmr)
 {
-	struct itimerspec new, old;
+	struct itimerspec64 new, old;
 	int ret;
 
-	if (copy_from_user(&new, utmr, sizeof(new)))
+	if (get_itimerspec64(&new, utmr))
 		return -EFAULT;
 	ret = do_timerfd_settime(ufd, flags, &new, &old);
 	if (ret)
 		return ret;
-	if (otmr && copy_to_user(otmr, &old, sizeof(old)))
+	if (otmr && put_itimerspec64(&old, otmr))
 		return -EFAULT;
 
 	return ret;
@@ -541,11 +551,11 @@ SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
 
 SYSCALL_DEFINE2(timerfd_gettime, int, ufd, struct itimerspec __user *, otmr)
 {
-	struct itimerspec kotmr;
+	struct itimerspec64 kotmr;
 	int ret = do_timerfd_gettime(ufd, &kotmr);
 	if (ret)
 		return ret;
-	return copy_to_user(otmr, &kotmr, sizeof(kotmr)) ? -EFAULT: 0;
+	return put_itimerspec64(&kotmr, otmr) ? -EFAULT : 0;
 }
 
 #ifdef CONFIG_COMPAT
@@ -553,15 +563,15 @@ COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
 		const struct compat_itimerspec __user *, utmr,
 		struct compat_itimerspec __user *, otmr)
 {
-	struct itimerspec new, old;
+	struct itimerspec64 new, old;
 	int ret;
 
-	if (get_compat_itimerspec(&new, utmr))
+	if (get_compat_itimerspec64(&new, utmr))
 		return -EFAULT;
 	ret = do_timerfd_settime(ufd, flags, &new, &old);
 	if (ret)
 		return ret;
-	if (otmr && put_compat_itimerspec(otmr, &old))
+	if (otmr && put_compat_itimerspec64(&old, otmr))
 		return -EFAULT;
 	return ret;
 }
@@ -569,10 +579,10 @@ COMPAT_SYSCALL_DEFINE4(timerfd_settime, int, ufd, int, flags,
 COMPAT_SYSCALL_DEFINE2(timerfd_gettime, int, ufd,
 		struct compat_itimerspec __user *, otmr)
 {
-	struct itimerspec kotmr;
+	struct itimerspec64 kotmr;
 	int ret = do_timerfd_gettime(ufd, &kotmr);
 	if (ret)
 		return ret;
-	return put_compat_itimerspec(otmr, &kotmr) ? -EFAULT: 0;
+	return put_compat_itimerspec64(&kotmr, otmr) ? -EFAULT : 0;
 }
 #endif
diff --git a/fs/tracefs/inode.c b/fs/tracefs/inode.c
index 21d36d284735..bea8ad876bf9 100644
--- a/fs/tracefs/inode.c
+++ b/fs/tracefs/inode.c
@@ -266,12 +266,10 @@ static const struct super_operations tracefs_super_operations = {
 
 static int trace_fill_super(struct super_block *sb, void *data, int silent)
 {
-	static struct tree_descr trace_files[] = {{""}};
+	static const struct tree_descr trace_files[] = {{""}};
 	struct tracefs_fs_info *fsi;
 	int err;
 
-	save_mount_options(sb, data);
-
 	fsi = kzalloc(sizeof(struct tracefs_fs_info), GFP_KERNEL);
 	sb->s_fs_info = fsi;
 	if (!fsi) {
diff --git a/fs/ubifs/Kconfig b/fs/ubifs/Kconfig
index b0d0623c83ed..83a961bf7280 100644
--- a/fs/ubifs/Kconfig
+++ b/fs/ubifs/Kconfig
@@ -61,3 +61,16 @@ config UBIFS_FS_ENCRYPTION
 	  feature is similar to ecryptfs, but it is more memory
 	  efficient since it avoids caching the encrypted and
 	  decrypted pages in the page cache.
+
+config UBIFS_FS_SECURITY
+	bool "UBIFS Security Labels"
+	depends on UBIFS_FS
+	default y
+	help
+	  Security labels provide an access control facility to support Linux
+	  Security Models (LSMs) accepted by AppArmor, SELinux, Smack and TOMOYO
+	  Linux. This option enables an extended attribute handler for file
+	  security labels in the ubifs filesystem, so that it requires enabling
+	  the extended attribute support in advance.
+
+	  If you are not using a security module, say N.
diff --git a/fs/ubifs/crypto.c b/fs/ubifs/crypto.c
index 3402720f2b28..114ba455bac3 100644
--- a/fs/ubifs/crypto.c
+++ b/fs/ubifs/crypto.c
@@ -9,8 +9,13 @@ static int ubifs_crypt_get_context(struct inode *inode, void *ctx, size_t len)
 static int ubifs_crypt_set_context(struct inode *inode, const void *ctx,
 				   size_t len, void *fs_data)
 {
+	/*
+	 * Creating an encryption context is done unlocked since we
+	 * operate on a new inode which is not visible to other users
+	 * at this point. So, no need to check whether inode is locked.
+	 */
 	return ubifs_xattr_set(inode, UBIFS_XATTR_NAME_ENCRYPTION_CONTEXT,
-			       ctx, len, 0);
+			       ctx, len, 0, false);
 }
 
 static bool ubifs_crypt_empty_dir(struct inode *inode)
@@ -26,15 +31,6 @@ static unsigned int ubifs_crypt_max_namelen(struct inode *inode)
 		return UBIFS_MAX_NLEN;
 }
 
-static int ubifs_key_prefix(struct inode *inode, u8 **key)
-{
-	static char prefix[] = "ubifs:";
-
-	*key = prefix;
-
-	return sizeof(prefix) - 1;
-}
-
 int ubifs_encrypt(const struct inode *inode, struct ubifs_data_node *dn,
 		  unsigned int in_len, unsigned int *out_len, int block)
 {
@@ -86,12 +82,12 @@ int ubifs_decrypt(const struct inode *inode, struct ubifs_data_node *dn,
 	return 0;
 }
 
-struct fscrypt_operations ubifs_crypt_operations = {
+const struct fscrypt_operations ubifs_crypt_operations = {
 	.flags			= FS_CFLG_OWN_PAGES,
+	.key_prefix		= "ubifs:",
 	.get_context		= ubifs_crypt_get_context,
 	.set_context		= ubifs_crypt_set_context,
 	.is_encrypted		= __ubifs_crypt_is_encrypted,
 	.empty_dir		= ubifs_crypt_empty_dir,
 	.max_namelen		= ubifs_crypt_max_namelen,
-	.key_prefix		= ubifs_key_prefix,
 };
diff --git a/fs/ubifs/debug.c b/fs/ubifs/debug.c
index 1e712a364680..7cd8a7b95299 100644
--- a/fs/ubifs/debug.c
+++ b/fs/ubifs/debug.c
@@ -32,6 +32,7 @@
 #include <linux/math64.h>
 #include <linux/uaccess.h>
 #include <linux/random.h>
+#include <linux/ctype.h>
 #include "ubifs.h"
 
 static DEFINE_SPINLOCK(dbg_lock);
@@ -286,8 +287,10 @@ void ubifs_dump_inode(struct ubifs_info *c, const struct inode *inode)
 			break;
 		}
 
-		pr_err("\t%d: %s (%s)\n",
-		       count++, dent->name, get_dent_type(dent->type));
+		pr_err("\t%d: inode %llu, type %s, len %d\n",
+		       count++, (unsigned long long) le64_to_cpu(dent->inum),
+		       get_dent_type(dent->type),
+		       le16_to_cpu(dent->nlen));
 
 		fname_name(&nm) = dent->name;
 		fname_len(&nm) = le16_to_cpu(dent->nlen);
@@ -464,7 +467,8 @@ void ubifs_dump_node(const struct ubifs_info *c, const void *node)
 			pr_err("(bad name length, not printing, bad or corrupted node)");
 		else {
 			for (i = 0; i < nlen && dent->name[i]; i++)
-				pr_cont("%c", dent->name[i]);
+				pr_cont("%c", isprint(dent->name[i]) ?
+					dent->name[i] : '?');
 		}
 		pr_cont("\n");
 
@@ -2387,8 +2391,8 @@ int dbg_check_nondata_nodes_order(struct ubifs_info *c, struct list_head *head)
 			ubifs_dump_node(c, sa->node);
 			return -EINVAL;
 		}
-		if (sa->type != UBIFS_INO_NODE && sa->type != UBIFS_DENT_NODE &&
-		    sa->type != UBIFS_XENT_NODE) {
+		if (sb->type != UBIFS_INO_NODE && sb->type != UBIFS_DENT_NODE &&
+		    sb->type != UBIFS_XENT_NODE) {
 			ubifs_err(c, "bad node type %d", sb->type);
 			ubifs_dump_node(c, sb->node);
 			return -EINVAL;
diff --git a/fs/ubifs/dir.c b/fs/ubifs/dir.c
index 528369f3e472..417fe0b29f23 100644
--- a/fs/ubifs/dir.c
+++ b/fs/ubifs/dir.c
@@ -121,7 +121,7 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir,
 
 	inode_init_owner(inode, dir, mode);
 	inode->i_mtime = inode->i_atime = inode->i_ctime =
-			 ubifs_current_time(inode);
+			 current_time(inode);
 	inode->i_mapping->nrpages = 0;
 
 	switch (mode & S_IFMT) {
@@ -143,6 +143,7 @@ struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir,
 	case S_IFBLK:
 	case S_IFCHR:
 		inode->i_op  = &ubifs_file_inode_operations;
+		encrypted = false;
 		break;
 	default:
 		BUG();
@@ -285,6 +286,15 @@ static struct dentry *ubifs_lookup(struct inode *dir, struct dentry *dentry,
 		goto out_dent;
 	}
 
+	if (ubifs_crypt_is_encrypted(dir) &&
+	    (S_ISDIR(inode->i_mode) || S_ISLNK(inode->i_mode)) &&
+	    !fscrypt_has_permitted_context(dir, inode)) {
+		ubifs_warn(c, "Inconsistent encryption contexts: %lu/%lu",
+			   dir->i_ino, inode->i_ino);
+		err = -EPERM;
+		goto out_inode;
+	}
+
 done:
 	kfree(dent);
 	fscrypt_free_filename(&nm);
@@ -295,6 +305,8 @@ done:
 	d_add(dentry, inode);
 	return NULL;
 
+out_inode:
+	iput(inode);
 out_dent:
 	kfree(dent);
 out_fname:
@@ -606,8 +618,8 @@ static int ubifs_readdir(struct file *file, struct dir_context *ctx)
 	}
 
 	while (1) {
-		dbg_gen("feed '%s', ino %llu, new f_pos %#x",
-			dent->name, (unsigned long long)le64_to_cpu(dent->inum),
+		dbg_gen("ino %llu, new f_pos %#x",
+			(unsigned long long)le64_to_cpu(dent->inum),
 			key_hash_flash(c, &dent->key));
 		ubifs_assert(le64_to_cpu(dent->ch.sqnum) >
 			     ubifs_inode(dir)->creat_sqnum);
@@ -748,9 +760,14 @@ static int ubifs_link(struct dentry *old_dentry, struct inode *dir,
 		goto out_fname;
 
 	lock_2_inodes(dir, inode);
+
+	/* Handle O_TMPFILE corner case, it is allowed to link a O_TMPFILE. */
+	if (inode->i_nlink == 0)
+		ubifs_delete_orphan(c, inode->i_ino);
+
 	inc_nlink(inode);
 	ihold(inode);
-	inode->i_ctime = ubifs_current_time(inode);
+	inode->i_ctime = current_time(inode);
 	dir->i_size += sz_change;
 	dir_ui->ui_size = dir->i_size;
 	dir->i_mtime = dir->i_ctime = inode->i_ctime;
@@ -768,6 +785,8 @@ out_cancel:
 	dir->i_size -= sz_change;
 	dir_ui->ui_size = dir->i_size;
 	drop_nlink(inode);
+	if (inode->i_nlink == 0)
+		ubifs_add_orphan(c, inode->i_ino);
 	unlock_2_inodes(dir, inode);
 	ubifs_release_budget(c, &req);
 	iput(inode);
@@ -823,7 +842,7 @@ static int ubifs_unlink(struct inode *dir, struct dentry *dentry)
 	}
 
 	lock_2_inodes(dir, inode);
-	inode->i_ctime = ubifs_current_time(dir);
+	inode->i_ctime = current_time(dir);
 	drop_nlink(inode);
 	dir->i_size -= sz_change;
 	dir_ui->ui_size = dir->i_size;
@@ -927,7 +946,7 @@ static int ubifs_rmdir(struct inode *dir, struct dentry *dentry)
 	}
 
 	lock_2_inodes(dir, inode);
-	inode->i_ctime = ubifs_current_time(dir);
+	inode->i_ctime = current_time(dir);
 	clear_nlink(inode);
 	drop_nlink(dir);
 	dir->i_size -= sz_change;
@@ -1043,7 +1062,6 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry,
 	int sz_change;
 	int err, devlen = 0;
 	struct ubifs_budget_req req = { .new_ino = 1, .new_dent = 1,
-					.new_ino_d = ALIGN(devlen, 8),
 					.dirtied_ino = 1 };
 	struct fscrypt_name nm;
 
@@ -1061,6 +1079,7 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry,
 		devlen = ubifs_encode_dev(dev, rdev);
 	}
 
+	req.new_ino_d = ALIGN(devlen, 8);
 	err = ubifs_budget_space(c, &req);
 	if (err) {
 		kfree(dev);
@@ -1068,8 +1087,10 @@ static int ubifs_mknod(struct inode *dir, struct dentry *dentry,
 	}
 
 	err = fscrypt_setup_filename(dir, &dentry->d_name, 0, &nm);
-	if (err)
+	if (err) {
+		kfree(dev);
 		goto out_budg;
+	}
 
 	sz_change = CALC_DENT_SIZE(fname_len(&nm));
 
@@ -1316,9 +1337,6 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
 	unsigned int uninitialized_var(saved_nlink);
 	struct fscrypt_name old_nm, new_nm;
 
-	if (flags & ~RENAME_NOREPLACE)
-		return -EINVAL;
-
 	/*
 	 * Budget request settings: deletion direntry, new direntry, removing
 	 * the old inode, and changing old and new parent directory inodes.
@@ -1379,17 +1397,14 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 		dev = kmalloc(sizeof(union ubifs_dev_desc), GFP_NOFS);
 		if (!dev) {
-			ubifs_release_budget(c, &req);
-			ubifs_release_budget(c, &ino_req);
-			return -ENOMEM;
+			err = -ENOMEM;
+			goto out_release;
 		}
 
 		err = do_tmpfile(old_dir, old_dentry, S_IFCHR | WHITEOUT_MODE, &whiteout);
 		if (err) {
-			ubifs_release_budget(c, &req);
-			ubifs_release_budget(c, &ino_req);
 			kfree(dev);
-			return err;
+			goto out_release;
 		}
 
 		whiteout->i_state |= I_LINKABLE;
@@ -1405,7 +1420,7 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
 	 * Like most other Unix systems, set the @i_ctime for inodes on a
 	 * rename.
 	 */
-	time = ubifs_current_time(old_dir);
+	time = current_time(old_dir);
 	old_inode->i_ctime = time;
 
 	/* We must adjust parent link count when renaming directories */
@@ -1477,12 +1492,10 @@ static int do_rename(struct inode *old_dir, struct dentry *old_dentry,
 
 		err = ubifs_budget_space(c, &wht_req);
 		if (err) {
-			ubifs_release_budget(c, &req);
-			ubifs_release_budget(c, &ino_req);
 			kfree(whiteout_ui->data);
 			whiteout_ui->data_len = 0;
 			iput(whiteout);
-			return err;
+			goto out_release;
 		}
 
 		inc_nlink(whiteout);
@@ -1537,6 +1550,7 @@ out_cancel:
 		iput(whiteout);
 	}
 	unlock_4_inodes(old_dir, new_dir, new_inode, whiteout);
+out_release:
 	ubifs_release_budget(c, &ino_req);
 	ubifs_release_budget(c, &req);
 	fscrypt_free_filename(&old_nm);
@@ -1578,7 +1592,7 @@ static int ubifs_xrename(struct inode *old_dir, struct dentry *old_dentry,
 
 	lock_4_inodes(old_dir, new_dir, NULL, NULL);
 
-	time = ubifs_current_time(old_dir);
+	time = current_time(old_dir);
 	fst_inode->i_ctime = time;
 	snd_inode->i_ctime = time;
 	old_dir->i_mtime = old_dir->i_ctime = time;
@@ -1622,14 +1636,29 @@ static int ubifs_rename(struct inode *old_dir, struct dentry *old_dentry,
 	return do_rename(old_dir, old_dentry, new_dir, new_dentry, flags);
 }
 
-int ubifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		  struct kstat *stat)
+int ubifs_getattr(const struct path *path, struct kstat *stat,
+		  u32 request_mask, unsigned int flags)
 {
 	loff_t size;
-	struct inode *inode = d_inode(dentry);
+	struct inode *inode = d_inode(path->dentry);
 	struct ubifs_inode *ui = ubifs_inode(inode);
 
 	mutex_lock(&ui->ui_mutex);
+
+	if (ui->flags & UBIFS_APPEND_FL)
+		stat->attributes |= STATX_ATTR_APPEND;
+	if (ui->flags & UBIFS_COMPR_FL)
+		stat->attributes |= STATX_ATTR_COMPRESSED;
+	if (ui->flags & UBIFS_CRYPT_FL)
+		stat->attributes |= STATX_ATTR_ENCRYPTED;
+	if (ui->flags & UBIFS_IMMUTABLE_FL)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+
+	stat->attributes_mask |= (STATX_ATTR_APPEND |
+				STATX_ATTR_COMPRESSED |
+				STATX_ATTR_ENCRYPTED |
+				STATX_ATTR_IMMUTABLE);
+
 	generic_fillattr(inode, stat);
 	stat->blksize = UBIFS_BLOCK_SIZE;
 	stat->size = ui->ui_size;
diff --git a/fs/ubifs/file.c b/fs/ubifs/file.c
index b0d783774c96..8cad0b19b404 100644
--- a/fs/ubifs/file.c
+++ b/fs/ubifs/file.c
@@ -735,6 +735,7 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu,
 	int err, page_idx, page_cnt, ret = 0, n = 0;
 	int allocate = bu->buf ? 0 : 1;
 	loff_t isize;
+	gfp_t ra_gfp_mask = readahead_gfp_mask(mapping) & ~__GFP_FS;
 
 	err = ubifs_tnc_get_bu_keys(c, bu);
 	if (err)
@@ -796,8 +797,7 @@ static int ubifs_do_bulk_read(struct ubifs_info *c, struct bu_info *bu,
 
 		if (page_offset > end_index)
 			break;
-		page = find_or_create_page(mapping, page_offset,
-					   GFP_NOFS | __GFP_COLD);
+		page = find_or_create_page(mapping, page_offset, ra_gfp_mask);
 		if (!page)
 			break;
 		if (!PageUptodate(page))
@@ -1196,7 +1196,7 @@ static int do_truncation(struct ubifs_info *c, struct inode *inode,
 	mutex_lock(&ui->ui_mutex);
 	ui->ui_size = inode->i_size;
 	/* Truncation changes inode [mc]time */
-	inode->i_mtime = inode->i_ctime = ubifs_current_time(inode);
+	inode->i_mtime = inode->i_ctime = current_time(inode);
 	/* Other attributes may be changed at the same time as well */
 	do_attr_changes(inode, attr);
 	err = ubifs_jnl_truncate(c, inode, old_size, new_size);
@@ -1243,7 +1243,7 @@ static int do_setattr(struct ubifs_info *c, struct inode *inode,
 	mutex_lock(&ui->ui_mutex);
 	if (attr->ia_valid & ATTR_SIZE) {
 		/* Truncation changes inode [mc]time */
-		inode->i_mtime = inode->i_ctime = ubifs_current_time(inode);
+		inode->i_mtime = inode->i_ctime = current_time(inode);
 		/* 'truncate_setsize()' changed @i_size, update @ui_size */
 		ui->ui_size = inode->i_size;
 	}
@@ -1284,6 +1284,14 @@ int ubifs_setattr(struct dentry *dentry, struct iattr *attr)
 	if (err)
 		return err;
 
+	if (ubifs_crypt_is_encrypted(inode) && (attr->ia_valid & ATTR_SIZE)) {
+		err = fscrypt_get_encryption_info(inode);
+		if (err)
+			return err;
+		if (!fscrypt_has_encryption_key(inode))
+			return -ENOKEY;
+	}
+
 	if ((attr->ia_valid & ATTR_SIZE) && attr->ia_size < inode->i_size)
 		/* Truncation to a smaller size */
 		err = do_truncation(c, inode, attr);
@@ -1420,7 +1428,7 @@ int ubifs_update_time(struct inode *inode, struct timespec *time,
  */
 static int update_mctime(struct inode *inode)
 {
-	struct timespec now = ubifs_current_time(inode);
+	struct timespec now = current_time(inode);
 	struct ubifs_inode *ui = ubifs_inode(inode);
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
 
@@ -1434,7 +1442,7 @@ static int update_mctime(struct inode *inode)
 			return err;
 
 		mutex_lock(&ui->ui_mutex);
-		inode->i_mtime = inode->i_ctime = ubifs_current_time(inode);
+		inode->i_mtime = inode->i_ctime = current_time(inode);
 		release = ui->dirty;
 		mark_inode_dirty_sync(inode);
 		mutex_unlock(&ui->ui_mutex);
@@ -1506,13 +1514,12 @@ static int ubifs_releasepage(struct page *page, gfp_t unused_gfp_flags)
  * mmap()d file has taken write protection fault and is being made writable.
  * UBIFS must ensure page is budgeted for.
  */
-static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma,
-				 struct vm_fault *vmf)
+static int ubifs_vm_page_mkwrite(struct vm_fault *vmf)
 {
 	struct page *page = vmf->page;
-	struct inode *inode = file_inode(vma->vm_file);
+	struct inode *inode = file_inode(vmf->vma->vm_file);
 	struct ubifs_info *c = inode->i_sb->s_fs_info;
-	struct timespec now = ubifs_current_time(inode);
+	struct timespec now = current_time(inode);
 	struct ubifs_budget_req req = { .new_page = 1 };
 	int err, update_time;
 
@@ -1580,7 +1587,7 @@ static int ubifs_vm_page_mkwrite(struct vm_area_struct *vma,
 		struct ubifs_inode *ui = ubifs_inode(inode);
 
 		mutex_lock(&ui->ui_mutex);
-		inode->i_mtime = inode->i_ctime = ubifs_current_time(inode);
+		inode->i_mtime = inode->i_ctime = current_time(inode);
 		release = ui->dirty;
 		mark_inode_dirty_sync(inode);
 		mutex_unlock(&ui->ui_mutex);
@@ -1608,15 +1615,6 @@ static const struct vm_operations_struct ubifs_file_vm_ops = {
 static int ubifs_file_mmap(struct file *file, struct vm_area_struct *vma)
 {
 	int err;
-	struct inode *inode = file->f_mapping->host;
-
-	if (ubifs_crypt_is_encrypted(inode)) {
-		err = fscrypt_get_encryption_info(inode);
-		if (err)
-			return -EACCES;
-		if (!fscrypt_has_encryption_key(inode))
-			return -ENOKEY;
-	}
 
 	err = generic_file_mmap(file, vma);
 	if (err)
@@ -1699,12 +1697,6 @@ static const char *ubifs_get_link(struct dentry *dentry,
 
 	pstr.name[pstr.len] = '\0';
 
-	// XXX this probably won't happen anymore...
-	if (pstr.name[0] == '\0') {
-		fscrypt_fname_free_buffer(&pstr);
-		return ERR_PTR(-ENOENT);
-	}
-
 	set_delayed_call(done, kfree_link, pstr.name);
 	return pstr.name;
 }
diff --git a/fs/ubifs/ioctl.c b/fs/ubifs/ioctl.c
index da519ba205f6..fdc311246807 100644
--- a/fs/ubifs/ioctl.c
+++ b/fs/ubifs/ioctl.c
@@ -53,7 +53,7 @@ void ubifs_set_inode_flags(struct inode *inode)
  * ioctl2ubifs - convert ioctl inode flags to UBIFS inode flags.
  * @ioctl_flags: flags to convert
  *
- * This function convert ioctl flags (@FS_COMPR_FL, etc) to UBIFS inode flags
+ * This function converts ioctl flags (@FS_COMPR_FL, etc) to UBIFS inode flags
  * (@UBIFS_COMPR_FL, etc).
  */
 static int ioctl2ubifs(int ioctl_flags)
@@ -78,8 +78,8 @@ static int ioctl2ubifs(int ioctl_flags)
  * ubifs2ioctl - convert UBIFS inode flags to ioctl inode flags.
  * @ubifs_flags: flags to convert
  *
- * This function convert UBIFS (@UBIFS_COMPR_FL, etc) to ioctl flags
- * (@FS_COMPR_FL, etc).
+ * This function converts UBIFS inode flags (@UBIFS_COMPR_FL, etc) to ioctl
+ * flags (@FS_COMPR_FL, etc).
  */
 static int ubifs2ioctl(int ubifs_flags)
 {
@@ -126,7 +126,7 @@ static int setflags(struct inode *inode, int flags)
 
 	ui->flags = ioctl2ubifs(flags);
 	ubifs_set_inode_flags(inode);
-	inode->i_ctime = ubifs_current_time(inode);
+	inode->i_ctime = current_time(inode);
 	release = ui->dirty;
 	mark_inode_dirty_sync(inode);
 	mutex_unlock(&ui->ui_mutex);
diff --git a/fs/ubifs/journal.c b/fs/ubifs/journal.c
index 294519b98874..04c4ec6483e5 100644
--- a/fs/ubifs/journal.c
+++ b/fs/ubifs/journal.c
@@ -549,8 +549,6 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 	struct ubifs_ino_node *ino;
 	union ubifs_key dent_key, ino_key;
 
-	//dbg_jnl("ino %lu, dent '%.*s', data len %d in dir ino %lu",
-	//	inode->i_ino, nm->len, nm->name, ui->data_len, dir->i_ino);
 	ubifs_assert(mutex_is_locked(&host_ui->ui_mutex));
 
 	dlen = UBIFS_DENT_NODE_SZ + fname_len(nm) + 1;
@@ -574,7 +572,7 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 	/* Make sure to also account for extended attributes */
 	len += host_ui->data_len;
 
-	dent = kmalloc(len, GFP_NOFS);
+	dent = kzalloc(len, GFP_NOFS);
 	if (!dent)
 		return -ENOMEM;
 
@@ -585,7 +583,10 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 
 	if (!xent) {
 		dent->ch.node_type = UBIFS_DENT_NODE;
-		dent_key_init(c, &dent_key, dir->i_ino, nm);
+		if (nm->hash)
+			dent_key_init_hash(c, &dent_key, dir->i_ino, nm->hash);
+		else
+			dent_key_init(c, &dent_key, dir->i_ino, nm);
 	} else {
 		dent->ch.node_type = UBIFS_XENT_NODE;
 		xent_key_init(c, &dent_key, dir->i_ino, nm);
@@ -629,7 +630,10 @@ int ubifs_jnl_update(struct ubifs_info *c, const struct inode *dir,
 	kfree(dent);
 
 	if (deletion) {
-		err = ubifs_tnc_remove_nm(c, &dent_key, nm);
+		if (nm->hash)
+			err = ubifs_tnc_remove_dh(c, &dent_key, nm->minor_hash);
+		else
+			err = ubifs_tnc_remove_nm(c, &dent_key, nm);
 		if (err)
 			goto out_ro;
 		err = ubifs_add_dirt(c, lnum, dlen);
@@ -950,9 +954,6 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir,
 	int twoparents = (fst_dir != snd_dir);
 	void *p;
 
-	//dbg_jnl("dent '%pd' in dir ino %lu between dent '%pd' in dir ino %lu",
-	//	fst_dentry, fst_dir->i_ino, snd_dentry, snd_dir->i_ino);
-
 	ubifs_assert(ubifs_inode(fst_dir)->data_len == 0);
 	ubifs_assert(ubifs_inode(snd_dir)->data_len == 0);
 	ubifs_assert(mutex_is_locked(&ubifs_inode(fst_dir)->ui_mutex));
@@ -967,7 +968,7 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir,
 	if (twoparents)
 		len += plen;
 
-	dent1 = kmalloc(len, GFP_NOFS);
+	dent1 = kzalloc(len, GFP_NOFS);
 	if (!dent1)
 		return -ENOMEM;
 
@@ -984,6 +985,7 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir,
 	dent1->nlen = cpu_to_le16(fname_len(snd_nm));
 	memcpy(dent1->name, fname_name(snd_nm), fname_len(snd_nm));
 	dent1->name[fname_len(snd_nm)] = '\0';
+	set_dent_cookie(c, dent1);
 	zero_dent_node_unused(dent1);
 	ubifs_prep_grp_node(c, dent1, dlen1, 0);
 
@@ -996,6 +998,7 @@ int ubifs_jnl_xrename(struct ubifs_info *c, const struct inode *fst_dir,
 	dent2->nlen = cpu_to_le16(fname_len(fst_nm));
 	memcpy(dent2->name, fname_name(fst_nm), fname_len(fst_nm));
 	dent2->name[fname_len(fst_nm)] = '\0';
+	set_dent_cookie(c, dent2);
 	zero_dent_node_unused(dent2);
 	ubifs_prep_grp_node(c, dent2, dlen2, 0);
 
@@ -1094,8 +1097,6 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 	int move = (old_dir != new_dir);
 	struct ubifs_inode *uninitialized_var(new_ui);
 
-	//dbg_jnl("dent '%pd' in dir ino %lu to dent '%pd' in dir ino %lu",
-	//	old_dentry, old_dir->i_ino, new_dentry, new_dir->i_ino);
 	ubifs_assert(ubifs_inode(old_dir)->data_len == 0);
 	ubifs_assert(ubifs_inode(new_dir)->data_len == 0);
 	ubifs_assert(mutex_is_locked(&ubifs_inode(old_dir)->ui_mutex));
@@ -1117,7 +1118,7 @@ int ubifs_jnl_rename(struct ubifs_info *c, const struct inode *old_dir,
 	len = aligned_dlen1 + aligned_dlen2 + ALIGN(ilen, 8) + ALIGN(plen, 8);
 	if (move)
 		len += plen;
-	dent = kmalloc(len, GFP_NOFS);
+	dent = kzalloc(len, GFP_NOFS);
 	if (!dent)
 		return -ENOMEM;
 
@@ -1298,7 +1299,9 @@ static int truncate_data_node(const struct ubifs_info *c, const struct inode *in
 			goto out;
 	}
 
-	if (compr_type != UBIFS_COMPR_NONE) {
+	if (compr_type == UBIFS_COMPR_NONE) {
+		out_len = *new_len;
+	} else {
 		err = ubifs_decompress(c, &dn->data, dlen, buf, &out_len, compr_type);
 		if (err)
 			goto out;
@@ -1485,9 +1488,6 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host,
 	int sync = IS_DIRSYNC(host);
 	struct ubifs_inode *host_ui = ubifs_inode(host);
 
-	//dbg_jnl("host %lu, xattr ino %lu, name '%s', data len %d",
-	//	host->i_ino, inode->i_ino, nm->name,
-	//	ubifs_inode(inode)->data_len);
 	ubifs_assert(inode->i_nlink == 0);
 	ubifs_assert(mutex_is_locked(&host_ui->ui_mutex));
 
@@ -1500,7 +1500,7 @@ int ubifs_jnl_delete_xattr(struct ubifs_info *c, const struct inode *host,
 	hlen = host_ui->data_len + UBIFS_INO_NODE_SZ;
 	len = aligned_xlen + UBIFS_INO_NODE_SZ + ALIGN(hlen, 8);
 
-	xent = kmalloc(len, GFP_NOFS);
+	xent = kzalloc(len, GFP_NOFS);
 	if (!xent)
 		return -ENOMEM;
 
@@ -1607,7 +1607,7 @@ int ubifs_jnl_change_xattr(struct ubifs_info *c, const struct inode *inode,
 	aligned_len1 = ALIGN(len1, 8);
 	aligned_len = aligned_len1 + ALIGN(len2, 8);
 
-	ino = kmalloc(aligned_len, GFP_NOFS);
+	ino = kzalloc(aligned_len, GFP_NOFS);
 	if (!ino)
 		return -ENOMEM;
 
diff --git a/fs/ubifs/key.h b/fs/ubifs/key.h
index 7547be512db2..b1f7c0caa3ac 100644
--- a/fs/ubifs/key.h
+++ b/fs/ubifs/key.h
@@ -162,6 +162,7 @@ static inline void dent_key_init(const struct ubifs_info *c,
 	uint32_t hash = c->key_hash(fname_name(nm), fname_len(nm));
 
 	ubifs_assert(!(hash & ~UBIFS_S_KEY_HASH_MASK));
+	ubifs_assert(!nm->hash && !nm->minor_hash);
 	key->u32[0] = inum;
 	key->u32[1] = hash | (UBIFS_DENT_KEY << UBIFS_S_KEY_HASH_BITS);
 }
diff --git a/fs/ubifs/misc.h b/fs/ubifs/misc.h
index 8ece6ca58c0b..caf83d68fb38 100644
--- a/fs/ubifs/misc.h
+++ b/fs/ubifs/misc.h
@@ -225,16 +225,6 @@ static inline void *ubifs_idx_key(const struct ubifs_info *c,
 }
 
 /**
- * ubifs_current_time - round current time to time granularity.
- * @inode: inode
- */
-static inline struct timespec ubifs_current_time(struct inode *inode)
-{
-	return (inode->i_sb->s_time_gran < NSEC_PER_SEC) ?
-		current_fs_time(inode->i_sb) : CURRENT_TIME_SEC;
-}
-
-/**
  * ubifs_tnc_lookup - look up a file-system node.
  * @c: UBIFS file-system description object
  * @key: node key to lookup
diff --git a/fs/ubifs/recovery.c b/fs/ubifs/recovery.c
index 586d59347fff..3af4472061cc 100644
--- a/fs/ubifs/recovery.c
+++ b/fs/ubifs/recovery.c
@@ -442,7 +442,6 @@ static void clean_buf(const struct ubifs_info *c, void **buf, int lnum,
 {
 	int empty_offs, pad_len;
 
-	lnum = lnum;
 	dbg_rcvry("cleaning corruption at %d:%d", lnum, *offs);
 
 	ubifs_assert(!(*offs & 7));
diff --git a/fs/ubifs/sb.c b/fs/ubifs/sb.c
index 7f1ead29e727..8c25081a5109 100644
--- a/fs/ubifs/sb.c
+++ b/fs/ubifs/sb.c
@@ -84,6 +84,8 @@ static int create_default_filesystem(struct ubifs_info *c)
 	int min_leb_cnt = UBIFS_MIN_LEB_CNT;
 	long long tmp64, main_bytes;
 	__le64 tmp_le64;
+	__le32 tmp_le32;
+	struct timespec ts;
 
 	/* Some functions called from here depend on the @c->key_len filed */
 	c->key_len = UBIFS_SK_LEN;
@@ -298,13 +300,17 @@ static int create_default_filesystem(struct ubifs_info *c)
 	ino->ch.node_type = UBIFS_INO_NODE;
 	ino->creat_sqnum = cpu_to_le64(++c->max_sqnum);
 	ino->nlink = cpu_to_le32(2);
-	tmp_le64 = cpu_to_le64(CURRENT_TIME_SEC.tv_sec);
+
+	ktime_get_real_ts(&ts);
+	ts = timespec_trunc(ts, DEFAULT_TIME_GRAN);
+	tmp_le64 = cpu_to_le64(ts.tv_sec);
 	ino->atime_sec   = tmp_le64;
 	ino->ctime_sec   = tmp_le64;
 	ino->mtime_sec   = tmp_le64;
-	ino->atime_nsec  = 0;
-	ino->ctime_nsec  = 0;
-	ino->mtime_nsec  = 0;
+	tmp_le32 = cpu_to_le32(ts.tv_nsec);
+	ino->atime_nsec  = tmp_le32;
+	ino->ctime_nsec  = tmp_le32;
+	ino->mtime_nsec  = tmp_le32;
 	ino->mode = cpu_to_le32(S_IFDIR | S_IRUGO | S_IWUSR | S_IXUGO);
 	ino->size = cpu_to_le64(UBIFS_INO_NODE_SZ);
 
diff --git a/fs/ubifs/super.c b/fs/ubifs/super.c
index e08aa04fc835..bffadbb67e47 100644
--- a/fs/ubifs/super.c
+++ b/fs/ubifs/super.c
@@ -45,7 +45,7 @@
 #define UBIFS_KMALLOC_OK (128*1024)
 
 /* Slab cache for UBIFS inodes */
-struct kmem_cache *ubifs_inode_slab;
+static struct kmem_cache *ubifs_inode_slab;
 
 /* UBIFS TNC shrinker description */
 static struct shrinker ubifs_shrinker_info = {
@@ -446,6 +446,8 @@ static int ubifs_show_options(struct seq_file *s, struct dentry *root)
 			   ubifs_compr_name(c->mount_opts.compr_type));
 	}
 
+	seq_printf(s, ",ubi=%d,vol=%d", c->vi.ubi_num, c->vi.vol_id);
+
 	return 0;
 }
 
@@ -931,6 +933,7 @@ enum {
 	Opt_chk_data_crc,
 	Opt_no_chk_data_crc,
 	Opt_override_compr,
+	Opt_ignore,
 	Opt_err,
 };
 
@@ -942,6 +945,8 @@ static const match_table_t tokens = {
 	{Opt_chk_data_crc, "chk_data_crc"},
 	{Opt_no_chk_data_crc, "no_chk_data_crc"},
 	{Opt_override_compr, "compr=%s"},
+	{Opt_ignore, "ubi=%s"},
+	{Opt_ignore, "vol=%s"},
 	{Opt_err, NULL},
 };
 
@@ -1042,6 +1047,8 @@ static int ubifs_parse_options(struct ubifs_info *c, char *options,
 			c->default_compr = c->mount_opts.compr_type;
 			break;
 		}
+		case Opt_ignore:
+			break;
 		default:
 		{
 			unsigned long flag;
@@ -1827,7 +1834,6 @@ static void ubifs_put_super(struct super_block *sb)
 	}
 
 	ubifs_umount(c);
-	bdi_destroy(&c->bdi);
 	ubi_close_volume(c->ubi);
 	mutex_unlock(&c->umount_mutex);
 }
@@ -1870,8 +1876,10 @@ static int ubifs_remount_fs(struct super_block *sb, int *flags, char *data)
 		bu_init(c);
 	else {
 		dbg_gen("disable bulk-read");
+		mutex_lock(&c->bu_mutex);
 		kfree(c->bu.buf);
 		c->bu.buf = NULL;
+		mutex_unlock(&c->bu_mutex);
 	}
 
 	ubifs_assert(c->lst.taken_empty_lebs > 0);
@@ -2000,7 +2008,7 @@ static struct ubifs_info *alloc_ubifs_info(struct ubi_volume_desc *ubi)
 }
 
 #ifndef CONFIG_UBIFS_FS_ENCRYPTION
-struct fscrypt_operations ubifs_crypt_operations = {
+const struct fscrypt_operations ubifs_crypt_operations = {
 	.is_encrypted		= __ubifs_crypt_is_encrypted,
 };
 #endif
@@ -2019,29 +2027,25 @@ static int ubifs_fill_super(struct super_block *sb, void *data, int silent)
 		goto out;
 	}
 
+	err = ubifs_parse_options(c, data, 0);
+	if (err)
+		goto out_close;
+
 	/*
 	 * UBIFS provides 'backing_dev_info' in order to disable read-ahead. For
 	 * UBIFS, I/O is not deferred, it is done immediately in readpage,
 	 * which means the user would have to wait not just for their own I/O
 	 * but the read-ahead I/O as well i.e. completely pointless.
 	 *
-	 * Read-ahead will be disabled because @c->bdi.ra_pages is 0.
+	 * Read-ahead will be disabled because @sb->s_bdi->ra_pages is 0. Also
+	 * @sb->s_bdi->capabilities are initialized to 0 so there won't be any
+	 * writeback happening.
 	 */
-	c->bdi.name = "ubifs",
-	c->bdi.capabilities = 0;
-	err  = bdi_init(&c->bdi);
+	err = super_setup_bdi_name(sb, "ubifs_%d_%d", c->vi.ubi_num,
+				   c->vi.vol_id);
 	if (err)
 		goto out_close;
-	err = bdi_register(&c->bdi, NULL, "ubifs_%d_%d",
-			   c->vi.ubi_num, c->vi.vol_id);
-	if (err)
-		goto out_bdi;
-
-	err = ubifs_parse_options(c, data, 0);
-	if (err)
-		goto out_bdi;
 
-	sb->s_bdi = &c->bdi;
 	sb->s_fs_info = c;
 	sb->s_magic = UBIFS_SUPER_MAGIC;
 	sb->s_blocksize = UBIFS_BLOCK_SIZE;
@@ -2080,8 +2084,6 @@ out_umount:
 	ubifs_umount(c);
 out_unlock:
 	mutex_unlock(&c->umount_mutex);
-out_bdi:
-	bdi_destroy(&c->bdi);
 out_close:
 	ubi_close_volume(c->ubi);
 out:
diff --git a/fs/ubifs/tnc.c b/fs/ubifs/tnc.c
index 709aa098dd46..0a213dcba2a1 100644
--- a/fs/ubifs/tnc.c
+++ b/fs/ubifs/tnc.c
@@ -1812,7 +1812,7 @@ static int do_lookup_nm(struct ubifs_info *c, const union ubifs_key *key,
 	int found, n, err;
 	struct ubifs_znode *znode;
 
-	//dbg_tnck(key, "name '%.*s' key ", nm->len, nm->name);
+	dbg_tnck(key, "key ");
 	mutex_lock(&c->tnc_mutex);
 	found = ubifs_lookup_level0(c, key, &znode, &n);
 	if (!found) {
@@ -1880,48 +1880,65 @@ int ubifs_tnc_lookup_nm(struct ubifs_info *c, const union ubifs_key *key,
 	return do_lookup_nm(c, key, node, nm);
 }
 
-static int do_lookup_dh(struct ubifs_info *c, const union ubifs_key *key,
-			struct ubifs_dent_node *dent, uint32_t cookie)
+static int search_dh_cookie(struct ubifs_info *c, const union ubifs_key *key,
+			    struct ubifs_dent_node *dent, uint32_t cookie,
+			    struct ubifs_znode **zn, int *n)
 {
-	int n, err, type = key_type(c, key);
-	struct ubifs_znode *znode;
+	int err;
+	struct ubifs_znode *znode = *zn;
 	struct ubifs_zbranch *zbr;
-	union ubifs_key *dkey, start_key;
-
-	ubifs_assert(is_hash_key(c, key));
-
-	lowest_dent_key(c, &start_key, key_inum(c, key));
-
-	mutex_lock(&c->tnc_mutex);
-	err = ubifs_lookup_level0(c, &start_key, &znode, &n);
-	if (unlikely(err < 0))
-		goto out_unlock;
+	union ubifs_key *dkey;
 
 	for (;;) {
 		if (!err) {
-			err = tnc_next(c, &znode, &n);
+			err = tnc_next(c, &znode, n);
 			if (err)
-				goto out_unlock;
+				goto out;
 		}
 
-		zbr = &znode->zbranch[n];
+		zbr = &znode->zbranch[*n];
 		dkey = &zbr->key;
 
 		if (key_inum(c, dkey) != key_inum(c, key) ||
-		    key_type(c, dkey) != type) {
+		    key_type(c, dkey) != key_type(c, key)) {
 			err = -ENOENT;
-			goto out_unlock;
+			goto out;
 		}
 
 		err = tnc_read_hashed_node(c, zbr, dent);
 		if (err)
-			goto out_unlock;
+			goto out;
 
 		if (key_hash(c, key) == key_hash(c, dkey) &&
-		    le32_to_cpu(dent->cookie) == cookie)
-			goto out_unlock;
+		    le32_to_cpu(dent->cookie) == cookie) {
+			*zn = znode;
+			goto out;
+		}
 	}
 
+out:
+
+	return err;
+}
+
+static int do_lookup_dh(struct ubifs_info *c, const union ubifs_key *key,
+			struct ubifs_dent_node *dent, uint32_t cookie)
+{
+	int n, err;
+	struct ubifs_znode *znode;
+	union ubifs_key start_key;
+
+	ubifs_assert(is_hash_key(c, key));
+
+	lowest_dent_key(c, &start_key, key_inum(c, key));
+
+	mutex_lock(&c->tnc_mutex);
+	err = ubifs_lookup_level0(c, &start_key, &znode, &n);
+	if (unlikely(err < 0))
+		goto out_unlock;
+
+	err = search_dh_cookie(c, key, dent, cookie, &znode, &n);
+
 out_unlock:
 	mutex_unlock(&c->tnc_mutex);
 	return err;
@@ -2393,8 +2410,7 @@ int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key,
 	struct ubifs_znode *znode;
 
 	mutex_lock(&c->tnc_mutex);
-	//dbg_tnck(key, "LEB %d:%d, name '%.*s', key ",
-	//	 lnum, offs, nm->len, nm->name);
+	dbg_tnck(key, "LEB %d:%d, key ", lnum, offs);
 	found = lookup_level0_dirty(c, key, &znode, &n);
 	if (found < 0) {
 		err = found;
@@ -2628,7 +2644,7 @@ int ubifs_tnc_remove_nm(struct ubifs_info *c, const union ubifs_key *key,
 	struct ubifs_znode *znode;
 
 	mutex_lock(&c->tnc_mutex);
-	//dbg_tnck(key, "%.*s, key ", nm->len, nm->name);
+	dbg_tnck(key, "key ");
 	err = lookup_level0_dirty(c, key, &znode, &n);
 	if (err < 0)
 		goto out_unlock;
@@ -2663,6 +2679,74 @@ out_unlock:
 }
 
 /**
+ * ubifs_tnc_remove_dh - remove an index entry for a "double hashed" node.
+ * @c: UBIFS file-system description object
+ * @key: key of node
+ * @cookie: node cookie for collision resolution
+ *
+ * Returns %0 on success or negative error code on failure.
+ */
+int ubifs_tnc_remove_dh(struct ubifs_info *c, const union ubifs_key *key,
+			uint32_t cookie)
+{
+	int n, err;
+	struct ubifs_znode *znode;
+	struct ubifs_dent_node *dent;
+	struct ubifs_zbranch *zbr;
+
+	if (!c->double_hash)
+		return -EOPNOTSUPP;
+
+	mutex_lock(&c->tnc_mutex);
+	err = lookup_level0_dirty(c, key, &znode, &n);
+	if (err <= 0)
+		goto out_unlock;
+
+	zbr = &znode->zbranch[n];
+	dent = kmalloc(UBIFS_MAX_DENT_NODE_SZ, GFP_NOFS);
+	if (!dent) {
+		err = -ENOMEM;
+		goto out_unlock;
+	}
+
+	err = tnc_read_hashed_node(c, zbr, dent);
+	if (err)
+		goto out_free;
+
+	/* If the cookie does not match, we're facing a hash collision. */
+	if (le32_to_cpu(dent->cookie) != cookie) {
+		union ubifs_key start_key;
+
+		lowest_dent_key(c, &start_key, key_inum(c, key));
+
+		err = ubifs_lookup_level0(c, &start_key, &znode, &n);
+		if (unlikely(err < 0))
+			goto out_free;
+
+		err = search_dh_cookie(c, key, dent, cookie, &znode, &n);
+		if (err)
+			goto out_free;
+	}
+
+	if (znode->cnext || !ubifs_zn_dirty(znode)) {
+		znode = dirty_cow_bottom_up(c, znode);
+		if (IS_ERR(znode)) {
+			err = PTR_ERR(znode);
+			goto out_free;
+		}
+	}
+	err = tnc_delete(c, znode, n);
+
+out_free:
+	kfree(dent);
+out_unlock:
+	if (!err)
+		err = dbg_check_tnc(c, 0);
+	mutex_unlock(&c->tnc_mutex);
+	return err;
+}
+
+/**
  * key_in_range - determine if a key falls within a range of keys.
  * @c: UBIFS file-system description object
  * @key: key to check
@@ -2802,6 +2886,8 @@ int ubifs_tnc_remove_ino(struct ubifs_info *c, ino_t inum)
 		dbg_tnc("xent '%s', ino %lu", xent->name,
 			(unsigned long)xattr_inum);
 
+		ubifs_evict_xattr_inode(c, xattr_inum);
+
 		fname_name(&nm) = xent->name;
 		fname_len(&nm) = le16_to_cpu(xent->nlen);
 		err = ubifs_tnc_remove_nm(c, &key1, &nm);
@@ -2863,7 +2949,7 @@ struct ubifs_dent_node *ubifs_tnc_next_ent(struct ubifs_info *c,
 	struct ubifs_zbranch *zbr;
 	union ubifs_key *dkey;
 
-	//dbg_tnck(key, "%s ", nm->name ? (char *)nm->name : "(lowest)");
+	dbg_tnck(key, "key ");
 	ubifs_assert(is_hash_key(c, key));
 
 	mutex_lock(&c->tnc_mutex);
diff --git a/fs/ubifs/tnc_commit.c b/fs/ubifs/tnc_commit.c
index 51157da3f76e..aa31f60220ef 100644
--- a/fs/ubifs/tnc_commit.c
+++ b/fs/ubifs/tnc_commit.c
@@ -57,6 +57,8 @@ static int make_idx_node(struct ubifs_info *c, struct ubifs_idx_node *idx,
 			ubifs_dump_znode(c, znode);
 			if (zbr->znode)
 				ubifs_dump_znode(c, zbr->znode);
+
+			return -EINVAL;
 		}
 	}
 	ubifs_prepare_node(c, idx, len, 0);
@@ -859,6 +861,8 @@ static int write_index(struct ubifs_info *c)
 				ubifs_dump_znode(c, znode);
 				if (zbr->znode)
 					ubifs_dump_znode(c, zbr->znode);
+
+				return -EINVAL;
 			}
 		}
 		len = ubifs_idx_node_sz(c, znode->child_cnt);
diff --git a/fs/ubifs/ubifs.h b/fs/ubifs/ubifs.h
index ca72382ce6cc..cd43651f1731 100644
--- a/fs/ubifs/ubifs.h
+++ b/fs/ubifs/ubifs.h
@@ -38,7 +38,11 @@
 #include <linux/backing-dev.h>
 #include <linux/security.h>
 #include <linux/xattr.h>
-#include <linux/fscrypto.h>
+#ifdef CONFIG_UBIFS_FS_ENCRYPTION
+#include <linux/fscrypt_supp.h>
+#else
+#include <linux/fscrypt_notsupp.h>
+#endif
 #include <linux/random.h>
 #include "ubifs-media.h"
 
@@ -968,7 +972,6 @@ struct ubifs_debug_info;
  * struct ubifs_info - UBIFS file-system description data structure
  * (per-superblock).
  * @vfs_sb: VFS @struct super_block object
- * @bdi: backing device info object to make VFS happy and disable read-ahead
  *
  * @highest_inum: highest used inode number
  * @max_sqnum: current global sequence number
@@ -1216,7 +1219,6 @@ struct ubifs_debug_info;
  */
 struct ubifs_info {
 	struct super_block *vfs_sb;
-	struct backing_dev_info bdi;
 
 	ino_t highest_inum;
 	unsigned long long max_sqnum;
@@ -1449,7 +1451,6 @@ struct ubifs_info {
 extern struct list_head ubifs_infos;
 extern spinlock_t ubifs_infos_lock;
 extern atomic_long_t ubifs_clean_zn_cnt;
-extern struct kmem_cache *ubifs_inode_slab;
 extern const struct super_operations ubifs_super_operations;
 extern const struct address_space_operations ubifs_file_address_operations;
 extern const struct file_operations ubifs_file_operations;
@@ -1457,7 +1458,6 @@ extern const struct inode_operations ubifs_file_inode_operations;
 extern const struct file_operations ubifs_dir_operations;
 extern const struct inode_operations ubifs_dir_inode_operations;
 extern const struct inode_operations ubifs_symlink_inode_operations;
-extern struct backing_dev_info ubifs_backing_dev_info;
 extern struct ubifs_compressor *ubifs_compressors[UBIFS_COMPR_TYPES_CNT];
 
 /* io.c */
@@ -1589,6 +1589,8 @@ int ubifs_tnc_add_nm(struct ubifs_info *c, const union ubifs_key *key,
 int ubifs_tnc_remove(struct ubifs_info *c, const union ubifs_key *key);
 int ubifs_tnc_remove_nm(struct ubifs_info *c, const union ubifs_key *key,
 			const struct fscrypt_name *nm);
+int ubifs_tnc_remove_dh(struct ubifs_info *c, const union ubifs_key *key,
+			uint32_t cookie);
 int ubifs_tnc_remove_range(struct ubifs_info *c, union ubifs_key *from_key,
 			   union ubifs_key *to_key);
 int ubifs_tnc_remove_ino(struct ubifs_info *c, ino_t inum);
@@ -1745,19 +1747,30 @@ int ubifs_update_time(struct inode *inode, struct timespec *time, int flags);
 /* dir.c */
 struct inode *ubifs_new_inode(struct ubifs_info *c, struct inode *dir,
 			      umode_t mode);
-int ubifs_getattr(struct vfsmount *mnt, struct dentry *dentry,
-		  struct kstat *stat);
+int ubifs_getattr(const struct path *path, struct kstat *stat,
+		  u32 request_mask, unsigned int flags);
 int ubifs_check_dir_empty(struct inode *dir);
 
 /* xattr.c */
 extern const struct xattr_handler *ubifs_xattr_handlers[];
 ssize_t ubifs_listxattr(struct dentry *dentry, char *buffer, size_t size);
-int ubifs_init_security(struct inode *dentry, struct inode *inode,
-			const struct qstr *qstr);
 int ubifs_xattr_set(struct inode *host, const char *name, const void *value,
-		    size_t size, int flags);
+		    size_t size, int flags, bool check_lock);
 ssize_t ubifs_xattr_get(struct inode *host, const char *name, void *buf,
 			size_t size);
+void ubifs_evict_xattr_inode(struct ubifs_info *c, ino_t xattr_inum);
+
+#ifdef CONFIG_UBIFS_FS_SECURITY
+extern int ubifs_init_security(struct inode *dentry, struct inode *inode,
+			const struct qstr *qstr);
+#else
+static inline int ubifs_init_security(struct inode *dentry,
+			struct inode *inode, const struct qstr *qstr)
+{
+	return 0;
+}
+#endif
+
 
 /* super.c */
 struct inode *ubifs_iget(struct super_block *sb, unsigned long inum);
@@ -1797,28 +1810,6 @@ int ubifs_decompress(const struct ubifs_info *c, const void *buf, int len,
 #include "key.h"
 
 #ifndef CONFIG_UBIFS_FS_ENCRYPTION
-#define fscrypt_set_d_op(i)
-#define fscrypt_get_ctx                 fscrypt_notsupp_get_ctx
-#define fscrypt_release_ctx             fscrypt_notsupp_release_ctx
-#define fscrypt_encrypt_page            fscrypt_notsupp_encrypt_page
-#define fscrypt_decrypt_page            fscrypt_notsupp_decrypt_page
-#define fscrypt_decrypt_bio_pages       fscrypt_notsupp_decrypt_bio_pages
-#define fscrypt_pullback_bio_page       fscrypt_notsupp_pullback_bio_page
-#define fscrypt_restore_control_page    fscrypt_notsupp_restore_control_page
-#define fscrypt_zeroout_range           fscrypt_notsupp_zeroout_range
-#define fscrypt_ioctl_set_policy	fscrypt_notsupp_ioctl_set_policy
-#define fscrypt_ioctl_get_policy	fscrypt_notsupp_ioctl_get_policy
-#define fscrypt_has_permitted_context   fscrypt_notsupp_has_permitted_context
-#define fscrypt_inherit_context         fscrypt_notsupp_inherit_context
-#define fscrypt_get_encryption_info     fscrypt_notsupp_get_encryption_info
-#define fscrypt_put_encryption_info     fscrypt_notsupp_put_encryption_info
-#define fscrypt_setup_filename          fscrypt_notsupp_setup_filename
-#define fscrypt_free_filename           fscrypt_notsupp_free_filename
-#define fscrypt_fname_encrypted_size    fscrypt_notsupp_fname_encrypted_size
-#define fscrypt_fname_alloc_buffer      fscrypt_notsupp_fname_alloc_buffer
-#define fscrypt_fname_free_buffer       fscrypt_notsupp_fname_free_buffer
-#define fscrypt_fname_disk_to_usr       fscrypt_notsupp_fname_disk_to_usr
-#define fscrypt_fname_usr_to_disk       fscrypt_notsupp_fname_usr_to_disk
 static inline int ubifs_encrypt(const struct inode *inode,
 				struct ubifs_data_node *dn,
 				unsigned int in_len, unsigned int *out_len,
@@ -1842,7 +1833,7 @@ int ubifs_decrypt(const struct inode *inode, struct ubifs_data_node *dn,
 		  unsigned int *out_len, int block);
 #endif
 
-extern struct fscrypt_operations ubifs_crypt_operations;
+extern const struct fscrypt_operations ubifs_crypt_operations;
 
 static inline bool __ubifs_crypt_is_encrypted(struct inode *inode)
 {
diff --git a/fs/ubifs/xattr.c b/fs/ubifs/xattr.c
index efe00fcb8b75..c13eae819cbc 100644
--- a/fs/ubifs/xattr.c
+++ b/fs/ubifs/xattr.c
@@ -152,7 +152,7 @@ static int create_xattr(struct ubifs_info *c, struct inode *host,
 	ui->data_len = size;
 
 	mutex_lock(&host_ui->ui_mutex);
-	host->i_ctime = ubifs_current_time(host);
+	host->i_ctime = current_time(host);
 	host_ui->xattr_cnt += 1;
 	host_ui->xattr_size += CALC_DENT_SIZE(fname_len(nm));
 	host_ui->xattr_size += CALC_XATTR_BYTES(size);
@@ -234,7 +234,7 @@ static int change_xattr(struct ubifs_info *c, struct inode *host,
 	mutex_unlock(&ui->ui_mutex);
 
 	mutex_lock(&host_ui->ui_mutex);
-	host->i_ctime = ubifs_current_time(host);
+	host->i_ctime = current_time(host);
 	host_ui->xattr_size -= CALC_XATTR_BYTES(old_size);
 	host_ui->xattr_size += CALC_XATTR_BYTES(size);
 
@@ -280,7 +280,7 @@ static struct inode *iget_xattr(struct ubifs_info *c, ino_t inum)
 }
 
 int ubifs_xattr_set(struct inode *host, const char *name, const void *value,
-		    size_t size, int flags)
+		    size_t size, int flags, bool check_lock)
 {
 	struct inode *inode;
 	struct ubifs_info *c = host->i_sb->s_fs_info;
@@ -289,12 +289,7 @@ int ubifs_xattr_set(struct inode *host, const char *name, const void *value,
 	union ubifs_key key;
 	int err;
 
-	/*
-	 * Creating an encryption context is done unlocked since we
-	 * operate on a new inode which is not visible to other users
-	 * at this point.
-	 */
-	if (strcmp(name, UBIFS_XATTR_NAME_ENCRYPTION_CONTEXT) != 0)
+	if (check_lock)
 		ubifs_assert(inode_is_locked(host));
 
 	if (size > UBIFS_MAX_INO_DATA)
@@ -488,7 +483,7 @@ static int remove_xattr(struct ubifs_info *c, struct inode *host,
 		return err;
 
 	mutex_lock(&host_ui->ui_mutex);
-	host->i_ctime = ubifs_current_time(host);
+	host->i_ctime = current_time(host);
 	host_ui->xattr_cnt -= 1;
 	host_ui->xattr_size -= CALC_DENT_SIZE(fname_len(nm));
 	host_ui->xattr_size -= CALC_XATTR_BYTES(ui->data_len);
@@ -513,6 +508,28 @@ out_cancel:
 	return err;
 }
 
+/**
+ * ubifs_evict_xattr_inode - Evict an xattr inode.
+ * @c: UBIFS file-system description object
+ * @xattr_inum: xattr inode number
+ *
+ * When an inode that hosts xattrs is being removed we have to make sure
+ * that cached inodes of the xattrs also get removed from the inode cache
+ * otherwise we'd waste memory. This function looks up an inode from the
+ * inode cache and clears the link counter such that iput() will evict
+ * the inode.
+ */
+void ubifs_evict_xattr_inode(struct ubifs_info *c, ino_t xattr_inum)
+{
+	struct inode *inode;
+
+	inode = ilookup(c->vfs_sb, xattr_inum);
+	if (inode) {
+		clear_nlink(inode);
+		iput(inode);
+	}
+}
+
 static int ubifs_xattr_remove(struct inode *host, const char *name)
 {
 	struct inode *inode;
@@ -559,6 +576,7 @@ out_free:
 	return err;
 }
 
+#ifdef CONFIG_UBIFS_FS_SECURITY
 static int init_xattrs(struct inode *inode, const struct xattr *xattr_array,
 		      void *fs_info)
 {
@@ -575,8 +593,12 @@ static int init_xattrs(struct inode *inode, const struct xattr *xattr_array,
 		}
 		strcpy(name, XATTR_SECURITY_PREFIX);
 		strcpy(name + XATTR_SECURITY_PREFIX_LEN, xattr->name);
+		/*
+		 * creating a new inode without holding the inode rwsem,
+		 * no need to check whether inode is locked.
+		 */
 		err = ubifs_xattr_set(inode, name, xattr->value,
-				      xattr->value_len, 0);
+				      xattr->value_len, 0, false);
 		kfree(name);
 		if (err < 0)
 			break;
@@ -599,6 +621,7 @@ int ubifs_init_security(struct inode *dentry, struct inode *inode,
 	}
 	return err;
 }
+#endif
 
 static int xattr_get(const struct xattr_handler *handler,
 			   struct dentry *dentry, struct inode *inode,
@@ -622,7 +645,7 @@ static int xattr_set(const struct xattr_handler *handler,
 	name = xattr_full_name(handler, name);
 
 	if (value)
-		return ubifs_xattr_set(inode, name, value, size, flags);
+		return ubifs_xattr_set(inode, name, value, size, flags, true);
 	else
 		return ubifs_xattr_remove(inode, name);
 }
@@ -639,15 +662,19 @@ static const struct xattr_handler ubifs_trusted_xattr_handler = {
 	.set = xattr_set,
 };
 
+#ifdef CONFIG_UBIFS_FS_SECURITY
 static const struct xattr_handler ubifs_security_xattr_handler = {
 	.prefix = XATTR_SECURITY_PREFIX,
 	.get = xattr_get,
 	.set = xattr_set,
 };
+#endif
 
 const struct xattr_handler *ubifs_xattr_handlers[] = {
 	&ubifs_user_xattr_handler,
 	&ubifs_trusted_xattr_handler,
+#ifdef CONFIG_UBIFS_FS_SECURITY
 	&ubifs_security_xattr_handler,
+#endif
 	NULL
 };
diff --git a/fs/udf/ecma_167.h b/fs/udf/ecma_167.h
index 4792b771aa80..9f24bd1a9f44 100644
--- a/fs/udf/ecma_167.h
+++ b/fs/udf/ecma_167.h
@@ -41,7 +41,7 @@
 struct charspec {
 	uint8_t		charSetType;
 	uint8_t		charSetInfo[63];
-} __attribute__ ((packed));
+} __packed;
 
 /* Character Set Type (ECMA 167r3 1/7.2.1.1) */
 #define CHARSPEC_TYPE_CS0		0x00	/* (1/7.2.2) */
@@ -68,7 +68,7 @@ struct timestamp {
 	uint8_t		centiseconds;
 	uint8_t		hundredsOfMicroseconds;
 	uint8_t		microseconds;
-} __attribute__ ((packed));
+} __packed;
 
 /* Type and Time Zone (ECMA 167r3 1/7.3.1) */
 #define TIMESTAMP_TYPE_MASK		0xF000
@@ -82,7 +82,7 @@ struct regid {
 	uint8_t		flags;
 	uint8_t		ident[23];
 	uint8_t		identSuffix[8];
-} __attribute__ ((packed));
+} __packed;
 
 /* Flags (ECMA 167r3 1/7.4.1) */
 #define ENTITYID_FLAGS_DIRTY		0x00
@@ -95,7 +95,7 @@ struct volStructDesc {
 	uint8_t		stdIdent[VSD_STD_ID_LEN];
 	uint8_t		structVersion;
 	uint8_t		structData[2041];
-} __attribute__ ((packed));
+} __packed;
 
 /* Standard Identifier (EMCA 167r2 2/9.1.2) */
 #define VSD_STD_ID_NSR02		"NSR02"	/* (3/9.1) */
@@ -114,7 +114,7 @@ struct beginningExtendedAreaDesc {
 	uint8_t		stdIdent[VSD_STD_ID_LEN];
 	uint8_t		structVersion;
 	uint8_t		structData[2041];
-} __attribute__ ((packed));
+} __packed;
 
 /* Terminating Extended Area Descriptor (ECMA 167r3 2/9.3) */
 struct terminatingExtendedAreaDesc {
@@ -122,7 +122,7 @@ struct terminatingExtendedAreaDesc {
 	uint8_t		stdIdent[VSD_STD_ID_LEN];
 	uint8_t		structVersion;
 	uint8_t		structData[2041];
-} __attribute__ ((packed));
+} __packed;
 
 /* Boot Descriptor (ECMA 167r3 2/9.4) */
 struct bootDesc {
@@ -140,7 +140,7 @@ struct bootDesc {
 	__le16			flags;
 	uint8_t			reserved2[32];
 	uint8_t			bootUse[1906];
-} __attribute__ ((packed));
+} __packed;
 
 /* Flags (ECMA 167r3 2/9.4.12) */
 #define BOOT_FLAGS_ERASE		0x01
@@ -149,7 +149,7 @@ struct bootDesc {
 struct extent_ad {
 	__le32		extLength;
 	__le32		extLocation;
-} __attribute__ ((packed));
+} __packed;
 
 struct kernel_extent_ad {
 	uint32_t	extLength;
@@ -166,7 +166,7 @@ struct tag {
 	__le16		descCRC;
 	__le16		descCRCLength;
 	__le32		tagLocation;
-} __attribute__ ((packed));
+} __packed;
 
 /* Tag Identifier (ECMA 167r3 3/7.2.1) */
 #define TAG_IDENT_PVD			0x0001
@@ -186,7 +186,7 @@ struct NSRDesc {
 	uint8_t		structVersion;
 	uint8_t		reserved;
 	uint8_t		structData[2040];
-} __attribute__ ((packed));
+} __packed;
 
 /* Primary Volume Descriptor (ECMA 167r3 3/10.1) */
 struct primaryVolDesc {
@@ -212,7 +212,7 @@ struct primaryVolDesc {
 	__le32			predecessorVolDescSeqLocation;
 	__le16			flags;
 	uint8_t			reserved[22];
-} __attribute__ ((packed));
+} __packed;
 
 /* Flags (ECMA 167r3 3/10.1.21) */
 #define PVD_FLAGS_VSID_COMMON		0x0001
@@ -223,7 +223,7 @@ struct anchorVolDescPtr {
 	struct extent_ad	mainVolDescSeqExt;
 	struct extent_ad	reserveVolDescSeqExt;
 	uint8_t	 		reserved[480];
-} __attribute__ ((packed));
+} __packed;
 
 /* Volume Descriptor Pointer (ECMA 167r3 3/10.3) */
 struct volDescPtr {
@@ -231,7 +231,7 @@ struct volDescPtr {
 	__le32			volDescSeqNum;
 	struct extent_ad	nextVolDescSeqExt;
 	uint8_t			reserved[484];
-} __attribute__ ((packed));
+} __packed;
 
 /* Implementation Use Volume Descriptor (ECMA 167r3 3/10.4) */
 struct impUseVolDesc {
@@ -239,7 +239,7 @@ struct impUseVolDesc {
 	__le32		volDescSeqNum;
 	struct regid	impIdent;
 	uint8_t		impUse[460];
-} __attribute__ ((packed));
+} __packed;
 
 /* Partition Descriptor (ECMA 167r3 3/10.5) */
 struct partitionDesc {
@@ -255,7 +255,7 @@ struct partitionDesc {
 	struct regid impIdent;
 	uint8_t impUse[128];
 	uint8_t reserved[156];
-} __attribute__ ((packed));
+} __packed;
 
 /* Partition Flags (ECMA 167r3 3/10.5.3) */
 #define PD_PARTITION_FLAGS_ALLOC	0x0001
@@ -291,14 +291,14 @@ struct logicalVolDesc {
 	uint8_t			impUse[128];
 	struct extent_ad	integritySeqExt;
 	uint8_t			partitionMaps[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Generic Partition Map (ECMA 167r3 3/10.7.1) */
 struct genericPartitionMap {
 	uint8_t		partitionMapType;
 	uint8_t		partitionMapLength;
 	uint8_t		partitionMapping[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Partition Map Type (ECMA 167r3 3/10.7.1.1) */
 #define GP_PARTITION_MAP_TYPE_UNDEF	0x00
@@ -311,14 +311,14 @@ struct genericPartitionMap1 {
 	uint8_t		partitionMapLength;
 	__le16		volSeqNum;
 	__le16		partitionNum;
-} __attribute__ ((packed));
+} __packed;
 
 /* Type 2 Partition Map (ECMA 167r3 3/10.7.3) */
 struct genericPartitionMap2 {
 	uint8_t		partitionMapType;
 	uint8_t		partitionMapLength;
 	uint8_t		partitionIdent[62];
-} __attribute__ ((packed));
+} __packed;
 
 /* Unallocated Space Descriptor (ECMA 167r3 3/10.8) */
 struct unallocSpaceDesc {
@@ -326,13 +326,13 @@ struct unallocSpaceDesc {
 	__le32			volDescSeqNum;
 	__le32			numAllocDescs;
 	struct extent_ad	allocDescs[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Terminating Descriptor (ECMA 167r3 3/10.9) */
 struct terminatingDesc {
 	struct tag	descTag;
 	uint8_t		reserved[496];
-} __attribute__ ((packed));
+} __packed;
 
 /* Logical Volume Integrity Descriptor (ECMA 167r3 3/10.10) */
 struct logicalVolIntegrityDesc {
@@ -346,7 +346,7 @@ struct logicalVolIntegrityDesc {
 	__le32			freeSpaceTable[0];
 	__le32			sizeTable[0];
 	uint8_t			impUse[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Integrity Type (ECMA 167r3 3/10.10.3) */
 #define LVID_INTEGRITY_TYPE_OPEN	0x00000000
@@ -356,7 +356,7 @@ struct logicalVolIntegrityDesc {
 struct lb_addr {
 	__le32		logicalBlockNum;
 	__le16	 	partitionReferenceNum;
-} __attribute__ ((packed));
+} __packed;
 
 /* ... and its in-core analog */
 struct kernel_lb_addr {
@@ -368,14 +368,14 @@ struct kernel_lb_addr {
 struct short_ad {
         __le32		extLength;
         __le32		extPosition;
-} __attribute__ ((packed));
+} __packed;
 
 /* Long Allocation Descriptor (ECMA 167r3 4/14.14.2) */
 struct long_ad {
 	__le32		extLength;
 	struct lb_addr	extLocation;
 	uint8_t		impUse[6];
-} __attribute__ ((packed));
+} __packed;
 
 struct kernel_long_ad {
 	uint32_t		extLength;
@@ -389,7 +389,7 @@ struct ext_ad {
 	__le32		recordedLength;
 	__le32		informationLength;
 	struct lb_addr	extLocation;
-} __attribute__ ((packed));
+} __packed;
 
 struct kernel_ext_ad {
 	uint32_t		extLength;
@@ -434,7 +434,7 @@ struct fileSetDesc {
 	struct long_ad		nextExt;
 	struct long_ad		streamDirectoryICB;
 	uint8_t			reserved[32];
-} __attribute__ ((packed));
+} __packed;
 
 /* Partition Header Descriptor (ECMA 167r3 4/14.3) */
 struct partitionHeaderDesc {
@@ -444,7 +444,7 @@ struct partitionHeaderDesc {
 	struct short_ad	freedSpaceTable;
 	struct short_ad	freedSpaceBitmap;
 	uint8_t		reserved[88];
-} __attribute__ ((packed));
+} __packed;
 
 /* File Identifier Descriptor (ECMA 167r3 4/14.4) */
 struct fileIdentDesc {
@@ -457,7 +457,7 @@ struct fileIdentDesc {
 	uint8_t		impUse[0];
 	uint8_t		fileIdent[0];
 	uint8_t		padding[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* File Characteristics (ECMA 167r3 4/14.4.3) */
 #define FID_FILE_CHAR_HIDDEN		0x01
@@ -471,7 +471,7 @@ struct allocExtDesc {
 	struct tag	descTag;
 	__le32		previousAllocExtLocation;
 	__le32		lengthAllocDescs;
-} __attribute__ ((packed));
+} __packed;
 
 /* ICB Tag (ECMA 167r3 4/14.6) */
 struct icbtag {
@@ -483,7 +483,7 @@ struct icbtag {
 	uint8_t		fileType;
 	struct lb_addr	parentICBLocation;
 	__le16		flags;
-} __attribute__ ((packed));
+} __packed;
 
 /* Strategy Type (ECMA 167r3 4/14.6.2) */
 #define ICBTAG_STRATEGY_TYPE_UNDEF	0x0000
@@ -531,13 +531,13 @@ struct indirectEntry {
 	struct tag	descTag;
 	struct icbtag	icbTag;
 	struct long_ad	indirectICB;
-} __attribute__ ((packed));
+} __packed;
 
 /* Terminal Entry (ECMA 167r3 4/14.8) */
 struct terminalEntry {
 	struct tag	descTag;
 	struct icbtag	icbTag;
-} __attribute__ ((packed));
+} __packed;
 
 /* File Entry (ECMA 167r3 4/14.9) */
 struct fileEntry {
@@ -563,7 +563,7 @@ struct fileEntry {
 	__le32			lengthAllocDescs;
 	uint8_t			extendedAttr[0];
 	uint8_t			allocDescs[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Permissions (ECMA 167r3 4/14.9.5) */
 #define FE_PERM_O_EXEC			0x00000001U
@@ -607,7 +607,7 @@ struct extendedAttrHeaderDesc {
 	struct tag	descTag;
 	__le32		impAttrLocation;
 	__le32		appAttrLocation;
-} __attribute__ ((packed));
+} __packed;
 
 /* Generic Format (ECMA 167r3 4/14.10.2) */
 struct genericFormat {
@@ -616,7 +616,7 @@ struct genericFormat {
 	uint8_t		reserved[3];
 	__le32		attrLength;
 	uint8_t		attrData[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Character Set Information (ECMA 167r3 4/14.10.3) */
 struct charSetInfo {
@@ -627,7 +627,7 @@ struct charSetInfo {
 	__le32		escapeSeqLength;
 	uint8_t		charSetType;
 	uint8_t		escapeSeq[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Alternate Permissions (ECMA 167r3 4/14.10.4) */
 struct altPerms {
@@ -638,7 +638,7 @@ struct altPerms {
 	__le16		ownerIdent;
 	__le16		groupIdent;
 	__le16		permission;
-} __attribute__ ((packed));
+} __packed;
 
 /* File Times Extended Attribute (ECMA 167r3 4/14.10.5) */
 struct fileTimesExtAttr {
@@ -649,7 +649,7 @@ struct fileTimesExtAttr {
 	__le32		dataLength;
 	__le32		fileTimeExistence;
 	uint8_t		fileTimes;
-} __attribute__ ((packed));
+} __packed;
 
 /* FileTimeExistence (ECMA 167r3 4/14.10.5.6) */
 #define FTE_CREATION			0x00000001
@@ -666,7 +666,7 @@ struct infoTimesExtAttr {
 	__le32		dataLength;
 	__le32		infoTimeExistence;
 	uint8_t		infoTimes[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Device Specification (ECMA 167r3 4/14.10.7) */
 struct deviceSpec {
@@ -678,7 +678,7 @@ struct deviceSpec {
 	__le32		majorDeviceIdent;
 	__le32		minorDeviceIdent;
 	uint8_t		impUse[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Implementation Use Extended Attr (ECMA 167r3 4/14.10.8) */
 struct impUseExtAttr {
@@ -689,7 +689,7 @@ struct impUseExtAttr {
 	__le32		impUseLength;
 	struct regid	impIdent;
 	uint8_t		impUse[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Application Use Extended Attribute (ECMA 167r3 4/14.10.9) */
 struct appUseExtAttr {
@@ -700,7 +700,7 @@ struct appUseExtAttr {
 	__le32		appUseLength;
 	struct regid	appIdent;
 	uint8_t		appUse[0];
-} __attribute__ ((packed));
+} __packed;
 
 #define EXTATTR_CHAR_SET		1
 #define EXTATTR_ALT_PERMS		3
@@ -716,7 +716,7 @@ struct unallocSpaceEntry {
 	struct icbtag	icbTag;
 	__le32		lengthAllocDescs;
 	uint8_t		allocDescs[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Space Bitmap Descriptor (ECMA 167r3 4/14.12) */
 struct spaceBitmapDesc {
@@ -724,7 +724,7 @@ struct spaceBitmapDesc {
 	__le32		numOfBits;
 	__le32		numOfBytes;
 	uint8_t		bitmap[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Partition Integrity Entry (ECMA 167r3 4/14.13) */
 struct partitionIntegrityEntry {
@@ -735,7 +735,7 @@ struct partitionIntegrityEntry {
 	uint8_t			reserved[175];
 	struct regid		impIdent;
 	uint8_t			impUse[256];
-} __attribute__ ((packed));
+} __packed;
 
 /* Short Allocation Descriptor (ECMA 167r3 4/14.14.1) */
 
@@ -753,7 +753,7 @@ struct partitionIntegrityEntry {
 struct logicalVolHeaderDesc {
 	__le64		uniqueID;
 	uint8_t		reserved[24];
-} __attribute__ ((packed));
+} __packed;
 
 /* Path Component (ECMA 167r3 4/14.16.1) */
 struct pathComponent {
@@ -761,7 +761,7 @@ struct pathComponent {
 	uint8_t		lengthComponentIdent;
 	__le16		componentFileVersionNum;
 	dstring		componentIdent[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* File Entry (ECMA 167r3 4/14.17) */
 struct extendedFileEntry {
@@ -791,6 +791,6 @@ struct extendedFileEntry {
 	__le32			lengthAllocDescs;
 	uint8_t			extendedAttr[0];
 	uint8_t			allocDescs[0];
-} __attribute__ ((packed));
+} __packed;
 
 #endif /* _ECMA_167_H */
diff --git a/fs/udf/file.c b/fs/udf/file.c
index dbcb3a4a0cb9..356c2bf148a5 100644
--- a/fs/udf/file.c
+++ b/fs/udf/file.c
@@ -43,13 +43,18 @@ static void __udf_adinicb_readpage(struct page *page)
 	struct inode *inode = page->mapping->host;
 	char *kaddr;
 	struct udf_inode_info *iinfo = UDF_I(inode);
-
-	kaddr = kmap(page);
-	memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, inode->i_size);
-	memset(kaddr + inode->i_size, 0, PAGE_SIZE - inode->i_size);
+	loff_t isize = i_size_read(inode);
+
+	/*
+	 * We have to be careful here as truncate can change i_size under us.
+	 * So just sample it once and use the same value everywhere.
+	 */
+	kaddr = kmap_atomic(page);
+	memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr, isize);
+	memset(kaddr + isize, 0, PAGE_SIZE - isize);
 	flush_dcache_page(page);
 	SetPageUptodate(page);
-	kunmap(page);
+	kunmap_atomic(kaddr);
 }
 
 static int udf_adinicb_readpage(struct file *file, struct page *page)
@@ -70,11 +75,12 @@ static int udf_adinicb_writepage(struct page *page,
 
 	BUG_ON(!PageLocked(page));
 
-	kaddr = kmap(page);
-	memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr, inode->i_size);
-	mark_inode_dirty(inode);
+	kaddr = kmap_atomic(page);
+	memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr,
+		i_size_read(inode));
 	SetPageUptodate(page);
-	kunmap(page);
+	kunmap_atomic(kaddr);
+	mark_inode_dirty(inode);
 	unlock_page(page);
 
 	return 0;
@@ -176,54 +182,46 @@ long udf_ioctl(struct file *filp, unsigned int cmd, unsigned long arg)
 {
 	struct inode *inode = file_inode(filp);
 	long old_block, new_block;
-	int result = -EINVAL;
+	int result;
 
 	if (inode_permission(inode, MAY_READ) != 0) {
 		udf_debug("no permission to access inode %lu\n", inode->i_ino);
-		result = -EPERM;
-		goto out;
+		return -EPERM;
 	}
 
-	if (!arg) {
+	if (!arg && ((cmd == UDF_GETVOLIDENT) || (cmd == UDF_GETEASIZE) ||
+		     (cmd == UDF_RELOCATE_BLOCKS) || (cmd == UDF_GETEABLOCK))) {
 		udf_debug("invalid argument to udf_ioctl\n");
-		result = -EINVAL;
-		goto out;
+		return -EINVAL;
 	}
 
 	switch (cmd) {
 	case UDF_GETVOLIDENT:
 		if (copy_to_user((char __user *)arg,
 				 UDF_SB(inode->i_sb)->s_volume_ident, 32))
-			result = -EFAULT;
-		else
-			result = 0;
-		goto out;
+			return -EFAULT;
+		return 0;
 	case UDF_RELOCATE_BLOCKS:
-		if (!capable(CAP_SYS_ADMIN)) {
-			result = -EPERM;
-			goto out;
-		}
-		if (get_user(old_block, (long __user *)arg)) {
-			result = -EFAULT;
-			goto out;
-		}
+		if (!capable(CAP_SYS_ADMIN))
+			return -EPERM;
+		if (get_user(old_block, (long __user *)arg))
+			return -EFAULT;
 		result = udf_relocate_blocks(inode->i_sb,
 						old_block, &new_block);
 		if (result == 0)
 			result = put_user(new_block, (long __user *)arg);
-		goto out;
+		return result;
 	case UDF_GETEASIZE:
-		result = put_user(UDF_I(inode)->i_lenEAttr, (int __user *)arg);
-		goto out;
+		return put_user(UDF_I(inode)->i_lenEAttr, (int __user *)arg);
 	case UDF_GETEABLOCK:
-		result = copy_to_user((char __user *)arg,
-				      UDF_I(inode)->i_ext.i_data,
-				      UDF_I(inode)->i_lenEAttr) ? -EFAULT : 0;
-		goto out;
+		return copy_to_user((char __user *)arg,
+				    UDF_I(inode)->i_ext.i_data,
+				    UDF_I(inode)->i_lenEAttr) ? -EFAULT : 0;
+	default:
+		return -ENOIOCTLCMD;
 	}
 
-out:
-	return result;
+	return 0;
 }
 
 static int udf_release_file(struct inode *inode, struct file *filp)
diff --git a/fs/udf/inode.c b/fs/udf/inode.c
index 0f3db71753aa..18fdb9d90812 100644
--- a/fs/udf/inode.c
+++ b/fs/udf/inode.c
@@ -43,10 +43,6 @@
 #include "udf_i.h"
 #include "udf_sb.h"
 
-MODULE_AUTHOR("Ben Fennema");
-MODULE_DESCRIPTION("Universal Disk Format Filesystem");
-MODULE_LICENSE("GPL");
-
 #define EXTENT_MERGE_SIZE 5
 
 static umode_t udf_convert_permissions(struct fileEntry *);
@@ -57,14 +53,12 @@ static sector_t inode_getblk(struct inode *, sector_t, int *, int *);
 static int8_t udf_insert_aext(struct inode *, struct extent_position,
 			      struct kernel_lb_addr, uint32_t);
 static void udf_split_extents(struct inode *, int *, int, int,
-			      struct kernel_long_ad[EXTENT_MERGE_SIZE], int *);
+			      struct kernel_long_ad *, int *);
 static void udf_prealloc_extents(struct inode *, int, int,
-				 struct kernel_long_ad[EXTENT_MERGE_SIZE], int *);
-static void udf_merge_extents(struct inode *,
-			      struct kernel_long_ad[EXTENT_MERGE_SIZE], int *);
-static void udf_update_extents(struct inode *,
-			       struct kernel_long_ad[EXTENT_MERGE_SIZE], int, int,
-			       struct extent_position *);
+				 struct kernel_long_ad *, int *);
+static void udf_merge_extents(struct inode *, struct kernel_long_ad *, int *);
+static void udf_update_extents(struct inode *, struct kernel_long_ad *, int,
+			       int, struct extent_position *);
 static int udf_get_block(struct inode *, sector_t, struct buffer_head *, int);
 
 static void __udf_clear_extent_cache(struct inode *inode)
@@ -111,7 +105,7 @@ static int udf_read_extent_cache(struct inode *inode, loff_t bcount,
 
 /* Add extent to extent cache */
 static void udf_update_extent_cache(struct inode *inode, loff_t estart,
-				    struct extent_position *pos, int next_epos)
+				    struct extent_position *pos)
 {
 	struct udf_inode_info *iinfo = UDF_I(inode);
 
@@ -120,19 +114,16 @@ static void udf_update_extent_cache(struct inode *inode, loff_t estart,
 	__udf_clear_extent_cache(inode);
 	if (pos->bh)
 		get_bh(pos->bh);
-	memcpy(&iinfo->cached_extent.epos, pos,
-	       sizeof(struct extent_position));
+	memcpy(&iinfo->cached_extent.epos, pos, sizeof(struct extent_position));
 	iinfo->cached_extent.lstart = estart;
-	if (next_epos)
-		switch (iinfo->i_alloc_type) {
-		case ICBTAG_FLAG_AD_SHORT:
-			iinfo->cached_extent.epos.offset -=
-			sizeof(struct short_ad);
-			break;
-		case ICBTAG_FLAG_AD_LONG:
-			iinfo->cached_extent.epos.offset -=
-			sizeof(struct long_ad);
-		}
+	switch (iinfo->i_alloc_type) {
+	case ICBTAG_FLAG_AD_SHORT:
+		iinfo->cached_extent.epos.offset -= sizeof(struct short_ad);
+		break;
+	case ICBTAG_FLAG_AD_LONG:
+		iinfo->cached_extent.epos.offset -= sizeof(struct long_ad);
+		break;
+	}
 	spin_unlock(&iinfo->i_extent_cache_lock);
 }
 
@@ -285,14 +276,14 @@ int udf_expand_file_adinicb(struct inode *inode)
 		return -ENOMEM;
 
 	if (!PageUptodate(page)) {
-		kaddr = kmap(page);
+		kaddr = kmap_atomic(page);
 		memset(kaddr + iinfo->i_lenAlloc, 0x00,
 		       PAGE_SIZE - iinfo->i_lenAlloc);
 		memcpy(kaddr, iinfo->i_ext.i_data + iinfo->i_lenEAttr,
 			iinfo->i_lenAlloc);
 		flush_dcache_page(page);
 		SetPageUptodate(page);
-		kunmap(page);
+		kunmap_atomic(kaddr);
 	}
 	down_write(&iinfo->i_data_sem);
 	memset(iinfo->i_ext.i_data + iinfo->i_lenEAttr, 0x00,
@@ -309,11 +300,11 @@ int udf_expand_file_adinicb(struct inode *inode)
 	if (err) {
 		/* Restore everything back so that we don't lose data... */
 		lock_page(page);
-		kaddr = kmap(page);
 		down_write(&iinfo->i_data_sem);
+		kaddr = kmap_atomic(page);
 		memcpy(iinfo->i_ext.i_data + iinfo->i_lenEAttr, kaddr,
 		       inode->i_size);
-		kunmap(page);
+		kunmap_atomic(kaddr);
 		unlock_page(page);
 		iinfo->i_alloc_type = ICBTAG_FLAG_AD_IN_ICB;
 		inode->i_data.a_ops = &udf_adinicb_aops;
@@ -747,11 +738,8 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 				 ~(inode->i_sb->s_blocksize - 1));
 			udf_write_aext(inode, &cur_epos, &eloc, elen, 1);
 		}
-		brelse(prev_epos.bh);
-		brelse(cur_epos.bh);
-		brelse(next_epos.bh);
 		newblock = udf_get_lb_pblock(inode->i_sb, &eloc, offset);
-		return newblock;
+		goto out_free;
 	}
 
 	/* Are we beyond EOF? */
@@ -774,11 +762,9 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 		/* Create extents for the hole between EOF and offset */
 		ret = udf_do_extend_file(inode, &prev_epos, laarr, offset);
 		if (ret < 0) {
-			brelse(prev_epos.bh);
-			brelse(cur_epos.bh);
-			brelse(next_epos.bh);
 			*err = ret;
-			return 0;
+			newblock = 0;
+			goto out_free;
 		}
 		c = 0;
 		offset = 0;
@@ -841,11 +827,9 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 				iinfo->i_location.partitionReferenceNum,
 				goal, err);
 		if (!newblocknum) {
-			brelse(prev_epos.bh);
-			brelse(cur_epos.bh);
-			brelse(next_epos.bh);
 			*err = -ENOSPC;
-			return 0;
+			newblock = 0;
+			goto out_free;
 		}
 		if (isBeyondEOF)
 			iinfo->i_lenExtents += inode->i_sb->s_blocksize;
@@ -857,14 +841,12 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 	 * block */
 	udf_split_extents(inode, &c, offset, newblocknum, laarr, &endnum);
 
-#ifdef UDF_PREALLOCATE
 	/* We preallocate blocks only for regular files. It also makes sense
 	 * for directories but there's a problem when to drop the
 	 * preallocation. We might use some delayed work for that but I feel
 	 * it's overengineering for a filesystem like UDF. */
 	if (S_ISREG(inode->i_mode))
 		udf_prealloc_extents(inode, c, lastblock, laarr, &endnum);
-#endif
 
 	/* merge any continuous blocks in laarr */
 	udf_merge_extents(inode, laarr, &endnum);
@@ -874,15 +856,11 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 	 * the new number of extents is less than the old number */
 	udf_update_extents(inode, laarr, startnum, endnum, &prev_epos);
 
-	brelse(prev_epos.bh);
-	brelse(cur_epos.bh);
-	brelse(next_epos.bh);
-
 	newblock = udf_get_pblock(inode->i_sb, newblocknum,
 				iinfo->i_location.partitionReferenceNum, 0);
 	if (!newblock) {
 		*err = -EIO;
-		return 0;
+		goto out_free;
 	}
 	*new = 1;
 	iinfo->i_next_alloc_block = block;
@@ -893,13 +871,15 @@ static sector_t inode_getblk(struct inode *inode, sector_t block,
 		udf_sync_inode(inode);
 	else
 		mark_inode_dirty(inode);
-
+out_free:
+	brelse(prev_epos.bh);
+	brelse(cur_epos.bh);
+	brelse(next_epos.bh);
 	return newblock;
 }
 
 static void udf_split_extents(struct inode *inode, int *c, int offset,
-			      int newblocknum,
-			      struct kernel_long_ad laarr[EXTENT_MERGE_SIZE],
+			      int newblocknum, struct kernel_long_ad *laarr,
 			      int *endnum)
 {
 	unsigned long blocksize = inode->i_sb->s_blocksize;
@@ -963,7 +943,7 @@ static void udf_split_extents(struct inode *inode, int *c, int offset,
 }
 
 static void udf_prealloc_extents(struct inode *inode, int c, int lastblock,
-				 struct kernel_long_ad laarr[EXTENT_MERGE_SIZE],
+				 struct kernel_long_ad *laarr,
 				 int *endnum)
 {
 	int start, length = 0, currlength = 0, i;
@@ -1058,8 +1038,7 @@ static void udf_prealloc_extents(struct inode *inode, int c, int lastblock,
 	}
 }
 
-static void udf_merge_extents(struct inode *inode,
-			      struct kernel_long_ad laarr[EXTENT_MERGE_SIZE],
+static void udf_merge_extents(struct inode *inode, struct kernel_long_ad *laarr,
 			      int *endnum)
 {
 	int i;
@@ -1158,8 +1137,7 @@ static void udf_merge_extents(struct inode *inode,
 	}
 }
 
-static void udf_update_extents(struct inode *inode,
-			       struct kernel_long_ad laarr[EXTENT_MERGE_SIZE],
+static void udf_update_extents(struct inode *inode, struct kernel_long_ad *laarr,
 			       int startnum, int endnum,
 			       struct extent_position *epos)
 {
@@ -1215,7 +1193,7 @@ int udf_setsize(struct inode *inode, loff_t newsize)
 {
 	int err;
 	struct udf_inode_info *iinfo;
-	int bsize = 1 << inode->i_blkbits;
+	int bsize = i_blocksize(inode);
 
 	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
 	      S_ISLNK(inode->i_mode)))
@@ -1244,8 +1222,8 @@ int udf_setsize(struct inode *inode, loff_t newsize)
 			return err;
 		}
 set_size:
-		truncate_setsize(inode, newsize);
 		up_write(&iinfo->i_data_sem);
+		truncate_setsize(inode, newsize);
 	} else {
 		if (iinfo->i_alloc_type == ICBTAG_FLAG_AD_IN_ICB) {
 			down_write(&iinfo->i_data_sem);
@@ -1262,9 +1240,9 @@ set_size:
 					  udf_get_block);
 		if (err)
 			return err;
+		truncate_setsize(inode, newsize);
 		down_write(&iinfo->i_data_sem);
 		udf_clear_extent_cache(inode);
-		truncate_setsize(inode, newsize);
 		udf_truncate_extents(inode);
 		up_write(&iinfo->i_data_sem);
 	}
@@ -1299,6 +1277,12 @@ static int udf_read_inode(struct inode *inode, bool hidden_inode)
 	int ret = -EIO;
 
 reread:
+	if (iloc->partitionReferenceNum >= sbi->s_partitions) {
+		udf_debug("partition reference: %d > logical volume partitions: %d\n",
+			  iloc->partitionReferenceNum, sbi->s_partitions);
+		return -EIO;
+	}
+
 	if (iloc->logicalBlockNum >=
 	    sbi->s_partmaps[iloc->partitionReferenceNum].s_partition_len) {
 		udf_debug("block=%d, partition=%d out of range\n",
@@ -1549,9 +1533,9 @@ reread:
 		break;
 	case ICBTAG_FILE_TYPE_SYMLINK:
 		inode->i_data.a_ops = &udf_symlink_aops;
-		inode->i_op = &page_symlink_inode_operations;
+		inode->i_op = &udf_symlink_inode_operations;
 		inode_nohighmem(inode);
-		inode->i_mode = S_IFLNK | S_IRWXUGO;
+		inode->i_mode = S_IFLNK | 0777;
 		break;
 	case ICBTAG_FILE_TYPE_MAIN:
 		udf_debug("METADATA FILE-----\n");
@@ -1607,9 +1591,9 @@ static umode_t udf_convert_permissions(struct fileEntry *fe)
 	permissions = le32_to_cpu(fe->permissions);
 	flags = le16_to_cpu(fe->icbTag.flags);
 
-	mode =	((permissions) & S_IRWXO) |
-		((permissions >> 2) & S_IRWXG) |
-		((permissions >> 4) & S_IRWXU) |
+	mode =	((permissions) & 0007) |
+		((permissions >> 2) & 0070) |
+		((permissions >> 4) & 0700) |
 		((flags & ICBTAG_FLAG_SETUID) ? S_ISUID : 0) |
 		((flags & ICBTAG_FLAG_SETGID) ? S_ISGID : 0) |
 		((flags & ICBTAG_FLAG_STICKY) ? S_ISVTX : 0);
@@ -1627,6 +1611,14 @@ static int udf_sync_inode(struct inode *inode)
 	return udf_update_inode(inode, 1);
 }
 
+static void udf_adjust_time(struct udf_inode_info *iinfo, struct timespec time)
+{
+	if (iinfo->i_crtime.tv_sec > time.tv_sec ||
+	    (iinfo->i_crtime.tv_sec == time.tv_sec &&
+	     iinfo->i_crtime.tv_nsec > time.tv_nsec))
+		iinfo->i_crtime = time;
+}
+
 static int udf_update_inode(struct inode *inode, int do_sync)
 {
 	struct buffer_head *bh = NULL;
@@ -1677,9 +1669,9 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 	else
 		fe->gid = cpu_to_le32(i_gid_read(inode));
 
-	udfperms = ((inode->i_mode & S_IRWXO)) |
-		   ((inode->i_mode & S_IRWXG) << 2) |
-		   ((inode->i_mode & S_IRWXU) << 4);
+	udfperms = ((inode->i_mode & 0007)) |
+		   ((inode->i_mode & 0070) << 2) |
+		   ((inode->i_mode & 0700) << 4);
 
 	udfperms |= (le32_to_cpu(fe->permissions) &
 		    (FE_PERM_O_DELETE | FE_PERM_O_CHATTR |
@@ -1753,20 +1745,9 @@ static int udf_update_inode(struct inode *inode, int do_sync)
 		efe->objectSize = cpu_to_le64(inode->i_size);
 		efe->logicalBlocksRecorded = cpu_to_le64(lb_recorded);
 
-		if (iinfo->i_crtime.tv_sec > inode->i_atime.tv_sec ||
-		    (iinfo->i_crtime.tv_sec == inode->i_atime.tv_sec &&
-		     iinfo->i_crtime.tv_nsec > inode->i_atime.tv_nsec))
-			iinfo->i_crtime = inode->i_atime;
-
-		if (iinfo->i_crtime.tv_sec > inode->i_mtime.tv_sec ||
-		    (iinfo->i_crtime.tv_sec == inode->i_mtime.tv_sec &&
-		     iinfo->i_crtime.tv_nsec > inode->i_mtime.tv_nsec))
-			iinfo->i_crtime = inode->i_mtime;
-
-		if (iinfo->i_crtime.tv_sec > inode->i_ctime.tv_sec ||
-		    (iinfo->i_crtime.tv_sec == inode->i_ctime.tv_sec &&
-		     iinfo->i_crtime.tv_nsec > inode->i_ctime.tv_nsec))
-			iinfo->i_crtime = inode->i_ctime;
+		udf_adjust_time(iinfo, inode->i_atime);
+		udf_adjust_time(iinfo, inode->i_mtime);
+		udf_adjust_time(iinfo, inode->i_ctime);
 
 		udf_time_to_disk_stamp(&efe->accessTime, inode->i_atime);
 		udf_time_to_disk_stamp(&efe->modificationTime, inode->i_mtime);
@@ -2286,8 +2267,7 @@ int8_t inode_bmap(struct inode *inode, sector_t block,
 		  uint32_t *elen, sector_t *offset)
 {
 	unsigned char blocksize_bits = inode->i_sb->s_blocksize_bits;
-	loff_t lbcount = 0, bcount =
-	    (loff_t) block << blocksize_bits;
+	loff_t lbcount = 0, bcount = (loff_t) block << blocksize_bits;
 	int8_t etype;
 	struct udf_inode_info *iinfo;
 
@@ -2308,7 +2288,7 @@ int8_t inode_bmap(struct inode *inode, sector_t block,
 		lbcount += *elen;
 	} while (lbcount <= bcount);
 	/* update extent cache */
-	udf_update_extent_cache(inode, lbcount - *elen, pos, 1);
+	udf_update_extent_cache(inode, lbcount - *elen, pos);
 	*offset = (bcount + *elen - lbcount) >> blocksize_bits;
 
 	return etype;
diff --git a/fs/udf/lowlevel.c b/fs/udf/lowlevel.c
index 6ad5a453af97..5c7ec121990d 100644
--- a/fs/udf/lowlevel.c
+++ b/fs/udf/lowlevel.c
@@ -58,7 +58,7 @@ unsigned long udf_get_last_block(struct super_block *sb)
 	 */
 	if (ioctl_by_bdev(bdev, CDROM_LAST_WRITTEN, (unsigned long) &lblock) ||
 	    lblock == 0)
-		lblock = bdev->bd_inode->i_size >> sb->s_blocksize_bits;
+		lblock = i_size_read(bdev->bd_inode) >> sb->s_blocksize_bits;
 
 	if (lblock)
 		return lblock - 1;
diff --git a/fs/udf/misc.c b/fs/udf/misc.c
index 71d1c25f360d..3949c4bec3a3 100644
--- a/fs/udf/misc.c
+++ b/fs/udf/misc.c
@@ -141,8 +141,6 @@ struct genericFormat *udf_add_extendedattr(struct inode *inode, uint32_t size,
 		iinfo->i_lenEAttr += size;
 		return (struct genericFormat *)&ea[offset];
 	}
-	if (loc & 0x02)
-		;
 
 	return NULL;
 }
diff --git a/fs/udf/namei.c b/fs/udf/namei.c
index 2d65e280748b..385ee89d5824 100644
--- a/fs/udf/namei.c
+++ b/fs/udf/namei.c
@@ -906,7 +906,7 @@ out:
 static int udf_symlink(struct inode *dir, struct dentry *dentry,
 		       const char *symname)
 {
-	struct inode *inode = udf_new_inode(dir, S_IFLNK | S_IRWXUGO);
+	struct inode *inode = udf_new_inode(dir, S_IFLNK | 0777);
 	struct pathComponent *pc;
 	const char *compstart;
 	struct extent_position epos = {};
@@ -931,7 +931,7 @@ static int udf_symlink(struct inode *dir, struct dentry *dentry,
 	}
 
 	inode->i_data.a_ops = &udf_symlink_aops;
-	inode->i_op = &page_symlink_inode_operations;
+	inode->i_op = &udf_symlink_inode_operations;
 	inode_nohighmem(inode);
 
 	if (iinfo->i_alloc_type != ICBTAG_FLAG_AD_IN_ICB) {
diff --git a/fs/udf/osta_udf.h b/fs/udf/osta_udf.h
index fbff74654df2..a4da59e38b7f 100644
--- a/fs/udf/osta_udf.h
+++ b/fs/udf/osta_udf.h
@@ -70,17 +70,17 @@ struct UDFIdentSuffix {
 	uint8_t		OSClass;
 	uint8_t		OSIdentifier;
 	uint8_t		reserved[4];
-} __attribute__ ((packed));
+} __packed;
 
 struct impIdentSuffix {
 	uint8_t		OSClass;
 	uint8_t		OSIdentifier;
 	uint8_t		reserved[6];
-} __attribute__ ((packed));
+} __packed;
 
 struct appIdentSuffix {
 	uint8_t		impUse[8];
-} __attribute__ ((packed));
+} __packed;
 
 /* Logical Volume Integrity Descriptor (UDF 2.50 2.2.6) */
 /* Implementation Use (UDF 2.50 2.2.6.4) */
@@ -92,7 +92,7 @@ struct logicalVolIntegrityDescImpUse {
 	__le16		minUDFWriteRev;
 	__le16		maxUDFWriteRev;
 	uint8_t		impUse[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Implementation Use Volume Descriptor (UDF 2.50 2.2.7) */
 /* Implementation Use (UDF 2.50 2.2.7.2) */
@@ -104,7 +104,7 @@ struct impUseVolDescImpUse {
 	dstring		LVInfo3[36];
 	struct regid	impIdent;
 	uint8_t		impUse[128];
-} __attribute__ ((packed));
+} __packed;
 
 struct udfPartitionMap2 {
 	uint8_t		partitionMapType;
@@ -113,7 +113,7 @@ struct udfPartitionMap2 {
 	struct regid	partIdent;
 	__le16		volSeqNum;
 	__le16		partitionNum;
-} __attribute__ ((packed));
+} __packed;
 
 /* Virtual Partition Map (UDF 2.50 2.2.8) */
 struct virtualPartitionMap {
@@ -124,7 +124,7 @@ struct virtualPartitionMap {
 	__le16		volSeqNum;
 	__le16		partitionNum;
 	uint8_t		reserved2[24];
-} __attribute__ ((packed));
+} __packed;
 
 /* Sparable Partition Map (UDF 2.50 2.2.9) */
 struct sparablePartitionMap {
@@ -139,7 +139,7 @@ struct sparablePartitionMap {
 	uint8_t reserved2[1];
 	__le32 sizeSparingTable;
 	__le32 locSparingTable[4];
-} __attribute__ ((packed));
+} __packed;
 
 /* Metadata Partition Map (UDF 2.4.0 2.2.10) */
 struct metadataPartitionMap {
@@ -156,14 +156,14 @@ struct metadataPartitionMap {
 	__le16		alignUnitSize;
 	uint8_t		flags;
 	uint8_t		reserved2[5];
-} __attribute__ ((packed));
+} __packed;
 
 /* Virtual Allocation Table (UDF 1.5 2.2.10) */
 struct virtualAllocationTable15 {
 	__le32		VirtualSector[0];
 	struct regid	vatIdent;
 	__le32		previousVATICBLoc;
-} __attribute__ ((packed));
+} __packed;
 
 #define ICBTAG_FILE_TYPE_VAT15		0x00U
 
@@ -181,7 +181,7 @@ struct virtualAllocationTable20 {
 	__le16		reserved;
 	uint8_t		impUse[0];
 	__le32		vatEntry[0];
-} __attribute__ ((packed));
+} __packed;
 
 #define ICBTAG_FILE_TYPE_VAT20		0xF8U
 
@@ -189,7 +189,7 @@ struct virtualAllocationTable20 {
 struct sparingEntry {
 	__le32		origLocation;
 	__le32		mappedLocation;
-} __attribute__ ((packed));
+} __packed;
 
 struct sparingTable {
 	struct tag	descTag;
@@ -199,7 +199,7 @@ struct sparingTable {
 	__le32		sequenceNum;
 	struct sparingEntry
 			mapEntry[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* Metadata File (and Metadata Mirror File) (UDF 2.50 2.2.13.1) */
 #define ICBTAG_FILE_TYPE_MAIN		0xFA
@@ -210,7 +210,7 @@ struct sparingTable {
 struct allocDescImpUse {
 	__le16		flags;
 	uint8_t		impUse[4];
-} __attribute__ ((packed));
+} __packed;
 
 #define AD_IU_EXT_ERASED		0x0001
 
@@ -222,7 +222,7 @@ struct allocDescImpUse {
 struct freeEaSpace {
 	__le16		headerChecksum;
 	uint8_t		freeEASpace[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* DVD Copyright Management Information (UDF 2.50 3.3.4.5.1.2) */
 struct DVDCopyrightImpUse {
@@ -230,14 +230,14 @@ struct DVDCopyrightImpUse {
 	uint8_t		CGMSInfo;
 	uint8_t		dataType;
 	uint8_t		protectionSystemInfo[4];
-} __attribute__ ((packed));
+} __packed;
 
 /* Application Use Extended Attribute (UDF 2.50 3.3.4.6) */
 /* FreeAppEASpace (UDF 2.50 3.3.4.6.1) */
 struct freeAppEASpace {
 	__le16		headerChecksum;
 	uint8_t		freeEASpace[0];
-} __attribute__ ((packed));
+} __packed;
 
 /* UDF Defined System Stream (UDF 2.50 3.3.7) */
 #define UDF_ID_UNIQUE_ID		"*UDF Unique ID Mapping Data"
diff --git a/fs/udf/super.c b/fs/udf/super.c
index 4942549e7dc8..462ac2e9258c 100644
--- a/fs/udf/super.c
+++ b/fs/udf/super.c
@@ -73,8 +73,6 @@
 #define VDS_POS_TERMINATING_DESC	6
 #define VDS_POS_LENGTH			7
 
-#define UDF_DEFAULT_BLOCKSIZE 2048
-
 #define VSD_FIRST_SECTOR_OFFSET		32768
 #define VSD_MAX_SECTOR_OFFSET		0x800000
 
@@ -264,9 +262,6 @@ static void __exit exit_udf_fs(void)
 	destroy_inodecache();
 }
 
-module_init(init_udf_fs)
-module_exit(exit_udf_fs)
-
 static int udf_sb_alloc_partition_maps(struct super_block *sb, u32 count)
 {
 	struct udf_sb_info *sbi = UDF_SB(sb);
@@ -1216,7 +1211,8 @@ static int udf_load_vat(struct super_block *sb, int p_index, int type1_index)
 	struct udf_inode_info *vati;
 	uint32_t pos;
 	struct virtualAllocationTable20 *vat20;
-	sector_t blocks = sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits;
+	sector_t blocks = i_size_read(sb->s_bdev->bd_inode) >>
+			  sb->s_blocksize_bits;
 
 	udf_find_vat_block(sb, p_index, type1_index, sbi->s_last_block);
 	if (!sbi->s_vat_inode &&
@@ -1806,7 +1802,7 @@ static int udf_check_anchor_block(struct super_block *sb, sector_t block,
 
 	if (UDF_QUERY_FLAG(sb, UDF_FLAG_VARCONV) &&
 	    udf_fixed_to_variable(block) >=
-	    sb->s_bdev->bd_inode->i_size >> sb->s_blocksize_bits)
+	    i_size_read(sb->s_bdev->bd_inode) >> sb->s_blocksize_bits)
 		return -EAGAIN;
 
 	bh = udf_read_tagged(sb, block, block, &ident);
@@ -1868,7 +1864,7 @@ static int udf_scan_anchors(struct super_block *sb, sector_t *lastblock,
 		last[last_count++] = *lastblock - 152;
 
 	for (i = 0; i < last_count; i++) {
-		if (last[i] >= sb->s_bdev->bd_inode->i_size >>
+		if (last[i] >= i_size_read(sb->s_bdev->bd_inode) >>
 				sb->s_blocksize_bits)
 			continue;
 		ret = udf_check_anchor_block(sb, last[i], fileset);
@@ -1957,7 +1953,7 @@ static int udf_load_vrs(struct super_block *sb, struct udf_options *uopt,
 		if (!nsr_off) {
 			if (!silent)
 				udf_warn(sb, "No VRS found\n");
-			return 0;
+			return -EINVAL;
 		}
 		if (nsr_off == -1)
 			udf_debug("Failed to read sector at offset %d. "
@@ -1986,6 +1982,7 @@ static void udf_open_lvid(struct super_block *sb)
 	struct buffer_head *bh = sbi->s_lvid_bh;
 	struct logicalVolIntegrityDesc *lvid;
 	struct logicalVolIntegrityDescImpUse *lvidiu;
+	struct timespec ts;
 
 	if (!bh)
 		return;
@@ -1997,8 +1994,8 @@ static void udf_open_lvid(struct super_block *sb)
 	mutex_lock(&sbi->s_alloc_mutex);
 	lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX;
 	lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX;
-	udf_time_to_disk_stamp(&lvid->recordingDateAndTime,
-				CURRENT_TIME);
+	ktime_get_real_ts(&ts);
+	udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts);
 	lvid->integrityType = cpu_to_le32(LVID_INTEGRITY_TYPE_OPEN);
 
 	lvid->descTag.descCRC = cpu_to_le16(
@@ -2019,6 +2016,7 @@ static void udf_close_lvid(struct super_block *sb)
 	struct buffer_head *bh = sbi->s_lvid_bh;
 	struct logicalVolIntegrityDesc *lvid;
 	struct logicalVolIntegrityDescImpUse *lvidiu;
+	struct timespec ts;
 
 	if (!bh)
 		return;
@@ -2030,7 +2028,8 @@ static void udf_close_lvid(struct super_block *sb)
 	mutex_lock(&sbi->s_alloc_mutex);
 	lvidiu->impIdent.identSuffix[0] = UDF_OS_CLASS_UNIX;
 	lvidiu->impIdent.identSuffix[1] = UDF_OS_ID_LINUX;
-	udf_time_to_disk_stamp(&lvid->recordingDateAndTime, CURRENT_TIME);
+	ktime_get_real_ts(&ts);
+	udf_time_to_disk_stamp(&lvid->recordingDateAndTime, ts);
 	if (UDF_MAX_WRITE_VERSION > le16_to_cpu(lvidiu->maxUDFWriteRev))
 		lvidiu->maxUDFWriteRev = cpu_to_le16(UDF_MAX_WRITE_VERSION);
 	if (sbi->s_udfrev > le16_to_cpu(lvidiu->minUDFReadRev))
@@ -2158,15 +2157,25 @@ static int udf_fill_super(struct super_block *sb, void *options, int silent)
 		ret = udf_load_vrs(sb, &uopt, silent, &fileset);
 	} else {
 		uopt.blocksize = bdev_logical_block_size(sb->s_bdev);
-		ret = udf_load_vrs(sb, &uopt, silent, &fileset);
-		if (ret == -EAGAIN && uopt.blocksize != UDF_DEFAULT_BLOCKSIZE) {
-			if (!silent)
-				pr_notice("Rescanning with blocksize %d\n",
-					  UDF_DEFAULT_BLOCKSIZE);
-			brelse(sbi->s_lvid_bh);
-			sbi->s_lvid_bh = NULL;
-			uopt.blocksize = UDF_DEFAULT_BLOCKSIZE;
+		while (uopt.blocksize <= 4096) {
 			ret = udf_load_vrs(sb, &uopt, silent, &fileset);
+			if (ret < 0) {
+				if (!silent && ret != -EACCES) {
+					pr_notice("Scanning with blocksize %d failed\n",
+						  uopt.blocksize);
+				}
+				brelse(sbi->s_lvid_bh);
+				sbi->s_lvid_bh = NULL;
+				/*
+				 * EACCES is special - we want to propagate to
+				 * upper layers that we cannot handle RW mount.
+				 */
+				if (ret == -EACCES)
+					break;
+			} else
+				break;
+
+			uopt.blocksize <<= 1;
 		}
 	}
 	if (ret < 0) {
@@ -2497,3 +2506,9 @@ static unsigned int udf_count_free(struct super_block *sb)
 
 	return accum;
 }
+
+MODULE_AUTHOR("Ben Fennema");
+MODULE_DESCRIPTION("Universal Disk Format Filesystem");
+MODULE_LICENSE("GPL");
+module_init(init_udf_fs)
+module_exit(exit_udf_fs)
diff --git a/fs/udf/symlink.c b/fs/udf/symlink.c
index 8d619773056b..6023c97c6da2 100644
--- a/fs/udf/symlink.c
+++ b/fs/udf/symlink.c
@@ -152,9 +152,40 @@ out_unmap:
 	return err;
 }
 
+static int udf_symlink_getattr(const struct path *path, struct kstat *stat,
+				u32 request_mask, unsigned int flags)
+{
+	struct dentry *dentry = path->dentry;
+	struct inode *inode = d_backing_inode(dentry);
+	struct page *page;
+
+	generic_fillattr(inode, stat);
+	page = read_mapping_page(inode->i_mapping, 0, NULL);
+	if (IS_ERR(page))
+		return PTR_ERR(page);
+	/*
+	 * UDF uses non-trivial encoding of symlinks so i_size does not match
+	 * number of characters reported by readlink(2) which apparently some
+	 * applications expect. Also POSIX says that "The value returned in the
+	 * st_size field shall be the length of the contents of the symbolic
+	 * link, and shall not count a trailing null if one is present." So
+	 * let's report the length of string returned by readlink(2) for
+	 * st_size.
+	 */
+	stat->size = strlen(page_address(page));
+	put_page(page);
+
+	return 0;
+}
+
 /*
  * symlinks can't do much...
  */
 const struct address_space_operations udf_symlink_aops = {
 	.readpage		= udf_symlink_filler,
 };
+
+const struct inode_operations udf_symlink_inode_operations = {
+	.get_link	= page_get_link,
+	.getattr	= udf_symlink_getattr,
+};
diff --git a/fs/udf/udfdecl.h b/fs/udf/udfdecl.h
index 263829ef1873..63b034984378 100644
--- a/fs/udf/udfdecl.h
+++ b/fs/udf/udfdecl.h
@@ -15,7 +15,6 @@
 #include "udfend.h"
 #include "udf_i.h"
 
-#define UDF_PREALLOCATE
 #define UDF_DEFAULT_PREALLOC_BLOCKS	8
 
 extern __printf(3, 4) void _udf_err(struct super_block *sb,
@@ -85,6 +84,7 @@ extern const struct inode_operations udf_dir_inode_operations;
 extern const struct file_operations udf_dir_operations;
 extern const struct inode_operations udf_file_inode_operations;
 extern const struct file_operations udf_file_operations;
+extern const struct inode_operations udf_symlink_inode_operations;
 extern const struct address_space_operations udf_aops;
 extern const struct address_space_operations udf_adinicb_aops;
 extern const struct address_space_operations udf_symlink_aops;
diff --git a/fs/udf/udftime.c b/fs/udf/udftime.c
index 77c331f1a770..14626b34d13e 100644
--- a/fs/udf/udftime.c
+++ b/fs/udf/udftime.c
@@ -38,56 +38,11 @@
 
 #include <linux/types.h>
 #include <linux/kernel.h>
-
-#define EPOCH_YEAR 1970
-
-#ifndef __isleap
-/* Nonzero if YEAR is a leap year (every 4 years,
-   except every 100th isn't, and every 400th is).  */
-#define	__isleap(year)	\
-  ((year) % 4 == 0 && ((year) % 100 != 0 || (year) % 400 == 0))
-#endif
-
-/* How many days come before each month (0-12).  */
-static const unsigned short int __mon_yday[2][13] = {
-	/* Normal years.  */
-	{0, 31, 59, 90, 120, 151, 181, 212, 243, 273, 304, 334, 365},
-	/* Leap years.  */
-	{0, 31, 60, 91, 121, 152, 182, 213, 244, 274, 305, 335, 366}
-};
-
-#define MAX_YEAR_SECONDS	69
-#define SPD			0x15180	/*3600*24 */
-#define SPY(y, l, s)		(SPD * (365 * y + l) + s)
-
-static time_t year_seconds[MAX_YEAR_SECONDS] = {
-/*1970*/ SPY(0,   0, 0), SPY(1,   0, 0), SPY(2,   0, 0), SPY(3,   1, 0),
-/*1974*/ SPY(4,   1, 0), SPY(5,   1, 0), SPY(6,   1, 0), SPY(7,   2, 0),
-/*1978*/ SPY(8,   2, 0), SPY(9,   2, 0), SPY(10,  2, 0), SPY(11,  3, 0),
-/*1982*/ SPY(12,  3, 0), SPY(13,  3, 0), SPY(14,  3, 0), SPY(15,  4, 0),
-/*1986*/ SPY(16,  4, 0), SPY(17,  4, 0), SPY(18,  4, 0), SPY(19,  5, 0),
-/*1990*/ SPY(20,  5, 0), SPY(21,  5, 0), SPY(22,  5, 0), SPY(23,  6, 0),
-/*1994*/ SPY(24,  6, 0), SPY(25,  6, 0), SPY(26,  6, 0), SPY(27,  7, 0),
-/*1998*/ SPY(28,  7, 0), SPY(29,  7, 0), SPY(30,  7, 0), SPY(31,  8, 0),
-/*2002*/ SPY(32,  8, 0), SPY(33,  8, 0), SPY(34,  8, 0), SPY(35,  9, 0),
-/*2006*/ SPY(36,  9, 0), SPY(37,  9, 0), SPY(38,  9, 0), SPY(39, 10, 0),
-/*2010*/ SPY(40, 10, 0), SPY(41, 10, 0), SPY(42, 10, 0), SPY(43, 11, 0),
-/*2014*/ SPY(44, 11, 0), SPY(45, 11, 0), SPY(46, 11, 0), SPY(47, 12, 0),
-/*2018*/ SPY(48, 12, 0), SPY(49, 12, 0), SPY(50, 12, 0), SPY(51, 13, 0),
-/*2022*/ SPY(52, 13, 0), SPY(53, 13, 0), SPY(54, 13, 0), SPY(55, 14, 0),
-/*2026*/ SPY(56, 14, 0), SPY(57, 14, 0), SPY(58, 14, 0), SPY(59, 15, 0),
-/*2030*/ SPY(60, 15, 0), SPY(61, 15, 0), SPY(62, 15, 0), SPY(63, 16, 0),
-/*2034*/ SPY(64, 16, 0), SPY(65, 16, 0), SPY(66, 16, 0), SPY(67, 17, 0),
-/*2038*/ SPY(68, 17, 0)
-};
-
-#define SECS_PER_HOUR	(60 * 60)
-#define SECS_PER_DAY	(SECS_PER_HOUR * 24)
+#include <linux/time.h>
 
 struct timespec *
 udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src)
 {
-	int yday;
 	u16 typeAndTimezone = le16_to_cpu(src.typeAndTimezone);
 	u16 year = le16_to_cpu(src.year);
 	uint8_t type = typeAndTimezone >> 12;
@@ -102,15 +57,9 @@ udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src)
 	} else
 		offset = 0;
 
-	if ((year < EPOCH_YEAR) ||
-	    (year >= EPOCH_YEAR + MAX_YEAR_SECONDS)) {
-		return NULL;
-	}
-	dest->tv_sec = year_seconds[year - EPOCH_YEAR];
+	dest->tv_sec = mktime64(year, src.month, src.day, src.hour, src.minute,
+			src.second);
 	dest->tv_sec -= offset * 60;
-
-	yday = ((__mon_yday[__isleap(year)][src.month - 1]) + src.day - 1);
-	dest->tv_sec += (((yday * 24) + src.hour) * 60 + src.minute) * 60 + src.second;
 	dest->tv_nsec = 1000 * (src.centiseconds * 10000 +
 			src.hundredsOfMicroseconds * 100 + src.microseconds);
 	return dest;
@@ -119,9 +68,9 @@ udf_disk_stamp_to_time(struct timespec *dest, struct timestamp src)
 struct timestamp *
 udf_time_to_disk_stamp(struct timestamp *dest, struct timespec ts)
 {
-	long int days, rem, y;
-	const unsigned short int *ip;
+	long seconds;
 	int16_t offset;
+	struct tm tm;
 
 	offset = -sys_tz.tz_minuteswest;
 
@@ -130,35 +79,14 @@ udf_time_to_disk_stamp(struct timestamp *dest, struct timespec ts)
 
 	dest->typeAndTimezone = cpu_to_le16(0x1000 | (offset & 0x0FFF));
 
-	ts.tv_sec += offset * 60;
-	days = ts.tv_sec / SECS_PER_DAY;
-	rem = ts.tv_sec % SECS_PER_DAY;
-	dest->hour = rem / SECS_PER_HOUR;
-	rem %= SECS_PER_HOUR;
-	dest->minute = rem / 60;
-	dest->second = rem % 60;
-	y = 1970;
-
-#define DIV(a, b) ((a) / (b) - ((a) % (b) < 0))
-#define LEAPS_THRU_END_OF(y) (DIV (y, 4) - DIV (y, 100) + DIV (y, 400))
-
-	while (days < 0 || days >= (__isleap(y) ? 366 : 365)) {
-		long int yg = y + days / 365 - (days % 365 < 0);
-
-		/* Adjust DAYS and Y to match the guessed year.  */
-		days -= ((yg - y) * 365
-			 + LEAPS_THRU_END_OF(yg - 1)
-			 - LEAPS_THRU_END_OF(y - 1));
-		y = yg;
-	}
-	dest->year = cpu_to_le16(y);
-	ip = __mon_yday[__isleap(y)];
-	for (y = 11; days < (long int)ip[y]; --y)
-		continue;
-	days -= ip[y];
-	dest->month = y + 1;
-	dest->day = days + 1;
-
+	seconds = ts.tv_sec + offset * 60;
+	time64_to_tm(seconds, 0, &tm);
+	dest->year = cpu_to_le16(tm.tm_year + 1900);
+	dest->month = tm.tm_mon + 1;
+	dest->day = tm.tm_mday;
+	dest->hour = tm.tm_hour;
+	dest->minute = tm.tm_min;
+	dest->second = tm.tm_sec;
 	dest->centiseconds = ts.tv_nsec / 10000000;
 	dest->hundredsOfMicroseconds = (ts.tv_nsec / 1000 -
 					dest->centiseconds * 10000) / 100;
diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c
index a0376a2c1c29..f80be4c5df9d 100644
--- a/fs/ufs/balloc.c
+++ b/fs/ufs/balloc.c
@@ -82,7 +82,8 @@ void ufs_free_fragments(struct inode *inode, u64 fragment, unsigned count)
 			ufs_error (sb, "ufs_free_fragments",
 				   "bit already cleared for fragment %u", i);
 	}
-	
+
+	inode_sub_bytes(inode, count << uspi->s_fshift);
 	fs32_add(sb, &ucg->cg_cs.cs_nffree, count);
 	uspi->cs_total.cs_nffree += count;
 	fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, count);
@@ -184,6 +185,7 @@ do_more:
 			ufs_error(sb, "ufs_free_blocks", "freeing free fragment");
 		}
 		ubh_setblock(UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
+		inode_sub_bytes(inode, uspi->s_fpb << uspi->s_fshift);
 		if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
 			ufs_clusteracct (sb, ucpi, blkno, 1);
 
@@ -398,10 +400,12 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	/*
 	 * There is not enough space for user on the device
 	 */
-	if (!capable(CAP_SYS_RESOURCE) && ufs_freespace(uspi, UFS_MINFREE) <= 0) {
-		mutex_unlock(&UFS_SB(sb)->s_lock);
-		UFSD("EXIT (FAILED)\n");
-		return 0;
+	if (unlikely(ufs_freefrags(uspi) <= uspi->s_root_blocks)) {
+		if (!capable(CAP_SYS_RESOURCE)) {
+			mutex_unlock(&UFS_SB(sb)->s_lock);
+			UFSD("EXIT (FAILED)\n");
+			return 0;
+		}
 	}
 
 	if (goal >= uspi->s_size) 
@@ -419,12 +423,12 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 		if (result) {
 			ufs_clear_frags(inode, result + oldcount,
 					newcount - oldcount, locked_page != NULL);
+			*err = 0;
 			write_seqlock(&UFS_I(inode)->meta_lock);
 			ufs_cpu_to_data_ptr(sb, p, result);
-			write_sequnlock(&UFS_I(inode)->meta_lock);
-			*err = 0;
 			UFS_I(inode)->i_lastfrag =
 				max(UFS_I(inode)->i_lastfrag, fragment + count);
+			write_sequnlock(&UFS_I(inode)->meta_lock);
 		}
 		mutex_unlock(&UFS_SB(sb)->s_lock);
 		UFSD("EXIT, result %llu\n", (unsigned long long)result);
@@ -437,8 +441,10 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	result = ufs_add_fragments(inode, tmp, oldcount, newcount);
 	if (result) {
 		*err = 0;
+		read_seqlock_excl(&UFS_I(inode)->meta_lock);
 		UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag,
 						fragment + count);
+		read_sequnlock_excl(&UFS_I(inode)->meta_lock);
 		ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
 				locked_page != NULL);
 		mutex_unlock(&UFS_SB(sb)->s_lock);
@@ -449,39 +455,29 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	/*
 	 * allocate new block and move data
 	 */
-	switch (fs32_to_cpu(sb, usb1->fs_optim)) {
-	    case UFS_OPTSPACE:
+	if (fs32_to_cpu(sb, usb1->fs_optim) == UFS_OPTSPACE) {
 		request = newcount;
-		if (uspi->s_minfree < 5 || uspi->cs_total.cs_nffree
-		    > uspi->s_dsize * uspi->s_minfree / (2 * 100))
-			break;
-		usb1->fs_optim = cpu_to_fs32(sb, UFS_OPTTIME);
-		break;
-	    default:
-		usb1->fs_optim = cpu_to_fs32(sb, UFS_OPTTIME);
-	
-	    case UFS_OPTTIME:
+		if (uspi->cs_total.cs_nffree < uspi->s_space_to_time)
+			usb1->fs_optim = cpu_to_fs32(sb, UFS_OPTTIME);
+	} else {
 		request = uspi->s_fpb;
-		if (uspi->cs_total.cs_nffree < uspi->s_dsize *
-		    (uspi->s_minfree - 2) / 100)
-			break;
-		usb1->fs_optim = cpu_to_fs32(sb, UFS_OPTTIME);
-		break;
+		if (uspi->cs_total.cs_nffree > uspi->s_time_to_space)
+			usb1->fs_optim = cpu_to_fs32(sb, UFS_OPTSPACE);
 	}
 	result = ufs_alloc_fragments (inode, cgno, goal, request, err);
 	if (result) {
 		ufs_clear_frags(inode, result + oldcount, newcount - oldcount,
 				locked_page != NULL);
+		mutex_unlock(&UFS_SB(sb)->s_lock);
 		ufs_change_blocknr(inode, fragment - oldcount, oldcount,
 				   uspi->s_sbbase + tmp,
 				   uspi->s_sbbase + result, locked_page);
+		*err = 0;
 		write_seqlock(&UFS_I(inode)->meta_lock);
 		ufs_cpu_to_data_ptr(sb, p, result);
-		write_sequnlock(&UFS_I(inode)->meta_lock);
-		*err = 0;
 		UFS_I(inode)->i_lastfrag = max(UFS_I(inode)->i_lastfrag,
 						fragment + count);
-		mutex_unlock(&UFS_SB(sb)->s_lock);
+		write_sequnlock(&UFS_I(inode)->meta_lock);
 		if (newcount < request)
 			ufs_free_fragments (inode, result + newcount, request - newcount);
 		ufs_free_fragments (inode, tmp, oldcount);
@@ -494,6 +490,20 @@ u64 ufs_new_fragments(struct inode *inode, void *p, u64 fragment,
 	return 0;
 }		
 
+static bool try_add_frags(struct inode *inode, unsigned frags)
+{
+	unsigned size = frags * i_blocksize(inode);
+	spin_lock(&inode->i_lock);
+	__inode_add_bytes(inode, size);
+	if (unlikely((u32)inode->i_blocks != inode->i_blocks)) {
+		__inode_sub_bytes(inode, size);
+		spin_unlock(&inode->i_lock);
+		return false;
+	}
+	spin_unlock(&inode->i_lock);
+	return true;
+}
+
 static u64 ufs_add_fragments(struct inode *inode, u64 fragment,
 			     unsigned oldcount, unsigned newcount)
 {
@@ -530,6 +540,9 @@ static u64 ufs_add_fragments(struct inode *inode, u64 fragment,
 	for (i = oldcount; i < newcount; i++)
 		if (ubh_isclr (UCPI_UBH(ucpi), ucpi->c_freeoff, fragno + i))
 			return 0;
+
+	if (!try_add_frags(inode, count))
+		return 0;
 	/*
 	 * Block can be extended
 	 */
@@ -647,6 +660,7 @@ cg_found:
 			ubh_setbit (UCPI_UBH(ucpi), ucpi->c_freeoff, goal + i);
 		i = uspi->s_fpb - count;
 
+		inode_sub_bytes(inode, i << uspi->s_fshift);
 		fs32_add(sb, &ucg->cg_cs.cs_nffree, i);
 		uspi->cs_total.cs_nffree += i;
 		fs32_add(sb, &UFS_SB(sb)->fs_cs(cgno).cs_nffree, i);
@@ -657,6 +671,8 @@ cg_found:
 	result = ufs_bitmap_search (sb, ucpi, goal, allocsize);
 	if (result == INVBLOCK)
 		return 0;
+	if (!try_add_frags(inode, count))
+		return 0;
 	for (i = 0; i < count; i++)
 		ubh_clrbit (UCPI_UBH(ucpi), ucpi->c_freeoff, result + i);
 	
@@ -716,6 +732,8 @@ norot:
 		return INVBLOCK;
 	ucpi->c_rotor = result;
 gotit:
+	if (!try_add_frags(inode, uspi->s_fpb))
+		return 0;
 	blkno = ufs_fragstoblks(result);
 	ubh_clrblock (UCPI_UBH(ucpi), ucpi->c_freeoff, blkno);
 	if ((UFS_SB(sb)->s_flags & UFS_CG_MASK) == UFS_CG_44BSD)
diff --git a/fs/ufs/dir.c b/fs/ufs/dir.c
index de01b8f2aa78..48609f1d9580 100644
--- a/fs/ufs/dir.c
+++ b/fs/ufs/dir.c
@@ -53,7 +53,7 @@ static int ufs_commit_chunk(struct page *page, loff_t pos, unsigned len)
 		mark_inode_dirty(dir);
 	}
 	if (IS_DIRSYNC(dir))
-		err = write_one_page(page, 1);
+		err = write_one_page(page);
 	else
 		unlock_page(page);
 	return err;
diff --git a/fs/ufs/ialloc.c b/fs/ufs/ialloc.c
index 9774555b3721..d1dd8cc33179 100644
--- a/fs/ufs/ialloc.c
+++ b/fs/ufs/ialloc.c
@@ -176,6 +176,7 @@ struct inode *ufs_new_inode(struct inode *dir, umode_t mode)
 	struct ufs_cg_private_info * ucpi;
 	struct ufs_cylinder_group * ucg;
 	struct inode * inode;
+	struct timespec64 ts;
 	unsigned cg, bit, i, j, start;
 	struct ufs_inode_info *ufsi;
 	int err = -ENOSPC;
@@ -323,8 +324,9 @@ cg_found:
 		lock_buffer(bh);
 		ufs2_inode = (struct ufs2_inode *)bh->b_data;
 		ufs2_inode += ufs_inotofsbo(inode->i_ino);
-		ufs2_inode->ui_birthtime = cpu_to_fs64(sb, CURRENT_TIME.tv_sec);
-		ufs2_inode->ui_birthnsec = cpu_to_fs32(sb, CURRENT_TIME.tv_nsec);
+		ktime_get_real_ts64(&ts);
+		ufs2_inode->ui_birthtime = cpu_to_fs64(sb, ts.tv_sec);
+		ufs2_inode->ui_birthnsec = cpu_to_fs32(sb, ts.tv_nsec);
 		mark_buffer_dirty(bh);
 		unlock_buffer(bh);
 		if (sb->s_flags & MS_SYNCHRONOUS)
diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c
index 7e41aee7b69a..f36d6a53687d 100644
--- a/fs/ufs/inode.c
+++ b/fs/ufs/inode.c
@@ -235,7 +235,8 @@ ufs_extend_tail(struct inode *inode, u64 writes_to,
 
 	p = ufs_get_direct_data_ptr(uspi, ufsi, block);
 	tmp = ufs_new_fragments(inode, p, lastfrag, ufs_data_ptr_to_cpu(sb, p),
-				new_size, err, locked_page);
+				new_size - (lastfrag & uspi->s_fpbmask), err,
+				locked_page);
 	return tmp != 0;
 }
 
@@ -284,7 +285,7 @@ ufs_inode_getfrag(struct inode *inode, unsigned index,
 			goal += uspi->s_fpb;
 	}
 	tmp = ufs_new_fragments(inode, p, ufs_blknum(new_fragment),
-				goal, uspi->s_fpb, err, locked_page);
+				goal, nfrags, err, locked_page);
 
 	if (!tmp) {
 		*err = -ENOSPC;
@@ -400,11 +401,20 @@ static int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buff
 	u64 phys64 = 0;
 	unsigned frag = fragment & uspi->s_fpbmask;
 
-	if (!create) {
-		phys64 = ufs_frag_map(inode, offsets, depth);
-		goto out;
-	}
+	phys64 = ufs_frag_map(inode, offsets, depth);
+	if (!create)
+		goto done;
 
+	if (phys64) {
+		if (fragment >= UFS_NDIR_FRAGMENT)
+			goto done;
+		read_seqlock_excl(&UFS_I(inode)->meta_lock);
+		if (fragment < UFS_I(inode)->i_lastfrag) {
+			read_sequnlock_excl(&UFS_I(inode)->meta_lock);
+			goto done;
+		}
+		read_sequnlock_excl(&UFS_I(inode)->meta_lock);
+	}
         /* This code entered only while writing ....? */
 
 	mutex_lock(&UFS_I(inode)->truncate_mutex);
@@ -448,6 +458,11 @@ out:
 	}
 	mutex_unlock(&UFS_I(inode)->truncate_mutex);
 	return err;
+
+done:
+	if (phys64)
+		map_bh(bh_result, sb, phys64 + frag);
+	return 0;
 }
 
 static int ufs_writepage(struct page *page, struct writeback_control *wbc)
@@ -551,10 +566,8 @@ static int ufs1_read_inode(struct inode *inode, struct ufs_inode *ufs_inode)
 	 */
 	inode->i_mode = mode = fs16_to_cpu(sb, ufs_inode->ui_mode);
 	set_nlink(inode, fs16_to_cpu(sb, ufs_inode->ui_nlink));
-	if (inode->i_nlink == 0) {
-		ufs_error (sb, "ufs_read_inode", "inode %lu has zero nlink\n", inode->i_ino);
-		return -1;
-	}
+	if (inode->i_nlink == 0)
+		return -ESTALE;
 
 	/*
 	 * Linux now has 32-bit uid and gid, so we can support EFT.
@@ -563,9 +576,9 @@ static int ufs1_read_inode(struct inode *inode, struct ufs_inode *ufs_inode)
 	i_gid_write(inode, ufs_get_inode_gid(sb, ufs_inode));
 
 	inode->i_size = fs64_to_cpu(sb, ufs_inode->ui_size);
-	inode->i_atime.tv_sec = fs32_to_cpu(sb, ufs_inode->ui_atime.tv_sec);
-	inode->i_ctime.tv_sec = fs32_to_cpu(sb, ufs_inode->ui_ctime.tv_sec);
-	inode->i_mtime.tv_sec = fs32_to_cpu(sb, ufs_inode->ui_mtime.tv_sec);
+	inode->i_atime.tv_sec = (signed)fs32_to_cpu(sb, ufs_inode->ui_atime.tv_sec);
+	inode->i_ctime.tv_sec = (signed)fs32_to_cpu(sb, ufs_inode->ui_ctime.tv_sec);
+	inode->i_mtime.tv_sec = (signed)fs32_to_cpu(sb, ufs_inode->ui_mtime.tv_sec);
 	inode->i_mtime.tv_nsec = 0;
 	inode->i_atime.tv_nsec = 0;
 	inode->i_ctime.tv_nsec = 0;
@@ -599,10 +612,8 @@ static int ufs2_read_inode(struct inode *inode, struct ufs2_inode *ufs2_inode)
 	 */
 	inode->i_mode = mode = fs16_to_cpu(sb, ufs2_inode->ui_mode);
 	set_nlink(inode, fs16_to_cpu(sb, ufs2_inode->ui_nlink));
-	if (inode->i_nlink == 0) {
-		ufs_error (sb, "ufs_read_inode", "inode %lu has zero nlink\n", inode->i_ino);
-		return -1;
-	}
+	if (inode->i_nlink == 0)
+		return -ESTALE;
 
         /*
          * Linux now has 32-bit uid and gid, so we can support EFT.
@@ -642,7 +653,7 @@ struct inode *ufs_iget(struct super_block *sb, unsigned long ino)
 	struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
 	struct buffer_head * bh;
 	struct inode *inode;
-	int err;
+	int err = -EIO;
 
 	UFSD("ENTER, ino %lu\n", ino);
 
@@ -677,9 +688,10 @@ struct inode *ufs_iget(struct super_block *sb, unsigned long ino)
 		err = ufs1_read_inode(inode,
 				      ufs_inode + ufs_inotofsbo(inode->i_ino));
 	}
-
+	brelse(bh);
 	if (err)
 		goto bad_inode;
+
 	inode->i_version++;
 	ufsi->i_lastfrag =
 		(inode->i_size + uspi->s_fsize - 1) >> uspi->s_fshift;
@@ -688,15 +700,13 @@ struct inode *ufs_iget(struct super_block *sb, unsigned long ino)
 
 	ufs_set_inode_ops(inode);
 
-	brelse(bh);
-
 	UFSD("EXIT\n");
 	unlock_new_inode(inode);
 	return inode;
 
 bad_inode:
 	iget_failed(inode);
-	return ERR_PTR(-EIO);
+	return ERR_PTR(err);
 }
 
 static void ufs1_update_inode(struct inode *inode, struct ufs_inode *ufs_inode)
@@ -841,8 +851,11 @@ void ufs_evict_inode(struct inode * inode)
 	truncate_inode_pages_final(&inode->i_data);
 	if (want_delete) {
 		inode->i_size = 0;
-		if (inode->i_blocks)
+		if (inode->i_blocks &&
+		    (S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
+		     S_ISLNK(inode->i_mode)))
 			ufs_truncate_blocks(inode);
+		ufs_update_inode(inode, inode_needs_sync(inode));
 	}
 
 	invalidate_inode_buffers(inode);
@@ -868,7 +881,6 @@ static inline void free_data(struct to_free *ctx, u64 from, unsigned count)
 	ctx->to = from + count;
 }
 
-#define DIRECT_BLOCK ((inode->i_size + uspi->s_bsize - 1) >> uspi->s_bshift)
 #define DIRECT_FRAGMENT ((inode->i_size + uspi->s_fsize - 1) >> uspi->s_fshift)
 
 static void ufs_trunc_direct(struct inode *inode)
@@ -1100,25 +1112,30 @@ out:
        return err;
 }
 
-static void __ufs_truncate_blocks(struct inode *inode)
+static void ufs_truncate_blocks(struct inode *inode)
 {
 	struct ufs_inode_info *ufsi = UFS_I(inode);
 	struct super_block *sb = inode->i_sb;
 	struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
 	unsigned offsets[4];
-	int depth = ufs_block_to_path(inode, DIRECT_BLOCK, offsets);
+	int depth;
 	int depth2;
 	unsigned i;
 	struct ufs_buffer_head *ubh[3];
 	void *p;
 	u64 block;
 
-	if (!depth)
-		return;
+	if (inode->i_size) {
+		sector_t last = (inode->i_size - 1) >> uspi->s_bshift;
+		depth = ufs_block_to_path(inode, last, offsets);
+		if (!depth)
+			return;
+	} else {
+		depth = 1;
+	}
 
-	/* find the last non-zero in offsets[] */
 	for (depth2 = depth - 1; depth2; depth2--)
-		if (offsets[depth2])
+		if (offsets[depth2] != uspi->s_apb - 1)
 			break;
 
 	mutex_lock(&ufsi->truncate_mutex);
@@ -1127,9 +1144,8 @@ static void __ufs_truncate_blocks(struct inode *inode)
 		offsets[0] = UFS_IND_BLOCK;
 	} else {
 		/* get the blocks that should be partially emptied */
-		p = ufs_get_direct_data_ptr(uspi, ufsi, offsets[0]);
+		p = ufs_get_direct_data_ptr(uspi, ufsi, offsets[0]++);
 		for (i = 0; i < depth2; i++) {
-			offsets[i]++;	/* next branch is fully freed */
 			block = ufs_data_ptr_to_cpu(sb, p);
 			if (!block)
 				break;
@@ -1140,7 +1156,7 @@ static void __ufs_truncate_blocks(struct inode *inode)
 				write_sequnlock(&ufsi->meta_lock);
 				break;
 			}
-			p = ubh_get_data_ptr(uspi, ubh[i], offsets[i + 1]);
+			p = ubh_get_data_ptr(uspi, ubh[i], offsets[i + 1]++);
 		}
 		while (i--)
 			free_branch_tail(inode, offsets[i + 1], ubh[i], depth - i - 1);
@@ -1155,7 +1171,9 @@ static void __ufs_truncate_blocks(struct inode *inode)
 			free_full_branch(inode, block, i - UFS_IND_BLOCK + 1);
 		}
 	}
+	read_seqlock_excl(&ufsi->meta_lock);
 	ufsi->i_lastfrag = DIRECT_FRAGMENT;
+	read_sequnlock_excl(&ufsi->meta_lock);
 	mark_inode_dirty(inode);
 	mutex_unlock(&ufsi->truncate_mutex);
 }
@@ -1183,7 +1201,7 @@ static int ufs_truncate(struct inode *inode, loff_t size)
 
 	truncate_setsize(inode, size);
 
-	__ufs_truncate_blocks(inode);
+	ufs_truncate_blocks(inode);
 	inode->i_mtime = inode->i_ctime = current_time(inode);
 	mark_inode_dirty(inode);
 out:
@@ -1191,16 +1209,6 @@ out:
 	return err;
 }
 
-static void ufs_truncate_blocks(struct inode *inode)
-{
-	if (!(S_ISREG(inode->i_mode) || S_ISDIR(inode->i_mode) ||
-	      S_ISLNK(inode->i_mode)))
-		return;
-	if (IS_APPEND(inode) || IS_IMMUTABLE(inode))
-		return;
-	__ufs_truncate_blocks(inode);
-}
-
 int ufs_setattr(struct dentry *dentry, struct iattr *attr)
 {
 	struct inode *inode = d_inode(dentry);
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 131b2b77c818..0a4f58a5073c 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -480,7 +480,7 @@ static void ufs_setup_cstotal(struct super_block *sb)
 	usb3 = ubh_get_usb_third(uspi);
 
 	if ((mtype == UFS_MOUNT_UFSTYPE_44BSD &&
-	     (usb1->fs_flags & UFS_FLAGS_UPDATED)) ||
+	     (usb2->fs_un.fs_u2.fs_maxbsize == usb1->fs_bsize)) ||
 	    mtype == UFS_MOUNT_UFSTYPE_UFS2) {
 		/*we have statistic in different place, then usual*/
 		uspi->cs_total.cs_ndir = fs64_to_cpu(sb, usb2->fs_un.fs_u2.cs_ndir);
@@ -596,9 +596,7 @@ static void ufs_put_cstotal(struct super_block *sb)
 	usb2 = ubh_get_usb_second(uspi);
 	usb3 = ubh_get_usb_third(uspi);
 
-	if ((mtype == UFS_MOUNT_UFSTYPE_44BSD &&
-	     (usb1->fs_flags & UFS_FLAGS_UPDATED)) ||
-	    mtype == UFS_MOUNT_UFSTYPE_UFS2) {
+	if (mtype == UFS_MOUNT_UFSTYPE_UFS2) {
 		/*we have statistic in different place, then usual*/
 		usb2->fs_un.fs_u2.cs_ndir =
 			cpu_to_fs64(sb, uspi->cs_total.cs_ndir);
@@ -608,16 +606,26 @@ static void ufs_put_cstotal(struct super_block *sb)
 			cpu_to_fs64(sb, uspi->cs_total.cs_nifree);
 		usb3->fs_un1.fs_u2.cs_nffree =
 			cpu_to_fs64(sb, uspi->cs_total.cs_nffree);
-	} else {
-		usb1->fs_cstotal.cs_ndir =
-			cpu_to_fs32(sb, uspi->cs_total.cs_ndir);
-		usb1->fs_cstotal.cs_nbfree =
-			cpu_to_fs32(sb, uspi->cs_total.cs_nbfree);
-		usb1->fs_cstotal.cs_nifree =
-			cpu_to_fs32(sb, uspi->cs_total.cs_nifree);
-		usb1->fs_cstotal.cs_nffree =
-			cpu_to_fs32(sb, uspi->cs_total.cs_nffree);
+		goto out;
+	}
+
+	if (mtype == UFS_MOUNT_UFSTYPE_44BSD &&
+	     (usb2->fs_un.fs_u2.fs_maxbsize == usb1->fs_bsize)) {
+		/* store stats in both old and new places */
+		usb2->fs_un.fs_u2.cs_ndir =
+			cpu_to_fs64(sb, uspi->cs_total.cs_ndir);
+		usb2->fs_un.fs_u2.cs_nbfree =
+			cpu_to_fs64(sb, uspi->cs_total.cs_nbfree);
+		usb3->fs_un1.fs_u2.cs_nifree =
+			cpu_to_fs64(sb, uspi->cs_total.cs_nifree);
+		usb3->fs_un1.fs_u2.cs_nffree =
+			cpu_to_fs64(sb, uspi->cs_total.cs_nffree);
 	}
+	usb1->fs_cstotal.cs_ndir = cpu_to_fs32(sb, uspi->cs_total.cs_ndir);
+	usb1->fs_cstotal.cs_nbfree = cpu_to_fs32(sb, uspi->cs_total.cs_nbfree);
+	usb1->fs_cstotal.cs_nifree = cpu_to_fs32(sb, uspi->cs_total.cs_nifree);
+	usb1->fs_cstotal.cs_nffree = cpu_to_fs32(sb, uspi->cs_total.cs_nffree);
+out:
 	ubh_mark_buffer_dirty(USPI_UBH(uspi));
 	ufs_print_super_stuff(sb, usb1, usb2, usb3);
 	UFSD("EXIT\n");
@@ -746,6 +754,23 @@ static void ufs_put_super(struct super_block *sb)
 	return;
 }
 
+static u64 ufs_max_bytes(struct super_block *sb)
+{
+	struct ufs_sb_private_info *uspi = UFS_SB(sb)->s_uspi;
+	int bits = uspi->s_apbshift;
+	u64 res;
+
+	if (bits > 21)
+		res = ~0ULL;
+	else
+		res = UFS_NDADDR + (1LL << bits) + (1LL << (2*bits)) +
+			(1LL << (3*bits));
+
+	if (res >= (MAX_LFS_FILESIZE >> uspi->s_bshift))
+		return MAX_LFS_FILESIZE;
+	return res << uspi->s_bshift;
+}
+
 static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 {
 	struct ufs_sb_info * sbi;
@@ -812,9 +837,8 @@ static int ufs_fill_super(struct super_block *sb, void *data, int silent)
 	uspi->s_dirblksize = UFS_SECTOR_SIZE;
 	super_block_offset=UFS_SBLOCK;
 
-	/* Keep 2Gig file limit. Some UFS variants need to override 
-	   this but as I don't know which I'll let those in the know loosen
-	   the rules */
+	sb->s_maxbytes = MAX_LFS_FILESIZE;
+
 	switch (sbi->s_mount_opt & UFS_MOUNT_UFSTYPE) {
 	case UFS_MOUNT_UFSTYPE_44BSD:
 		UFSD("ufstype=44bsd\n");
@@ -980,6 +1004,13 @@ again:
 		flags |=  UFS_ST_SUN;
 	}
 
+	if ((flags & UFS_ST_MASK) == UFS_ST_44BSD &&
+	    uspi->s_postblformat == UFS_42POSTBLFMT) {
+		if (!silent)
+			pr_err("this is not a 44bsd filesystem");
+		goto failed;
+	}
+
 	/*
 	 * Check ufs magic number
 	 */
@@ -1127,8 +1158,8 @@ magic_found:
 	uspi->s_cgmask = fs32_to_cpu(sb, usb1->fs_cgmask);
 
 	if ((flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2) {
-		uspi->s_u2_size  = fs64_to_cpu(sb, usb3->fs_un1.fs_u2.fs_size);
-		uspi->s_u2_dsize = fs64_to_cpu(sb, usb3->fs_un1.fs_u2.fs_dsize);
+		uspi->s_size  = fs64_to_cpu(sb, usb3->fs_un1.fs_u2.fs_size);
+		uspi->s_dsize = fs64_to_cpu(sb, usb3->fs_un1.fs_u2.fs_dsize);
 	} else {
 		uspi->s_size  =  fs32_to_cpu(sb, usb1->fs_size);
 		uspi->s_dsize =  fs32_to_cpu(sb, usb1->fs_dsize);
@@ -1177,6 +1208,18 @@ magic_found:
 	uspi->s_postbloff = fs32_to_cpu(sb, usb3->fs_postbloff);
 	uspi->s_rotbloff = fs32_to_cpu(sb, usb3->fs_rotbloff);
 
+	uspi->s_root_blocks = mul_u64_u32_div(uspi->s_dsize,
+					      uspi->s_minfree, 100);
+	if (uspi->s_minfree <= 5) {
+		uspi->s_time_to_space = ~0ULL;
+		uspi->s_space_to_time = 0;
+		usb1->fs_optim = cpu_to_fs32(sb, UFS_OPTSPACE);
+	} else {
+		uspi->s_time_to_space = (uspi->s_root_blocks / 2) + 1;
+		uspi->s_space_to_time = mul_u64_u32_div(uspi->s_dsize,
+					      uspi->s_minfree - 2, 100) - 1;
+	}
+
 	/*
 	 * Compute another frequently used values
 	 */
@@ -1212,6 +1255,7 @@ magic_found:
 			    "fast symlink size (%u)\n", uspi->s_maxsymlinklen);
 		uspi->s_maxsymlinklen = maxsymlen;
 	}
+	sb->s_maxbytes = ufs_max_bytes(sb);
 	sb->s_max_links = UFS_LINK_MAX;
 
 	inode = ufs_iget(sb, UFS_ROOTINO);
@@ -1365,19 +1409,17 @@ static int ufs_statfs(struct dentry *dentry, struct kstatfs *buf)
 	mutex_lock(&UFS_SB(sb)->s_lock);
 	usb3 = ubh_get_usb_third(uspi);
 	
-	if ((flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2) {
+	if ((flags & UFS_TYPE_MASK) == UFS_TYPE_UFS2)
 		buf->f_type = UFS2_MAGIC;
-		buf->f_blocks = fs64_to_cpu(sb, usb3->fs_un1.fs_u2.fs_dsize);
-	} else {
+	else
 		buf->f_type = UFS_MAGIC;
-		buf->f_blocks = uspi->s_dsize;
-	}
-	buf->f_bfree = ufs_blkstofrags(uspi->cs_total.cs_nbfree) +
-		uspi->cs_total.cs_nffree;
+
+	buf->f_blocks = uspi->s_dsize;
+	buf->f_bfree = ufs_freefrags(uspi);
 	buf->f_ffree = uspi->cs_total.cs_nifree;
 	buf->f_bsize = sb->s_blocksize;
-	buf->f_bavail = (buf->f_bfree > (((long)buf->f_blocks / 100) * uspi->s_minfree))
-		? (buf->f_bfree - (((long)buf->f_blocks / 100) * uspi->s_minfree)) : 0;
+	buf->f_bavail = (buf->f_bfree > uspi->s_root_blocks)
+		? (buf->f_bfree - uspi->s_root_blocks) : 0;
 	buf->f_files = uspi->s_ncg * uspi->s_ipg;
 	buf->f_namelen = UFS_MAXNAMLEN;
 	buf->f_fsid.val[0] = (u32)id;
diff --git a/fs/ufs/ufs_fs.h b/fs/ufs/ufs_fs.h
index 0cbd5d340b67..150eef6f1233 100644
--- a/fs/ufs/ufs_fs.h
+++ b/fs/ufs/ufs_fs.h
@@ -733,10 +733,8 @@ struct ufs_sb_private_info {
 	__u32	s_dblkno;	/* offset of first data after cg */
 	__u32	s_cgoffset;	/* cylinder group offset in cylinder */
 	__u32	s_cgmask;	/* used to calc mod fs_ntrak */
-	__u32	s_size;		/* number of blocks (fragments) in fs */
-	__u32	s_dsize;	/* number of data blocks in fs */
-	__u64	s_u2_size;	/* ufs2: number of blocks (fragments) in fs */
-	__u64	s_u2_dsize;	/*ufs2:  number of data blocks in fs */
+	__u64	s_size;		/* number of blocks (fragments) in fs */
+	__u64	s_dsize;	/* number of data blocks in fs */
 	__u32	s_ncg;		/* number of cylinder groups */
 	__u32	s_bsize;	/* size of basic blocks */
 	__u32	s_fsize;	/* size of fragments */
@@ -793,6 +791,9 @@ struct ufs_sb_private_info {
 	__u32	s_maxsymlinklen;/* upper limit on fast symlinks' size */
 	__s32	fs_magic;       /* filesystem magic */
 	unsigned int s_dirblksize;
+	__u64   s_root_blocks;
+	__u64	s_time_to_space;
+	__u64	s_space_to_time;
 };
 
 /*
diff --git a/fs/ufs/util.c b/fs/ufs/util.c
index f41ad0a6106f..02497a492eb2 100644
--- a/fs/ufs/util.c
+++ b/fs/ufs/util.c
@@ -243,9 +243,8 @@ ufs_set_inode_dev(struct super_block *sb, struct ufs_inode_info *ufsi, dev_t dev
 struct page *ufs_get_locked_page(struct address_space *mapping,
 				 pgoff_t index)
 {
-	struct page *page;
-
-	page = find_lock_page(mapping, index);
+	struct inode *inode = mapping->host;
+	struct page *page = find_lock_page(mapping, index);
 	if (!page) {
 		page = read_mapping_page(mapping, index, NULL);
 
@@ -253,7 +252,7 @@ struct page *ufs_get_locked_page(struct address_space *mapping,
 			printk(KERN_ERR "ufs_change_blocknr: "
 			       "read_mapping_page error: ino %lu, index: %lu\n",
 			       mapping->host->i_ino, index);
-			goto out;
+			return page;
 		}
 
 		lock_page(page);
@@ -262,8 +261,7 @@ struct page *ufs_get_locked_page(struct address_space *mapping,
 			/* Truncate got there first */
 			unlock_page(page);
 			put_page(page);
-			page = NULL;
-			goto out;
+			return NULL;
 		}
 
 		if (!PageUptodate(page) || PageError(page)) {
@@ -272,11 +270,12 @@ struct page *ufs_get_locked_page(struct address_space *mapping,
 
 			printk(KERN_ERR "ufs_change_blocknr: "
 			       "can not read page: ino %lu, index: %lu\n",
-			       mapping->host->i_ino, index);
+			       inode->i_ino, index);
 
-			page = ERR_PTR(-EIO);
+			return ERR_PTR(-EIO);
 		}
 	}
-out:
+	if (!page_has_buffers(page))
+		create_empty_buffers(page, 1 << inode->i_blkbits, 0);
 	return page;
 }
diff --git a/fs/ufs/util.h b/fs/ufs/util.h
index b7fbf53dbc81..9fc7119a1551 100644
--- a/fs/ufs/util.h
+++ b/fs/ufs/util.h
@@ -350,16 +350,11 @@ static inline void *ubh_get_data_ptr(struct ufs_sb_private_info *uspi,
 #define ubh_blkmap(ubh,begin,bit) \
 	((*ubh_get_addr(ubh, (begin) + ((bit) >> 3)) >> ((bit) & 7)) & (0xff >> (UFS_MAXFRAG - uspi->s_fpb)))
 
-/*
- * Determine the number of available frags given a
- * percentage to hold in reserve.
- */
 static inline u64
-ufs_freespace(struct ufs_sb_private_info *uspi, int percentreserved)
+ufs_freefrags(struct ufs_sb_private_info *uspi)
 {
 	return ufs_blkstofrags(uspi->cs_total.cs_nbfree) +
-		uspi->cs_total.cs_nffree -
-		(uspi->s_dsize * (percentreserved) / 100);
+		uspi->cs_total.cs_nffree;
 }
 
 /*
@@ -473,15 +468,19 @@ static inline unsigned _ubh_find_last_zero_bit_(
 static inline int _ubh_isblockset_(struct ufs_sb_private_info * uspi,
 	struct ufs_buffer_head * ubh, unsigned begin, unsigned block)
 {
+	u8 mask;
 	switch (uspi->s_fpb) {
 	case 8:
 	    	return (*ubh_get_addr (ubh, begin + block) == 0xff);
 	case 4:
-		return (*ubh_get_addr (ubh, begin + (block >> 1)) == (0x0f << ((block & 0x01) << 2)));
+		mask = 0x0f << ((block & 0x01) << 2);
+		return (*ubh_get_addr (ubh, begin + (block >> 1)) & mask) == mask;
 	case 2:
-		return (*ubh_get_addr (ubh, begin + (block >> 2)) == (0x03 << ((block & 0x03) << 1)));
+		mask = 0x03 << ((block & 0x03) << 1);
+		return (*ubh_get_addr (ubh, begin + (block >> 2)) & mask) == mask;
 	case 1:
-		return (*ubh_get_addr (ubh, begin + (block >> 3)) == (0x01 << (block & 0x07)));
+		mask = 0x01 << (block & 0x07);
+		return (*ubh_get_addr (ubh, begin + (block >> 3)) & mask) == mask;
 	}
 	return 0;	
 }
diff --git a/fs/userfaultfd.c b/fs/userfaultfd.c
index 43953e03c356..cadcd12a3d35 100644
--- a/fs/userfaultfd.c
+++ b/fs/userfaultfd.c
@@ -12,8 +12,10 @@
  *  mm/ksm.c (mm hashing).
  */
 
+#include <linux/list.h>
 #include <linux/hashtable.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
+#include <linux/sched/mm.h>
 #include <linux/mm.h>
 #include <linux/poll.h>
 #include <linux/slab.h>
@@ -26,6 +28,7 @@
 #include <linux/mempolicy.h>
 #include <linux/ioctl.h>
 #include <linux/security.h>
+#include <linux/hugetlb.h>
 
 static struct kmem_cache *userfaultfd_ctx_cachep __read_mostly;
 
@@ -45,12 +48,16 @@ struct userfaultfd_ctx {
 	wait_queue_head_t fault_wqh;
 	/* waitqueue head for the pseudo fd to wakeup poll/read */
 	wait_queue_head_t fd_wqh;
+	/* waitqueue head for events */
+	wait_queue_head_t event_wqh;
 	/* a refile sequence protected by fault_pending_wqh lock */
 	struct seqcount refile_seq;
 	/* pseudo fd refcounting */
 	atomic_t refcount;
 	/* userfaultfd syscall flags */
 	unsigned int flags;
+	/* features requested from the userspace */
+	unsigned int features;
 	/* state machine */
 	enum userfaultfd_state state;
 	/* released */
@@ -59,9 +66,22 @@ struct userfaultfd_ctx {
 	struct mm_struct *mm;
 };
 
+struct userfaultfd_fork_ctx {
+	struct userfaultfd_ctx *orig;
+	struct userfaultfd_ctx *new;
+	struct list_head list;
+};
+
+struct userfaultfd_unmap_ctx {
+	struct userfaultfd_ctx *ctx;
+	unsigned long start;
+	unsigned long end;
+	struct list_head list;
+};
+
 struct userfaultfd_wait_queue {
 	struct uffd_msg msg;
-	wait_queue_t wq;
+	wait_queue_entry_t wq;
 	struct userfaultfd_ctx *ctx;
 	bool waken;
 };
@@ -71,7 +91,7 @@ struct userfaultfd_wake_range {
 	unsigned long len;
 };
 
-static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode,
+static int userfaultfd_wake_function(wait_queue_entry_t *wq, unsigned mode,
 				     int wake_flags, void *key)
 {
 	struct userfaultfd_wake_range *range = key;
@@ -109,7 +129,7 @@ static int userfaultfd_wake_function(wait_queue_t *wq, unsigned mode,
 		 * wouldn't be enough, the smp_mb__before_spinlock is
 		 * enough to avoid an explicit smp_mb() here.
 		 */
-		list_del_init(&wq->task_list);
+		list_del_init(&wq->entry);
 out:
 	return ret;
 }
@@ -118,8 +138,6 @@ out:
  * userfaultfd_ctx_get - Acquires a reference to the internal userfaultfd
  * context.
  * @ctx: [in] Pointer to the userfaultfd context.
- *
- * Returns: In case of success, returns not zero.
  */
 static void userfaultfd_ctx_get(struct userfaultfd_ctx *ctx)
 {
@@ -142,6 +160,8 @@ static void userfaultfd_ctx_put(struct userfaultfd_ctx *ctx)
 		VM_BUG_ON(waitqueue_active(&ctx->fault_pending_wqh));
 		VM_BUG_ON(spin_is_locked(&ctx->fault_wqh.lock));
 		VM_BUG_ON(waitqueue_active(&ctx->fault_wqh));
+		VM_BUG_ON(spin_is_locked(&ctx->event_wqh.lock));
+		VM_BUG_ON(waitqueue_active(&ctx->event_wqh));
 		VM_BUG_ON(spin_is_locked(&ctx->fd_wqh.lock));
 		VM_BUG_ON(waitqueue_active(&ctx->fd_wqh));
 		mmdrop(ctx->mm);
@@ -169,7 +189,7 @@ static inline struct uffd_msg userfault_msg(unsigned long address,
 	msg.arg.pagefault.address = address;
 	if (flags & FAULT_FLAG_WRITE)
 		/*
-		 * If UFFD_FEATURE_PAGEFAULT_FLAG_WRITE was set in the
+		 * If UFFD_FEATURE_PAGEFAULT_FLAG_WP was set in the
 		 * uffdio_api.features and UFFD_PAGEFAULT_FLAG_WRITE
 		 * was not set in a UFFD_EVENT_PAGEFAULT, it means it
 		 * was a read fault, otherwise if set it means it's
@@ -188,6 +208,51 @@ static inline struct uffd_msg userfault_msg(unsigned long address,
 	return msg;
 }
 
+#ifdef CONFIG_HUGETLB_PAGE
+/*
+ * Same functionality as userfaultfd_must_wait below with modifications for
+ * hugepmd ranges.
+ */
+static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
+					 struct vm_area_struct *vma,
+					 unsigned long address,
+					 unsigned long flags,
+					 unsigned long reason)
+{
+	struct mm_struct *mm = ctx->mm;
+	pte_t *pte;
+	bool ret = true;
+
+	VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
+
+	pte = huge_pte_offset(mm, address, vma_mmu_pagesize(vma));
+	if (!pte)
+		goto out;
+
+	ret = false;
+
+	/*
+	 * Lockless access: we're in a wait_event so it's ok if it
+	 * changes under us.
+	 */
+	if (huge_pte_none(*pte))
+		ret = true;
+	if (!huge_pte_write(*pte) && (reason & VM_UFFD_WP))
+		ret = true;
+out:
+	return ret;
+}
+#else
+static inline bool userfaultfd_huge_must_wait(struct userfaultfd_ctx *ctx,
+					 struct vm_area_struct *vma,
+					 unsigned long address,
+					 unsigned long flags,
+					 unsigned long reason)
+{
+	return false;	/* should never get here */
+}
+#endif /* CONFIG_HUGETLB_PAGE */
+
 /*
  * Verify the pagetables are still not ok after having reigstered into
  * the fault_pending_wqh to avoid userland having to UFFDIO_WAKE any
@@ -202,6 +267,7 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 {
 	struct mm_struct *mm = ctx->mm;
 	pgd_t *pgd;
+	p4d_t *p4d;
 	pud_t *pud;
 	pmd_t *pmd, _pmd;
 	pte_t *pte;
@@ -212,7 +278,10 @@ static inline bool userfaultfd_must_wait(struct userfaultfd_ctx *ctx,
 	pgd = pgd_offset(mm, address);
 	if (!pgd_present(*pgd))
 		goto out;
-	pud = pud_offset(pgd, address);
+	p4d = p4d_offset(pgd, address);
+	if (!p4d_present(*p4d))
+		goto out;
+	pud = pud_offset(p4d, address);
 	if (!pud_present(*pud))
 		goto out;
 	pmd = pmd_offset(pud, address);
@@ -273,9 +342,28 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	bool must_wait, return_to_userland;
 	long blocking_state;
 
-	BUG_ON(!rwsem_is_locked(&mm->mmap_sem));
-
 	ret = VM_FAULT_SIGBUS;
+
+	/*
+	 * We don't do userfault handling for the final child pid update.
+	 *
+	 * We also don't do userfault handling during
+	 * coredumping. hugetlbfs has the special
+	 * follow_hugetlb_page() to skip missing pages in the
+	 * FOLL_DUMP case, anon memory also checks for FOLL_DUMP with
+	 * the no_page_table() helper in follow_page_mask(), but the
+	 * shmem_vm_ops->fault method is invoked even during
+	 * coredumping without mmap_sem and it ends up here.
+	 */
+	if (current->flags & (PF_EXITING|PF_DUMPCORE))
+		goto out;
+
+	/*
+	 * Coredumping runs without mmap_sem so we can only check that
+	 * the mmap_sem is held, if PF_DUMPCORE was not set.
+	 */
+	WARN_ON_ONCE(!rwsem_is_locked(&mm->mmap_sem));
+
 	ctx = vmf->vma->vm_userfaultfd_ctx.ctx;
 	if (!ctx)
 		goto out;
@@ -294,12 +382,6 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 		goto out;
 
 	/*
-	 * We don't do userfault handling for the final child pid update.
-	 */
-	if (current->flags & PF_EXITING)
-		goto out;
-
-	/*
 	 * Check that we can return VM_FAULT_RETRY.
 	 *
 	 * NOTE: it should become possible to return VM_FAULT_RETRY
@@ -364,8 +446,13 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	set_current_state(blocking_state);
 	spin_unlock(&ctx->fault_pending_wqh.lock);
 
-	must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
-					  reason);
+	if (!is_vm_hugetlb_page(vmf->vma))
+		must_wait = userfaultfd_must_wait(ctx, vmf->address, vmf->flags,
+						  reason);
+	else
+		must_wait = userfaultfd_huge_must_wait(ctx, vmf->vma,
+						       vmf->address,
+						       vmf->flags, reason);
 	up_read(&mm->mmap_sem);
 
 	if (likely(must_wait && !ACCESS_ONCE(ctx->released) &&
@@ -421,7 +508,7 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 			 * in such case.
 			 */
 			down_read(&mm->mmap_sem);
-			ret = 0;
+			ret = VM_FAULT_NOPAGE;
 		}
 	}
 
@@ -438,13 +525,13 @@ int handle_userfault(struct vm_fault *vmf, unsigned long reason)
 	 * and it's fine not to block on the spinlock. The uwq on this
 	 * kernel stack can be released after the list_del_init.
 	 */
-	if (!list_empty_careful(&uwq.wq.task_list)) {
+	if (!list_empty_careful(&uwq.wq.entry)) {
 		spin_lock(&ctx->fault_pending_wqh.lock);
 		/*
 		 * No need of list_del_init(), the uwq on the stack
 		 * will be freed shortly anyway.
 		 */
-		list_del(&uwq.wq.task_list);
+		list_del(&uwq.wq.entry);
 		spin_unlock(&ctx->fault_pending_wqh.lock);
 	}
 
@@ -458,6 +545,257 @@ out:
 	return ret;
 }
 
+static void userfaultfd_event_wait_completion(struct userfaultfd_ctx *ctx,
+					      struct userfaultfd_wait_queue *ewq)
+{
+	if (WARN_ON_ONCE(current->flags & PF_EXITING))
+		goto out;
+
+	ewq->ctx = ctx;
+	init_waitqueue_entry(&ewq->wq, current);
+
+	spin_lock(&ctx->event_wqh.lock);
+	/*
+	 * After the __add_wait_queue the uwq is visible to userland
+	 * through poll/read().
+	 */
+	__add_wait_queue(&ctx->event_wqh, &ewq->wq);
+	for (;;) {
+		set_current_state(TASK_KILLABLE);
+		if (ewq->msg.event == 0)
+			break;
+		if (ACCESS_ONCE(ctx->released) ||
+		    fatal_signal_pending(current)) {
+			__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
+			if (ewq->msg.event == UFFD_EVENT_FORK) {
+				struct userfaultfd_ctx *new;
+
+				new = (struct userfaultfd_ctx *)
+					(unsigned long)
+					ewq->msg.arg.reserved.reserved1;
+
+				userfaultfd_ctx_put(new);
+			}
+			break;
+		}
+
+		spin_unlock(&ctx->event_wqh.lock);
+
+		wake_up_poll(&ctx->fd_wqh, POLLIN);
+		schedule();
+
+		spin_lock(&ctx->event_wqh.lock);
+	}
+	__set_current_state(TASK_RUNNING);
+	spin_unlock(&ctx->event_wqh.lock);
+
+	/*
+	 * ctx may go away after this if the userfault pseudo fd is
+	 * already released.
+	 */
+out:
+	userfaultfd_ctx_put(ctx);
+}
+
+static void userfaultfd_event_complete(struct userfaultfd_ctx *ctx,
+				       struct userfaultfd_wait_queue *ewq)
+{
+	ewq->msg.event = 0;
+	wake_up_locked(&ctx->event_wqh);
+	__remove_wait_queue(&ctx->event_wqh, &ewq->wq);
+}
+
+int dup_userfaultfd(struct vm_area_struct *vma, struct list_head *fcs)
+{
+	struct userfaultfd_ctx *ctx = NULL, *octx;
+	struct userfaultfd_fork_ctx *fctx;
+
+	octx = vma->vm_userfaultfd_ctx.ctx;
+	if (!octx || !(octx->features & UFFD_FEATURE_EVENT_FORK)) {
+		vma->vm_userfaultfd_ctx = NULL_VM_UFFD_CTX;
+		vma->vm_flags &= ~(VM_UFFD_WP | VM_UFFD_MISSING);
+		return 0;
+	}
+
+	list_for_each_entry(fctx, fcs, list)
+		if (fctx->orig == octx) {
+			ctx = fctx->new;
+			break;
+		}
+
+	if (!ctx) {
+		fctx = kmalloc(sizeof(*fctx), GFP_KERNEL);
+		if (!fctx)
+			return -ENOMEM;
+
+		ctx = kmem_cache_alloc(userfaultfd_ctx_cachep, GFP_KERNEL);
+		if (!ctx) {
+			kfree(fctx);
+			return -ENOMEM;
+		}
+
+		atomic_set(&ctx->refcount, 1);
+		ctx->flags = octx->flags;
+		ctx->state = UFFD_STATE_RUNNING;
+		ctx->features = octx->features;
+		ctx->released = false;
+		ctx->mm = vma->vm_mm;
+		atomic_inc(&ctx->mm->mm_count);
+
+		userfaultfd_ctx_get(octx);
+		fctx->orig = octx;
+		fctx->new = ctx;
+		list_add_tail(&fctx->list, fcs);
+	}
+
+	vma->vm_userfaultfd_ctx.ctx = ctx;
+	return 0;
+}
+
+static void dup_fctx(struct userfaultfd_fork_ctx *fctx)
+{
+	struct userfaultfd_ctx *ctx = fctx->orig;
+	struct userfaultfd_wait_queue ewq;
+
+	msg_init(&ewq.msg);
+
+	ewq.msg.event = UFFD_EVENT_FORK;
+	ewq.msg.arg.reserved.reserved1 = (unsigned long)fctx->new;
+
+	userfaultfd_event_wait_completion(ctx, &ewq);
+}
+
+void dup_userfaultfd_complete(struct list_head *fcs)
+{
+	struct userfaultfd_fork_ctx *fctx, *n;
+
+	list_for_each_entry_safe(fctx, n, fcs, list) {
+		dup_fctx(fctx);
+		list_del(&fctx->list);
+		kfree(fctx);
+	}
+}
+
+void mremap_userfaultfd_prep(struct vm_area_struct *vma,
+			     struct vm_userfaultfd_ctx *vm_ctx)
+{
+	struct userfaultfd_ctx *ctx;
+
+	ctx = vma->vm_userfaultfd_ctx.ctx;
+	if (ctx && (ctx->features & UFFD_FEATURE_EVENT_REMAP)) {
+		vm_ctx->ctx = ctx;
+		userfaultfd_ctx_get(ctx);
+	}
+}
+
+void mremap_userfaultfd_complete(struct vm_userfaultfd_ctx *vm_ctx,
+				 unsigned long from, unsigned long to,
+				 unsigned long len)
+{
+	struct userfaultfd_ctx *ctx = vm_ctx->ctx;
+	struct userfaultfd_wait_queue ewq;
+
+	if (!ctx)
+		return;
+
+	if (to & ~PAGE_MASK) {
+		userfaultfd_ctx_put(ctx);
+		return;
+	}
+
+	msg_init(&ewq.msg);
+
+	ewq.msg.event = UFFD_EVENT_REMAP;
+	ewq.msg.arg.remap.from = from;
+	ewq.msg.arg.remap.to = to;
+	ewq.msg.arg.remap.len = len;
+
+	userfaultfd_event_wait_completion(ctx, &ewq);
+}
+
+bool userfaultfd_remove(struct vm_area_struct *vma,
+			unsigned long start, unsigned long end)
+{
+	struct mm_struct *mm = vma->vm_mm;
+	struct userfaultfd_ctx *ctx;
+	struct userfaultfd_wait_queue ewq;
+
+	ctx = vma->vm_userfaultfd_ctx.ctx;
+	if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_REMOVE))
+		return true;
+
+	userfaultfd_ctx_get(ctx);
+	up_read(&mm->mmap_sem);
+
+	msg_init(&ewq.msg);
+
+	ewq.msg.event = UFFD_EVENT_REMOVE;
+	ewq.msg.arg.remove.start = start;
+	ewq.msg.arg.remove.end = end;
+
+	userfaultfd_event_wait_completion(ctx, &ewq);
+
+	return false;
+}
+
+static bool has_unmap_ctx(struct userfaultfd_ctx *ctx, struct list_head *unmaps,
+			  unsigned long start, unsigned long end)
+{
+	struct userfaultfd_unmap_ctx *unmap_ctx;
+
+	list_for_each_entry(unmap_ctx, unmaps, list)
+		if (unmap_ctx->ctx == ctx && unmap_ctx->start == start &&
+		    unmap_ctx->end == end)
+			return true;
+
+	return false;
+}
+
+int userfaultfd_unmap_prep(struct vm_area_struct *vma,
+			   unsigned long start, unsigned long end,
+			   struct list_head *unmaps)
+{
+	for ( ; vma && vma->vm_start < end; vma = vma->vm_next) {
+		struct userfaultfd_unmap_ctx *unmap_ctx;
+		struct userfaultfd_ctx *ctx = vma->vm_userfaultfd_ctx.ctx;
+
+		if (!ctx || !(ctx->features & UFFD_FEATURE_EVENT_UNMAP) ||
+		    has_unmap_ctx(ctx, unmaps, start, end))
+			continue;
+
+		unmap_ctx = kzalloc(sizeof(*unmap_ctx), GFP_KERNEL);
+		if (!unmap_ctx)
+			return -ENOMEM;
+
+		userfaultfd_ctx_get(ctx);
+		unmap_ctx->ctx = ctx;
+		unmap_ctx->start = start;
+		unmap_ctx->end = end;
+		list_add_tail(&unmap_ctx->list, unmaps);
+	}
+
+	return 0;
+}
+
+void userfaultfd_unmap_complete(struct mm_struct *mm, struct list_head *uf)
+{
+	struct userfaultfd_unmap_ctx *ctx, *n;
+	struct userfaultfd_wait_queue ewq;
+
+	list_for_each_entry_safe(ctx, n, uf, list) {
+		msg_init(&ewq.msg);
+
+		ewq.msg.event = UFFD_EVENT_UNMAP;
+		ewq.msg.arg.remove.start = ctx->start;
+		ewq.msg.arg.remove.end = ctx->end;
+
+		userfaultfd_event_wait_completion(ctx->ctx, &ewq);
+
+		list_del(&ctx->list);
+		kfree(ctx);
+	}
+}
+
 static int userfaultfd_release(struct inode *inode, struct file *file)
 {
 	struct userfaultfd_ctx *ctx = file->private_data;
@@ -522,25 +860,36 @@ wakeup:
 }
 
 /* fault_pending_wqh.lock must be hold by the caller */
-static inline struct userfaultfd_wait_queue *find_userfault(
-	struct userfaultfd_ctx *ctx)
+static inline struct userfaultfd_wait_queue *find_userfault_in(
+		wait_queue_head_t *wqh)
 {
-	wait_queue_t *wq;
+	wait_queue_entry_t *wq;
 	struct userfaultfd_wait_queue *uwq;
 
-	VM_BUG_ON(!spin_is_locked(&ctx->fault_pending_wqh.lock));
+	VM_BUG_ON(!spin_is_locked(&wqh->lock));
 
 	uwq = NULL;
-	if (!waitqueue_active(&ctx->fault_pending_wqh))
+	if (!waitqueue_active(wqh))
 		goto out;
 	/* walk in reverse to provide FIFO behavior to read userfaults */
-	wq = list_last_entry(&ctx->fault_pending_wqh.task_list,
-			     typeof(*wq), task_list);
+	wq = list_last_entry(&wqh->head, typeof(*wq), entry);
 	uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
 out:
 	return uwq;
 }
 
+static inline struct userfaultfd_wait_queue *find_userfault(
+		struct userfaultfd_ctx *ctx)
+{
+	return find_userfault_in(&ctx->fault_pending_wqh);
+}
+
+static inline struct userfaultfd_wait_queue *find_userfault_evt(
+		struct userfaultfd_ctx *ctx)
+{
+	return find_userfault_in(&ctx->event_wqh);
+}
+
 static unsigned int userfaultfd_poll(struct file *file, poll_table *wait)
 {
 	struct userfaultfd_ctx *ctx = file->private_data;
@@ -572,18 +921,59 @@ static unsigned int userfaultfd_poll(struct file *file, poll_table *wait)
 		smp_mb();
 		if (waitqueue_active(&ctx->fault_pending_wqh))
 			ret = POLLIN;
+		else if (waitqueue_active(&ctx->event_wqh))
+			ret = POLLIN;
+
 		return ret;
 	default:
-		BUG();
+		WARN_ON_ONCE(1);
+		return POLLERR;
 	}
 }
 
+static const struct file_operations userfaultfd_fops;
+
+static int resolve_userfault_fork(struct userfaultfd_ctx *ctx,
+				  struct userfaultfd_ctx *new,
+				  struct uffd_msg *msg)
+{
+	int fd;
+	struct file *file;
+	unsigned int flags = new->flags & UFFD_SHARED_FCNTL_FLAGS;
+
+	fd = get_unused_fd_flags(flags);
+	if (fd < 0)
+		return fd;
+
+	file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, new,
+				  O_RDWR | flags);
+	if (IS_ERR(file)) {
+		put_unused_fd(fd);
+		return PTR_ERR(file);
+	}
+
+	fd_install(fd, file);
+	msg->arg.reserved.reserved1 = 0;
+	msg->arg.fork.ufd = fd;
+
+	return 0;
+}
+
 static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 				    struct uffd_msg *msg)
 {
 	ssize_t ret;
 	DECLARE_WAITQUEUE(wait, current);
 	struct userfaultfd_wait_queue *uwq;
+	/*
+	 * Handling fork event requires sleeping operations, so
+	 * we drop the event_wqh lock, then do these ops, then
+	 * lock it back and wake up the waiter. While the lock is
+	 * dropped the ewq may go away so we keep track of it
+	 * carefully.
+	 */
+	LIST_HEAD(fork_event);
+	struct userfaultfd_ctx *fork_nctx = NULL;
 
 	/* always take the fd_wqh lock before the fault_pending_wqh lock */
 	spin_lock(&ctx->fd_wqh.lock);
@@ -616,14 +1006,14 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 			 * changes __remove_wait_queue() to use
 			 * list_del_init() in turn breaking the
 			 * !list_empty_careful() check in
-			 * handle_userfault(). The uwq->wq.task_list
+			 * handle_userfault(). The uwq->wq.head list
 			 * must never be empty at any time during the
 			 * refile, or the waitqueue could disappear
 			 * from under us. The "wait_queue_head_t"
 			 * parameter of __remove_wait_queue() is unused
 			 * anyway.
 			 */
-			list_del(&uwq->wq.task_list);
+			list_del(&uwq->wq.entry);
 			__add_wait_queue(&ctx->fault_wqh, &uwq->wq);
 
 			write_seqcount_end(&ctx->refile_seq);
@@ -635,6 +1025,29 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 			break;
 		}
 		spin_unlock(&ctx->fault_pending_wqh.lock);
+
+		spin_lock(&ctx->event_wqh.lock);
+		uwq = find_userfault_evt(ctx);
+		if (uwq) {
+			*msg = uwq->msg;
+
+			if (uwq->msg.event == UFFD_EVENT_FORK) {
+				fork_nctx = (struct userfaultfd_ctx *)
+					(unsigned long)
+					uwq->msg.arg.reserved.reserved1;
+				list_move(&uwq->wq.entry, &fork_event);
+				spin_unlock(&ctx->event_wqh.lock);
+				ret = 0;
+				break;
+			}
+
+			userfaultfd_event_complete(ctx, uwq);
+			spin_unlock(&ctx->event_wqh.lock);
+			ret = 0;
+			break;
+		}
+		spin_unlock(&ctx->event_wqh.lock);
+
 		if (signal_pending(current)) {
 			ret = -ERESTARTSYS;
 			break;
@@ -651,6 +1064,23 @@ static ssize_t userfaultfd_ctx_read(struct userfaultfd_ctx *ctx, int no_wait,
 	__set_current_state(TASK_RUNNING);
 	spin_unlock(&ctx->fd_wqh.lock);
 
+	if (!ret && msg->event == UFFD_EVENT_FORK) {
+		ret = resolve_userfault_fork(ctx, fork_nctx, msg);
+
+		if (!ret) {
+			spin_lock(&ctx->event_wqh.lock);
+			if (!list_empty(&fork_event)) {
+				uwq = list_first_entry(&fork_event,
+						       typeof(*uwq),
+						       wq.entry);
+				list_del(&uwq->wq.entry);
+				__add_wait_queue(&ctx->event_wqh, &uwq->wq);
+				userfaultfd_event_complete(ctx, uwq);
+			}
+			spin_unlock(&ctx->event_wqh.lock);
+		}
+	}
+
 	return ret;
 }
 
@@ -687,11 +1117,6 @@ static ssize_t userfaultfd_read(struct file *file, char __user *buf,
 static void __wake_userfault(struct userfaultfd_ctx *ctx,
 			     struct userfaultfd_wake_range *range)
 {
-	unsigned long start, end;
-
-	start = range->start;
-	end = range->start + range->len;
-
 	spin_lock(&ctx->fault_pending_wqh.lock);
 	/* wake all in the range and autoremove */
 	if (waitqueue_active(&ctx->fault_pending_wqh))
@@ -753,6 +1178,12 @@ static __always_inline int validate_range(struct mm_struct *mm,
 	return 0;
 }
 
+static inline bool vma_can_userfault(struct vm_area_struct *vma)
+{
+	return vma_is_anonymous(vma) || is_vm_hugetlb_page(vma) ||
+		vma_is_shmem(vma);
+}
+
 static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 				unsigned long arg)
 {
@@ -763,6 +1194,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	struct uffdio_register __user *user_uffdio_register;
 	unsigned long vm_flags, new_flags;
 	bool found;
+	bool non_anon_pages;
 	unsigned long start, end, vma_end;
 
 	user_uffdio_register = (struct uffdio_register __user *) arg;
@@ -814,13 +1246,21 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		goto out_unlock;
 
 	/*
+	 * If the first vma contains huge pages, make sure start address
+	 * is aligned to huge page size.
+	 */
+	if (is_vm_hugetlb_page(vma)) {
+		unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
+
+		if (start & (vma_hpagesize - 1))
+			goto out_unlock;
+	}
+
+	/*
 	 * Search for not compatible vmas.
-	 *
-	 * FIXME: this shall be relaxed later so that it doesn't fail
-	 * on tmpfs backed vmas (in addition to the current allowance
-	 * on anonymous vmas).
 	 */
 	found = false;
+	non_anon_pages = false;
 	for (cur = vma; cur && cur->vm_start < end; cur = cur->vm_next) {
 		cond_resched();
 
@@ -829,8 +1269,21 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 
 		/* check not compatible vmas */
 		ret = -EINVAL;
-		if (cur->vm_ops)
+		if (!vma_can_userfault(cur))
 			goto out_unlock;
+		/*
+		 * If this vma contains ending address, and huge pages
+		 * check alignment.
+		 */
+		if (is_vm_hugetlb_page(cur) && end <= cur->vm_end &&
+		    end > cur->vm_start) {
+			unsigned long vma_hpagesize = vma_kernel_pagesize(cur);
+
+			ret = -EINVAL;
+
+			if (end & (vma_hpagesize - 1))
+				goto out_unlock;
+		}
 
 		/*
 		 * Check that this vma isn't already owned by a
@@ -843,6 +1296,12 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 		    cur->vm_userfaultfd_ctx.ctx != ctx)
 			goto out_unlock;
 
+		/*
+		 * Note vmas containing huge pages
+		 */
+		if (is_vm_hugetlb_page(cur) || vma_is_shmem(cur))
+			non_anon_pages = true;
+
 		found = true;
 	}
 	BUG_ON(!found);
@@ -854,7 +1313,7 @@ static int userfaultfd_register(struct userfaultfd_ctx *ctx,
 	do {
 		cond_resched();
 
-		BUG_ON(vma->vm_ops);
+		BUG_ON(!vma_can_userfault(vma));
 		BUG_ON(vma->vm_userfaultfd_ctx.ctx &&
 		       vma->vm_userfaultfd_ctx.ctx != ctx);
 
@@ -912,7 +1371,8 @@ out_unlock:
 		 * userland which ioctls methods are guaranteed to
 		 * succeed on this range.
 		 */
-		if (put_user(UFFD_API_RANGE_IOCTLS,
+		if (put_user(non_anon_pages ? UFFD_API_RANGE_IOCTLS_BASIC :
+			     UFFD_API_RANGE_IOCTLS,
 			     &user_uffdio_register->ioctls))
 			ret = -EFAULT;
 	}
@@ -959,11 +1419,18 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		goto out_unlock;
 
 	/*
+	 * If the first vma contains huge pages, make sure start address
+	 * is aligned to huge page size.
+	 */
+	if (is_vm_hugetlb_page(vma)) {
+		unsigned long vma_hpagesize = vma_kernel_pagesize(vma);
+
+		if (start & (vma_hpagesize - 1))
+			goto out_unlock;
+	}
+
+	/*
 	 * Search for not compatible vmas.
-	 *
-	 * FIXME: this shall be relaxed later so that it doesn't fail
-	 * on tmpfs backed vmas (in addition to the current allowance
-	 * on anonymous vmas).
 	 */
 	found = false;
 	ret = -EINVAL;
@@ -980,7 +1447,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 		 * provides for more strict behavior to notice
 		 * unregistration errors.
 		 */
-		if (cur->vm_ops)
+		if (!vma_can_userfault(cur))
 			goto out_unlock;
 
 		found = true;
@@ -994,7 +1461,7 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 	do {
 		cond_resched();
 
-		BUG_ON(vma->vm_ops);
+		BUG_ON(!vma_can_userfault(vma));
 
 		/*
 		 * Nothing to do: this vma is already registered into this
@@ -1007,6 +1474,19 @@ static int userfaultfd_unregister(struct userfaultfd_ctx *ctx,
 			start = vma->vm_start;
 		vma_end = min(end, vma->vm_end);
 
+		if (userfaultfd_missing(vma)) {
+			/*
+			 * Wake any concurrent pending userfault while
+			 * we unregister, so they will not hang
+			 * permanently and it avoids userland to call
+			 * UFFDIO_WAKE explicitly.
+			 */
+			struct userfaultfd_wake_range range;
+			range.start = start;
+			range.len = vma_end - start;
+			wake_userfault(vma->vm_userfaultfd_ctx.ctx, &range);
+		}
+
 		new_flags = vma->vm_flags & ~(VM_UFFD_MISSING | VM_UFFD_WP);
 		prev = vma_merge(mm, prev, start, vma_end, new_flags,
 				 vma->anon_vma, vma->vm_file, vma->vm_pgoff,
@@ -1116,6 +1596,8 @@ static int userfaultfd_copy(struct userfaultfd_ctx *ctx,
 		ret = mcopy_atomic(ctx->mm, uffdio_copy.dst, uffdio_copy.src,
 				   uffdio_copy.len);
 		mmput(ctx->mm);
+	} else {
+		return -ENOSPC;
 	}
 	if (unlikely(put_user(ret, &user_uffdio_copy->copy)))
 		return -EFAULT;
@@ -1178,6 +1660,14 @@ out:
 	return ret;
 }
 
+static inline unsigned int uffd_ctx_features(__u64 user_features)
+{
+	/*
+	 * For the current set of features the bits just coincide
+	 */
+	return (unsigned int)user_features;
+}
+
 /*
  * userland asks for a certain API version and we return which bits
  * and ioctl commands are implemented in this kernel for such API
@@ -1189,6 +1679,7 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 	struct uffdio_api uffdio_api;
 	void __user *buf = (void __user *)arg;
 	int ret;
+	__u64 features;
 
 	ret = -EINVAL;
 	if (ctx->state != UFFD_STATE_WAIT_API)
@@ -1196,19 +1687,23 @@ static int userfaultfd_api(struct userfaultfd_ctx *ctx,
 	ret = -EFAULT;
 	if (copy_from_user(&uffdio_api, buf, sizeof(uffdio_api)))
 		goto out;
-	if (uffdio_api.api != UFFD_API || uffdio_api.features) {
+	features = uffdio_api.features;
+	if (uffdio_api.api != UFFD_API || (features & ~UFFD_API_FEATURES)) {
 		memset(&uffdio_api, 0, sizeof(uffdio_api));
 		if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
 			goto out;
 		ret = -EINVAL;
 		goto out;
 	}
+	/* report all available features and ioctls to userland */
 	uffdio_api.features = UFFD_API_FEATURES;
 	uffdio_api.ioctls = UFFD_API_IOCTLS;
 	ret = -EFAULT;
 	if (copy_to_user(buf, &uffdio_api, sizeof(uffdio_api)))
 		goto out;
 	ctx->state = UFFD_STATE_RUNNING;
+	/* only enable the requested features for this uffd context */
+	ctx->features = uffd_ctx_features(features);
 	ret = 0;
 out:
 	return ret;
@@ -1250,17 +1745,17 @@ static long userfaultfd_ioctl(struct file *file, unsigned cmd,
 static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f)
 {
 	struct userfaultfd_ctx *ctx = f->private_data;
-	wait_queue_t *wq;
+	wait_queue_entry_t *wq;
 	struct userfaultfd_wait_queue *uwq;
 	unsigned long pending = 0, total = 0;
 
 	spin_lock(&ctx->fault_pending_wqh.lock);
-	list_for_each_entry(wq, &ctx->fault_pending_wqh.task_list, task_list) {
+	list_for_each_entry(wq, &ctx->fault_pending_wqh.head, entry) {
 		uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
 		pending++;
 		total++;
 	}
-	list_for_each_entry(wq, &ctx->fault_wqh.task_list, task_list) {
+	list_for_each_entry(wq, &ctx->fault_wqh.head, entry) {
 		uwq = container_of(wq, struct userfaultfd_wait_queue, wq);
 		total++;
 	}
@@ -1272,7 +1767,7 @@ static void userfaultfd_show_fdinfo(struct seq_file *m, struct file *f)
 	 *	protocols: aa:... bb:...
 	 */
 	seq_printf(m, "pending:\t%lu\ntotal:\t%lu\nAPI:\t%Lx:%x:%Lx\n",
-		   pending, total, UFFD_API, UFFD_API_FEATURES,
+		   pending, total, UFFD_API, ctx->features,
 		   UFFD_API_IOCTLS|UFFD_API_RANGE_IOCTLS);
 }
 #endif
@@ -1295,22 +1790,23 @@ static void init_once_userfaultfd_ctx(void *mem)
 
 	init_waitqueue_head(&ctx->fault_pending_wqh);
 	init_waitqueue_head(&ctx->fault_wqh);
+	init_waitqueue_head(&ctx->event_wqh);
 	init_waitqueue_head(&ctx->fd_wqh);
 	seqcount_init(&ctx->refile_seq);
 }
 
 /**
- * userfaultfd_file_create - Creates an userfaultfd file pointer.
+ * userfaultfd_file_create - Creates a userfaultfd file pointer.
  * @flags: Flags for the userfaultfd file.
  *
- * This function creates an userfaultfd file pointer, w/out installing
+ * This function creates a userfaultfd file pointer, w/out installing
  * it into the fd table. This is useful when the userfaultfd file is
  * used during the initialization of data structures that require
  * extra setup after the userfaultfd creation. So the userfaultfd
  * creation is split into the file pointer creation phase, and the
  * file descriptor installation phase.  In this way races with
  * userspace closing the newly installed file descriptor can be
- * avoided.  Returns an userfaultfd file pointer, or a proper error
+ * avoided.  Returns a userfaultfd file pointer, or a proper error
  * pointer.
  */
 static struct file *userfaultfd_file_create(int flags)
@@ -1335,11 +1831,12 @@ static struct file *userfaultfd_file_create(int flags)
 
 	atomic_set(&ctx->refcount, 1);
 	ctx->flags = flags;
+	ctx->features = 0;
 	ctx->state = UFFD_STATE_WAIT_API;
 	ctx->released = false;
 	ctx->mm = current->mm;
 	/* prevent the mm struct to be freed */
-	atomic_inc(&ctx->mm->mm_count);
+	mmgrab(ctx->mm);
 
 	file = anon_inode_getfile("[userfaultfd]", &userfaultfd_fops, ctx,
 				  O_RDWR | (flags & UFFD_SHARED_FCNTL_FLAGS));
diff --git a/fs/utimes.c b/fs/utimes.c
index 32b15b3f6629..6571d8c848a0 100644
--- a/fs/utimes.c
+++ b/fs/utimes.c
@@ -1,14 +1,10 @@
-#include <linux/compiler.h>
 #include <linux/file.h>
-#include <linux/fs.h>
-#include <linux/linkage.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
-#include <linux/sched.h>
-#include <linux/stat.h>
 #include <linux/utime.h>
 #include <linux/syscalls.h>
 #include <linux/uaccess.h>
+#include <linux/compat.h>
 #include <asm/unistd.h>
 
 #ifdef __ARCH_WANT_SYS_UTIME
@@ -219,3 +215,63 @@ SYSCALL_DEFINE2(utimes, char __user *, filename,
 {
 	return sys_futimesat(AT_FDCWD, filename, utimes);
 }
+
+#ifdef CONFIG_COMPAT
+/*
+ * Not all architectures have sys_utime, so implement this in terms
+ * of sys_utimes.
+ */
+COMPAT_SYSCALL_DEFINE2(utime, const char __user *, filename,
+		       struct compat_utimbuf __user *, t)
+{
+	struct timespec tv[2];
+
+	if (t) {
+		if (get_user(tv[0].tv_sec, &t->actime) ||
+		    get_user(tv[1].tv_sec, &t->modtime))
+			return -EFAULT;
+		tv[0].tv_nsec = 0;
+		tv[1].tv_nsec = 0;
+	}
+	return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0);
+}
+
+COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags)
+{
+	struct timespec tv[2];
+
+	if  (t) {
+		if (compat_get_timespec(&tv[0], &t[0]) ||
+		    compat_get_timespec(&tv[1], &t[1]))
+			return -EFAULT;
+
+		if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT)
+			return 0;
+	}
+	return do_utimes(dfd, filename, t ? tv : NULL, flags);
+}
+
+COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t)
+{
+	struct timespec tv[2];
+
+	if (t) {
+		if (get_user(tv[0].tv_sec, &t[0].tv_sec) ||
+		    get_user(tv[0].tv_nsec, &t[0].tv_usec) ||
+		    get_user(tv[1].tv_sec, &t[1].tv_sec) ||
+		    get_user(tv[1].tv_nsec, &t[1].tv_usec))
+			return -EFAULT;
+		if (tv[0].tv_nsec >= 1000000 || tv[0].tv_nsec < 0 ||
+		    tv[1].tv_nsec >= 1000000 || tv[1].tv_nsec < 0)
+			return -EINVAL;
+		tv[0].tv_nsec *= 1000;
+		tv[1].tv_nsec *= 1000;
+	}
+	return do_utimes(dfd, filename, t ? tv : NULL, 0);
+}
+
+COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t)
+{
+	return compat_sys_futimesat(AT_FDCWD, filename, t);
+}
+#endif
diff --git a/fs/xattr.c b/fs/xattr.c
index 7e3317cf4045..464c94bf65f9 100644
--- a/fs/xattr.c
+++ b/fs/xattr.c
@@ -431,12 +431,9 @@ setxattr(struct dentry *d, const char __user *name, const void __user *value,
 	if (size) {
 		if (size > XATTR_SIZE_MAX)
 			return -E2BIG;
-		kvalue = kmalloc(size, GFP_KERNEL | __GFP_NOWARN);
-		if (!kvalue) {
-			kvalue = vmalloc(size);
-			if (!kvalue)
-				return -ENOMEM;
-		}
+		kvalue = kvmalloc(size, GFP_KERNEL);
+		if (!kvalue)
+			return -ENOMEM;
 		if (copy_from_user(kvalue, value, size)) {
 			error = -EFAULT;
 			goto out;
@@ -528,12 +525,9 @@ getxattr(struct dentry *d, const char __user *name, void __user *value,
 	if (size) {
 		if (size > XATTR_SIZE_MAX)
 			size = XATTR_SIZE_MAX;
-		kvalue = kzalloc(size, GFP_KERNEL | __GFP_NOWARN);
-		if (!kvalue) {
-			kvalue = vmalloc(size);
-			if (!kvalue)
-				return -ENOMEM;
-		}
+		kvalue = kvzalloc(size, GFP_KERNEL);
+		if (!kvalue)
+			return -ENOMEM;
 	}
 
 	error = vfs_getxattr(d, kname, kvalue, size);
@@ -611,12 +605,9 @@ listxattr(struct dentry *d, char __user *list, size_t size)
 	if (size) {
 		if (size > XATTR_LIST_MAX)
 			size = XATTR_LIST_MAX;
-		klist = kmalloc(size, __GFP_NOWARN | GFP_KERNEL);
-		if (!klist) {
-			klist = vmalloc(size);
-			if (!klist)
-				return -ENOMEM;
-		}
+		klist = kvmalloc(size, GFP_KERNEL);
+		if (!klist)
+			return -ENOMEM;
 	}
 
 	error = vfs_listxattr(d, klist, size);
diff --git a/fs/xfs/Kconfig b/fs/xfs/Kconfig
index 35faf128f36d..1b98cfa342ab 100644
--- a/fs/xfs/Kconfig
+++ b/fs/xfs/Kconfig
@@ -96,3 +96,16 @@ config XFS_DEBUG
 	  not useful unless you are debugging a particular problem.
 
 	  Say N unless you are an XFS developer, or you play one on TV.
+
+config XFS_ASSERT_FATAL
+	bool "XFS fatal asserts"
+	default y
+	depends on XFS_FS && XFS_DEBUG
+	help
+	  Set the default DEBUG mode ASSERT failure behavior.
+
+	  Say Y here to cause DEBUG mode ASSERT failures to result in fatal
+	  errors that BUG() the kernel by default. If you say N, ASSERT failures
+	  result in warnings.
+
+	  This behavior can be modified at runtime via sysfs.
diff --git a/fs/xfs/Makefile b/fs/xfs/Makefile
index 26ef1958b65b..a6e955bfead8 100644
--- a/fs/xfs/Makefile
+++ b/fs/xfs/Makefile
@@ -79,6 +79,7 @@ xfs-y				+= xfs_aops.o \
 				   xfs_extent_busy.o \
 				   xfs_file.o \
 				   xfs_filestream.o \
+				   xfs_fsmap.o \
 				   xfs_fsops.o \
 				   xfs_globals.o \
 				   xfs_icache.o \
@@ -97,8 +98,7 @@ xfs-y				+= xfs_aops.o \
 				   xfs_sysfs.o \
 				   xfs_trans.o \
 				   xfs_xattr.o \
-				   kmem.o \
-				   uuid.o
+				   kmem.o
 
 # low-level transaction/log code
 xfs-y				+= xfs_log.o \
diff --git a/fs/xfs/kmem.c b/fs/xfs/kmem.c
index 339c696bbc01..393b6849aeb3 100644
--- a/fs/xfs/kmem.c
+++ b/fs/xfs/kmem.c
@@ -16,6 +16,7 @@
  * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
  */
 #include <linux/mm.h>
+#include <linux/sched/mm.h>
 #include <linux/highmem.h>
 #include <linux/slab.h>
 #include <linux/swap.h>
@@ -24,24 +25,6 @@
 #include "kmem.h"
 #include "xfs_message.h"
 
-/*
- * Greedy allocation.  May fail and may return vmalloced memory.
- */
-void *
-kmem_zalloc_greedy(size_t *size, size_t minsize, size_t maxsize)
-{
-	void		*ptr;
-	size_t		kmsize = maxsize;
-
-	while (!(ptr = vzalloc(kmsize))) {
-		if ((kmsize >>= 1) <= minsize)
-			kmsize = minsize;
-	}
-	if (ptr)
-		*size = kmsize;
-	return ptr;
-}
-
 void *
 kmem_alloc(size_t size, xfs_km_flags_t flags)
 {
@@ -65,7 +48,7 @@ kmem_alloc(size_t size, xfs_km_flags_t flags)
 void *
 kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
 {
-	unsigned noio_flag = 0;
+	unsigned nofs_flag = 0;
 	void	*ptr;
 	gfp_t	lflags;
 
@@ -77,17 +60,17 @@ kmem_zalloc_large(size_t size, xfs_km_flags_t flags)
 	 * __vmalloc() will allocate data pages and auxillary structures (e.g.
 	 * pagetables) with GFP_KERNEL, yet we may be under GFP_NOFS context
 	 * here. Hence we need to tell memory reclaim that we are in such a
-	 * context via PF_MEMALLOC_NOIO to prevent memory reclaim re-entering
+	 * context via PF_MEMALLOC_NOFS to prevent memory reclaim re-entering
 	 * the filesystem here and potentially deadlocking.
 	 */
-	if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
-		noio_flag = memalloc_noio_save();
+	if (flags & KM_NOFS)
+		nofs_flag = memalloc_nofs_save();
 
 	lflags = kmem_flags_convert(flags);
-	ptr = __vmalloc(size, lflags | __GFP_HIGHMEM | __GFP_ZERO, PAGE_KERNEL);
+	ptr = __vmalloc(size, lflags | __GFP_ZERO, PAGE_KERNEL);
 
-	if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
-		memalloc_noio_restore(noio_flag);
+	if (flags & KM_NOFS)
+		memalloc_nofs_restore(nofs_flag);
 
 	return ptr;
 }
diff --git a/fs/xfs/kmem.h b/fs/xfs/kmem.h
index 689f746224e7..4d85992d75b2 100644
--- a/fs/xfs/kmem.h
+++ b/fs/xfs/kmem.h
@@ -50,10 +50,20 @@ kmem_flags_convert(xfs_km_flags_t flags)
 		lflags = GFP_ATOMIC | __GFP_NOWARN;
 	} else {
 		lflags = GFP_KERNEL | __GFP_NOWARN;
-		if ((current->flags & PF_FSTRANS) || (flags & KM_NOFS))
+		if (flags & KM_NOFS)
 			lflags &= ~__GFP_FS;
 	}
 
+	/*
+	 * Default page/slab allocator behavior is to retry for ever
+	 * for small allocations. We can override this behavior by using
+	 * __GFP_RETRY_MAYFAIL which will tell the allocator to retry as long
+	 * as it is feasible but rather fail than retry forever for all
+	 * request sizes.
+	 */
+	if (flags & KM_MAYFAIL)
+		lflags |= __GFP_RETRY_MAYFAIL;
+
 	if (flags & KM_ZERO)
 		lflags |= __GFP_ZERO;
 
@@ -69,8 +79,6 @@ static inline void  kmem_free(const void *ptr)
 }
 
 
-extern void *kmem_zalloc_greedy(size_t *, size_t, size_t);
-
 static inline void *
 kmem_zalloc(size_t size, xfs_km_flags_t flags)
 {
diff --git a/fs/xfs/libxfs/xfs_ag_resv.c b/fs/xfs/libxfs/xfs_ag_resv.c
index 33db69be4832..b008ff3250eb 100644
--- a/fs/xfs/libxfs/xfs_ag_resv.c
+++ b/fs/xfs/libxfs/xfs_ag_resv.c
@@ -111,8 +111,7 @@ xfs_ag_resv_critical(
 
 	/* Critically low if less than 10% or max btree height remains. */
 	return XFS_TEST_ERROR(avail < orig / 10 || avail < XFS_BTREE_MAXLEVELS,
-			pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL,
-			XFS_RANDOM_AG_RESV_CRITICAL);
+			pag->pag_mount, XFS_ERRTAG_AG_RESV_CRITICAL);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_alloc.c b/fs/xfs/libxfs/xfs_alloc.c
index 9f06a211e157..744dcaec34cc 100644
--- a/fs/xfs/libxfs/xfs_alloc.c
+++ b/fs/xfs/libxfs/xfs_alloc.c
@@ -221,20 +221,22 @@ xfs_alloc_get_rec(
  * Compute aligned version of the found extent.
  * Takes alignment and min length into account.
  */
-STATIC void
+STATIC bool
 xfs_alloc_compute_aligned(
 	xfs_alloc_arg_t	*args,		/* allocation argument structure */
 	xfs_agblock_t	foundbno,	/* starting block in found extent */
 	xfs_extlen_t	foundlen,	/* length in found extent */
 	xfs_agblock_t	*resbno,	/* result block number */
-	xfs_extlen_t	*reslen)	/* result length */
+	xfs_extlen_t	*reslen,	/* result length */
+	unsigned	*busy_gen)
 {
-	xfs_agblock_t	bno;
-	xfs_extlen_t	len;
+	xfs_agblock_t	bno = foundbno;
+	xfs_extlen_t	len = foundlen;
 	xfs_extlen_t	diff;
+	bool		busy;
 
 	/* Trim busy sections out of found extent */
-	xfs_extent_busy_trim(args, foundbno, foundlen, &bno, &len);
+	busy = xfs_extent_busy_trim(args, &bno, &len, busy_gen);
 
 	/*
 	 * If we have a largish extent that happens to start before min_agbno,
@@ -259,6 +261,8 @@ xfs_alloc_compute_aligned(
 		*resbno = bno;
 		*reslen = len;
 	}
+
+	return busy;
 }
 
 /*
@@ -602,7 +606,7 @@ const struct xfs_buf_ops xfs_agfl_buf_ops = {
 /*
  * Read in the allocation group free block array.
  */
-STATIC int				/* error */
+int					/* error */
 xfs_alloc_read_agfl(
 	xfs_mount_t	*mp,		/* mount point structure */
 	xfs_trans_t	*tp,		/* transaction pointer */
@@ -737,10 +741,11 @@ xfs_alloc_ag_vextent_exact(
 	int		error;
 	xfs_agblock_t	fbno;	/* start block of found extent */
 	xfs_extlen_t	flen;	/* length of found extent */
-	xfs_agblock_t	tbno;	/* start block of trimmed extent */
-	xfs_extlen_t	tlen;	/* length of trimmed extent */
-	xfs_agblock_t	tend;	/* end block of trimmed extent */
+	xfs_agblock_t	tbno;	/* start block of busy extent */
+	xfs_extlen_t	tlen;	/* length of busy extent */
+	xfs_agblock_t	tend;	/* end block of busy extent */
 	int		i;	/* success/failure of operation */
+	unsigned	busy_gen;
 
 	ASSERT(args->alignment == 1);
 
@@ -773,7 +778,9 @@ xfs_alloc_ag_vextent_exact(
 	/*
 	 * Check for overlapping busy extents.
 	 */
-	xfs_extent_busy_trim(args, fbno, flen, &tbno, &tlen);
+	tbno = fbno;
+	tlen = flen;
+	xfs_extent_busy_trim(args, &tbno, &tlen, &busy_gen);
 
 	/*
 	 * Give up if the start of the extent is busy, or the freespace isn't
@@ -853,6 +860,7 @@ xfs_alloc_find_best_extent(
 	xfs_agblock_t		sdiff;
 	int			error;
 	int			i;
+	unsigned		busy_gen;
 
 	/* The good extent is perfect, no need to  search. */
 	if (!gdiff)
@@ -866,7 +874,8 @@ xfs_alloc_find_best_extent(
 		if (error)
 			goto error0;
 		XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0);
-		xfs_alloc_compute_aligned(args, *sbno, *slen, sbnoa, slena);
+		xfs_alloc_compute_aligned(args, *sbno, *slen,
+				sbnoa, slena, &busy_gen);
 
 		/*
 		 * The good extent is closer than this one.
@@ -955,7 +964,8 @@ xfs_alloc_ag_vextent_near(
 	xfs_extlen_t	ltlena;		/* aligned ... */
 	xfs_agblock_t	ltnew;		/* useful start bno of left side */
 	xfs_extlen_t	rlen;		/* length of returned extent */
-	int		forced = 0;
+	bool		busy;
+	unsigned	busy_gen;
 #ifdef DEBUG
 	/*
 	 * Randomly don't execute the first algorithm.
@@ -982,6 +992,7 @@ restart:
 	ltlen = 0;
 	gtlena = 0;
 	ltlena = 0;
+	busy = false;
 
 	/*
 	 * Get a cursor for the by-size btree.
@@ -1064,8 +1075,8 @@ restart:
 			if ((error = xfs_alloc_get_rec(cnt_cur, &ltbno, &ltlen, &i)))
 				goto error0;
 			XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0);
-			xfs_alloc_compute_aligned(args, ltbno, ltlen,
-						  &ltbnoa, &ltlena);
+			busy = xfs_alloc_compute_aligned(args, ltbno, ltlen,
+					&ltbnoa, &ltlena, &busy_gen);
 			if (ltlena < args->minlen)
 				continue;
 			if (ltbnoa < args->min_agbno || ltbnoa > args->max_agbno)
@@ -1183,8 +1194,8 @@ restart:
 			if ((error = xfs_alloc_get_rec(bno_cur_lt, &ltbno, &ltlen, &i)))
 				goto error0;
 			XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0);
-			xfs_alloc_compute_aligned(args, ltbno, ltlen,
-						  &ltbnoa, &ltlena);
+			busy |= xfs_alloc_compute_aligned(args, ltbno, ltlen,
+					&ltbnoa, &ltlena, &busy_gen);
 			if (ltlena >= args->minlen && ltbnoa >= args->min_agbno)
 				break;
 			if ((error = xfs_btree_decrement(bno_cur_lt, 0, &i)))
@@ -1199,8 +1210,8 @@ restart:
 			if ((error = xfs_alloc_get_rec(bno_cur_gt, &gtbno, &gtlen, &i)))
 				goto error0;
 			XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0);
-			xfs_alloc_compute_aligned(args, gtbno, gtlen,
-						  &gtbnoa, &gtlena);
+			busy |= xfs_alloc_compute_aligned(args, gtbno, gtlen,
+					&gtbnoa, &gtlena, &busy_gen);
 			if (gtlena >= args->minlen && gtbnoa <= args->max_agbno)
 				break;
 			if ((error = xfs_btree_increment(bno_cur_gt, 0, &i)))
@@ -1261,9 +1272,9 @@ restart:
 	if (bno_cur_lt == NULL && bno_cur_gt == NULL) {
 		xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
 
-		if (!forced++) {
+		if (busy) {
 			trace_xfs_alloc_near_busy(args);
-			xfs_log_force(args->mp, XFS_LOG_SYNC);
+			xfs_extent_busy_flush(args->mp, args->pag, busy_gen);
 			goto restart;
 		}
 		trace_xfs_alloc_size_neither(args);
@@ -1344,7 +1355,8 @@ xfs_alloc_ag_vextent_size(
 	int		i;		/* temp status variable */
 	xfs_agblock_t	rbno;		/* returned block number */
 	xfs_extlen_t	rlen;		/* length of returned extent */
-	int		forced = 0;
+	bool		busy;
+	unsigned	busy_gen;
 
 restart:
 	/*
@@ -1353,6 +1365,7 @@ restart:
 	cnt_cur = xfs_allocbt_init_cursor(args->mp, args->tp, args->agbp,
 		args->agno, XFS_BTNUM_CNT);
 	bno_cur = NULL;
+	busy = false;
 
 	/*
 	 * Look for an entry >= maxlen+alignment-1 blocks.
@@ -1362,14 +1375,13 @@ restart:
 		goto error0;
 
 	/*
-	 * If none or we have busy extents that we cannot allocate from, then
-	 * we have to settle for a smaller extent. In the case that there are
-	 * no large extents, this will return the last entry in the tree unless
-	 * the tree is empty. In the case that there are only busy large
-	 * extents, this will return the largest small extent unless there
+	 * If none then we have to settle for a smaller extent. In the case that
+	 * there are no large extents, this will return the last entry in the
+	 * tree unless the tree is empty. In the case that there are only busy
+	 * large extents, this will return the largest small extent unless there
 	 * are no smaller extents available.
 	 */
-	if (!i || forced > 1) {
+	if (!i) {
 		error = xfs_alloc_ag_vextent_small(args, cnt_cur,
 						   &fbno, &flen, &i);
 		if (error)
@@ -1380,13 +1392,11 @@ restart:
 			return 0;
 		}
 		ASSERT(i == 1);
-		xfs_alloc_compute_aligned(args, fbno, flen, &rbno, &rlen);
+		busy = xfs_alloc_compute_aligned(args, fbno, flen, &rbno,
+				&rlen, &busy_gen);
 	} else {
 		/*
 		 * Search for a non-busy extent that is large enough.
-		 * If we are at low space, don't check, or if we fall of
-		 * the end of the btree, turn off the busy check and
-		 * restart.
 		 */
 		for (;;) {
 			error = xfs_alloc_get_rec(cnt_cur, &fbno, &flen, &i);
@@ -1394,8 +1404,8 @@ restart:
 				goto error0;
 			XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0);
 
-			xfs_alloc_compute_aligned(args, fbno, flen,
-						  &rbno, &rlen);
+			busy = xfs_alloc_compute_aligned(args, fbno, flen,
+					&rbno, &rlen, &busy_gen);
 
 			if (rlen >= args->maxlen)
 				break;
@@ -1407,18 +1417,13 @@ restart:
 				/*
 				 * Our only valid extents must have been busy.
 				 * Make it unbusy by forcing the log out and
-				 * retrying. If we've been here before, forcing
-				 * the log isn't making the extents available,
-				 * which means they have probably been freed in
-				 * this transaction.  In that case, we have to
-				 * give up on them and we'll attempt a minlen
-				 * allocation the next time around.
+				 * retrying.
 				 */
 				xfs_btree_del_cursor(cnt_cur,
 						     XFS_BTREE_NOERROR);
 				trace_xfs_alloc_size_busy(args);
-				if (!forced++)
-					xfs_log_force(args->mp, XFS_LOG_SYNC);
+				xfs_extent_busy_flush(args->mp,
+							args->pag, busy_gen);
 				goto restart;
 			}
 		}
@@ -1454,8 +1459,8 @@ restart:
 			XFS_WANT_CORRUPTED_GOTO(args->mp, i == 1, error0);
 			if (flen < bestrlen)
 				break;
-			xfs_alloc_compute_aligned(args, fbno, flen,
-						  &rbno, &rlen);
+			busy = xfs_alloc_compute_aligned(args, fbno, flen,
+					&rbno, &rlen, &busy_gen);
 			rlen = XFS_EXTLEN_MIN(args->maxlen, rlen);
 			XFS_WANT_CORRUPTED_GOTO(args->mp, rlen == 0 ||
 				(rlen <= flen && rbno + rlen <= fbno + flen),
@@ -1484,10 +1489,10 @@ restart:
 	 */
 	args->len = rlen;
 	if (rlen < args->minlen) {
-		if (!forced++) {
+		if (busy) {
 			xfs_btree_del_cursor(cnt_cur, XFS_BTREE_NOERROR);
 			trace_xfs_alloc_size_busy(args);
-			xfs_log_force(args->mp, XFS_LOG_SYNC);
+			xfs_extent_busy_flush(args->mp, args->pag, busy_gen);
 			goto restart;
 		}
 		goto out_nominleft;
@@ -2449,8 +2454,7 @@ xfs_agf_read_verify(
 	    !xfs_buf_verify_cksum(bp, XFS_AGF_CRC_OFF))
 		xfs_buf_ioerror(bp, -EFSBADCRC);
 	else if (XFS_TEST_ERROR(!xfs_agf_verify(mp, bp), mp,
-				XFS_ERRTAG_ALLOC_READ_AGF,
-				XFS_RANDOM_ALLOC_READ_AGF))
+				XFS_ERRTAG_ALLOC_READ_AGF))
 		xfs_buf_ioerror(bp, -EFSCORRUPTED);
 
 	if (bp->b_error)
@@ -2659,21 +2663,11 @@ xfs_alloc_vextent(
 		args->agbno = XFS_FSB_TO_AGBNO(mp, args->fsbno);
 		args->type = XFS_ALLOCTYPE_NEAR_BNO;
 		/* FALLTHROUGH */
-	case XFS_ALLOCTYPE_ANY_AG:
-	case XFS_ALLOCTYPE_START_AG:
 	case XFS_ALLOCTYPE_FIRST_AG:
 		/*
 		 * Rotate through the allocation groups looking for a winner.
 		 */
-		if (type == XFS_ALLOCTYPE_ANY_AG) {
-			/*
-			 * Start with the last place we left off.
-			 */
-			args->agno = sagno = (mp->m_agfrotor / rotorstep) %
-					mp->m_sb.sb_agcount;
-			args->type = XFS_ALLOCTYPE_THIS_AG;
-			flags = XFS_ALLOC_FLAG_TRYLOCK;
-		} else if (type == XFS_ALLOCTYPE_FIRST_AG) {
+		if (type == XFS_ALLOCTYPE_FIRST_AG) {
 			/*
 			 * Start with allocation group given by bno.
 			 */
@@ -2682,8 +2676,6 @@ xfs_alloc_vextent(
 			sagno = 0;
 			flags = 0;
 		} else {
-			if (type == XFS_ALLOCTYPE_START_AG)
-				args->type = XFS_ALLOCTYPE_THIS_AG;
 			/*
 			 * Start with the given allocation group.
 			 */
@@ -2751,7 +2743,7 @@ xfs_alloc_vextent(
 			}
 			xfs_perag_put(args->pag);
 		}
-		if (bump_rotor || (type == XFS_ALLOCTYPE_ANY_AG)) {
+		if (bump_rotor) {
 			if (args->agno == sagno)
 				mp->m_agfrotor = (mp->m_agfrotor + 1) %
 					(mp->m_sb.sb_agcount * rotorstep);
@@ -2849,8 +2841,7 @@ xfs_free_extent(
 	ASSERT(type != XFS_AG_RESV_AGFL);
 
 	if (XFS_TEST_ERROR(false, mp,
-			XFS_ERRTAG_FREE_EXTENT,
-			XFS_RANDOM_FREE_EXTENT))
+			XFS_ERRTAG_FREE_EXTENT))
 		return -EIO;
 
 	error = xfs_free_extent_fix_freelist(tp, agno, &agbp);
@@ -2875,3 +2866,60 @@ err:
 	xfs_trans_brelse(tp, agbp);
 	return error;
 }
+
+struct xfs_alloc_query_range_info {
+	xfs_alloc_query_range_fn	fn;
+	void				*priv;
+};
+
+/* Format btree record and pass to our callback. */
+STATIC int
+xfs_alloc_query_range_helper(
+	struct xfs_btree_cur		*cur,
+	union xfs_btree_rec		*rec,
+	void				*priv)
+{
+	struct xfs_alloc_query_range_info	*query = priv;
+	struct xfs_alloc_rec_incore		irec;
+
+	irec.ar_startblock = be32_to_cpu(rec->alloc.ar_startblock);
+	irec.ar_blockcount = be32_to_cpu(rec->alloc.ar_blockcount);
+	return query->fn(cur, &irec, query->priv);
+}
+
+/* Find all free space within a given range of blocks. */
+int
+xfs_alloc_query_range(
+	struct xfs_btree_cur			*cur,
+	struct xfs_alloc_rec_incore		*low_rec,
+	struct xfs_alloc_rec_incore		*high_rec,
+	xfs_alloc_query_range_fn		fn,
+	void					*priv)
+{
+	union xfs_btree_irec			low_brec;
+	union xfs_btree_irec			high_brec;
+	struct xfs_alloc_query_range_info	query;
+
+	ASSERT(cur->bc_btnum == XFS_BTNUM_BNO);
+	low_brec.a = *low_rec;
+	high_brec.a = *high_rec;
+	query.priv = priv;
+	query.fn = fn;
+	return xfs_btree_query_range(cur, &low_brec, &high_brec,
+			xfs_alloc_query_range_helper, &query);
+}
+
+/* Find all free space records. */
+int
+xfs_alloc_query_all(
+	struct xfs_btree_cur			*cur,
+	xfs_alloc_query_range_fn		fn,
+	void					*priv)
+{
+	struct xfs_alloc_query_range_info	query;
+
+	ASSERT(cur->bc_btnum == XFS_BTNUM_BNO);
+	query.priv = priv;
+	query.fn = fn;
+	return xfs_btree_query_all(cur, xfs_alloc_query_range_helper, &query);
+}
diff --git a/fs/xfs/libxfs/xfs_alloc.h b/fs/xfs/libxfs/xfs_alloc.h
index 1d0f48a501a3..ef26edc2e938 100644
--- a/fs/xfs/libxfs/xfs_alloc.h
+++ b/fs/xfs/libxfs/xfs_alloc.h
@@ -29,9 +29,7 @@ extern struct workqueue_struct *xfs_alloc_wq;
 /*
  * Freespace allocation types.  Argument to xfs_alloc_[v]extent.
  */
-#define XFS_ALLOCTYPE_ANY_AG	0x01	/* allocate anywhere, use rotor */
 #define XFS_ALLOCTYPE_FIRST_AG	0x02	/* ... start at ag 0 */
-#define XFS_ALLOCTYPE_START_AG	0x04	/* anywhere, start in this a.g. */
 #define XFS_ALLOCTYPE_THIS_AG	0x08	/* anywhere in this a.g. */
 #define XFS_ALLOCTYPE_START_BNO	0x10	/* near this block else anywhere */
 #define XFS_ALLOCTYPE_NEAR_BNO	0x20	/* in this a.g. and near this block */
@@ -41,9 +39,7 @@ extern struct workqueue_struct *xfs_alloc_wq;
 typedef unsigned int xfs_alloctype_t;
 
 #define XFS_ALLOC_TYPES \
-	{ XFS_ALLOCTYPE_ANY_AG,		"ANY_AG" }, \
 	{ XFS_ALLOCTYPE_FIRST_AG,	"FIRST_AG" }, \
-	{ XFS_ALLOCTYPE_START_AG,	"START_AG" }, \
 	{ XFS_ALLOCTYPE_THIS_AG,	"THIS_AG" }, \
 	{ XFS_ALLOCTYPE_START_BNO,	"START_BNO" }, \
 	{ XFS_ALLOCTYPE_NEAR_BNO,	"NEAR_BNO" }, \
@@ -217,10 +213,24 @@ xfs_alloc_get_rec(
 
 int xfs_read_agf(struct xfs_mount *mp, struct xfs_trans *tp,
 			xfs_agnumber_t agno, int flags, struct xfs_buf **bpp);
+int xfs_alloc_read_agfl(struct xfs_mount *mp, struct xfs_trans *tp,
+			xfs_agnumber_t agno, struct xfs_buf **bpp);
 int xfs_alloc_fix_freelist(struct xfs_alloc_arg *args, int flags);
 int xfs_free_extent_fix_freelist(struct xfs_trans *tp, xfs_agnumber_t agno,
 		struct xfs_buf **agbp);
 
 xfs_extlen_t xfs_prealloc_blocks(struct xfs_mount *mp);
 
+typedef int (*xfs_alloc_query_range_fn)(
+	struct xfs_btree_cur		*cur,
+	struct xfs_alloc_rec_incore	*rec,
+	void				*priv);
+
+int xfs_alloc_query_range(struct xfs_btree_cur *cur,
+		struct xfs_alloc_rec_incore *low_rec,
+		struct xfs_alloc_rec_incore *high_rec,
+		xfs_alloc_query_range_fn fn, void *priv);
+int xfs_alloc_query_all(struct xfs_btree_cur *cur, xfs_alloc_query_range_fn fn,
+		void *priv);
+
 #endif	/* __XFS_ALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_alloc_btree.c b/fs/xfs/libxfs/xfs_alloc_btree.c
index efb467b10a71..cfde0a0f9706 100644
--- a/fs/xfs/libxfs/xfs_alloc_btree.c
+++ b/fs/xfs/libxfs/xfs_alloc_btree.c
@@ -205,19 +205,37 @@ xfs_allocbt_init_key_from_rec(
 	union xfs_btree_key	*key,
 	union xfs_btree_rec	*rec)
 {
-	ASSERT(rec->alloc.ar_startblock != 0);
-
 	key->alloc.ar_startblock = rec->alloc.ar_startblock;
 	key->alloc.ar_blockcount = rec->alloc.ar_blockcount;
 }
 
 STATIC void
+xfs_bnobt_init_high_key_from_rec(
+	union xfs_btree_key	*key,
+	union xfs_btree_rec	*rec)
+{
+	__u32			x;
+
+	x = be32_to_cpu(rec->alloc.ar_startblock);
+	x += be32_to_cpu(rec->alloc.ar_blockcount) - 1;
+	key->alloc.ar_startblock = cpu_to_be32(x);
+	key->alloc.ar_blockcount = 0;
+}
+
+STATIC void
+xfs_cntbt_init_high_key_from_rec(
+	union xfs_btree_key	*key,
+	union xfs_btree_rec	*rec)
+{
+	key->alloc.ar_blockcount = rec->alloc.ar_blockcount;
+	key->alloc.ar_startblock = 0;
+}
+
+STATIC void
 xfs_allocbt_init_rec_from_cur(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_rec	*rec)
 {
-	ASSERT(cur->bc_rec.a.ar_startblock != 0);
-
 	rec->alloc.ar_startblock = cpu_to_be32(cur->bc_rec.a.ar_startblock);
 	rec->alloc.ar_blockcount = cpu_to_be32(cur->bc_rec.a.ar_blockcount);
 }
@@ -235,25 +253,58 @@ xfs_allocbt_init_ptr_from_cur(
 	ptr->s = agf->agf_roots[cur->bc_btnum];
 }
 
-STATIC __int64_t
-xfs_allocbt_key_diff(
+STATIC int64_t
+xfs_bnobt_key_diff(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*key)
 {
 	xfs_alloc_rec_incore_t	*rec = &cur->bc_rec.a;
 	xfs_alloc_key_t		*kp = &key->alloc;
-	__int64_t		diff;
 
-	if (cur->bc_btnum == XFS_BTNUM_BNO) {
-		return (__int64_t)be32_to_cpu(kp->ar_startblock) -
-				rec->ar_startblock;
-	}
+	return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
+}
+
+STATIC int64_t
+xfs_cntbt_key_diff(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*key)
+{
+	xfs_alloc_rec_incore_t	*rec = &cur->bc_rec.a;
+	xfs_alloc_key_t		*kp = &key->alloc;
+	int64_t			diff;
+
+	diff = (int64_t)be32_to_cpu(kp->ar_blockcount) - rec->ar_blockcount;
+	if (diff)
+		return diff;
+
+	return (int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
+}
+
+STATIC int64_t
+xfs_bnobt_diff_two_keys(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*k1,
+	union xfs_btree_key	*k2)
+{
+	return (int64_t)be32_to_cpu(k1->alloc.ar_startblock) -
+			  be32_to_cpu(k2->alloc.ar_startblock);
+}
+
+STATIC int64_t
+xfs_cntbt_diff_two_keys(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*k1,
+	union xfs_btree_key	*k2)
+{
+	int64_t			diff;
 
-	diff = (__int64_t)be32_to_cpu(kp->ar_blockcount) - rec->ar_blockcount;
+	diff =  be32_to_cpu(k1->alloc.ar_blockcount) -
+		be32_to_cpu(k2->alloc.ar_blockcount);
 	if (diff)
 		return diff;
 
-	return (__int64_t)be32_to_cpu(kp->ar_startblock) - rec->ar_startblock;
+	return  be32_to_cpu(k1->alloc.ar_startblock) -
+		be32_to_cpu(k2->alloc.ar_startblock);
 }
 
 static bool
@@ -344,46 +395,54 @@ const struct xfs_buf_ops xfs_allocbt_buf_ops = {
 };
 
 
-#if defined(DEBUG) || defined(XFS_WARN)
 STATIC int
-xfs_allocbt_keys_inorder(
+xfs_bnobt_keys_inorder(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*k1,
 	union xfs_btree_key	*k2)
 {
-	if (cur->bc_btnum == XFS_BTNUM_BNO) {
-		return be32_to_cpu(k1->alloc.ar_startblock) <
-		       be32_to_cpu(k2->alloc.ar_startblock);
-	} else {
-		return be32_to_cpu(k1->alloc.ar_blockcount) <
-			be32_to_cpu(k2->alloc.ar_blockcount) ||
-			(k1->alloc.ar_blockcount == k2->alloc.ar_blockcount &&
-			 be32_to_cpu(k1->alloc.ar_startblock) <
-			 be32_to_cpu(k2->alloc.ar_startblock));
-	}
+	return be32_to_cpu(k1->alloc.ar_startblock) <
+	       be32_to_cpu(k2->alloc.ar_startblock);
 }
 
 STATIC int
-xfs_allocbt_recs_inorder(
+xfs_bnobt_recs_inorder(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_rec	*r1,
 	union xfs_btree_rec	*r2)
 {
-	if (cur->bc_btnum == XFS_BTNUM_BNO) {
-		return be32_to_cpu(r1->alloc.ar_startblock) +
-			be32_to_cpu(r1->alloc.ar_blockcount) <=
-			be32_to_cpu(r2->alloc.ar_startblock);
-	} else {
-		return be32_to_cpu(r1->alloc.ar_blockcount) <
-			be32_to_cpu(r2->alloc.ar_blockcount) ||
-			(r1->alloc.ar_blockcount == r2->alloc.ar_blockcount &&
-			 be32_to_cpu(r1->alloc.ar_startblock) <
-			 be32_to_cpu(r2->alloc.ar_startblock));
-	}
+	return be32_to_cpu(r1->alloc.ar_startblock) +
+		be32_to_cpu(r1->alloc.ar_blockcount) <=
+		be32_to_cpu(r2->alloc.ar_startblock);
+}
+
+STATIC int
+xfs_cntbt_keys_inorder(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*k1,
+	union xfs_btree_key	*k2)
+{
+	return be32_to_cpu(k1->alloc.ar_blockcount) <
+		be32_to_cpu(k2->alloc.ar_blockcount) ||
+		(k1->alloc.ar_blockcount == k2->alloc.ar_blockcount &&
+		 be32_to_cpu(k1->alloc.ar_startblock) <
+		 be32_to_cpu(k2->alloc.ar_startblock));
+}
+
+STATIC int
+xfs_cntbt_recs_inorder(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_rec	*r1,
+	union xfs_btree_rec	*r2)
+{
+	return be32_to_cpu(r1->alloc.ar_blockcount) <
+		be32_to_cpu(r2->alloc.ar_blockcount) ||
+		(r1->alloc.ar_blockcount == r2->alloc.ar_blockcount &&
+		 be32_to_cpu(r1->alloc.ar_startblock) <
+		 be32_to_cpu(r2->alloc.ar_startblock));
 }
-#endif	/* DEBUG */
 
-static const struct xfs_btree_ops xfs_allocbt_ops = {
+static const struct xfs_btree_ops xfs_bnobt_ops = {
 	.rec_len		= sizeof(xfs_alloc_rec_t),
 	.key_len		= sizeof(xfs_alloc_key_t),
 
@@ -395,14 +454,36 @@ static const struct xfs_btree_ops xfs_allocbt_ops = {
 	.get_minrecs		= xfs_allocbt_get_minrecs,
 	.get_maxrecs		= xfs_allocbt_get_maxrecs,
 	.init_key_from_rec	= xfs_allocbt_init_key_from_rec,
+	.init_high_key_from_rec	= xfs_bnobt_init_high_key_from_rec,
 	.init_rec_from_cur	= xfs_allocbt_init_rec_from_cur,
 	.init_ptr_from_cur	= xfs_allocbt_init_ptr_from_cur,
-	.key_diff		= xfs_allocbt_key_diff,
+	.key_diff		= xfs_bnobt_key_diff,
 	.buf_ops		= &xfs_allocbt_buf_ops,
-#if defined(DEBUG) || defined(XFS_WARN)
-	.keys_inorder		= xfs_allocbt_keys_inorder,
-	.recs_inorder		= xfs_allocbt_recs_inorder,
-#endif
+	.diff_two_keys		= xfs_bnobt_diff_two_keys,
+	.keys_inorder		= xfs_bnobt_keys_inorder,
+	.recs_inorder		= xfs_bnobt_recs_inorder,
+};
+
+static const struct xfs_btree_ops xfs_cntbt_ops = {
+	.rec_len		= sizeof(xfs_alloc_rec_t),
+	.key_len		= sizeof(xfs_alloc_key_t),
+
+	.dup_cursor		= xfs_allocbt_dup_cursor,
+	.set_root		= xfs_allocbt_set_root,
+	.alloc_block		= xfs_allocbt_alloc_block,
+	.free_block		= xfs_allocbt_free_block,
+	.update_lastrec		= xfs_allocbt_update_lastrec,
+	.get_minrecs		= xfs_allocbt_get_minrecs,
+	.get_maxrecs		= xfs_allocbt_get_maxrecs,
+	.init_key_from_rec	= xfs_allocbt_init_key_from_rec,
+	.init_high_key_from_rec	= xfs_cntbt_init_high_key_from_rec,
+	.init_rec_from_cur	= xfs_allocbt_init_rec_from_cur,
+	.init_ptr_from_cur	= xfs_allocbt_init_ptr_from_cur,
+	.key_diff		= xfs_cntbt_key_diff,
+	.buf_ops		= &xfs_allocbt_buf_ops,
+	.diff_two_keys		= xfs_cntbt_diff_two_keys,
+	.keys_inorder		= xfs_cntbt_keys_inorder,
+	.recs_inorder		= xfs_cntbt_recs_inorder,
 };
 
 /*
@@ -427,16 +508,15 @@ xfs_allocbt_init_cursor(
 	cur->bc_mp = mp;
 	cur->bc_btnum = btnum;
 	cur->bc_blocklog = mp->m_sb.sb_blocklog;
-	cur->bc_ops = &xfs_allocbt_ops;
-	if (btnum == XFS_BTNUM_BNO)
-		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtb_2);
-	else
-		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtc_2);
 
 	if (btnum == XFS_BTNUM_CNT) {
+		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtc_2);
+		cur->bc_ops = &xfs_cntbt_ops;
 		cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_CNT]);
 		cur->bc_flags = XFS_BTREE_LASTREC_UPDATE;
 	} else {
+		cur->bc_statoff = XFS_STATS_CALC_INDEX(xs_abtb_2);
+		cur->bc_ops = &xfs_bnobt_ops;
 		cur->bc_nlevels = be32_to_cpu(agf->agf_levels[XFS_BTNUM_BNO]);
 	}
 
diff --git a/fs/xfs/libxfs/xfs_attr.c b/fs/xfs/libxfs/xfs_attr.c
index 6622d46ddec3..de7b9bd30bec 100644
--- a/fs/xfs/libxfs/xfs_attr.c
+++ b/fs/xfs/libxfs/xfs_attr.c
@@ -114,6 +114,25 @@ xfs_inode_hasattr(
  * Overall external interface routines.
  *========================================================================*/
 
+/* Retrieve an extended attribute and its value.  Must have ilock. */
+int
+xfs_attr_get_ilocked(
+	struct xfs_inode	*ip,
+	struct xfs_da_args	*args)
+{
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
+
+	if (!xfs_inode_hasattr(ip))
+		return -ENOATTR;
+	else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
+		return xfs_attr_shortform_getvalue(args);
+	else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK))
+		return xfs_attr_leaf_get(args);
+	else
+		return xfs_attr_node_get(args);
+}
+
+/* Retrieve an extended attribute by name, and its value. */
 int
 xfs_attr_get(
 	struct xfs_inode	*ip,
@@ -141,14 +160,7 @@ xfs_attr_get(
 	args.op_flags = XFS_DA_OP_OKNOENT;
 
 	lock_mode = xfs_ilock_attr_map_shared(ip);
-	if (!xfs_inode_hasattr(ip))
-		error = -ENOATTR;
-	else if (ip->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
-		error = xfs_attr_shortform_getvalue(&args);
-	else if (xfs_bmap_one_block(ip, XFS_ATTR_FORK))
-		error = xfs_attr_leaf_get(&args);
-	else
-		error = xfs_attr_node_get(&args);
+	error = xfs_attr_get_ilocked(ip, &args);
 	xfs_iunlock(ip, lock_mode);
 
 	*valuelenp = args.valuelen;
diff --git a/fs/xfs/libxfs/xfs_attr_leaf.c b/fs/xfs/libxfs/xfs_attr_leaf.c
index 2852521fc8ec..c6c15e5717e4 100644
--- a/fs/xfs/libxfs/xfs_attr_leaf.c
+++ b/fs/xfs/libxfs/xfs_attr_leaf.c
@@ -351,7 +351,7 @@ xfs_attr3_leaf_read(
 
 	err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp,
 				XFS_ATTR_FORK, &xfs_attr3_leaf_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_ATTR_LEAF_BUF);
 	return err;
 }
diff --git a/fs/xfs/libxfs/xfs_attr_remote.c b/fs/xfs/libxfs/xfs_attr_remote.c
index d52f525f5b2d..5236d8e45146 100644
--- a/fs/xfs/libxfs/xfs_attr_remote.c
+++ b/fs/xfs/libxfs/xfs_attr_remote.c
@@ -253,7 +253,7 @@ xfs_attr_rmtval_copyout(
 	xfs_ino_t	ino,
 	int		*offset,
 	int		*valuelen,
-	__uint8_t	**dst)
+	uint8_t		**dst)
 {
 	char		*src = bp->b_addr;
 	xfs_daddr_t	bno = bp->b_bn;
@@ -301,7 +301,7 @@ xfs_attr_rmtval_copyin(
 	xfs_ino_t	ino,
 	int		*offset,
 	int		*valuelen,
-	__uint8_t	**src)
+	uint8_t		**src)
 {
 	char		*dst = bp->b_addr;
 	xfs_daddr_t	bno = bp->b_bn;
@@ -355,7 +355,7 @@ xfs_attr_rmtval_get(
 	struct xfs_mount	*mp = args->dp->i_mount;
 	struct xfs_buf		*bp;
 	xfs_dablk_t		lblkno = args->rmtblkno;
-	__uint8_t		*dst = args->value;
+	uint8_t			*dst = args->value;
 	int			valuelen;
 	int			nmap;
 	int			error;
@@ -386,7 +386,8 @@ xfs_attr_rmtval_get(
 			       (map[i].br_startblock != HOLESTARTBLOCK));
 			dblkno = XFS_FSB_TO_DADDR(mp, map[i].br_startblock);
 			dblkcnt = XFS_FSB_TO_BB(mp, map[i].br_blockcount);
-			error = xfs_trans_read_buf(mp, NULL, mp->m_ddev_targp,
+			error = xfs_trans_read_buf(mp, args->trans,
+						   mp->m_ddev_targp,
 						   dblkno, dblkcnt, 0, &bp,
 						   &xfs_attr3_rmt_buf_ops);
 			if (error)
@@ -395,7 +396,7 @@ xfs_attr_rmtval_get(
 			error = xfs_attr_rmtval_copyout(mp, bp, args->dp->i_ino,
 							&offset, &valuelen,
 							&dst);
-			xfs_buf_relse(bp);
+			xfs_trans_brelse(args->trans, bp);
 			if (error)
 				return error;
 
@@ -421,7 +422,7 @@ xfs_attr_rmtval_set(
 	struct xfs_bmbt_irec	map;
 	xfs_dablk_t		lblkno;
 	xfs_fileoff_t		lfileoff = 0;
-	__uint8_t		*src = args->value;
+	uint8_t			*src = args->value;
 	int			blkcnt;
 	int			valuelen;
 	int			nmap;
diff --git a/fs/xfs/libxfs/xfs_attr_sf.h b/fs/xfs/libxfs/xfs_attr_sf.h
index 90928bbe693c..afd684ae3136 100644
--- a/fs/xfs/libxfs/xfs_attr_sf.h
+++ b/fs/xfs/libxfs/xfs_attr_sf.h
@@ -31,10 +31,10 @@ typedef struct xfs_attr_sf_entry xfs_attr_sf_entry_t;
  * We generate this then sort it, attr_list() must return things in hash-order.
  */
 typedef struct xfs_attr_sf_sort {
-	__uint8_t	entno;		/* entry number in original list */
-	__uint8_t	namelen;	/* length of name value (no null) */
-	__uint8_t	valuelen;	/* length of value */
-	__uint8_t	flags;		/* flags bits (see xfs_attr_leaf.h) */
+	uint8_t		entno;		/* entry number in original list */
+	uint8_t		namelen;	/* length of name value (no null) */
+	uint8_t		valuelen;	/* length of value */
+	uint8_t		flags;		/* flags bits (see xfs_attr_leaf.h) */
 	xfs_dahash_t	hash;		/* this entry's hash value */
 	unsigned char	*name;		/* name value, pointer into buffer */
 } xfs_attr_sf_sort_t;
@@ -42,7 +42,7 @@ typedef struct xfs_attr_sf_sort {
 #define XFS_ATTR_SF_ENTSIZE_BYNAME(nlen,vlen)	/* space name/value uses */ \
 	(((int)sizeof(xfs_attr_sf_entry_t)-1 + (nlen)+(vlen)))
 #define XFS_ATTR_SF_ENTSIZE_MAX			/* max space for name&value */ \
-	((1 << (NBBY*(int)sizeof(__uint8_t))) - 1)
+	((1 << (NBBY*(int)sizeof(uint8_t))) - 1)
 #define XFS_ATTR_SF_ENTSIZE(sfep)		/* space an entry uses */ \
 	((int)sizeof(xfs_attr_sf_entry_t)-1 + (sfep)->namelen+(sfep)->valuelen)
 #define XFS_ATTR_SF_NEXTENTRY(sfep)		/* next entry in struct */ \
diff --git a/fs/xfs/libxfs/xfs_bit.h b/fs/xfs/libxfs/xfs_bit.h
index e1649c0d3e02..61c6b2025d0c 100644
--- a/fs/xfs/libxfs/xfs_bit.h
+++ b/fs/xfs/libxfs/xfs_bit.h
@@ -25,47 +25,47 @@
 /*
  * masks with n high/low bits set, 64-bit values
  */
-static inline __uint64_t xfs_mask64hi(int n)
+static inline uint64_t xfs_mask64hi(int n)
 {
-	return (__uint64_t)-1 << (64 - (n));
+	return (uint64_t)-1 << (64 - (n));
 }
-static inline __uint32_t xfs_mask32lo(int n)
+static inline uint32_t xfs_mask32lo(int n)
 {
-	return ((__uint32_t)1 << (n)) - 1;
+	return ((uint32_t)1 << (n)) - 1;
 }
-static inline __uint64_t xfs_mask64lo(int n)
+static inline uint64_t xfs_mask64lo(int n)
 {
-	return ((__uint64_t)1 << (n)) - 1;
+	return ((uint64_t)1 << (n)) - 1;
 }
 
 /* Get high bit set out of 32-bit argument, -1 if none set */
-static inline int xfs_highbit32(__uint32_t v)
+static inline int xfs_highbit32(uint32_t v)
 {
 	return fls(v) - 1;
 }
 
 /* Get high bit set out of 64-bit argument, -1 if none set */
-static inline int xfs_highbit64(__uint64_t v)
+static inline int xfs_highbit64(uint64_t v)
 {
 	return fls64(v) - 1;
 }
 
 /* Get low bit set out of 32-bit argument, -1 if none set */
-static inline int xfs_lowbit32(__uint32_t v)
+static inline int xfs_lowbit32(uint32_t v)
 {
 	return ffs(v) - 1;
 }
 
 /* Get low bit set out of 64-bit argument, -1 if none set */
-static inline int xfs_lowbit64(__uint64_t v)
+static inline int xfs_lowbit64(uint64_t v)
 {
-	__uint32_t	w = (__uint32_t)v;
+	uint32_t	w = (uint32_t)v;
 	int		n = 0;
 
 	if (w) {	/* lower bits */
 		n = ffs(w);
 	} else {	/* upper bits */
-		w = (__uint32_t)(v >> 32);
+		w = (uint32_t)(v >> 32);
 		if (w) {
 			n = ffs(w);
 			if (n)
diff --git a/fs/xfs/libxfs/xfs_bmap.c b/fs/xfs/libxfs/xfs_bmap.c
index bfc00de5c6f1..0a9880777c9c 100644
--- a/fs/xfs/libxfs/xfs_bmap.c
+++ b/fs/xfs/libxfs/xfs_bmap.c
@@ -740,15 +740,9 @@ xfs_bmap_extents_to_btree(
 	 * Fill in the root.
 	 */
 	block = ifp->if_broot;
-	if (xfs_sb_version_hascrc(&mp->m_sb))
-		xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL,
-				 XFS_BMAP_CRC_MAGIC, 1, 1, ip->i_ino,
-				 XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS);
-	else
-		xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL,
-				 XFS_BMAP_MAGIC, 1, 1, ip->i_ino,
+	xfs_btree_init_block_int(mp, block, XFS_BUF_DADDR_NULL,
+				 XFS_BTNUM_BMAP, 1, 1, ip->i_ino,
 				 XFS_BTREE_LONG_PTRS);
-
 	/*
 	 * Need a cursor.  Can't allocate until bb_level is filled in.
 	 */
@@ -769,7 +763,6 @@ xfs_bmap_extents_to_btree(
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = XFS_INO_TO_FSB(mp, ip->i_ino);
 	} else if (dfops->dop_low) {
-try_another_ag:
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		args.fsbno = *firstblock;
 	} else {
@@ -785,28 +778,16 @@ try_another_ag:
 		return error;
 	}
 
-	/*
-	 * During a CoW operation, the allocation and bmbt updates occur in
-	 * different transactions.  The mapping code tries to put new bmbt
-	 * blocks near extents being mapped, but the only way to guarantee this
-	 * is if the alloc and the mapping happen in a single transaction that
-	 * has a block reservation.  That isn't the case here, so if we run out
-	 * of space we'll try again with another AG.
-	 */
-	if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
-	    args.fsbno == NULLFSBLOCK &&
-	    args.type == XFS_ALLOCTYPE_NEAR_BNO) {
-		dfops->dop_low = true;
-		goto try_another_ag;
+	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
+		xfs_iroot_realloc(ip, -1, whichfork);
+		xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
+		return -ENOSPC;
 	}
 	/*
 	 * Allocation can't fail, the space was reserved.
 	 */
-	ASSERT(args.fsbno != NULLFSBLOCK);
 	ASSERT(*firstblock == NULLFSBLOCK ||
-	       args.agno == XFS_FSB_TO_AGNO(mp, *firstblock) ||
-	       (dfops->dop_low &&
-		args.agno > XFS_FSB_TO_AGNO(mp, *firstblock)));
+	       args.agno >= XFS_FSB_TO_AGNO(mp, *firstblock));
 	*firstblock = cur->bc_private.b.firstblock = args.fsbno;
 	cur->bc_private.b.allocated++;
 	ip->i_d.di_nblocks++;
@@ -817,13 +798,8 @@ try_another_ag:
 	 */
 	abp->b_ops = &xfs_bmbt_buf_ops;
 	ablock = XFS_BUF_TO_BLOCK(abp);
-	if (xfs_sb_version_hascrc(&mp->m_sb))
-		xfs_btree_init_block_int(mp, ablock, abp->b_bn,
-				XFS_BMAP_CRC_MAGIC, 0, 0, ip->i_ino,
-				XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS);
-	else
-		xfs_btree_init_block_int(mp, ablock, abp->b_bn,
-				XFS_BMAP_MAGIC, 0, 0, ip->i_ino,
+	xfs_btree_init_block_int(mp, ablock, abp->b_bn,
+				XFS_BTNUM_BMAP, 0, 0, ip->i_ino,
 				XFS_BTREE_LONG_PTRS);
 
 	arp = XFS_BMBT_REC_ADDR(mp, ablock, 1);
@@ -934,7 +910,6 @@ xfs_bmap_local_to_extents(
 	 * file currently fits in an inode.
 	 */
 	if (*firstblock == NULLFSBLOCK) {
-try_another_ag:
 		args.fsbno = XFS_INO_TO_FSB(args.mp, ip->i_ino);
 		args.type = XFS_ALLOCTYPE_START_BNO;
 	} else {
@@ -947,19 +922,6 @@ try_another_ag:
 	if (error)
 		goto done;
 
-	/*
-	 * During a CoW operation, the allocation and bmbt updates occur in
-	 * different transactions.  The mapping code tries to put new bmbt
-	 * blocks near extents being mapped, but the only way to guarantee this
-	 * is if the alloc and the mapping happen in a single transaction that
-	 * has a block reservation.  That isn't the case here, so if we run out
-	 * of space we'll try again with another AG.
-	 */
-	if (xfs_sb_version_hasreflink(&ip->i_mount->m_sb) &&
-	    args.fsbno == NULLFSBLOCK &&
-	    args.type == XFS_ALLOCTYPE_NEAR_BNO) {
-		goto try_another_ag;
-	}
 	/* Can't fail, the space was reserved. */
 	ASSERT(args.fsbno != NULLFSBLOCK);
 	ASSERT(args.len == 1);
@@ -1269,7 +1231,6 @@ xfs_bmap_read_extents(
 	xfs_fsblock_t		bno;	/* block # of "block" */
 	xfs_buf_t		*bp;	/* buffer for "block" */
 	int			error;	/* error return value */
-	xfs_exntfmt_t		exntf;	/* XFS_EXTFMT_NOSTATE, if checking */
 	xfs_extnum_t		i, j;	/* index into the extents list */
 	xfs_ifork_t		*ifp;	/* fork structure */
 	int			level;	/* btree level, for checking */
@@ -1278,11 +1239,8 @@ xfs_bmap_read_extents(
 	/* REFERENCED */
 	xfs_extnum_t		room;	/* number of entries there's room for */
 
-	bno = NULLFSBLOCK;
 	mp = ip->i_mount;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
-	exntf = (whichfork != XFS_DATA_FORK) ? XFS_EXTFMT_NOSTATE :
-					XFS_EXTFMT_INODE(ip);
 	block = ifp->if_broot;
 	/*
 	 * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
@@ -1291,9 +1249,7 @@ xfs_bmap_read_extents(
 	ASSERT(level > 0);
 	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
 	bno = be64_to_cpu(*pp);
-	ASSERT(bno != NULLFSBLOCK);
-	ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
-	ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
+
 	/*
 	 * Go down the tree until leaf level is reached, following the first
 	 * pointer (leftmost) at each level.
@@ -1324,7 +1280,6 @@ xfs_bmap_read_extents(
 		xfs_bmbt_rec_t	*frp;
 		xfs_fsblock_t	nextbno;
 		xfs_extnum_t	num_recs;
-		xfs_extnum_t	start;
 
 		num_recs = xfs_btree_get_numrecs(block);
 		if (unlikely(i + num_recs > room)) {
@@ -1347,23 +1302,13 @@ xfs_bmap_read_extents(
 		 * Copy records into the extent records.
 		 */
 		frp = XFS_BMBT_REC_ADDR(mp, block, 1);
-		start = i;
 		for (j = 0; j < num_recs; j++, i++, frp++) {
 			xfs_bmbt_rec_host_t *trp = xfs_iext_get_ext(ifp, i);
 			trp->l0 = be64_to_cpu(frp->l0);
 			trp->l1 = be64_to_cpu(frp->l1);
-		}
-		if (exntf == XFS_EXTFMT_NOSTATE) {
-			/*
-			 * Check all attribute bmap btree records and
-			 * any "older" data bmap btree records for a
-			 * set bit in the "extent flag" position.
-			 */
-			if (unlikely(xfs_check_nostate_extents(ifp,
-					start, num_recs))) {
+			if (!xfs_bmbt_validate_extent(mp, whichfork, trp)) {
 				XFS_ERROR_REPORT("xfs_bmap_read_extents(2)",
-						 XFS_ERRLEVEL_LOW,
-						 ip->i_mount);
+						 XFS_ERRLEVEL_LOW, mp);
 				goto error0;
 			}
 		}
@@ -1864,6 +1809,7 @@ xfs_bmap_add_extent_delay_real(
 		 */
 		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
 		xfs_bmbt_set_startblock(ep, new->br_startblock);
+		xfs_bmbt_set_state(ep, new->br_state);
 		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);
 
 		(*nextents)++;
@@ -2117,8 +2063,10 @@ xfs_bmap_add_extent_delay_real(
 		}
 		temp = xfs_bmap_worst_indlen(bma->ip, temp);
 		temp2 = xfs_bmap_worst_indlen(bma->ip, temp2);
-		diff = (int)(temp + temp2 - startblockval(PREV.br_startblock) -
-			(bma->cur ? bma->cur->bc_private.b.allocated : 0));
+		diff = (int)(temp + temp2 -
+			     (startblockval(PREV.br_startblock) -
+			      (bma->cur ?
+			       bma->cur->bc_private.b.allocated : 0)));
 		if (diff > 0) {
 			error = xfs_mod_fdblocks(bma->ip->i_mount,
 						 -((int64_t)diff), false);
@@ -2175,7 +2123,6 @@ xfs_bmap_add_extent_delay_real(
 		temp = da_new;
 		if (bma->cur)
 			temp += bma->cur->bc_private.b.allocated;
-		ASSERT(temp <= da_old);
 		if (temp < da_old)
 			xfs_mod_fdblocks(bma->ip->i_mount,
 					(int64_t)(da_old - temp), false);
@@ -2202,6 +2149,7 @@ STATIC int				/* error */
 xfs_bmap_add_extent_unwritten_real(
 	struct xfs_trans	*tp,
 	xfs_inode_t		*ip,	/* incore inode pointer */
+	int			whichfork,
 	xfs_extnum_t		*idx,	/* extent number to update/insert */
 	xfs_btree_cur_t		**curp,	/* if *curp is null, not a btree */
 	xfs_bmbt_irec_t		*new,	/* new data to add to file extents */
@@ -2221,12 +2169,14 @@ xfs_bmap_add_extent_unwritten_real(
 					/* left is 0, right is 1, prev is 2 */
 	int			rval=0;	/* return value (logging flags) */
 	int			state = 0;/* state bits, accessed thru macros */
-	struct xfs_mount	*mp = tp->t_mountp;
+	struct xfs_mount	*mp = ip->i_mount;
 
 	*logflagsp = 0;
 
 	cur = *curp;
-	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+	ifp = XFS_IFORK_PTR(ip, whichfork);
+	if (whichfork == XFS_COW_FORK)
+		state |= BMAP_COWFORK;
 
 	ASSERT(*idx >= 0);
 	ASSERT(*idx <= xfs_iext_count(ifp));
@@ -2285,7 +2235,7 @@ xfs_bmap_add_extent_unwritten_real(
 	 * Don't set contiguous if the combined extent would be too large.
 	 * Also check for all-three-contiguous being too large.
 	 */
-	if (*idx < xfs_iext_count(&ip->i_df) - 1) {
+	if (*idx < xfs_iext_count(ifp) - 1) {
 		state |= BMAP_RIGHT_VALID;
 		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx + 1), &RIGHT);
 		if (isnullstartblock(RIGHT.br_startblock))
@@ -2325,7 +2275,8 @@ xfs_bmap_add_extent_unwritten_real(
 		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 
 		xfs_iext_remove(ip, *idx + 1, 2, state);
-		ip->i_d.di_nextents -= 2;
+		XFS_IFORK_NEXT_SET(ip, whichfork,
+				XFS_IFORK_NEXTENTS(ip, whichfork) - 2);
 		if (cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
 		else {
@@ -2368,7 +2319,8 @@ xfs_bmap_add_extent_unwritten_real(
 		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 
 		xfs_iext_remove(ip, *idx + 1, 1, state);
-		ip->i_d.di_nextents--;
+		XFS_IFORK_NEXT_SET(ip, whichfork,
+				XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
 		if (cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
 		else {
@@ -2403,7 +2355,8 @@ xfs_bmap_add_extent_unwritten_real(
 		xfs_bmbt_set_state(ep, newext);
 		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 		xfs_iext_remove(ip, *idx + 1, 1, state);
-		ip->i_d.di_nextents--;
+		XFS_IFORK_NEXT_SET(ip, whichfork,
+				XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
 		if (cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
 		else {
@@ -2515,7 +2468,8 @@ xfs_bmap_add_extent_unwritten_real(
 		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 
 		xfs_iext_insert(ip, *idx, 1, new, state);
-		ip->i_d.di_nextents++;
+		XFS_IFORK_NEXT_SET(ip, whichfork,
+				XFS_IFORK_NEXTENTS(ip, whichfork) + 1);
 		if (cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
 		else {
@@ -2593,7 +2547,8 @@ xfs_bmap_add_extent_unwritten_real(
 		++*idx;
 		xfs_iext_insert(ip, *idx, 1, new, state);
 
-		ip->i_d.di_nextents++;
+		XFS_IFORK_NEXT_SET(ip, whichfork,
+				XFS_IFORK_NEXTENTS(ip, whichfork) + 1);
 		if (cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
 		else {
@@ -2641,7 +2596,8 @@ xfs_bmap_add_extent_unwritten_real(
 		++*idx;
 		xfs_iext_insert(ip, *idx, 2, &r[0], state);
 
-		ip->i_d.di_nextents += 2;
+		XFS_IFORK_NEXT_SET(ip, whichfork,
+				XFS_IFORK_NEXTENTS(ip, whichfork) + 2);
 		if (cur == NULL)
 			rval = XFS_ILOG_CORE | XFS_ILOG_DEXT;
 		else {
@@ -2695,17 +2651,17 @@ xfs_bmap_add_extent_unwritten_real(
 	}
 
 	/* update reverse mappings */
-	error = xfs_rmap_convert_extent(mp, dfops, ip, XFS_DATA_FORK, new);
+	error = xfs_rmap_convert_extent(mp, dfops, ip, whichfork, new);
 	if (error)
 		goto done;
 
 	/* convert to a btree if necessary */
-	if (xfs_bmap_needs_btree(ip, XFS_DATA_FORK)) {
+	if (xfs_bmap_needs_btree(ip, whichfork)) {
 		int	tmp_logflags;	/* partial log flag return val */
 
 		ASSERT(cur == NULL);
 		error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, &cur,
-				0, &tmp_logflags, XFS_DATA_FORK);
+				0, &tmp_logflags, whichfork);
 		*logflagsp |= tmp_logflags;
 		if (error)
 			goto done;
@@ -2717,7 +2673,7 @@ xfs_bmap_add_extent_unwritten_real(
 		*curp = cur;
 	}
 
-	xfs_bmap_check_leaf_extents(*curp, ip, XFS_DATA_FORK);
+	xfs_bmap_check_leaf_extents(*curp, ip, whichfork);
 done:
 	*logflagsp |= rval;
 	return error;
@@ -2809,7 +2765,8 @@ xfs_bmap_add_extent_hole_delay(
 		oldlen = startblockval(left.br_startblock) +
 			startblockval(new->br_startblock) +
 			startblockval(right.br_startblock);
-		newlen = xfs_bmap_worst_indlen(ip, temp);
+		newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
+					 oldlen);
 		xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, *idx),
 			nullstartblock((int)newlen));
 		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
@@ -2830,7 +2787,8 @@ xfs_bmap_add_extent_hole_delay(
 		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx), temp);
 		oldlen = startblockval(left.br_startblock) +
 			startblockval(new->br_startblock);
-		newlen = xfs_bmap_worst_indlen(ip, temp);
+		newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
+					 oldlen);
 		xfs_bmbt_set_startblock(xfs_iext_get_ext(ifp, *idx),
 			nullstartblock((int)newlen));
 		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
@@ -2846,7 +2804,8 @@ xfs_bmap_add_extent_hole_delay(
 		temp = new->br_blockcount + right.br_blockcount;
 		oldlen = startblockval(new->br_startblock) +
 			startblockval(right.br_startblock);
-		newlen = xfs_bmap_worst_indlen(ip, temp);
+		newlen = XFS_FILBLKS_MIN(xfs_bmap_worst_indlen(ip, temp),
+					 oldlen);
 		xfs_bmbt_set_allf(xfs_iext_get_ext(ifp, *idx),
 			new->br_startoff,
 			nullstartblock((int)newlen), temp, right.br_state);
@@ -2878,41 +2837,45 @@ xfs_bmap_add_extent_hole_delay(
  */
 STATIC int				/* error */
 xfs_bmap_add_extent_hole_real(
-	struct xfs_bmalloca	*bma,
-	int			whichfork)
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	int			whichfork,
+	xfs_extnum_t		*idx,
+	struct xfs_btree_cur	**curp,
+	struct xfs_bmbt_irec	*new,
+	xfs_fsblock_t		*first,
+	struct xfs_defer_ops	*dfops,
+	int			*logflagsp)
 {
-	struct xfs_bmbt_irec	*new = &bma->got;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_btree_cur	*cur = *curp;
 	int			error;	/* error return value */
 	int			i;	/* temp state */
-	xfs_ifork_t		*ifp;	/* inode fork pointer */
 	xfs_bmbt_irec_t		left;	/* left neighbor extent entry */
 	xfs_bmbt_irec_t		right;	/* right neighbor extent entry */
 	int			rval=0;	/* return value (logging flags) */
 	int			state;	/* state bits, accessed thru macros */
-	struct xfs_mount	*mp;
 
-	mp = bma->ip->i_mount;
-	ifp = XFS_IFORK_PTR(bma->ip, whichfork);
-
-	ASSERT(bma->idx >= 0);
-	ASSERT(bma->idx <= xfs_iext_count(ifp));
+	ASSERT(*idx >= 0);
+	ASSERT(*idx <= xfs_iext_count(ifp));
 	ASSERT(!isnullstartblock(new->br_startblock));
-	ASSERT(!bma->cur ||
-	       !(bma->cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL));
-	ASSERT(whichfork != XFS_COW_FORK);
+	ASSERT(!cur || !(cur->bc_private.b.flags & XFS_BTCUR_BPRV_WASDEL));
 
 	XFS_STATS_INC(mp, xs_add_exlist);
 
 	state = 0;
 	if (whichfork == XFS_ATTR_FORK)
 		state |= BMAP_ATTRFORK;
+	if (whichfork == XFS_COW_FORK)
+		state |= BMAP_COWFORK;
 
 	/*
 	 * Check and set flags if this segment has a left neighbor.
 	 */
-	if (bma->idx > 0) {
+	if (*idx > 0) {
 		state |= BMAP_LEFT_VALID;
-		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx - 1), &left);
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx - 1), &left);
 		if (isnullstartblock(left.br_startblock))
 			state |= BMAP_LEFT_DELAY;
 	}
@@ -2921,9 +2884,9 @@ xfs_bmap_add_extent_hole_real(
 	 * Check and set flags if this segment has a current value.
 	 * Not true if we're inserting into the "hole" at eof.
 	 */
-	if (bma->idx < xfs_iext_count(ifp)) {
+	if (*idx < xfs_iext_count(ifp)) {
 		state |= BMAP_RIGHT_VALID;
-		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, bma->idx), &right);
+		xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *idx), &right);
 		if (isnullstartblock(right.br_startblock))
 			state |= BMAP_RIGHT_DELAY;
 	}
@@ -2960,36 +2923,36 @@ xfs_bmap_add_extent_hole_real(
 		 * left and on the right.
 		 * Merge all three into a single extent record.
 		 */
-		--bma->idx;
-		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
-		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, bma->idx),
+		--*idx;
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx),
 			left.br_blockcount + new->br_blockcount +
 			right.br_blockcount);
-		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 
-		xfs_iext_remove(bma->ip, bma->idx + 1, 1, state);
+		xfs_iext_remove(ip, *idx + 1, 1, state);
 
-		XFS_IFORK_NEXT_SET(bma->ip, whichfork,
-			XFS_IFORK_NEXTENTS(bma->ip, whichfork) - 1);
-		if (bma->cur == NULL) {
+		XFS_IFORK_NEXT_SET(ip, whichfork,
+			XFS_IFORK_NEXTENTS(ip, whichfork) - 1);
+		if (cur == NULL) {
 			rval = XFS_ILOG_CORE | xfs_ilog_fext(whichfork);
 		} else {
 			rval = XFS_ILOG_CORE;
-			error = xfs_bmbt_lookup_eq(bma->cur, right.br_startoff,
+			error = xfs_bmbt_lookup_eq(cur, right.br_startoff,
 					right.br_startblock, right.br_blockcount,
 					&i);
 			if (error)
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
-			error = xfs_btree_delete(bma->cur, &i);
+			error = xfs_btree_delete(cur, &i);
 			if (error)
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
-			error = xfs_btree_decrement(bma->cur, 0, &i);
+			error = xfs_btree_decrement(cur, 0, &i);
 			if (error)
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
-			error = xfs_bmbt_update(bma->cur, left.br_startoff,
+			error = xfs_bmbt_update(cur, left.br_startoff,
 					left.br_startblock,
 					left.br_blockcount +
 						new->br_blockcount +
@@ -3006,23 +2969,23 @@ xfs_bmap_add_extent_hole_real(
 		 * on the left.
 		 * Merge the new allocation with the left neighbor.
 		 */
-		--bma->idx;
-		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
-		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, bma->idx),
+		--*idx;
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		xfs_bmbt_set_blockcount(xfs_iext_get_ext(ifp, *idx),
 			left.br_blockcount + new->br_blockcount);
-		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 
-		if (bma->cur == NULL) {
+		if (cur == NULL) {
 			rval = xfs_ilog_fext(whichfork);
 		} else {
 			rval = 0;
-			error = xfs_bmbt_lookup_eq(bma->cur, left.br_startoff,
+			error = xfs_bmbt_lookup_eq(cur, left.br_startoff,
 					left.br_startblock, left.br_blockcount,
 					&i);
 			if (error)
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
-			error = xfs_bmbt_update(bma->cur, left.br_startoff,
+			error = xfs_bmbt_update(cur, left.br_startoff,
 					left.br_startblock,
 					left.br_blockcount +
 						new->br_blockcount,
@@ -3038,25 +3001,25 @@ xfs_bmap_add_extent_hole_real(
 		 * on the right.
 		 * Merge the new allocation with the right neighbor.
 		 */
-		trace_xfs_bmap_pre_update(bma->ip, bma->idx, state, _THIS_IP_);
-		xfs_bmbt_set_allf(xfs_iext_get_ext(ifp, bma->idx),
+		trace_xfs_bmap_pre_update(ip, *idx, state, _THIS_IP_);
+		xfs_bmbt_set_allf(xfs_iext_get_ext(ifp, *idx),
 			new->br_startoff, new->br_startblock,
 			new->br_blockcount + right.br_blockcount,
 			right.br_state);
-		trace_xfs_bmap_post_update(bma->ip, bma->idx, state, _THIS_IP_);
+		trace_xfs_bmap_post_update(ip, *idx, state, _THIS_IP_);
 
-		if (bma->cur == NULL) {
+		if (cur == NULL) {
 			rval = xfs_ilog_fext(whichfork);
 		} else {
 			rval = 0;
-			error = xfs_bmbt_lookup_eq(bma->cur,
+			error = xfs_bmbt_lookup_eq(cur,
 					right.br_startoff,
 					right.br_startblock,
 					right.br_blockcount, &i);
 			if (error)
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
-			error = xfs_bmbt_update(bma->cur, new->br_startoff,
+			error = xfs_bmbt_update(cur, new->br_startoff,
 					new->br_startblock,
 					new->br_blockcount +
 						right.br_blockcount,
@@ -3072,22 +3035,22 @@ xfs_bmap_add_extent_hole_real(
 		 * real allocation.
 		 * Insert a new entry.
 		 */
-		xfs_iext_insert(bma->ip, bma->idx, 1, new, state);
-		XFS_IFORK_NEXT_SET(bma->ip, whichfork,
-			XFS_IFORK_NEXTENTS(bma->ip, whichfork) + 1);
-		if (bma->cur == NULL) {
+		xfs_iext_insert(ip, *idx, 1, new, state);
+		XFS_IFORK_NEXT_SET(ip, whichfork,
+			XFS_IFORK_NEXTENTS(ip, whichfork) + 1);
+		if (cur == NULL) {
 			rval = XFS_ILOG_CORE | xfs_ilog_fext(whichfork);
 		} else {
 			rval = XFS_ILOG_CORE;
-			error = xfs_bmbt_lookup_eq(bma->cur,
+			error = xfs_bmbt_lookup_eq(cur,
 					new->br_startoff,
 					new->br_startblock,
 					new->br_blockcount, &i);
 			if (error)
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(mp, i == 0, done);
-			bma->cur->bc_rec.b.br_state = new->br_state;
-			error = xfs_btree_insert(bma->cur, &i);
+			cur->bc_rec.b.br_state = new->br_state;
+			error = xfs_btree_insert(cur, &i);
 			if (error)
 				goto done;
 			XFS_WANT_CORRUPTED_GOTO(mp, i == 1, done);
@@ -3096,30 +3059,30 @@ xfs_bmap_add_extent_hole_real(
 	}
 
 	/* add reverse mapping */
-	error = xfs_rmap_map_extent(mp, bma->dfops, bma->ip, whichfork, new);
+	error = xfs_rmap_map_extent(mp, dfops, ip, whichfork, new);
 	if (error)
 		goto done;
 
 	/* convert to a btree if necessary */
-	if (xfs_bmap_needs_btree(bma->ip, whichfork)) {
+	if (xfs_bmap_needs_btree(ip, whichfork)) {
 		int	tmp_logflags;	/* partial log flag return val */
 
-		ASSERT(bma->cur == NULL);
-		error = xfs_bmap_extents_to_btree(bma->tp, bma->ip,
-				bma->firstblock, bma->dfops, &bma->cur,
+		ASSERT(cur == NULL);
+		error = xfs_bmap_extents_to_btree(tp, ip, first, dfops, curp,
 				0, &tmp_logflags, whichfork);
-		bma->logflags |= tmp_logflags;
+		*logflagsp |= tmp_logflags;
+		cur = *curp;
 		if (error)
 			goto done;
 	}
 
 	/* clear out the allocated field, done with it now in any case. */
-	if (bma->cur)
-		bma->cur->bc_private.b.allocated = 0;
+	if (cur)
+		cur->bc_private.b.allocated = 0;
 
-	xfs_bmap_check_leaf_extents(bma->cur, bma->ip, whichfork);
+	xfs_bmap_check_leaf_extents(cur, ip, whichfork);
 done:
-	bma->logflags |= rval;
+	*logflagsp |= rval;
 	return error;
 }
 
@@ -3822,17 +3785,13 @@ xfs_bmap_btalloc(
 		 * the first block that was allocated.
 		 */
 		ASSERT(*ap->firstblock == NULLFSBLOCK ||
-		       XFS_FSB_TO_AGNO(mp, *ap->firstblock) ==
-		       XFS_FSB_TO_AGNO(mp, args.fsbno) ||
-		       (ap->dfops->dop_low &&
-			XFS_FSB_TO_AGNO(mp, *ap->firstblock) <
-			XFS_FSB_TO_AGNO(mp, args.fsbno)));
+		       XFS_FSB_TO_AGNO(mp, *ap->firstblock) <=
+		       XFS_FSB_TO_AGNO(mp, args.fsbno));
 
 		ap->blkno = args.fsbno;
 		if (*ap->firstblock == NULLFSBLOCK)
 			*ap->firstblock = args.fsbno;
-		ASSERT(nullfb || fb_agno == args.agno ||
-		       (ap->dfops->dop_low && fb_agno < args.agno));
+		ASSERT(nullfb || fb_agno <= args.agno);
 		ap->length = args.len;
 		if (!(ap->flags & XFS_BMAPI_COWFORK))
 			ap->ip->i_d.di_nblocks += args.len;
@@ -3855,60 +3814,6 @@ xfs_bmap_btalloc(
 }
 
 /*
- * For a remap operation, just "allocate" an extent at the address that the
- * caller passed in, and ensure that the AGFL is the right size.  The caller
- * will then map the "allocated" extent into the file somewhere.
- */
-STATIC int
-xfs_bmap_remap_alloc(
-	struct xfs_bmalloca	*ap)
-{
-	struct xfs_trans	*tp = ap->tp;
-	struct xfs_mount	*mp = tp->t_mountp;
-	xfs_agblock_t		bno;
-	struct xfs_alloc_arg	args;
-	int			error;
-
-	/*
-	 * validate that the block number is legal - the enables us to detect
-	 * and handle a silent filesystem corruption rather than crashing.
-	 */
-	memset(&args, 0, sizeof(struct xfs_alloc_arg));
-	args.tp = ap->tp;
-	args.mp = ap->tp->t_mountp;
-	bno = *ap->firstblock;
-	args.agno = XFS_FSB_TO_AGNO(mp, bno);
-	args.agbno = XFS_FSB_TO_AGBNO(mp, bno);
-	if (args.agno >= mp->m_sb.sb_agcount ||
-	    args.agbno >= mp->m_sb.sb_agblocks)
-		return -EFSCORRUPTED;
-
-	/* "Allocate" the extent from the range we passed in. */
-	trace_xfs_bmap_remap_alloc(ap->ip, *ap->firstblock, ap->length);
-	ap->blkno = bno;
-	ap->ip->i_d.di_nblocks += ap->length;
-	xfs_trans_log_inode(ap->tp, ap->ip, XFS_ILOG_CORE);
-
-	/* Fix the freelist, like a real allocator does. */
-	args.datatype = ap->datatype;
-	args.pag = xfs_perag_get(args.mp, args.agno);
-	ASSERT(args.pag);
-
-	/*
-	 * The freelist fixing code will decline the allocation if
-	 * the size and shape of the free space doesn't allow for
-	 * allocating the extent and updating all the metadata that
-	 * happens during an allocation.  We're remapping, not
-	 * allocating, so skip that check by pretending to be freeing.
-	 */
-	error = xfs_alloc_fix_freelist(&args, XFS_ALLOC_FLAG_FREEING);
-	xfs_perag_put(args.pag);
-	if (error)
-		trace_xfs_bmap_remap_alloc_error(ap->ip, error, _RET_IP_);
-	return error;
-}
-
-/*
  * xfs_bmap_alloc is called by xfs_bmapi to allocate an extent for a file.
  * It figures out where to ask the underlying allocator to put the new extent.
  */
@@ -3916,8 +3821,6 @@ STATIC int
 xfs_bmap_alloc(
 	struct xfs_bmalloca	*ap)	/* bmap alloc argument struct */
 {
-	if (ap->flags & XFS_BMAPI_REMAP)
-		return xfs_bmap_remap_alloc(ap);
 	if (XFS_IS_REALTIME_INODE(ap->ip) &&
 	    xfs_alloc_is_userdata(ap->datatype))
 		return xfs_bmap_rtalloc(ap);
@@ -4089,7 +3992,7 @@ xfs_bmapi_read(
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT("xfs_bmapi_read", XFS_ERRLEVEL_LOW, mp);
 		return -EFSCORRUPTED;
 	}
@@ -4156,6 +4059,19 @@ xfs_bmapi_read(
 	return 0;
 }
 
+/*
+ * Add a delayed allocation extent to an inode. Blocks are reserved from the
+ * global pool and the extent inserted into the inode in-core extent tree.
+ *
+ * On entry, got refers to the first extent beyond the offset of the extent to
+ * allocate or eof is specified if no such extent exists. On return, got refers
+ * to the extent record that was inserted to the inode fork.
+ *
+ * Note that the allocated extent may have been merged with contiguous extents
+ * during insertion into the inode fork. Thus, got does not reflect the current
+ * state of the inode fork on return. If necessary, the caller can use lastx to
+ * look up the updated record in the inode fork.
+ */
 int
 xfs_bmapi_reserve_delalloc(
 	struct xfs_inode	*ip,
@@ -4242,13 +4158,8 @@ xfs_bmapi_reserve_delalloc(
 	got->br_startblock = nullstartblock(indlen);
 	got->br_blockcount = alen;
 	got->br_state = XFS_EXT_NORM;
-	xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
 
-	/*
-	 * Update our extent pointer, given that xfs_bmap_add_extent_hole_delay
-	 * might have merged it into one of the neighbouring ones.
-	 */
-	xfs_bmbt_get_all(xfs_iext_get_ext(ifp, *lastx), got);
+	xfs_bmap_add_extent_hole_delay(ip, whichfork, lastx, got);
 
 	/*
 	 * Tag the inode if blocks were preallocated. Note that COW fork
@@ -4260,10 +4171,6 @@ xfs_bmapi_reserve_delalloc(
 	if (whichfork == XFS_COW_FORK && (prealloc || aoff < off || alen > len))
 		xfs_inode_set_cowblocks_tag(ip);
 
-	ASSERT(got->br_startoff <= aoff);
-	ASSERT(got->br_startoff + got->br_blockcount >= aoff + alen);
-	ASSERT(isnullstartblock(got->br_startblock));
-	ASSERT(got->br_state == XFS_EXT_NORM);
 	return 0;
 
 out_unreserve_blocks:
@@ -4368,17 +4275,25 @@ xfs_bmapi_allocate(
 	bma->got.br_state = XFS_EXT_NORM;
 
 	/*
-	 * A wasdelay extent has been initialized, so shouldn't be flagged
-	 * as unwritten.
+	 * In the data fork, a wasdelay extent has been initialized, so
+	 * shouldn't be flagged as unwritten.
+	 *
+	 * For the cow fork, however, we convert delalloc reservations
+	 * (extents allocated for speculative preallocation) to
+	 * allocated unwritten extents, and only convert the unwritten
+	 * extents to real extents when we're about to write the data.
 	 */
-	if (!bma->wasdel && (bma->flags & XFS_BMAPI_PREALLOC) &&
+	if ((!bma->wasdel || (bma->flags & XFS_BMAPI_COWFORK)) &&
+	    (bma->flags & XFS_BMAPI_PREALLOC) &&
 	    xfs_sb_version_hasextflgbit(&mp->m_sb))
 		bma->got.br_state = XFS_EXT_UNWRITTEN;
 
 	if (bma->wasdel)
 		error = xfs_bmap_add_extent_delay_real(bma, whichfork);
 	else
-		error = xfs_bmap_add_extent_hole_real(bma, whichfork);
+		error = xfs_bmap_add_extent_hole_real(bma->tp, bma->ip,
+				whichfork, &bma->idx, &bma->cur, &bma->got,
+				bma->firstblock, bma->dfops, &bma->logflags);
 
 	bma->logflags |= tmp_logflags;
 	if (error)
@@ -4422,8 +4337,6 @@ xfs_bmapi_convert_unwritten(
 			(XFS_BMAPI_PREALLOC | XFS_BMAPI_CONVERT))
 		return 0;
 
-	ASSERT(whichfork != XFS_COW_FORK);
-
 	/*
 	 * Modify (by adding) the state flag, if writing.
 	 */
@@ -4448,8 +4361,8 @@ xfs_bmapi_convert_unwritten(
 			return error;
 	}
 
-	error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, &bma->idx,
-			&bma->cur, mval, bma->firstblock, bma->dfops,
+	error = xfs_bmap_add_extent_unwritten_real(bma->tp, bma->ip, whichfork,
+			&bma->idx, &bma->cur, mval, bma->firstblock, bma->dfops,
 			&tmp_logflags);
 	/*
 	 * Log the inode core unconditionally in the unwritten extent conversion
@@ -4458,8 +4371,12 @@ xfs_bmapi_convert_unwritten(
 	 * in the transaction for the sake of fsync(), even if nothing has
 	 * changed, because fsync() will not force the log for this transaction
 	 * unless it sees the inode pinned.
+	 *
+	 * Note: If we're only converting cow fork extents, there aren't
+	 * any on-disk updates to make, so we don't need to log anything.
 	 */
-	bma->logflags |= tmp_logflags | XFS_ILOG_CORE;
+	if (whichfork != XFS_COW_FORK)
+		bma->logflags |= tmp_logflags | XFS_ILOG_CORE;
 	if (error)
 		return error;
 
@@ -4533,15 +4450,13 @@ xfs_bmapi_write(
 	ASSERT(*nmap >= 1);
 	ASSERT(*nmap <= XFS_BMAP_MAX_NMAP);
 	ASSERT(!(flags & XFS_BMAPI_IGSTATE));
-	ASSERT(tp != NULL);
+	ASSERT(tp != NULL ||
+	       (flags & (XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK)) ==
+			(XFS_BMAPI_CONVERT | XFS_BMAPI_COWFORK));
 	ASSERT(len > 0);
 	ASSERT(XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_LOCAL);
 	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
-	ASSERT(!(flags & XFS_BMAPI_REMAP) || whichfork == XFS_DATA_FORK);
-	ASSERT(!(flags & XFS_BMAPI_PREALLOC) || !(flags & XFS_BMAPI_REMAP));
-	ASSERT(!(flags & XFS_BMAPI_CONVERT) || !(flags & XFS_BMAPI_REMAP));
-	ASSERT(!(flags & XFS_BMAPI_PREALLOC) || whichfork != XFS_COW_FORK);
-	ASSERT(!(flags & XFS_BMAPI_CONVERT) || whichfork != XFS_COW_FORK);
+	ASSERT(!(flags & XFS_BMAPI_REMAP));
 
 	/* zeroing is for currently only for data extents, not metadata */
 	ASSERT((flags & (XFS_BMAPI_METADATA | XFS_BMAPI_ZERO)) !=
@@ -4558,7 +4473,7 @@ xfs_bmapi_write(
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT("xfs_bmapi_write", XFS_ERRLEVEL_LOW, mp);
 		return -EFSCORRUPTED;
 	}
@@ -4625,13 +4540,8 @@ xfs_bmapi_write(
 			} else {
 				need_alloc = true;
 			}
-		} else {
-			/*
-			 * Make sure we only reflink into a hole.
-			 */
-			ASSERT(!(flags & XFS_BMAPI_REMAP));
-			if (isnullstartblock(bma.got.br_startblock))
-				wasdelay = true;
+		} else if (isnullstartblock(bma.got.br_startblock)) {
+			wasdelay = true;
 		}
 
 		/*
@@ -4746,13 +4656,9 @@ error0:
 	if (bma.cur) {
 		if (!error) {
 			ASSERT(*firstblock == NULLFSBLOCK ||
-			       XFS_FSB_TO_AGNO(mp, *firstblock) ==
+			       XFS_FSB_TO_AGNO(mp, *firstblock) <=
 			       XFS_FSB_TO_AGNO(mp,
-				       bma.cur->bc_private.b.firstblock) ||
-			       (dfops->dop_low &&
-				XFS_FSB_TO_AGNO(mp, *firstblock) <
-				XFS_FSB_TO_AGNO(mp,
-					bma.cur->bc_private.b.firstblock)));
+				       bma.cur->bc_private.b.firstblock));
 			*firstblock = bma.cur->bc_private.b.firstblock;
 		}
 		xfs_btree_del_cursor(bma.cur,
@@ -4764,6 +4670,93 @@ error0:
 	return error;
 }
 
+static int
+xfs_bmapi_remap(
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	xfs_fileoff_t		bno,
+	xfs_filblks_t		len,
+	xfs_fsblock_t		startblock,
+	struct xfs_defer_ops	*dfops)
+{
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+	struct xfs_btree_cur	*cur = NULL;
+	xfs_fsblock_t		firstblock = NULLFSBLOCK;
+	struct xfs_bmbt_irec	got;
+	xfs_extnum_t		idx;
+	int			logflags = 0, error;
+
+	ASSERT(len > 0);
+	ASSERT(len <= (xfs_filblks_t)MAXEXTLEN);
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL));
+
+	if (unlikely(XFS_TEST_ERROR(
+	    (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS &&
+	     XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE),
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
+		XFS_ERROR_REPORT("xfs_bmapi_remap", XFS_ERRLEVEL_LOW, mp);
+		return -EFSCORRUPTED;
+	}
+
+	if (XFS_FORCED_SHUTDOWN(mp))
+		return -EIO;
+
+	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+		error = xfs_iread_extents(NULL, ip, XFS_DATA_FORK);
+		if (error)
+			return error;
+	}
+
+	if (xfs_iext_lookup_extent(ip, ifp, bno, &idx, &got)) {
+		/* make sure we only reflink into a hole. */
+		ASSERT(got.br_startoff > bno);
+		ASSERT(got.br_startoff - bno >= len);
+	}
+
+	ip->i_d.di_nblocks += len;
+	xfs_trans_log_inode(tp, ip, XFS_ILOG_CORE);
+
+	if (ifp->if_flags & XFS_IFBROOT) {
+		cur = xfs_bmbt_init_cursor(mp, tp, ip, XFS_DATA_FORK);
+		cur->bc_private.b.firstblock = firstblock;
+		cur->bc_private.b.dfops = dfops;
+		cur->bc_private.b.flags = 0;
+	}
+
+	got.br_startoff = bno;
+	got.br_startblock = startblock;
+	got.br_blockcount = len;
+	got.br_state = XFS_EXT_NORM;
+
+	error = xfs_bmap_add_extent_hole_real(tp, ip, XFS_DATA_FORK, &idx, &cur,
+			&got, &firstblock, dfops, &logflags);
+	if (error)
+		goto error0;
+
+	if (xfs_bmap_wants_extents(ip, XFS_DATA_FORK)) {
+		int		tmp_logflags = 0;
+
+		error = xfs_bmap_btree_to_extents(tp, ip, cur,
+			&tmp_logflags, XFS_DATA_FORK);
+		logflags |= tmp_logflags;
+	}
+
+error0:
+	if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS)
+		logflags &= ~XFS_ILOG_DEXT;
+	else if (ip->i_d.di_format != XFS_DINODE_FMT_BTREE)
+		logflags &= ~XFS_ILOG_DBROOT;
+
+	if (logflags)
+		xfs_trans_log_inode(tp, ip, logflags);
+	if (cur) {
+		xfs_btree_del_cursor(cur,
+				error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	}
+	return error;
+}
+
 /*
  * When a delalloc extent is split (e.g., due to a hole punch), the original
  * indlen reservation must be shared across the two new extents that are left
@@ -4787,34 +4780,59 @@ xfs_bmap_split_indlen(
 	xfs_filblks_t			len2 = *indlen2;
 	xfs_filblks_t			nres = len1 + len2; /* new total res. */
 	xfs_filblks_t			stolen = 0;
+	xfs_filblks_t			resfactor;
 
 	/*
 	 * Steal as many blocks as we can to try and satisfy the worst case
 	 * indlen for both new extents.
 	 */
-	while (nres > ores && avail) {
-		nres--;
-		avail--;
-		stolen++;
-	}
+	if (ores < nres && avail)
+		stolen = XFS_FILBLKS_MIN(nres - ores, avail);
+	ores += stolen;
+
+	 /* nothing else to do if we've satisfied the new reservation */
+	if (ores >= nres)
+		return stolen;
 
 	/*
-	 * The only blocks available are those reserved for the original
-	 * extent and what we can steal from the extent being removed.
-	 * If this still isn't enough to satisfy the combined
-	 * requirements for the two new extents, skim blocks off of each
-	 * of the new reservations until they match what is available.
+	 * We can't meet the total required reservation for the two extents.
+	 * Calculate the percent of the overall shortage between both extents
+	 * and apply this percentage to each of the requested indlen values.
+	 * This distributes the shortage fairly and reduces the chances that one
+	 * of the two extents is left with nothing when extents are repeatedly
+	 * split.
 	 */
-	while (nres > ores) {
-		if (len1) {
-			len1--;
-			nres--;
+	resfactor = (ores * 100);
+	do_div(resfactor, nres);
+	len1 *= resfactor;
+	do_div(len1, 100);
+	len2 *= resfactor;
+	do_div(len2, 100);
+	ASSERT(len1 + len2 <= ores);
+	ASSERT(len1 < *indlen1 && len2 < *indlen2);
+
+	/*
+	 * Hand out the remainder to each extent. If one of the two reservations
+	 * is zero, we want to make sure that one gets a block first. The loop
+	 * below starts with len1, so hand len2 a block right off the bat if it
+	 * is zero.
+	 */
+	ores -= (len1 + len2);
+	ASSERT((*indlen1 - len1) + (*indlen2 - len2) >= ores);
+	if (ores && !len2 && *indlen2) {
+		len2++;
+		ores--;
+	}
+	while (ores) {
+		if (len1 < *indlen1) {
+			len1++;
+			ores--;
 		}
-		if (nres == ores)
+		if (!ores)
 			break;
-		if (len2) {
-			len2--;
-			nres--;
+		if (len2 < *indlen2) {
+			len2++;
+			ores--;
 		}
 	}
 
@@ -4856,7 +4874,7 @@ xfs_bmap_del_extent_delay(
 	ASSERT(got_endoff >= del_endoff);
 
 	if (isrt) {
-		int64_t rtexts = XFS_FSB_TO_B(mp, del->br_blockcount);
+		uint64_t rtexts = XFS_FSB_TO_B(mp, del->br_blockcount);
 
 		do_div(rtexts, mp->m_sb.sb_rextsize);
 		xfs_mod_frextents(mp, rtexts);
@@ -5416,6 +5434,7 @@ __xfs_bunmapi(
 	int			whichfork;	/* data or attribute fork */
 	xfs_fsblock_t		sum;
 	xfs_filblks_t		len = *rlen;	/* length to unmap in file */
+	xfs_fileoff_t		max_len;
 
 	trace_xfs_bunmap(ip, bno, len, flags, _RET_IP_);
 
@@ -5437,6 +5456,16 @@ __xfs_bunmapi(
 	ASSERT(len > 0);
 	ASSERT(nexts >= 0);
 
+	/*
+	 * Guesstimate how many blocks we can unmap without running the risk of
+	 * blowing out the transaction with a mix of EFIs and reflink
+	 * adjustments.
+	 */
+	if (xfs_is_reflink_inode(ip) && whichfork == XFS_DATA_FORK)
+		max_len = min(len, xfs_refcount_max_unmap(tp->t_log_res));
+	else
+		max_len = len;
+
 	if (!(ifp->if_flags & XFS_IFEXTENTS) &&
 	    (error = xfs_iread_extents(tp, ip, whichfork)))
 		return error;
@@ -5481,7 +5510,7 @@ __xfs_bunmapi(
 
 	extno = 0;
 	while (bno != (xfs_fileoff_t)-1 && bno >= start && lastx >= 0 &&
-	       (nexts == 0 || extno < nexts)) {
+	       (nexts == 0 || extno < nexts) && max_len > 0) {
 		/*
 		 * Is the found extent after a hole in which bno lives?
 		 * Just back up to the previous extent, if so.
@@ -5513,6 +5542,15 @@ __xfs_bunmapi(
 		}
 		if (del.br_startoff + del.br_blockcount > bno + 1)
 			del.br_blockcount = bno + 1 - del.br_startoff;
+
+		/* How much can we safely unmap? */
+		if (max_len < del.br_blockcount) {
+			del.br_startoff += del.br_blockcount - max_len;
+			if (!wasdel)
+				del.br_startblock += del.br_blockcount - max_len;
+			del.br_blockcount = max_len;
+		}
+
 		sum = del.br_startblock + del.br_blockcount;
 		if (isrt &&
 		    (mod = do_mod(sum, mp->m_sb.sb_rextsize))) {
@@ -5556,8 +5594,8 @@ __xfs_bunmapi(
 			}
 			del.br_state = XFS_EXT_UNWRITTEN;
 			error = xfs_bmap_add_extent_unwritten_real(tp, ip,
-					&lastx, &cur, &del, firstblock, dfops,
-					&logflags);
+					whichfork, &lastx, &cur, &del,
+					firstblock, dfops, &logflags);
 			if (error)
 				goto error0;
 			goto nodelete;
@@ -5610,8 +5648,9 @@ __xfs_bunmapi(
 				prev.br_state = XFS_EXT_UNWRITTEN;
 				lastx--;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
-						ip, &lastx, &cur, &prev,
-						firstblock, dfops, &logflags);
+						ip, whichfork, &lastx, &cur,
+						&prev, firstblock, dfops,
+						&logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5619,8 +5658,9 @@ __xfs_bunmapi(
 				ASSERT(del.br_state == XFS_EXT_NORM);
 				del.br_state = XFS_EXT_UNWRITTEN;
 				error = xfs_bmap_add_extent_unwritten_real(tp,
-						ip, &lastx, &cur, &del,
-						firstblock, dfops, &logflags);
+						ip, whichfork, &lastx, &cur,
+						&del, firstblock, dfops,
+						&logflags);
 				if (error)
 					goto error0;
 				goto nodelete;
@@ -5687,6 +5727,7 @@ __xfs_bunmapi(
 		if (!isrt && wasdel)
 			xfs_mod_fdblocks(mp, (int64_t)del.br_blockcount, false);
 
+		max_len -= del.br_blockcount;
 		bno = del.br_startoff - 1;
 nodelete:
 		/*
@@ -6057,7 +6098,7 @@ xfs_bmap_shift_extents(
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT("xfs_bmap_shift_extents",
 				 XFS_ERRLEVEL_LOW, mp);
 		return -EFSCORRUPTED;
@@ -6209,7 +6250,7 @@ xfs_bmap_split_extent_at(
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, whichfork) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT("xfs_bmap_split_extent_at",
 				 XFS_ERRLEVEL_LOW, mp);
 		return -EFSCORRUPTED;
@@ -6452,49 +6493,33 @@ xfs_bmap_finish_one(
 	int				whichfork,
 	xfs_fileoff_t			startoff,
 	xfs_fsblock_t			startblock,
-	xfs_filblks_t			blockcount,
+	xfs_filblks_t			*blockcount,
 	xfs_exntst_t			state)
 {
-	struct xfs_bmbt_irec		bmap;
-	int				nimaps = 1;
 	xfs_fsblock_t			firstfsb;
-	int				flags = XFS_BMAPI_REMAP;
-	int				done;
 	int				error = 0;
 
-	bmap.br_startblock = startblock;
-	bmap.br_startoff = startoff;
-	bmap.br_blockcount = blockcount;
-	bmap.br_state = state;
-
 	trace_xfs_bmap_deferred(tp->t_mountp,
 			XFS_FSB_TO_AGNO(tp->t_mountp, startblock), type,
 			XFS_FSB_TO_AGBNO(tp->t_mountp, startblock),
-			ip->i_ino, whichfork, startoff, blockcount, state);
+			ip->i_ino, whichfork, startoff, *blockcount, state);
 
-	if (whichfork != XFS_DATA_FORK && whichfork != XFS_ATTR_FORK)
+	if (WARN_ON_ONCE(whichfork != XFS_DATA_FORK))
 		return -EFSCORRUPTED;
-	if (whichfork == XFS_ATTR_FORK)
-		flags |= XFS_BMAPI_ATTRFORK;
 
 	if (XFS_TEST_ERROR(false, tp->t_mountp,
-			XFS_ERRTAG_BMAP_FINISH_ONE,
-			XFS_RANDOM_BMAP_FINISH_ONE))
+			XFS_ERRTAG_BMAP_FINISH_ONE))
 		return -EIO;
 
 	switch (type) {
 	case XFS_BMAP_MAP:
-		firstfsb = bmap.br_startblock;
-		error = xfs_bmapi_write(tp, ip, bmap.br_startoff,
-					bmap.br_blockcount, flags, &firstfsb,
-					bmap.br_blockcount, &bmap, &nimaps,
-					dfops);
+		error = xfs_bmapi_remap(tp, ip, startoff, *blockcount,
+				startblock, dfops);
+		*blockcount = 0;
 		break;
 	case XFS_BMAP_UNMAP:
-		error = xfs_bunmapi(tp, ip, bmap.br_startoff,
-				bmap.br_blockcount, flags, 1, &firstfsb,
-				dfops, &done);
-		ASSERT(done);
+		error = __xfs_bunmapi(tp, ip, startoff, blockcount,
+				XFS_BMAPI_REMAP, 1, &firstfsb, dfops);
 		break;
 	default:
 		ASSERT(0);
diff --git a/fs/xfs/libxfs/xfs_bmap.h b/fs/xfs/libxfs/xfs_bmap.h
index cdef87db5262..851982a5dfbc 100644
--- a/fs/xfs/libxfs/xfs_bmap.h
+++ b/fs/xfs/libxfs/xfs_bmap.h
@@ -172,6 +172,18 @@ static inline int xfs_bmapi_whichfork(int bmapi_flags)
 
 
 /*
+ * Return true if the extent is a real, allocated extent, or false if it is  a
+ * delayed allocation, and unwritten extent or a hole.
+ */
+static inline bool xfs_bmap_is_real_extent(struct xfs_bmbt_irec *irec)
+{
+	return irec->br_state != XFS_EXT_UNWRITTEN &&
+		irec->br_startblock != HOLESTARTBLOCK &&
+		irec->br_startblock != DELAYSTARTBLOCK &&
+		!isnullstartblock(irec->br_startblock);
+}
+
+/*
  * This macro is used to determine how many extents will be shifted
  * in one write transaction. We could require two splits,
  * an extent move on the first and an extent merge on the second,
@@ -232,8 +244,6 @@ int	xfs_bmap_del_extent_delay(struct xfs_inode *ip, int whichfork,
 		struct xfs_bmbt_irec *del);
 void	xfs_bmap_del_extent_cow(struct xfs_inode *ip, xfs_extnum_t *idx,
 		struct xfs_bmbt_irec *got, struct xfs_bmbt_irec *del);
-int	xfs_check_nostate_extents(struct xfs_ifork *ifp, xfs_extnum_t idx,
-		xfs_extnum_t num);
 uint	xfs_default_attroffset(struct xfs_inode *ip);
 int	xfs_bmap_shift_extents(struct xfs_trans *tp, struct xfs_inode *ip,
 		xfs_fileoff_t *next_fsb, xfs_fileoff_t offset_shift_fsb,
@@ -261,7 +271,7 @@ struct xfs_bmap_intent {
 int	xfs_bmap_finish_one(struct xfs_trans *tp, struct xfs_defer_ops *dfops,
 		struct xfs_inode *ip, enum xfs_bmap_intent_type type,
 		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
-		xfs_filblks_t blockcount, xfs_exntst_t state);
+		xfs_filblks_t *blockcount, xfs_exntst_t state);
 int	xfs_bmap_map_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
 		struct xfs_inode *ip, struct xfs_bmbt_irec *imap);
 int	xfs_bmap_unmap_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.c b/fs/xfs/libxfs/xfs_bmap_btree.c
index d9be241fc86f..85de22513014 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.c
+++ b/fs/xfs/libxfs/xfs_bmap_btree.c
@@ -71,15 +71,9 @@ xfs_bmdr_to_bmbt(
 	xfs_bmbt_key_t		*tkp;
 	__be64			*tpp;
 
-	if (xfs_sb_version_hascrc(&mp->m_sb))
-		xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL,
-				 XFS_BMAP_CRC_MAGIC, 0, 0, ip->i_ino,
-				 XFS_BTREE_LONG_PTRS | XFS_BTREE_CRC_BLOCKS);
-	else
-		xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL,
-				 XFS_BMAP_MAGIC, 0, 0, ip->i_ino,
+	xfs_btree_init_block_int(mp, rblock, XFS_BUF_DADDR_NULL,
+				 XFS_BTNUM_BMAP, 0, 0, ip->i_ino,
 				 XFS_BTREE_LONG_PTRS);
-
 	rblock->bb_level = dblock->bb_level;
 	ASSERT(be16_to_cpu(rblock->bb_level) > 0);
 	rblock->bb_numrecs = dblock->bb_numrecs;
@@ -100,8 +94,8 @@ xfs_bmdr_to_bmbt(
  */
 STATIC void
 __xfs_bmbt_get_all(
-		__uint64_t l0,
-		__uint64_t l1,
+		uint64_t l0,
+		uint64_t l1,
 		xfs_bmbt_irec_t *s)
 {
 	int	ext_flag;
@@ -372,32 +366,6 @@ xfs_bmbt_to_bmdr(
 	memcpy(tpp, fpp, sizeof(*fpp) * dmxr);
 }
 
-/*
- * Check extent records, which have just been read, for
- * any bit in the extent flag field. ASSERT on debug
- * kernels, as this condition should not occur.
- * Return an error condition (1) if any flags found,
- * otherwise return 0.
- */
-
-int
-xfs_check_nostate_extents(
-	xfs_ifork_t		*ifp,
-	xfs_extnum_t		idx,
-	xfs_extnum_t		num)
-{
-	for (; num > 0; num--, idx++) {
-		xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, idx);
-		if ((ep->l0 >>
-		     (64 - BMBT_EXNTFLAG_BITLEN)) != 0) {
-			ASSERT(0);
-			return 1;
-		}
-	}
-	return 0;
-}
-
-
 STATIC struct xfs_btree_cur *
 xfs_bmbt_dup_cursor(
 	struct xfs_btree_cur	*cur)
@@ -453,7 +421,6 @@ xfs_bmbt_alloc_block(
 
 	if (args.fsbno == NULLFSBLOCK) {
 		args.fsbno = be64_to_cpu(start->l);
-try_another_ag:
 		args.type = XFS_ALLOCTYPE_START_BNO;
 		/*
 		 * Make sure there is sufficient room left in the AG to
@@ -483,22 +450,6 @@ try_another_ag:
 	if (error)
 		goto error0;
 
-	/*
-	 * During a CoW operation, the allocation and bmbt updates occur in
-	 * different transactions.  The mapping code tries to put new bmbt
-	 * blocks near extents being mapped, but the only way to guarantee this
-	 * is if the alloc and the mapping happen in a single transaction that
-	 * has a block reservation.  That isn't the case here, so if we run out
-	 * of space we'll try again with another AG.
-	 */
-	if (xfs_sb_version_hasreflink(&cur->bc_mp->m_sb) &&
-	    args.fsbno == NULLFSBLOCK &&
-	    args.type == XFS_ALLOCTYPE_NEAR_BNO) {
-		cur->bc_private.b.dfops->dop_low = true;
-		args.fsbno = cur->bc_private.b.firstblock;
-		goto try_another_ag;
-	}
-
 	if (args.fsbno == NULLFSBLOCK && args.minleft) {
 		/*
 		 * Could not find an AG with enough free space to satisfy
@@ -512,7 +463,7 @@ try_another_ag:
 			goto error0;
 		cur->bc_private.b.dfops->dop_low = true;
 	}
-	if (args.fsbno == NULLFSBLOCK) {
+	if (WARN_ON_ONCE(args.fsbno == NULLFSBLOCK)) {
 		XFS_BTREE_TRACE_CURSOR(cur, XBT_EXIT);
 		*stat = 0;
 		return 0;
@@ -622,6 +573,16 @@ xfs_bmbt_init_key_from_rec(
 }
 
 STATIC void
+xfs_bmbt_init_high_key_from_rec(
+	union xfs_btree_key	*key,
+	union xfs_btree_rec	*rec)
+{
+	key->bmbt.br_startoff = cpu_to_be64(
+			xfs_bmbt_disk_get_startoff(&rec->bmbt) +
+			xfs_bmbt_disk_get_blockcount(&rec->bmbt) - 1);
+}
+
+STATIC void
 xfs_bmbt_init_rec_from_cur(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_rec	*rec)
@@ -637,15 +598,25 @@ xfs_bmbt_init_ptr_from_cur(
 	ptr->l = 0;
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_bmbt_key_diff(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*key)
 {
-	return (__int64_t)be64_to_cpu(key->bmbt.br_startoff) -
+	return (int64_t)be64_to_cpu(key->bmbt.br_startoff) -
 				      cur->bc_rec.b.br_startoff;
 }
 
+STATIC int64_t
+xfs_bmbt_diff_two_keys(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*k1,
+	union xfs_btree_key	*k2)
+{
+	return (int64_t)be64_to_cpu(k1->bmbt.br_startoff) -
+			  be64_to_cpu(k2->bmbt.br_startoff);
+}
+
 static bool
 xfs_bmbt_verify(
 	struct xfs_buf		*bp)
@@ -736,7 +707,6 @@ const struct xfs_buf_ops xfs_bmbt_buf_ops = {
 };
 
 
-#if defined(DEBUG) || defined(XFS_WARN)
 STATIC int
 xfs_bmbt_keys_inorder(
 	struct xfs_btree_cur	*cur,
@@ -757,7 +727,6 @@ xfs_bmbt_recs_inorder(
 		xfs_bmbt_disk_get_blockcount(&r1->bmbt) <=
 		xfs_bmbt_disk_get_startoff(&r2->bmbt);
 }
-#endif	/* DEBUG */
 
 static const struct xfs_btree_ops xfs_bmbt_ops = {
 	.rec_len		= sizeof(xfs_bmbt_rec_t),
@@ -771,14 +740,14 @@ static const struct xfs_btree_ops xfs_bmbt_ops = {
 	.get_minrecs		= xfs_bmbt_get_minrecs,
 	.get_dmaxrecs		= xfs_bmbt_get_dmaxrecs,
 	.init_key_from_rec	= xfs_bmbt_init_key_from_rec,
+	.init_high_key_from_rec	= xfs_bmbt_init_high_key_from_rec,
 	.init_rec_from_cur	= xfs_bmbt_init_rec_from_cur,
 	.init_ptr_from_cur	= xfs_bmbt_init_ptr_from_cur,
 	.key_diff		= xfs_bmbt_key_diff,
+	.diff_two_keys		= xfs_bmbt_diff_two_keys,
 	.buf_ops		= &xfs_bmbt_buf_ops,
-#if defined(DEBUG) || defined(XFS_WARN)
 	.keys_inorder		= xfs_bmbt_keys_inorder,
 	.recs_inorder		= xfs_bmbt_recs_inorder,
-#endif
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_bmap_btree.h b/fs/xfs/libxfs/xfs_bmap_btree.h
index 819a8a4dee95..9da5a8d4f184 100644
--- a/fs/xfs/libxfs/xfs_bmap_btree.h
+++ b/fs/xfs/libxfs/xfs_bmap_btree.h
@@ -25,14 +25,6 @@ struct xfs_inode;
 struct xfs_trans;
 
 /*
- * Extent state and extent format macros.
- */
-#define XFS_EXTFMT_INODE(x)	\
-	(xfs_sb_version_hasextflgbit(&((x)->i_mount->m_sb)) ? \
-		XFS_EXTFMT_HASSTATE : XFS_EXTFMT_NOSTATE)
-#define ISUNWRITTEN(x)	((x)->br_state == XFS_EXT_UNWRITTEN)
-
-/*
  * Btree block header size depends on a superblock flag.
  */
 #define XFS_BMBT_BLOCK_LEN(mp) \
@@ -140,4 +132,18 @@ extern int xfs_bmbt_change_owner(struct xfs_trans *tp, struct xfs_inode *ip,
 extern struct xfs_btree_cur *xfs_bmbt_init_cursor(struct xfs_mount *,
 		struct xfs_trans *, struct xfs_inode *, int);
 
+/*
+ * Check that the extent does not contain an invalid unwritten extent flag.
+ */
+static inline bool xfs_bmbt_validate_extent(struct xfs_mount *mp, int whichfork,
+		struct xfs_bmbt_rec_host *ep)
+{
+	if (ep->l0 >> (64 - BMBT_EXNTFLAG_BITLEN) == 0)
+		return true;
+	if (whichfork == XFS_DATA_FORK &&
+	    xfs_sb_version_hasextflgbit(&mp->m_sb))
+		return true;
+	return false;
+}
+
 #endif	/* __XFS_BMAP_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_btree.c b/fs/xfs/libxfs/xfs_btree.c
index 21e6a6ab6b9a..4da85fff69ad 100644
--- a/fs/xfs/libxfs/xfs_btree.c
+++ b/fs/xfs/libxfs/xfs_btree.c
@@ -43,15 +43,25 @@ kmem_zone_t	*xfs_btree_cur_zone;
 /*
  * Btree magic numbers.
  */
-static const __uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
+static const uint32_t xfs_magics[2][XFS_BTNUM_MAX] = {
 	{ XFS_ABTB_MAGIC, XFS_ABTC_MAGIC, 0, XFS_BMAP_MAGIC, XFS_IBT_MAGIC,
 	  XFS_FIBT_MAGIC, 0 },
 	{ XFS_ABTB_CRC_MAGIC, XFS_ABTC_CRC_MAGIC, XFS_RMAP_CRC_MAGIC,
 	  XFS_BMAP_CRC_MAGIC, XFS_IBT_CRC_MAGIC, XFS_FIBT_CRC_MAGIC,
 	  XFS_REFC_CRC_MAGIC }
 };
-#define xfs_btree_magic(cur) \
-	xfs_magics[!!((cur)->bc_flags & XFS_BTREE_CRC_BLOCKS)][cur->bc_btnum]
+
+uint32_t
+xfs_btree_magic(
+	int			crc,
+	xfs_btnum_t		btnum)
+{
+	uint32_t		magic = xfs_magics[crc][btnum];
+
+	/* Ensure we asked for crc for crc-only magics. */
+	ASSERT(magic != 0);
+	return magic;
+}
 
 STATIC int				/* error (0 or EFSCORRUPTED) */
 xfs_btree_check_lblock(
@@ -62,10 +72,13 @@ xfs_btree_check_lblock(
 {
 	int			lblock_ok = 1; /* block passes checks */
 	struct xfs_mount	*mp;	/* file system mount point */
+	xfs_btnum_t		btnum = cur->bc_btnum;
+	int			crc;
 
 	mp = cur->bc_mp;
+	crc = xfs_sb_version_hascrc(&mp->m_sb);
 
-	if (xfs_sb_version_hascrc(&mp->m_sb)) {
+	if (crc) {
 		lblock_ok = lblock_ok &&
 			uuid_equal(&block->bb_u.l.bb_uuid,
 				   &mp->m_sb.sb_meta_uuid) &&
@@ -74,7 +87,7 @@ xfs_btree_check_lblock(
 	}
 
 	lblock_ok = lblock_ok &&
-		be32_to_cpu(block->bb_magic) == xfs_btree_magic(cur) &&
+		be32_to_cpu(block->bb_magic) == xfs_btree_magic(crc, btnum) &&
 		be16_to_cpu(block->bb_level) == level &&
 		be16_to_cpu(block->bb_numrecs) <=
 			cur->bc_ops->get_maxrecs(cur, level) &&
@@ -88,8 +101,7 @@ xfs_btree_check_lblock(
 			be64_to_cpu(block->bb_u.l.bb_rightsib)));
 
 	if (unlikely(XFS_TEST_ERROR(!lblock_ok, mp,
-			XFS_ERRTAG_BTREE_CHECK_LBLOCK,
-			XFS_RANDOM_BTREE_CHECK_LBLOCK))) {
+			XFS_ERRTAG_BTREE_CHECK_LBLOCK))) {
 		if (bp)
 			trace_xfs_btree_corrupt(bp, _RET_IP_);
 		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
@@ -110,13 +122,16 @@ xfs_btree_check_sblock(
 	struct xfs_agf		*agf;	/* ag. freespace structure */
 	xfs_agblock_t		agflen;	/* native ag. freespace length */
 	int			sblock_ok = 1; /* block passes checks */
+	xfs_btnum_t		btnum = cur->bc_btnum;
+	int			crc;
 
 	mp = cur->bc_mp;
+	crc = xfs_sb_version_hascrc(&mp->m_sb);
 	agbp = cur->bc_private.a.agbp;
 	agf = XFS_BUF_TO_AGF(agbp);
 	agflen = be32_to_cpu(agf->agf_length);
 
-	if (xfs_sb_version_hascrc(&mp->m_sb)) {
+	if (crc) {
 		sblock_ok = sblock_ok &&
 			uuid_equal(&block->bb_u.s.bb_uuid,
 				   &mp->m_sb.sb_meta_uuid) &&
@@ -125,7 +140,7 @@ xfs_btree_check_sblock(
 	}
 
 	sblock_ok = sblock_ok &&
-		be32_to_cpu(block->bb_magic) == xfs_btree_magic(cur) &&
+		be32_to_cpu(block->bb_magic) == xfs_btree_magic(crc, btnum) &&
 		be16_to_cpu(block->bb_level) == level &&
 		be16_to_cpu(block->bb_numrecs) <=
 			cur->bc_ops->get_maxrecs(cur, level) &&
@@ -137,8 +152,7 @@ xfs_btree_check_sblock(
 		block->bb_u.s.bb_rightsib;
 
 	if (unlikely(XFS_TEST_ERROR(!sblock_ok, mp,
-			XFS_ERRTAG_BTREE_CHECK_SBLOCK,
-			XFS_RANDOM_BTREE_CHECK_SBLOCK))) {
+			XFS_ERRTAG_BTREE_CHECK_SBLOCK))) {
 		if (bp)
 			trace_xfs_btree_corrupt(bp, _RET_IP_);
 		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
@@ -552,7 +566,7 @@ xfs_btree_ptr_offset(
 /*
  * Return a pointer to the n-th record in the btree block.
  */
-STATIC union xfs_btree_rec *
+union xfs_btree_rec *
 xfs_btree_rec_addr(
 	struct xfs_btree_cur	*cur,
 	int			n,
@@ -565,7 +579,7 @@ xfs_btree_rec_addr(
 /*
  * Return a pointer to the n-th key in the btree block.
  */
-STATIC union xfs_btree_key *
+union xfs_btree_key *
 xfs_btree_key_addr(
 	struct xfs_btree_cur	*cur,
 	int			n,
@@ -578,7 +592,7 @@ xfs_btree_key_addr(
 /*
  * Return a pointer to the n-th high key in the btree block.
  */
-STATIC union xfs_btree_key *
+union xfs_btree_key *
 xfs_btree_high_key_addr(
 	struct xfs_btree_cur	*cur,
 	int			n,
@@ -591,7 +605,7 @@ xfs_btree_high_key_addr(
 /*
  * Return a pointer to the n-th block pointer in the btree block.
  */
-STATIC union xfs_btree_ptr *
+union xfs_btree_ptr *
 xfs_btree_ptr_addr(
 	struct xfs_btree_cur	*cur,
 	int			n,
@@ -625,7 +639,7 @@ xfs_btree_get_iroot(
  * Retrieve the block pointer from the cursor at the given level.
  * This may be an inode btree root or from a buffer.
  */
-STATIC struct xfs_btree_block *		/* generic btree block pointer */
+struct xfs_btree_block *		/* generic btree block pointer */
 xfs_btree_get_block(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	int			level,	/* level in btree */
@@ -762,14 +776,14 @@ xfs_btree_lastrec(
  */
 void
 xfs_btree_offsets(
-	__int64_t	fields,		/* bitmask of fields */
+	int64_t		fields,		/* bitmask of fields */
 	const short	*offsets,	/* table of field offsets */
 	int		nbits,		/* number of bits to inspect */
 	int		*first,		/* output: first byte offset */
 	int		*last)		/* output: last byte offset */
 {
 	int		i;		/* current bit number */
-	__int64_t	imask;		/* mask for current bit number */
+	int64_t		imask;		/* mask for current bit number */
 
 	ASSERT(fields != 0);
 	/*
@@ -810,7 +824,8 @@ xfs_btree_read_bufl(
 	xfs_daddr_t		d;		/* real disk block address */
 	int			error;
 
-	ASSERT(fsbno != NULLFSBLOCK);
+	if (!XFS_FSB_SANITY_CHECK(mp, fsbno))
+		return -EFSCORRUPTED;
 	d = XFS_FSB_TO_DADDR(mp, fsbno);
 	error = xfs_trans_read_buf(mp, tp, mp->m_ddev_targp, d,
 				   mp->m_bsize, lock, &bp, ops);
@@ -1084,12 +1099,15 @@ xfs_btree_init_block_int(
 	struct xfs_mount	*mp,
 	struct xfs_btree_block	*buf,
 	xfs_daddr_t		blkno,
-	__u32			magic,
+	xfs_btnum_t		btnum,
 	__u16			level,
 	__u16			numrecs,
 	__u64			owner,
 	unsigned int		flags)
 {
+	int			crc = xfs_sb_version_hascrc(&mp->m_sb);
+	__u32			magic = xfs_btree_magic(crc, btnum);
+
 	buf->bb_magic = cpu_to_be32(magic);
 	buf->bb_level = cpu_to_be16(level);
 	buf->bb_numrecs = cpu_to_be16(numrecs);
@@ -1097,7 +1115,7 @@ xfs_btree_init_block_int(
 	if (flags & XFS_BTREE_LONG_PTRS) {
 		buf->bb_u.l.bb_leftsib = cpu_to_be64(NULLFSBLOCK);
 		buf->bb_u.l.bb_rightsib = cpu_to_be64(NULLFSBLOCK);
-		if (flags & XFS_BTREE_CRC_BLOCKS) {
+		if (crc) {
 			buf->bb_u.l.bb_blkno = cpu_to_be64(blkno);
 			buf->bb_u.l.bb_owner = cpu_to_be64(owner);
 			uuid_copy(&buf->bb_u.l.bb_uuid, &mp->m_sb.sb_meta_uuid);
@@ -1110,7 +1128,7 @@ xfs_btree_init_block_int(
 
 		buf->bb_u.s.bb_leftsib = cpu_to_be32(NULLAGBLOCK);
 		buf->bb_u.s.bb_rightsib = cpu_to_be32(NULLAGBLOCK);
-		if (flags & XFS_BTREE_CRC_BLOCKS) {
+		if (crc) {
 			buf->bb_u.s.bb_blkno = cpu_to_be64(blkno);
 			buf->bb_u.s.bb_owner = cpu_to_be32(__owner);
 			uuid_copy(&buf->bb_u.s.bb_uuid, &mp->m_sb.sb_meta_uuid);
@@ -1123,14 +1141,14 @@ void
 xfs_btree_init_block(
 	struct xfs_mount *mp,
 	struct xfs_buf	*bp,
-	__u32		magic,
+	xfs_btnum_t	btnum,
 	__u16		level,
 	__u16		numrecs,
 	__u64		owner,
 	unsigned int	flags)
 {
 	xfs_btree_init_block_int(mp, XFS_BUF_TO_BLOCK(bp), bp->b_bn,
-				 magic, level, numrecs, owner, flags);
+				 btnum, level, numrecs, owner, flags);
 }
 
 STATIC void
@@ -1140,7 +1158,7 @@ xfs_btree_init_block_cur(
 	int			level,
 	int			numrecs)
 {
-	__u64 owner;
+	__u64			owner;
 
 	/*
 	 * we can pull the owner from the cursor right now as the different
@@ -1154,7 +1172,7 @@ xfs_btree_init_block_cur(
 		owner = cur->bc_private.a.agno;
 
 	xfs_btree_init_block_int(cur->bc_mp, XFS_BUF_TO_BLOCK(bp), bp->b_bn,
-				 xfs_btree_magic(cur), level, numrecs,
+				 cur->bc_btnum, level, numrecs,
 				 owner, cur->bc_flags);
 }
 
@@ -1736,7 +1754,7 @@ error0:
 	return error;
 }
 
-STATIC int
+int
 xfs_btree_lookup_get_block(
 	struct xfs_btree_cur	*cur,	/* btree cursor */
 	int			level,	/* level in the btree */
@@ -1826,7 +1844,7 @@ xfs_btree_lookup(
 	int			*stat)	/* success/failure */
 {
 	struct xfs_btree_block	*block;	/* current btree block */
-	__int64_t		diff;	/* difference for the current key */
+	int64_t			diff;	/* difference for the current key */
 	int			error;	/* error return value */
 	int			keyno;	/* current key number */
 	int			level;	/* level in the btree */
@@ -2866,7 +2884,7 @@ xfs_btree_split_worker(
 	struct xfs_btree_split_args	*args = container_of(work,
 						struct xfs_btree_split_args, work);
 	unsigned long		pflags;
-	unsigned long		new_pflags = PF_FSTRANS;
+	unsigned long		new_pflags = PF_MEMALLOC_NOFS;
 
 	/*
 	 * we are in a transaction context here, but may also be doing work
@@ -4375,7 +4393,7 @@ xfs_btree_visit_blocks(
 			xfs_btree_readahead_ptr(cur, ptr, 1);
 
 			/* save for the next iteration of the loop */
-			lptr = *ptr;
+			xfs_btree_copy_ptrs(cur, &lptr, ptr, 1);
 		}
 
 		/* for each buffer in the level */
@@ -4415,7 +4433,7 @@ xfs_btree_visit_blocks(
  * recovery completion writes the changes to disk.
  */
 struct xfs_btree_block_change_owner_info {
-	__uint64_t		new_owner;
+	uint64_t		new_owner;
 	struct list_head	*buffer_list;
 };
 
@@ -4461,7 +4479,7 @@ xfs_btree_block_change_owner(
 int
 xfs_btree_change_owner(
 	struct xfs_btree_cur	*cur,
-	__uint64_t		new_owner,
+	uint64_t		new_owner,
 	struct list_head	*buffer_list)
 {
 	struct xfs_btree_block_change_owner_info	bbcoi;
@@ -4565,7 +4583,7 @@ xfs_btree_simple_query_range(
 {
 	union xfs_btree_rec		*recp;
 	union xfs_btree_key		rec_key;
-	__int64_t			diff;
+	int64_t				diff;
 	int				stat;
 	bool				firstrec = true;
 	int				error;
@@ -4662,8 +4680,8 @@ xfs_btree_overlapped_query_range(
 	union xfs_btree_key		*hkp;
 	union xfs_btree_rec		*recp;
 	struct xfs_btree_block		*block;
-	__int64_t			ldiff;
-	__int64_t			hdiff;
+	int64_t				ldiff;
+	int64_t				hdiff;
 	int				level;
 	struct xfs_buf			*bp;
 	int				i;
@@ -4822,6 +4840,23 @@ xfs_btree_query_range(
 			fn, priv);
 }
 
+/* Query a btree for all records. */
+int
+xfs_btree_query_all(
+	struct xfs_btree_cur		*cur,
+	xfs_btree_query_range_fn	fn,
+	void				*priv)
+{
+	union xfs_btree_key		low_key;
+	union xfs_btree_key		high_key;
+
+	memset(&cur->bc_rec, 0, sizeof(cur->bc_rec));
+	memset(&low_key, 0, sizeof(low_key));
+	memset(&high_key, 0xFF, sizeof(high_key));
+
+	return xfs_btree_simple_query_range(cur, &low_key, &high_key, fn, priv);
+}
+
 /*
  * Calculate the number of blocks needed to store a given number of records
  * in a short-format (per-AG metadata) btree.
diff --git a/fs/xfs/libxfs/xfs_btree.h b/fs/xfs/libxfs/xfs_btree.h
index b69b947c4c1b..9c95e965cfe5 100644
--- a/fs/xfs/libxfs/xfs_btree.h
+++ b/fs/xfs/libxfs/xfs_btree.h
@@ -76,6 +76,8 @@ union xfs_btree_rec {
 #define	XFS_BTNUM_RMAP	((xfs_btnum_t)XFS_BTNUM_RMAPi)
 #define	XFS_BTNUM_REFC	((xfs_btnum_t)XFS_BTNUM_REFCi)
 
+uint32_t xfs_btree_magic(int crc, xfs_btnum_t btnum);
+
 /*
  * For logging record fields.
  */
@@ -148,20 +150,19 @@ struct xfs_btree_ops {
 					  union xfs_btree_rec *rec);
 
 	/* difference between key value and cursor value */
-	__int64_t (*key_diff)(struct xfs_btree_cur *cur,
+	int64_t (*key_diff)(struct xfs_btree_cur *cur,
 			      union xfs_btree_key *key);
 
 	/*
 	 * Difference between key2 and key1 -- positive if key1 > key2,
 	 * negative if key1 < key2, and zero if equal.
 	 */
-	__int64_t (*diff_two_keys)(struct xfs_btree_cur *cur,
+	int64_t (*diff_two_keys)(struct xfs_btree_cur *cur,
 				   union xfs_btree_key *key1,
 				   union xfs_btree_key *key2);
 
 	const struct xfs_buf_ops	*buf_ops;
 
-#if defined(DEBUG) || defined(XFS_WARN)
 	/* check that k1 is lower than k2 */
 	int	(*keys_inorder)(struct xfs_btree_cur *cur,
 				union xfs_btree_key *k1,
@@ -171,7 +172,6 @@ struct xfs_btree_ops {
 	int	(*recs_inorder)(struct xfs_btree_cur *cur,
 				union xfs_btree_rec *r1,
 				union xfs_btree_rec *r2);
-#endif
 };
 
 /*
@@ -211,11 +211,11 @@ typedef struct xfs_btree_cur
 	union xfs_btree_irec	bc_rec;	/* current insert/search record value */
 	struct xfs_buf	*bc_bufs[XFS_BTREE_MAXLEVELS];	/* buf ptr per level */
 	int		bc_ptrs[XFS_BTREE_MAXLEVELS];	/* key/record # */
-	__uint8_t	bc_ra[XFS_BTREE_MAXLEVELS];	/* readahead bits */
+	uint8_t		bc_ra[XFS_BTREE_MAXLEVELS];	/* readahead bits */
 #define	XFS_BTCUR_LEFTRA	1	/* left sibling has been read-ahead */
 #define	XFS_BTCUR_RIGHTRA	2	/* right sibling has been read-ahead */
-	__uint8_t	bc_nlevels;	/* number of levels in the tree */
-	__uint8_t	bc_blocklog;	/* log2(blocksize) of btree blocks */
+	uint8_t		bc_nlevels;	/* number of levels in the tree */
+	uint8_t		bc_blocklog;	/* log2(blocksize) of btree blocks */
 	xfs_btnum_t	bc_btnum;	/* identifies which btree type */
 	int		bc_statoff;	/* offset of btre stats array */
 	union {
@@ -328,7 +328,7 @@ xfs_btree_islastblock(
  */
 void
 xfs_btree_offsets(
-	__int64_t		fields,	/* bitmask of fields */
+	int64_t			fields,	/* bitmask of fields */
 	const short		*offsets,/* table of field offsets */
 	int			nbits,	/* number of bits to inspect */
 	int			*first,	/* output: first byte offset */
@@ -378,7 +378,7 @@ void
 xfs_btree_init_block(
 	struct xfs_mount *mp,
 	struct xfs_buf	*bp,
-	__u32		magic,
+	xfs_btnum_t	btnum,
 	__u16		level,
 	__u16		numrecs,
 	__u64		owner,
@@ -389,7 +389,7 @@ xfs_btree_init_block_int(
 	struct xfs_mount	*mp,
 	struct xfs_btree_block	*buf,
 	xfs_daddr_t		blkno,
-	__u32			magic,
+	xfs_btnum_t		btnum,
 	__u16			level,
 	__u16			numrecs,
 	__u64			owner,
@@ -406,7 +406,7 @@ int xfs_btree_new_iroot(struct xfs_btree_cur *, int *, int *);
 int xfs_btree_insert(struct xfs_btree_cur *, int *);
 int xfs_btree_delete(struct xfs_btree_cur *, int *);
 int xfs_btree_get_rec(struct xfs_btree_cur *, union xfs_btree_rec **, int *);
-int xfs_btree_change_owner(struct xfs_btree_cur *cur, __uint64_t new_owner,
+int xfs_btree_change_owner(struct xfs_btree_cur *cur, uint64_t new_owner,
 			   struct list_head *buffer_list);
 
 /*
@@ -432,7 +432,7 @@ static inline int xfs_btree_get_numrecs(struct xfs_btree_block *block)
 }
 
 static inline void xfs_btree_set_numrecs(struct xfs_btree_block *block,
-		__uint16_t numrecs)
+		uint16_t numrecs)
 {
 	block->bb_numrecs = cpu_to_be16(numrecs);
 }
@@ -456,7 +456,7 @@ static inline int xfs_btree_get_level(struct xfs_btree_block *block)
 #define	XFS_FILBLKS_MAX(a,b)	max_t(xfs_filblks_t, (a), (b))
 
 #define	XFS_FSB_SANITY_CHECK(mp,fsb)	\
-	(XFS_FSB_TO_AGNO(mp, fsb) < mp->m_sb.sb_agcount && \
+	(fsb && XFS_FSB_TO_AGNO(mp, fsb) < mp->m_sb.sb_agcount && \
 		XFS_FSB_TO_AGBNO(mp, fsb) < mp->m_sb.sb_agblocks)
 
 /*
@@ -494,6 +494,8 @@ typedef int (*xfs_btree_query_range_fn)(struct xfs_btree_cur *cur,
 int xfs_btree_query_range(struct xfs_btree_cur *cur,
 		union xfs_btree_irec *low_rec, union xfs_btree_irec *high_rec,
 		xfs_btree_query_range_fn fn, void *priv);
+int xfs_btree_query_all(struct xfs_btree_cur *cur, xfs_btree_query_range_fn fn,
+		void *priv);
 
 typedef int (*xfs_btree_visit_blocks_fn)(struct xfs_btree_cur *cur, int level,
 		void *data);
@@ -502,4 +504,17 @@ int xfs_btree_visit_blocks(struct xfs_btree_cur *cur,
 
 int xfs_btree_count_blocks(struct xfs_btree_cur *cur, xfs_extlen_t *blocks);
 
+union xfs_btree_rec *xfs_btree_rec_addr(struct xfs_btree_cur *cur, int n,
+		struct xfs_btree_block *block);
+union xfs_btree_key *xfs_btree_key_addr(struct xfs_btree_cur *cur, int n,
+		struct xfs_btree_block *block);
+union xfs_btree_key *xfs_btree_high_key_addr(struct xfs_btree_cur *cur, int n,
+		struct xfs_btree_block *block);
+union xfs_btree_ptr *xfs_btree_ptr_addr(struct xfs_btree_cur *cur, int n,
+		struct xfs_btree_block *block);
+int xfs_btree_lookup_get_block(struct xfs_btree_cur *cur, int level,
+		union xfs_btree_ptr *pp, struct xfs_btree_block **blkp);
+struct xfs_btree_block *xfs_btree_get_block(struct xfs_btree_cur *cur,
+		int level, struct xfs_buf **bpp);
+
 #endif	/* __XFS_BTREE_H__ */
diff --git a/fs/xfs/libxfs/xfs_cksum.h b/fs/xfs/libxfs/xfs_cksum.h
index a416c7cb23ea..8211f48b98e6 100644
--- a/fs/xfs/libxfs/xfs_cksum.h
+++ b/fs/xfs/libxfs/xfs_cksum.h
@@ -1,7 +1,7 @@
 #ifndef _XFS_CKSUM_H
 #define _XFS_CKSUM_H 1
 
-#define XFS_CRC_SEED	(~(__uint32_t)0)
+#define XFS_CRC_SEED	(~(uint32_t)0)
 
 /*
  * Calculate the intermediate checksum for a buffer that has the CRC field
@@ -9,11 +9,11 @@
  * cksum_offset parameter. We do not modify the buffer during verification,
  * hence we have to split the CRC calculation across the cksum_offset.
  */
-static inline __uint32_t
+static inline uint32_t
 xfs_start_cksum_safe(char *buffer, size_t length, unsigned long cksum_offset)
 {
-	__uint32_t zero = 0;
-	__uint32_t crc;
+	uint32_t zero = 0;
+	uint32_t crc;
 
 	/* Calculate CRC up to the checksum. */
 	crc = crc32c(XFS_CRC_SEED, buffer, cksum_offset);
@@ -30,7 +30,7 @@ xfs_start_cksum_safe(char *buffer, size_t length, unsigned long cksum_offset)
  * Fast CRC method where the buffer is modified. Callers must have exclusive
  * access to the buffer while the calculation takes place.
  */
-static inline __uint32_t
+static inline uint32_t
 xfs_start_cksum_update(char *buffer, size_t length, unsigned long cksum_offset)
 {
 	/* zero the CRC field */
@@ -48,7 +48,7 @@ xfs_start_cksum_update(char *buffer, size_t length, unsigned long cksum_offset)
  * so that it is consistent on disk.
  */
 static inline __le32
-xfs_end_cksum(__uint32_t crc)
+xfs_end_cksum(uint32_t crc)
 {
 	return ~cpu_to_le32(crc);
 }
@@ -62,7 +62,7 @@ xfs_end_cksum(__uint32_t crc)
 static inline void
 xfs_update_cksum(char *buffer, size_t length, unsigned long cksum_offset)
 {
-	__uint32_t crc = xfs_start_cksum_update(buffer, length, cksum_offset);
+	uint32_t crc = xfs_start_cksum_update(buffer, length, cksum_offset);
 
 	*(__le32 *)(buffer + cksum_offset) = xfs_end_cksum(crc);
 }
@@ -73,7 +73,7 @@ xfs_update_cksum(char *buffer, size_t length, unsigned long cksum_offset)
 static inline int
 xfs_verify_cksum(char *buffer, size_t length, unsigned long cksum_offset)
 {
-	__uint32_t crc = xfs_start_cksum_safe(buffer, length, cksum_offset);
+	uint32_t crc = xfs_start_cksum_safe(buffer, length, cksum_offset);
 
 	return *(__le32 *)(buffer + cksum_offset) == xfs_end_cksum(crc);
 }
diff --git a/fs/xfs/libxfs/xfs_da_btree.c b/fs/xfs/libxfs/xfs_da_btree.c
index f2dc1a950c85..6d4335815c3f 100644
--- a/fs/xfs/libxfs/xfs_da_btree.c
+++ b/fs/xfs/libxfs/xfs_da_btree.c
@@ -263,7 +263,7 @@ xfs_da3_node_read(
 
 	err = xfs_da_read_buf(tp, dp, bno, mappedbno, bpp,
 					which_fork, &xfs_da3_node_buf_ops);
-	if (!err && tp) {
+	if (!err && tp && *bpp) {
 		struct xfs_da_blkinfo	*info = (*bpp)->b_addr;
 		int			type;
 
@@ -1282,7 +1282,7 @@ xfs_da3_fixhashpath(
 			return;
 		break;
 	case XFS_DIR2_LEAFN_MAGIC:
-		lasthash = xfs_dir2_leafn_lasthash(dp, blk->bp, &count);
+		lasthash = xfs_dir2_leaf_lasthash(dp, blk->bp, &count);
 		if (count == 0)
 			return;
 		break;
@@ -1502,8 +1502,8 @@ xfs_da3_node_lookup_int(
 		if (blk->magic == XFS_DIR2_LEAFN_MAGIC ||
 		    blk->magic == XFS_DIR3_LEAFN_MAGIC) {
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
-			blk->hashval = xfs_dir2_leafn_lasthash(args->dp,
-							       blk->bp, NULL);
+			blk->hashval = xfs_dir2_leaf_lasthash(args->dp,
+							      blk->bp, NULL);
 			break;
 		}
 
@@ -1929,8 +1929,8 @@ xfs_da3_path_shift(
 			blk->magic = XFS_DIR2_LEAFN_MAGIC;
 			ASSERT(level == path->active-1);
 			blk->index = 0;
-			blk->hashval = xfs_dir2_leafn_lasthash(args->dp,
-							       blk->bp, NULL);
+			blk->hashval = xfs_dir2_leaf_lasthash(args->dp,
+							      blk->bp, NULL);
 			break;
 		default:
 			ASSERT(0);
@@ -1952,7 +1952,7 @@ xfs_da3_path_shift(
  * This is implemented with some source-level loop unrolling.
  */
 xfs_dahash_t
-xfs_da_hashname(const __uint8_t *name, int namelen)
+xfs_da_hashname(const uint8_t *name, int namelen)
 {
 	xfs_dahash_t hash;
 
@@ -2633,7 +2633,7 @@ out_free:
 /*
  * Readahead the dir/attr block.
  */
-xfs_daddr_t
+int
 xfs_da_reada_buf(
 	struct xfs_inode	*dp,
 	xfs_dablk_t		bno,
@@ -2664,7 +2664,5 @@ out_free:
 	if (mapp != &map)
 		kmem_free(mapp);
 
-	if (error)
-		return -1;
-	return mappedbno;
+	return error;
 }
diff --git a/fs/xfs/libxfs/xfs_da_btree.h b/fs/xfs/libxfs/xfs_da_btree.h
index 98c75cbe6ac2..ae6de17467f2 100644
--- a/fs/xfs/libxfs/xfs_da_btree.h
+++ b/fs/xfs/libxfs/xfs_da_btree.h
@@ -60,10 +60,10 @@ enum xfs_dacmp {
  */
 typedef struct xfs_da_args {
 	struct xfs_da_geometry *geo;	/* da block geometry */
-	const __uint8_t	*name;		/* string (maybe not NULL terminated) */
+	const uint8_t		*name;		/* string (maybe not NULL terminated) */
 	int		namelen;	/* length of string (maybe no NULL) */
-	__uint8_t	filetype;	/* filetype of inode for directories */
-	__uint8_t	*value;		/* set of bytes (maybe contain NULLs) */
+	uint8_t		filetype;	/* filetype of inode for directories */
+	uint8_t		*value;		/* set of bytes (maybe contain NULLs) */
 	int		valuelen;	/* length of value */
 	int		flags;		/* argument flags (eg: ATTR_NOCREATE) */
 	xfs_dahash_t	hashval;	/* hash value of name */
@@ -201,13 +201,13 @@ int	xfs_da_read_buf(struct xfs_trans *trans, struct xfs_inode *dp,
 			       xfs_dablk_t bno, xfs_daddr_t mappedbno,
 			       struct xfs_buf **bpp, int whichfork,
 			       const struct xfs_buf_ops *ops);
-xfs_daddr_t	xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno,
+int	xfs_da_reada_buf(struct xfs_inode *dp, xfs_dablk_t bno,
 				xfs_daddr_t mapped_bno, int whichfork,
 				const struct xfs_buf_ops *ops);
 int	xfs_da_shrink_inode(xfs_da_args_t *args, xfs_dablk_t dead_blkno,
 					  struct xfs_buf *dead_buf);
 
-uint xfs_da_hashname(const __uint8_t *name_string, int name_length);
+uint xfs_da_hashname(const uint8_t *name_string, int name_length);
 enum xfs_dacmp xfs_da_compname(struct xfs_da_args *args,
 				const unsigned char *name, int len);
 
diff --git a/fs/xfs/libxfs/xfs_da_format.c b/fs/xfs/libxfs/xfs_da_format.c
index f1e8d4dbb600..6d77d1a8498a 100644
--- a/fs/xfs/libxfs/xfs_da_format.c
+++ b/fs/xfs/libxfs/xfs_da_format.c
@@ -49,7 +49,7 @@ xfs_dir3_sf_entsize(
 	struct xfs_dir2_sf_hdr	*hdr,
 	int			len)
 {
-	return xfs_dir2_sf_entsize(hdr, len) + sizeof(__uint8_t);
+	return xfs_dir2_sf_entsize(hdr, len) + sizeof(uint8_t);
 }
 
 static struct xfs_dir2_sf_entry *
@@ -77,7 +77,7 @@ xfs_dir3_sf_nextentry(
  * not necessary. For non-filetype enable directories, the type is always
  * unknown and we never store the value.
  */
-static __uint8_t
+static uint8_t
 xfs_dir2_sfe_get_ftype(
 	struct xfs_dir2_sf_entry *sfep)
 {
@@ -87,16 +87,16 @@ xfs_dir2_sfe_get_ftype(
 static void
 xfs_dir2_sfe_put_ftype(
 	struct xfs_dir2_sf_entry *sfep,
-	__uint8_t		ftype)
+	uint8_t			ftype)
 {
 	ASSERT(ftype < XFS_DIR3_FT_MAX);
 }
 
-static __uint8_t
+static uint8_t
 xfs_dir3_sfe_get_ftype(
 	struct xfs_dir2_sf_entry *sfep)
 {
-	__uint8_t	ftype;
+	uint8_t		ftype;
 
 	ftype = sfep->name[sfep->namelen];
 	if (ftype >= XFS_DIR3_FT_MAX)
@@ -107,7 +107,7 @@ xfs_dir3_sfe_get_ftype(
 static void
 xfs_dir3_sfe_put_ftype(
 	struct xfs_dir2_sf_entry *sfep,
-	__uint8_t		ftype)
+	uint8_t			ftype)
 {
 	ASSERT(ftype < XFS_DIR3_FT_MAX);
 
@@ -124,7 +124,7 @@ xfs_dir3_sfe_put_ftype(
 static xfs_ino_t
 xfs_dir2_sf_get_ino(
 	struct xfs_dir2_sf_hdr	*hdr,
-	__uint8_t		*from)
+	uint8_t			*from)
 {
 	if (hdr->i8count)
 		return get_unaligned_be64(from) & 0x00ffffffffffffffULL;
@@ -135,7 +135,7 @@ xfs_dir2_sf_get_ino(
 static void
 xfs_dir2_sf_put_ino(
 	struct xfs_dir2_sf_hdr	*hdr,
-	__uint8_t		*to,
+	uint8_t			*to,
 	xfs_ino_t		ino)
 {
 	ASSERT((ino & 0xff00000000000000ULL) == 0);
@@ -225,7 +225,7 @@ xfs_dir3_sfe_put_ino(
 
 #define XFS_DIR3_DATA_ENTSIZE(n)					\
 	round_up((offsetof(struct xfs_dir2_data_entry, name[0]) + (n) +	\
-		 sizeof(xfs_dir2_data_off_t) + sizeof(__uint8_t)),	\
+		 sizeof(xfs_dir2_data_off_t) + sizeof(uint8_t)),	\
 		XFS_DIR2_DATA_ALIGN)
 
 static int
@@ -242,7 +242,7 @@ xfs_dir3_data_entsize(
 	return XFS_DIR3_DATA_ENTSIZE(n);
 }
 
-static __uint8_t
+static uint8_t
 xfs_dir2_data_get_ftype(
 	struct xfs_dir2_data_entry *dep)
 {
@@ -252,16 +252,16 @@ xfs_dir2_data_get_ftype(
 static void
 xfs_dir2_data_put_ftype(
 	struct xfs_dir2_data_entry *dep,
-	__uint8_t		ftype)
+	uint8_t			ftype)
 {
 	ASSERT(ftype < XFS_DIR3_FT_MAX);
 }
 
-static __uint8_t
+static uint8_t
 xfs_dir3_data_get_ftype(
 	struct xfs_dir2_data_entry *dep)
 {
-	__uint8_t	ftype = dep->name[dep->namelen];
+	uint8_t		ftype = dep->name[dep->namelen];
 
 	if (ftype >= XFS_DIR3_FT_MAX)
 		return XFS_DIR3_FT_UNKNOWN;
@@ -271,7 +271,7 @@ xfs_dir3_data_get_ftype(
 static void
 xfs_dir3_data_put_ftype(
 	struct xfs_dir2_data_entry *dep,
-	__uint8_t		type)
+	uint8_t			type)
 {
 	ASSERT(type < XFS_DIR3_FT_MAX);
 	ASSERT(dep->namelen != 0);
diff --git a/fs/xfs/libxfs/xfs_da_format.h b/fs/xfs/libxfs/xfs_da_format.h
index 9a492a9e19bd..3771edcb301d 100644
--- a/fs/xfs/libxfs/xfs_da_format.h
+++ b/fs/xfs/libxfs/xfs_da_format.h
@@ -111,11 +111,11 @@ struct xfs_da3_intnode {
  * appropriate.
  */
 struct xfs_da3_icnode_hdr {
-	__uint32_t	forw;
-	__uint32_t	back;
-	__uint16_t	magic;
-	__uint16_t	count;
-	__uint16_t	level;
+	uint32_t	forw;
+	uint32_t	back;
+	uint16_t	magic;
+	uint16_t	count;
+	uint16_t	level;
 };
 
 /*
@@ -187,14 +187,14 @@ struct xfs_da3_icnode_hdr {
 /*
  * Byte offset in data block and shortform entry.
  */
-typedef	__uint16_t	xfs_dir2_data_off_t;
+typedef uint16_t	xfs_dir2_data_off_t;
 #define	NULLDATAOFF	0xffffU
 typedef uint		xfs_dir2_data_aoff_t;	/* argument form */
 
 /*
  * Offset in data space of a data entry.
  */
-typedef	__uint32_t	xfs_dir2_dataptr_t;
+typedef uint32_t	xfs_dir2_dataptr_t;
 #define	XFS_DIR2_MAX_DATAPTR	((xfs_dir2_dataptr_t)0xffffffff)
 #define	XFS_DIR2_NULL_DATAPTR	((xfs_dir2_dataptr_t)0)
 
@@ -206,7 +206,7 @@ typedef	xfs_off_t	xfs_dir2_off_t;
 /*
  * Directory block number (logical dirblk in file)
  */
-typedef	__uint32_t	xfs_dir2_db_t;
+typedef uint32_t	xfs_dir2_db_t;
 
 #define XFS_INO32_SIZE	4
 #define XFS_INO64_SIZE	8
@@ -226,9 +226,9 @@ typedef	__uint32_t	xfs_dir2_db_t;
  * over them.
  */
 typedef struct xfs_dir2_sf_hdr {
-	__uint8_t		count;		/* count of entries */
-	__uint8_t		i8count;	/* count of 8-byte inode #s */
-	__uint8_t		parent[8];	/* parent dir inode number */
+	uint8_t			count;		/* count of entries */
+	uint8_t			i8count;	/* count of 8-byte inode #s */
+	uint8_t			parent[8];	/* parent dir inode number */
 } __packed xfs_dir2_sf_hdr_t;
 
 typedef struct xfs_dir2_sf_entry {
@@ -447,11 +447,11 @@ struct xfs_dir3_leaf_hdr {
 };
 
 struct xfs_dir3_icleaf_hdr {
-	__uint32_t		forw;
-	__uint32_t		back;
-	__uint16_t		magic;
-	__uint16_t		count;
-	__uint16_t		stale;
+	uint32_t		forw;
+	uint32_t		back;
+	uint16_t		magic;
+	uint16_t		count;
+	uint16_t		stale;
 };
 
 /*
@@ -538,10 +538,10 @@ struct xfs_dir3_free {
  * xfs_dir3_free_hdr_from_disk/xfs_dir3_free_hdr_to_disk.
  */
 struct xfs_dir3_icfree_hdr {
-	__uint32_t	magic;
-	__uint32_t	firstdb;
-	__uint32_t	nvalid;
-	__uint32_t	nused;
+	uint32_t	magic;
+	uint32_t	firstdb;
+	uint32_t	nvalid;
+	uint32_t	nused;
 
 };
 
@@ -632,10 +632,10 @@ typedef struct xfs_attr_shortform {
 		__u8	padding;
 	} hdr;
 	struct xfs_attr_sf_entry {
-		__uint8_t namelen;	/* actual length of name (no NULL) */
-		__uint8_t valuelen;	/* actual length of value (no NULL) */
-		__uint8_t flags;	/* flags bits (see xfs_attr_leaf.h) */
-		__uint8_t nameval[1];	/* name & value bytes concatenated */
+		uint8_t namelen;	/* actual length of name (no NULL) */
+		uint8_t valuelen;	/* actual length of value (no NULL) */
+		uint8_t flags;	/* flags bits (see xfs_attr_leaf.h) */
+		uint8_t nameval[1];	/* name & value bytes concatenated */
 	} list[1];			/* variable sized array */
 } xfs_attr_shortform_t;
 
@@ -725,22 +725,22 @@ struct xfs_attr3_leafblock {
  * incore, neutral version of the attribute leaf header
  */
 struct xfs_attr3_icleaf_hdr {
-	__uint32_t	forw;
-	__uint32_t	back;
-	__uint16_t	magic;
-	__uint16_t	count;
-	__uint16_t	usedbytes;
+	uint32_t	forw;
+	uint32_t	back;
+	uint16_t	magic;
+	uint16_t	count;
+	uint16_t	usedbytes;
 	/*
 	 * firstused is 32-bit here instead of 16-bit like the on-disk variant
 	 * to support maximum fsb size of 64k without overflow issues throughout
 	 * the attr code. Instead, the overflow condition is handled on
 	 * conversion to/from disk.
 	 */
-	__uint32_t	firstused;
+	uint32_t	firstused;
 	__u8		holes;
 	struct {
-		__uint16_t	base;
-		__uint16_t	size;
+		uint16_t	base;
+		uint16_t	size;
 	} freemap[XFS_ATTR_LEAF_MAPSIZE];
 };
 
diff --git a/fs/xfs/libxfs/xfs_dir2.c b/fs/xfs/libxfs/xfs_dir2.c
index 2f389d366e93..ccf9783fd3f0 100644
--- a/fs/xfs/libxfs/xfs_dir2.c
+++ b/fs/xfs/libxfs/xfs_dir2.c
@@ -218,8 +218,7 @@ xfs_dir_ino_validate(
 		agblkno != 0 &&
 		ioff < (1 << mp->m_sb.sb_inopblog) &&
 		XFS_AGINO_TO_INO(mp, agno, agino) == ino;
-	if (unlikely(XFS_TEST_ERROR(!ino_ok, mp, XFS_ERRTAG_DIR_INO_VALIDATE,
-			XFS_RANDOM_DIR_INO_VALIDATE))) {
+	if (unlikely(XFS_TEST_ERROR(!ino_ok, mp, XFS_ERRTAG_DIR_INO_VALIDATE))) {
 		xfs_warn(mp, "Invalid inode number 0x%Lx",
 				(unsigned long long) ino);
 		XFS_ERROR_REPORT("xfs_dir_ino_validate", XFS_ERRLEVEL_LOW, mp);
diff --git a/fs/xfs/libxfs/xfs_dir2.h b/fs/xfs/libxfs/xfs_dir2.h
index d6e6d9d16f6c..21c8f8bf94d5 100644
--- a/fs/xfs/libxfs/xfs_dir2.h
+++ b/fs/xfs/libxfs/xfs_dir2.h
@@ -47,9 +47,9 @@ struct xfs_dir_ops {
 	struct xfs_dir2_sf_entry *
 		(*sf_nextentry)(struct xfs_dir2_sf_hdr *hdr,
 				struct xfs_dir2_sf_entry *sfep);
-	__uint8_t (*sf_get_ftype)(struct xfs_dir2_sf_entry *sfep);
+	uint8_t (*sf_get_ftype)(struct xfs_dir2_sf_entry *sfep);
 	void	(*sf_put_ftype)(struct xfs_dir2_sf_entry *sfep,
-				__uint8_t ftype);
+				uint8_t ftype);
 	xfs_ino_t (*sf_get_ino)(struct xfs_dir2_sf_hdr *hdr,
 				struct xfs_dir2_sf_entry *sfep);
 	void	(*sf_put_ino)(struct xfs_dir2_sf_hdr *hdr,
@@ -60,9 +60,9 @@ struct xfs_dir_ops {
 				     xfs_ino_t ino);
 
 	int	(*data_entsize)(int len);
-	__uint8_t (*data_get_ftype)(struct xfs_dir2_data_entry *dep);
+	uint8_t (*data_get_ftype)(struct xfs_dir2_data_entry *dep);
 	void	(*data_put_ftype)(struct xfs_dir2_data_entry *dep,
-				__uint8_t ftype);
+				uint8_t ftype);
 	__be16 * (*data_entry_tag_p)(struct xfs_dir2_data_entry *dep);
 	struct xfs_dir2_data_free *
 		(*data_bestfree_p)(struct xfs_dir2_data_hdr *hdr);
diff --git a/fs/xfs/libxfs/xfs_dir2_block.c b/fs/xfs/libxfs/xfs_dir2_block.c
index aa17cb788946..43c902f7a68d 100644
--- a/fs/xfs/libxfs/xfs_dir2_block.c
+++ b/fs/xfs/libxfs/xfs_dir2_block.c
@@ -139,7 +139,7 @@ xfs_dir3_block_read(
 
 	err = xfs_da_read_buf(tp, dp, mp->m_dir_geo->datablk, -1, bpp,
 				XFS_DATA_FORK, &xfs_dir3_block_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_BLOCK_BUF);
 	return err;
 }
diff --git a/fs/xfs/libxfs/xfs_dir2_leaf.c b/fs/xfs/libxfs/xfs_dir2_leaf.c
index b887fb2a2bcf..27297a689d9c 100644
--- a/fs/xfs/libxfs/xfs_dir2_leaf.c
+++ b/fs/xfs/libxfs/xfs_dir2_leaf.c
@@ -145,7 +145,7 @@ xfs_dir3_leaf_check_int(
 static bool
 xfs_dir3_leaf_verify(
 	struct xfs_buf		*bp,
-	__uint16_t		magic)
+	uint16_t		magic)
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 	struct xfs_dir2_leaf	*leaf = bp->b_addr;
@@ -154,7 +154,7 @@ xfs_dir3_leaf_verify(
 
 	if (xfs_sb_version_hascrc(&mp->m_sb)) {
 		struct xfs_dir3_leaf_hdr *leaf3 = bp->b_addr;
-		__uint16_t		magic3;
+		uint16_t		magic3;
 
 		magic3 = (magic == XFS_DIR2_LEAF1_MAGIC) ? XFS_DIR3_LEAF1_MAGIC
 							 : XFS_DIR3_LEAFN_MAGIC;
@@ -178,7 +178,7 @@ xfs_dir3_leaf_verify(
 static void
 __read_verify(
 	struct xfs_buf  *bp,
-	__uint16_t	magic)
+	uint16_t	magic)
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 
@@ -195,7 +195,7 @@ __read_verify(
 static void
 __write_verify(
 	struct xfs_buf  *bp,
-	__uint16_t	magic)
+	uint16_t	magic)
 {
 	struct xfs_mount	*mp = bp->b_target->bt_mount;
 	struct xfs_buf_log_item	*bip = bp->b_fspriv;
@@ -256,7 +256,7 @@ const struct xfs_buf_ops xfs_dir3_leafn_buf_ops = {
 	.verify_write = xfs_dir3_leafn_write_verify,
 };
 
-static int
+int
 xfs_dir3_leaf_read(
 	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
@@ -268,7 +268,7 @@ xfs_dir3_leaf_read(
 
 	err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp,
 				XFS_DATA_FORK, &xfs_dir3_leaf1_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAF1_BUF);
 	return err;
 }
@@ -285,7 +285,7 @@ xfs_dir3_leafn_read(
 
 	err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp,
 				XFS_DATA_FORK, &xfs_dir3_leafn_buf_ops);
-	if (!err && tp)
+	if (!err && tp && *bpp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_LEAFN_BUF);
 	return err;
 }
@@ -299,7 +299,7 @@ xfs_dir3_leaf_init(
 	struct xfs_trans	*tp,
 	struct xfs_buf		*bp,
 	xfs_ino_t		owner,
-	__uint16_t		type)
+	uint16_t		type)
 {
 	struct xfs_dir2_leaf	*leaf = bp->b_addr;
 
@@ -343,7 +343,7 @@ xfs_dir3_leaf_get_buf(
 	xfs_da_args_t		*args,
 	xfs_dir2_db_t		bno,
 	struct xfs_buf		**bpp,
-	__uint16_t		magic)
+	uint16_t		magic)
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_trans	*tp = args->trans;
diff --git a/fs/xfs/libxfs/xfs_dir2_node.c b/fs/xfs/libxfs/xfs_dir2_node.c
index 75a557432d0f..682e2bf370c7 100644
--- a/fs/xfs/libxfs/xfs_dir2_node.c
+++ b/fs/xfs/libxfs/xfs_dir2_node.c
@@ -155,6 +155,42 @@ const struct xfs_buf_ops xfs_dir3_free_buf_ops = {
 	.verify_write = xfs_dir3_free_write_verify,
 };
 
+/* Everything ok in the free block header? */
+static bool
+xfs_dir3_free_header_check(
+	struct xfs_inode	*dp,
+	xfs_dablk_t		fbno,
+	struct xfs_buf		*bp)
+{
+	struct xfs_mount	*mp = dp->i_mount;
+	unsigned int		firstdb;
+	int			maxbests;
+
+	maxbests = dp->d_ops->free_max_bests(mp->m_dir_geo);
+	firstdb = (xfs_dir2_da_to_db(mp->m_dir_geo, fbno) -
+		   xfs_dir2_byte_to_db(mp->m_dir_geo, XFS_DIR2_FREE_OFFSET)) *
+			maxbests;
+	if (xfs_sb_version_hascrc(&mp->m_sb)) {
+		struct xfs_dir3_free_hdr *hdr3 = bp->b_addr;
+
+		if (be32_to_cpu(hdr3->firstdb) != firstdb)
+			return false;
+		if (be32_to_cpu(hdr3->nvalid) > maxbests)
+			return false;
+		if (be32_to_cpu(hdr3->nvalid) < be32_to_cpu(hdr3->nused))
+			return false;
+	} else {
+		struct xfs_dir2_free_hdr *hdr = bp->b_addr;
+
+		if (be32_to_cpu(hdr->firstdb) != firstdb)
+			return false;
+		if (be32_to_cpu(hdr->nvalid) > maxbests)
+			return false;
+		if (be32_to_cpu(hdr->nvalid) < be32_to_cpu(hdr->nused))
+			return false;
+	}
+	return true;
+}
 
 static int
 __xfs_dir3_free_read(
@@ -168,11 +204,22 @@ __xfs_dir3_free_read(
 
 	err = xfs_da_read_buf(tp, dp, fbno, mappedbno, bpp,
 				XFS_DATA_FORK, &xfs_dir3_free_buf_ops);
+	if (err || !*bpp)
+		return err;
+
+	/* Check things that we can't do in the verifier. */
+	if (!xfs_dir3_free_header_check(dp, fbno, *bpp)) {
+		xfs_buf_ioerror(*bpp, -EFSCORRUPTED);
+		xfs_verifier_error(*bpp);
+		xfs_trans_brelse(tp, *bpp);
+		return -EFSCORRUPTED;
+	}
 
 	/* try read returns without an error or *bpp if it lands in a hole */
-	if (!err && tp && *bpp)
+	if (tp)
 		xfs_trans_buf_set_type(tp, *bpp, XFS_BLFT_DIR_FREE_BUF);
-	return err;
+
+	return 0;
 }
 
 int
@@ -481,7 +528,7 @@ xfs_dir2_free_hdr_check(
  * Stale entries are ok.
  */
 xfs_dahash_t					/* hash value */
-xfs_dir2_leafn_lasthash(
+xfs_dir2_leaf_lasthash(
 	struct xfs_inode *dp,
 	struct xfs_buf	*bp,			/* leaf buffer */
 	int		*count)			/* count of entries in leaf */
@@ -493,7 +540,9 @@ xfs_dir2_leafn_lasthash(
 	dp->d_ops->leaf_hdr_from_disk(&leafhdr, leaf);
 
 	ASSERT(leafhdr.magic == XFS_DIR2_LEAFN_MAGIC ||
-	       leafhdr.magic == XFS_DIR3_LEAFN_MAGIC);
+	       leafhdr.magic == XFS_DIR3_LEAFN_MAGIC ||
+	       leafhdr.magic == XFS_DIR2_LEAF1_MAGIC ||
+	       leafhdr.magic == XFS_DIR3_LEAF1_MAGIC);
 
 	if (count)
 		*count = leafhdr.count;
@@ -1358,8 +1407,8 @@ xfs_dir2_leafn_split(
 	/*
 	 * Update last hashval in each block since we added the name.
 	 */
-	oldblk->hashval = xfs_dir2_leafn_lasthash(dp, oldblk->bp, NULL);
-	newblk->hashval = xfs_dir2_leafn_lasthash(dp, newblk->bp, NULL);
+	oldblk->hashval = xfs_dir2_leaf_lasthash(dp, oldblk->bp, NULL);
+	newblk->hashval = xfs_dir2_leaf_lasthash(dp, newblk->bp, NULL);
 	xfs_dir3_leaf_check(dp, oldblk->bp);
 	xfs_dir3_leaf_check(dp, newblk->bp);
 	return error;
diff --git a/fs/xfs/libxfs/xfs_dir2_priv.h b/fs/xfs/libxfs/xfs_dir2_priv.h
index d04547fcf274..4badd26c47e6 100644
--- a/fs/xfs/libxfs/xfs_dir2_priv.h
+++ b/fs/xfs/libxfs/xfs_dir2_priv.h
@@ -58,6 +58,8 @@ extern int xfs_dir3_data_init(struct xfs_da_args *args, xfs_dir2_db_t blkno,
 		struct xfs_buf **bpp);
 
 /* xfs_dir2_leaf.c */
+extern int xfs_dir3_leaf_read(struct xfs_trans *tp, struct xfs_inode *dp,
+		xfs_dablk_t fbno, xfs_daddr_t mappedbno, struct xfs_buf **bpp);
 extern int xfs_dir3_leafn_read(struct xfs_trans *tp, struct xfs_inode *dp,
 		xfs_dablk_t fbno, xfs_daddr_t mappedbno, struct xfs_buf **bpp);
 extern int xfs_dir2_block_to_leaf(struct xfs_da_args *args,
@@ -69,7 +71,7 @@ extern void xfs_dir3_leaf_compact_x1(struct xfs_dir3_icleaf_hdr *leafhdr,
 		struct xfs_dir2_leaf_entry *ents, int *indexp,
 		int *lowstalep, int *highstalep, int *lowlogp, int *highlogp);
 extern int xfs_dir3_leaf_get_buf(struct xfs_da_args *args, xfs_dir2_db_t bno,
-		struct xfs_buf **bpp, __uint16_t magic);
+		struct xfs_buf **bpp, uint16_t magic);
 extern void xfs_dir3_leaf_log_ents(struct xfs_da_args *args,
 		struct xfs_buf *bp, int first, int last);
 extern void xfs_dir3_leaf_log_header(struct xfs_da_args *args,
@@ -93,7 +95,7 @@ extern bool xfs_dir3_leaf_check_int(struct xfs_mount *mp, struct xfs_inode *dp,
 /* xfs_dir2_node.c */
 extern int xfs_dir2_leaf_to_node(struct xfs_da_args *args,
 		struct xfs_buf *lbp);
-extern xfs_dahash_t xfs_dir2_leafn_lasthash(struct xfs_inode *dp,
+extern xfs_dahash_t xfs_dir2_leaf_lasthash(struct xfs_inode *dp,
 		struct xfs_buf *bp, int *count);
 extern int xfs_dir2_leafn_lookup_int(struct xfs_buf *bp,
 		struct xfs_da_args *args, int *indexp,
@@ -125,9 +127,10 @@ extern int xfs_dir2_sf_create(struct xfs_da_args *args, xfs_ino_t pino);
 extern int xfs_dir2_sf_lookup(struct xfs_da_args *args);
 extern int xfs_dir2_sf_removename(struct xfs_da_args *args);
 extern int xfs_dir2_sf_replace(struct xfs_da_args *args);
+extern int xfs_dir2_sf_verify(struct xfs_inode *ip);
 
 /* xfs_dir2_readdir.c */
-extern int xfs_readdir(struct xfs_inode *dp, struct dir_context *ctx,
-		       size_t bufsize);
+extern int xfs_readdir(struct xfs_trans *tp, struct xfs_inode *dp,
+		       struct dir_context *ctx, size_t bufsize);
 
 #endif /* __XFS_DIR2_PRIV_H__ */
diff --git a/fs/xfs/libxfs/xfs_dir2_sf.c b/fs/xfs/libxfs/xfs_dir2_sf.c
index c6809ff41197..be8b9755f66a 100644
--- a/fs/xfs/libxfs/xfs_dir2_sf.c
+++ b/fs/xfs/libxfs/xfs_dir2_sf.c
@@ -629,6 +629,112 @@ xfs_dir2_sf_check(
 }
 #endif	/* DEBUG */
 
+/* Verify the consistency of an inline directory. */
+int
+xfs_dir2_sf_verify(
+	struct xfs_inode		*ip)
+{
+	struct xfs_mount		*mp = ip->i_mount;
+	struct xfs_dir2_sf_hdr		*sfp;
+	struct xfs_dir2_sf_entry	*sfep;
+	struct xfs_dir2_sf_entry	*next_sfep;
+	char				*endp;
+	const struct xfs_dir_ops	*dops;
+	struct xfs_ifork		*ifp;
+	xfs_ino_t			ino;
+	int				i;
+	int				i8count;
+	int				offset;
+	int				size;
+	int				error;
+	uint8_t				filetype;
+
+	ASSERT(ip->i_d.di_format == XFS_DINODE_FMT_LOCAL);
+	/*
+	 * xfs_iread calls us before xfs_setup_inode sets up ip->d_ops,
+	 * so we can only trust the mountpoint to have the right pointer.
+	 */
+	dops = xfs_dir_get_ops(mp, NULL);
+
+	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+	sfp = (struct xfs_dir2_sf_hdr *)ifp->if_u1.if_data;
+	size = ifp->if_bytes;
+
+	/*
+	 * Give up if the directory is way too short.
+	 */
+	if (size <= offsetof(struct xfs_dir2_sf_hdr, parent) ||
+	    size < xfs_dir2_sf_hdr_size(sfp->i8count))
+		return -EFSCORRUPTED;
+
+	endp = (char *)sfp + size;
+
+	/* Check .. entry */
+	ino = dops->sf_get_parent_ino(sfp);
+	i8count = ino > XFS_DIR2_MAX_SHORT_INUM;
+	error = xfs_dir_ino_validate(mp, ino);
+	if (error)
+		return error;
+	offset = dops->data_first_offset;
+
+	/* Check all reported entries */
+	sfep = xfs_dir2_sf_firstentry(sfp);
+	for (i = 0; i < sfp->count; i++) {
+		/*
+		 * struct xfs_dir2_sf_entry has a variable length.
+		 * Check the fixed-offset parts of the structure are
+		 * within the data buffer.
+		 */
+		if (((char *)sfep + sizeof(*sfep)) >= endp)
+			return -EFSCORRUPTED;
+
+		/* Don't allow names with known bad length. */
+		if (sfep->namelen == 0)
+			return -EFSCORRUPTED;
+
+		/*
+		 * Check that the variable-length part of the structure is
+		 * within the data buffer.  The next entry starts after the
+		 * name component, so nextentry is an acceptable test.
+		 */
+		next_sfep = dops->sf_nextentry(sfp, sfep);
+		if (endp < (char *)next_sfep)
+			return -EFSCORRUPTED;
+
+		/* Check that the offsets always increase. */
+		if (xfs_dir2_sf_get_offset(sfep) < offset)
+			return -EFSCORRUPTED;
+
+		/* Check the inode number. */
+		ino = dops->sf_get_ino(sfp, sfep);
+		i8count += ino > XFS_DIR2_MAX_SHORT_INUM;
+		error = xfs_dir_ino_validate(mp, ino);
+		if (error)
+			return error;
+
+		/* Check the file type. */
+		filetype = dops->sf_get_ftype(sfep);
+		if (filetype >= XFS_DIR3_FT_MAX)
+			return -EFSCORRUPTED;
+
+		offset = xfs_dir2_sf_get_offset(sfep) +
+				dops->data_entsize(sfep->namelen);
+
+		sfep = next_sfep;
+	}
+	if (i8count != sfp->i8count)
+		return -EFSCORRUPTED;
+	if ((void *)sfep != (void *)endp)
+		return -EFSCORRUPTED;
+
+	/* Make sure this whole thing ought to be in local format. */
+	if (offset + (sfp->count + 2) * (uint)sizeof(xfs_dir2_leaf_entry_t) +
+	    (uint)sizeof(xfs_dir2_block_tail_t) > mp->m_dir_geo->blksize)
+		return -EFSCORRUPTED;
+
+	return 0;
+}
+
 /*
  * Create a new (shortform) directory.
  */
diff --git a/fs/xfs/libxfs/xfs_dquot_buf.c b/fs/xfs/libxfs/xfs_dquot_buf.c
index ac9a003dd29a..747085b4ef44 100644
--- a/fs/xfs/libxfs/xfs_dquot_buf.c
+++ b/fs/xfs/libxfs/xfs_dquot_buf.c
@@ -35,13 +35,8 @@ int
 xfs_calc_dquots_per_chunk(
 	unsigned int		nbblks)	/* basic block units */
 {
-	unsigned int	ndquots;
-
 	ASSERT(nbblks > 0);
-	ndquots = BBTOB(nbblks);
-	do_div(ndquots, sizeof(xfs_dqblk_t));
-
-	return ndquots;
+	return BBTOB(nbblks) / sizeof(xfs_dqblk_t);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_format.h b/fs/xfs/libxfs/xfs_format.h
index 6b7579e7b60a..23229f0c5b15 100644
--- a/fs/xfs/libxfs/xfs_format.h
+++ b/fs/xfs/libxfs/xfs_format.h
@@ -103,8 +103,8 @@ struct xfs_ifork;
  * Must be padded to 64 bit alignment.
  */
 typedef struct xfs_sb {
-	__uint32_t	sb_magicnum;	/* magic number == XFS_SB_MAGIC */
-	__uint32_t	sb_blocksize;	/* logical block size, bytes */
+	uint32_t	sb_magicnum;	/* magic number == XFS_SB_MAGIC */
+	uint32_t	sb_blocksize;	/* logical block size, bytes */
 	xfs_rfsblock_t	sb_dblocks;	/* number of data blocks */
 	xfs_rfsblock_t	sb_rblocks;	/* number of realtime blocks */
 	xfs_rtblock_t	sb_rextents;	/* number of realtime extents */
@@ -118,45 +118,45 @@ typedef struct xfs_sb {
 	xfs_agnumber_t	sb_agcount;	/* number of allocation groups */
 	xfs_extlen_t	sb_rbmblocks;	/* number of rt bitmap blocks */
 	xfs_extlen_t	sb_logblocks;	/* number of log blocks */
-	__uint16_t	sb_versionnum;	/* header version == XFS_SB_VERSION */
-	__uint16_t	sb_sectsize;	/* volume sector size, bytes */
-	__uint16_t	sb_inodesize;	/* inode size, bytes */
-	__uint16_t	sb_inopblock;	/* inodes per block */
+	uint16_t	sb_versionnum;	/* header version == XFS_SB_VERSION */
+	uint16_t	sb_sectsize;	/* volume sector size, bytes */
+	uint16_t	sb_inodesize;	/* inode size, bytes */
+	uint16_t	sb_inopblock;	/* inodes per block */
 	char		sb_fname[12];	/* file system name */
-	__uint8_t	sb_blocklog;	/* log2 of sb_blocksize */
-	__uint8_t	sb_sectlog;	/* log2 of sb_sectsize */
-	__uint8_t	sb_inodelog;	/* log2 of sb_inodesize */
-	__uint8_t	sb_inopblog;	/* log2 of sb_inopblock */
-	__uint8_t	sb_agblklog;	/* log2 of sb_agblocks (rounded up) */
-	__uint8_t	sb_rextslog;	/* log2 of sb_rextents */
-	__uint8_t	sb_inprogress;	/* mkfs is in progress, don't mount */
-	__uint8_t	sb_imax_pct;	/* max % of fs for inode space */
+	uint8_t		sb_blocklog;	/* log2 of sb_blocksize */
+	uint8_t		sb_sectlog;	/* log2 of sb_sectsize */
+	uint8_t		sb_inodelog;	/* log2 of sb_inodesize */
+	uint8_t		sb_inopblog;	/* log2 of sb_inopblock */
+	uint8_t		sb_agblklog;	/* log2 of sb_agblocks (rounded up) */
+	uint8_t		sb_rextslog;	/* log2 of sb_rextents */
+	uint8_t		sb_inprogress;	/* mkfs is in progress, don't mount */
+	uint8_t		sb_imax_pct;	/* max % of fs for inode space */
 					/* statistics */
 	/*
 	 * These fields must remain contiguous.  If you really
 	 * want to change their layout, make sure you fix the
 	 * code in xfs_trans_apply_sb_deltas().
 	 */
-	__uint64_t	sb_icount;	/* allocated inodes */
-	__uint64_t	sb_ifree;	/* free inodes */
-	__uint64_t	sb_fdblocks;	/* free data blocks */
-	__uint64_t	sb_frextents;	/* free realtime extents */
+	uint64_t	sb_icount;	/* allocated inodes */
+	uint64_t	sb_ifree;	/* free inodes */
+	uint64_t	sb_fdblocks;	/* free data blocks */
+	uint64_t	sb_frextents;	/* free realtime extents */
 	/*
 	 * End contiguous fields.
 	 */
 	xfs_ino_t	sb_uquotino;	/* user quota inode */
 	xfs_ino_t	sb_gquotino;	/* group quota inode */
-	__uint16_t	sb_qflags;	/* quota flags */
-	__uint8_t	sb_flags;	/* misc. flags */
-	__uint8_t	sb_shared_vn;	/* shared version number */
+	uint16_t	sb_qflags;	/* quota flags */
+	uint8_t		sb_flags;	/* misc. flags */
+	uint8_t		sb_shared_vn;	/* shared version number */
 	xfs_extlen_t	sb_inoalignmt;	/* inode chunk alignment, fsblocks */
-	__uint32_t	sb_unit;	/* stripe or raid unit */
-	__uint32_t	sb_width;	/* stripe or raid width */
-	__uint8_t	sb_dirblklog;	/* log2 of dir block size (fsbs) */
-	__uint8_t	sb_logsectlog;	/* log2 of the log sector size */
-	__uint16_t	sb_logsectsize;	/* sector size for the log, bytes */
-	__uint32_t	sb_logsunit;	/* stripe unit size for the log */
-	__uint32_t	sb_features2;	/* additional feature bits */
+	uint32_t	sb_unit;	/* stripe or raid unit */
+	uint32_t	sb_width;	/* stripe or raid width */
+	uint8_t		sb_dirblklog;	/* log2 of dir block size (fsbs) */
+	uint8_t		sb_logsectlog;	/* log2 of the log sector size */
+	uint16_t	sb_logsectsize;	/* sector size for the log, bytes */
+	uint32_t	sb_logsunit;	/* stripe unit size for the log */
+	uint32_t	sb_features2;	/* additional feature bits */
 
 	/*
 	 * bad features2 field as a result of failing to pad the sb structure to
@@ -167,17 +167,17 @@ typedef struct xfs_sb {
 	 * the value in sb_features2 when formatting the incore superblock to
 	 * the disk buffer.
 	 */
-	__uint32_t	sb_bad_features2;
+	uint32_t	sb_bad_features2;
 
 	/* version 5 superblock fields start here */
 
 	/* feature masks */
-	__uint32_t	sb_features_compat;
-	__uint32_t	sb_features_ro_compat;
-	__uint32_t	sb_features_incompat;
-	__uint32_t	sb_features_log_incompat;
+	uint32_t	sb_features_compat;
+	uint32_t	sb_features_ro_compat;
+	uint32_t	sb_features_incompat;
+	uint32_t	sb_features_log_incompat;
 
-	__uint32_t	sb_crc;		/* superblock crc */
+	uint32_t	sb_crc;		/* superblock crc */
 	xfs_extlen_t	sb_spino_align;	/* sparse inode chunk alignment */
 
 	xfs_ino_t	sb_pquotino;	/* project quota inode */
@@ -449,7 +449,7 @@ static inline void xfs_sb_version_addprojid32bit(struct xfs_sb *sbp)
 static inline bool
 xfs_sb_has_compat_feature(
 	struct xfs_sb	*sbp,
-	__uint32_t	feature)
+	uint32_t	feature)
 {
 	return (sbp->sb_features_compat & feature) != 0;
 }
@@ -465,7 +465,7 @@ xfs_sb_has_compat_feature(
 static inline bool
 xfs_sb_has_ro_compat_feature(
 	struct xfs_sb	*sbp,
-	__uint32_t	feature)
+	uint32_t	feature)
 {
 	return (sbp->sb_features_ro_compat & feature) != 0;
 }
@@ -482,7 +482,7 @@ xfs_sb_has_ro_compat_feature(
 static inline bool
 xfs_sb_has_incompat_feature(
 	struct xfs_sb	*sbp,
-	__uint32_t	feature)
+	uint32_t	feature)
 {
 	return (sbp->sb_features_incompat & feature) != 0;
 }
@@ -492,7 +492,7 @@ xfs_sb_has_incompat_feature(
 static inline bool
 xfs_sb_has_incompat_log_feature(
 	struct xfs_sb	*sbp,
-	__uint32_t	feature)
+	uint32_t	feature)
 {
 	return (sbp->sb_features_log_incompat & feature) != 0;
 }
@@ -594,8 +594,8 @@ xfs_is_quota_inode(struct xfs_sb *sbp, xfs_ino_t ino)
  */
 #define XFS_FSB_TO_B(mp,fsbno)	((xfs_fsize_t)(fsbno) << (mp)->m_sb.sb_blocklog)
 #define XFS_B_TO_FSB(mp,b)	\
-	((((__uint64_t)(b)) + (mp)->m_blockmask) >> (mp)->m_sb.sb_blocklog)
-#define XFS_B_TO_FSBT(mp,b)	(((__uint64_t)(b)) >> (mp)->m_sb.sb_blocklog)
+	((((uint64_t)(b)) + (mp)->m_blockmask) >> (mp)->m_sb.sb_blocklog)
+#define XFS_B_TO_FSBT(mp,b)	(((uint64_t)(b)) >> (mp)->m_sb.sb_blocklog)
 #define XFS_B_FSB_OFFSET(mp,b)	((b) & (mp)->m_blockmask)
 
 /*
@@ -930,10 +930,8 @@ static inline uint xfs_dinode_size(int version)
 /*
  * The 32 bit link count in the inode theoretically maxes out at UINT_MAX.
  * Since the pathconf interface is signed, we use 2^31 - 1 instead.
- * The old inode format had a 16 bit link count, so its maximum is USHRT_MAX.
  */
 #define	XFS_MAXLINK		((1U << 31) - 1U)
-#define	XFS_MAXLINK_1		65535U
 
 /*
  * Values for di_format
@@ -1074,7 +1072,7 @@ static inline void xfs_dinode_put_rdev(struct xfs_dinode *dip, xfs_dev_t rdev)
  * next agno_log bits - ag number
  * high agno_log-agblklog-inopblog bits - 0
  */
-#define	XFS_INO_MASK(k)			(__uint32_t)((1ULL << (k)) - 1)
+#define	XFS_INO_MASK(k)			(uint32_t)((1ULL << (k)) - 1)
 #define	XFS_INO_OFFSET_BITS(mp)		(mp)->m_sb.sb_inopblog
 #define	XFS_INO_AGBNO_BITS(mp)		(mp)->m_sb.sb_agblklog
 #define	XFS_INO_AGINO_BITS(mp)		(mp)->m_agino_log
@@ -1213,6 +1211,7 @@ struct xfs_dsymlink_hdr {
 
 #define XFS_SYMLINK_CRC_OFF	offsetof(struct xfs_dsymlink_hdr, sl_crc)
 
+#define XFS_SYMLINK_MAXLEN	1024
 /*
  * The maximum pathlen is 1024 bytes. Since the minimum file system
  * blocksize is 512 bytes, we can get a max of 3 extents back from
@@ -1271,16 +1270,16 @@ typedef __be32 xfs_alloc_ptr_t;
 #define	XFS_FIBT_MAGIC		0x46494254	/* 'FIBT' */
 #define	XFS_FIBT_CRC_MAGIC	0x46494233	/* 'FIB3' */
 
-typedef	__uint64_t	xfs_inofree_t;
+typedef uint64_t	xfs_inofree_t;
 #define	XFS_INODES_PER_CHUNK		(NBBY * sizeof(xfs_inofree_t))
 #define	XFS_INODES_PER_CHUNK_LOG	(XFS_NBBYLOG + 3)
 #define	XFS_INOBT_ALL_FREE		((xfs_inofree_t)-1)
 #define	XFS_INOBT_MASK(i)		((xfs_inofree_t)1 << (i))
 
 #define XFS_INOBT_HOLEMASK_FULL		0	/* holemask for full chunk */
-#define XFS_INOBT_HOLEMASK_BITS		(NBBY * sizeof(__uint16_t))
+#define XFS_INOBT_HOLEMASK_BITS		(NBBY * sizeof(uint16_t))
 #define XFS_INODES_PER_HOLEMASK_BIT	\
-	(XFS_INODES_PER_CHUNK / (NBBY * sizeof(__uint16_t)))
+	(XFS_INODES_PER_CHUNK / (NBBY * sizeof(uint16_t)))
 
 static inline xfs_inofree_t xfs_inobt_maskn(int i, int n)
 {
@@ -1314,9 +1313,9 @@ typedef struct xfs_inobt_rec {
 
 typedef struct xfs_inobt_rec_incore {
 	xfs_agino_t	ir_startino;	/* starting inode number */
-	__uint16_t	ir_holemask;	/* hole mask for sparse chunks */
-	__uint8_t	ir_count;	/* total inode count */
-	__uint8_t	ir_freecount;	/* count of free inodes (set bits) */
+	uint16_t	ir_holemask;	/* hole mask for sparse chunks */
+	uint8_t		ir_count;	/* total inode count */
+	uint8_t		ir_freecount;	/* count of free inodes (set bits) */
 	xfs_inofree_t	ir_free;	/* free inode mask */
 } xfs_inobt_rec_incore_t;
 
@@ -1399,15 +1398,15 @@ struct xfs_rmap_rec {
  *  rm_offset:54-60 aren't used and should be zero
  *  rm_offset:0-53 is the block offset within the inode
  */
-#define XFS_RMAP_OFF_ATTR_FORK	((__uint64_t)1ULL << 63)
-#define XFS_RMAP_OFF_BMBT_BLOCK	((__uint64_t)1ULL << 62)
-#define XFS_RMAP_OFF_UNWRITTEN	((__uint64_t)1ULL << 61)
+#define XFS_RMAP_OFF_ATTR_FORK	((uint64_t)1ULL << 63)
+#define XFS_RMAP_OFF_BMBT_BLOCK	((uint64_t)1ULL << 62)
+#define XFS_RMAP_OFF_UNWRITTEN	((uint64_t)1ULL << 61)
 
-#define XFS_RMAP_LEN_MAX	((__uint32_t)~0U)
+#define XFS_RMAP_LEN_MAX	((uint32_t)~0U)
 #define XFS_RMAP_OFF_FLAGS	(XFS_RMAP_OFF_ATTR_FORK | \
 				 XFS_RMAP_OFF_BMBT_BLOCK | \
 				 XFS_RMAP_OFF_UNWRITTEN)
-#define XFS_RMAP_OFF_MASK	((__uint64_t)0x3FFFFFFFFFFFFFULL)
+#define XFS_RMAP_OFF_MASK	((uint64_t)0x3FFFFFFFFFFFFFULL)
 
 #define XFS_RMAP_OFF(off)		((off) & XFS_RMAP_OFF_MASK)
 
@@ -1433,8 +1432,8 @@ struct xfs_rmap_rec {
 struct xfs_rmap_irec {
 	xfs_agblock_t	rm_startblock;	/* extent start block */
 	xfs_extlen_t	rm_blockcount;	/* extent length */
-	__uint64_t	rm_owner;	/* extent owner */
-	__uint64_t	rm_offset;	/* offset within the owner */
+	uint64_t	rm_owner;	/* extent owner */
+	uint64_t	rm_offset;	/* offset within the owner */
 	unsigned int	rm_flags;	/* state flags */
 };
 
@@ -1546,11 +1545,11 @@ typedef struct xfs_bmbt_rec {
 	__be64			l0, l1;
 } xfs_bmbt_rec_t;
 
-typedef __uint64_t	xfs_bmbt_rec_base_t;	/* use this for casts */
+typedef uint64_t	xfs_bmbt_rec_base_t;	/* use this for casts */
 typedef xfs_bmbt_rec_t xfs_bmdr_rec_t;
 
 typedef struct xfs_bmbt_rec_host {
-	__uint64_t		l0, l1;
+	uint64_t		l0, l1;
 } xfs_bmbt_rec_host_t;
 
 /*
@@ -1578,19 +1577,10 @@ static inline xfs_filblks_t startblockval(xfs_fsblock_t x)
 }
 
 /*
- * Possible extent formats.
- */
-typedef enum {
-	XFS_EXTFMT_NOSTATE = 0,
-	XFS_EXTFMT_HASSTATE
-} xfs_exntfmt_t;
-
-/*
  * Possible extent states.
  */
 typedef enum {
 	XFS_EXT_NORM, XFS_EXT_UNWRITTEN,
-	XFS_EXT_DMAPI_OFFLINE, XFS_EXT_INVALID
 } xfs_exntst_t;
 
 /*
diff --git a/fs/xfs/libxfs/xfs_fs.h b/fs/xfs/libxfs/xfs_fs.h
index b72dc821d78b..8c61f21535d4 100644
--- a/fs/xfs/libxfs/xfs_fs.h
+++ b/fs/xfs/libxfs/xfs_fs.h
@@ -92,6 +92,18 @@ struct getbmapx {
 #define BMV_OF_LAST		0x4	/* segment is the last in the file */
 #define BMV_OF_SHARED		0x8	/* segment shared with another file */
 
+/*	fmr_owner special values for FS_IOC_GETFSMAP */
+#define XFS_FMR_OWN_FREE	FMR_OWN_FREE      /* free space */
+#define XFS_FMR_OWN_UNKNOWN	FMR_OWN_UNKNOWN   /* unknown owner */
+#define XFS_FMR_OWN_FS		FMR_OWNER('X', 1) /* static fs metadata */
+#define XFS_FMR_OWN_LOG		FMR_OWNER('X', 2) /* journalling log */
+#define XFS_FMR_OWN_AG		FMR_OWNER('X', 3) /* per-AG metadata */
+#define XFS_FMR_OWN_INOBT	FMR_OWNER('X', 4) /* inode btree blocks */
+#define XFS_FMR_OWN_INODES	FMR_OWNER('X', 5) /* inodes */
+#define XFS_FMR_OWN_REFC	FMR_OWNER('X', 6) /* refcount tree */
+#define XFS_FMR_OWN_COW		FMR_OWNER('X', 7) /* cow staging */
+#define XFS_FMR_OWN_DEFECTIVE	FMR_OWNER('X', 8) /* bad blocks */
+
 /*
  * Structure for XFS_IOC_FSSETDM.
  * For use by backup and restore programs to set the XFS on-disk inode
@@ -290,10 +302,10 @@ typedef struct xfs_bstat {
  * and using two 16bit values to hold new 32bit projid was choosen
  * to retain compatibility with "old" filesystems).
  */
-static inline __uint32_t
+static inline uint32_t
 bstat_get_projid(struct xfs_bstat *bs)
 {
-	return (__uint32_t)bs->bs_projid_hi << 16 | bs->bs_projid_lo;
+	return (uint32_t)bs->bs_projid_hi << 16 | bs->bs_projid_lo;
 }
 
 /*
@@ -434,19 +446,15 @@ typedef struct xfs_handle {
 } xfs_handle_t;
 #define ha_fsid ha_u._ha_fsid
 
-#define XFS_HSIZE(handle)	(((char *) &(handle).ha_fid.fid_pad	 \
-				 - (char *) &(handle))			  \
-				 + (handle).ha_fid.fid_len)
-
 /*
  * Structure passed to XFS_IOC_SWAPEXT
  */
 typedef struct xfs_swapext
 {
-	__int64_t	sx_version;	/* version */
+	int64_t		sx_version;	/* version */
 #define XFS_SX_VERSION		0
-	__int64_t	sx_fdtarget;	/* fd of target file */
-	__int64_t	sx_fdtmp;	/* fd of tmp file */
+	int64_t		sx_fdtarget;	/* fd of target file */
+	int64_t		sx_fdtmp;	/* fd of tmp file */
 	xfs_off_t	sx_offset;	/* offset into file */
 	xfs_off_t	sx_length;	/* leng from offset */
 	char		sx_pad[16];	/* pad space, unused */
@@ -502,6 +510,7 @@ typedef struct xfs_swapext
 #define XFS_IOC_GETBMAPX	_IOWR('X', 56, struct getbmap)
 #define XFS_IOC_ZERO_RANGE	_IOW ('X', 57, struct xfs_flock64)
 #define XFS_IOC_FREE_EOFBLOCKS	_IOR ('X', 58, struct xfs_fs_eofblocks)
+/*	XFS_IOC_GETFSMAP ------ hoisted 59         */
 
 /*
  * ioctl commands that replace IRIX syssgi()'s
@@ -533,7 +542,7 @@ typedef struct xfs_swapext
 #define XFS_IOC_ATTRLIST_BY_HANDLE   _IOW ('X', 122, struct xfs_fsop_attrlist_handlereq)
 #define XFS_IOC_ATTRMULTI_BY_HANDLE  _IOW ('X', 123, struct xfs_fsop_attrmulti_handlereq)
 #define XFS_IOC_FSGEOMETRY	     _IOR ('X', 124, struct xfs_fsop_geom)
-#define XFS_IOC_GOINGDOWN	     _IOR ('X', 125, __uint32_t)
+#define XFS_IOC_GOINGDOWN	     _IOR ('X', 125, uint32_t)
 /*	XFS_IOC_GETFSUUID ---------- deprecated 140	 */
 
 
diff --git a/fs/xfs/libxfs/xfs_ialloc.c b/fs/xfs/libxfs/xfs_ialloc.c
index f272abff11e1..ffd5a15d1bb6 100644
--- a/fs/xfs/libxfs/xfs_ialloc.c
+++ b/fs/xfs/libxfs/xfs_ialloc.c
@@ -46,13 +46,12 @@
 /*
  * Allocation group level functions.
  */
-static inline int
+int
 xfs_ialloc_cluster_alignment(
 	struct xfs_mount	*mp)
 {
 	if (xfs_sb_version_hasalign(&mp->m_sb) &&
-	    mp->m_sb.sb_inoalignmt >=
-			XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size))
+	    mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp))
 		return mp->m_sb.sb_inoalignmt;
 	return 1;
 }
@@ -99,24 +98,15 @@ xfs_inobt_update(
 	return xfs_btree_update(cur, &rec);
 }
 
-/*
- * Get the data from the pointed-to record.
- */
-int					/* error */
-xfs_inobt_get_rec(
-	struct xfs_btree_cur	*cur,	/* btree cursor */
-	xfs_inobt_rec_incore_t	*irec,	/* btree record */
-	int			*stat)	/* output: success/failure */
+/* Convert on-disk btree record to incore inobt record. */
+void
+xfs_inobt_btrec_to_irec(
+	struct xfs_mount		*mp,
+	union xfs_btree_rec		*rec,
+	struct xfs_inobt_rec_incore	*irec)
 {
-	union xfs_btree_rec	*rec;
-	int			error;
-
-	error = xfs_btree_get_rec(cur, &rec, stat);
-	if (error || *stat == 0)
-		return error;
-
 	irec->ir_startino = be32_to_cpu(rec->inobt.ir_startino);
-	if (xfs_sb_version_hassparseinodes(&cur->bc_mp->m_sb)) {
+	if (xfs_sb_version_hassparseinodes(&mp->m_sb)) {
 		irec->ir_holemask = be16_to_cpu(rec->inobt.ir_u.sp.ir_holemask);
 		irec->ir_count = rec->inobt.ir_u.sp.ir_count;
 		irec->ir_freecount = rec->inobt.ir_u.sp.ir_freecount;
@@ -131,6 +121,25 @@ xfs_inobt_get_rec(
 				be32_to_cpu(rec->inobt.ir_u.f.ir_freecount);
 	}
 	irec->ir_free = be64_to_cpu(rec->inobt.ir_free);
+}
+
+/*
+ * Get the data from the pointed-to record.
+ */
+int
+xfs_inobt_get_rec(
+	struct xfs_btree_cur		*cur,
+	struct xfs_inobt_rec_incore	*irec,
+	int				*stat)
+{
+	union xfs_btree_rec		*rec;
+	int				error;
+
+	error = xfs_btree_get_rec(cur, &rec, stat);
+	if (error || *stat == 0)
+		return error;
+
+	xfs_inobt_btrec_to_irec(cur->bc_mp, rec, irec);
 
 	return 0;
 }
@@ -141,9 +150,9 @@ xfs_inobt_get_rec(
 STATIC int
 xfs_inobt_insert_rec(
 	struct xfs_btree_cur	*cur,
-	__uint16_t		holemask,
-	__uint8_t		count,
-	__int32_t		freecount,
+	uint16_t		holemask,
+	uint8_t			count,
+	int32_t			freecount,
 	xfs_inofree_t		free,
 	int			*stat)
 {
@@ -2543,8 +2552,7 @@ xfs_agi_read_verify(
 	    !xfs_buf_verify_cksum(bp, XFS_AGI_CRC_OFF))
 		xfs_buf_ioerror(bp, -EFSBADCRC);
 	else if (XFS_TEST_ERROR(!xfs_agi_verify(bp), mp,
-				XFS_ERRTAG_IALLOC_READ_AGI,
-				XFS_RANDOM_IALLOC_READ_AGI))
+				XFS_ERRTAG_IALLOC_READ_AGI))
 		xfs_buf_ioerror(bp, -EFSCORRUPTED);
 
 	if (bp->b_error)
diff --git a/fs/xfs/libxfs/xfs_ialloc.h b/fs/xfs/libxfs/xfs_ialloc.h
index 0bb89669fc07..b32cfb5aeb5b 100644
--- a/fs/xfs/libxfs/xfs_ialloc.h
+++ b/fs/xfs/libxfs/xfs_ialloc.h
@@ -168,5 +168,10 @@ int xfs_ialloc_inode_init(struct xfs_mount *mp, struct xfs_trans *tp,
 int xfs_read_agi(struct xfs_mount *mp, struct xfs_trans *tp,
 		xfs_agnumber_t agno, struct xfs_buf **bpp);
 
+union xfs_btree_rec;
+void xfs_inobt_btrec_to_irec(struct xfs_mount *mp, union xfs_btree_rec *rec,
+		struct xfs_inobt_rec_incore *irec);
+
+int xfs_ialloc_cluster_alignment(struct xfs_mount *mp);
 
 #endif	/* __XFS_IALLOC_H__ */
diff --git a/fs/xfs/libxfs/xfs_ialloc_btree.c b/fs/xfs/libxfs/xfs_ialloc_btree.c
index 7c471881c9a6..317caba9faa6 100644
--- a/fs/xfs/libxfs/xfs_ialloc_btree.c
+++ b/fs/xfs/libxfs/xfs_ialloc_btree.c
@@ -175,6 +175,18 @@ xfs_inobt_init_key_from_rec(
 }
 
 STATIC void
+xfs_inobt_init_high_key_from_rec(
+	union xfs_btree_key	*key,
+	union xfs_btree_rec	*rec)
+{
+	__u32			x;
+
+	x = be32_to_cpu(rec->inobt.ir_startino);
+	x += XFS_INODES_PER_CHUNK - 1;
+	key->inobt.ir_startino = cpu_to_be32(x);
+}
+
+STATIC void
 xfs_inobt_init_rec_from_cur(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_rec	*rec)
@@ -219,15 +231,25 @@ xfs_finobt_init_ptr_from_cur(
 	ptr->s = agi->agi_free_root;
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_inobt_key_diff(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*key)
 {
-	return (__int64_t)be32_to_cpu(key->inobt.ir_startino) -
+	return (int64_t)be32_to_cpu(key->inobt.ir_startino) -
 			  cur->bc_rec.i.ir_startino;
 }
 
+STATIC int64_t
+xfs_inobt_diff_two_keys(
+	struct xfs_btree_cur	*cur,
+	union xfs_btree_key	*k1,
+	union xfs_btree_key	*k2)
+{
+	return (int64_t)be32_to_cpu(k1->inobt.ir_startino) -
+			  be32_to_cpu(k2->inobt.ir_startino);
+}
+
 static int
 xfs_inobt_verify(
 	struct xfs_buf		*bp)
@@ -302,7 +324,6 @@ const struct xfs_buf_ops xfs_inobt_buf_ops = {
 	.verify_write = xfs_inobt_write_verify,
 };
 
-#if defined(DEBUG) || defined(XFS_WARN)
 STATIC int
 xfs_inobt_keys_inorder(
 	struct xfs_btree_cur	*cur,
@@ -322,7 +343,6 @@ xfs_inobt_recs_inorder(
 	return be32_to_cpu(r1->inobt.ir_startino) + XFS_INODES_PER_CHUNK <=
 		be32_to_cpu(r2->inobt.ir_startino);
 }
-#endif	/* DEBUG */
 
 static const struct xfs_btree_ops xfs_inobt_ops = {
 	.rec_len		= sizeof(xfs_inobt_rec_t),
@@ -335,14 +355,14 @@ static const struct xfs_btree_ops xfs_inobt_ops = {
 	.get_minrecs		= xfs_inobt_get_minrecs,
 	.get_maxrecs		= xfs_inobt_get_maxrecs,
 	.init_key_from_rec	= xfs_inobt_init_key_from_rec,
+	.init_high_key_from_rec	= xfs_inobt_init_high_key_from_rec,
 	.init_rec_from_cur	= xfs_inobt_init_rec_from_cur,
 	.init_ptr_from_cur	= xfs_inobt_init_ptr_from_cur,
 	.key_diff		= xfs_inobt_key_diff,
 	.buf_ops		= &xfs_inobt_buf_ops,
-#if defined(DEBUG) || defined(XFS_WARN)
+	.diff_two_keys		= xfs_inobt_diff_two_keys,
 	.keys_inorder		= xfs_inobt_keys_inorder,
 	.recs_inorder		= xfs_inobt_recs_inorder,
-#endif
 };
 
 static const struct xfs_btree_ops xfs_finobt_ops = {
@@ -356,14 +376,14 @@ static const struct xfs_btree_ops xfs_finobt_ops = {
 	.get_minrecs		= xfs_inobt_get_minrecs,
 	.get_maxrecs		= xfs_inobt_get_maxrecs,
 	.init_key_from_rec	= xfs_inobt_init_key_from_rec,
+	.init_high_key_from_rec	= xfs_inobt_init_high_key_from_rec,
 	.init_rec_from_cur	= xfs_inobt_init_rec_from_cur,
 	.init_ptr_from_cur	= xfs_finobt_init_ptr_from_cur,
 	.key_diff		= xfs_inobt_key_diff,
 	.buf_ops		= &xfs_inobt_buf_ops,
-#if defined(DEBUG) || defined(XFS_WARN)
+	.diff_two_keys		= xfs_inobt_diff_two_keys,
 	.keys_inorder		= xfs_inobt_keys_inorder,
 	.recs_inorder		= xfs_inobt_recs_inorder,
-#endif
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_inode_buf.c b/fs/xfs/libxfs/xfs_inode_buf.c
index d93f9d918cfc..378f8fbc91a7 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.c
+++ b/fs/xfs/libxfs/xfs_inode_buf.c
@@ -105,8 +105,7 @@ xfs_inode_buf_verify(
 		di_ok = dip->di_magic == cpu_to_be16(XFS_DINODE_MAGIC) &&
 			xfs_dinode_good_version(mp, dip->di_version);
 		if (unlikely(XFS_TEST_ERROR(!di_ok, mp,
-						XFS_ERRTAG_ITOBP_INOTOBP,
-						XFS_RANDOM_ITOBP_INOTOBP))) {
+						XFS_ERRTAG_ITOBP_INOTOBP))) {
 			if (readahead) {
 				bp->b_flags &= ~XBF_DONE;
 				xfs_buf_ioerror(bp, -EIO);
@@ -381,7 +380,7 @@ xfs_log_dinode_to_disk(
 	}
 }
 
-static bool
+bool
 xfs_dinode_verify(
 	struct xfs_mount	*mp,
 	xfs_ino_t		ino,
@@ -444,7 +443,7 @@ xfs_dinode_calc_crc(
 	struct xfs_mount	*mp,
 	struct xfs_dinode	*dip)
 {
-	__uint32_t		crc;
+	uint32_t		crc;
 
 	if (dip->di_version < 3)
 		return;
@@ -508,7 +507,7 @@ xfs_iread(
 
 	/* even unallocated inodes are verified */
 	if (!xfs_dinode_verify(mp, ip->i_ino, dip)) {
-		xfs_alert(mp, "%s: validation failed for inode %lld failed",
+		xfs_alert(mp, "%s: validation failed for inode %lld",
 				__func__, ip->i_ino);
 
 		XFS_CORRUPTION_ERROR(__func__, XFS_ERRLEVEL_LOW, mp, dip);
diff --git a/fs/xfs/libxfs/xfs_inode_buf.h b/fs/xfs/libxfs/xfs_inode_buf.h
index 6848a0afbce7..a9c97a356c30 100644
--- a/fs/xfs/libxfs/xfs_inode_buf.h
+++ b/fs/xfs/libxfs/xfs_inode_buf.h
@@ -28,26 +28,26 @@ struct xfs_dinode;
  * format specific structures at the appropriate time.
  */
 struct xfs_icdinode {
-	__int8_t	di_version;	/* inode version */
-	__int8_t	di_format;	/* format of di_c data */
-	__uint16_t	di_flushiter;	/* incremented on flush */
-	__uint32_t	di_uid;		/* owner's user id */
-	__uint32_t	di_gid;		/* owner's group id */
-	__uint16_t	di_projid_lo;	/* lower part of owner's project id */
-	__uint16_t	di_projid_hi;	/* higher part of owner's project id */
+	int8_t		di_version;	/* inode version */
+	int8_t		di_format;	/* format of di_c data */
+	uint16_t	di_flushiter;	/* incremented on flush */
+	uint32_t	di_uid;		/* owner's user id */
+	uint32_t	di_gid;		/* owner's group id */
+	uint16_t	di_projid_lo;	/* lower part of owner's project id */
+	uint16_t	di_projid_hi;	/* higher part of owner's project id */
 	xfs_fsize_t	di_size;	/* number of bytes in file */
 	xfs_rfsblock_t	di_nblocks;	/* # of direct & btree blocks used */
 	xfs_extlen_t	di_extsize;	/* basic/minimum extent size for file */
 	xfs_extnum_t	di_nextents;	/* number of extents in data fork */
 	xfs_aextnum_t	di_anextents;	/* number of extents in attribute fork*/
-	__uint8_t	di_forkoff;	/* attr fork offs, <<3 for 64b align */
-	__int8_t	di_aformat;	/* format of attr fork's data */
-	__uint32_t	di_dmevmask;	/* DMIG event mask */
-	__uint16_t	di_dmstate;	/* DMIG state info */
-	__uint16_t	di_flags;	/* random flags, XFS_DIFLAG_... */
+	uint8_t		di_forkoff;	/* attr fork offs, <<3 for 64b align */
+	int8_t		di_aformat;	/* format of attr fork's data */
+	uint32_t	di_dmevmask;	/* DMIG event mask */
+	uint16_t	di_dmstate;	/* DMIG state info */
+	uint16_t	di_flags;	/* random flags, XFS_DIFLAG_... */
 
-	__uint64_t	di_flags2;	/* more random flags */
-	__uint32_t	di_cowextsize;	/* basic cow extent size for file */
+	uint64_t	di_flags2;	/* more random flags */
+	uint32_t	di_cowextsize;	/* basic cow extent size for file */
 
 	xfs_ictimestamp_t di_crtime;	/* time created */
 };
@@ -82,4 +82,7 @@ void	xfs_inobp_check(struct xfs_mount *, struct xfs_buf *);
 #define	xfs_inobp_check(mp, bp)
 #endif /* DEBUG */
 
+bool	xfs_dinode_verify(struct xfs_mount *mp, xfs_ino_t ino,
+			  struct xfs_dinode *dip);
+
 #endif	/* __XFS_INODE_BUF_H__ */
diff --git a/fs/xfs/libxfs/xfs_inode_fork.c b/fs/xfs/libxfs/xfs_inode_fork.c
index 222e103356c6..0e80f34fe97c 100644
--- a/fs/xfs/libxfs/xfs_inode_fork.c
+++ b/fs/xfs/libxfs/xfs_inode_fork.c
@@ -26,12 +26,15 @@
 #include "xfs_inode.h"
 #include "xfs_trans.h"
 #include "xfs_inode_item.h"
+#include "xfs_btree.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_bmap.h"
 #include "xfs_error.h"
 #include "xfs_trace.h"
 #include "xfs_attr_sf.h"
 #include "xfs_da_format.h"
+#include "xfs_da_btree.h"
+#include "xfs_dir2_priv.h"
 
 kmem_zone_t *xfs_ifork_zone;
 
@@ -39,35 +42,6 @@ STATIC int xfs_iformat_local(xfs_inode_t *, xfs_dinode_t *, int, int);
 STATIC int xfs_iformat_extents(xfs_inode_t *, xfs_dinode_t *, int);
 STATIC int xfs_iformat_btree(xfs_inode_t *, xfs_dinode_t *, int);
 
-#ifdef DEBUG
-/*
- * Make sure that the extents in the given memory buffer
- * are valid.
- */
-void
-xfs_validate_extents(
-	xfs_ifork_t		*ifp,
-	int			nrecs,
-	xfs_exntfmt_t		fmt)
-{
-	xfs_bmbt_irec_t		irec;
-	xfs_bmbt_rec_host_t	rec;
-	int			i;
-
-	for (i = 0; i < nrecs; i++) {
-		xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, i);
-		rec.l0 = get_unaligned(&ep->l0);
-		rec.l1 = get_unaligned(&ep->l1);
-		xfs_bmbt_get_all(&rec, &irec);
-		if (fmt == XFS_EXTFMT_NOSTATE)
-			ASSERT(irec.br_state == XFS_EXT_NORM);
-	}
-}
-#else /* DEBUG */
-#define xfs_validate_extents(ifp, nrecs, fmt)
-#endif /* DEBUG */
-
-
 /*
  * Move inode type and inode format specific information from the
  * on-disk inode to the in-core inode.  For fifos, devs, and sockets
@@ -209,6 +183,16 @@ xfs_iformat_fork(
 	if (error)
 		return error;
 
+	/* Check inline dir contents. */
+	if (S_ISDIR(VFS_I(ip)->i_mode) &&
+	    dip->di_format == XFS_DINODE_FMT_LOCAL) {
+		error = xfs_dir2_sf_verify(ip);
+		if (error) {
+			xfs_idestroy_fork(ip, XFS_DATA_FORK);
+			return error;
+		}
+	}
+
 	if (xfs_is_reflink_inode(ip)) {
 		ASSERT(ip->i_cowfp == NULL);
 		xfs_ifork_init_cow(ip);
@@ -319,7 +303,6 @@ xfs_iformat_local(
 	int		whichfork,
 	int		size)
 {
-
 	/*
 	 * If the size is unreasonable, then something
 	 * is wrong and we just bail out rather than crash in
@@ -340,40 +323,33 @@ xfs_iformat_local(
 }
 
 /*
- * The file consists of a set of extents all
- * of which fit into the on-disk inode.
- * If there are few enough extents to fit into
- * the if_inline_ext, then copy them there.
- * Otherwise allocate a buffer for them and copy
- * them into it.  Either way, set if_extents
- * to point at the extents.
+ * The file consists of a set of extents all of which fit into the on-disk
+ * inode.  If there are few enough extents to fit into the if_inline_ext, then
+ * copy them there.  Otherwise allocate a buffer for them and copy them into it.
+ * Either way, set if_extents to point at the extents.
  */
 STATIC int
 xfs_iformat_extents(
-	xfs_inode_t	*ip,
-	xfs_dinode_t	*dip,
-	int		whichfork)
+	struct xfs_inode	*ip,
+	struct xfs_dinode	*dip,
+	int			whichfork)
 {
-	xfs_bmbt_rec_t	*dp;
-	xfs_ifork_t	*ifp;
-	int		nex;
-	int		size;
-	int		i;
-
-	ifp = XFS_IFORK_PTR(ip, whichfork);
-	nex = XFS_DFORK_NEXTENTS(dip, whichfork);
-	size = nex * (uint)sizeof(xfs_bmbt_rec_t);
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, whichfork);
+	int			nex = XFS_DFORK_NEXTENTS(dip, whichfork);
+	int			size = nex * sizeof(xfs_bmbt_rec_t);
+	struct xfs_bmbt_rec	*dp;
+	int			i;
 
 	/*
-	 * If the number of extents is unreasonable, then something
-	 * is wrong and we just bail out rather than crash in
-	 * kmem_alloc() or memcpy() below.
+	 * If the number of extents is unreasonable, then something is wrong and
+	 * we just bail out rather than crash in kmem_alloc() or memcpy() below.
 	 */
-	if (unlikely(size < 0 || size > XFS_DFORK_SIZE(dip, ip->i_mount, whichfork))) {
+	if (unlikely(size < 0 || size > XFS_DFORK_SIZE(dip, mp, whichfork))) {
 		xfs_warn(ip->i_mount, "corrupt inode %Lu ((a)extents = %d).",
 			(unsigned long long) ip->i_ino, nex);
 		XFS_CORRUPTION_ERROR("xfs_iformat_extents(1)", XFS_ERRLEVEL_LOW,
-				     ip->i_mount, dip);
+				     mp, dip);
 		return -EFSCORRUPTED;
 	}
 
@@ -388,22 +364,17 @@ xfs_iformat_extents(
 	ifp->if_bytes = size;
 	if (size) {
 		dp = (xfs_bmbt_rec_t *) XFS_DFORK_PTR(dip, whichfork);
-		xfs_validate_extents(ifp, nex, XFS_EXTFMT_INODE(ip));
 		for (i = 0; i < nex; i++, dp++) {
 			xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, i);
 			ep->l0 = get_unaligned_be64(&dp->l0);
 			ep->l1 = get_unaligned_be64(&dp->l1);
+			if (!xfs_bmbt_validate_extent(mp, whichfork, ep)) {
+				XFS_ERROR_REPORT("xfs_iformat_extents(2)",
+						 XFS_ERRLEVEL_LOW, mp);
+				return -EFSCORRUPTED;
+			}
 		}
 		XFS_BMAP_TRACE_EXLIST(ip, nex, whichfork);
-		if (whichfork != XFS_DATA_FORK ||
-			XFS_EXTFMT_INODE(ip) == XFS_EXTFMT_NOSTATE)
-				if (unlikely(xfs_check_nostate_extents(
-				    ifp, 0, nex))) {
-					XFS_ERROR_REPORT("xfs_iformat_extents(2)",
-							 XFS_ERRLEVEL_LOW,
-							 ip->i_mount);
-					return -EFSCORRUPTED;
-				}
 	}
 	ifp->if_flags |= XFS_IFEXTENTS;
 	return 0;
@@ -429,11 +400,13 @@ xfs_iformat_btree(
 	/* REFERENCED */
 	int			nrecs;
 	int			size;
+	int			level;
 
 	ifp = XFS_IFORK_PTR(ip, whichfork);
 	dfp = (xfs_bmdr_block_t *)XFS_DFORK_PTR(dip, whichfork);
 	size = XFS_BMAP_BROOT_SPACE(mp, dfp);
 	nrecs = be16_to_cpu(dfp->bb_numrecs);
+	level = be16_to_cpu(dfp->bb_level);
 
 	/*
 	 * blow out if -- fork has less extents than can fit in
@@ -446,7 +419,8 @@ xfs_iformat_btree(
 					XFS_IFORK_MAXEXT(ip, whichfork) ||
 		     XFS_BMDR_SPACE_CALC(nrecs) >
 					XFS_DFORK_SIZE(dip, mp, whichfork) ||
-		     XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks)) {
+		     XFS_IFORK_NEXTENTS(ip, whichfork) > ip->i_d.di_nblocks) ||
+		     level == 0 || level > XFS_BTREE_MAXLEVELS) {
 		xfs_warn(mp, "corrupt inode %Lu (btree).",
 					(unsigned long long) ip->i_ino);
 		XFS_CORRUPTION_ERROR("xfs_iformat_btree", XFS_ERRLEVEL_LOW,
@@ -497,15 +471,13 @@ xfs_iread_extents(
 	 * We know that the size is valid (it's checked in iformat_btree)
 	 */
 	ifp->if_bytes = ifp->if_real_bytes = 0;
-	ifp->if_flags |= XFS_IFEXTENTS;
 	xfs_iext_add(ifp, 0, nextents);
 	error = xfs_bmap_read_extents(tp, ip, whichfork);
 	if (error) {
 		xfs_iext_destroy(ifp);
-		ifp->if_flags &= ~XFS_IFEXTENTS;
 		return error;
 	}
-	xfs_validate_extents(ifp, nextents, XFS_EXTFMT_INODE(ip));
+	ifp->if_flags |= XFS_IFEXTENTS;
 	return 0;
 }
 /*
@@ -823,6 +795,9 @@ xfs_iextents_copy(
 	copied = 0;
 	for (i = 0; i < nrecs; i++) {
 		xfs_bmbt_rec_host_t *ep = xfs_iext_get_ext(ifp, i);
+
+		ASSERT(xfs_bmbt_validate_extent(ip->i_mount, whichfork, ep));
+
 		start_block = xfs_bmbt_get_startblock(ep);
 		if (isnullstartblock(start_block)) {
 			/*
@@ -838,7 +813,6 @@ xfs_iextents_copy(
 		copied++;
 	}
 	ASSERT(copied != 0);
-	xfs_validate_extents(ifp, copied, XFS_EXTFMT_INODE(ip));
 
 	return (copied * (uint)sizeof(xfs_bmbt_rec_t));
 }
diff --git a/fs/xfs/libxfs/xfs_log_format.h b/fs/xfs/libxfs/xfs_log_format.h
index 7ae571f8e34a..8372e9bcd7b6 100644
--- a/fs/xfs/libxfs/xfs_log_format.h
+++ b/fs/xfs/libxfs/xfs_log_format.h
@@ -31,7 +31,7 @@ struct xfs_trans_res;
  * through all the log items definitions and everything they encode into the
  * log.
  */
-typedef __uint32_t xlog_tid_t;
+typedef uint32_t xlog_tid_t;
 
 #define XLOG_MIN_ICLOGS		2
 #define XLOG_MAX_ICLOGS		8
@@ -211,7 +211,7 @@ typedef struct xfs_log_iovec {
 typedef struct xfs_trans_header {
 	uint		th_magic;		/* magic number */
 	uint		th_type;		/* transaction type */
-	__int32_t	th_tid;			/* transaction id (unused) */
+	int32_t		th_tid;			/* transaction id (unused) */
 	uint		th_num_items;		/* num items logged by trans */
 } xfs_trans_header_t;
 
@@ -265,52 +265,52 @@ typedef struct xfs_trans_header {
  * must be added on to the end.
  */
 typedef struct xfs_inode_log_format {
-	__uint16_t		ilf_type;	/* inode log item type */
-	__uint16_t		ilf_size;	/* size of this item */
-	__uint32_t		ilf_fields;	/* flags for fields logged */
-	__uint16_t		ilf_asize;	/* size of attr d/ext/root */
-	__uint16_t		ilf_dsize;	/* size of data/ext/root */
-	__uint64_t		ilf_ino;	/* inode number */
+	uint16_t		ilf_type;	/* inode log item type */
+	uint16_t		ilf_size;	/* size of this item */
+	uint32_t		ilf_fields;	/* flags for fields logged */
+	uint16_t		ilf_asize;	/* size of attr d/ext/root */
+	uint16_t		ilf_dsize;	/* size of data/ext/root */
+	uint64_t		ilf_ino;	/* inode number */
 	union {
-		__uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
+		uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
 		uuid_t		ilfu_uuid;	/* mount point value */
 	} ilf_u;
-	__int64_t		ilf_blkno;	/* blkno of inode buffer */
-	__int32_t		ilf_len;	/* len of inode buffer */
-	__int32_t		ilf_boffset;	/* off of inode in buffer */
+	int64_t			ilf_blkno;	/* blkno of inode buffer */
+	int32_t			ilf_len;	/* len of inode buffer */
+	int32_t			ilf_boffset;	/* off of inode in buffer */
 } xfs_inode_log_format_t;
 
 typedef struct xfs_inode_log_format_32 {
-	__uint16_t		ilf_type;	/* inode log item type */
-	__uint16_t		ilf_size;	/* size of this item */
-	__uint32_t		ilf_fields;	/* flags for fields logged */
-	__uint16_t		ilf_asize;	/* size of attr d/ext/root */
-	__uint16_t		ilf_dsize;	/* size of data/ext/root */
-	__uint64_t		ilf_ino;	/* inode number */
+	uint16_t		ilf_type;	/* inode log item type */
+	uint16_t		ilf_size;	/* size of this item */
+	uint32_t		ilf_fields;	/* flags for fields logged */
+	uint16_t		ilf_asize;	/* size of attr d/ext/root */
+	uint16_t		ilf_dsize;	/* size of data/ext/root */
+	uint64_t		ilf_ino;	/* inode number */
 	union {
-		__uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
+		uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
 		uuid_t		ilfu_uuid;	/* mount point value */
 	} ilf_u;
-	__int64_t		ilf_blkno;	/* blkno of inode buffer */
-	__int32_t		ilf_len;	/* len of inode buffer */
-	__int32_t		ilf_boffset;	/* off of inode in buffer */
+	int64_t			ilf_blkno;	/* blkno of inode buffer */
+	int32_t			ilf_len;	/* len of inode buffer */
+	int32_t			ilf_boffset;	/* off of inode in buffer */
 } __attribute__((packed)) xfs_inode_log_format_32_t;
 
 typedef struct xfs_inode_log_format_64 {
-	__uint16_t		ilf_type;	/* inode log item type */
-	__uint16_t		ilf_size;	/* size of this item */
-	__uint32_t		ilf_fields;	/* flags for fields logged */
-	__uint16_t		ilf_asize;	/* size of attr d/ext/root */
-	__uint16_t		ilf_dsize;	/* size of data/ext/root */
-	__uint32_t		ilf_pad;	/* pad for 64 bit boundary */
-	__uint64_t		ilf_ino;	/* inode number */
+	uint16_t		ilf_type;	/* inode log item type */
+	uint16_t		ilf_size;	/* size of this item */
+	uint32_t		ilf_fields;	/* flags for fields logged */
+	uint16_t		ilf_asize;	/* size of attr d/ext/root */
+	uint16_t		ilf_dsize;	/* size of data/ext/root */
+	uint32_t		ilf_pad;	/* pad for 64 bit boundary */
+	uint64_t		ilf_ino;	/* inode number */
 	union {
-		__uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
+		uint32_t	ilfu_rdev;	/* rdev value for dev inode*/
 		uuid_t		ilfu_uuid;	/* mount point value */
 	} ilf_u;
-	__int64_t		ilf_blkno;	/* blkno of inode buffer */
-	__int32_t		ilf_len;	/* len of inode buffer */
-	__int32_t		ilf_boffset;	/* off of inode in buffer */
+	int64_t			ilf_blkno;	/* blkno of inode buffer */
+	int32_t			ilf_len;	/* len of inode buffer */
+	int32_t			ilf_boffset;	/* off of inode in buffer */
 } xfs_inode_log_format_64_t;
 
 
@@ -379,8 +379,8 @@ static inline int xfs_ilog_fdata(int w)
  * information.
  */
 typedef struct xfs_ictimestamp {
-	__int32_t	t_sec;		/* timestamp seconds */
-	__int32_t	t_nsec;		/* timestamp nanoseconds */
+	int32_t		t_sec;		/* timestamp seconds */
+	int32_t		t_nsec;		/* timestamp nanoseconds */
 } xfs_ictimestamp_t;
 
 /*
@@ -388,18 +388,18 @@ typedef struct xfs_ictimestamp {
  * kept identical to struct xfs_dinode except for the endianness annotations.
  */
 struct xfs_log_dinode {
-	__uint16_t	di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
-	__uint16_t	di_mode;	/* mode and type of file */
-	__int8_t	di_version;	/* inode version */
-	__int8_t	di_format;	/* format of di_c data */
-	__uint8_t	di_pad3[2];	/* unused in v2/3 inodes */
-	__uint32_t	di_uid;		/* owner's user id */
-	__uint32_t	di_gid;		/* owner's group id */
-	__uint32_t	di_nlink;	/* number of links to file */
-	__uint16_t	di_projid_lo;	/* lower part of owner's project id */
-	__uint16_t	di_projid_hi;	/* higher part of owner's project id */
-	__uint8_t	di_pad[6];	/* unused, zeroed space */
-	__uint16_t	di_flushiter;	/* incremented on flush */
+	uint16_t	di_magic;	/* inode magic # = XFS_DINODE_MAGIC */
+	uint16_t	di_mode;	/* mode and type of file */
+	int8_t		di_version;	/* inode version */
+	int8_t		di_format;	/* format of di_c data */
+	uint8_t		di_pad3[2];	/* unused in v2/3 inodes */
+	uint32_t	di_uid;		/* owner's user id */
+	uint32_t	di_gid;		/* owner's group id */
+	uint32_t	di_nlink;	/* number of links to file */
+	uint16_t	di_projid_lo;	/* lower part of owner's project id */
+	uint16_t	di_projid_hi;	/* higher part of owner's project id */
+	uint8_t		di_pad[6];	/* unused, zeroed space */
+	uint16_t	di_flushiter;	/* incremented on flush */
 	xfs_ictimestamp_t di_atime;	/* time last accessed */
 	xfs_ictimestamp_t di_mtime;	/* time last modified */
 	xfs_ictimestamp_t di_ctime;	/* time created/inode modified */
@@ -408,23 +408,23 @@ struct xfs_log_dinode {
 	xfs_extlen_t	di_extsize;	/* basic/minimum extent size for file */
 	xfs_extnum_t	di_nextents;	/* number of extents in data fork */
 	xfs_aextnum_t	di_anextents;	/* number of extents in attribute fork*/
-	__uint8_t	di_forkoff;	/* attr fork offs, <<3 for 64b align */
-	__int8_t	di_aformat;	/* format of attr fork's data */
-	__uint32_t	di_dmevmask;	/* DMIG event mask */
-	__uint16_t	di_dmstate;	/* DMIG state info */
-	__uint16_t	di_flags;	/* random flags, XFS_DIFLAG_... */
-	__uint32_t	di_gen;		/* generation number */
+	uint8_t		di_forkoff;	/* attr fork offs, <<3 for 64b align */
+	int8_t		di_aformat;	/* format of attr fork's data */
+	uint32_t	di_dmevmask;	/* DMIG event mask */
+	uint16_t	di_dmstate;	/* DMIG state info */
+	uint16_t	di_flags;	/* random flags, XFS_DIFLAG_... */
+	uint32_t	di_gen;		/* generation number */
 
 	/* di_next_unlinked is the only non-core field in the old dinode */
 	xfs_agino_t	di_next_unlinked;/* agi unlinked list ptr */
 
 	/* start of the extended dinode, writable fields */
-	__uint32_t	di_crc;		/* CRC of the inode */
-	__uint64_t	di_changecount;	/* number of attribute changes */
+	uint32_t	di_crc;		/* CRC of the inode */
+	uint64_t	di_changecount;	/* number of attribute changes */
 	xfs_lsn_t	di_lsn;		/* flush sequence */
-	__uint64_t	di_flags2;	/* more random flags */
-	__uint32_t	di_cowextsize;	/* basic cow extent size for file */
-	__uint8_t	di_pad2[12];	/* more padding for future expansion */
+	uint64_t	di_flags2;	/* more random flags */
+	uint32_t	di_cowextsize;	/* basic cow extent size for file */
+	uint8_t		di_pad2[12];	/* more padding for future expansion */
 
 	/* fields only written to during inode creation */
 	xfs_ictimestamp_t di_crtime;	/* time created */
@@ -483,7 +483,7 @@ typedef struct xfs_buf_log_format {
 	unsigned short	blf_size;	/* size of this item */
 	unsigned short	blf_flags;	/* misc state */
 	unsigned short	blf_len;	/* number of blocks in this buf */
-	__int64_t	blf_blkno;	/* starting blkno of this buf */
+	int64_t		blf_blkno;	/* starting blkno of this buf */
 	unsigned int	blf_map_size;	/* used size of data bitmap in words */
 	unsigned int	blf_data_map[XFS_BLF_DATAMAP_SIZE]; /* dirty bitmap */
 } xfs_buf_log_format_t;
@@ -533,7 +533,7 @@ xfs_blft_to_flags(struct xfs_buf_log_format *blf, enum xfs_blft type)
 	blf->blf_flags |= ((type << XFS_BLFT_SHIFT) & XFS_BLFT_MASK);
 }
 
-static inline __uint16_t
+static inline uint16_t
 xfs_blft_from_flags(struct xfs_buf_log_format *blf)
 {
 	return (blf->blf_flags & XFS_BLFT_MASK) >> XFS_BLFT_SHIFT;
@@ -554,14 +554,14 @@ typedef struct xfs_extent {
  * conversion routine.
  */
 typedef struct xfs_extent_32 {
-	__uint64_t	ext_start;
-	__uint32_t	ext_len;
+	uint64_t	ext_start;
+	uint32_t	ext_len;
 } __attribute__((packed)) xfs_extent_32_t;
 
 typedef struct xfs_extent_64 {
-	__uint64_t	ext_start;
-	__uint32_t	ext_len;
-	__uint32_t	ext_pad;
+	uint64_t	ext_start;
+	uint32_t	ext_len;
+	uint32_t	ext_pad;
 } xfs_extent_64_t;
 
 /*
@@ -570,26 +570,26 @@ typedef struct xfs_extent_64 {
  * size is given by efi_nextents.
  */
 typedef struct xfs_efi_log_format {
-	__uint16_t		efi_type;	/* efi log item type */
-	__uint16_t		efi_size;	/* size of this item */
-	__uint32_t		efi_nextents;	/* # extents to free */
-	__uint64_t		efi_id;		/* efi identifier */
+	uint16_t		efi_type;	/* efi log item type */
+	uint16_t		efi_size;	/* size of this item */
+	uint32_t		efi_nextents;	/* # extents to free */
+	uint64_t		efi_id;		/* efi identifier */
 	xfs_extent_t		efi_extents[1];	/* array of extents to free */
 } xfs_efi_log_format_t;
 
 typedef struct xfs_efi_log_format_32 {
-	__uint16_t		efi_type;	/* efi log item type */
-	__uint16_t		efi_size;	/* size of this item */
-	__uint32_t		efi_nextents;	/* # extents to free */
-	__uint64_t		efi_id;		/* efi identifier */
+	uint16_t		efi_type;	/* efi log item type */
+	uint16_t		efi_size;	/* size of this item */
+	uint32_t		efi_nextents;	/* # extents to free */
+	uint64_t		efi_id;		/* efi identifier */
 	xfs_extent_32_t		efi_extents[1];	/* array of extents to free */
 } __attribute__((packed)) xfs_efi_log_format_32_t;
 
 typedef struct xfs_efi_log_format_64 {
-	__uint16_t		efi_type;	/* efi log item type */
-	__uint16_t		efi_size;	/* size of this item */
-	__uint32_t		efi_nextents;	/* # extents to free */
-	__uint64_t		efi_id;		/* efi identifier */
+	uint16_t		efi_type;	/* efi log item type */
+	uint16_t		efi_size;	/* size of this item */
+	uint32_t		efi_nextents;	/* # extents to free */
+	uint64_t		efi_id;		/* efi identifier */
 	xfs_extent_64_t		efi_extents[1];	/* array of extents to free */
 } xfs_efi_log_format_64_t;
 
@@ -599,26 +599,26 @@ typedef struct xfs_efi_log_format_64 {
  * size is given by efd_nextents;
  */
 typedef struct xfs_efd_log_format {
-	__uint16_t		efd_type;	/* efd log item type */
-	__uint16_t		efd_size;	/* size of this item */
-	__uint32_t		efd_nextents;	/* # of extents freed */
-	__uint64_t		efd_efi_id;	/* id of corresponding efi */
+	uint16_t		efd_type;	/* efd log item type */
+	uint16_t		efd_size;	/* size of this item */
+	uint32_t		efd_nextents;	/* # of extents freed */
+	uint64_t		efd_efi_id;	/* id of corresponding efi */
 	xfs_extent_t		efd_extents[1];	/* array of extents freed */
 } xfs_efd_log_format_t;
 
 typedef struct xfs_efd_log_format_32 {
-	__uint16_t		efd_type;	/* efd log item type */
-	__uint16_t		efd_size;	/* size of this item */
-	__uint32_t		efd_nextents;	/* # of extents freed */
-	__uint64_t		efd_efi_id;	/* id of corresponding efi */
+	uint16_t		efd_type;	/* efd log item type */
+	uint16_t		efd_size;	/* size of this item */
+	uint32_t		efd_nextents;	/* # of extents freed */
+	uint64_t		efd_efi_id;	/* id of corresponding efi */
 	xfs_extent_32_t		efd_extents[1];	/* array of extents freed */
 } __attribute__((packed)) xfs_efd_log_format_32_t;
 
 typedef struct xfs_efd_log_format_64 {
-	__uint16_t		efd_type;	/* efd log item type */
-	__uint16_t		efd_size;	/* size of this item */
-	__uint32_t		efd_nextents;	/* # of extents freed */
-	__uint64_t		efd_efi_id;	/* id of corresponding efi */
+	uint16_t		efd_type;	/* efd log item type */
+	uint16_t		efd_size;	/* size of this item */
+	uint32_t		efd_nextents;	/* # of extents freed */
+	uint64_t		efd_efi_id;	/* id of corresponding efi */
 	xfs_extent_64_t		efd_extents[1];	/* array of extents freed */
 } xfs_efd_log_format_64_t;
 
@@ -626,11 +626,11 @@ typedef struct xfs_efd_log_format_64 {
  * RUI/RUD (reverse mapping) log format definitions
  */
 struct xfs_map_extent {
-	__uint64_t		me_owner;
-	__uint64_t		me_startblock;
-	__uint64_t		me_startoff;
-	__uint32_t		me_len;
-	__uint32_t		me_flags;
+	uint64_t		me_owner;
+	uint64_t		me_startblock;
+	uint64_t		me_startoff;
+	uint32_t		me_len;
+	uint32_t		me_flags;
 };
 
 /* rmap me_flags: upper bits are flags, lower byte is type code */
@@ -659,10 +659,10 @@ struct xfs_map_extent {
  * size is given by rui_nextents.
  */
 struct xfs_rui_log_format {
-	__uint16_t		rui_type;	/* rui log item type */
-	__uint16_t		rui_size;	/* size of this item */
-	__uint32_t		rui_nextents;	/* # extents to free */
-	__uint64_t		rui_id;		/* rui identifier */
+	uint16_t		rui_type;	/* rui log item type */
+	uint16_t		rui_size;	/* size of this item */
+	uint32_t		rui_nextents;	/* # extents to free */
+	uint64_t		rui_id;		/* rui identifier */
 	struct xfs_map_extent	rui_extents[];	/* array of extents to rmap */
 };
 
@@ -680,19 +680,19 @@ xfs_rui_log_format_sizeof(
  * size is given by rud_nextents;
  */
 struct xfs_rud_log_format {
-	__uint16_t		rud_type;	/* rud log item type */
-	__uint16_t		rud_size;	/* size of this item */
-	__uint32_t		__pad;
-	__uint64_t		rud_rui_id;	/* id of corresponding rui */
+	uint16_t		rud_type;	/* rud log item type */
+	uint16_t		rud_size;	/* size of this item */
+	uint32_t		__pad;
+	uint64_t		rud_rui_id;	/* id of corresponding rui */
 };
 
 /*
  * CUI/CUD (refcount update) log format definitions
  */
 struct xfs_phys_extent {
-	__uint64_t		pe_startblock;
-	__uint32_t		pe_len;
-	__uint32_t		pe_flags;
+	uint64_t		pe_startblock;
+	uint32_t		pe_len;
+	uint32_t		pe_flags;
 };
 
 /* refcount pe_flags: upper bits are flags, lower byte is type code */
@@ -707,10 +707,10 @@ struct xfs_phys_extent {
  * size is given by cui_nextents.
  */
 struct xfs_cui_log_format {
-	__uint16_t		cui_type;	/* cui log item type */
-	__uint16_t		cui_size;	/* size of this item */
-	__uint32_t		cui_nextents;	/* # extents to free */
-	__uint64_t		cui_id;		/* cui identifier */
+	uint16_t		cui_type;	/* cui log item type */
+	uint16_t		cui_size;	/* size of this item */
+	uint32_t		cui_nextents;	/* # extents to free */
+	uint64_t		cui_id;		/* cui identifier */
 	struct xfs_phys_extent	cui_extents[];	/* array of extents */
 };
 
@@ -728,10 +728,10 @@ xfs_cui_log_format_sizeof(
  * size is given by cud_nextents;
  */
 struct xfs_cud_log_format {
-	__uint16_t		cud_type;	/* cud log item type */
-	__uint16_t		cud_size;	/* size of this item */
-	__uint32_t		__pad;
-	__uint64_t		cud_cui_id;	/* id of corresponding cui */
+	uint16_t		cud_type;	/* cud log item type */
+	uint16_t		cud_size;	/* size of this item */
+	uint32_t		__pad;
+	uint64_t		cud_cui_id;	/* id of corresponding cui */
 };
 
 /*
@@ -755,10 +755,10 @@ struct xfs_cud_log_format {
  * size is given by bui_nextents.
  */
 struct xfs_bui_log_format {
-	__uint16_t		bui_type;	/* bui log item type */
-	__uint16_t		bui_size;	/* size of this item */
-	__uint32_t		bui_nextents;	/* # extents to free */
-	__uint64_t		bui_id;		/* bui identifier */
+	uint16_t		bui_type;	/* bui log item type */
+	uint16_t		bui_size;	/* size of this item */
+	uint32_t		bui_nextents;	/* # extents to free */
+	uint64_t		bui_id;		/* bui identifier */
 	struct xfs_map_extent	bui_extents[];	/* array of extents to bmap */
 };
 
@@ -776,10 +776,10 @@ xfs_bui_log_format_sizeof(
  * size is given by bud_nextents;
  */
 struct xfs_bud_log_format {
-	__uint16_t		bud_type;	/* bud log item type */
-	__uint16_t		bud_size;	/* size of this item */
-	__uint32_t		__pad;
-	__uint64_t		bud_bui_id;	/* id of corresponding bui */
+	uint16_t		bud_type;	/* bud log item type */
+	uint16_t		bud_size;	/* size of this item */
+	uint32_t		__pad;
+	uint64_t		bud_bui_id;	/* id of corresponding bui */
 };
 
 /*
@@ -789,12 +789,12 @@ struct xfs_bud_log_format {
  * 32 bits : log_recovery code assumes that.
  */
 typedef struct xfs_dq_logformat {
-	__uint16_t		qlf_type;      /* dquot log item type */
-	__uint16_t		qlf_size;      /* size of this item */
+	uint16_t		qlf_type;      /* dquot log item type */
+	uint16_t		qlf_size;      /* size of this item */
 	xfs_dqid_t		qlf_id;	       /* usr/grp/proj id : 32 bits */
-	__int64_t		qlf_blkno;     /* blkno of dquot buffer */
-	__int32_t		qlf_len;       /* len of dquot buffer */
-	__uint32_t		qlf_boffset;   /* off of dquot in buffer */
+	int64_t			qlf_blkno;     /* blkno of dquot buffer */
+	int32_t			qlf_len;       /* len of dquot buffer */
+	uint32_t		qlf_boffset;   /* off of dquot in buffer */
 } xfs_dq_logformat_t;
 
 /*
@@ -853,8 +853,8 @@ typedef struct xfs_qoff_logformat {
  * decoding can be done correctly.
  */
 struct xfs_icreate_log {
-	__uint16_t	icl_type;	/* type of log format structure */
-	__uint16_t	icl_size;	/* size of log format structure */
+	uint16_t	icl_type;	/* type of log format structure */
+	uint16_t	icl_size;	/* size of log format structure */
 	__be32		icl_ag;		/* ag being allocated in */
 	__be32		icl_agbno;	/* start block of inode range */
 	__be32		icl_count;	/* number of inodes to initialise */
diff --git a/fs/xfs/libxfs/xfs_log_recover.h b/fs/xfs/libxfs/xfs_log_recover.h
index d9f65e2d5cc8..66948a9fd486 100644
--- a/fs/xfs/libxfs/xfs_log_recover.h
+++ b/fs/xfs/libxfs/xfs_log_recover.h
@@ -26,7 +26,7 @@
 #define XLOG_RHASH_SIZE	16
 #define XLOG_RHASH_SHIFT 2
 #define XLOG_RHASH(tid)	\
-	((((__uint32_t)tid)>>XLOG_RHASH_SHIFT) & (XLOG_RHASH_SIZE-1))
+	((((uint32_t)tid)>>XLOG_RHASH_SHIFT) & (XLOG_RHASH_SIZE-1))
 
 #define XLOG_MAX_REGIONS_IN_ITEM   (XFS_MAX_BLOCKSIZE / XFS_BLF_CHUNK / 2 + 1)
 
@@ -42,7 +42,6 @@ typedef struct xlog_recover_item {
 	xfs_log_iovec_t		*ri_buf;	/* ptr to regions buffer */
 } xlog_recover_item_t;
 
-struct xlog_tid;
 typedef struct xlog_recover {
 	struct hlist_node	r_list;
 	xlog_tid_t		r_log_tid;	/* log's transaction id */
diff --git a/fs/xfs/libxfs/xfs_quota_defs.h b/fs/xfs/libxfs/xfs_quota_defs.h
index 8eed51275bb3..d69c772271cb 100644
--- a/fs/xfs/libxfs/xfs_quota_defs.h
+++ b/fs/xfs/libxfs/xfs_quota_defs.h
@@ -27,8 +27,8 @@
  * they may need 64-bit accounting. Hence, 64-bit quota-counters,
  * and quota-limits. This is a waste in the common case, but hey ...
  */
-typedef __uint64_t	xfs_qcnt_t;
-typedef __uint16_t	xfs_qwarncnt_t;
+typedef uint64_t	xfs_qcnt_t;
+typedef uint16_t	xfs_qwarncnt_t;
 
 /*
  * flags for q_flags field in the dquot.
diff --git a/fs/xfs/libxfs/xfs_refcount.c b/fs/xfs/libxfs/xfs_refcount.c
index b177ef33cd4c..900ea231f9a3 100644
--- a/fs/xfs/libxfs/xfs_refcount.c
+++ b/fs/xfs/libxfs/xfs_refcount.c
@@ -784,14 +784,6 @@ xfs_refcount_merge_extents(
 }
 
 /*
- * While we're adjusting the refcounts records of an extent, we have
- * to keep an eye on the number of extents we're dirtying -- run too
- * many in a single transaction and we'll exceed the transaction's
- * reservation and crash the fs.  Each record adds 12 bytes to the
- * log (plus any key updates) so we'll conservatively assume 24 bytes
- * per record.  We must also leave space for btree splits on both ends
- * of the range and space for the CUD and a new CUI.
- *
  * XXX: This is a pretty hand-wavy estimate.  The penalty for guessing
  * true incorrectly is a shutdown FS; the penalty for guessing false
  * incorrectly is more transaction rolls than might be necessary.
@@ -813,8 +805,7 @@ xfs_refcount_still_have_space(
 	 */
 	if (cur->bc_private.a.priv.refc.nr_ops > 2 &&
 	    XFS_TEST_ERROR(false, cur->bc_mp,
-			XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE,
-			XFS_RANDOM_REFCOUNT_CONTINUE_UPDATE))
+			XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE))
 		return false;
 
 	if (cur->bc_private.a.priv.refc.nr_ops == 0)
@@ -822,7 +813,7 @@ xfs_refcount_still_have_space(
 	else if (overhead > cur->bc_tp->t_log_res)
 		return false;
 	return  cur->bc_tp->t_log_res - overhead >
-		cur->bc_private.a.priv.refc.nr_ops * 32;
+		cur->bc_private.a.priv.refc.nr_ops * XFS_REFCOUNT_ITEM_OVERHEAD;
 }
 
 /*
@@ -1076,8 +1067,7 @@ xfs_refcount_finish_one(
 			blockcount);
 
 	if (XFS_TEST_ERROR(false, mp,
-			XFS_ERRTAG_REFCOUNT_FINISH_ONE,
-			XFS_RANDOM_REFCOUNT_FINISH_ONE))
+			XFS_ERRTAG_REFCOUNT_FINISH_ONE))
 		return -EIO;
 
 	/*
@@ -1629,13 +1619,28 @@ xfs_refcount_recover_cow_leftovers(
 	if (mp->m_sb.sb_agblocks >= XFS_REFC_COW_START)
 		return -EOPNOTSUPP;
 
-	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	INIT_LIST_HEAD(&debris);
+
+	/*
+	 * In this first part, we use an empty transaction to gather up
+	 * all the leftover CoW extents so that we can subsequently
+	 * delete them.  The empty transaction is used to avoid
+	 * a buffer lock deadlock if there happens to be a loop in the
+	 * refcountbt because we're allowed to re-grab a buffer that is
+	 * already attached to our transaction.  When we're done
+	 * recording the CoW debris we cancel the (empty) transaction
+	 * and everything goes away cleanly.
+	 */
+	error = xfs_trans_alloc_empty(mp, &tp);
 	if (error)
 		return error;
-	cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL);
+
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
+	if (error)
+		goto out_trans;
+	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
 
 	/* Find all the leftover CoW staging extents. */
-	INIT_LIST_HEAD(&debris);
 	memset(&low, 0, sizeof(low));
 	memset(&high, 0, sizeof(high));
 	low.rc.rc_startblock = XFS_REFC_COW_START;
@@ -1645,10 +1650,11 @@ xfs_refcount_recover_cow_leftovers(
 	if (error)
 		goto out_cursor;
 	xfs_btree_del_cursor(cur, XFS_BTREE_NOERROR);
-	xfs_buf_relse(agbp);
+	xfs_trans_brelse(tp, agbp);
+	xfs_trans_cancel(tp);
 
 	/* Now iterate the list to free the leftovers */
-	list_for_each_entry(rr, &debris, rr_list) {
+	list_for_each_entry_safe(rr, n, &debris, rr_list) {
 		/* Set up transaction. */
 		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0, 0, &tp);
 		if (error)
@@ -1676,8 +1682,16 @@ xfs_refcount_recover_cow_leftovers(
 		error = xfs_trans_commit(tp);
 		if (error)
 			goto out_free;
+
+		list_del(&rr->rr_list);
+		kmem_free(rr);
 	}
 
+	return error;
+out_defer:
+	xfs_defer_cancel(&dfops);
+out_trans:
+	xfs_trans_cancel(tp);
 out_free:
 	/* Free the leftover list */
 	list_for_each_entry_safe(rr, n, &debris, rr_list) {
@@ -1688,11 +1702,6 @@ out_free:
 
 out_cursor:
 	xfs_btree_del_cursor(cur, XFS_BTREE_ERROR);
-	xfs_buf_relse(agbp);
-	goto out_free;
-
-out_defer:
-	xfs_defer_cancel(&dfops);
-	xfs_trans_cancel(tp);
-	goto out_free;
+	xfs_trans_brelse(tp, agbp);
+	goto out_trans;
 }
diff --git a/fs/xfs/libxfs/xfs_refcount.h b/fs/xfs/libxfs/xfs_refcount.h
index 098dc668ab2c..eafb9d1f3b37 100644
--- a/fs/xfs/libxfs/xfs_refcount.h
+++ b/fs/xfs/libxfs/xfs_refcount.h
@@ -67,4 +67,20 @@ extern int xfs_refcount_free_cow_extent(struct xfs_mount *mp,
 extern int xfs_refcount_recover_cow_leftovers(struct xfs_mount *mp,
 		xfs_agnumber_t agno);
 
+/*
+ * While we're adjusting the refcounts records of an extent, we have
+ * to keep an eye on the number of extents we're dirtying -- run too
+ * many in a single transaction and we'll exceed the transaction's
+ * reservation and crash the fs.  Each record adds 12 bytes to the
+ * log (plus any key updates) so we'll conservatively assume 32 bytes
+ * per record.  We must also leave space for btree splits on both ends
+ * of the range and space for the CUD and a new CUI.
+ */
+#define XFS_REFCOUNT_ITEM_OVERHEAD	32
+
+static inline xfs_fileoff_t xfs_refcount_max_unmap(int log_res)
+{
+	return (log_res * 3 / 4) / XFS_REFCOUNT_ITEM_OVERHEAD;
+}
+
 #endif	/* __XFS_REFCOUNT_H__ */
diff --git a/fs/xfs/libxfs/xfs_refcount_btree.c b/fs/xfs/libxfs/xfs_refcount_btree.c
index 50add5272807..3c59dd3d58d7 100644
--- a/fs/xfs/libxfs/xfs_refcount_btree.c
+++ b/fs/xfs/libxfs/xfs_refcount_btree.c
@@ -202,7 +202,7 @@ xfs_refcountbt_init_ptr_from_cur(
 	ptr->s = agf->agf_refcount_root;
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_refcountbt_key_diff(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*key)
@@ -210,16 +210,16 @@ xfs_refcountbt_key_diff(
 	struct xfs_refcount_irec	*rec = &cur->bc_rec.rc;
 	struct xfs_refcount_key		*kp = &key->refc;
 
-	return (__int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock;
+	return (int64_t)be32_to_cpu(kp->rc_startblock) - rec->rc_startblock;
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_refcountbt_diff_two_keys(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*k1,
 	union xfs_btree_key	*k2)
 {
-	return (__int64_t)be32_to_cpu(k1->refc.rc_startblock) -
+	return (int64_t)be32_to_cpu(k1->refc.rc_startblock) -
 			  be32_to_cpu(k2->refc.rc_startblock);
 }
 
@@ -285,7 +285,6 @@ const struct xfs_buf_ops xfs_refcountbt_buf_ops = {
 	.verify_write		= xfs_refcountbt_write_verify,
 };
 
-#if defined(DEBUG) || defined(XFS_WARN)
 STATIC int
 xfs_refcountbt_keys_inorder(
 	struct xfs_btree_cur	*cur,
@@ -306,7 +305,6 @@ xfs_refcountbt_recs_inorder(
 		be32_to_cpu(r1->refc.rc_blockcount) <=
 		be32_to_cpu(r2->refc.rc_startblock);
 }
-#endif
 
 static const struct xfs_btree_ops xfs_refcountbt_ops = {
 	.rec_len		= sizeof(struct xfs_refcount_rec),
@@ -325,10 +323,8 @@ static const struct xfs_btree_ops xfs_refcountbt_ops = {
 	.key_diff		= xfs_refcountbt_key_diff,
 	.buf_ops		= &xfs_refcountbt_buf_ops,
 	.diff_two_keys		= xfs_refcountbt_diff_two_keys,
-#if defined(DEBUG) || defined(XFS_WARN)
 	.keys_inorder		= xfs_refcountbt_keys_inorder,
 	.recs_inorder		= xfs_refcountbt_recs_inorder,
-#endif
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rmap.c b/fs/xfs/libxfs/xfs_rmap.c
index 3a8cc7139912..55c88a732690 100644
--- a/fs/xfs/libxfs/xfs_rmap.c
+++ b/fs/xfs/libxfs/xfs_rmap.c
@@ -179,7 +179,8 @@ done:
 	return error;
 }
 
-static int
+/* Convert an internal btree record to an rmap record. */
+int
 xfs_rmap_btrec_to_irec(
 	union xfs_btree_rec	*rec,
 	struct xfs_rmap_irec	*irec)
@@ -2001,14 +2002,14 @@ xfs_rmap_query_range_helper(
 /* Find all rmaps between two keys. */
 int
 xfs_rmap_query_range(
-	struct xfs_btree_cur		*cur,
-	struct xfs_rmap_irec		*low_rec,
-	struct xfs_rmap_irec		*high_rec,
-	xfs_rmap_query_range_fn	fn,
-	void				*priv)
+	struct xfs_btree_cur			*cur,
+	struct xfs_rmap_irec			*low_rec,
+	struct xfs_rmap_irec			*high_rec,
+	xfs_rmap_query_range_fn			fn,
+	void					*priv)
 {
-	union xfs_btree_irec		low_brec;
-	union xfs_btree_irec		high_brec;
+	union xfs_btree_irec			low_brec;
+	union xfs_btree_irec			high_brec;
 	struct xfs_rmap_query_range_info	query;
 
 	low_brec.r = *low_rec;
@@ -2019,6 +2020,20 @@ xfs_rmap_query_range(
 			xfs_rmap_query_range_helper, &query);
 }
 
+/* Find all rmaps. */
+int
+xfs_rmap_query_all(
+	struct xfs_btree_cur			*cur,
+	xfs_rmap_query_range_fn			fn,
+	void					*priv)
+{
+	struct xfs_rmap_query_range_info	query;
+
+	query.priv = priv;
+	query.fn = fn;
+	return xfs_btree_query_all(cur, xfs_rmap_query_range_helper, &query);
+}
+
 /* Clean up after calling xfs_rmap_finish_one. */
 void
 xfs_rmap_finish_one_cleanup(
@@ -2047,7 +2062,7 @@ int
 xfs_rmap_finish_one(
 	struct xfs_trans		*tp,
 	enum xfs_rmap_intent_type	type,
-	__uint64_t			owner,
+	uint64_t			owner,
 	int				whichfork,
 	xfs_fileoff_t			startoff,
 	xfs_fsblock_t			startblock,
@@ -2072,8 +2087,7 @@ xfs_rmap_finish_one(
 			startoff, blockcount, state);
 
 	if (XFS_TEST_ERROR(false, mp,
-			XFS_ERRTAG_RMAP_FINISH_ONE,
-			XFS_RANDOM_RMAP_FINISH_ONE))
+			XFS_ERRTAG_RMAP_FINISH_ONE))
 		return -EIO;
 
 	/*
@@ -2168,7 +2182,7 @@ __xfs_rmap_add(
 	struct xfs_mount		*mp,
 	struct xfs_defer_ops		*dfops,
 	enum xfs_rmap_intent_type	type,
-	__uint64_t			owner,
+	uint64_t			owner,
 	int				whichfork,
 	struct xfs_bmbt_irec		*bmap)
 {
@@ -2252,7 +2266,7 @@ xfs_rmap_alloc_extent(
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
-	__uint64_t		owner)
+	uint64_t		owner)
 {
 	struct xfs_bmbt_irec	bmap;
 
@@ -2276,7 +2290,7 @@ xfs_rmap_free_extent(
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		bno,
 	xfs_extlen_t		len,
-	__uint64_t		owner)
+	uint64_t		owner)
 {
 	struct xfs_bmbt_irec	bmap;
 
@@ -2291,3 +2305,31 @@ xfs_rmap_free_extent(
 	return __xfs_rmap_add(mp, dfops, XFS_RMAP_FREE, owner,
 			XFS_DATA_FORK, &bmap);
 }
+
+/* Compare rmap records.  Returns -1 if a < b, 1 if a > b, and 0 if equal. */
+int
+xfs_rmap_compare(
+	const struct xfs_rmap_irec	*a,
+	const struct xfs_rmap_irec	*b)
+{
+	__u64				oa;
+	__u64				ob;
+
+	oa = xfs_rmap_irec_offset_pack(a);
+	ob = xfs_rmap_irec_offset_pack(b);
+
+	if (a->rm_startblock < b->rm_startblock)
+		return -1;
+	else if (a->rm_startblock > b->rm_startblock)
+		return 1;
+	else if (a->rm_owner < b->rm_owner)
+		return -1;
+	else if (a->rm_owner > b->rm_owner)
+		return 1;
+	else if (oa < ob)
+		return -1;
+	else if (oa > ob)
+		return 1;
+	else
+		return 0;
+}
diff --git a/fs/xfs/libxfs/xfs_rmap.h b/fs/xfs/libxfs/xfs_rmap.h
index 789930599339..466ede637080 100644
--- a/fs/xfs/libxfs/xfs_rmap.h
+++ b/fs/xfs/libxfs/xfs_rmap.h
@@ -162,6 +162,8 @@ typedef int (*xfs_rmap_query_range_fn)(
 int xfs_rmap_query_range(struct xfs_btree_cur *cur,
 		struct xfs_rmap_irec *low_rec, struct xfs_rmap_irec *high_rec,
 		xfs_rmap_query_range_fn fn, void *priv);
+int xfs_rmap_query_all(struct xfs_btree_cur *cur, xfs_rmap_query_range_fn fn,
+		void *priv);
 
 enum xfs_rmap_intent_type {
 	XFS_RMAP_MAP,
@@ -177,7 +179,7 @@ enum xfs_rmap_intent_type {
 struct xfs_rmap_intent {
 	struct list_head			ri_list;
 	enum xfs_rmap_intent_type		ri_type;
-	__uint64_t				ri_owner;
+	uint64_t				ri_owner;
 	int					ri_whichfork;
 	struct xfs_bmbt_irec			ri_bmap;
 };
@@ -194,15 +196,15 @@ int xfs_rmap_convert_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
 		struct xfs_bmbt_irec *imap);
 int xfs_rmap_alloc_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
 		xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len,
-		__uint64_t owner);
+		uint64_t owner);
 int xfs_rmap_free_extent(struct xfs_mount *mp, struct xfs_defer_ops *dfops,
 		xfs_agnumber_t agno, xfs_agblock_t bno, xfs_extlen_t len,
-		__uint64_t owner);
+		uint64_t owner);
 
 void xfs_rmap_finish_one_cleanup(struct xfs_trans *tp,
 		struct xfs_btree_cur *rcur, int error);
 int xfs_rmap_finish_one(struct xfs_trans *tp, enum xfs_rmap_intent_type type,
-		__uint64_t owner, int whichfork, xfs_fileoff_t startoff,
+		uint64_t owner, int whichfork, xfs_fileoff_t startoff,
 		xfs_fsblock_t startblock, xfs_filblks_t blockcount,
 		xfs_exntst_t state, struct xfs_btree_cur **pcur);
 
@@ -212,5 +214,10 @@ int xfs_rmap_find_left_neighbor(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 int xfs_rmap_lookup_le_range(struct xfs_btree_cur *cur, xfs_agblock_t bno,
 		uint64_t owner, uint64_t offset, unsigned int flags,
 		struct xfs_rmap_irec *irec, int	*stat);
+int xfs_rmap_compare(const struct xfs_rmap_irec *a,
+		const struct xfs_rmap_irec *b);
+union xfs_btree_rec;
+int xfs_rmap_btrec_to_irec(union xfs_btree_rec *rec,
+		struct xfs_rmap_irec *irec);
 
 #endif	/* __XFS_RMAP_H__ */
diff --git a/fs/xfs/libxfs/xfs_rmap_btree.c b/fs/xfs/libxfs/xfs_rmap_btree.c
index 74e5a54bc428..9d9c9192584c 100644
--- a/fs/xfs/libxfs/xfs_rmap_btree.c
+++ b/fs/xfs/libxfs/xfs_rmap_btree.c
@@ -199,7 +199,7 @@ xfs_rmapbt_init_high_key_from_rec(
 	union xfs_btree_key	*key,
 	union xfs_btree_rec	*rec)
 {
-	__uint64_t		off;
+	uint64_t		off;
 	int			adj;
 
 	adj = be32_to_cpu(rec->rmap.rm_blockcount) - 1;
@@ -241,7 +241,7 @@ xfs_rmapbt_init_ptr_from_cur(
 	ptr->s = agf->agf_roots[cur->bc_btnum];
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_rmapbt_key_diff(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*key)
@@ -249,9 +249,9 @@ xfs_rmapbt_key_diff(
 	struct xfs_rmap_irec	*rec = &cur->bc_rec.r;
 	struct xfs_rmap_key	*kp = &key->rmap;
 	__u64			x, y;
-	__int64_t		d;
+	int64_t			d;
 
-	d = (__int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock;
+	d = (int64_t)be32_to_cpu(kp->rm_startblock) - rec->rm_startblock;
 	if (d)
 		return d;
 
@@ -271,7 +271,7 @@ xfs_rmapbt_key_diff(
 	return 0;
 }
 
-STATIC __int64_t
+STATIC int64_t
 xfs_rmapbt_diff_two_keys(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*k1,
@@ -279,10 +279,10 @@ xfs_rmapbt_diff_two_keys(
 {
 	struct xfs_rmap_key	*kp1 = &k1->rmap;
 	struct xfs_rmap_key	*kp2 = &k2->rmap;
-	__int64_t		d;
+	int64_t			d;
 	__u64			x, y;
 
-	d = (__int64_t)be32_to_cpu(kp1->rm_startblock) -
+	d = (int64_t)be32_to_cpu(kp1->rm_startblock) -
 		       be32_to_cpu(kp2->rm_startblock);
 	if (d)
 		return d;
@@ -377,17 +377,16 @@ const struct xfs_buf_ops xfs_rmapbt_buf_ops = {
 	.verify_write		= xfs_rmapbt_write_verify,
 };
 
-#if defined(DEBUG) || defined(XFS_WARN)
 STATIC int
 xfs_rmapbt_keys_inorder(
 	struct xfs_btree_cur	*cur,
 	union xfs_btree_key	*k1,
 	union xfs_btree_key	*k2)
 {
-	__uint32_t		x;
-	__uint32_t		y;
-	__uint64_t		a;
-	__uint64_t		b;
+	uint32_t		x;
+	uint32_t		y;
+	uint64_t		a;
+	uint64_t		b;
 
 	x = be32_to_cpu(k1->rmap.rm_startblock);
 	y = be32_to_cpu(k2->rmap.rm_startblock);
@@ -414,10 +413,10 @@ xfs_rmapbt_recs_inorder(
 	union xfs_btree_rec	*r1,
 	union xfs_btree_rec	*r2)
 {
-	__uint32_t		x;
-	__uint32_t		y;
-	__uint64_t		a;
-	__uint64_t		b;
+	uint32_t		x;
+	uint32_t		y;
+	uint64_t		a;
+	uint64_t		b;
 
 	x = be32_to_cpu(r1->rmap.rm_startblock);
 	y = be32_to_cpu(r2->rmap.rm_startblock);
@@ -437,7 +436,6 @@ xfs_rmapbt_recs_inorder(
 		return 1;
 	return 0;
 }
-#endif	/* DEBUG */
 
 static const struct xfs_btree_ops xfs_rmapbt_ops = {
 	.rec_len		= sizeof(struct xfs_rmap_rec),
@@ -456,10 +454,8 @@ static const struct xfs_btree_ops xfs_rmapbt_ops = {
 	.key_diff		= xfs_rmapbt_key_diff,
 	.buf_ops		= &xfs_rmapbt_buf_ops,
 	.diff_two_keys		= xfs_rmapbt_diff_two_keys,
-#if defined(DEBUG) || defined(XFS_WARN)
 	.keys_inorder		= xfs_rmapbt_keys_inorder,
 	.recs_inorder		= xfs_rmapbt_recs_inorder,
-#endif
 };
 
 /*
diff --git a/fs/xfs/libxfs/xfs_rtbitmap.c b/fs/xfs/libxfs/xfs_rtbitmap.c
index ea45584a9913..5d4e43ef4eea 100644
--- a/fs/xfs/libxfs/xfs_rtbitmap.c
+++ b/fs/xfs/libxfs/xfs_rtbitmap.c
@@ -70,7 +70,7 @@ const struct xfs_buf_ops xfs_rtbuf_ops = {
  * Get a buffer for the bitmap or summary file block specified.
  * The buffer is returned read and locked.
  */
-static int
+int
 xfs_rtbuf_get(
 	xfs_mount_t	*mp,		/* file system mount structure */
 	xfs_trans_t	*tp,		/* transaction pointer */
@@ -1011,8 +1011,78 @@ xfs_rtfree_extent(
 	    mp->m_sb.sb_rextents) {
 		if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM))
 			mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
-		*(__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0;
+		*(uint64_t *)&VFS_I(mp->m_rbmip)->i_atime = 0;
 		xfs_trans_log_inode(tp, mp->m_rbmip, XFS_ILOG_CORE);
 	}
 	return 0;
 }
+
+/* Find all the free records within a given range. */
+int
+xfs_rtalloc_query_range(
+	struct xfs_trans		*tp,
+	struct xfs_rtalloc_rec		*low_rec,
+	struct xfs_rtalloc_rec		*high_rec,
+	xfs_rtalloc_query_range_fn	fn,
+	void				*priv)
+{
+	struct xfs_rtalloc_rec		rec;
+	struct xfs_mount		*mp = tp->t_mountp;
+	xfs_rtblock_t			rtstart;
+	xfs_rtblock_t			rtend;
+	xfs_rtblock_t			rem;
+	int				is_free;
+	int				error = 0;
+
+	if (low_rec->ar_startblock > high_rec->ar_startblock)
+		return -EINVAL;
+	else if (low_rec->ar_startblock == high_rec->ar_startblock)
+		return 0;
+
+	/* Iterate the bitmap, looking for discrepancies. */
+	rtstart = low_rec->ar_startblock;
+	rem = high_rec->ar_startblock - rtstart;
+	while (rem) {
+		/* Is the first block free? */
+		error = xfs_rtcheck_range(mp, tp, rtstart, 1, 1, &rtend,
+				&is_free);
+		if (error)
+			break;
+
+		/* How long does the extent go for? */
+		error = xfs_rtfind_forw(mp, tp, rtstart,
+				high_rec->ar_startblock - 1, &rtend);
+		if (error)
+			break;
+
+		if (is_free) {
+			rec.ar_startblock = rtstart;
+			rec.ar_blockcount = rtend - rtstart + 1;
+
+			error = fn(tp, &rec, priv);
+			if (error)
+				break;
+		}
+
+		rem -= rtend - rtstart + 1;
+		rtstart = rtend + 1;
+	}
+
+	return error;
+}
+
+/* Find all the free records. */
+int
+xfs_rtalloc_query_all(
+	struct xfs_trans		*tp,
+	xfs_rtalloc_query_range_fn	fn,
+	void				*priv)
+{
+	struct xfs_rtalloc_rec		keys[2];
+
+	keys[0].ar_startblock = 0;
+	keys[1].ar_startblock = tp->t_mountp->m_sb.sb_rblocks;
+	keys[0].ar_blockcount = keys[1].ar_blockcount = 0;
+
+	return xfs_rtalloc_query_range(tp, &keys[0], &keys[1], fn, priv);
+}
diff --git a/fs/xfs/libxfs/xfs_sb.c b/fs/xfs/libxfs/xfs_sb.c
index 584ec896a533..9b5aae2bcc0b 100644
--- a/fs/xfs/libxfs/xfs_sb.c
+++ b/fs/xfs/libxfs/xfs_sb.c
@@ -448,7 +448,7 @@ xfs_sb_quota_to_disk(
 	struct xfs_dsb	*to,
 	struct xfs_sb	*from)
 {
-	__uint16_t	qflags = from->sb_qflags;
+	uint16_t	qflags = from->sb_qflags;
 
 	to->sb_uquotino = cpu_to_be64(from->sb_uquotino);
 	if (xfs_sb_version_has_pquotino(from)) {
@@ -756,7 +756,7 @@ xfs_sb_mount_common(
 	mp->m_refc_mnr[1] = mp->m_refc_mxr[1] / 2;
 
 	mp->m_bsize = XFS_FSB_TO_BB(mp, 1);
-	mp->m_ialloc_inos = (int)MAX((__uint16_t)XFS_INODES_PER_CHUNK,
+	mp->m_ialloc_inos = (int)MAX((uint16_t)XFS_INODES_PER_CHUNK,
 					sbp->sb_inopblock);
 	mp->m_ialloc_blks = mp->m_ialloc_inos >> sbp->sb_inopblog;
 
diff --git a/fs/xfs/libxfs/xfs_symlink_remote.c b/fs/xfs/libxfs/xfs_symlink_remote.c
index 2e2c6716b623..c484877129a0 100644
--- a/fs/xfs/libxfs/xfs_symlink_remote.c
+++ b/fs/xfs/libxfs/xfs_symlink_remote.c
@@ -114,7 +114,7 @@ xfs_symlink_verify(
 	if (bp->b_bn != be64_to_cpu(dsl->sl_blkno))
 		return false;
 	if (be32_to_cpu(dsl->sl_offset) +
-				be32_to_cpu(dsl->sl_bytes) >= MAXPATHLEN)
+				be32_to_cpu(dsl->sl_bytes) >= XFS_SYMLINK_MAXLEN)
 		return false;
 	if (dsl->sl_owner == 0)
 		return false;
diff --git a/fs/xfs/libxfs/xfs_trans_resv.c b/fs/xfs/libxfs/xfs_trans_resv.c
index b456cca1bfb2..6bd916bd35e2 100644
--- a/fs/xfs/libxfs/xfs_trans_resv.c
+++ b/fs/xfs/libxfs/xfs_trans_resv.c
@@ -477,14 +477,14 @@ xfs_calc_mkdir_reservation(
 /*
  * Making a new symplink is the same as creating a new file, but
  * with the added blocks for remote symlink data which can be up to 1kB in
- * length (MAXPATHLEN).
+ * length (XFS_SYMLINK_MAXLEN).
  */
 STATIC uint
 xfs_calc_symlink_reservation(
 	struct xfs_mount	*mp)
 {
 	return xfs_calc_create_reservation(mp) +
-	       xfs_calc_buf_res(1, MAXPATHLEN);
+	       xfs_calc_buf_res(1, XFS_SYMLINK_MAXLEN);
 }
 
 /*
diff --git a/fs/xfs/libxfs/xfs_trans_space.h b/fs/xfs/libxfs/xfs_trans_space.h
index 7917f6e44286..d787c677d2a3 100644
--- a/fs/xfs/libxfs/xfs_trans_space.h
+++ b/fs/xfs/libxfs/xfs_trans_space.h
@@ -21,8 +21,20 @@
 /*
  * Components of space reservations.
  */
+
+/* Worst case number of rmaps that can be held in a block. */
 #define XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)    \
 		(((mp)->m_rmap_mxr[0]) - ((mp)->m_rmap_mnr[0]))
+
+/* Adding one rmap could split every level up to the top of the tree. */
+#define XFS_RMAPADD_SPACE_RES(mp) ((mp)->m_rmap_maxlevels)
+
+/* Blocks we might need to add "b" rmaps to a tree. */
+#define XFS_NRMAPADD_SPACE_RES(mp, b)\
+	(((b + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) - 1) / \
+	  XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * \
+	  XFS_RMAPADD_SPACE_RES(mp))
+
 #define XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)    \
 		(((mp)->m_alloc_mxr[0]) - ((mp)->m_alloc_mnr[0]))
 #define	XFS_EXTENTADD_SPACE_RES(mp,w)	(XFS_BM_MAXLEVELS(mp,w) - 1)
@@ -30,13 +42,12 @@
 	(((b + XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp) - 1) / \
 	  XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)) * \
 	  XFS_EXTENTADD_SPACE_RES(mp,w))
+
+/* Blocks we might need to add "b" mappings & rmappings to a file. */
 #define XFS_SWAP_RMAP_SPACE_RES(mp,b,w)\
-	(((b + XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp) - 1) / \
-	  XFS_MAX_CONTIG_EXTENTS_PER_BLOCK(mp)) * \
-	  XFS_EXTENTADD_SPACE_RES(mp,w) + \
-	 ((b + XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp) - 1) / \
-	  XFS_MAX_CONTIG_RMAPS_PER_BLOCK(mp)) * \
-	  (mp)->m_rmap_maxlevels)
+	(XFS_NEXTENTADD_SPACE_RES((mp), (b), (w)) + \
+	 XFS_NRMAPADD_SPACE_RES((mp), (b)))
+
 #define	XFS_DAENTER_1B(mp,w)	\
 	((w) == XFS_DATA_FORK ? (mp)->m_dir_geo->fsbcount : 1)
 #define	XFS_DAENTER_DBS(mp,w)	\
diff --git a/fs/xfs/libxfs/xfs_types.h b/fs/xfs/libxfs/xfs_types.h
index 717909f2f7b7..0220159bd463 100644
--- a/fs/xfs/libxfs/xfs_types.h
+++ b/fs/xfs/libxfs/xfs_types.h
@@ -18,34 +18,34 @@
 #ifndef __XFS_TYPES_H__
 #define	__XFS_TYPES_H__
 
-typedef __uint32_t	prid_t;		/* project ID */
+typedef uint32_t	prid_t;		/* project ID */
 
-typedef __uint32_t	xfs_agblock_t;	/* blockno in alloc. group */
-typedef	__uint32_t	xfs_agino_t;	/* inode # within allocation grp */
-typedef	__uint32_t	xfs_extlen_t;	/* extent length in blocks */
-typedef	__uint32_t	xfs_agnumber_t;	/* allocation group number */
-typedef __int32_t	xfs_extnum_t;	/* # of extents in a file */
-typedef __int16_t	xfs_aextnum_t;	/* # extents in an attribute fork */
-typedef	__int64_t	xfs_fsize_t;	/* bytes in a file */
-typedef __uint64_t	xfs_ufsize_t;	/* unsigned bytes in a file */
+typedef uint32_t	xfs_agblock_t;	/* blockno in alloc. group */
+typedef uint32_t	xfs_agino_t;	/* inode # within allocation grp */
+typedef uint32_t	xfs_extlen_t;	/* extent length in blocks */
+typedef uint32_t	xfs_agnumber_t;	/* allocation group number */
+typedef int32_t		xfs_extnum_t;	/* # of extents in a file */
+typedef int16_t		xfs_aextnum_t;	/* # extents in an attribute fork */
+typedef int64_t		xfs_fsize_t;	/* bytes in a file */
+typedef uint64_t	xfs_ufsize_t;	/* unsigned bytes in a file */
 
-typedef	__int32_t	xfs_suminfo_t;	/* type of bitmap summary info */
-typedef	__int32_t	xfs_rtword_t;	/* word type for bitmap manipulations */
+typedef int32_t		xfs_suminfo_t;	/* type of bitmap summary info */
+typedef int32_t		xfs_rtword_t;	/* word type for bitmap manipulations */
 
-typedef	__int64_t	xfs_lsn_t;	/* log sequence number */
-typedef	__int32_t	xfs_tid_t;	/* transaction identifier */
+typedef int64_t		xfs_lsn_t;	/* log sequence number */
+typedef int32_t		xfs_tid_t;	/* transaction identifier */
 
-typedef	__uint32_t	xfs_dablk_t;	/* dir/attr block number (in file) */
-typedef	__uint32_t	xfs_dahash_t;	/* dir/attr hash value */
+typedef uint32_t	xfs_dablk_t;	/* dir/attr block number (in file) */
+typedef uint32_t	xfs_dahash_t;	/* dir/attr hash value */
 
-typedef	__uint64_t	xfs_fsblock_t;	/* blockno in filesystem (agno|agbno) */
-typedef __uint64_t	xfs_rfsblock_t;	/* blockno in filesystem (raw) */
-typedef __uint64_t	xfs_rtblock_t;	/* extent (block) in realtime area */
-typedef __uint64_t	xfs_fileoff_t;	/* block number in a file */
-typedef __uint64_t	xfs_filblks_t;	/* number of blocks in a file */
+typedef uint64_t	xfs_fsblock_t;	/* blockno in filesystem (agno|agbno) */
+typedef uint64_t	xfs_rfsblock_t;	/* blockno in filesystem (raw) */
+typedef uint64_t	xfs_rtblock_t;	/* extent (block) in realtime area */
+typedef uint64_t	xfs_fileoff_t;	/* block number in a file */
+typedef uint64_t	xfs_filblks_t;	/* number of blocks in a file */
 
-typedef	__int64_t	xfs_srtblock_t;	/* signed version of xfs_rtblock_t */
-typedef __int64_t	xfs_sfiloff_t;	/* signed block number in a file */
+typedef int64_t		xfs_srtblock_t;	/* signed version of xfs_rtblock_t */
+typedef int64_t		xfs_sfiloff_t;	/* signed block number in a file */
 
 /*
  * Null values for the types.
@@ -125,7 +125,7 @@ struct xfs_name {
  * uid_t and gid_t are hard-coded to 32 bits in the inode.
  * Hence, an 'id' in a dquot is 32 bits..
  */
-typedef __uint32_t	xfs_dqid_t;
+typedef uint32_t	xfs_dqid_t;
 
 /*
  * Constants for bit manipulations.
diff --git a/fs/xfs/uuid.c b/fs/xfs/uuid.c
deleted file mode 100644
index b83f76b6d410..000000000000
--- a/fs/xfs/uuid.c
+++ /dev/null
@@ -1,63 +0,0 @@
-/*
- * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#include <xfs.h>
-
-/* IRIX interpretation of an uuid_t */
-typedef struct {
-	__be32	uu_timelow;
-	__be16	uu_timemid;
-	__be16	uu_timehi;
-	__be16	uu_clockseq;
-	__be16	uu_node[3];
-} xfs_uu_t;
-
-/*
- * uuid_getnodeuniq - obtain the node unique fields of a UUID.
- *
- * This is not in any way a standard or condoned UUID function;
- * it just something that's needed for user-level file handles.
- */
-void
-uuid_getnodeuniq(uuid_t *uuid, int fsid [2])
-{
-	xfs_uu_t *uup = (xfs_uu_t *)uuid;
-
-	fsid[0] = (be16_to_cpu(uup->uu_clockseq) << 16) |
-		   be16_to_cpu(uup->uu_timemid);
-	fsid[1] = be32_to_cpu(uup->uu_timelow);
-}
-
-int
-uuid_is_nil(uuid_t *uuid)
-{
-	int	i;
-	char	*cp = (char *)uuid;
-
-	if (uuid == NULL)
-		return 0;
-	/* implied check of version number here... */
-	for (i = 0; i < sizeof *uuid; i++)
-		if (*cp++) return 0;	/* not nil */
-	return 1;	/* is nil */
-}
-
-int
-uuid_equal(uuid_t *uuid1, uuid_t *uuid2)
-{
-	return memcmp(uuid1, uuid2, sizeof(uuid_t)) ? 0 : 1;
-}
diff --git a/fs/xfs/uuid.h b/fs/xfs/uuid.h
deleted file mode 100644
index 104db0f3bed6..000000000000
--- a/fs/xfs/uuid.h
+++ /dev/null
@@ -1,35 +0,0 @@
-/*
- * Copyright (c) 2000-2003,2005 Silicon Graphics, Inc.
- * All Rights Reserved.
- *
- * This program is free software; you can redistribute it and/or
- * modify it under the terms of the GNU General Public License as
- * published by the Free Software Foundation.
- *
- * This program is distributed in the hope that it would be useful,
- * but WITHOUT ANY WARRANTY; without even the implied warranty of
- * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
- * GNU General Public License for more details.
- *
- * You should have received a copy of the GNU General Public License
- * along with this program; if not, write the Free Software Foundation,
- * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301  USA
- */
-#ifndef __XFS_SUPPORT_UUID_H__
-#define __XFS_SUPPORT_UUID_H__
-
-typedef struct {
-	unsigned char	__u_bits[16];
-} uuid_t;
-
-extern int uuid_is_nil(uuid_t *uuid);
-extern int uuid_equal(uuid_t *uuid1, uuid_t *uuid2);
-extern void uuid_getnodeuniq(uuid_t *uuid, int fsid [2]);
-
-static inline void
-uuid_copy(uuid_t *dst, uuid_t *src)
-{
-	memcpy(dst, src, sizeof(uuid_t));
-}
-
-#endif	/* __XFS_SUPPORT_UUID_H__ */
diff --git a/fs/xfs/xfs.h b/fs/xfs/xfs.h
index a742c47f7d5a..80cd0fd86783 100644
--- a/fs/xfs/xfs.h
+++ b/fs/xfs/xfs.h
@@ -24,6 +24,10 @@
 #define XFS_BUF_LOCK_TRACKING 1
 #endif
 
+#ifdef CONFIG_XFS_ASSERT_FATAL
+#define XFS_ASSERT_FATAL 1
+#endif
+
 #ifdef CONFIG_XFS_WARN
 #define XFS_WARN 1
 #endif
diff --git a/fs/xfs/xfs_acl.c b/fs/xfs/xfs_acl.c
index b468e041f207..7034e17535de 100644
--- a/fs/xfs/xfs_acl.c
+++ b/fs/xfs/xfs_acl.c
@@ -170,8 +170,8 @@ xfs_get_acl(struct inode *inode, int type)
 	return acl;
 }
 
-STATIC int
-__xfs_set_acl(struct inode *inode, int type, struct posix_acl *acl)
+int
+__xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 {
 	struct xfs_inode *ip = XFS_I(inode);
 	unsigned char *ea_name;
@@ -268,5 +268,5 @@ xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type)
 	}
 
  set_acl:
-	return __xfs_set_acl(inode, type, acl);
+	return __xfs_set_acl(inode, acl, type);
 }
diff --git a/fs/xfs/xfs_acl.h b/fs/xfs/xfs_acl.h
index 286fa89217f5..04327318ef67 100644
--- a/fs/xfs/xfs_acl.h
+++ b/fs/xfs/xfs_acl.h
@@ -24,6 +24,7 @@ struct posix_acl;
 #ifdef CONFIG_XFS_POSIX_ACL
 extern struct posix_acl *xfs_get_acl(struct inode *inode, int type);
 extern int xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
+extern int __xfs_set_acl(struct inode *inode, struct posix_acl *acl, int type);
 #else
 static inline struct posix_acl *xfs_get_acl(struct inode *inode, int type)
 {
diff --git a/fs/xfs/xfs_aops.c b/fs/xfs/xfs_aops.c
index 631e7c0e0a29..6bf120bb1a17 100644
--- a/fs/xfs/xfs_aops.c
+++ b/fs/xfs/xfs_aops.c
@@ -103,19 +103,19 @@ xfs_finish_page_writeback(
 	unsigned int		bsize;
 
 	ASSERT(bvec->bv_offset < PAGE_SIZE);
-	ASSERT((bvec->bv_offset & ((1 << inode->i_blkbits) - 1)) == 0);
+	ASSERT((bvec->bv_offset & (i_blocksize(inode) - 1)) == 0);
 	ASSERT(end < PAGE_SIZE);
-	ASSERT((bvec->bv_len & ((1 << inode->i_blkbits) - 1)) == 0);
+	ASSERT((bvec->bv_len & (i_blocksize(inode) - 1)) == 0);
 
 	bh = head = page_buffers(bvec->bv_page);
 
 	bsize = bh->b_size;
 	do {
+		if (off > end)
+			break;
 		next = bh->b_this_page;
 		if (off < bvec->bv_offset)
 			goto next_bh;
-		if (off > end)
-			break;
 		bh->b_end_io(bh, !error);
 next_bh:
 		off += bsize;
@@ -189,7 +189,7 @@ xfs_setfilesize_trans_alloc(
 	 * We hand off the transaction to the completion thread now, so
 	 * clear the flag here.
 	 */
-	current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	return 0;
 }
 
@@ -252,7 +252,7 @@ xfs_setfilesize_ioend(
 	 * thus we need to mark ourselves as being in a transaction manually.
 	 * Similarly for freeze protection.
 	 */
-	current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
+	current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	__sb_writers_acquired(VFS_I(ip)->i_sb, SB_FREEZE_FS);
 
 	/* we abort the update if there was an IO error */
@@ -274,54 +274,50 @@ xfs_end_io(
 	struct xfs_ioend	*ioend =
 		container_of(work, struct xfs_ioend, io_work);
 	struct xfs_inode	*ip = XFS_I(ioend->io_inode);
-	int			error = ioend->io_bio->bi_error;
+	xfs_off_t		offset = ioend->io_offset;
+	size_t			size = ioend->io_size;
+	int			error;
 
 	/*
-	 * Set an error if the mount has shut down and proceed with end I/O
-	 * processing so it can perform whatever cleanups are necessary.
+	 * Just clean up the in-memory strutures if the fs has been shut down.
 	 */
-	if (XFS_FORCED_SHUTDOWN(ip->i_mount))
+	if (XFS_FORCED_SHUTDOWN(ip->i_mount)) {
 		error = -EIO;
+		goto done;
+	}
 
 	/*
-	 * For a CoW extent, we need to move the mapping from the CoW fork
-	 * to the data fork.  If instead an error happened, just dump the
-	 * new blocks.
+	 * Clean up any COW blocks on an I/O error.
 	 */
-	if (ioend->io_type == XFS_IO_COW) {
-		if (error)
-			goto done;
-		if (ioend->io_bio->bi_error) {
-			error = xfs_reflink_cancel_cow_range(ip,
-					ioend->io_offset, ioend->io_size);
-			goto done;
+	error = blk_status_to_errno(ioend->io_bio->bi_status);
+	if (unlikely(error)) {
+		switch (ioend->io_type) {
+		case XFS_IO_COW:
+			xfs_reflink_cancel_cow_range(ip, offset, size, true);
+			break;
 		}
-		error = xfs_reflink_end_cow(ip, ioend->io_offset,
-				ioend->io_size);
-		if (error)
-			goto done;
+
+		goto done;
 	}
 
 	/*
-	 * For unwritten extents we need to issue transactions to convert a
-	 * range to normal written extens after the data I/O has finished.
-	 * Detecting and handling completion IO errors is done individually
-	 * for each case as different cleanup operations need to be performed
-	 * on error.
+	 * Success:  commit the COW or unwritten blocks if needed.
 	 */
-	if (ioend->io_type == XFS_IO_UNWRITTEN) {
-		if (error)
-			goto done;
-		error = xfs_iomap_write_unwritten(ip, ioend->io_offset,
-						  ioend->io_size);
-	} else if (ioend->io_append_trans) {
-		error = xfs_setfilesize_ioend(ioend, error);
-	} else {
-		ASSERT(!xfs_ioend_is_append(ioend) ||
-		       ioend->io_type == XFS_IO_COW);
+	switch (ioend->io_type) {
+	case XFS_IO_COW:
+		error = xfs_reflink_end_cow(ip, offset, size);
+		break;
+	case XFS_IO_UNWRITTEN:
+		error = xfs_iomap_write_unwritten(ip, offset, size);
+		break;
+	default:
+		ASSERT(!xfs_ioend_is_append(ioend) || ioend->io_append_trans);
+		break;
 	}
 
 done:
+	if (ioend->io_append_trans)
+		error = xfs_setfilesize_ioend(ioend, error);
 	xfs_destroy_ioend(ioend, error);
 }
 
@@ -337,7 +333,7 @@ xfs_end_bio(
 	else if (ioend->io_append_trans)
 		queue_work(mp->m_data_workqueue, &ioend->io_work);
 	else
-		xfs_destroy_ioend(ioend, bio->bi_error);
+		xfs_destroy_ioend(ioend, blk_status_to_errno(bio->bi_status));
 }
 
 STATIC int
@@ -349,7 +345,7 @@ xfs_map_blocks(
 {
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
-	ssize_t			count = 1 << inode->i_blkbits;
+	ssize_t			count = i_blocksize(inode);
 	xfs_fileoff_t		offset_fsb, end_fsb;
 	int			error = 0;
 	int			bmapi_flags = XFS_BMAPI_ENTIRE;
@@ -481,6 +477,12 @@ xfs_submit_ioend(
 	struct xfs_ioend	*ioend,
 	int			status)
 {
+	/* Convert CoW extents to regular */
+	if (!status && ioend->io_type == XFS_IO_COW) {
+		status = xfs_reflink_convert_cow(XFS_I(ioend->io_inode),
+				ioend->io_offset, ioend->io_size);
+	}
+
 	/* Reserve log space if we might write beyond the on-disk inode size. */
 	if (!status &&
 	    ioend->io_type != XFS_IO_UNWRITTEN &&
@@ -499,11 +501,12 @@ xfs_submit_ioend(
 	 * time.
 	 */
 	if (status) {
-		ioend->io_bio->bi_error = status;
+		ioend->io_bio->bi_status = errno_to_blk_status(status);
 		bio_endio(ioend->io_bio);
 		return status;
 	}
 
+	ioend->io_bio->bi_write_hint = ioend->io_inode->i_write_hint;
 	submit_bio(ioend->io_bio);
 	return 0;
 }
@@ -563,6 +566,7 @@ xfs_chain_bio(
 	bio_chain(ioend->io_bio, new);
 	bio_get(ioend->io_bio);		/* for xfs_destroy_ioend */
 	ioend->io_bio->bi_opf = REQ_OP_WRITE | wbc_to_write_flags(wbc);
+	ioend->io_bio->bi_write_hint = ioend->io_inode->i_write_hint;
 	submit_bio(ioend->io_bio);
 	ioend->io_bio = new;
 }
@@ -752,7 +756,7 @@ xfs_aops_discard_page(
 			break;
 		}
 next_buffer:
-		offset += 1 << inode->i_blkbits;
+		offset += i_blocksize(inode);
 
 	} while ((bh = bh->b_this_page) != head);
 
@@ -835,12 +839,12 @@ xfs_writepage_map(
 	struct inode		*inode,
 	struct page		*page,
 	loff_t			offset,
-	__uint64_t              end_offset)
+	uint64_t              end_offset)
 {
 	LIST_HEAD(submit_list);
 	struct xfs_ioend	*ioend, *next;
 	struct buffer_head	*bh, *head;
-	ssize_t			len = 1 << inode->i_blkbits;
+	ssize_t			len = i_blocksize(inode);
 	int			error = 0;
 	int			count = 0;
 	int			uptodate = 1;
@@ -990,7 +994,7 @@ xfs_do_writepage(
 	struct xfs_writepage_ctx *wpc = data;
 	struct inode		*inode = page->mapping->host;
 	loff_t			offset;
-	__uint64_t              end_offset;
+	uint64_t              end_offset;
 	pgoff_t                 end_index;
 
 	trace_xfs_writepage(inode, page, 0, 0);
@@ -1015,7 +1019,7 @@ xfs_do_writepage(
 	 * Given that we do not allow direct reclaim to call us, we should
 	 * never be called while in a filesystem transaction.
 	 */
-	if (WARN_ON_ONCE(current->flags & PF_FSTRANS))
+	if (WARN_ON_ONCE(current->flags & PF_MEMALLOC_NOFS))
 		goto redirty;
 
 	/*
@@ -1204,7 +1208,7 @@ xfs_map_trim_size(
 	    offset + mapping_size >= i_size_read(inode)) {
 		/* limit mapping to block that spans EOF */
 		mapping_size = roundup_64(i_size_read(inode) - offset,
-					  1 << inode->i_blkbits);
+					  i_blocksize(inode));
 	}
 	if (mapping_size > LONG_MAX)
 		mapping_size = LONG_MAX;
@@ -1235,7 +1239,7 @@ xfs_get_blocks(
 		return -EIO;
 
 	offset = (xfs_off_t)iblock << inode->i_blkbits;
-	ASSERT(bh_result->b_size >= (1 << inode->i_blkbits));
+	ASSERT(bh_result->b_size >= i_blocksize(inode));
 	size = bh_result->b_size;
 
 	if (offset >= i_size_read(inode))
@@ -1260,8 +1264,8 @@ xfs_get_blocks(
 
 	if (nimaps) {
 		trace_xfs_get_blocks_found(ip, offset, size,
-				ISUNWRITTEN(&imap) ? XFS_IO_UNWRITTEN
-						   : XFS_IO_OVERWRITE, &imap);
+			imap.br_state == XFS_EXT_UNWRITTEN ?
+				XFS_IO_UNWRITTEN : XFS_IO_OVERWRITE, &imap);
 		xfs_iunlock(ip, lockmode);
 	} else {
 		trace_xfs_get_blocks_notfound(ip, offset, size);
@@ -1275,9 +1279,7 @@ xfs_get_blocks(
 	 * For unwritten extents do not report a disk address in the buffered
 	 * read case (treat as if we're reading into a hole).
 	 */
-	if (imap.br_startblock != HOLESTARTBLOCK &&
-	    imap.br_startblock != DELAYSTARTBLOCK &&
-	    !ISUNWRITTEN(&imap))
+	if (xfs_bmap_is_real_extent(&imap))
 		xfs_map_buffer(inode, bh_result, &imap, offset);
 
 	/*
@@ -1317,9 +1319,12 @@ xfs_vm_bmap(
 	 * The swap code (ab-)uses ->bmap to get a block mapping and then
 	 * bypasseѕ the file system for actual I/O.  We really can't allow
 	 * that on reflinks inodes, so we have to skip out here.  And yes,
-	 * 0 is the magic code for a bmap error..
+	 * 0 is the magic code for a bmap error.
+	 *
+	 * Since we don't pass back blockdev info, we can't return bmap
+	 * information for rt files either.
 	 */
-	if (xfs_is_reflink_inode(ip))
+	if (xfs_is_reflink_inode(ip) || XFS_IS_REALTIME_INODE(ip))
 		return 0;
 
 	filemap_write_and_wait(mapping);
@@ -1383,7 +1388,7 @@ xfs_vm_set_page_dirty(
 			if (offset < end_offset)
 				set_buffer_dirty(bh);
 			bh = bh->b_this_page;
-			offset += 1 << inode->i_blkbits;
+			offset += i_blocksize(inode);
 		} while (bh != head);
 	}
 	/*
diff --git a/fs/xfs/xfs_attr.h b/fs/xfs/xfs_attr.h
index d14691aa02b4..5d5a5e277f35 100644
--- a/fs/xfs/xfs_attr.h
+++ b/fs/xfs/xfs_attr.h
@@ -117,6 +117,7 @@ typedef void (*put_listent_func_t)(struct xfs_attr_list_context *, int,
 			      unsigned char *, int, int);
 
 typedef struct xfs_attr_list_context {
+	struct xfs_trans		*tp;
 	struct xfs_inode		*dp;		/* inode */
 	struct attrlist_cursor_kern	*cursor;	/* position in list */
 	char				*alist;		/* output buffer */
@@ -140,8 +141,10 @@ typedef struct xfs_attr_list_context {
  * Overall external interface routines.
  */
 int xfs_attr_inactive(struct xfs_inode *dp);
+int xfs_attr_list_int_ilocked(struct xfs_attr_list_context *);
 int xfs_attr_list_int(struct xfs_attr_list_context *);
 int xfs_inode_hasattr(struct xfs_inode *ip);
+int xfs_attr_get_ilocked(struct xfs_inode *ip, struct xfs_da_args *args);
 int xfs_attr_get(struct xfs_inode *ip, const unsigned char *name,
 		 unsigned char *value, int *valuelenp, int flags);
 int xfs_attr_set(struct xfs_inode *dp, const unsigned char *name,
diff --git a/fs/xfs/xfs_attr_list.c b/fs/xfs/xfs_attr_list.c
index 97c45b6eb91e..7740c8a5e736 100644
--- a/fs/xfs/xfs_attr_list.c
+++ b/fs/xfs/xfs_attr_list.c
@@ -230,7 +230,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	 */
 	bp = NULL;
 	if (cursor->blkno > 0) {
-		error = xfs_da3_node_read(NULL, dp, cursor->blkno, -1,
+		error = xfs_da3_node_read(context->tp, dp, cursor->blkno, -1,
 					      &bp, XFS_ATTR_FORK);
 		if ((error != 0) && (error != -EFSCORRUPTED))
 			return error;
@@ -242,7 +242,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 			case XFS_DA_NODE_MAGIC:
 			case XFS_DA3_NODE_MAGIC:
 				trace_xfs_attr_list_wrong_blk(context);
-				xfs_trans_brelse(NULL, bp);
+				xfs_trans_brelse(context->tp, bp);
 				bp = NULL;
 				break;
 			case XFS_ATTR_LEAF_MAGIC:
@@ -254,18 +254,18 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 				if (cursor->hashval > be32_to_cpu(
 						entries[leafhdr.count - 1].hashval)) {
 					trace_xfs_attr_list_wrong_blk(context);
-					xfs_trans_brelse(NULL, bp);
+					xfs_trans_brelse(context->tp, bp);
 					bp = NULL;
 				} else if (cursor->hashval <= be32_to_cpu(
 						entries[0].hashval)) {
 					trace_xfs_attr_list_wrong_blk(context);
-					xfs_trans_brelse(NULL, bp);
+					xfs_trans_brelse(context->tp, bp);
 					bp = NULL;
 				}
 				break;
 			default:
 				trace_xfs_attr_list_wrong_blk(context);
-				xfs_trans_brelse(NULL, bp);
+				xfs_trans_brelse(context->tp, bp);
 				bp = NULL;
 			}
 		}
@@ -279,9 +279,9 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 	if (bp == NULL) {
 		cursor->blkno = 0;
 		for (;;) {
-			__uint16_t magic;
+			uint16_t magic;
 
-			error = xfs_da3_node_read(NULL, dp,
+			error = xfs_da3_node_read(context->tp, dp,
 						      cursor->blkno, -1, &bp,
 						      XFS_ATTR_FORK);
 			if (error)
@@ -297,7 +297,7 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 						     XFS_ERRLEVEL_LOW,
 						     context->dp->i_mount,
 						     node);
-				xfs_trans_brelse(NULL, bp);
+				xfs_trans_brelse(context->tp, bp);
 				return -EFSCORRUPTED;
 			}
 
@@ -313,10 +313,10 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 				}
 			}
 			if (i == nodehdr.count) {
-				xfs_trans_brelse(NULL, bp);
+				xfs_trans_brelse(context->tp, bp);
 				return 0;
 			}
-			xfs_trans_brelse(NULL, bp);
+			xfs_trans_brelse(context->tp, bp);
 		}
 	}
 	ASSERT(bp != NULL);
@@ -333,12 +333,12 @@ xfs_attr_node_list(xfs_attr_list_context_t *context)
 		if (context->seen_enough || leafhdr.forw == 0)
 			break;
 		cursor->blkno = leafhdr.forw;
-		xfs_trans_brelse(NULL, bp);
-		error = xfs_attr3_leaf_read(NULL, dp, cursor->blkno, -1, &bp);
+		xfs_trans_brelse(context->tp, bp);
+		error = xfs_attr3_leaf_read(context->tp, dp, cursor->blkno, -1, &bp);
 		if (error)
 			return error;
 	}
-	xfs_trans_brelse(NULL, bp);
+	xfs_trans_brelse(context->tp, bp);
 	return 0;
 }
 
@@ -448,16 +448,36 @@ xfs_attr_leaf_list(xfs_attr_list_context_t *context)
 	trace_xfs_attr_leaf_list(context);
 
 	context->cursor->blkno = 0;
-	error = xfs_attr3_leaf_read(NULL, context->dp, 0, -1, &bp);
+	error = xfs_attr3_leaf_read(context->tp, context->dp, 0, -1, &bp);
 	if (error)
 		return error;
 
 	xfs_attr3_leaf_list_int(bp, context);
-	xfs_trans_brelse(NULL, bp);
+	xfs_trans_brelse(context->tp, bp);
 	return 0;
 }
 
 int
+xfs_attr_list_int_ilocked(
+	struct xfs_attr_list_context	*context)
+{
+	struct xfs_inode		*dp = context->dp;
+
+	ASSERT(xfs_isilocked(dp, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
+
+	/*
+	 * Decide on what work routines to call based on the inode size.
+	 */
+	if (!xfs_inode_hasattr(dp))
+		return 0;
+	else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL)
+		return xfs_attr_shortform_list(context);
+	else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK))
+		return xfs_attr_leaf_list(context);
+	return xfs_attr_node_list(context);
+}
+
+int
 xfs_attr_list_int(
 	xfs_attr_list_context_t *context)
 {
@@ -470,19 +490,8 @@ xfs_attr_list_int(
 	if (XFS_FORCED_SHUTDOWN(dp->i_mount))
 		return -EIO;
 
-	/*
-	 * Decide on what work routines to call based on the inode size.
-	 */
 	lock_mode = xfs_ilock_attr_map_shared(dp);
-	if (!xfs_inode_hasattr(dp)) {
-		error = 0;
-	} else if (dp->i_d.di_aformat == XFS_DINODE_FMT_LOCAL) {
-		error = xfs_attr_shortform_list(context);
-	} else if (xfs_bmap_one_block(dp, XFS_ATTR_FORK)) {
-		error = xfs_attr_leaf_list(context);
-	} else {
-		error = xfs_attr_node_list(context);
-	}
+	error = xfs_attr_list_int_ilocked(context);
 	xfs_iunlock(dp, lock_mode);
 	return error;
 }
diff --git a/fs/xfs/xfs_bmap_item.c b/fs/xfs/xfs_bmap_item.c
index 9bf57c76623b..88073910fa5d 100644
--- a/fs/xfs/xfs_bmap_item.c
+++ b/fs/xfs/xfs_bmap_item.c
@@ -34,6 +34,8 @@
 #include "xfs_bmap.h"
 #include "xfs_icache.h"
 #include "xfs_trace.h"
+#include "xfs_bmap_btree.h"
+#include "xfs_trans_space.h"
 
 
 kmem_zone_t	*xfs_bui_zone;
@@ -215,6 +217,7 @@ void
 xfs_bui_release(
 	struct xfs_bui_log_item	*buip)
 {
+	ASSERT(atomic_read(&buip->bui_refcount) > 0);
 	if (atomic_dec_and_test(&buip->bui_refcount)) {
 		xfs_trans_ail_remove(&buip->bui_item, SHUTDOWN_LOG_IO_ERROR);
 		xfs_bui_item_free(buip);
@@ -393,6 +396,7 @@ xfs_bui_recover(
 	struct xfs_map_extent		*bmap;
 	xfs_fsblock_t			startblock_fsb;
 	xfs_fsblock_t			inode_fsb;
+	xfs_filblks_t			count;
 	bool				op_ok;
 	struct xfs_bud_log_item		*budp;
 	enum xfs_bmap_intent_type	type;
@@ -401,6 +405,7 @@ xfs_bui_recover(
 	struct xfs_trans		*tp;
 	struct xfs_inode		*ip = NULL;
 	struct xfs_defer_ops		dfops;
+	struct xfs_bmbt_irec		irec;
 	xfs_fsblock_t			firstfsb;
 
 	ASSERT(!test_bit(XFS_BUI_RECOVERED, &buip->bui_flags));
@@ -446,7 +451,8 @@ xfs_bui_recover(
 		return -EIO;
 	}
 
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0, &tp);
+	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate,
+			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK), 0, 0, &tp);
 	if (error)
 		return error;
 	budp = xfs_trans_get_bud(tp, buip);
@@ -477,13 +483,24 @@ xfs_bui_recover(
 	}
 	xfs_trans_ijoin(tp, ip, 0);
 
+	count = bmap->me_len;
 	error = xfs_trans_log_finish_bmap_update(tp, budp, &dfops, type,
 			ip, whichfork, bmap->me_startoff,
-			bmap->me_startblock, bmap->me_len,
-			state);
+			bmap->me_startblock, &count, state);
 	if (error)
 		goto err_dfops;
 
+	if (count > 0) {
+		ASSERT(type == XFS_BMAP_UNMAP);
+		irec.br_startblock = bmap->me_startblock;
+		irec.br_blockcount = count;
+		irec.br_startoff = bmap->me_startoff;
+		irec.br_state = state;
+		error = xfs_bmap_unmap_extent(tp->t_mountp, &dfops, ip, &irec);
+		if (error)
+			goto err_dfops;
+	}
+
 	/* Finish transaction, free inodes. */
 	error = xfs_defer_finish(&tp, &dfops, NULL);
 	if (error)
diff --git a/fs/xfs/xfs_bmap_util.c b/fs/xfs/xfs_bmap_util.c
index c1417919ab0a..93e955262d07 100644
--- a/fs/xfs/xfs_bmap_util.c
+++ b/fs/xfs/xfs_bmap_util.c
@@ -81,14 +81,13 @@ xfs_zero_extent(
 	return blkdev_issue_zeroout(xfs_find_bdev_for_inode(VFS_I(ip)),
 		block << (mp->m_super->s_blocksize_bits - 9),
 		count_fsb << (mp->m_super->s_blocksize_bits - 9),
-		GFP_NOFS, true);
+		GFP_NOFS, 0);
 }
 
 int
 xfs_bmap_rtalloc(
 	struct xfs_bmalloca	*ap)	/* bmap alloc argument struct */
 {
-	xfs_alloctype_t	atype = 0;	/* type for allocation routines */
 	int		error;		/* error return value */
 	xfs_mount_t	*mp;		/* mount point structure */
 	xfs_extlen_t	prod = 0;	/* product factor for allocators */
@@ -155,18 +154,14 @@ xfs_bmap_rtalloc(
 	/*
 	 * Realtime allocation, done through xfs_rtallocate_extent.
 	 */
-	atype = ap->blkno == 0 ?  XFS_ALLOCTYPE_ANY_AG : XFS_ALLOCTYPE_NEAR_BNO;
 	do_div(ap->blkno, mp->m_sb.sb_rextsize);
 	rtb = ap->blkno;
 	ap->length = ralen;
-	if ((error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length,
-				&ralen, atype, ap->wasdel, prod, &rtb)))
-		return error;
-	if (rtb == NULLFSBLOCK && prod > 1 &&
-	    (error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1,
-					   ap->length, &ralen, atype,
-					   ap->wasdel, 1, &rtb)))
+	error = xfs_rtallocate_extent(ap->tp, ap->blkno, 1, ap->length,
+				&ralen, ap->wasdel, prod, &rtb);
+	if (error)
 		return error;
+
 	ap->blkno = rtb;
 	if (ap->blkno != NULLFSBLOCK) {
 		ap->blkno *= mp->m_sb.sb_rextsize;
@@ -224,20 +219,24 @@ xfs_bmap_eof(
  */
 
 /*
- * Count leaf blocks given a range of extent records.
+ * Count leaf blocks given a range of extent records.  Delayed allocation
+ * extents are not counted towards the totals.
  */
 STATIC void
 xfs_bmap_count_leaves(
-	xfs_ifork_t		*ifp,
-	xfs_extnum_t		idx,
-	int			numrecs,
-	int			*count)
+	struct xfs_ifork	*ifp,
+	xfs_extnum_t		*numrecs,
+	xfs_filblks_t		*count)
 {
-	int		b;
-
-	for (b = 0; b < numrecs; b++) {
-		xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, idx + b);
-		*count += xfs_bmbt_get_blockcount(frp);
+	xfs_extnum_t		i;
+	xfs_extnum_t		nr_exts = xfs_iext_count(ifp);
+
+	for (i = 0; i < nr_exts; i++) {
+		xfs_bmbt_rec_host_t *frp = xfs_iext_get_ext(ifp, i);
+		if (!isnullstartblock(xfs_bmbt_get_startblock(frp))) {
+			(*numrecs)++;
+			*count += xfs_bmbt_get_blockcount(frp);
+		}
 	}
 }
 
@@ -250,7 +249,7 @@ xfs_bmap_disk_count_leaves(
 	struct xfs_mount	*mp,
 	struct xfs_btree_block	*block,
 	int			numrecs,
-	int			*count)
+	xfs_filblks_t		*count)
 {
 	int		b;
 	xfs_bmbt_rec_t	*frp;
@@ -265,17 +264,18 @@ xfs_bmap_disk_count_leaves(
  * Recursively walks each level of a btree
  * to count total fsblocks in use.
  */
-STATIC int                                     /* error */
+STATIC int
 xfs_bmap_count_tree(
-	xfs_mount_t     *mp,            /* file system mount point */
-	xfs_trans_t     *tp,            /* transaction pointer */
-	xfs_ifork_t	*ifp,		/* inode fork pointer */
-	xfs_fsblock_t   blockno,	/* file system block number */
-	int             levelin,	/* level in btree */
-	int		*count)		/* Count of blocks */
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	struct xfs_ifork	*ifp,
+	xfs_fsblock_t		blockno,
+	int			levelin,
+	xfs_extnum_t		*nextents,
+	xfs_filblks_t		*count)
 {
 	int			error;
-	xfs_buf_t		*bp, *nbp;
+	struct xfs_buf		*bp, *nbp;
 	int			level = levelin;
 	__be64			*pp;
 	xfs_fsblock_t           bno = blockno;
@@ -308,8 +308,9 @@ xfs_bmap_count_tree(
 		/* Dive to the next level */
 		pp = XFS_BMBT_PTR_ADDR(mp, block, 1, mp->m_bmap_dmxr[1]);
 		bno = be64_to_cpu(*pp);
-		if (unlikely((error =
-		     xfs_bmap_count_tree(mp, tp, ifp, bno, level, count)) < 0)) {
+		error = xfs_bmap_count_tree(mp, tp, ifp, bno, level, nextents,
+				count);
+		if (error) {
 			xfs_trans_brelse(tp, bp);
 			XFS_ERROR_REPORT("xfs_bmap_count_tree(1)",
 					 XFS_ERRLEVEL_LOW, mp);
@@ -321,6 +322,7 @@ xfs_bmap_count_tree(
 		for (;;) {
 			nextbno = be64_to_cpu(block->bb_u.l.bb_rightsib);
 			numrecs = be16_to_cpu(block->bb_numrecs);
+			(*nextents) += numrecs;
 			xfs_bmap_disk_count_leaves(mp, block, numrecs, count);
 			xfs_trans_brelse(tp, bp);
 			if (nextbno == NULLFSBLOCK)
@@ -339,46 +341,64 @@ xfs_bmap_count_tree(
 }
 
 /*
- * Count fsblocks of the given fork.
+ * Count fsblocks of the given fork.  Delayed allocation extents are
+ * not counted towards the totals.
  */
-static int					/* error */
+int
 xfs_bmap_count_blocks(
-	xfs_trans_t		*tp,		/* transaction pointer */
-	xfs_inode_t		*ip,		/* incore inode */
-	int			whichfork,	/* data or attr fork */
-	int			*count)		/* out: count of blocks */
+	struct xfs_trans	*tp,
+	struct xfs_inode	*ip,
+	int			whichfork,
+	xfs_extnum_t		*nextents,
+	xfs_filblks_t		*count)
 {
+	struct xfs_mount	*mp;	/* file system mount structure */
+	__be64			*pp;	/* pointer to block address */
 	struct xfs_btree_block	*block;	/* current btree block */
+	struct xfs_ifork	*ifp;	/* fork structure */
 	xfs_fsblock_t		bno;	/* block # of "block" */
-	xfs_ifork_t		*ifp;	/* fork structure */
 	int			level;	/* btree level, for checking */
-	xfs_mount_t		*mp;	/* file system mount structure */
-	__be64			*pp;	/* pointer to block address */
+	int			error;
 
 	bno = NULLFSBLOCK;
 	mp = ip->i_mount;
+	*nextents = 0;
+	*count = 0;
 	ifp = XFS_IFORK_PTR(ip, whichfork);
-	if ( XFS_IFORK_FORMAT(ip, whichfork) == XFS_DINODE_FMT_EXTENTS ) {
-		xfs_bmap_count_leaves(ifp, 0, xfs_iext_count(ifp), count);
+	if (!ifp)
 		return 0;
-	}
 
-	/*
-	 * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
-	 */
-	block = ifp->if_broot;
-	level = be16_to_cpu(block->bb_level);
-	ASSERT(level > 0);
-	pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
-	bno = be64_to_cpu(*pp);
-	ASSERT(bno != NULLFSBLOCK);
-	ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
-	ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
-
-	if (unlikely(xfs_bmap_count_tree(mp, tp, ifp, bno, level, count) < 0)) {
-		XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)", XFS_ERRLEVEL_LOW,
-				 mp);
-		return -EFSCORRUPTED;
+	switch (XFS_IFORK_FORMAT(ip, whichfork)) {
+	case XFS_DINODE_FMT_EXTENTS:
+		xfs_bmap_count_leaves(ifp, nextents, count);
+		return 0;
+	case XFS_DINODE_FMT_BTREE:
+		if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+			error = xfs_iread_extents(tp, ip, whichfork);
+			if (error)
+				return error;
+		}
+
+		/*
+		 * Root level must use BMAP_BROOT_PTR_ADDR macro to get ptr out.
+		 */
+		block = ifp->if_broot;
+		level = be16_to_cpu(block->bb_level);
+		ASSERT(level > 0);
+		pp = XFS_BMAP_BROOT_PTR_ADDR(mp, block, 1, ifp->if_broot_bytes);
+		bno = be64_to_cpu(*pp);
+		ASSERT(bno != NULLFSBLOCK);
+		ASSERT(XFS_FSB_TO_AGNO(mp, bno) < mp->m_sb.sb_agcount);
+		ASSERT(XFS_FSB_TO_AGBNO(mp, bno) < mp->m_sb.sb_agblocks);
+
+		error = xfs_bmap_count_tree(mp, tp, ifp, bno, level,
+				nextents, count);
+		if (error) {
+			XFS_ERROR_REPORT("xfs_bmap_count_blocks(2)",
+					XFS_ERRLEVEL_LOW, mp);
+			return -EFSCORRUPTED;
+		}
+		return 0;
 	}
 
 	return 0;
@@ -394,11 +414,11 @@ xfs_getbmapx_fix_eof_hole(
 	struct getbmapx		*out,		/* output structure */
 	int			prealloced,	/* this is a file with
 						 * preallocated data space */
-	__int64_t		end,		/* last block requested */
+	int64_t			end,		/* last block requested */
 	xfs_fsblock_t		startblock,
 	bool			moretocome)
 {
-	__int64_t		fixlen;
+	int64_t			fixlen;
 	xfs_mount_t		*mp;		/* file system mount point */
 	xfs_ifork_t		*ifp;		/* inode fork pointer */
 	xfs_extnum_t		lastx;		/* last extent pointer */
@@ -453,16 +473,15 @@ xfs_getbmap_adjust_shared(
 	next_map->br_blockcount = 0;
 
 	/* Only written data blocks can be shared. */
-	if (!xfs_is_reflink_inode(ip) || whichfork != XFS_DATA_FORK ||
-	    map->br_startblock == DELAYSTARTBLOCK ||
-	    map->br_startblock == HOLESTARTBLOCK ||
-	    ISUNWRITTEN(map))
+	if (!xfs_is_reflink_inode(ip) ||
+	    whichfork != XFS_DATA_FORK ||
+	    !xfs_bmap_is_real_extent(map))
 		return 0;
 
 	agno = XFS_FSB_TO_AGNO(mp, map->br_startblock);
 	agbno = XFS_FSB_TO_AGBNO(mp, map->br_startblock);
-	error = xfs_reflink_find_shared(mp, agno, agbno, map->br_blockcount,
-			&ebno, &elen, true);
+	error = xfs_reflink_find_shared(mp, NULL, agno, agbno,
+			map->br_blockcount, &ebno, &elen, true);
 	if (error)
 		return error;
 
@@ -520,9 +539,9 @@ xfs_getbmap(
 	xfs_bmap_format_t	formatter,	/* format to user */
 	void			*arg)		/* formatter arg */
 {
-	__int64_t		bmvend;		/* last block requested */
+	int64_t			bmvend;		/* last block requested */
 	int			error = 0;	/* return value */
-	__int64_t		fixlen;		/* length for -1 case */
+	int64_t			fixlen;		/* length for -1 case */
 	int			i;		/* extent number */
 	int			lock;		/* lock state */
 	xfs_bmbt_irec_t		*map;		/* buffer for user's data */
@@ -588,9 +607,13 @@ xfs_getbmap(
 		}
 		break;
 	default:
+		/* Local format data forks report no extents. */
+		if (ip->i_d.di_format == XFS_DINODE_FMT_LOCAL) {
+			bmv->bmv_entries = 0;
+			return 0;
+		}
 		if (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS &&
-		    ip->i_d.di_format != XFS_DINODE_FMT_BTREE &&
-		    ip->i_d.di_format != XFS_DINODE_FMT_LOCAL)
+		    ip->i_d.di_format != XFS_DINODE_FMT_BTREE)
 			return -EINVAL;
 
 		if (xfs_get_extsz_hint(ip) ||
@@ -607,7 +630,7 @@ xfs_getbmap(
 	if (bmv->bmv_length == -1) {
 		fixlen = XFS_FSB_TO_BB(mp, XFS_B_TO_FSB(mp, fixlen));
 		bmv->bmv_length =
-			max_t(__int64_t, fixlen - bmv->bmv_offset, 0);
+			max_t(int64_t, fixlen - bmv->bmv_offset, 0);
 	} else if (bmv->bmv_length == 0) {
 		bmv->bmv_entries = 0;
 		return 0;
@@ -718,7 +741,7 @@ xfs_getbmap(
 			 * extents.
 			 */
 			if (map[i].br_startblock == DELAYSTARTBLOCK &&
-			    map[i].br_startoff <= XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
+			    map[i].br_startoff < XFS_B_TO_FSB(mp, XFS_ISIZE(ip)))
 				ASSERT((iflags & BMV_IF_DELALLOC) != 0);
 
                         if (map[i].br_startblock == HOLESTARTBLOCK &&
@@ -744,7 +767,7 @@ xfs_getbmap(
 				out[cur_ext].bmv_offset +
 				out[cur_ext].bmv_length;
 			bmv->bmv_length =
-				max_t(__int64_t, 0, bmvend - bmv->bmv_offset);
+				max_t(int64_t, 0, bmvend - bmv->bmv_offset);
 
 			/*
 			 * In case we don't want to return the hole,
@@ -787,11 +810,9 @@ xfs_getbmap(
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
 	for (i = 0; i < cur_ext; i++) {
-		int full = 0;	/* user array is full */
-
 		/* format results & advance arg */
-		error = formatter(&arg, &out[i], &full);
-		if (error || full)
+		error = formatter(&arg, &out[i]);
+		if (error)
 			break;
 	}
 
@@ -911,23 +932,22 @@ xfs_can_free_eofblocks(struct xfs_inode *ip, bool force)
 }
 
 /*
- * This is called by xfs_inactive to free any blocks beyond eof
- * when the link count isn't zero and by xfs_dm_punch_hole() when
- * punching a hole to EOF.
+ * This is called to free any blocks beyond eof. The caller must hold
+ * IOLOCK_EXCL unless we are in the inode reclaim path and have the only
+ * reference to the inode.
  */
 int
 xfs_free_eofblocks(
-	xfs_mount_t	*mp,
-	xfs_inode_t	*ip,
-	bool		need_iolock)
+	struct xfs_inode	*ip)
 {
-	xfs_trans_t	*tp;
-	int		error;
-	xfs_fileoff_t	end_fsb;
-	xfs_fileoff_t	last_fsb;
-	xfs_filblks_t	map_len;
-	int		nimaps;
-	xfs_bmbt_irec_t	imap;
+	struct xfs_trans	*tp;
+	int			error;
+	xfs_fileoff_t		end_fsb;
+	xfs_fileoff_t		last_fsb;
+	xfs_filblks_t		map_len;
+	int			nimaps;
+	struct xfs_bmbt_irec	imap;
+	struct xfs_mount	*mp = ip->i_mount;
 
 	/*
 	 * Figure out if there are any blocks beyond the end
@@ -944,6 +964,10 @@ xfs_free_eofblocks(
 	error = xfs_bmapi_read(ip, end_fsb, map_len, &imap, &nimaps, 0);
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
 
+	/*
+	 * If there are blocks after the end of file, truncate the file to its
+	 * current size to free them up.
+	 */
 	if (!error && (nimaps != 0) &&
 	    (imap.br_startblock != HOLESTARTBLOCK ||
 	     ip->i_delayed_blks)) {
@@ -954,22 +978,13 @@ xfs_free_eofblocks(
 		if (error)
 			return error;
 
-		/*
-		 * There are blocks after the end of file.
-		 * Free them up now by truncating the file to
-		 * its current size.
-		 */
-		if (need_iolock) {
-			if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL))
-				return -EAGAIN;
-		}
+		/* wait on dio to ensure i_size has settled */
+		inode_dio_wait(VFS_I(ip));
 
 		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_itruncate, 0, 0, 0,
 				&tp);
 		if (error) {
 			ASSERT(XFS_FORCED_SHUTDOWN(mp));
-			if (need_iolock)
-				xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 			return error;
 		}
 
@@ -997,8 +1012,6 @@ xfs_free_eofblocks(
 		}
 
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
-		if (need_iolock)
-			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 	}
 	return error;
 }
@@ -1222,11 +1235,8 @@ xfs_adjust_extent_unmap_boundaries(
 		return error;
 
 	if (nimap && imap.br_startblock != HOLESTARTBLOCK) {
-		xfs_daddr_t	block;
-
 		ASSERT(imap.br_startblock != DELAYSTARTBLOCK);
-		block = imap.br_startblock;
-		mod = do_div(block, mp->m_sb.sb_rextsize);
+		mod = do_mod(imap.br_startblock, mp->m_sb.sb_rextsize);
 		if (mod)
 			*startoffset_fsb += mp->m_sb.sb_rextsize - mod;
 	}
@@ -1324,8 +1334,16 @@ xfs_free_file_space(
 	/*
 	 * Now that we've unmap all full blocks we'll have to zero out any
 	 * partial block at the beginning and/or end.  xfs_zero_range is
-	 * smart enough to skip any holes, including those we just created.
+	 * smart enough to skip any holes, including those we just created,
+	 * but we must take care not to zero beyond EOF and enlarge i_size.
 	 */
+
+	if (offset >= XFS_ISIZE(ip))
+		return 0;
+
+	if (offset + len > XFS_ISIZE(ip))
+		len = XFS_ISIZE(ip) - offset;
+
 	return xfs_zero_range(ip, offset, len, NULL);
 }
 
@@ -1393,10 +1411,16 @@ xfs_shift_file_space(
 	xfs_fileoff_t		stop_fsb;
 	xfs_fileoff_t		next_fsb;
 	xfs_fileoff_t		shift_fsb;
+	uint			resblks;
 
 	ASSERT(direction == SHIFT_LEFT || direction == SHIFT_RIGHT);
 
 	if (direction == SHIFT_LEFT) {
+		/*
+		 * Reserve blocks to cover potential extent merges after left
+		 * shift operations.
+		 */
+		resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0);
 		next_fsb = XFS_B_TO_FSB(mp, offset + len);
 		stop_fsb = XFS_B_TO_FSB(mp, VFS_I(ip)->i_size);
 	} else {
@@ -1404,6 +1428,7 @@ xfs_shift_file_space(
 		 * If right shift, delegate the work of initialization of
 		 * next_fsb to xfs_bmap_shift_extent as it has ilock held.
 		 */
+		resblks = 0;
 		next_fsb = NULLFSBLOCK;
 		stop_fsb = XFS_B_TO_FSB(mp, offset);
 	}
@@ -1415,7 +1440,7 @@ xfs_shift_file_space(
 	 * into the accessible region of the file.
 	 */
 	if (xfs_can_free_eofblocks(ip, true)) {
-		error = xfs_free_eofblocks(mp, ip, false);
+		error = xfs_free_eofblocks(ip);
 		if (error)
 			return error;
 	}
@@ -1445,21 +1470,14 @@ xfs_shift_file_space(
 	}
 
 	while (!error && !done) {
-		/*
-		 * We would need to reserve permanent block for transaction.
-		 * This will come into picture when after shifting extent into
-		 * hole we found that adjacent extents can be merged which
-		 * may lead to freeing of a block during record update.
-		 */
-		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write,
-				XFS_DIOSTRAT_SPACE_RES(mp, 0), 0, 0, &tp);
+		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0,
+					&tp);
 		if (error)
 			break;
 
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		error = xfs_trans_reserve_quota(tp, mp, ip->i_udquot,
-				ip->i_gdquot, ip->i_pdquot,
-				XFS_DIOSTRAT_SPACE_RES(mp, 0), 0,
+				ip->i_gdquot, ip->i_pdquot, resblks, 0,
 				XFS_QMOPT_RES_REGBLKS);
 		if (error)
 			goto out_trans_cancel;
@@ -1624,7 +1642,7 @@ xfs_swap_extents_check_format(
 	 * extent format...
 	 */
 	if (tip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
-		if (XFS_IFORK_BOFF(ip) &&
+		if (XFS_IFORK_Q(ip) &&
 		    XFS_BMAP_BMDR_SPACE(tip->i_df.if_broot) > XFS_IFORK_BOFF(ip))
 			return -EINVAL;
 		if (XFS_IFORK_NEXTENTS(tip, XFS_DATA_FORK) <=
@@ -1634,7 +1652,7 @@ xfs_swap_extents_check_format(
 
 	/* Reciprocal target->temp btree format checks */
 	if (ip->i_d.di_format == XFS_DINODE_FMT_BTREE) {
-		if (XFS_IFORK_BOFF(tip) &&
+		if (XFS_IFORK_Q(tip) &&
 		    XFS_BMAP_BMDR_SPACE(ip->i_df.if_broot) > XFS_IFORK_BOFF(tip))
 			return -EINVAL;
 		if (XFS_IFORK_NEXTENTS(ip, XFS_DATA_FORK) <=
@@ -1683,7 +1701,7 @@ xfs_swap_extent_rmap(
 	xfs_filblks_t			ilen;
 	xfs_filblks_t			rlen;
 	int				nimaps;
-	__uint64_t			tip_flags2;
+	uint64_t			tip_flags2;
 
 	/*
 	 * If the source file has shared blocks, we must flag the donor
@@ -1796,10 +1814,11 @@ xfs_swap_extent_forks(
 	int			*target_log_flags)
 {
 	struct xfs_ifork	tempifp, *ifp, *tifp;
-	int			aforkblks = 0;
-	int			taforkblks = 0;
+	xfs_filblks_t		aforkblks = 0;
+	xfs_filblks_t		taforkblks = 0;
+	xfs_extnum_t		junk;
 	xfs_extnum_t		nextents;
-	__uint64_t		tmp;
+	uint64_t		tmp;
 	int			error;
 
 	/*
@@ -1807,14 +1826,14 @@ xfs_swap_extent_forks(
 	 */
 	if ( ((XFS_IFORK_Q(ip) != 0) && (ip->i_d.di_anextents > 0)) &&
 	     (ip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
-		error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK,
+		error = xfs_bmap_count_blocks(tp, ip, XFS_ATTR_FORK, &junk,
 				&aforkblks);
 		if (error)
 			return error;
 	}
 	if ( ((XFS_IFORK_Q(tip) != 0) && (tip->i_d.di_anextents > 0)) &&
 	     (tip->i_d.di_aformat != XFS_DINODE_FMT_LOCAL)) {
-		error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK,
+		error = xfs_bmap_count_blocks(tp, tip, XFS_ATTR_FORK, &junk,
 				&taforkblks);
 		if (error)
 			return error;
@@ -1857,15 +1876,15 @@ xfs_swap_extent_forks(
 	/*
 	 * Fix the on-disk inode values
 	 */
-	tmp = (__uint64_t)ip->i_d.di_nblocks;
+	tmp = (uint64_t)ip->i_d.di_nblocks;
 	ip->i_d.di_nblocks = tip->i_d.di_nblocks - taforkblks + aforkblks;
 	tip->i_d.di_nblocks = tmp + taforkblks - aforkblks;
 
-	tmp = (__uint64_t) ip->i_d.di_nextents;
+	tmp = (uint64_t) ip->i_d.di_nextents;
 	ip->i_d.di_nextents = tip->i_d.di_nextents;
 	tip->i_d.di_nextents = tmp;
 
-	tmp = (__uint64_t) ip->i_d.di_format;
+	tmp = (uint64_t) ip->i_d.di_format;
 	ip->i_d.di_format = tip->i_d.di_format;
 	tip->i_d.di_format = tmp;
 
@@ -1934,7 +1953,7 @@ xfs_swap_extents(
 	int			error = 0;
 	int			lock_flags;
 	struct xfs_ifork	*cowfp;
-	__uint64_t		f;
+	uint64_t		f;
 	int			resblks;
 
 	/*
diff --git a/fs/xfs/xfs_bmap_util.h b/fs/xfs/xfs_bmap_util.h
index 68a621a8e0c0..0cede1043571 100644
--- a/fs/xfs/xfs_bmap_util.h
+++ b/fs/xfs/xfs_bmap_util.h
@@ -35,7 +35,7 @@ int	xfs_bmap_punch_delalloc_range(struct xfs_inode *ip,
 		xfs_fileoff_t start_fsb, xfs_fileoff_t length);
 
 /* bmap to userspace formatter - copy to user & advance pointer */
-typedef int (*xfs_bmap_format_t)(void **, struct getbmapx *, int *);
+typedef int (*xfs_bmap_format_t)(void **, struct getbmapx *);
 int	xfs_getbmap(struct xfs_inode *ip, struct getbmapx *bmv,
 		xfs_bmap_format_t formatter, void *arg);
 
@@ -63,12 +63,15 @@ int	xfs_insert_file_space(struct xfs_inode *, xfs_off_t offset,
 
 /* EOF block manipulation functions */
 bool	xfs_can_free_eofblocks(struct xfs_inode *ip, bool force);
-int	xfs_free_eofblocks(struct xfs_mount *mp, struct xfs_inode *ip,
-			   bool need_iolock);
+int	xfs_free_eofblocks(struct xfs_inode *ip);
 
 int	xfs_swap_extents(struct xfs_inode *ip, struct xfs_inode *tip,
 			 struct xfs_swapext *sx);
 
 xfs_daddr_t xfs_fsb_to_db(struct xfs_inode *ip, xfs_fsblock_t fsb);
 
+int xfs_bmap_count_blocks(struct xfs_trans *tp, struct xfs_inode *ip,
+			  int whichfork, xfs_extnum_t *nextents,
+			  xfs_filblks_t *count);
+
 #endif	/* __XFS_BMAP_UTIL_H__ */
diff --git a/fs/xfs/xfs_buf.c b/fs/xfs/xfs_buf.c
index ac3b4db519df..72f038492ba8 100644
--- a/fs/xfs/xfs_buf.c
+++ b/fs/xfs/xfs_buf.c
@@ -33,6 +33,7 @@
 #include <linux/migrate.h>
 #include <linux/backing-dev.h>
 #include <linux/freezer.h>
+#include <linux/sched/mm.h>
 
 #include "xfs_format.h"
 #include "xfs_log_format.h"
@@ -96,12 +97,16 @@ static inline void
 xfs_buf_ioacct_inc(
 	struct xfs_buf	*bp)
 {
-	if (bp->b_flags & (XBF_NO_IOACCT|_XBF_IN_FLIGHT))
+	if (bp->b_flags & XBF_NO_IOACCT)
 		return;
 
 	ASSERT(bp->b_flags & XBF_ASYNC);
-	bp->b_flags |= _XBF_IN_FLIGHT;
-	percpu_counter_inc(&bp->b_target->bt_io_count);
+	spin_lock(&bp->b_lock);
+	if (!(bp->b_state & XFS_BSTATE_IN_FLIGHT)) {
+		bp->b_state |= XFS_BSTATE_IN_FLIGHT;
+		percpu_counter_inc(&bp->b_target->bt_io_count);
+	}
+	spin_unlock(&bp->b_lock);
 }
 
 /*
@@ -109,14 +114,24 @@ xfs_buf_ioacct_inc(
  * freed and unaccount from the buftarg.
  */
 static inline void
-xfs_buf_ioacct_dec(
+__xfs_buf_ioacct_dec(
 	struct xfs_buf	*bp)
 {
-	if (!(bp->b_flags & _XBF_IN_FLIGHT))
-		return;
+	lockdep_assert_held(&bp->b_lock);
+
+	if (bp->b_state & XFS_BSTATE_IN_FLIGHT) {
+		bp->b_state &= ~XFS_BSTATE_IN_FLIGHT;
+		percpu_counter_dec(&bp->b_target->bt_io_count);
+	}
+}
 
-	bp->b_flags &= ~_XBF_IN_FLIGHT;
-	percpu_counter_dec(&bp->b_target->bt_io_count);
+static inline void
+xfs_buf_ioacct_dec(
+	struct xfs_buf	*bp)
+{
+	spin_lock(&bp->b_lock);
+	__xfs_buf_ioacct_dec(bp);
+	spin_unlock(&bp->b_lock);
 }
 
 /*
@@ -148,9 +163,9 @@ xfs_buf_stale(
 	 * unaccounted (released to LRU) before that occurs. Drop in-flight
 	 * status now to preserve accounting consistency.
 	 */
-	xfs_buf_ioacct_dec(bp);
-
 	spin_lock(&bp->b_lock);
+	__xfs_buf_ioacct_dec(bp);
+
 	atomic_set(&bp->b_lru_ref, 0);
 	if (!(bp->b_state & XFS_BSTATE_DISPOSE) &&
 	    (list_lru_del(&bp->b_target->bt_lru, &bp->b_lru)))
@@ -442,17 +457,17 @@ _xfs_buf_map_pages(
 		bp->b_addr = NULL;
 	} else {
 		int retried = 0;
-		unsigned noio_flag;
+		unsigned nofs_flag;
 
 		/*
 		 * vm_map_ram() will allocate auxillary structures (e.g.
 		 * pagetables) with GFP_KERNEL, yet we are likely to be under
 		 * GFP_NOFS context here. Hence we need to tell memory reclaim
-		 * that we are in such a context via PF_MEMALLOC_NOIO to prevent
+		 * that we are in such a context via PF_MEMALLOC_NOFS to prevent
 		 * memory reclaim re-entering the filesystem here and
 		 * potentially deadlocking.
 		 */
-		noio_flag = memalloc_noio_save();
+		nofs_flag = memalloc_nofs_save();
 		do {
 			bp->b_addr = vm_map_ram(bp->b_pages, bp->b_page_count,
 						-1, PAGE_KERNEL);
@@ -460,7 +475,7 @@ _xfs_buf_map_pages(
 				break;
 			vm_unmap_aliases();
 		} while (retried++ <= 1);
-		memalloc_noio_restore(noio_flag);
+		memalloc_nofs_restore(nofs_flag);
 
 		if (!bp->b_addr)
 			return -ENOMEM;
@@ -758,7 +773,7 @@ xfs_buf_readahead_map(
 	int			nmaps,
 	const struct xfs_buf_ops *ops)
 {
-	if (bdi_read_congested(target->bt_bdi))
+	if (bdi_read_congested(target->bt_bdev->bd_bdi))
 		return;
 
 	xfs_buf_read_map(target, map, nmaps,
@@ -978,12 +993,12 @@ xfs_buf_rele(
 		 * ensures the decrement occurs only once per-buf.
 		 */
 		if ((atomic_read(&bp->b_hold) == 1) && !list_empty(&bp->b_lru))
-			xfs_buf_ioacct_dec(bp);
+			__xfs_buf_ioacct_dec(bp);
 		goto out_unlock;
 	}
 
 	/* the last reference has been dropped ... */
-	xfs_buf_ioacct_dec(bp);
+	__xfs_buf_ioacct_dec(bp);
 	if (!(bp->b_flags & XBF_STALE) && atomic_read(&bp->b_lru_ref)) {
 		/*
 		 * If the buffer is added to the LRU take a new reference to the
@@ -1078,6 +1093,8 @@ void
 xfs_buf_unlock(
 	struct xfs_buf		*bp)
 {
+	ASSERT(xfs_buf_islocked(bp));
+
 	XB_CLEAR_OWNER(bp);
 	up(&bp->b_sema);
 
@@ -1177,7 +1194,7 @@ xfs_buf_ioerror_alert(
 {
 	xfs_alert(bp->b_target->bt_mount,
 "metadata I/O error: block 0x%llx (\"%s\") error %d numblks %d",
-		(__uint64_t)XFS_BUF_ADDR(bp), func, -bp->b_error, bp->b_length);
+		(uint64_t)XFS_BUF_ADDR(bp), func, -bp->b_error, bp->b_length);
 }
 
 int
@@ -1210,8 +1227,11 @@ xfs_buf_bio_end_io(
 	 * don't overwrite existing errors - otherwise we can lose errors on
 	 * buffers that require multiple bios to complete.
 	 */
-	if (bio->bi_error)
-		cmpxchg(&bp->b_io_error, 0, bio->bi_error);
+	if (bio->bi_status) {
+		int error = blk_status_to_errno(bio->bi_status);
+
+		cmpxchg(&bp->b_io_error, 0, error);
+	}
 
 	if (!bp->b_error && xfs_buf_is_vmapped(bp) && (bp->b_flags & XBF_READ))
 		invalidate_kernel_vmap_range(bp->b_addr, xfs_buf_vmap_len(bp));
@@ -1791,7 +1811,6 @@ xfs_alloc_buftarg(
 	btp->bt_mount = mp;
 	btp->bt_dev =  bdev->bd_dev;
 	btp->bt_bdev = bdev;
-	btp->bt_bdi = blk_get_backing_dev_info(bdev);
 
 	if (xfs_setsize_buftarg_early(btp, bdev))
 		goto error;
@@ -1815,6 +1834,28 @@ error:
 }
 
 /*
+ * Cancel a delayed write list.
+ *
+ * Remove each buffer from the list, clear the delwri queue flag and drop the
+ * associated buffer reference.
+ */
+void
+xfs_buf_delwri_cancel(
+	struct list_head	*list)
+{
+	struct xfs_buf		*bp;
+
+	while (!list_empty(list)) {
+		bp = list_first_entry(list, struct xfs_buf, b_list);
+
+		xfs_buf_lock(bp);
+		bp->b_flags &= ~_XBF_DELWRI_Q;
+		list_del_init(&bp->b_list);
+		xfs_buf_relse(bp);
+	}
+}
+
+/*
  * Add a buffer to the delayed write list.
  *
  * This queues a buffer for writeout if it hasn't already been.  Note that
@@ -2009,6 +2050,66 @@ xfs_buf_delwri_submit(
 	return error;
 }
 
+/*
+ * Push a single buffer on a delwri queue.
+ *
+ * The purpose of this function is to submit a single buffer of a delwri queue
+ * and return with the buffer still on the original queue. The waiting delwri
+ * buffer submission infrastructure guarantees transfer of the delwri queue
+ * buffer reference to a temporary wait list. We reuse this infrastructure to
+ * transfer the buffer back to the original queue.
+ *
+ * Note the buffer transitions from the queued state, to the submitted and wait
+ * listed state and back to the queued state during this call. The buffer
+ * locking and queue management logic between _delwri_pushbuf() and
+ * _delwri_queue() guarantee that the buffer cannot be queued to another list
+ * before returning.
+ */
+int
+xfs_buf_delwri_pushbuf(
+	struct xfs_buf		*bp,
+	struct list_head	*buffer_list)
+{
+	LIST_HEAD		(submit_list);
+	int			error;
+
+	ASSERT(bp->b_flags & _XBF_DELWRI_Q);
+
+	trace_xfs_buf_delwri_pushbuf(bp, _RET_IP_);
+
+	/*
+	 * Isolate the buffer to a new local list so we can submit it for I/O
+	 * independently from the rest of the original list.
+	 */
+	xfs_buf_lock(bp);
+	list_move(&bp->b_list, &submit_list);
+	xfs_buf_unlock(bp);
+
+	/*
+	 * Delwri submission clears the DELWRI_Q buffer flag and returns with
+	 * the buffer on the wait list with an associated reference. Rather than
+	 * bounce the buffer from a local wait list back to the original list
+	 * after I/O completion, reuse the original list as the wait list.
+	 */
+	xfs_buf_delwri_submit_buffers(&submit_list, buffer_list);
+
+	/*
+	 * The buffer is now under I/O and wait listed as during typical delwri
+	 * submission. Lock the buffer to wait for I/O completion. Rather than
+	 * remove the buffer from the wait list and release the reference, we
+	 * want to return with the buffer queued to the original list. The
+	 * buffer already sits on the original list with a wait list reference,
+	 * however. If we let the queue inherit that wait list reference, all we
+	 * need to do is reset the DELWRI_Q flag.
+	 */
+	xfs_buf_lock(bp);
+	error = bp->b_error;
+	bp->b_flags |= _XBF_DELWRI_Q;
+	xfs_buf_unlock(bp);
+
+	return error;
+}
+
 int __init
 xfs_buf_init(void)
 {
diff --git a/fs/xfs/xfs_buf.h b/fs/xfs/xfs_buf.h
index 8a9d3a9599f0..20721261dae5 100644
--- a/fs/xfs/xfs_buf.h
+++ b/fs/xfs/xfs_buf.h
@@ -63,7 +63,6 @@ typedef enum {
 #define _XBF_KMEM	 (1 << 21)/* backed by heap memory */
 #define _XBF_DELWRI_Q	 (1 << 22)/* buffer on a delwri queue */
 #define _XBF_COMPOUND	 (1 << 23)/* compound buffer */
-#define _XBF_IN_FLIGHT	 (1 << 25) /* I/O in flight, for accounting purposes */
 
 typedef unsigned int xfs_buf_flags_t;
 
@@ -84,14 +83,14 @@ typedef unsigned int xfs_buf_flags_t;
 	{ _XBF_PAGES,		"PAGES" }, \
 	{ _XBF_KMEM,		"KMEM" }, \
 	{ _XBF_DELWRI_Q,	"DELWRI_Q" }, \
-	{ _XBF_COMPOUND,	"COMPOUND" }, \
-	{ _XBF_IN_FLIGHT,	"IN_FLIGHT" }
+	{ _XBF_COMPOUND,	"COMPOUND" }
 
 
 /*
  * Internal state flags.
  */
 #define XFS_BSTATE_DISPOSE	 (1 << 0)	/* buffer being discarded */
+#define XFS_BSTATE_IN_FLIGHT	 (1 << 1)	/* I/O in flight */
 
 /*
  * The xfs_buftarg contains 2 notions of "sector size" -
@@ -109,7 +108,6 @@ typedef unsigned int xfs_buf_flags_t;
 typedef struct xfs_buftarg {
 	dev_t			bt_dev;
 	struct block_device	*bt_bdev;
-	struct backing_dev_info	*bt_bdi;
 	struct xfs_mount	*bt_mount;
 	unsigned int		bt_meta_sectorsize;
 	size_t			bt_meta_sectormask;
@@ -292,7 +290,6 @@ xfs_buf_readahead(
 	return xfs_buf_readahead_map(target, &map, 1, ops);
 }
 
-struct xfs_buf *xfs_buf_get_empty(struct xfs_buftarg *target, size_t numblks);
 void xfs_buf_set_empty(struct xfs_buf *bp, size_t numblks);
 int xfs_buf_associate_memory(struct xfs_buf *bp, void *mem, size_t length);
 
@@ -331,9 +328,11 @@ extern void *xfs_buf_offset(struct xfs_buf *, size_t);
 extern void xfs_buf_stale(struct xfs_buf *bp);
 
 /* Delayed Write Buffer Routines */
+extern void xfs_buf_delwri_cancel(struct list_head *);
 extern bool xfs_buf_delwri_queue(struct xfs_buf *, struct list_head *);
 extern int xfs_buf_delwri_submit(struct list_head *);
 extern int xfs_buf_delwri_submit_nowait(struct list_head *);
+extern int xfs_buf_delwri_pushbuf(struct xfs_buf *, struct list_head *);
 
 /* Buffer Daemon Setup Routines */
 extern int xfs_buf_init(void);
diff --git a/fs/xfs/xfs_buf_item.c b/fs/xfs/xfs_buf_item.c
index 2975cb2319f4..f6a8422e9562 100644
--- a/fs/xfs/xfs_buf_item.c
+++ b/fs/xfs/xfs_buf_item.c
@@ -636,20 +636,23 @@ xfs_buf_item_unlock(
 
 	/*
 	 * Clean buffers, by definition, cannot be in the AIL. However, aborted
-	 * buffers may be dirty and hence in the AIL. Therefore if we are
-	 * aborting a buffer and we've just taken the last refernce away, we
-	 * have to check if it is in the AIL before freeing it. We need to free
-	 * it in this case, because an aborted transaction has already shut the
-	 * filesystem down and this is the last chance we will have to do so.
+	 * buffers may be in the AIL regardless of dirty state. An aborted
+	 * transaction that invalidates a buffer already in the AIL may have
+	 * marked it stale and cleared the dirty state, for example.
+	 *
+	 * Therefore if we are aborting a buffer and we've just taken the last
+	 * reference away, we have to check if it is in the AIL before freeing
+	 * it. We need to free it in this case, because an aborted transaction
+	 * has already shut the filesystem down and this is the last chance we
+	 * will have to do so.
 	 */
 	if (atomic_dec_and_test(&bip->bli_refcount)) {
-		if (clean)
-			xfs_buf_item_relse(bp);
-		else if (aborted) {
+		if (aborted) {
 			ASSERT(XFS_FORCED_SHUTDOWN(lip->li_mountp));
 			xfs_trans_ail_remove(lip, SHUTDOWN_LOG_IO_ERROR);
 			xfs_buf_item_relse(bp);
-		}
+		} else if (clean)
+			xfs_buf_item_relse(bp);
 	}
 
 	if (!(flags & XFS_BLI_HOLD))
@@ -1162,6 +1165,7 @@ xfs_buf_iodone_callbacks(
 	 */
 	bp->b_last_error = 0;
 	bp->b_retries = 0;
+	bp->b_first_retry_time = 0;
 
 	xfs_buf_do_callbacks(bp);
 	bp->b_fspriv = NULL;
diff --git a/fs/xfs/xfs_dir2_readdir.c b/fs/xfs/xfs_dir2_readdir.c
index 003a99b83bd8..ba2638d37031 100644
--- a/fs/xfs/xfs_dir2_readdir.c
+++ b/fs/xfs/xfs_dir2_readdir.c
@@ -44,7 +44,7 @@ static unsigned char xfs_dir3_filetype_table[] = {
 static unsigned char
 xfs_dir3_get_dtype(
 	struct xfs_mount	*mp,
-	__uint8_t		filetype)
+	uint8_t			filetype)
 {
 	if (!xfs_sb_version_hasftype(&mp->m_sb))
 		return DT_UNKNOWN;
@@ -71,22 +71,11 @@ xfs_dir2_sf_getdents(
 	struct xfs_da_geometry	*geo = args->geo;
 
 	ASSERT(dp->i_df.if_flags & XFS_IFINLINE);
-	/*
-	 * Give up if the directory is way too short.
-	 */
-	if (dp->i_d.di_size < offsetof(xfs_dir2_sf_hdr_t, parent)) {
-		ASSERT(XFS_FORCED_SHUTDOWN(dp->i_mount));
-		return -EIO;
-	}
-
 	ASSERT(dp->i_df.if_bytes == dp->i_d.di_size);
 	ASSERT(dp->i_df.if_u1.if_data != NULL);
 
 	sfp = (xfs_dir2_sf_hdr_t *)dp->i_df.if_u1.if_data;
 
-	if (dp->i_d.di_size < xfs_dir2_sf_hdr_size(sfp->i8count))
-		return -EFSCORRUPTED;
-
 	/*
 	 * If the block number in the offset is out of range, we're done.
 	 */
@@ -128,7 +117,7 @@ xfs_dir2_sf_getdents(
 	 */
 	sfep = xfs_dir2_sf_firstentry(sfp);
 	for (i = 0; i < sfp->count; i++) {
-		__uint8_t filetype;
+		uint8_t filetype;
 
 		off = xfs_dir2_db_off_to_dataptr(geo, geo->datablk,
 				xfs_dir2_sf_get_offset(sfep));
@@ -181,7 +170,7 @@ xfs_dir2_block_getdents(
 		return 0;
 
 	lock_mode = xfs_ilock_data_map_shared(dp);
-	error = xfs_dir3_block_read(NULL, dp, &bp);
+	error = xfs_dir3_block_read(args->trans, dp, &bp);
 	xfs_iunlock(dp, lock_mode);
 	if (error)
 		return error;
@@ -205,7 +194,7 @@ xfs_dir2_block_getdents(
 	 * Each object is a real entry (dep) or an unused one (dup).
 	 */
 	while (ptr < endptr) {
-		__uint8_t filetype;
+		uint8_t filetype;
 
 		dup = (xfs_dir2_data_unused_t *)ptr;
 		/*
@@ -239,7 +228,7 @@ xfs_dir2_block_getdents(
 		if (!dir_emit(ctx, (char *)dep->name, dep->namelen,
 			    be64_to_cpu(dep->inumber),
 			    xfs_dir3_get_dtype(dp->i_mount, filetype))) {
-			xfs_trans_brelse(NULL, bp);
+			xfs_trans_brelse(args->trans, bp);
 			return 0;
 		}
 	}
@@ -250,211 +239,104 @@ xfs_dir2_block_getdents(
 	 */
 	ctx->pos = xfs_dir2_db_off_to_dataptr(geo, geo->datablk + 1, 0) &
 								0x7fffffff;
-	xfs_trans_brelse(NULL, bp);
+	xfs_trans_brelse(args->trans, bp);
 	return 0;
 }
 
-struct xfs_dir2_leaf_map_info {
-	xfs_extlen_t	map_blocks;	/* number of fsbs in map */
-	xfs_dablk_t	map_off;	/* last mapped file offset */
-	int		map_size;	/* total entries in *map */
-	int		map_valid;	/* valid entries in *map */
-	int		nmap;		/* mappings to ask xfs_bmapi */
-	xfs_dir2_db_t	curdb;		/* db for current block */
-	int		ra_current;	/* number of read-ahead blks */
-	int		ra_index;	/* *map index for read-ahead */
-	int		ra_offset;	/* map entry offset for ra */
-	int		ra_want;	/* readahead count wanted */
-	struct xfs_bmbt_irec map[];	/* map vector for blocks */
-};
-
+/*
+ * Read a directory block and initiate readahead for blocks beyond that.
+ * We maintain a sliding readahead window of the remaining space in the
+ * buffer rounded up to the nearest block.
+ */
 STATIC int
 xfs_dir2_leaf_readbuf(
 	struct xfs_da_args	*args,
 	size_t			bufsize,
-	struct xfs_dir2_leaf_map_info *mip,
-	xfs_dir2_off_t		*curoff,
-	struct xfs_buf		**bpp,
-	bool			trim_map)
+	xfs_dir2_off_t		*cur_off,
+	xfs_dablk_t		*ra_blk,
+	struct xfs_buf		**bpp)
 {
 	struct xfs_inode	*dp = args->dp;
 	struct xfs_buf		*bp = NULL;
-	struct xfs_bmbt_irec	*map = mip->map;
+	struct xfs_da_geometry	*geo = args->geo;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(dp, XFS_DATA_FORK);
+	struct xfs_bmbt_irec	map;
 	struct blk_plug		plug;
+	xfs_dir2_off_t		new_off;
+	xfs_dablk_t		next_ra;
+	xfs_dablk_t		map_off;
+	xfs_dablk_t		last_da;
+	xfs_extnum_t		idx;
+	int			ra_want;
 	int			error = 0;
-	int			length;
-	int			i;
-	int			j;
-	struct xfs_da_geometry	*geo = args->geo;
-
-	/*
-	 * If the caller just finished processing a buffer, it will tell us
-	 * we need to trim that block out of the mapping now it is done.
-	 */
-	if (trim_map) {
-		mip->map_blocks -= geo->fsbcount;
-		/*
-		 * Loop to get rid of the extents for the
-		 * directory block.
-		 */
-		for (i = geo->fsbcount; i > 0; ) {
-			j = min_t(int, map->br_blockcount, i);
-			map->br_blockcount -= j;
-			map->br_startblock += j;
-			map->br_startoff += j;
-			/*
-			 * If mapping is done, pitch it from
-			 * the table.
-			 */
-			if (!map->br_blockcount && --mip->map_valid)
-				memmove(&map[0], &map[1],
-					sizeof(map[0]) * mip->map_valid);
-			i -= j;
-		}
-	}
-
-	/*
-	 * Recalculate the readahead blocks wanted.
-	 */
-	mip->ra_want = howmany(bufsize + geo->blksize, (1 << geo->fsblog)) - 1;
-	ASSERT(mip->ra_want >= 0);
-
-	/*
-	 * If we don't have as many as we want, and we haven't
-	 * run out of data blocks, get some more mappings.
-	 */
-	if (1 + mip->ra_want > mip->map_blocks &&
-	    mip->map_off < xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET)) {
-		/*
-		 * Get more bmaps, fill in after the ones
-		 * we already have in the table.
-		 */
-		mip->nmap = mip->map_size - mip->map_valid;
-		error = xfs_bmapi_read(dp, mip->map_off,
-				xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET) -
-								mip->map_off,
-				&map[mip->map_valid], &mip->nmap, 0);
 
-		/*
-		 * Don't know if we should ignore this or try to return an
-		 * error.  The trouble with returning errors is that readdir
-		 * will just stop without actually passing the error through.
-		 */
+	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+		error = xfs_iread_extents(args->trans, dp, XFS_DATA_FORK);
 		if (error)
-			goto out;	/* XXX */
-
-		/*
-		 * If we got all the mappings we asked for, set the final map
-		 * offset based on the last bmap value received.  Otherwise,
-		 * we've reached the end.
-		 */
-		if (mip->nmap == mip->map_size - mip->map_valid) {
-			i = mip->map_valid + mip->nmap - 1;
-			mip->map_off = map[i].br_startoff + map[i].br_blockcount;
-		} else
-			mip->map_off = xfs_dir2_byte_to_da(geo,
-							XFS_DIR2_LEAF_OFFSET);
-
-		/*
-		 * Look for holes in the mapping, and eliminate them.  Count up
-		 * the valid blocks.
-		 */
-		for (i = mip->map_valid; i < mip->map_valid + mip->nmap; ) {
-			if (map[i].br_startblock == HOLESTARTBLOCK) {
-				mip->nmap--;
-				length = mip->map_valid + mip->nmap - i;
-				if (length)
-					memmove(&map[i], &map[i + 1],
-						sizeof(map[i]) * length);
-			} else {
-				mip->map_blocks += map[i].br_blockcount;
-				i++;
-			}
-		}
-		mip->map_valid += mip->nmap;
+			goto out;
 	}
 
 	/*
-	 * No valid mappings, so no more data blocks.
+	 * Look for mapped directory blocks at or above the current offset.
+	 * Truncate down to the nearest directory block to start the scanning
+	 * operation.
 	 */
-	if (!mip->map_valid) {
-		*curoff = xfs_dir2_da_to_byte(geo, mip->map_off);
+	last_da = xfs_dir2_byte_to_da(geo, XFS_DIR2_LEAF_OFFSET);
+	map_off = xfs_dir2_db_to_da(geo, xfs_dir2_byte_to_db(geo, *cur_off));
+	if (!xfs_iext_lookup_extent(dp, ifp, map_off, &idx, &map))
 		goto out;
-	}
+	if (map.br_startoff >= last_da)
+		goto out;
+	xfs_trim_extent(&map, map_off, last_da - map_off);
 
-	/*
-	 * Read the directory block starting at the first mapping.
-	 */
-	mip->curdb = xfs_dir2_da_to_db(geo, map->br_startoff);
-	error = xfs_dir3_data_read(NULL, dp, map->br_startoff,
-			map->br_blockcount >= geo->fsbcount ?
-			    XFS_FSB_TO_DADDR(dp->i_mount, map->br_startblock) :
-			    -1, &bp);
-	/*
-	 * Should just skip over the data block instead of giving up.
-	 */
+	/* Read the directory block of that first mapping. */
+	new_off = xfs_dir2_da_to_byte(geo, map.br_startoff);
+	if (new_off > *cur_off)
+		*cur_off = new_off;
+	error = xfs_dir3_data_read(args->trans, dp, map.br_startoff, -1, &bp);
 	if (error)
-		goto out;	/* XXX */
-
-	/*
-	 * Adjust the current amount of read-ahead: we just read a block that
-	 * was previously ra.
-	 */
-	if (mip->ra_current)
-		mip->ra_current -= geo->fsbcount;
+		goto out;
 
 	/*
-	 * Do we need more readahead?
+	 * Start readahead for the next bufsize's worth of dir data blocks.
+	 * We may have already issued readahead for some of that range;
+	 * ra_blk tracks the last block we tried to read(ahead).
 	 */
+	ra_want = howmany(bufsize + geo->blksize, (1 << geo->fsblog));
+	if (*ra_blk >= last_da)
+		goto out;
+	else if (*ra_blk == 0)
+		*ra_blk = map.br_startoff;
+	next_ra = map.br_startoff + geo->fsbcount;
+	if (next_ra >= last_da)
+		goto out_no_ra;
+	if (map.br_blockcount < geo->fsbcount &&
+	    !xfs_iext_get_extent(ifp, ++idx, &map))
+		goto out_no_ra;
+	if (map.br_startoff >= last_da)
+		goto out_no_ra;
+	xfs_trim_extent(&map, next_ra, last_da - next_ra);
+
+	/* Start ra for each dir (not fs) block that has a mapping. */
 	blk_start_plug(&plug);
-	for (mip->ra_index = mip->ra_offset = i = 0;
-	     mip->ra_want > mip->ra_current && i < mip->map_blocks;
-	     i += geo->fsbcount) {
-		ASSERT(mip->ra_index < mip->map_valid);
-		/*
-		 * Read-ahead a contiguous directory block.
-		 */
-		if (i > mip->ra_current &&
-		    map[mip->ra_index].br_blockcount >= geo->fsbcount) {
-			xfs_dir3_data_readahead(dp,
-				map[mip->ra_index].br_startoff + mip->ra_offset,
-				XFS_FSB_TO_DADDR(dp->i_mount,
-					map[mip->ra_index].br_startblock +
-							mip->ra_offset));
-			mip->ra_current = i;
-		}
-
-		/*
-		 * Read-ahead a non-contiguous directory block.  This doesn't
-		 * use our mapping, but this is a very rare case.
-		 */
-		else if (i > mip->ra_current) {
-			xfs_dir3_data_readahead(dp,
-					map[mip->ra_index].br_startoff +
-							mip->ra_offset, -1);
-			mip->ra_current = i;
-		}
-
-		/*
-		 * Advance offset through the mapping table.
-		 */
-		for (j = 0; j < geo->fsbcount; j += length ) {
-			/*
-			 * The rest of this extent but not more than a dir
-			 * block.
-			 */
-			length = min_t(int, geo->fsbcount,
-					map[mip->ra_index].br_blockcount -
-							mip->ra_offset);
-			mip->ra_offset += length;
-
-			/*
-			 * Advance to the next mapping if this one is used up.
-			 */
-			if (mip->ra_offset == map[mip->ra_index].br_blockcount) {
-				mip->ra_offset = 0;
-				mip->ra_index++;
+	while (ra_want > 0) {
+		next_ra = roundup((xfs_dablk_t)map.br_startoff, geo->fsbcount);
+		while (ra_want > 0 &&
+		       next_ra < map.br_startoff + map.br_blockcount) {
+			if (next_ra >= last_da) {
+				*ra_blk = last_da;
+				break;
+			}
+			if (next_ra > *ra_blk) {
+				xfs_dir3_data_readahead(dp, next_ra, -2);
+				*ra_blk = next_ra;
 			}
+			ra_want -= geo->fsbcount;
+			next_ra += geo->fsbcount;
+		}
+		if (!xfs_iext_get_extent(ifp, ++idx, &map)) {
+			*ra_blk = last_da;
+			break;
 		}
 	}
 	blk_finish_plug(&plug);
@@ -462,6 +344,9 @@ xfs_dir2_leaf_readbuf(
 out:
 	*bpp = bp;
 	return error;
+out_no_ra:
+	*ra_blk = last_da;
+	goto out;
 }
 
 /*
@@ -479,14 +364,14 @@ xfs_dir2_leaf_getdents(
 	xfs_dir2_data_hdr_t	*hdr;		/* data block header */
 	xfs_dir2_data_entry_t	*dep;		/* data entry */
 	xfs_dir2_data_unused_t	*dup;		/* unused entry */
-	int			error = 0;	/* error return value */
-	int			length;		/* temporary length value */
-	int			byteoff;	/* offset in current block */
-	xfs_dir2_off_t		curoff;		/* current overall offset */
-	xfs_dir2_off_t		newoff;		/* new curoff after new blk */
 	char			*ptr = NULL;	/* pointer to current data */
-	struct xfs_dir2_leaf_map_info *map_info;
 	struct xfs_da_geometry	*geo = args->geo;
+	xfs_dablk_t		rablk = 0;	/* current readahead block */
+	xfs_dir2_off_t		curoff;		/* current overall offset */
+	int			length;		/* temporary length value */
+	int			byteoff;	/* offset in current block */
+	int			lock_mode;
+	int			error = 0;	/* error return value */
 
 	/*
 	 * If the offset is at or past the largest allowed value,
@@ -496,73 +381,35 @@ xfs_dir2_leaf_getdents(
 		return 0;
 
 	/*
-	 * Set up to bmap a number of blocks based on the caller's
-	 * buffer size, the directory block size, and the filesystem
-	 * block size.
-	 */
-	length = howmany(bufsize + geo->blksize, (1 << geo->fsblog));
-	map_info = kmem_zalloc(offsetof(struct xfs_dir2_leaf_map_info, map) +
-				(length * sizeof(struct xfs_bmbt_irec)),
-			       KM_SLEEP | KM_NOFS);
-	map_info->map_size = length;
-
-	/*
 	 * Inside the loop we keep the main offset value as a byte offset
 	 * in the directory file.
 	 */
 	curoff = xfs_dir2_dataptr_to_byte(ctx->pos);
 
 	/*
-	 * Force this conversion through db so we truncate the offset
-	 * down to get the start of the data block.
-	 */
-	map_info->map_off = xfs_dir2_db_to_da(geo,
-					      xfs_dir2_byte_to_db(geo, curoff));
-
-	/*
 	 * Loop over directory entries until we reach the end offset.
 	 * Get more blocks and readahead as necessary.
 	 */
 	while (curoff < XFS_DIR2_LEAF_OFFSET) {
-		__uint8_t filetype;
+		uint8_t filetype;
 
 		/*
 		 * If we have no buffer, or we're off the end of the
 		 * current buffer, need to get another one.
 		 */
 		if (!bp || ptr >= (char *)bp->b_addr + geo->blksize) {
-			int	lock_mode;
-			bool	trim_map = false;
-
 			if (bp) {
-				xfs_trans_brelse(NULL, bp);
+				xfs_trans_brelse(args->trans, bp);
 				bp = NULL;
-				trim_map = true;
 			}
 
 			lock_mode = xfs_ilock_data_map_shared(dp);
-			error = xfs_dir2_leaf_readbuf(args, bufsize, map_info,
-						      &curoff, &bp, trim_map);
+			error = xfs_dir2_leaf_readbuf(args, bufsize, &curoff,
+					&rablk, &bp);
 			xfs_iunlock(dp, lock_mode);
-			if (error || !map_info->map_valid)
+			if (error || !bp)
 				break;
 
-			/*
-			 * Having done a read, we need to set a new offset.
-			 */
-			newoff = xfs_dir2_db_off_to_byte(geo,
-							 map_info->curdb, 0);
-			/*
-			 * Start of the current block.
-			 */
-			if (curoff < newoff)
-				curoff = newoff;
-			/*
-			 * Make sure we're in the right block.
-			 */
-			else if (curoff > newoff)
-				ASSERT(xfs_dir2_byte_to_db(geo, curoff) ==
-				       map_info->curdb);
 			hdr = bp->b_addr;
 			xfs_dir3_data_check(dp, bp);
 			/*
@@ -647,17 +494,22 @@ xfs_dir2_leaf_getdents(
 		ctx->pos = XFS_DIR2_MAX_DATAPTR & 0x7fffffff;
 	else
 		ctx->pos = xfs_dir2_byte_to_dataptr(curoff) & 0x7fffffff;
-	kmem_free(map_info);
 	if (bp)
-		xfs_trans_brelse(NULL, bp);
+		xfs_trans_brelse(args->trans, bp);
 	return error;
 }
 
 /*
  * Read a directory.
+ *
+ * If supplied, the transaction collects locked dir buffers to avoid
+ * nested buffer deadlocks.  This function does not dirty the
+ * transaction.  The caller should ensure that the inode is locked
+ * before calling this function.
  */
 int
 xfs_readdir(
+	struct xfs_trans	*tp,
 	struct xfs_inode	*dp,
 	struct dir_context	*ctx,
 	size_t			bufsize)
@@ -676,6 +528,7 @@ xfs_readdir(
 
 	args.dp = dp;
 	args.geo = dp->i_mount->m_dir_geo;
+	args.trans = tp;
 
 	if (dp->i_d.di_format == XFS_DINODE_FMT_LOCAL)
 		rval = xfs_dir2_sf_getdents(&args, ctx);
diff --git a/fs/xfs/xfs_discard.c b/fs/xfs/xfs_discard.c
index 4ff499aa7338..b2cde5426182 100644
--- a/fs/xfs/xfs_discard.c
+++ b/fs/xfs/xfs_discard.c
@@ -39,7 +39,7 @@ xfs_trim_extents(
 	xfs_daddr_t		start,
 	xfs_daddr_t		end,
 	xfs_daddr_t		minlen,
-	__uint64_t		*blocks_trimmed)
+	uint64_t		*blocks_trimmed)
 {
 	struct block_device	*bdev = mp->m_ddev_targp->bt_bdev;
 	struct xfs_btree_cur	*cur;
@@ -132,6 +132,11 @@ next_extent:
 		error = xfs_btree_decrement(cur, 0, &i);
 		if (error)
 			goto out_del_cursor;
+
+		if (fatal_signal_pending(current)) {
+			error = -ERESTARTSYS;
+			goto out_del_cursor;
+		}
 	}
 
 out_del_cursor:
@@ -161,7 +166,7 @@ xfs_ioc_trim(
 	struct fstrim_range	range;
 	xfs_daddr_t		start, end, minlen;
 	xfs_agnumber_t		start_agno, end_agno, agno;
-	__uint64_t		blocks_trimmed = 0;
+	uint64_t		blocks_trimmed = 0;
 	int			error, last_error = 0;
 
 	if (!capable(CAP_SYS_ADMIN))
@@ -196,8 +201,11 @@ xfs_ioc_trim(
 	for (agno = start_agno; agno <= end_agno; agno++) {
 		error = xfs_trim_extents(mp, agno, start, end, minlen,
 					  &blocks_trimmed);
-		if (error)
+		if (error) {
 			last_error = error;
+			if (error == -ERESTARTSYS)
+				break;
+		}
 	}
 
 	if (last_error)
@@ -208,32 +216,3 @@ xfs_ioc_trim(
 		return -EFAULT;
 	return 0;
 }
-
-int
-xfs_discard_extents(
-	struct xfs_mount	*mp,
-	struct list_head	*list)
-{
-	struct xfs_extent_busy	*busyp;
-	int			error = 0;
-
-	list_for_each_entry(busyp, list, list) {
-		trace_xfs_discard_extent(mp, busyp->agno, busyp->bno,
-					 busyp->length);
-
-		error = blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
-				XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
-				XFS_FSB_TO_BB(mp, busyp->length),
-				GFP_NOFS, 0);
-		if (error && error != -EOPNOTSUPP) {
-			xfs_info(mp,
-	 "discard failed for extent [0x%llx,%u], error %d",
-				 (unsigned long long)busyp->bno,
-				 busyp->length,
-				 error);
-			return error;
-		}
-	}
-
-	return 0;
-}
diff --git a/fs/xfs/xfs_discard.h b/fs/xfs/xfs_discard.h
index 344879aea646..0f070f9e44e1 100644
--- a/fs/xfs/xfs_discard.h
+++ b/fs/xfs/xfs_discard.h
@@ -5,6 +5,5 @@ struct fstrim_range;
 struct list_head;
 
 extern int	xfs_ioc_trim(struct xfs_mount *, struct fstrim_range __user *);
-extern int	xfs_discard_extents(struct xfs_mount *, struct list_head *);
 
 #endif /* XFS_DISCARD_H */
diff --git a/fs/xfs/xfs_dquot.c b/fs/xfs/xfs_dquot.c
index 9d06cc30e875..fd2ef8c2c9a7 100644
--- a/fs/xfs/xfs_dquot.c
+++ b/fs/xfs/xfs_dquot.c
@@ -276,7 +276,7 @@ xfs_qm_init_dquot_blk(
 void
 xfs_dquot_set_prealloc_limits(struct xfs_dquot *dqp)
 {
-	__uint64_t space;
+	uint64_t space;
 
 	dqp->q_prealloc_hi_wmark = be64_to_cpu(dqp->q_core.d_blk_hardlimit);
 	dqp->q_prealloc_lo_wmark = be64_to_cpu(dqp->q_core.d_blk_softlimit);
@@ -695,21 +695,18 @@ error0:
  */
 static int
 xfs_dq_get_next_id(
-	xfs_mount_t		*mp,
+	struct xfs_mount	*mp,
 	uint			type,
-	xfs_dqid_t		*id,
-	loff_t			eof)
+	xfs_dqid_t		*id)
 {
-	struct xfs_inode	*quotip;
+	struct xfs_inode	*quotip = xfs_quota_inode(mp, type);
+	xfs_dqid_t		next_id = *id + 1; /* simple advance */
+	uint			lock_flags;
+	struct xfs_bmbt_irec	got;
+	xfs_extnum_t		idx;
 	xfs_fsblock_t		start;
-	loff_t			offset;
-	uint			lock;
-	xfs_dqid_t		next_id;
 	int			error = 0;
 
-	/* Simple advance */
-	next_id = *id + 1;
-
 	/* If we'd wrap past the max ID, stop */
 	if (next_id < *id)
 		return -ENOENT;
@@ -723,23 +720,25 @@ xfs_dq_get_next_id(
 	/* Nope, next_id is now past the current chunk, so find the next one */
 	start = (xfs_fsblock_t)next_id / mp->m_quotainfo->qi_dqperchunk;
 
-	quotip = xfs_quota_inode(mp, type);
-	lock = xfs_ilock_data_map_shared(quotip);
-
-	offset = __xfs_seek_hole_data(VFS_I(quotip), XFS_FSB_TO_B(mp, start),
-				      eof, SEEK_DATA);
-	if (offset < 0)
-		error = offset;
+	lock_flags = xfs_ilock_data_map_shared(quotip);
+	if (!(quotip->i_df.if_flags & XFS_IFEXTENTS)) {
+		error = xfs_iread_extents(NULL, quotip, XFS_DATA_FORK);
+		if (error)
+			return error;
+	}
 
-	xfs_iunlock(quotip, lock);
+	if (xfs_iext_lookup_extent(quotip, &quotip->i_df, start, &idx, &got)) {
+		/* contiguous chunk, bump startoff for the id calculation */
+		if (got.br_startoff < start)
+			got.br_startoff = start;
+		*id = got.br_startoff * mp->m_quotainfo->qi_dqperchunk;
+	} else {
+		error = -ENOENT;
+	}
 
-	/* -ENXIO is essentially "no more data" */
-	if (error)
-		return (error == -ENXIO ? -ENOENT: error);
+	xfs_iunlock(quotip, lock_flags);
 
-	/* Convert next data offset back to a quota id */
-	*id = XFS_B_TO_FSB(mp, offset) * mp->m_quotainfo->qi_dqperchunk;
-	return 0;
+	return error;
 }
 
 /*
@@ -762,7 +761,6 @@ xfs_qm_dqget(
 	struct xfs_quotainfo	*qi = mp->m_quotainfo;
 	struct radix_tree_root *tree = xfs_dquot_tree(qi, type);
 	struct xfs_dquot	*dqp;
-	loff_t			eof = 0;
 	int			error;
 
 	ASSERT(XFS_IS_QUOTA_RUNNING(mp));
@@ -790,21 +788,6 @@ xfs_qm_dqget(
 	}
 #endif
 
-	/* Get the end of the quota file if we need it */
-	if (flags & XFS_QMOPT_DQNEXT) {
-		struct xfs_inode	*quotip;
-		xfs_fileoff_t		last;
-		uint			lock_mode;
-
-		quotip = xfs_quota_inode(mp, type);
-		lock_mode = xfs_ilock_data_map_shared(quotip);
-		error = xfs_bmap_last_offset(quotip, &last, XFS_DATA_FORK);
-		xfs_iunlock(quotip, lock_mode);
-		if (error)
-			return error;
-		eof = XFS_FSB_TO_B(mp, last);
-	}
-
 restart:
 	mutex_lock(&qi->qi_tree_lock);
 	dqp = radix_tree_lookup(tree, id);
@@ -823,7 +806,7 @@ restart:
 			if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
 				xfs_dqunlock(dqp);
 				mutex_unlock(&qi->qi_tree_lock);
-				error = xfs_dq_get_next_id(mp, type, &id, eof);
+				error = xfs_dq_get_next_id(mp, type, &id);
 				if (error)
 					return error;
 				goto restart;
@@ -858,7 +841,7 @@ restart:
 
 	/* If we are asked to find next active id, keep looking */
 	if (error == -ENOENT && (flags & XFS_QMOPT_DQNEXT)) {
-		error = xfs_dq_get_next_id(mp, type, &id, eof);
+		error = xfs_dq_get_next_id(mp, type, &id);
 		if (!error)
 			goto restart;
 	}
@@ -917,7 +900,7 @@ restart:
 	if (flags & XFS_QMOPT_DQNEXT) {
 		if (XFS_IS_DQUOT_UNINITIALIZED(dqp)) {
 			xfs_qm_dqput(dqp);
-			error = xfs_dq_get_next_id(mp, type, &id, eof);
+			error = xfs_dq_get_next_id(mp, type, &id);
 			if (error)
 				return error;
 			goto restart;
diff --git a/fs/xfs/xfs_error.c b/fs/xfs/xfs_error.c
index ed7ee4e8af73..2f4feb959bfb 100644
--- a/fs/xfs/xfs_error.c
+++ b/fs/xfs/xfs_error.c
@@ -22,103 +22,280 @@
 #include "xfs_trans_resv.h"
 #include "xfs_mount.h"
 #include "xfs_error.h"
+#include "xfs_sysfs.h"
 
 #ifdef DEBUG
 
-int	xfs_etest[XFS_NUM_INJECT_ERROR];
-int64_t	xfs_etest_fsid[XFS_NUM_INJECT_ERROR];
-char *	xfs_etest_fsname[XFS_NUM_INJECT_ERROR];
-int	xfs_error_test_active;
+static unsigned int xfs_errortag_random_default[] = {
+	XFS_RANDOM_DEFAULT,
+	XFS_RANDOM_IFLUSH_1,
+	XFS_RANDOM_IFLUSH_2,
+	XFS_RANDOM_IFLUSH_3,
+	XFS_RANDOM_IFLUSH_4,
+	XFS_RANDOM_IFLUSH_5,
+	XFS_RANDOM_IFLUSH_6,
+	XFS_RANDOM_DA_READ_BUF,
+	XFS_RANDOM_BTREE_CHECK_LBLOCK,
+	XFS_RANDOM_BTREE_CHECK_SBLOCK,
+	XFS_RANDOM_ALLOC_READ_AGF,
+	XFS_RANDOM_IALLOC_READ_AGI,
+	XFS_RANDOM_ITOBP_INOTOBP,
+	XFS_RANDOM_IUNLINK,
+	XFS_RANDOM_IUNLINK_REMOVE,
+	XFS_RANDOM_DIR_INO_VALIDATE,
+	XFS_RANDOM_BULKSTAT_READ_CHUNK,
+	XFS_RANDOM_IODONE_IOERR,
+	XFS_RANDOM_STRATREAD_IOERR,
+	XFS_RANDOM_STRATCMPL_IOERR,
+	XFS_RANDOM_DIOWRITE_IOERR,
+	XFS_RANDOM_BMAPIFORMAT,
+	XFS_RANDOM_FREE_EXTENT,
+	XFS_RANDOM_RMAP_FINISH_ONE,
+	XFS_RANDOM_REFCOUNT_CONTINUE_UPDATE,
+	XFS_RANDOM_REFCOUNT_FINISH_ONE,
+	XFS_RANDOM_BMAP_FINISH_ONE,
+	XFS_RANDOM_AG_RESV_CRITICAL,
+	XFS_RANDOM_DROP_WRITES,
+	XFS_RANDOM_LOG_BAD_CRC,
+};
 
-int
-xfs_error_test(int error_tag, int *fsidp, char *expression,
-	       int line, char *file, unsigned long randfactor)
+struct xfs_errortag_attr {
+	struct attribute	attr;
+	unsigned int		tag;
+};
+
+static inline struct xfs_errortag_attr *
+to_attr(struct attribute *attr)
 {
-	int i;
-	int64_t fsid;
+	return container_of(attr, struct xfs_errortag_attr, attr);
+}
 
-	if (prandom_u32() % randfactor)
-		return 0;
+static inline struct xfs_mount *
+to_mp(struct kobject *kobject)
+{
+	struct xfs_kobj *kobj = to_kobj(kobject);
 
-	memcpy(&fsid, fsidp, sizeof(xfs_fsid_t));
+	return container_of(kobj, struct xfs_mount, m_errortag_kobj);
+}
+
+STATIC ssize_t
+xfs_errortag_attr_store(
+	struct kobject		*kobject,
+	struct attribute	*attr,
+	const char		*buf,
+	size_t			count)
+{
+	struct xfs_mount	*mp = to_mp(kobject);
+	struct xfs_errortag_attr *xfs_attr = to_attr(attr);
+	int			ret;
+	unsigned int		val;
 
-	for (i = 0; i < XFS_NUM_INJECT_ERROR; i++)  {
-		if (xfs_etest[i] == error_tag && xfs_etest_fsid[i] == fsid) {
-			xfs_warn(NULL,
-	"Injecting error (%s) at file %s, line %d, on filesystem \"%s\"",
-				expression, file, line, xfs_etest_fsname[i]);
-			return 1;
-		}
+	if (strcmp(buf, "default") == 0) {
+		val = xfs_errortag_random_default[xfs_attr->tag];
+	} else {
+		ret = kstrtouint(buf, 0, &val);
+		if (ret)
+			return ret;
 	}
 
-	return 0;
+	ret = xfs_errortag_set(mp, xfs_attr->tag, val);
+	if (ret)
+		return ret;
+	return count;
 }
 
+STATIC ssize_t
+xfs_errortag_attr_show(
+	struct kobject		*kobject,
+	struct attribute	*attr,
+	char			*buf)
+{
+	struct xfs_mount	*mp = to_mp(kobject);
+	struct xfs_errortag_attr *xfs_attr = to_attr(attr);
+
+	return snprintf(buf, PAGE_SIZE, "%u\n",
+			xfs_errortag_get(mp, xfs_attr->tag));
+}
+
+static const struct sysfs_ops xfs_errortag_sysfs_ops = {
+	.show = xfs_errortag_attr_show,
+	.store = xfs_errortag_attr_store,
+};
+
+#define XFS_ERRORTAG_ATTR_RW(_name, _tag) \
+static struct xfs_errortag_attr xfs_errortag_attr_##_name = {		\
+	.attr = {.name = __stringify(_name),				\
+		 .mode = VERIFY_OCTAL_PERMISSIONS(S_IWUSR | S_IRUGO) },	\
+	.tag	= (_tag),						\
+}
+
+#define XFS_ERRORTAG_ATTR_LIST(_name) &xfs_errortag_attr_##_name.attr
+
+XFS_ERRORTAG_ATTR_RW(noerror,		XFS_ERRTAG_NOERROR);
+XFS_ERRORTAG_ATTR_RW(iflush1,		XFS_ERRTAG_IFLUSH_1);
+XFS_ERRORTAG_ATTR_RW(iflush2,		XFS_ERRTAG_IFLUSH_2);
+XFS_ERRORTAG_ATTR_RW(iflush3,		XFS_ERRTAG_IFLUSH_3);
+XFS_ERRORTAG_ATTR_RW(iflush4,		XFS_ERRTAG_IFLUSH_4);
+XFS_ERRORTAG_ATTR_RW(iflush5,		XFS_ERRTAG_IFLUSH_5);
+XFS_ERRORTAG_ATTR_RW(iflush6,		XFS_ERRTAG_IFLUSH_6);
+XFS_ERRORTAG_ATTR_RW(dareadbuf,		XFS_ERRTAG_DA_READ_BUF);
+XFS_ERRORTAG_ATTR_RW(btree_chk_lblk,	XFS_ERRTAG_BTREE_CHECK_LBLOCK);
+XFS_ERRORTAG_ATTR_RW(btree_chk_sblk,	XFS_ERRTAG_BTREE_CHECK_SBLOCK);
+XFS_ERRORTAG_ATTR_RW(readagf,		XFS_ERRTAG_ALLOC_READ_AGF);
+XFS_ERRORTAG_ATTR_RW(readagi,		XFS_ERRTAG_IALLOC_READ_AGI);
+XFS_ERRORTAG_ATTR_RW(itobp,		XFS_ERRTAG_ITOBP_INOTOBP);
+XFS_ERRORTAG_ATTR_RW(iunlink,		XFS_ERRTAG_IUNLINK);
+XFS_ERRORTAG_ATTR_RW(iunlinkrm,		XFS_ERRTAG_IUNLINK_REMOVE);
+XFS_ERRORTAG_ATTR_RW(dirinovalid,	XFS_ERRTAG_DIR_INO_VALIDATE);
+XFS_ERRORTAG_ATTR_RW(bulkstat,		XFS_ERRTAG_BULKSTAT_READ_CHUNK);
+XFS_ERRORTAG_ATTR_RW(logiodone,		XFS_ERRTAG_IODONE_IOERR);
+XFS_ERRORTAG_ATTR_RW(stratread,		XFS_ERRTAG_STRATREAD_IOERR);
+XFS_ERRORTAG_ATTR_RW(stratcmpl,		XFS_ERRTAG_STRATCMPL_IOERR);
+XFS_ERRORTAG_ATTR_RW(diowrite,		XFS_ERRTAG_DIOWRITE_IOERR);
+XFS_ERRORTAG_ATTR_RW(bmapifmt,		XFS_ERRTAG_BMAPIFORMAT);
+XFS_ERRORTAG_ATTR_RW(free_extent,	XFS_ERRTAG_FREE_EXTENT);
+XFS_ERRORTAG_ATTR_RW(rmap_finish_one,	XFS_ERRTAG_RMAP_FINISH_ONE);
+XFS_ERRORTAG_ATTR_RW(refcount_continue_update,	XFS_ERRTAG_REFCOUNT_CONTINUE_UPDATE);
+XFS_ERRORTAG_ATTR_RW(refcount_finish_one,	XFS_ERRTAG_REFCOUNT_FINISH_ONE);
+XFS_ERRORTAG_ATTR_RW(bmap_finish_one,	XFS_ERRTAG_BMAP_FINISH_ONE);
+XFS_ERRORTAG_ATTR_RW(ag_resv_critical,	XFS_ERRTAG_AG_RESV_CRITICAL);
+XFS_ERRORTAG_ATTR_RW(drop_writes,	XFS_ERRTAG_DROP_WRITES);
+XFS_ERRORTAG_ATTR_RW(log_bad_crc,	XFS_ERRTAG_LOG_BAD_CRC);
+
+static struct attribute *xfs_errortag_attrs[] = {
+	XFS_ERRORTAG_ATTR_LIST(noerror),
+	XFS_ERRORTAG_ATTR_LIST(iflush1),
+	XFS_ERRORTAG_ATTR_LIST(iflush2),
+	XFS_ERRORTAG_ATTR_LIST(iflush3),
+	XFS_ERRORTAG_ATTR_LIST(iflush4),
+	XFS_ERRORTAG_ATTR_LIST(iflush5),
+	XFS_ERRORTAG_ATTR_LIST(iflush6),
+	XFS_ERRORTAG_ATTR_LIST(dareadbuf),
+	XFS_ERRORTAG_ATTR_LIST(btree_chk_lblk),
+	XFS_ERRORTAG_ATTR_LIST(btree_chk_sblk),
+	XFS_ERRORTAG_ATTR_LIST(readagf),
+	XFS_ERRORTAG_ATTR_LIST(readagi),
+	XFS_ERRORTAG_ATTR_LIST(itobp),
+	XFS_ERRORTAG_ATTR_LIST(iunlink),
+	XFS_ERRORTAG_ATTR_LIST(iunlinkrm),
+	XFS_ERRORTAG_ATTR_LIST(dirinovalid),
+	XFS_ERRORTAG_ATTR_LIST(bulkstat),
+	XFS_ERRORTAG_ATTR_LIST(logiodone),
+	XFS_ERRORTAG_ATTR_LIST(stratread),
+	XFS_ERRORTAG_ATTR_LIST(stratcmpl),
+	XFS_ERRORTAG_ATTR_LIST(diowrite),
+	XFS_ERRORTAG_ATTR_LIST(bmapifmt),
+	XFS_ERRORTAG_ATTR_LIST(free_extent),
+	XFS_ERRORTAG_ATTR_LIST(rmap_finish_one),
+	XFS_ERRORTAG_ATTR_LIST(refcount_continue_update),
+	XFS_ERRORTAG_ATTR_LIST(refcount_finish_one),
+	XFS_ERRORTAG_ATTR_LIST(bmap_finish_one),
+	XFS_ERRORTAG_ATTR_LIST(ag_resv_critical),
+	XFS_ERRORTAG_ATTR_LIST(drop_writes),
+	XFS_ERRORTAG_ATTR_LIST(log_bad_crc),
+	NULL,
+};
+
+struct kobj_type xfs_errortag_ktype = {
+	.release = xfs_sysfs_release,
+	.sysfs_ops = &xfs_errortag_sysfs_ops,
+	.default_attrs = xfs_errortag_attrs,
+};
+
 int
-xfs_errortag_add(unsigned int error_tag, xfs_mount_t *mp)
+xfs_errortag_init(
+	struct xfs_mount	*mp)
 {
-	int i;
-	int len;
-	int64_t fsid;
+	mp->m_errortag = kmem_zalloc(sizeof(unsigned int) * XFS_ERRTAG_MAX,
+			KM_SLEEP | KM_MAYFAIL);
+	if (!mp->m_errortag)
+		return -ENOMEM;
 
-	if (error_tag >= XFS_ERRTAG_MAX)
-		return -EINVAL;
+	return xfs_sysfs_init(&mp->m_errortag_kobj, &xfs_errortag_ktype,
+			       &mp->m_kobj, "errortag");
+}
 
-	memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t));
+void
+xfs_errortag_del(
+	struct xfs_mount	*mp)
+{
+	xfs_sysfs_del(&mp->m_errortag_kobj);
+	kmem_free(mp->m_errortag);
+}
 
-	for (i = 0; i < XFS_NUM_INJECT_ERROR; i++)  {
-		if (xfs_etest_fsid[i] == fsid && xfs_etest[i] == error_tag) {
-			xfs_warn(mp, "error tag #%d on", error_tag);
-			return 0;
-		}
-	}
+bool
+xfs_errortag_test(
+	struct xfs_mount	*mp,
+	const char		*expression,
+	const char		*file,
+	int			line,
+	unsigned int		error_tag)
+{
+	unsigned int		randfactor;
 
-	for (i = 0; i < XFS_NUM_INJECT_ERROR; i++)  {
-		if (xfs_etest[i] == 0) {
-			xfs_warn(mp, "Turned on XFS error tag #%d",
-				error_tag);
-			xfs_etest[i] = error_tag;
-			xfs_etest_fsid[i] = fsid;
-			len = strlen(mp->m_fsname);
-			xfs_etest_fsname[i] = kmem_alloc(len + 1, KM_SLEEP);
-			strcpy(xfs_etest_fsname[i], mp->m_fsname);
-			xfs_error_test_active++;
-			return 0;
-		}
-	}
+	/*
+	 * To be able to use error injection anywhere, we need to ensure error
+	 * injection mechanism is already initialized.
+	 *
+	 * Code paths like I/O completion can be called before the
+	 * initialization is complete, but be able to inject errors in such
+	 * places is still useful.
+	 */
+	if (!mp->m_errortag)
+		return false;
 
-	xfs_warn(mp, "error tag overflow, too many turned on");
+	ASSERT(error_tag < XFS_ERRTAG_MAX);
+	randfactor = mp->m_errortag[error_tag];
+	if (!randfactor || prandom_u32() % randfactor)
+		return false;
 
-	return 1;
+	xfs_warn_ratelimited(mp,
+"Injecting error (%s) at file %s, line %d, on filesystem \"%s\"",
+			expression, file, line, mp->m_fsname);
+	return true;
 }
 
 int
-xfs_errortag_clearall(xfs_mount_t *mp, int loud)
+xfs_errortag_get(
+	struct xfs_mount	*mp,
+	unsigned int		error_tag)
 {
-	int64_t fsid;
-	int cleared = 0;
-	int i;
-
-	memcpy(&fsid, mp->m_fixedfsid, sizeof(xfs_fsid_t));
-
-
-	for (i = 0; i < XFS_NUM_INJECT_ERROR; i++) {
-		if ((fsid == 0LL || xfs_etest_fsid[i] == fsid) &&
-		     xfs_etest[i] != 0) {
-			cleared = 1;
-			xfs_warn(mp, "Clearing XFS error tag #%d",
-				xfs_etest[i]);
-			xfs_etest[i] = 0;
-			xfs_etest_fsid[i] = 0LL;
-			kmem_free(xfs_etest_fsname[i]);
-			xfs_etest_fsname[i] = NULL;
-			xfs_error_test_active--;
-		}
-	}
+	if (error_tag >= XFS_ERRTAG_MAX)
+		return -EINVAL;
+
+	return mp->m_errortag[error_tag];
+}
+
+int
+xfs_errortag_set(
+	struct xfs_mount	*mp,
+	unsigned int		error_tag,
+	unsigned int		tag_value)
+{
+	if (error_tag >= XFS_ERRTAG_MAX)
+		return -EINVAL;
 
-	if (loud || cleared)
-		xfs_warn(mp, "Cleared all XFS error tags for filesystem");
+	mp->m_errortag[error_tag] = tag_value;
+	return 0;
+}
 
+int
+xfs_errortag_add(
+	struct xfs_mount	*mp,
+	unsigned int		error_tag)
+{
+	if (error_tag >= XFS_ERRTAG_MAX)
+		return -EINVAL;
+
+	return xfs_errortag_set(mp, error_tag,
+			xfs_errortag_random_default[error_tag]);
+}
+
+int
+xfs_errortag_clearall(
+	struct xfs_mount	*mp)
+{
+	memset(mp->m_errortag, 0, sizeof(unsigned int) * XFS_ERRTAG_MAX);
 	return 0;
 }
 #endif /* DEBUG */
diff --git a/fs/xfs/xfs_error.h b/fs/xfs/xfs_error.h
index 05f8666733a0..7577be5f09bc 100644
--- a/fs/xfs/xfs_error.h
+++ b/fs/xfs/xfs_error.h
@@ -96,7 +96,17 @@ extern void xfs_verifier_error(struct xfs_buf *bp);
 #define XFS_ERRTAG_REFCOUNT_FINISH_ONE			25
 #define XFS_ERRTAG_BMAP_FINISH_ONE			26
 #define XFS_ERRTAG_AG_RESV_CRITICAL			27
-#define XFS_ERRTAG_MAX					28
+/*
+ * DEBUG mode instrumentation to test and/or trigger delayed allocation
+ * block killing in the event of failed writes. When enabled, all
+ * buffered writes are silenty dropped and handled as if they failed.
+ * All delalloc blocks in the range of the write (including pre-existing
+ * delalloc blocks!) are tossed as part of the write failure error
+ * handling sequence.
+ */
+#define XFS_ERRTAG_DROP_WRITES				28
+#define XFS_ERRTAG_LOG_BAD_CRC				29
+#define XFS_ERRTAG_MAX					30
 
 /*
  * Random factors for above tags, 1 means always, 2 means 1/2 time, etc.
@@ -129,23 +139,29 @@ extern void xfs_verifier_error(struct xfs_buf *bp);
 #define XFS_RANDOM_REFCOUNT_FINISH_ONE			1
 #define XFS_RANDOM_BMAP_FINISH_ONE			1
 #define XFS_RANDOM_AG_RESV_CRITICAL			4
+#define XFS_RANDOM_DROP_WRITES				1
+#define XFS_RANDOM_LOG_BAD_CRC				1
 
 #ifdef DEBUG
-extern int xfs_error_test_active;
-extern int xfs_error_test(int, int *, char *, int, char *, unsigned long);
-
-#define	XFS_NUM_INJECT_ERROR				10
-#define XFS_TEST_ERROR(expr, mp, tag, rf)		\
-	((expr) || (xfs_error_test_active && \
-	 xfs_error_test((tag), (mp)->m_fixedfsid, "expr", __LINE__, __FILE__, \
-			(rf))))
+extern int xfs_errortag_init(struct xfs_mount *mp);
+extern void xfs_errortag_del(struct xfs_mount *mp);
+extern bool xfs_errortag_test(struct xfs_mount *mp, const char *expression,
+		const char *file, int line, unsigned int error_tag);
+#define XFS_TEST_ERROR(expr, mp, tag)		\
+	((expr) || xfs_errortag_test((mp), #expr, __FILE__, __LINE__, (tag)))
 
-extern int xfs_errortag_add(unsigned int error_tag, struct xfs_mount *mp);
-extern int xfs_errortag_clearall(struct xfs_mount *mp, int loud);
+extern int xfs_errortag_get(struct xfs_mount *mp, unsigned int error_tag);
+extern int xfs_errortag_set(struct xfs_mount *mp, unsigned int error_tag,
+		unsigned int tag_value);
+extern int xfs_errortag_add(struct xfs_mount *mp, unsigned int error_tag);
+extern int xfs_errortag_clearall(struct xfs_mount *mp);
 #else
-#define XFS_TEST_ERROR(expr, mp, tag, rf)	(expr)
-#define xfs_errortag_add(tag, mp)		(ENOSYS)
-#define xfs_errortag_clearall(mp, loud)		(ENOSYS)
+#define xfs_errortag_init(mp)			(0)
+#define xfs_errortag_del(mp)
+#define XFS_TEST_ERROR(expr, mp, tag)		(expr)
+#define xfs_errortag_set(mp, tag, val)		(ENOSYS)
+#define xfs_errortag_add(mp, tag)		(ENOSYS)
+#define xfs_errortag_clearall(mp)		(ENOSYS)
 #endif /* DEBUG */
 
 /*
diff --git a/fs/xfs/xfs_extent_busy.c b/fs/xfs/xfs_extent_busy.c
index 162dc186cf04..77760dbf0242 100644
--- a/fs/xfs/xfs_extent_busy.c
+++ b/fs/xfs/xfs_extent_busy.c
@@ -45,18 +45,7 @@ xfs_extent_busy_insert(
 	struct rb_node		**rbp;
 	struct rb_node		*parent = NULL;
 
-	new = kmem_zalloc(sizeof(struct xfs_extent_busy), KM_MAYFAIL);
-	if (!new) {
-		/*
-		 * No Memory!  Since it is now not possible to track the free
-		 * block, make this a synchronous transaction to insure that
-		 * the block is not reused before this transaction commits.
-		 */
-		trace_xfs_extent_busy_enomem(tp->t_mountp, agno, bno, len);
-		xfs_trans_set_sync(tp);
-		return;
-	}
-
+	new = kmem_zalloc(sizeof(struct xfs_extent_busy), KM_SLEEP);
 	new->agno = agno;
 	new->bno = bno;
 	new->length = len;
@@ -345,25 +334,31 @@ restart:
  * subset of the extent that is not busy.  If *rlen is smaller than
  * args->minlen no suitable extent could be found, and the higher level
  * code needs to force out the log and retry the allocation.
+ *
+ * Return the current busy generation for the AG if the extent is busy. This
+ * value can be used to wait for at least one of the currently busy extents
+ * to be cleared. Note that the busy list is not guaranteed to be empty after
+ * the gen is woken. The state of a specific extent must always be confirmed
+ * with another call to xfs_extent_busy_trim() before it can be used.
  */
-void
+bool
 xfs_extent_busy_trim(
 	struct xfs_alloc_arg	*args,
-	xfs_agblock_t		bno,
-	xfs_extlen_t		len,
-	xfs_agblock_t		*rbno,
-	xfs_extlen_t		*rlen)
+	xfs_agblock_t		*bno,
+	xfs_extlen_t		*len,
+	unsigned		*busy_gen)
 {
 	xfs_agblock_t		fbno;
 	xfs_extlen_t		flen;
 	struct rb_node		*rbp;
+	bool			ret = false;
 
-	ASSERT(len > 0);
+	ASSERT(*len > 0);
 
 	spin_lock(&args->pag->pagb_lock);
 restart:
-	fbno = bno;
-	flen = len;
+	fbno = *bno;
+	flen = *len;
 	rbp = args->pag->pagb_tree.rb_node;
 	while (rbp && flen >= args->minlen) {
 		struct xfs_extent_busy *busyp =
@@ -515,24 +510,25 @@ restart:
 
 		flen = fend - fbno;
 	}
-	spin_unlock(&args->pag->pagb_lock);
+out:
 
-	if (fbno != bno || flen != len) {
-		trace_xfs_extent_busy_trim(args->mp, args->agno, bno, len,
+	if (fbno != *bno || flen != *len) {
+		trace_xfs_extent_busy_trim(args->mp, args->agno, *bno, *len,
 					  fbno, flen);
+		*bno = fbno;
+		*len = flen;
+		*busy_gen = args->pag->pagb_gen;
+		ret = true;
 	}
-	*rbno = fbno;
-	*rlen = flen;
-	return;
+	spin_unlock(&args->pag->pagb_lock);
+	return ret;
 fail:
 	/*
 	 * Return a zero extent length as failure indications.  All callers
 	 * re-check if the trimmed extent satisfies the minlen requirement.
 	 */
-	spin_unlock(&args->pag->pagb_lock);
-	trace_xfs_extent_busy_trim(args->mp, args->agno, bno, len, fbno, 0);
-	*rbno = fbno;
-	*rlen = 0;
+	flen = 0;
+	goto out;
 }
 
 STATIC void
@@ -551,6 +547,21 @@ xfs_extent_busy_clear_one(
 	kmem_free(busyp);
 }
 
+static void
+xfs_extent_busy_put_pag(
+	struct xfs_perag	*pag,
+	bool			wakeup)
+		__releases(pag->pagb_lock)
+{
+	if (wakeup) {
+		pag->pagb_gen++;
+		wake_up_all(&pag->pagb_wait);
+	}
+
+	spin_unlock(&pag->pagb_lock);
+	xfs_perag_put(pag);
+}
+
 /*
  * Remove all extents on the passed in list from the busy extents tree.
  * If do_discard is set skip extents that need to be discarded, and mark
@@ -565,27 +576,76 @@ xfs_extent_busy_clear(
 	struct xfs_extent_busy	*busyp, *n;
 	struct xfs_perag	*pag = NULL;
 	xfs_agnumber_t		agno = NULLAGNUMBER;
+	bool			wakeup = false;
 
 	list_for_each_entry_safe(busyp, n, list, list) {
 		if (busyp->agno != agno) {
-			if (pag) {
-				spin_unlock(&pag->pagb_lock);
-				xfs_perag_put(pag);
-			}
-			pag = xfs_perag_get(mp, busyp->agno);
-			spin_lock(&pag->pagb_lock);
+			if (pag)
+				xfs_extent_busy_put_pag(pag, wakeup);
 			agno = busyp->agno;
+			pag = xfs_perag_get(mp, agno);
+			spin_lock(&pag->pagb_lock);
+			wakeup = false;
 		}
 
 		if (do_discard && busyp->length &&
-		    !(busyp->flags & XFS_EXTENT_BUSY_SKIP_DISCARD))
+		    !(busyp->flags & XFS_EXTENT_BUSY_SKIP_DISCARD)) {
 			busyp->flags = XFS_EXTENT_BUSY_DISCARDED;
-		else
+		} else {
 			xfs_extent_busy_clear_one(mp, pag, busyp);
+			wakeup = true;
+		}
 	}
 
-	if (pag) {
-		spin_unlock(&pag->pagb_lock);
+	if (pag)
+		xfs_extent_busy_put_pag(pag, wakeup);
+}
+
+/*
+ * Flush out all busy extents for this AG.
+ */
+void
+xfs_extent_busy_flush(
+	struct xfs_mount	*mp,
+	struct xfs_perag	*pag,
+	unsigned		busy_gen)
+{
+	DEFINE_WAIT		(wait);
+	int			log_flushed = 0, error;
+
+	trace_xfs_log_force(mp, 0, _THIS_IP_);
+	error = _xfs_log_force(mp, XFS_LOG_SYNC, &log_flushed);
+	if (error)
+		return;
+
+	do {
+		prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE);
+		if  (busy_gen != READ_ONCE(pag->pagb_gen))
+			break;
+		schedule();
+	} while (1);
+
+	finish_wait(&pag->pagb_wait, &wait);
+}
+
+void
+xfs_extent_busy_wait_all(
+	struct xfs_mount	*mp)
+{
+	DEFINE_WAIT		(wait);
+	xfs_agnumber_t		agno;
+
+	for (agno = 0; agno < mp->m_sb.sb_agcount; agno++) {
+		struct xfs_perag *pag = xfs_perag_get(mp, agno);
+
+		do {
+			prepare_to_wait(&pag->pagb_wait, &wait, TASK_KILLABLE);
+			if  (RB_EMPTY_ROOT(&pag->pagb_tree))
+				break;
+			schedule();
+		} while (1);
+		finish_wait(&pag->pagb_wait, &wait);
+
 		xfs_perag_put(pag);
 	}
 }
@@ -596,9 +656,17 @@ xfs_extent_busy_clear(
 int
 xfs_extent_busy_ag_cmp(
 	void			*priv,
-	struct list_head	*a,
-	struct list_head	*b)
+	struct list_head	*l1,
+	struct list_head	*l2)
 {
-	return container_of(a, struct xfs_extent_busy, list)->agno -
-		container_of(b, struct xfs_extent_busy, list)->agno;
+	struct xfs_extent_busy	*b1 =
+		container_of(l1, struct xfs_extent_busy, list);
+	struct xfs_extent_busy	*b2 =
+		container_of(l2, struct xfs_extent_busy, list);
+	s32 diff;
+
+	diff = b1->agno - b2->agno;
+	if (!diff)
+		diff = b1->bno - b2->bno;
+	return diff;
 }
diff --git a/fs/xfs/xfs_extent_busy.h b/fs/xfs/xfs_extent_busy.h
index bfff284d2dcc..60195ea1b84a 100644
--- a/fs/xfs/xfs_extent_busy.h
+++ b/fs/xfs/xfs_extent_busy.h
@@ -58,9 +58,16 @@ void
 xfs_extent_busy_reuse(struct xfs_mount *mp, xfs_agnumber_t agno,
 	xfs_agblock_t fbno, xfs_extlen_t flen, bool userdata);
 
+bool
+xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t *bno,
+		xfs_extlen_t *len, unsigned *busy_gen);
+
+void
+xfs_extent_busy_flush(struct xfs_mount *mp, struct xfs_perag *pag,
+	unsigned busy_gen);
+
 void
-xfs_extent_busy_trim(struct xfs_alloc_arg *args, xfs_agblock_t bno,
-	xfs_extlen_t len, xfs_agblock_t *rbno, xfs_extlen_t *rlen);
+xfs_extent_busy_wait_all(struct xfs_mount *mp);
 
 int
 xfs_extent_busy_ag_cmp(void *priv, struct list_head *a, struct list_head *b);
diff --git a/fs/xfs/xfs_extfree_item.c b/fs/xfs/xfs_extfree_item.c
index d7bc14906af8..44f8c5451210 100644
--- a/fs/xfs/xfs_extfree_item.c
+++ b/fs/xfs/xfs_extfree_item.c
@@ -290,6 +290,7 @@ void
 xfs_efi_release(
 	struct xfs_efi_log_item	*efip)
 {
+	ASSERT(atomic_read(&efip->efi_refcount) > 0);
 	if (atomic_dec_and_test(&efip->efi_refcount)) {
 		xfs_trans_ail_remove(&efip->efi_item, SHUTDOWN_LOG_IO_ERROR);
 		xfs_efi_item_free(efip);
diff --git a/fs/xfs/xfs_file.c b/fs/xfs/xfs_file.c
index bbb9eb6811b2..c4893e226fd8 100644
--- a/fs/xfs/xfs_file.c
+++ b/fs/xfs/xfs_file.c
@@ -140,7 +140,7 @@ xfs_file_fsync(
 
 	trace_xfs_file_fsync(ip);
 
-	error = filemap_write_and_wait_range(inode->i_mapping, start, end);
+	error = file_write_and_wait_range(file, start, end);
 	if (error)
 		return error;
 
@@ -237,7 +237,11 @@ xfs_file_dax_read(
 	if (!count)
 		return 0; /* skip atime */
 
-	xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_SHARED)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		xfs_ilock(ip, XFS_IOLOCK_SHARED);
+	}
 	ret = dax_iomap_rw(iocb, to, &xfs_iomap_ops);
 	xfs_iunlock(ip, XFS_IOLOCK_SHARED);
 
@@ -527,12 +531,25 @@ xfs_file_dio_aio_write(
 	if ((iocb->ki_pos & mp->m_blockmask) ||
 	    ((iocb->ki_pos + count) & mp->m_blockmask)) {
 		unaligned_io = 1;
+
+		/*
+		 * We can't properly handle unaligned direct I/O to reflink
+		 * files yet, as we can't unshare a partial block.
+		 */
+		if (xfs_is_reflink_inode(ip)) {
+			trace_xfs_reflink_bounce_dio_write(ip, iocb->ki_pos, count);
+			return -EREMCHG;
+		}
 		iolock = XFS_IOLOCK_EXCL;
 	} else {
 		iolock = XFS_IOLOCK_SHARED;
 	}
 
-	xfs_ilock(ip, iolock);
+	if (!xfs_ilock_nowait(ip, iolock)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		xfs_ilock(ip, iolock);
+	}
 
 	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
@@ -544,22 +561,20 @@ xfs_file_dio_aio_write(
 	 * otherwise demote the lock if we had to take the exclusive lock
 	 * for other reasons in xfs_file_aio_write_checks.
 	 */
-	if (unaligned_io)
-		inode_dio_wait(inode);
-	else if (iolock == XFS_IOLOCK_EXCL) {
+	if (unaligned_io) {
+		/* If we are going to wait for other DIO to finish, bail */
+		if (iocb->ki_flags & IOCB_NOWAIT) {
+			if (atomic_read(&inode->i_dio_count))
+				return -EAGAIN;
+		} else {
+			inode_dio_wait(inode);
+		}
+	} else if (iolock == XFS_IOLOCK_EXCL) {
 		xfs_ilock_demote(ip, XFS_IOLOCK_EXCL);
 		iolock = XFS_IOLOCK_SHARED;
 	}
 
 	trace_xfs_file_direct_write(ip, count, iocb->ki_pos);
-
-	/* If this is a block-aligned directio CoW, remap immediately. */
-	if (xfs_is_reflink_inode(ip) && !unaligned_io) {
-		ret = xfs_reflink_allocate_cow_range(ip, iocb->ki_pos, count);
-		if (ret)
-			goto out;
-	}
-
 	ret = iomap_dio_rw(iocb, from, &xfs_iomap_ops, xfs_dio_write_end_io);
 out:
 	xfs_iunlock(ip, iolock);
@@ -584,7 +599,12 @@ xfs_file_dax_write(
 	size_t			count;
 	loff_t			pos;
 
-	xfs_ilock(ip, iolock);
+	if (!xfs_ilock_nowait(ip, iolock)) {
+		if (iocb->ki_flags & IOCB_NOWAIT)
+			return -EAGAIN;
+		xfs_ilock(ip, iolock);
+	}
+
 	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
 	if (ret)
 		goto out;
@@ -614,8 +634,10 @@ xfs_file_buffered_aio_write(
 	struct xfs_inode	*ip = XFS_I(inode);
 	ssize_t			ret;
 	int			enospc = 0;
-	int			iolock = XFS_IOLOCK_EXCL;
+	int			iolock;
 
+write_retry:
+	iolock = XFS_IOLOCK_EXCL;
 	xfs_ilock(ip, iolock);
 
 	ret = xfs_file_aio_write_checks(iocb, from, &iolock);
@@ -625,7 +647,6 @@ xfs_file_buffered_aio_write(
 	/* We can write back this queue in page reclaim */
 	current->backing_dev_info = inode_to_bdi(inode);
 
-write_retry:
 	trace_xfs_file_buffered_write(ip, iov_iter_count(from), iocb->ki_pos);
 	ret = iomap_file_buffered_write(iocb, from, &xfs_iomap_ops);
 	if (likely(ret >= 0))
@@ -641,26 +662,31 @@ write_retry:
 	 * running at the same time.
 	 */
 	if (ret == -EDQUOT && !enospc) {
+		xfs_iunlock(ip, iolock);
 		enospc = xfs_inode_free_quota_eofblocks(ip);
 		if (enospc)
 			goto write_retry;
 		enospc = xfs_inode_free_quota_cowblocks(ip);
 		if (enospc)
 			goto write_retry;
+		iolock = 0;
 	} else if (ret == -ENOSPC && !enospc) {
 		struct xfs_eofblocks eofb = {0};
 
 		enospc = 1;
 		xfs_flush_inodes(ip->i_mount);
-		eofb.eof_scan_owner = ip->i_ino; /* for locking */
+
+		xfs_iunlock(ip, iolock);
 		eofb.eof_flags = XFS_EOF_FLAGS_SYNC;
 		xfs_icache_free_eofblocks(ip->i_mount, &eofb);
+		xfs_icache_free_cowblocks(ip->i_mount, &eofb);
 		goto write_retry;
 	}
 
 	current->backing_dev_info = NULL;
 out:
-	xfs_iunlock(ip, iolock);
+	if (iolock)
+		xfs_iunlock(ip, iolock);
 	return ret;
 }
 
@@ -748,7 +774,7 @@ xfs_file_fallocate(
 		if (error)
 			goto out_unlock;
 	} else if (mode & FALLOC_FL_COLLAPSE_RANGE) {
-		unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
+		unsigned int blksize_mask = i_blocksize(inode) - 1;
 
 		if (offset & blksize_mask || len & blksize_mask) {
 			error = -EINVAL;
@@ -770,7 +796,7 @@ xfs_file_fallocate(
 		if (error)
 			goto out_unlock;
 	} else if (mode & FALLOC_FL_INSERT_RANGE) {
-		unsigned blksize_mask = (1 << inode->i_blkbits) - 1;
+		unsigned int blksize_mask = i_blocksize(inode) - 1;
 
 		new_size = i_size_read(inode) + len;
 		if (offset & blksize_mask || len & blksize_mask) {
@@ -886,6 +912,7 @@ xfs_file_open(
 		return -EFBIG;
 	if (XFS_FORCED_SHUTDOWN(XFS_M(inode->i_sb)))
 		return -EIO;
+	file->f_mode |= FMODE_AIO_NOWAIT;
 	return 0;
 }
 
@@ -908,9 +935,9 @@ xfs_dir_open(
 	 */
 	mode = xfs_ilock_data_map_shared(ip);
 	if (ip->i_d.di_nextents > 0)
-		xfs_dir3_data_readahead(ip, 0, -1);
+		error = xfs_dir3_data_readahead(ip, 0, -1);
 	xfs_iunlock(ip, mode);
-	return 0;
+	return error;
 }
 
 STATIC int
@@ -944,395 +971,7 @@ xfs_file_readdir(
 	 */
 	bufsize = (size_t)min_t(loff_t, 32768, ip->i_d.di_size);
 
-	return xfs_readdir(ip, ctx, bufsize);
-}
-
-/*
- * This type is designed to indicate the type of offset we would like
- * to search from page cache for xfs_seek_hole_data().
- */
-enum {
-	HOLE_OFF = 0,
-	DATA_OFF,
-};
-
-/*
- * Lookup the desired type of offset from the given page.
- *
- * On success, return true and the offset argument will point to the
- * start of the region that was found.  Otherwise this function will
- * return false and keep the offset argument unchanged.
- */
-STATIC bool
-xfs_lookup_buffer_offset(
-	struct page		*page,
-	loff_t			*offset,
-	unsigned int		type)
-{
-	loff_t			lastoff = page_offset(page);
-	bool			found = false;
-	struct buffer_head	*bh, *head;
-
-	bh = head = page_buffers(page);
-	do {
-		/*
-		 * Unwritten extents that have data in the page
-		 * cache covering them can be identified by the
-		 * BH_Unwritten state flag.  Pages with multiple
-		 * buffers might have a mix of holes, data and
-		 * unwritten extents - any buffer with valid
-		 * data in it should have BH_Uptodate flag set
-		 * on it.
-		 */
-		if (buffer_unwritten(bh) ||
-		    buffer_uptodate(bh)) {
-			if (type == DATA_OFF)
-				found = true;
-		} else {
-			if (type == HOLE_OFF)
-				found = true;
-		}
-
-		if (found) {
-			*offset = lastoff;
-			break;
-		}
-		lastoff += bh->b_size;
-	} while ((bh = bh->b_this_page) != head);
-
-	return found;
-}
-
-/*
- * This routine is called to find out and return a data or hole offset
- * from the page cache for unwritten extents according to the desired
- * type for xfs_seek_hole_data().
- *
- * The argument offset is used to tell where we start to search from the
- * page cache.  Map is used to figure out the end points of the range to
- * lookup pages.
- *
- * Return true if the desired type of offset was found, and the argument
- * offset is filled with that address.  Otherwise, return false and keep
- * offset unchanged.
- */
-STATIC bool
-xfs_find_get_desired_pgoff(
-	struct inode		*inode,
-	struct xfs_bmbt_irec	*map,
-	unsigned int		type,
-	loff_t			*offset)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	struct pagevec		pvec;
-	pgoff_t			index;
-	pgoff_t			end;
-	loff_t			endoff;
-	loff_t			startoff = *offset;
-	loff_t			lastoff = startoff;
-	bool			found = false;
-
-	pagevec_init(&pvec, 0);
-
-	index = startoff >> PAGE_SHIFT;
-	endoff = XFS_FSB_TO_B(mp, map->br_startoff + map->br_blockcount);
-	end = endoff >> PAGE_SHIFT;
-	do {
-		int		want;
-		unsigned	nr_pages;
-		unsigned int	i;
-
-		want = min_t(pgoff_t, end - index, PAGEVEC_SIZE);
-		nr_pages = pagevec_lookup(&pvec, inode->i_mapping, index,
-					  want);
-		/*
-		 * No page mapped into given range.  If we are searching holes
-		 * and if this is the first time we got into the loop, it means
-		 * that the given offset is landed in a hole, return it.
-		 *
-		 * If we have already stepped through some block buffers to find
-		 * holes but they all contains data.  In this case, the last
-		 * offset is already updated and pointed to the end of the last
-		 * mapped page, if it does not reach the endpoint to search,
-		 * that means there should be a hole between them.
-		 */
-		if (nr_pages == 0) {
-			/* Data search found nothing */
-			if (type == DATA_OFF)
-				break;
-
-			ASSERT(type == HOLE_OFF);
-			if (lastoff == startoff || lastoff < endoff) {
-				found = true;
-				*offset = lastoff;
-			}
-			break;
-		}
-
-		/*
-		 * At lease we found one page.  If this is the first time we
-		 * step into the loop, and if the first page index offset is
-		 * greater than the given search offset, a hole was found.
-		 */
-		if (type == HOLE_OFF && lastoff == startoff &&
-		    lastoff < page_offset(pvec.pages[0])) {
-			found = true;
-			break;
-		}
-
-		for (i = 0; i < nr_pages; i++) {
-			struct page	*page = pvec.pages[i];
-			loff_t		b_offset;
-
-			/*
-			 * At this point, the page may be truncated or
-			 * invalidated (changing page->mapping to NULL),
-			 * or even swizzled back from swapper_space to tmpfs
-			 * file mapping. However, page->index will not change
-			 * because we have a reference on the page.
-			 *
-			 * Searching done if the page index is out of range.
-			 * If the current offset is not reaches the end of
-			 * the specified search range, there should be a hole
-			 * between them.
-			 */
-			if (page->index > end) {
-				if (type == HOLE_OFF && lastoff < endoff) {
-					*offset = lastoff;
-					found = true;
-				}
-				goto out;
-			}
-
-			lock_page(page);
-			/*
-			 * Page truncated or invalidated(page->mapping == NULL).
-			 * We can freely skip it and proceed to check the next
-			 * page.
-			 */
-			if (unlikely(page->mapping != inode->i_mapping)) {
-				unlock_page(page);
-				continue;
-			}
-
-			if (!page_has_buffers(page)) {
-				unlock_page(page);
-				continue;
-			}
-
-			found = xfs_lookup_buffer_offset(page, &b_offset, type);
-			if (found) {
-				/*
-				 * The found offset may be less than the start
-				 * point to search if this is the first time to
-				 * come here.
-				 */
-				*offset = max_t(loff_t, startoff, b_offset);
-				unlock_page(page);
-				goto out;
-			}
-
-			/*
-			 * We either searching data but nothing was found, or
-			 * searching hole but found a data buffer.  In either
-			 * case, probably the next page contains the desired
-			 * things, update the last offset to it so.
-			 */
-			lastoff = page_offset(page) + PAGE_SIZE;
-			unlock_page(page);
-		}
-
-		/*
-		 * The number of returned pages less than our desired, search
-		 * done.  In this case, nothing was found for searching data,
-		 * but we found a hole behind the last offset.
-		 */
-		if (nr_pages < want) {
-			if (type == HOLE_OFF) {
-				*offset = lastoff;
-				found = true;
-			}
-			break;
-		}
-
-		index = pvec.pages[i - 1]->index + 1;
-		pagevec_release(&pvec);
-	} while (index <= end);
-
-out:
-	pagevec_release(&pvec);
-	return found;
-}
-
-/*
- * caller must lock inode with xfs_ilock_data_map_shared,
- * can we craft an appropriate ASSERT?
- *
- * end is because the VFS-level lseek interface is defined such that any
- * offset past i_size shall return -ENXIO, but we use this for quota code
- * which does not maintain i_size, and we want to SEEK_DATA past i_size.
- */
-loff_t
-__xfs_seek_hole_data(
-	struct inode		*inode,
-	loff_t			start,
-	loff_t			end,
-	int			whence)
-{
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	loff_t			uninitialized_var(offset);
-	xfs_fileoff_t		fsbno;
-	xfs_filblks_t		lastbno;
-	int			error;
-
-	if (start >= end) {
-		error = -ENXIO;
-		goto out_error;
-	}
-
-	/*
-	 * Try to read extents from the first block indicated
-	 * by fsbno to the end block of the file.
-	 */
-	fsbno = XFS_B_TO_FSBT(mp, start);
-	lastbno = XFS_B_TO_FSB(mp, end);
-
-	for (;;) {
-		struct xfs_bmbt_irec	map[2];
-		int			nmap = 2;
-		unsigned int		i;
-
-		error = xfs_bmapi_read(ip, fsbno, lastbno - fsbno, map, &nmap,
-				       XFS_BMAPI_ENTIRE);
-		if (error)
-			goto out_error;
-
-		/* No extents at given offset, must be beyond EOF */
-		if (nmap == 0) {
-			error = -ENXIO;
-			goto out_error;
-		}
-
-		for (i = 0; i < nmap; i++) {
-			offset = max_t(loff_t, start,
-				       XFS_FSB_TO_B(mp, map[i].br_startoff));
-
-			/* Landed in the hole we wanted? */
-			if (whence == SEEK_HOLE &&
-			    map[i].br_startblock == HOLESTARTBLOCK)
-				goto out;
-
-			/* Landed in the data extent we wanted? */
-			if (whence == SEEK_DATA &&
-			    (map[i].br_startblock == DELAYSTARTBLOCK ||
-			     (map[i].br_state == XFS_EXT_NORM &&
-			      !isnullstartblock(map[i].br_startblock))))
-				goto out;
-
-			/*
-			 * Landed in an unwritten extent, try to search
-			 * for hole or data from page cache.
-			 */
-			if (map[i].br_state == XFS_EXT_UNWRITTEN) {
-				if (xfs_find_get_desired_pgoff(inode, &map[i],
-				      whence == SEEK_HOLE ? HOLE_OFF : DATA_OFF,
-							&offset))
-					goto out;
-			}
-		}
-
-		/*
-		 * We only received one extent out of the two requested. This
-		 * means we've hit EOF and didn't find what we are looking for.
-		 */
-		if (nmap == 1) {
-			/*
-			 * If we were looking for a hole, set offset to
-			 * the end of the file (i.e., there is an implicit
-			 * hole at the end of any file).
-		 	 */
-			if (whence == SEEK_HOLE) {
-				offset = end;
-				break;
-			}
-			/*
-			 * If we were looking for data, it's nowhere to be found
-			 */
-			ASSERT(whence == SEEK_DATA);
-			error = -ENXIO;
-			goto out_error;
-		}
-
-		ASSERT(i > 1);
-
-		/*
-		 * Nothing was found, proceed to the next round of search
-		 * if the next reading offset is not at or beyond EOF.
-		 */
-		fsbno = map[i - 1].br_startoff + map[i - 1].br_blockcount;
-		start = XFS_FSB_TO_B(mp, fsbno);
-		if (start >= end) {
-			if (whence == SEEK_HOLE) {
-				offset = end;
-				break;
-			}
-			ASSERT(whence == SEEK_DATA);
-			error = -ENXIO;
-			goto out_error;
-		}
-	}
-
-out:
-	/*
-	 * If at this point we have found the hole we wanted, the returned
-	 * offset may be bigger than the file size as it may be aligned to
-	 * page boundary for unwritten extents.  We need to deal with this
-	 * situation in particular.
-	 */
-	if (whence == SEEK_HOLE)
-		offset = min_t(loff_t, offset, end);
-
-	return offset;
-
-out_error:
-	return error;
-}
-
-STATIC loff_t
-xfs_seek_hole_data(
-	struct file		*file,
-	loff_t			start,
-	int			whence)
-{
-	struct inode		*inode = file->f_mapping->host;
-	struct xfs_inode	*ip = XFS_I(inode);
-	struct xfs_mount	*mp = ip->i_mount;
-	uint			lock;
-	loff_t			offset, end;
-	int			error = 0;
-
-	if (XFS_FORCED_SHUTDOWN(mp))
-		return -EIO;
-
-	lock = xfs_ilock_data_map_shared(ip);
-
-	end = i_size_read(inode);
-	offset = __xfs_seek_hole_data(inode, start, end, whence);
-	if (offset < 0) {
-		error = offset;
-		goto out_unlock;
-	}
-
-	offset = vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
-
-out_unlock:
-	xfs_iunlock(ip, lock);
-
-	if (error)
-		return error;
-	return offset;
+	return xfs_readdir(NULL, ip, ctx, bufsize);
 }
 
 STATIC loff_t
@@ -1341,17 +980,25 @@ xfs_file_llseek(
 	loff_t		offset,
 	int		whence)
 {
+	struct inode		*inode = file->f_mapping->host;
+
+	if (XFS_FORCED_SHUTDOWN(XFS_I(inode)->i_mount))
+		return -EIO;
+
 	switch (whence) {
-	case SEEK_END:
-	case SEEK_CUR:
-	case SEEK_SET:
+	default:
 		return generic_file_llseek(file, offset, whence);
 	case SEEK_HOLE:
+		offset = iomap_seek_hole(inode, offset, &xfs_iomap_ops);
+		break;
 	case SEEK_DATA:
-		return xfs_seek_hole_data(file, offset, whence);
-	default:
-		return -EINVAL;
+		offset = iomap_seek_data(inode, offset, &xfs_iomap_ops);
+		break;
 	}
+
+	if (offset < 0)
+		return offset;
+	return vfs_setpos(file, offset, inode->i_sb->s_maxbytes);
 }
 
 /*
@@ -1373,22 +1020,21 @@ xfs_file_llseek(
  */
 STATIC int
 xfs_filemap_page_mkwrite(
-	struct vm_area_struct	*vma,
 	struct vm_fault		*vmf)
 {
-	struct inode		*inode = file_inode(vma->vm_file);
+	struct inode		*inode = file_inode(vmf->vma->vm_file);
 	int			ret;
 
 	trace_xfs_filemap_page_mkwrite(XFS_I(inode));
 
 	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
+	file_update_time(vmf->vma->vm_file);
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	if (IS_DAX(inode)) {
-		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
+		ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
 	} else {
-		ret = iomap_page_mkwrite(vma, vmf, &xfs_iomap_ops);
+		ret = iomap_page_mkwrite(vmf, &xfs_iomap_ops);
 		ret = block_page_mkwrite_return(ret);
 	}
 
@@ -1400,23 +1046,22 @@ xfs_filemap_page_mkwrite(
 
 STATIC int
 xfs_filemap_fault(
-	struct vm_area_struct	*vma,
 	struct vm_fault		*vmf)
 {
-	struct inode		*inode = file_inode(vma->vm_file);
+	struct inode		*inode = file_inode(vmf->vma->vm_file);
 	int			ret;
 
 	trace_xfs_filemap_fault(XFS_I(inode));
 
 	/* DAX can shortcut the normal fault path on write faults! */
 	if ((vmf->flags & FAULT_FLAG_WRITE) && IS_DAX(inode))
-		return xfs_filemap_page_mkwrite(vma, vmf);
+		return xfs_filemap_page_mkwrite(vmf);
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 	if (IS_DAX(inode))
-		ret = dax_iomap_fault(vma, vmf, &xfs_iomap_ops);
+		ret = dax_iomap_fault(vmf, PE_SIZE_PTE, &xfs_iomap_ops);
 	else
-		ret = filemap_fault(vma, vmf);
+		ret = filemap_fault(vmf);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
 	return ret;
@@ -1425,36 +1070,34 @@ xfs_filemap_fault(
 /*
  * Similar to xfs_filemap_fault(), the DAX fault path can call into here on
  * both read and write faults. Hence we need to handle both cases. There is no
- * ->pmd_mkwrite callout for huge pages, so we have a single function here to
+ * ->huge_mkwrite callout for huge pages, so we have a single function here to
  * handle both cases here. @flags carries the information on the type of fault
  * occuring.
  */
 STATIC int
-xfs_filemap_pmd_fault(
-	struct vm_area_struct	*vma,
-	unsigned long		addr,
-	pmd_t			*pmd,
-	unsigned int		flags)
+xfs_filemap_huge_fault(
+	struct vm_fault		*vmf,
+	enum page_entry_size	pe_size)
 {
-	struct inode		*inode = file_inode(vma->vm_file);
+	struct inode		*inode = file_inode(vmf->vma->vm_file);
 	struct xfs_inode	*ip = XFS_I(inode);
 	int			ret;
 
 	if (!IS_DAX(inode))
 		return VM_FAULT_FALLBACK;
 
-	trace_xfs_filemap_pmd_fault(ip);
+	trace_xfs_filemap_huge_fault(ip);
 
-	if (flags & FAULT_FLAG_WRITE) {
+	if (vmf->flags & FAULT_FLAG_WRITE) {
 		sb_start_pagefault(inode->i_sb);
-		file_update_time(vma->vm_file);
+		file_update_time(vmf->vma->vm_file);
 	}
 
 	xfs_ilock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
-	ret = dax_iomap_pmd_fault(vma, addr, pmd, flags, &xfs_iomap_ops);
+	ret = dax_iomap_fault(vmf, pe_size, &xfs_iomap_ops);
 	xfs_iunlock(XFS_I(inode), XFS_MMAPLOCK_SHARED);
 
-	if (flags & FAULT_FLAG_WRITE)
+	if (vmf->flags & FAULT_FLAG_WRITE)
 		sb_end_pagefault(inode->i_sb);
 
 	return ret;
@@ -1468,11 +1111,10 @@ xfs_filemap_pmd_fault(
  */
 static int
 xfs_filemap_pfn_mkwrite(
-	struct vm_area_struct	*vma,
 	struct vm_fault		*vmf)
 {
 
-	struct inode		*inode = file_inode(vma->vm_file);
+	struct inode		*inode = file_inode(vmf->vma->vm_file);
 	struct xfs_inode	*ip = XFS_I(inode);
 	int			ret = VM_FAULT_NOPAGE;
 	loff_t			size;
@@ -1480,7 +1122,7 @@ xfs_filemap_pfn_mkwrite(
 	trace_xfs_filemap_pfn_mkwrite(ip);
 
 	sb_start_pagefault(inode->i_sb);
-	file_update_time(vma->vm_file);
+	file_update_time(vmf->vma->vm_file);
 
 	/* check if the faulting page hasn't raced with truncate */
 	xfs_ilock(ip, XFS_MMAPLOCK_SHARED);
@@ -1488,7 +1130,7 @@ xfs_filemap_pfn_mkwrite(
 	if (vmf->pgoff >= size)
 		ret = VM_FAULT_SIGBUS;
 	else if (IS_DAX(inode))
-		ret = dax_pfn_mkwrite(vma, vmf);
+		ret = dax_pfn_mkwrite(vmf);
 	xfs_iunlock(ip, XFS_MMAPLOCK_SHARED);
 	sb_end_pagefault(inode->i_sb);
 	return ret;
@@ -1497,7 +1139,7 @@ xfs_filemap_pfn_mkwrite(
 
 static const struct vm_operations_struct xfs_file_vm_ops = {
 	.fault		= xfs_filemap_fault,
-	.pmd_fault	= xfs_filemap_pmd_fault,
+	.huge_fault	= xfs_filemap_huge_fault,
 	.map_pages	= filemap_map_pages,
 	.page_mkwrite	= xfs_filemap_page_mkwrite,
 	.pfn_mkwrite	= xfs_filemap_pfn_mkwrite,
diff --git a/fs/xfs/xfs_fsmap.c b/fs/xfs/xfs_fsmap.c
new file mode 100644
index 000000000000..814ed729881d
--- /dev/null
+++ b/fs/xfs/xfs_fsmap.c
@@ -0,0 +1,943 @@
+/*
+ * Copyright (C) 2017 Oracle.  All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+#include "xfs.h"
+#include "xfs_fs.h"
+#include "xfs_shared.h"
+#include "xfs_format.h"
+#include "xfs_log_format.h"
+#include "xfs_trans_resv.h"
+#include "xfs_sb.h"
+#include "xfs_mount.h"
+#include "xfs_defer.h"
+#include "xfs_inode.h"
+#include "xfs_trans.h"
+#include "xfs_error.h"
+#include "xfs_btree.h"
+#include "xfs_rmap_btree.h"
+#include "xfs_trace.h"
+#include "xfs_log.h"
+#include "xfs_rmap.h"
+#include "xfs_alloc.h"
+#include "xfs_bit.h"
+#include <linux/fsmap.h>
+#include "xfs_fsmap.h"
+#include "xfs_refcount.h"
+#include "xfs_refcount_btree.h"
+#include "xfs_alloc_btree.h"
+#include "xfs_rtalloc.h"
+
+/* Convert an xfs_fsmap to an fsmap. */
+void
+xfs_fsmap_from_internal(
+	struct fsmap		*dest,
+	struct xfs_fsmap	*src)
+{
+	dest->fmr_device = src->fmr_device;
+	dest->fmr_flags = src->fmr_flags;
+	dest->fmr_physical = BBTOB(src->fmr_physical);
+	dest->fmr_owner = src->fmr_owner;
+	dest->fmr_offset = BBTOB(src->fmr_offset);
+	dest->fmr_length = BBTOB(src->fmr_length);
+	dest->fmr_reserved[0] = 0;
+	dest->fmr_reserved[1] = 0;
+	dest->fmr_reserved[2] = 0;
+}
+
+/* Convert an fsmap to an xfs_fsmap. */
+void
+xfs_fsmap_to_internal(
+	struct xfs_fsmap	*dest,
+	struct fsmap		*src)
+{
+	dest->fmr_device = src->fmr_device;
+	dest->fmr_flags = src->fmr_flags;
+	dest->fmr_physical = BTOBBT(src->fmr_physical);
+	dest->fmr_owner = src->fmr_owner;
+	dest->fmr_offset = BTOBBT(src->fmr_offset);
+	dest->fmr_length = BTOBBT(src->fmr_length);
+}
+
+/* Convert an fsmap owner into an rmapbt owner. */
+static int
+xfs_fsmap_owner_to_rmap(
+	struct xfs_rmap_irec	*dest,
+	struct xfs_fsmap	*src)
+{
+	if (!(src->fmr_flags & FMR_OF_SPECIAL_OWNER)) {
+		dest->rm_owner = src->fmr_owner;
+		return 0;
+	}
+
+	switch (src->fmr_owner) {
+	case 0:			/* "lowest owner id possible" */
+	case -1ULL:		/* "highest owner id possible" */
+		dest->rm_owner = 0;
+		break;
+	case XFS_FMR_OWN_FREE:
+		dest->rm_owner = XFS_RMAP_OWN_NULL;
+		break;
+	case XFS_FMR_OWN_UNKNOWN:
+		dest->rm_owner = XFS_RMAP_OWN_UNKNOWN;
+		break;
+	case XFS_FMR_OWN_FS:
+		dest->rm_owner = XFS_RMAP_OWN_FS;
+		break;
+	case XFS_FMR_OWN_LOG:
+		dest->rm_owner = XFS_RMAP_OWN_LOG;
+		break;
+	case XFS_FMR_OWN_AG:
+		dest->rm_owner = XFS_RMAP_OWN_AG;
+		break;
+	case XFS_FMR_OWN_INOBT:
+		dest->rm_owner = XFS_RMAP_OWN_INOBT;
+		break;
+	case XFS_FMR_OWN_INODES:
+		dest->rm_owner = XFS_RMAP_OWN_INODES;
+		break;
+	case XFS_FMR_OWN_REFC:
+		dest->rm_owner = XFS_RMAP_OWN_REFC;
+		break;
+	case XFS_FMR_OWN_COW:
+		dest->rm_owner = XFS_RMAP_OWN_COW;
+		break;
+	case XFS_FMR_OWN_DEFECTIVE:	/* not implemented */
+		/* fall through */
+	default:
+		return -EINVAL;
+	}
+	return 0;
+}
+
+/* Convert an rmapbt owner into an fsmap owner. */
+static int
+xfs_fsmap_owner_from_rmap(
+	struct xfs_fsmap	*dest,
+	struct xfs_rmap_irec	*src)
+{
+	dest->fmr_flags = 0;
+	if (!XFS_RMAP_NON_INODE_OWNER(src->rm_owner)) {
+		dest->fmr_owner = src->rm_owner;
+		return 0;
+	}
+	dest->fmr_flags |= FMR_OF_SPECIAL_OWNER;
+
+	switch (src->rm_owner) {
+	case XFS_RMAP_OWN_FS:
+		dest->fmr_owner = XFS_FMR_OWN_FS;
+		break;
+	case XFS_RMAP_OWN_LOG:
+		dest->fmr_owner = XFS_FMR_OWN_LOG;
+		break;
+	case XFS_RMAP_OWN_AG:
+		dest->fmr_owner = XFS_FMR_OWN_AG;
+		break;
+	case XFS_RMAP_OWN_INOBT:
+		dest->fmr_owner = XFS_FMR_OWN_INOBT;
+		break;
+	case XFS_RMAP_OWN_INODES:
+		dest->fmr_owner = XFS_FMR_OWN_INODES;
+		break;
+	case XFS_RMAP_OWN_REFC:
+		dest->fmr_owner = XFS_FMR_OWN_REFC;
+		break;
+	case XFS_RMAP_OWN_COW:
+		dest->fmr_owner = XFS_FMR_OWN_COW;
+		break;
+	case XFS_RMAP_OWN_NULL:	/* "free" */
+		dest->fmr_owner = XFS_FMR_OWN_FREE;
+		break;
+	default:
+		return -EFSCORRUPTED;
+	}
+	return 0;
+}
+
+/* getfsmap query state */
+struct xfs_getfsmap_info {
+	struct xfs_fsmap_head	*head;
+	xfs_fsmap_format_t	formatter;	/* formatting fn */
+	void			*format_arg;	/* format buffer */
+	struct xfs_buf		*agf_bp;	/* AGF, for refcount queries */
+	xfs_daddr_t		next_daddr;	/* next daddr we expect */
+	u64			missing_owner;	/* owner of holes */
+	u32			dev;		/* device id */
+	xfs_agnumber_t		agno;		/* AG number, if applicable */
+	struct xfs_rmap_irec	low;		/* low rmap key */
+	struct xfs_rmap_irec	high;		/* high rmap key */
+	bool			last;		/* last extent? */
+};
+
+/* Associate a device with a getfsmap handler. */
+struct xfs_getfsmap_dev {
+	u32			dev;
+	int			(*fn)(struct xfs_trans *tp,
+				      struct xfs_fsmap *keys,
+				      struct xfs_getfsmap_info *info);
+};
+
+/* Compare two getfsmap device handlers. */
+static int
+xfs_getfsmap_dev_compare(
+	const void			*p1,
+	const void			*p2)
+{
+	const struct xfs_getfsmap_dev	*d1 = p1;
+	const struct xfs_getfsmap_dev	*d2 = p2;
+
+	return d1->dev - d2->dev;
+}
+
+/* Decide if this mapping is shared. */
+STATIC int
+xfs_getfsmap_is_shared(
+	struct xfs_trans		*tp,
+	struct xfs_getfsmap_info	*info,
+	struct xfs_rmap_irec		*rec,
+	bool				*stat)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_btree_cur		*cur;
+	xfs_agblock_t			fbno;
+	xfs_extlen_t			flen;
+	int				error;
+
+	*stat = false;
+	if (!xfs_sb_version_hasreflink(&mp->m_sb))
+		return 0;
+	/* rt files will have agno set to NULLAGNUMBER */
+	if (info->agno == NULLAGNUMBER)
+		return 0;
+
+	/* Are there any shared blocks here? */
+	flen = 0;
+	cur = xfs_refcountbt_init_cursor(mp, tp, info->agf_bp,
+			info->agno, NULL);
+
+	error = xfs_refcount_find_shared(cur, rec->rm_startblock,
+			rec->rm_blockcount, &fbno, &flen, false);
+
+	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
+	if (error)
+		return error;
+
+	*stat = flen > 0;
+	return 0;
+}
+
+/*
+ * Format a reverse mapping for getfsmap, having translated rm_startblock
+ * into the appropriate daddr units.
+ */
+STATIC int
+xfs_getfsmap_helper(
+	struct xfs_trans		*tp,
+	struct xfs_getfsmap_info	*info,
+	struct xfs_rmap_irec		*rec,
+	xfs_daddr_t			rec_daddr)
+{
+	struct xfs_fsmap		fmr;
+	struct xfs_mount		*mp = tp->t_mountp;
+	bool				shared;
+	int				error;
+
+	if (fatal_signal_pending(current))
+		return -EINTR;
+
+	/*
+	 * Filter out records that start before our startpoint, if the
+	 * caller requested that.
+	 */
+	if (xfs_rmap_compare(rec, &info->low) < 0) {
+		rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+		if (info->next_daddr < rec_daddr)
+			info->next_daddr = rec_daddr;
+		return XFS_BTREE_QUERY_RANGE_CONTINUE;
+	}
+
+	/* Are we just counting mappings? */
+	if (info->head->fmh_count == 0) {
+		if (rec_daddr > info->next_daddr)
+			info->head->fmh_entries++;
+
+		if (info->last)
+			return XFS_BTREE_QUERY_RANGE_CONTINUE;
+
+		info->head->fmh_entries++;
+
+		rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+		if (info->next_daddr < rec_daddr)
+			info->next_daddr = rec_daddr;
+		return XFS_BTREE_QUERY_RANGE_CONTINUE;
+	}
+
+	/*
+	 * If the record starts past the last physical block we saw,
+	 * then we've found a gap.  Report the gap as being owned by
+	 * whatever the caller specified is the missing owner.
+	 */
+	if (rec_daddr > info->next_daddr) {
+		if (info->head->fmh_entries >= info->head->fmh_count)
+			return XFS_BTREE_QUERY_RANGE_ABORT;
+
+		fmr.fmr_device = info->dev;
+		fmr.fmr_physical = info->next_daddr;
+		fmr.fmr_owner = info->missing_owner;
+		fmr.fmr_offset = 0;
+		fmr.fmr_length = rec_daddr - info->next_daddr;
+		fmr.fmr_flags = FMR_OF_SPECIAL_OWNER;
+		error = info->formatter(&fmr, info->format_arg);
+		if (error)
+			return error;
+		info->head->fmh_entries++;
+	}
+
+	if (info->last)
+		goto out;
+
+	/* Fill out the extent we found */
+	if (info->head->fmh_entries >= info->head->fmh_count)
+		return XFS_BTREE_QUERY_RANGE_ABORT;
+
+	trace_xfs_fsmap_mapping(mp, info->dev, info->agno, rec);
+
+	fmr.fmr_device = info->dev;
+	fmr.fmr_physical = rec_daddr;
+	error = xfs_fsmap_owner_from_rmap(&fmr, rec);
+	if (error)
+		return error;
+	fmr.fmr_offset = XFS_FSB_TO_BB(mp, rec->rm_offset);
+	fmr.fmr_length = XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+	if (rec->rm_flags & XFS_RMAP_UNWRITTEN)
+		fmr.fmr_flags |= FMR_OF_PREALLOC;
+	if (rec->rm_flags & XFS_RMAP_ATTR_FORK)
+		fmr.fmr_flags |= FMR_OF_ATTR_FORK;
+	if (rec->rm_flags & XFS_RMAP_BMBT_BLOCK)
+		fmr.fmr_flags |= FMR_OF_EXTENT_MAP;
+	if (fmr.fmr_flags == 0) {
+		error = xfs_getfsmap_is_shared(tp, info, rec, &shared);
+		if (error)
+			return error;
+		if (shared)
+			fmr.fmr_flags |= FMR_OF_SHARED;
+	}
+	error = info->formatter(&fmr, info->format_arg);
+	if (error)
+		return error;
+	info->head->fmh_entries++;
+
+out:
+	rec_daddr += XFS_FSB_TO_BB(mp, rec->rm_blockcount);
+	if (info->next_daddr < rec_daddr)
+		info->next_daddr = rec_daddr;
+	return XFS_BTREE_QUERY_RANGE_CONTINUE;
+}
+
+/* Transform a rmapbt irec into a fsmap */
+STATIC int
+xfs_getfsmap_datadev_helper(
+	struct xfs_btree_cur		*cur,
+	struct xfs_rmap_irec		*rec,
+	void				*priv)
+{
+	struct xfs_mount		*mp = cur->bc_mp;
+	struct xfs_getfsmap_info	*info = priv;
+	xfs_fsblock_t			fsb;
+	xfs_daddr_t			rec_daddr;
+
+	fsb = XFS_AGB_TO_FSB(mp, cur->bc_private.a.agno, rec->rm_startblock);
+	rec_daddr = XFS_FSB_TO_DADDR(mp, fsb);
+
+	return xfs_getfsmap_helper(cur->bc_tp, info, rec, rec_daddr);
+}
+
+/* Transform a rtbitmap "record" into a fsmap */
+STATIC int
+xfs_getfsmap_rtdev_rtbitmap_helper(
+	struct xfs_trans		*tp,
+	struct xfs_rtalloc_rec		*rec,
+	void				*priv)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_getfsmap_info	*info = priv;
+	struct xfs_rmap_irec		irec;
+	xfs_daddr_t			rec_daddr;
+
+	rec_daddr = XFS_FSB_TO_BB(mp, rec->ar_startblock);
+
+	irec.rm_startblock = rec->ar_startblock;
+	irec.rm_blockcount = rec->ar_blockcount;
+	irec.rm_owner = XFS_RMAP_OWN_NULL;	/* "free" */
+	irec.rm_offset = 0;
+	irec.rm_flags = 0;
+
+	return xfs_getfsmap_helper(tp, info, &irec, rec_daddr);
+}
+
+/* Transform a bnobt irec into a fsmap */
+STATIC int
+xfs_getfsmap_datadev_bnobt_helper(
+	struct xfs_btree_cur		*cur,
+	struct xfs_alloc_rec_incore	*rec,
+	void				*priv)
+{
+	struct xfs_mount		*mp = cur->bc_mp;
+	struct xfs_getfsmap_info	*info = priv;
+	struct xfs_rmap_irec		irec;
+	xfs_daddr_t			rec_daddr;
+
+	rec_daddr = XFS_AGB_TO_DADDR(mp, cur->bc_private.a.agno,
+			rec->ar_startblock);
+
+	irec.rm_startblock = rec->ar_startblock;
+	irec.rm_blockcount = rec->ar_blockcount;
+	irec.rm_owner = XFS_RMAP_OWN_NULL;	/* "free" */
+	irec.rm_offset = 0;
+	irec.rm_flags = 0;
+
+	return xfs_getfsmap_helper(cur->bc_tp, info, &irec, rec_daddr);
+}
+
+/* Set rmap flags based on the getfsmap flags */
+static void
+xfs_getfsmap_set_irec_flags(
+	struct xfs_rmap_irec	*irec,
+	struct xfs_fsmap	*fmr)
+{
+	irec->rm_flags = 0;
+	if (fmr->fmr_flags & FMR_OF_ATTR_FORK)
+		irec->rm_flags |= XFS_RMAP_ATTR_FORK;
+	if (fmr->fmr_flags & FMR_OF_EXTENT_MAP)
+		irec->rm_flags |= XFS_RMAP_BMBT_BLOCK;
+	if (fmr->fmr_flags & FMR_OF_PREALLOC)
+		irec->rm_flags |= XFS_RMAP_UNWRITTEN;
+}
+
+/* Execute a getfsmap query against the log device. */
+STATIC int
+xfs_getfsmap_logdev(
+	struct xfs_trans		*tp,
+	struct xfs_fsmap		*keys,
+	struct xfs_getfsmap_info	*info)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_rmap_irec		rmap;
+	int				error;
+
+	/* Set up search keys */
+	info->low.rm_startblock = XFS_BB_TO_FSBT(mp, keys[0].fmr_physical);
+	info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
+	error = xfs_fsmap_owner_to_rmap(&info->low, keys);
+	if (error)
+		return error;
+	info->low.rm_blockcount = 0;
+	xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
+
+	error = xfs_fsmap_owner_to_rmap(&info->high, keys + 1);
+	if (error)
+		return error;
+	info->high.rm_startblock = -1U;
+	info->high.rm_owner = ULLONG_MAX;
+	info->high.rm_offset = ULLONG_MAX;
+	info->high.rm_blockcount = 0;
+	info->high.rm_flags = XFS_RMAP_KEY_FLAGS | XFS_RMAP_REC_FLAGS;
+	info->missing_owner = XFS_FMR_OWN_FREE;
+
+	trace_xfs_fsmap_low_key(mp, info->dev, info->agno, &info->low);
+	trace_xfs_fsmap_high_key(mp, info->dev, info->agno, &info->high);
+
+	if (keys[0].fmr_physical > 0)
+		return 0;
+
+	/* Fabricate an rmap entry for the external log device. */
+	rmap.rm_startblock = 0;
+	rmap.rm_blockcount = mp->m_sb.sb_logblocks;
+	rmap.rm_owner = XFS_RMAP_OWN_LOG;
+	rmap.rm_offset = 0;
+	rmap.rm_flags = 0;
+
+	return xfs_getfsmap_helper(tp, info, &rmap, 0);
+}
+
+/* Execute a getfsmap query against the realtime device. */
+STATIC int
+__xfs_getfsmap_rtdev(
+	struct xfs_trans		*tp,
+	struct xfs_fsmap		*keys,
+	int				(*query_fn)(struct xfs_trans *,
+						    struct xfs_getfsmap_info *),
+	struct xfs_getfsmap_info	*info)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	xfs_fsblock_t			start_fsb;
+	xfs_fsblock_t			end_fsb;
+	xfs_daddr_t			eofs;
+	int				error = 0;
+
+	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_rblocks);
+	if (keys[0].fmr_physical >= eofs)
+		return 0;
+	if (keys[1].fmr_physical >= eofs)
+		keys[1].fmr_physical = eofs - 1;
+	start_fsb = XFS_BB_TO_FSBT(mp, keys[0].fmr_physical);
+	end_fsb = XFS_BB_TO_FSB(mp, keys[1].fmr_physical);
+
+	/* Set up search keys */
+	info->low.rm_startblock = start_fsb;
+	error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
+	if (error)
+		return error;
+	info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
+	info->low.rm_blockcount = 0;
+	xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
+
+	info->high.rm_startblock = end_fsb;
+	error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]);
+	if (error)
+		return error;
+	info->high.rm_offset = XFS_BB_TO_FSBT(mp, keys[1].fmr_offset);
+	info->high.rm_blockcount = 0;
+	xfs_getfsmap_set_irec_flags(&info->high, &keys[1]);
+
+	trace_xfs_fsmap_low_key(mp, info->dev, info->agno, &info->low);
+	trace_xfs_fsmap_high_key(mp, info->dev, info->agno, &info->high);
+
+	return query_fn(tp, info);
+}
+
+/* Actually query the realtime bitmap. */
+STATIC int
+xfs_getfsmap_rtdev_rtbitmap_query(
+	struct xfs_trans		*tp,
+	struct xfs_getfsmap_info	*info)
+{
+	struct xfs_rtalloc_rec		alow;
+	struct xfs_rtalloc_rec		ahigh;
+	int				error;
+
+	xfs_ilock(tp->t_mountp->m_rbmip, XFS_ILOCK_SHARED);
+
+	alow.ar_startblock = info->low.rm_startblock;
+	ahigh.ar_startblock = info->high.rm_startblock;
+	error = xfs_rtalloc_query_range(tp, &alow, &ahigh,
+			xfs_getfsmap_rtdev_rtbitmap_helper, info);
+	if (error)
+		goto err;
+
+	/* Report any gaps at the end of the rtbitmap */
+	info->last = true;
+	error = xfs_getfsmap_rtdev_rtbitmap_helper(tp, &ahigh, info);
+	if (error)
+		goto err;
+err:
+	xfs_iunlock(tp->t_mountp->m_rbmip, XFS_ILOCK_SHARED);
+	return error;
+}
+
+/* Execute a getfsmap query against the realtime device rtbitmap. */
+STATIC int
+xfs_getfsmap_rtdev_rtbitmap(
+	struct xfs_trans		*tp,
+	struct xfs_fsmap		*keys,
+	struct xfs_getfsmap_info	*info)
+{
+	info->missing_owner = XFS_FMR_OWN_UNKNOWN;
+	return __xfs_getfsmap_rtdev(tp, keys, xfs_getfsmap_rtdev_rtbitmap_query,
+			info);
+}
+
+/* Execute a getfsmap query against the regular data device. */
+STATIC int
+__xfs_getfsmap_datadev(
+	struct xfs_trans		*tp,
+	struct xfs_fsmap		*keys,
+	struct xfs_getfsmap_info	*info,
+	int				(*query_fn)(struct xfs_trans *,
+						    struct xfs_getfsmap_info *,
+						    struct xfs_btree_cur **,
+						    void *),
+	void				*priv)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_btree_cur		*bt_cur = NULL;
+	xfs_fsblock_t			start_fsb;
+	xfs_fsblock_t			end_fsb;
+	xfs_agnumber_t			start_ag;
+	xfs_agnumber_t			end_ag;
+	xfs_daddr_t			eofs;
+	int				error = 0;
+
+	eofs = XFS_FSB_TO_BB(mp, mp->m_sb.sb_dblocks);
+	if (keys[0].fmr_physical >= eofs)
+		return 0;
+	if (keys[1].fmr_physical >= eofs)
+		keys[1].fmr_physical = eofs - 1;
+	start_fsb = XFS_DADDR_TO_FSB(mp, keys[0].fmr_physical);
+	end_fsb = XFS_DADDR_TO_FSB(mp, keys[1].fmr_physical);
+
+	/*
+	 * Convert the fsmap low/high keys to AG based keys.  Initialize
+	 * low to the fsmap low key and max out the high key to the end
+	 * of the AG.
+	 */
+	info->low.rm_startblock = XFS_FSB_TO_AGBNO(mp, start_fsb);
+	info->low.rm_offset = XFS_BB_TO_FSBT(mp, keys[0].fmr_offset);
+	error = xfs_fsmap_owner_to_rmap(&info->low, &keys[0]);
+	if (error)
+		return error;
+	info->low.rm_blockcount = 0;
+	xfs_getfsmap_set_irec_flags(&info->low, &keys[0]);
+
+	info->high.rm_startblock = -1U;
+	info->high.rm_owner = ULLONG_MAX;
+	info->high.rm_offset = ULLONG_MAX;
+	info->high.rm_blockcount = 0;
+	info->high.rm_flags = XFS_RMAP_KEY_FLAGS | XFS_RMAP_REC_FLAGS;
+
+	start_ag = XFS_FSB_TO_AGNO(mp, start_fsb);
+	end_ag = XFS_FSB_TO_AGNO(mp, end_fsb);
+
+	/* Query each AG */
+	for (info->agno = start_ag; info->agno <= end_ag; info->agno++) {
+		/*
+		 * Set the AG high key from the fsmap high key if this
+		 * is the last AG that we're querying.
+		 */
+		if (info->agno == end_ag) {
+			info->high.rm_startblock = XFS_FSB_TO_AGBNO(mp,
+					end_fsb);
+			info->high.rm_offset = XFS_BB_TO_FSBT(mp,
+					keys[1].fmr_offset);
+			error = xfs_fsmap_owner_to_rmap(&info->high, &keys[1]);
+			if (error)
+				goto err;
+			xfs_getfsmap_set_irec_flags(&info->high, &keys[1]);
+		}
+
+		if (bt_cur) {
+			xfs_btree_del_cursor(bt_cur, XFS_BTREE_NOERROR);
+			bt_cur = NULL;
+			xfs_trans_brelse(tp, info->agf_bp);
+			info->agf_bp = NULL;
+		}
+
+		error = xfs_alloc_read_agf(mp, tp, info->agno, 0,
+				&info->agf_bp);
+		if (error)
+			goto err;
+
+		trace_xfs_fsmap_low_key(mp, info->dev, info->agno, &info->low);
+		trace_xfs_fsmap_high_key(mp, info->dev, info->agno,
+				&info->high);
+
+		error = query_fn(tp, info, &bt_cur, priv);
+		if (error)
+			goto err;
+
+		/*
+		 * Set the AG low key to the start of the AG prior to
+		 * moving on to the next AG.
+		 */
+		if (info->agno == start_ag) {
+			info->low.rm_startblock = 0;
+			info->low.rm_owner = 0;
+			info->low.rm_offset = 0;
+			info->low.rm_flags = 0;
+		}
+	}
+
+	/* Report any gap at the end of the AG */
+	info->last = true;
+	error = query_fn(tp, info, &bt_cur, priv);
+	if (error)
+		goto err;
+
+err:
+	if (bt_cur)
+		xfs_btree_del_cursor(bt_cur, error < 0 ? XFS_BTREE_ERROR :
+							 XFS_BTREE_NOERROR);
+	if (info->agf_bp) {
+		xfs_trans_brelse(tp, info->agf_bp);
+		info->agf_bp = NULL;
+	}
+
+	return error;
+}
+
+/* Actually query the rmap btree. */
+STATIC int
+xfs_getfsmap_datadev_rmapbt_query(
+	struct xfs_trans		*tp,
+	struct xfs_getfsmap_info	*info,
+	struct xfs_btree_cur		**curpp,
+	void				*priv)
+{
+	/* Report any gap at the end of the last AG. */
+	if (info->last)
+		return xfs_getfsmap_datadev_helper(*curpp, &info->high, info);
+
+	/* Allocate cursor for this AG and query_range it. */
+	*curpp = xfs_rmapbt_init_cursor(tp->t_mountp, tp, info->agf_bp,
+			info->agno);
+	return xfs_rmap_query_range(*curpp, &info->low, &info->high,
+			xfs_getfsmap_datadev_helper, info);
+}
+
+/* Execute a getfsmap query against the regular data device rmapbt. */
+STATIC int
+xfs_getfsmap_datadev_rmapbt(
+	struct xfs_trans		*tp,
+	struct xfs_fsmap		*keys,
+	struct xfs_getfsmap_info	*info)
+{
+	info->missing_owner = XFS_FMR_OWN_FREE;
+	return __xfs_getfsmap_datadev(tp, keys, info,
+			xfs_getfsmap_datadev_rmapbt_query, NULL);
+}
+
+/* Actually query the bno btree. */
+STATIC int
+xfs_getfsmap_datadev_bnobt_query(
+	struct xfs_trans		*tp,
+	struct xfs_getfsmap_info	*info,
+	struct xfs_btree_cur		**curpp,
+	void				*priv)
+{
+	struct xfs_alloc_rec_incore	*key = priv;
+
+	/* Report any gap at the end of the last AG. */
+	if (info->last)
+		return xfs_getfsmap_datadev_bnobt_helper(*curpp, &key[1], info);
+
+	/* Allocate cursor for this AG and query_range it. */
+	*curpp = xfs_allocbt_init_cursor(tp->t_mountp, tp, info->agf_bp,
+			info->agno, XFS_BTNUM_BNO);
+	key->ar_startblock = info->low.rm_startblock;
+	key[1].ar_startblock = info->high.rm_startblock;
+	return xfs_alloc_query_range(*curpp, key, &key[1],
+			xfs_getfsmap_datadev_bnobt_helper, info);
+}
+
+/* Execute a getfsmap query against the regular data device's bnobt. */
+STATIC int
+xfs_getfsmap_datadev_bnobt(
+	struct xfs_trans		*tp,
+	struct xfs_fsmap		*keys,
+	struct xfs_getfsmap_info	*info)
+{
+	struct xfs_alloc_rec_incore	akeys[2];
+
+	info->missing_owner = XFS_FMR_OWN_UNKNOWN;
+	return __xfs_getfsmap_datadev(tp, keys, info,
+			xfs_getfsmap_datadev_bnobt_query, &akeys[0]);
+}
+
+/* Do we recognize the device? */
+STATIC bool
+xfs_getfsmap_is_valid_device(
+	struct xfs_mount	*mp,
+	struct xfs_fsmap	*fm)
+{
+	if (fm->fmr_device == 0 || fm->fmr_device == UINT_MAX ||
+	    fm->fmr_device == new_encode_dev(mp->m_ddev_targp->bt_dev))
+		return true;
+	if (mp->m_logdev_targp &&
+	    fm->fmr_device == new_encode_dev(mp->m_logdev_targp->bt_dev))
+		return true;
+	if (mp->m_rtdev_targp &&
+	    fm->fmr_device == new_encode_dev(mp->m_rtdev_targp->bt_dev))
+		return true;
+	return false;
+}
+
+/* Ensure that the low key is less than the high key. */
+STATIC bool
+xfs_getfsmap_check_keys(
+	struct xfs_fsmap		*low_key,
+	struct xfs_fsmap		*high_key)
+{
+	if (low_key->fmr_device > high_key->fmr_device)
+		return false;
+	if (low_key->fmr_device < high_key->fmr_device)
+		return true;
+
+	if (low_key->fmr_physical > high_key->fmr_physical)
+		return false;
+	if (low_key->fmr_physical < high_key->fmr_physical)
+		return true;
+
+	if (low_key->fmr_owner > high_key->fmr_owner)
+		return false;
+	if (low_key->fmr_owner < high_key->fmr_owner)
+		return true;
+
+	if (low_key->fmr_offset > high_key->fmr_offset)
+		return false;
+	if (low_key->fmr_offset < high_key->fmr_offset)
+		return true;
+
+	return false;
+}
+
+#define XFS_GETFSMAP_DEVS	3
+/*
+ * Get filesystem's extents as described in head, and format for
+ * output.  Calls formatter to fill the user's buffer until all
+ * extents are mapped, until the passed-in head->fmh_count slots have
+ * been filled, or until the formatter short-circuits the loop, if it
+ * is tracking filled-in extents on its own.
+ *
+ * Key to Confusion
+ * ----------------
+ * There are multiple levels of keys and counters at work here:
+ * xfs_fsmap_head.fmh_keys	-- low and high fsmap keys passed in;
+ * 				   these reflect fs-wide sector addrs.
+ * dkeys			-- fmh_keys used to query each device;
+ * 				   these are fmh_keys but w/ the low key
+ * 				   bumped up by fmr_length.
+ * xfs_getfsmap_info.next_daddr	-- next disk addr we expect to see; this
+ *				   is how we detect gaps in the fsmap
+				   records and report them.
+ * xfs_getfsmap_info.low/high	-- per-AG low/high keys computed from
+ * 				   dkeys; used to query the metadata.
+ */
+int
+xfs_getfsmap(
+	struct xfs_mount		*mp,
+	struct xfs_fsmap_head		*head,
+	xfs_fsmap_format_t		formatter,
+	void				*arg)
+{
+	struct xfs_trans		*tp = NULL;
+	struct xfs_fsmap		dkeys[2];	/* per-dev keys */
+	struct xfs_getfsmap_dev		handlers[XFS_GETFSMAP_DEVS];
+	struct xfs_getfsmap_info	info = { NULL };
+	bool				use_rmap;
+	int				i;
+	int				error = 0;
+
+	if (head->fmh_iflags & ~FMH_IF_VALID)
+		return -EINVAL;
+	if (!xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[0]) ||
+	    !xfs_getfsmap_is_valid_device(mp, &head->fmh_keys[1]))
+		return -EINVAL;
+
+	use_rmap = capable(CAP_SYS_ADMIN) &&
+		   xfs_sb_version_hasrmapbt(&mp->m_sb);
+	head->fmh_entries = 0;
+
+	/* Set up our device handlers. */
+	memset(handlers, 0, sizeof(handlers));
+	handlers[0].dev = new_encode_dev(mp->m_ddev_targp->bt_dev);
+	if (use_rmap)
+		handlers[0].fn = xfs_getfsmap_datadev_rmapbt;
+	else
+		handlers[0].fn = xfs_getfsmap_datadev_bnobt;
+	if (mp->m_logdev_targp != mp->m_ddev_targp) {
+		handlers[1].dev = new_encode_dev(mp->m_logdev_targp->bt_dev);
+		handlers[1].fn = xfs_getfsmap_logdev;
+	}
+	if (mp->m_rtdev_targp) {
+		handlers[2].dev = new_encode_dev(mp->m_rtdev_targp->bt_dev);
+		handlers[2].fn = xfs_getfsmap_rtdev_rtbitmap;
+	}
+
+	xfs_sort(handlers, XFS_GETFSMAP_DEVS, sizeof(struct xfs_getfsmap_dev),
+			xfs_getfsmap_dev_compare);
+
+	/*
+	 * To continue where we left off, we allow userspace to use the
+	 * last mapping from a previous call as the low key of the next.
+	 * This is identified by a non-zero length in the low key. We
+	 * have to increment the low key in this scenario to ensure we
+	 * don't return the same mapping again, and instead return the
+	 * very next mapping.
+	 *
+	 * If the low key mapping refers to file data, the same physical
+	 * blocks could be mapped to several other files/offsets.
+	 * According to rmapbt record ordering, the minimal next
+	 * possible record for the block range is the next starting
+	 * offset in the same inode. Therefore, bump the file offset to
+	 * continue the search appropriately.  For all other low key
+	 * mapping types (attr blocks, metadata), bump the physical
+	 * offset as there can be no other mapping for the same physical
+	 * block range.
+	 */
+	dkeys[0] = head->fmh_keys[0];
+	if (dkeys[0].fmr_flags & (FMR_OF_SPECIAL_OWNER | FMR_OF_EXTENT_MAP)) {
+		dkeys[0].fmr_physical += dkeys[0].fmr_length;
+		dkeys[0].fmr_owner = 0;
+		if (dkeys[0].fmr_offset)
+			return -EINVAL;
+	} else
+		dkeys[0].fmr_offset += dkeys[0].fmr_length;
+	dkeys[0].fmr_length = 0;
+	memset(&dkeys[1], 0xFF, sizeof(struct xfs_fsmap));
+
+	if (!xfs_getfsmap_check_keys(dkeys, &head->fmh_keys[1]))
+		return -EINVAL;
+
+	info.next_daddr = head->fmh_keys[0].fmr_physical +
+			  head->fmh_keys[0].fmr_length;
+	info.formatter = formatter;
+	info.format_arg = arg;
+	info.head = head;
+
+	/* For each device we support... */
+	for (i = 0; i < XFS_GETFSMAP_DEVS; i++) {
+		/* Is this device within the range the user asked for? */
+		if (!handlers[i].fn)
+			continue;
+		if (head->fmh_keys[0].fmr_device > handlers[i].dev)
+			continue;
+		if (head->fmh_keys[1].fmr_device < handlers[i].dev)
+			break;
+
+		/*
+		 * If this device number matches the high key, we have
+		 * to pass the high key to the handler to limit the
+		 * query results.  If the device number exceeds the
+		 * low key, zero out the low key so that we get
+		 * everything from the beginning.
+		 */
+		if (handlers[i].dev == head->fmh_keys[1].fmr_device)
+			dkeys[1] = head->fmh_keys[1];
+		if (handlers[i].dev > head->fmh_keys[0].fmr_device)
+			memset(&dkeys[0], 0, sizeof(struct xfs_fsmap));
+
+		error = xfs_trans_alloc_empty(mp, &tp);
+		if (error)
+			break;
+
+		info.dev = handlers[i].dev;
+		info.last = false;
+		info.agno = NULLAGNUMBER;
+		error = handlers[i].fn(tp, dkeys, &info);
+		if (error)
+			break;
+		xfs_trans_cancel(tp);
+		tp = NULL;
+		info.next_daddr = 0;
+	}
+
+	if (tp)
+		xfs_trans_cancel(tp);
+	head->fmh_oflags = FMH_OF_DEV_T;
+	return error;
+}
diff --git a/fs/xfs/xfs_fsmap.h b/fs/xfs/xfs_fsmap.h
new file mode 100644
index 000000000000..0b9bf822595c
--- /dev/null
+++ b/fs/xfs/xfs_fsmap.h
@@ -0,0 +1,53 @@
+/*
+ * Copyright (C) 2017 Oracle.  All Rights Reserved.
+ *
+ * Author: Darrick J. Wong <darrick.wong@oracle.com>
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of the GNU General Public License
+ * as published by the Free Software Foundation; either version 2
+ * of the License, or (at your option) any later version.
+ *
+ * This program is distributed in the hope that it would be useful,
+ * but WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ * GNU General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write the Free Software Foundation,
+ * Inc.,  51 Franklin St, Fifth Floor, Boston, MA  02110-1301, USA.
+ */
+#ifndef __XFS_FSMAP_H__
+#define __XFS_FSMAP_H__
+
+struct fsmap;
+
+/* internal fsmap representation */
+struct xfs_fsmap {
+	dev_t		fmr_device;	/* device id */
+	uint32_t	fmr_flags;	/* mapping flags */
+	uint64_t	fmr_physical;	/* device offset of segment */
+	uint64_t	fmr_owner;	/* owner id */
+	xfs_fileoff_t	fmr_offset;	/* file offset of segment */
+	xfs_filblks_t	fmr_length;	/* length of segment, blocks */
+};
+
+struct xfs_fsmap_head {
+	uint32_t	fmh_iflags;	/* control flags */
+	uint32_t	fmh_oflags;	/* output flags */
+	unsigned int	fmh_count;	/* # of entries in array incl. input */
+	unsigned int	fmh_entries;	/* # of entries filled in (output). */
+
+	struct xfs_fsmap fmh_keys[2];	/* low and high keys */
+};
+
+void xfs_fsmap_from_internal(struct fsmap *dest, struct xfs_fsmap *src);
+void xfs_fsmap_to_internal(struct xfs_fsmap *dest, struct fsmap *src);
+
+/* fsmap to userspace formatter - copy to user & advance pointer */
+typedef int (*xfs_fsmap_format_t)(struct xfs_fsmap *, void *);
+
+int xfs_getfsmap(struct xfs_mount *mp, struct xfs_fsmap_head *head,
+		xfs_fsmap_format_t formatter, void *arg);
+
+#endif /* __XFS_FSMAP_H__ */
diff --git a/fs/xfs/xfs_fsops.c b/fs/xfs/xfs_fsops.c
index 242e8091296d..8f22fc579dbb 100644
--- a/fs/xfs/xfs_fsops.c
+++ b/fs/xfs/xfs_fsops.c
@@ -352,12 +352,7 @@ xfs_growfs_data_private(
 			goto error0;
 		}
 
-		if (xfs_sb_version_hascrc(&mp->m_sb))
-			xfs_btree_init_block(mp, bp, XFS_ABTB_CRC_MAGIC, 0, 1,
-						agno, XFS_BTREE_CRC_BLOCKS);
-		else
-			xfs_btree_init_block(mp, bp, XFS_ABTB_MAGIC, 0, 1,
-						agno, 0);
+		xfs_btree_init_block(mp, bp, XFS_BTNUM_BNO, 0, 1, agno, 0);
 
 		arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
 		arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
@@ -381,12 +376,7 @@ xfs_growfs_data_private(
 			goto error0;
 		}
 
-		if (xfs_sb_version_hascrc(&mp->m_sb))
-			xfs_btree_init_block(mp, bp, XFS_ABTC_CRC_MAGIC, 0, 1,
-						agno, XFS_BTREE_CRC_BLOCKS);
-		else
-			xfs_btree_init_block(mp, bp, XFS_ABTC_MAGIC, 0, 1,
-						agno, 0);
+		xfs_btree_init_block(mp, bp, XFS_BTNUM_CNT, 0, 1, agno, 0);
 
 		arec = XFS_ALLOC_REC_ADDR(mp, XFS_BUF_TO_BLOCK(bp), 1);
 		arec->ar_startblock = cpu_to_be32(mp->m_ag_prealloc_blocks);
@@ -413,8 +403,8 @@ xfs_growfs_data_private(
 				goto error0;
 			}
 
-			xfs_btree_init_block(mp, bp, XFS_RMAP_CRC_MAGIC, 0, 0,
-						agno, XFS_BTREE_CRC_BLOCKS);
+			xfs_btree_init_block(mp, bp, XFS_BTNUM_RMAP, 0, 0,
+						agno, 0);
 			block = XFS_BUF_TO_BLOCK(bp);
 
 
@@ -488,12 +478,7 @@ xfs_growfs_data_private(
 			goto error0;
 		}
 
-		if (xfs_sb_version_hascrc(&mp->m_sb))
-			xfs_btree_init_block(mp, bp, XFS_IBT_CRC_MAGIC, 0, 0,
-						agno, XFS_BTREE_CRC_BLOCKS);
-		else
-			xfs_btree_init_block(mp, bp, XFS_IBT_MAGIC, 0, 0,
-						agno, 0);
+		xfs_btree_init_block(mp, bp, XFS_BTNUM_INO , 0, 0, agno, 0);
 
 		error = xfs_bwrite(bp);
 		xfs_buf_relse(bp);
@@ -513,13 +498,8 @@ xfs_growfs_data_private(
 				goto error0;
 			}
 
-			if (xfs_sb_version_hascrc(&mp->m_sb))
-				xfs_btree_init_block(mp, bp, XFS_FIBT_CRC_MAGIC,
-						     0, 0, agno,
-						     XFS_BTREE_CRC_BLOCKS);
-			else
-				xfs_btree_init_block(mp, bp, XFS_FIBT_MAGIC, 0,
-						     0, agno, 0);
+			xfs_btree_init_block(mp, bp, XFS_BTNUM_FINO,
+						     0, 0, agno, 0);
 
 			error = xfs_bwrite(bp);
 			xfs_buf_relse(bp);
@@ -540,9 +520,8 @@ xfs_growfs_data_private(
 				goto error0;
 			}
 
-			xfs_btree_init_block(mp, bp, XFS_REFC_CRC_MAGIC,
-					     0, 0, agno,
-					     XFS_BTREE_CRC_BLOCKS);
+			xfs_btree_init_block(mp, bp, XFS_BTNUM_REFC,
+					     0, 0, agno, 0);
 
 			error = xfs_bwrite(bp);
 			xfs_buf_relse(bp);
@@ -623,7 +602,7 @@ xfs_growfs_data_private(
 	if (nagimax)
 		mp->m_maxagi = nagimax;
 	if (mp->m_sb.sb_imax_pct) {
-		__uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct;
+		uint64_t icount = mp->m_sb.sb_dblocks * mp->m_sb.sb_imax_pct;
 		do_div(icount, 100);
 		mp->m_maxicount = icount << mp->m_sb.sb_inopblog;
 	} else
@@ -814,17 +793,17 @@ xfs_fs_counts(
 int
 xfs_reserve_blocks(
 	xfs_mount_t             *mp,
-	__uint64_t              *inval,
+	uint64_t              *inval,
 	xfs_fsop_resblks_t      *outval)
 {
-	__int64_t		lcounter, delta;
-	__int64_t		fdblks_delta = 0;
-	__uint64_t		request;
-	__int64_t		free;
+	int64_t			lcounter, delta;
+	int64_t			fdblks_delta = 0;
+	uint64_t		request;
+	int64_t			free;
 	int			error = 0;
 
 	/* If inval is null, report current values and return */
-	if (inval == (__uint64_t *)NULL) {
+	if (inval == (uint64_t *)NULL) {
 		if (!outval)
 			return -EINVAL;
 		outval->resblks = mp->m_resblks;
@@ -925,7 +904,7 @@ out:
 int
 xfs_fs_goingdown(
 	xfs_mount_t	*mp,
-	__uint32_t	inflags)
+	uint32_t	inflags)
 {
 	switch (inflags) {
 	case XFS_FSOP_GOING_FLAGS_DEFAULT: {
diff --git a/fs/xfs/xfs_fsops.h b/fs/xfs/xfs_fsops.h
index f34915898fea..2954c13a3acd 100644
--- a/fs/xfs/xfs_fsops.h
+++ b/fs/xfs/xfs_fsops.h
@@ -22,9 +22,9 @@ extern int xfs_fs_geometry(xfs_mount_t *mp, xfs_fsop_geom_t *geo, int nversion);
 extern int xfs_growfs_data(xfs_mount_t *mp, xfs_growfs_data_t *in);
 extern int xfs_growfs_log(xfs_mount_t *mp, xfs_growfs_log_t *in);
 extern int xfs_fs_counts(xfs_mount_t *mp, xfs_fsop_counts_t *cnt);
-extern int xfs_reserve_blocks(xfs_mount_t *mp, __uint64_t *inval,
+extern int xfs_reserve_blocks(xfs_mount_t *mp, uint64_t *inval,
 				xfs_fsop_resblks_t *outval);
-extern int xfs_fs_goingdown(xfs_mount_t *mp, __uint32_t inflags);
+extern int xfs_fs_goingdown(xfs_mount_t *mp, uint32_t inflags);
 
 extern int xfs_fs_reserve_ag_blocks(struct xfs_mount *mp);
 extern int xfs_fs_unreserve_ag_blocks(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_globals.c b/fs/xfs/xfs_globals.c
index 687a4b01fc53..3e1cc3001bcb 100644
--- a/fs/xfs/xfs_globals.c
+++ b/fs/xfs/xfs_globals.c
@@ -47,4 +47,9 @@ xfs_param_t xfs_params = {
 
 struct xfs_globals xfs_globals = {
 	.log_recovery_delay	=	0,	/* no delay by default */
+#ifdef XFS_ASSERT_FATAL
+	.bug_on_assert		=	true,	/* assert failures BUG() */
+#else
+	.bug_on_assert		=	false,	/* assert failures WARN() */
+#endif
 };
diff --git a/fs/xfs/xfs_icache.c b/fs/xfs/xfs_icache.c
index 70ca4f608321..0a9e6985a0d0 100644
--- a/fs/xfs/xfs_icache.c
+++ b/fs/xfs/xfs_icache.c
@@ -66,7 +66,6 @@ xfs_inode_alloc(
 
 	XFS_STATS_INC(mp, vn_active);
 	ASSERT(atomic_read(&ip->i_pincount) == 0);
-	ASSERT(!spin_is_locked(&ip->i_flags_lock));
 	ASSERT(!xfs_isiflocked(ip));
 	ASSERT(ip->i_ino == 0);
 
@@ -190,7 +189,7 @@ xfs_perag_set_reclaim_tag(
 {
 	struct xfs_mount	*mp = pag->pag_mount;
 
-	ASSERT(spin_is_locked(&pag->pag_ici_lock));
+	lockdep_assert_held(&pag->pag_ici_lock);
 	if (pag->pag_ici_reclaimable++)
 		return;
 
@@ -212,7 +211,7 @@ xfs_perag_clear_reclaim_tag(
 {
 	struct xfs_mount	*mp = pag->pag_mount;
 
-	ASSERT(spin_is_locked(&pag->pag_ici_lock));
+	lockdep_assert_held(&pag->pag_ici_lock);
 	if (--pag->pag_ici_reclaimable)
 		return;
 
@@ -262,6 +261,22 @@ xfs_inode_clear_reclaim_tag(
 	xfs_perag_clear_reclaim_tag(pag);
 }
 
+static void
+xfs_inew_wait(
+	struct xfs_inode	*ip)
+{
+	wait_queue_head_t *wq = bit_waitqueue(&ip->i_flags, __XFS_INEW_BIT);
+	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_INEW_BIT);
+
+	do {
+		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
+		if (!xfs_iflags_test(ip, XFS_INEW))
+			break;
+		schedule();
+	} while (true);
+	finish_wait(wq, &wait.wq_entry);
+}
+
 /*
  * When we recycle a reclaimable inode, we need to re-initialise the VFS inode
  * part of the structure. This is made more complex by the fact we store
@@ -353,6 +368,11 @@ xfs_iget_cache_hit(
 	if (ip->i_flags & XFS_IRECLAIMABLE) {
 		trace_xfs_iget_reclaim(ip);
 
+		if (flags & XFS_IGET_INCORE) {
+			error = -EAGAIN;
+			goto out_error;
+		}
+
 		/*
 		 * We need to set XFS_IRECLAIM to prevent xfs_reclaim_inode
 		 * from stomping over us while we recycle the inode.  We can't
@@ -366,14 +386,17 @@ xfs_iget_cache_hit(
 
 		error = xfs_reinit_inode(mp, inode);
 		if (error) {
+			bool wake;
 			/*
 			 * Re-initializing the inode failed, and we are in deep
 			 * trouble.  Try to re-add it to the reclaim list.
 			 */
 			rcu_read_lock();
 			spin_lock(&ip->i_flags_lock);
-
+			wake = !!__xfs_iflags_test(ip, XFS_INEW);
 			ip->i_flags &= ~(XFS_INEW | XFS_IRECLAIM);
+			if (wake)
+				wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
 			ASSERT(ip->i_flags & XFS_IRECLAIMABLE);
 			trace_xfs_iget_reclaim_fail(ip);
 			goto out_error;
@@ -414,7 +437,8 @@ xfs_iget_cache_hit(
 	if (lock_flags != 0)
 		xfs_ilock(ip, lock_flags);
 
-	xfs_iflags_clear(ip, XFS_ISTALE | XFS_IDONTCACHE);
+	if (!(flags & XFS_IGET_INCORE))
+		xfs_iflags_clear(ip, XFS_ISTALE | XFS_IDONTCACHE);
 	XFS_STATS_INC(mp, xs_ig_found);
 
 	return 0;
@@ -585,6 +609,10 @@ again:
 			goto out_error_or_again;
 	} else {
 		rcu_read_unlock();
+		if (flags & XFS_IGET_INCORE) {
+			error = -ENOENT;
+			goto out_error_or_again;
+		}
 		XFS_STATS_INC(mp, xs_ig_missed);
 
 		error = xfs_iget_cache_miss(mp, pag, tp, ino, &ip,
@@ -605,7 +633,7 @@ again:
 	return 0;
 
 out_error_or_again:
-	if (error == -EAGAIN) {
+	if (!(flags & XFS_IGET_INCORE) && error == -EAGAIN) {
 		delay(1);
 		goto again;
 	}
@@ -614,6 +642,44 @@ out_error_or_again:
 }
 
 /*
+ * "Is this a cached inode that's also allocated?"
+ *
+ * Look up an inode by number in the given file system.  If the inode is
+ * in cache and isn't in purgatory, return 1 if the inode is allocated
+ * and 0 if it is not.  For all other cases (not in cache, being torn
+ * down, etc.), return a negative error code.
+ *
+ * The caller has to prevent inode allocation and freeing activity,
+ * presumably by locking the AGI buffer.   This is to ensure that an
+ * inode cannot transition from allocated to freed until the caller is
+ * ready to allow that.  If the inode is in an intermediate state (new,
+ * reclaimable, or being reclaimed), -EAGAIN will be returned; if the
+ * inode is not in the cache, -ENOENT will be returned.  The caller must
+ * deal with these scenarios appropriately.
+ *
+ * This is a specialized use case for the online scrubber; if you're
+ * reading this, you probably want xfs_iget.
+ */
+int
+xfs_icache_inode_is_allocated(
+	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
+	xfs_ino_t		ino,
+	bool			*inuse)
+{
+	struct xfs_inode	*ip;
+	int			error;
+
+	error = xfs_iget(mp, tp, ino, XFS_IGET_INCORE, 0, &ip);
+	if (error)
+		return error;
+
+	*inuse = !!(VFS_I(ip)->i_mode);
+	IRELE(ip);
+	return 0;
+}
+
+/*
  * The inode lookup is done in batches to keep the amount of lock traffic and
  * radix tree lookups to a minimum. The batch size is a trade off between
  * lookup reduction and stack usage. This is in the reclaim path, so we can't
@@ -623,9 +689,11 @@ out_error_or_again:
 
 STATIC int
 xfs_inode_ag_walk_grab(
-	struct xfs_inode	*ip)
+	struct xfs_inode	*ip,
+	int			flags)
 {
 	struct inode		*inode = VFS_I(ip);
+	bool			newinos = !!(flags & XFS_AGITER_INEW_WAIT);
 
 	ASSERT(rcu_read_lock_held());
 
@@ -643,7 +711,8 @@ xfs_inode_ag_walk_grab(
 		goto out_unlock_noent;
 
 	/* avoid new or reclaimable inodes. Leave for reclaim code to flush */
-	if (__xfs_iflags_test(ip, XFS_INEW | XFS_IRECLAIMABLE | XFS_IRECLAIM))
+	if ((!newinos && __xfs_iflags_test(ip, XFS_INEW)) ||
+	    __xfs_iflags_test(ip, XFS_IRECLAIMABLE | XFS_IRECLAIM))
 		goto out_unlock_noent;
 	spin_unlock(&ip->i_flags_lock);
 
@@ -671,7 +740,8 @@ xfs_inode_ag_walk(
 					   void *args),
 	int			flags,
 	void			*args,
-	int			tag)
+	int			tag,
+	int			iter_flags)
 {
 	uint32_t		first_index;
 	int			last_error = 0;
@@ -713,7 +783,7 @@ restart:
 		for (i = 0; i < nr_found; i++) {
 			struct xfs_inode *ip = batch[i];
 
-			if (done || xfs_inode_ag_walk_grab(ip))
+			if (done || xfs_inode_ag_walk_grab(ip, iter_flags))
 				batch[i] = NULL;
 
 			/*
@@ -741,6 +811,9 @@ restart:
 		for (i = 0; i < nr_found; i++) {
 			if (!batch[i])
 				continue;
+			if ((iter_flags & XFS_AGITER_INEW_WAIT) &&
+			    xfs_iflags_test(batch[i], XFS_INEW))
+				xfs_inew_wait(batch[i]);
 			error = execute(batch[i], flags, args);
 			IRELE(batch[i]);
 			if (error == -EAGAIN) {
@@ -820,12 +893,13 @@ xfs_cowblocks_worker(
 }
 
 int
-xfs_inode_ag_iterator(
+xfs_inode_ag_iterator_flags(
 	struct xfs_mount	*mp,
 	int			(*execute)(struct xfs_inode *ip, int flags,
 					   void *args),
 	int			flags,
-	void			*args)
+	void			*args,
+	int			iter_flags)
 {
 	struct xfs_perag	*pag;
 	int			error = 0;
@@ -835,7 +909,8 @@ xfs_inode_ag_iterator(
 	ag = 0;
 	while ((pag = xfs_perag_get(mp, ag))) {
 		ag = pag->pag_agno + 1;
-		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1);
+		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, -1,
+					  iter_flags);
 		xfs_perag_put(pag);
 		if (error) {
 			last_error = error;
@@ -847,6 +922,17 @@ xfs_inode_ag_iterator(
 }
 
 int
+xfs_inode_ag_iterator(
+	struct xfs_mount	*mp,
+	int			(*execute)(struct xfs_inode *ip, int flags,
+					   void *args),
+	int			flags,
+	void			*args)
+{
+	return xfs_inode_ag_iterator_flags(mp, execute, flags, args, 0);
+}
+
+int
 xfs_inode_ag_iterator_tag(
 	struct xfs_mount	*mp,
 	int			(*execute)(struct xfs_inode *ip, int flags,
@@ -863,7 +949,8 @@ xfs_inode_ag_iterator_tag(
 	ag = 0;
 	while ((pag = xfs_perag_get_tag(mp, ag, tag))) {
 		ag = pag->pag_agno + 1;
-		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag);
+		error = xfs_inode_ag_walk(mp, pag, execute, flags, args, tag,
+					  0);
 		xfs_perag_put(pag);
 		if (error) {
 			last_error = error;
@@ -1322,13 +1409,10 @@ xfs_inode_free_eofblocks(
 	int			flags,
 	void			*args)
 {
-	int ret;
+	int ret = 0;
 	struct xfs_eofblocks *eofb = args;
-	bool need_iolock = true;
 	int match;
 
-	ASSERT(!eofb || (eofb && eofb->eof_scan_owner != 0));
-
 	if (!xfs_can_free_eofblocks(ip, false)) {
 		/* inode could be preallocated or append-only */
 		trace_xfs_inode_free_eofblocks_invalid(ip);
@@ -1356,21 +1440,19 @@ xfs_inode_free_eofblocks(
 		if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE &&
 		    XFS_ISIZE(ip) < eofb->eof_min_file_size)
 			return 0;
-
-		/*
-		 * A scan owner implies we already hold the iolock. Skip it in
-		 * xfs_free_eofblocks() to avoid deadlock. This also eliminates
-		 * the possibility of EAGAIN being returned.
-		 */
-		if (eofb->eof_scan_owner == ip->i_ino)
-			need_iolock = false;
 	}
 
-	ret = xfs_free_eofblocks(ip->i_mount, ip, need_iolock);
-
-	/* don't revisit the inode if we're not waiting */
-	if (ret == -EAGAIN && !(flags & SYNC_WAIT))
-		ret = 0;
+	/*
+	 * If the caller is waiting, return -EAGAIN to keep the background
+	 * scanner moving and revisit the inode in a subsequent pass.
+	 */
+	if (!xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
+		if (flags & SYNC_WAIT)
+			ret = -EAGAIN;
+		return ret;
+	}
+	ret = xfs_free_eofblocks(ip);
+	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 
 	return ret;
 }
@@ -1417,15 +1499,10 @@ __xfs_inode_free_quota_eofblocks(
 	struct xfs_eofblocks eofb = {0};
 	struct xfs_dquot *dq;
 
-	ASSERT(xfs_isilocked(ip, XFS_IOLOCK_EXCL));
-
 	/*
-	 * Set the scan owner to avoid a potential livelock. Otherwise, the scan
-	 * can repeatedly trylock on the inode we're currently processing. We
-	 * run a sync scan to increase effectiveness and use the union filter to
+	 * Run a sync scan to increase effectiveness and use the union filter to
 	 * cover all applicable quotas in a single scan.
 	 */
-	eofb.eof_scan_owner = ip->i_ino;
 	eofb.eof_flags = XFS_EOF_FLAGS_UNION|XFS_EOF_FLAGS_SYNC;
 
 	if (XFS_IS_UQUOTA_ENFORCED(ip->i_mount)) {
@@ -1577,12 +1654,9 @@ xfs_inode_free_cowblocks(
 {
 	int ret;
 	struct xfs_eofblocks *eofb = args;
-	bool need_iolock = true;
 	int match;
 	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 
-	ASSERT(!eofb || (eofb && eofb->eof_scan_owner != 0));
-
 	/*
 	 * Just clear the tag if we have an empty cow fork or none at all. It's
 	 * possible the inode was fully unshared since it was originally tagged.
@@ -1615,28 +1689,16 @@ xfs_inode_free_cowblocks(
 		if (eofb->eof_flags & XFS_EOF_FLAGS_MINFILESIZE &&
 		    XFS_ISIZE(ip) < eofb->eof_min_file_size)
 			return 0;
-
-		/*
-		 * A scan owner implies we already hold the iolock. Skip it in
-		 * xfs_free_eofblocks() to avoid deadlock. This also eliminates
-		 * the possibility of EAGAIN being returned.
-		 */
-		if (eofb->eof_scan_owner == ip->i_ino)
-			need_iolock = false;
 	}
 
 	/* Free the CoW blocks */
-	if (need_iolock) {
-		xfs_ilock(ip, XFS_IOLOCK_EXCL);
-		xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
-	}
+	xfs_ilock(ip, XFS_IOLOCK_EXCL);
+	xfs_ilock(ip, XFS_MMAPLOCK_EXCL);
 
-	ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
+	ret = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, false);
 
-	if (need_iolock) {
-		xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
-		xfs_iunlock(ip, XFS_IOLOCK_EXCL);
-	}
+	xfs_iunlock(ip, XFS_MMAPLOCK_EXCL);
+	xfs_iunlock(ip, XFS_IOLOCK_EXCL);
 
 	return ret;
 }
diff --git a/fs/xfs/xfs_icache.h b/fs/xfs/xfs_icache.h
index a1e02f4708ab..bff4d85e5498 100644
--- a/fs/xfs/xfs_icache.h
+++ b/fs/xfs/xfs_icache.h
@@ -27,7 +27,6 @@ struct xfs_eofblocks {
 	kgid_t		eof_gid;
 	prid_t		eof_prid;
 	__u64		eof_min_file_size;
-	xfs_ino_t	eof_scan_owner;
 };
 
 #define SYNC_WAIT		0x0001	/* wait for i/o to complete */
@@ -48,6 +47,12 @@ struct xfs_eofblocks {
 #define XFS_IGET_CREATE		0x1
 #define XFS_IGET_UNTRUSTED	0x2
 #define XFS_IGET_DONTCACHE	0x4
+#define XFS_IGET_INCORE		0x8	/* don't read from disk or reinit */
+
+/*
+ * flags for AG inode iterator
+ */
+#define XFS_AGITER_INEW_WAIT	0x1	/* wait on new inodes */
 
 int xfs_iget(struct xfs_mount *mp, struct xfs_trans *tp, xfs_ino_t ino,
 	     uint flags, uint lock_flags, xfs_inode_t **ipp);
@@ -80,6 +85,9 @@ void xfs_cowblocks_worker(struct work_struct *);
 int xfs_inode_ag_iterator(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, int flags, void *args),
 	int flags, void *args);
+int xfs_inode_ag_iterator_flags(struct xfs_mount *mp,
+	int (*execute)(struct xfs_inode *ip, int flags, void *args),
+	int flags, void *args, int iter_flags);
 int xfs_inode_ag_iterator_tag(struct xfs_mount *mp,
 	int (*execute)(struct xfs_inode *ip, int flags, void *args),
 	int flags, void *args, int tag);
@@ -102,7 +110,6 @@ xfs_fs_eofblocks_from_user(
 	dst->eof_flags = src->eof_flags;
 	dst->eof_prid = src->eof_prid;
 	dst->eof_min_file_size = src->eof_min_file_size;
-	dst->eof_scan_owner = NULLFSINO;
 
 	dst->eof_uid = INVALID_UID;
 	if (src->eof_flags & XFS_EOF_FLAGS_UID) {
@@ -120,4 +127,7 @@ xfs_fs_eofblocks_from_user(
 	return 0;
 }
 
+int xfs_icache_inode_is_allocated(struct xfs_mount *mp, struct xfs_trans *tp,
+				  xfs_ino_t ino, bool *inuse);
+
 #endif
diff --git a/fs/xfs/xfs_inode.c b/fs/xfs/xfs_inode.c
index de32f0fe47c8..ceef77c0416a 100644
--- a/fs/xfs/xfs_inode.c
+++ b/fs/xfs/xfs_inode.c
@@ -50,6 +50,7 @@
 #include "xfs_log.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_reflink.h"
+#include "xfs_dir2_priv.h"
 
 kmem_zone_t *xfs_inode_zone;
 
@@ -621,17 +622,17 @@ __xfs_iflock(
 	DEFINE_WAIT_BIT(wait, &ip->i_flags, __XFS_IFLOCK_BIT);
 
 	do {
-		prepare_to_wait_exclusive(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait_exclusive(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
 		if (xfs_isiflocked(ip))
 			io_schedule();
 	} while (!xfs_iflock_nowait(ip));
 
-	finish_wait(wq, &wait.wait);
+	finish_wait(wq, &wait.wq_entry);
 }
 
 STATIC uint
 _xfs_dic2xflags(
-	__uint16_t		di_flags,
+	uint16_t		di_flags,
 	uint64_t		di_flags2,
 	bool			has_attr)
 {
@@ -854,8 +855,8 @@ xfs_ialloc(
 		inode->i_version = 1;
 		ip->i_d.di_flags2 = 0;
 		ip->i_d.di_cowextsize = 0;
-		ip->i_d.di_crtime.t_sec = (__int32_t)tv.tv_sec;
-		ip->i_d.di_crtime.t_nsec = (__int32_t)tv.tv_nsec;
+		ip->i_d.di_crtime.t_sec = (int32_t)tv.tv_sec;
+		ip->i_d.di_crtime.t_nsec = (int32_t)tv.tv_nsec;
 	}
 
 
@@ -1615,7 +1616,7 @@ xfs_itruncate_extents(
 
 	/* Remove all pending CoW reservations. */
 	error = xfs_reflink_cancel_cow_blocks(ip, &tp, first_unmap_block,
-			last_block);
+			last_block, true);
 	if (error)
 		goto out;
 
@@ -1692,32 +1693,34 @@ xfs_release(
 	if (xfs_can_free_eofblocks(ip, false)) {
 
 		/*
+		 * Check if the inode is being opened, written and closed
+		 * frequently and we have delayed allocation blocks outstanding
+		 * (e.g. streaming writes from the NFS server), truncating the
+		 * blocks past EOF will cause fragmentation to occur.
+		 *
+		 * In this case don't do the truncation, but we have to be
+		 * careful how we detect this case. Blocks beyond EOF show up as
+		 * i_delayed_blks even when the inode is clean, so we need to
+		 * truncate them away first before checking for a dirty release.
+		 * Hence on the first dirty close we will still remove the
+		 * speculative allocation, but after that we will leave it in
+		 * place.
+		 */
+		if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE))
+			return 0;
+		/*
 		 * If we can't get the iolock just skip truncating the blocks
 		 * past EOF because we could deadlock with the mmap_sem
-		 * otherwise.  We'll get another chance to drop them once the
+		 * otherwise. We'll get another chance to drop them once the
 		 * last reference to the inode is dropped, so we'll never leak
 		 * blocks permanently.
-		 *
-		 * Further, check if the inode is being opened, written and
-		 * closed frequently and we have delayed allocation blocks
-		 * outstanding (e.g. streaming writes from the NFS server),
-		 * truncating the blocks past EOF will cause fragmentation to
-		 * occur.
-		 *
-		 * In this case don't do the truncation, either, but we have to
-		 * be careful how we detect this case. Blocks beyond EOF show
-		 * up as i_delayed_blks even when the inode is clean, so we
-		 * need to truncate them away first before checking for a dirty
-		 * release. Hence on the first dirty close we will still remove
-		 * the speculative allocation, but after that we will leave it
-		 * in place.
 		 */
-		if (xfs_iflags_test(ip, XFS_IDIRTY_RELEASE))
-			return 0;
-
-		error = xfs_free_eofblocks(mp, ip, true);
-		if (error && error != -EAGAIN)
-			return error;
+		if (xfs_ilock_nowait(ip, XFS_IOLOCK_EXCL)) {
+			error = xfs_free_eofblocks(ip);
+			xfs_iunlock(ip, XFS_IOLOCK_EXCL);
+			if (error)
+				return error;
+		}
 
 		/* delalloc blocks after truncation means it really is dirty */
 		if (ip->i_delayed_blks)
@@ -1903,9 +1906,13 @@ xfs_inactive(
 		 * force is true because we are evicting an inode from the
 		 * cache. Post-eof blocks must be freed, lest we end up with
 		 * broken free space accounting.
+		 *
+		 * Note: don't bother with iolock here since lockdep complains
+		 * about acquiring it in reclaim context. We have the only
+		 * reference to the inode at this point anyways.
 		 */
 		if (xfs_can_free_eofblocks(ip, true))
-			xfs_free_eofblocks(mp, ip, false);
+			xfs_free_eofblocks(ip);
 
 		return;
 	}
@@ -2479,11 +2486,11 @@ __xfs_iunpin_wait(
 	xfs_iunpin(ip);
 
 	do {
-		prepare_to_wait(wq, &wait.wait, TASK_UNINTERRUPTIBLE);
+		prepare_to_wait(wq, &wait.wq_entry, TASK_UNINTERRUPTIBLE);
 		if (xfs_ipincount(ip))
 			io_schedule();
 	} while (xfs_ipincount(ip));
-	finish_wait(wq, &wait.wait);
+	finish_wait(wq, &wait.wq_entry);
 }
 
 void
@@ -3482,7 +3489,7 @@ xfs_iflush_int(
 	dip = xfs_buf_offset(bp, ip->i_imap.im_boffset);
 
 	if (XFS_TEST_ERROR(dip->di_magic != cpu_to_be16(XFS_DINODE_MAGIC),
-			       mp, XFS_ERRTAG_IFLUSH_1, XFS_RANDOM_IFLUSH_1)) {
+			       mp, XFS_ERRTAG_IFLUSH_1)) {
 		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
 			"%s: Bad inode %Lu magic number 0x%x, ptr 0x%p",
 			__func__, ip->i_ino, be16_to_cpu(dip->di_magic), dip);
@@ -3492,7 +3499,7 @@ xfs_iflush_int(
 		if (XFS_TEST_ERROR(
 		    (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
 		    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE),
-		    mp, XFS_ERRTAG_IFLUSH_3, XFS_RANDOM_IFLUSH_3)) {
+		    mp, XFS_ERRTAG_IFLUSH_3)) {
 			xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
 				"%s: Bad regular inode %Lu, ptr 0x%p",
 				__func__, ip->i_ino, ip);
@@ -3503,7 +3510,7 @@ xfs_iflush_int(
 		    (ip->i_d.di_format != XFS_DINODE_FMT_EXTENTS) &&
 		    (ip->i_d.di_format != XFS_DINODE_FMT_BTREE) &&
 		    (ip->i_d.di_format != XFS_DINODE_FMT_LOCAL),
-		    mp, XFS_ERRTAG_IFLUSH_4, XFS_RANDOM_IFLUSH_4)) {
+		    mp, XFS_ERRTAG_IFLUSH_4)) {
 			xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
 				"%s: Bad directory inode %Lu, ptr 0x%p",
 				__func__, ip->i_ino, ip);
@@ -3511,8 +3518,7 @@ xfs_iflush_int(
 		}
 	}
 	if (XFS_TEST_ERROR(ip->i_d.di_nextents + ip->i_d.di_anextents >
-				ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5,
-				XFS_RANDOM_IFLUSH_5)) {
+				ip->i_d.di_nblocks, mp, XFS_ERRTAG_IFLUSH_5)) {
 		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
 			"%s: detected corrupt incore inode %Lu, "
 			"total extents = %d, nblocks = %Ld, ptr 0x%p",
@@ -3522,7 +3528,7 @@ xfs_iflush_int(
 		goto corrupt_out;
 	}
 	if (XFS_TEST_ERROR(ip->i_d.di_forkoff > mp->m_sb.sb_inodesize,
-				mp, XFS_ERRTAG_IFLUSH_6, XFS_RANDOM_IFLUSH_6)) {
+				mp, XFS_ERRTAG_IFLUSH_6)) {
 		xfs_alert_tag(mp, XFS_PTAG_IFLUSH,
 			"%s: bad inode %Lu, forkoff 0x%x, ptr 0x%p",
 			__func__, ip->i_ino, ip->i_d.di_forkoff, ip);
@@ -3541,6 +3547,12 @@ xfs_iflush_int(
 	if (ip->i_d.di_version < 3)
 		ip->i_d.di_flushiter++;
 
+	/* Check the inline directory data. */
+	if (S_ISDIR(VFS_I(ip)->i_mode) &&
+	    ip->i_d.di_format == XFS_DINODE_FMT_LOCAL &&
+	    xfs_dir2_sf_verify(ip))
+		goto corrupt_out;
+
 	/*
 	 * Copy the dirty parts of the inode into the on-disk inode.  We always
 	 * copy out the core of the inode, because if the inode is dirty at all
diff --git a/fs/xfs/xfs_inode.h b/fs/xfs/xfs_inode.h
index 10dcf27b4c85..0ee453de239a 100644
--- a/fs/xfs/xfs_inode.h
+++ b/fs/xfs/xfs_inode.h
@@ -192,8 +192,8 @@ static inline void
 xfs_set_projid(struct xfs_inode *ip,
 		prid_t projid)
 {
-	ip->i_d.di_projid_hi = (__uint16_t) (projid >> 16);
-	ip->i_d.di_projid_lo = (__uint16_t) (projid & 0xffff);
+	ip->i_d.di_projid_hi = (uint16_t) (projid >> 16);
+	ip->i_d.di_projid_lo = (uint16_t) (projid & 0xffff);
 }
 
 static inline prid_t
@@ -216,7 +216,8 @@ static inline bool xfs_is_reflink_inode(struct xfs_inode *ip)
 #define XFS_IRECLAIM		(1 << 0) /* started reclaiming this inode */
 #define XFS_ISTALE		(1 << 1) /* inode has been staled */
 #define XFS_IRECLAIMABLE	(1 << 2) /* inode can be reclaimed */
-#define XFS_INEW		(1 << 3) /* inode has just been allocated */
+#define __XFS_INEW_BIT		3	 /* inode has just been allocated */
+#define XFS_INEW		(1 << __XFS_INEW_BIT)
 #define XFS_ITRUNCATED		(1 << 5) /* truncated down so flush-on-close */
 #define XFS_IDIRTY_RELEASE	(1 << 6) /* dirty release already seen */
 #define __XFS_IFLOCK_BIT	7	 /* inode is being flushed right now */
@@ -444,9 +445,6 @@ int	xfs_zero_eof(struct xfs_inode *ip, xfs_off_t offset,
 		     xfs_fsize_t isize, bool *did_zeroing);
 int	xfs_zero_range(struct xfs_inode *ip, xfs_off_t pos, xfs_off_t count,
 		bool *did_zero);
-loff_t	__xfs_seek_hole_data(struct inode *inode, loff_t start,
-			     loff_t eof, int whence);
-
 
 /* from xfs_iops.c */
 extern void xfs_setup_inode(struct xfs_inode *ip);
@@ -464,6 +462,7 @@ static inline void xfs_finish_inode_setup(struct xfs_inode *ip)
 	xfs_iflags_clear(ip, XFS_INEW);
 	barrier();
 	unlock_new_inode(VFS_I(ip));
+	wake_up_bit(&ip->i_flags, __XFS_INEW_BIT);
 }
 
 static inline void xfs_setup_existing_inode(struct xfs_inode *ip)
diff --git a/fs/xfs/xfs_inode_item.c b/fs/xfs/xfs_inode_item.c
index d90e7811ccdd..013cc78d7daf 100644
--- a/fs/xfs/xfs_inode_item.c
+++ b/fs/xfs/xfs_inode_item.c
@@ -731,22 +731,27 @@ xfs_iflush_done(
 	 * holding the lock before removing the inode from the AIL.
 	 */
 	if (need_ail) {
-		struct xfs_log_item *log_items[need_ail];
-		int i = 0;
+		bool			mlip_changed = false;
+
+		/* this is an opencoded batch version of xfs_trans_ail_delete */
 		spin_lock(&ailp->xa_lock);
 		for (blip = lip; blip; blip = blip->li_bio_list) {
-			iip = INODE_ITEM(blip);
-			if (iip->ili_logged &&
-			    blip->li_lsn == iip->ili_flush_lsn) {
-				log_items[i++] = blip;
-			}
-			ASSERT(i <= need_ail);
+			if (INODE_ITEM(blip)->ili_logged &&
+			    blip->li_lsn == INODE_ITEM(blip)->ili_flush_lsn)
+				mlip_changed |= xfs_ail_delete_one(ailp, blip);
 		}
-		/* xfs_trans_ail_delete_bulk() drops the AIL lock. */
-		xfs_trans_ail_delete_bulk(ailp, log_items, i,
-					  SHUTDOWN_CORRUPT_INCORE);
-	}
 
+		if (mlip_changed) {
+			if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount))
+				xlog_assign_tail_lsn_locked(ailp->xa_mount);
+			if (list_empty(&ailp->xa_ail))
+				wake_up_all(&ailp->xa_empty);
+		}
+		spin_unlock(&ailp->xa_lock);
+
+		if (mlip_changed)
+			xfs_log_space_wake(ailp->xa_mount);
+	}
 
 	/*
 	 * clean up and unlock the flush lock now we are done. We can clear the
@@ -829,9 +834,7 @@ xfs_inode_item_format_convert(
 		in_f->ilf_dsize = in_f32->ilf_dsize;
 		in_f->ilf_ino = in_f32->ilf_ino;
 		/* copy biggest field of ilf_u */
-		memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
-		       in_f32->ilf_u.ilfu_uuid.__u_bits,
-		       sizeof(uuid_t));
+		uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f32->ilf_u.ilfu_uuid);
 		in_f->ilf_blkno = in_f32->ilf_blkno;
 		in_f->ilf_len = in_f32->ilf_len;
 		in_f->ilf_boffset = in_f32->ilf_boffset;
@@ -846,9 +849,7 @@ xfs_inode_item_format_convert(
 		in_f->ilf_dsize = in_f64->ilf_dsize;
 		in_f->ilf_ino = in_f64->ilf_ino;
 		/* copy biggest field of ilf_u */
-		memcpy(in_f->ilf_u.ilfu_uuid.__u_bits,
-		       in_f64->ilf_u.ilfu_uuid.__u_bits,
-		       sizeof(uuid_t));
+		uuid_copy(&in_f->ilf_u.ilfu_uuid, &in_f64->ilf_u.ilfu_uuid);
 		in_f->ilf_blkno = in_f64->ilf_blkno;
 		in_f->ilf_len = in_f64->ilf_len;
 		in_f->ilf_boffset = in_f64->ilf_boffset;
diff --git a/fs/xfs/xfs_ioctl.c b/fs/xfs/xfs_ioctl.c
index c67cfb451fd3..9c0c7a920304 100644
--- a/fs/xfs/xfs_ioctl.c
+++ b/fs/xfs/xfs_ioctl.c
@@ -41,8 +41,12 @@
 #include "xfs_trans.h"
 #include "xfs_pnfs.h"
 #include "xfs_acl.h"
+#include "xfs_btree.h"
+#include <linux/fsmap.h>
+#include "xfs_fsmap.h"
 
 #include <linux/capability.h>
+#include <linux/cred.h>
 #include <linux/dcache.h>
 #include <linux/mount.h>
 #include <linux/namei.h>
@@ -116,8 +120,7 @@ xfs_find_handle(
 		handle.ha_fid.fid_pad = 0;
 		handle.ha_fid.fid_gen = inode->i_generation;
 		handle.ha_fid.fid_ino = ip->i_ino;
-
-		hsize = XFS_HSIZE(handle);
+		hsize = sizeof(xfs_handle_t);
 	}
 
 	error = -EFAULT;
@@ -440,8 +443,8 @@ xfs_attrmulti_attr_get(
 	struct inode		*inode,
 	unsigned char		*name,
 	unsigned char		__user *ubuf,
-	__uint32_t		*len,
-	__uint32_t		flags)
+	uint32_t		*len,
+	uint32_t		flags)
 {
 	unsigned char		*kbuf;
 	int			error = -EFAULT;
@@ -469,8 +472,8 @@ xfs_attrmulti_attr_set(
 	struct inode		*inode,
 	unsigned char		*name,
 	const unsigned char	__user *ubuf,
-	__uint32_t		len,
-	__uint32_t		flags)
+	uint32_t		len,
+	uint32_t		flags)
 {
 	unsigned char		*kbuf;
 	int			error;
@@ -495,7 +498,7 @@ int
 xfs_attrmulti_attr_remove(
 	struct inode		*inode,
 	unsigned char		*name,
-	__uint32_t		flags)
+	uint32_t		flags)
 {
 	int			error;
 
@@ -873,7 +876,7 @@ xfs_merge_ioc_xflags(
 
 STATIC unsigned int
 xfs_di2lxflags(
-	__uint16_t	di_flags)
+	uint16_t	di_flags)
 {
 	unsigned int	flags = 0;
 
@@ -1284,7 +1287,7 @@ xfs_ioctl_setattr_check_projid(
 	struct fsxattr		*fa)
 {
 	/* Disallow 32bit project ids if projid32bit feature is not enabled. */
-	if (fa->fsx_projid > (__uint16_t)-1 &&
+	if (fa->fsx_projid > (uint16_t)-1 &&
 	    !xfs_sb_version_hasprojid32bit(&ip->i_mount->m_sb))
 		return -EINVAL;
 
@@ -1524,7 +1527,7 @@ out_drop_write:
 }
 
 STATIC int
-xfs_getbmap_format(void **ap, struct getbmapx *bmv, int *full)
+xfs_getbmap_format(void **ap, struct getbmapx *bmv)
 {
 	struct getbmap __user	*base = (struct getbmap __user *)*ap;
 
@@ -1542,10 +1545,11 @@ xfs_ioc_getbmap(
 	unsigned int		cmd,
 	void			__user *arg)
 {
-	struct getbmapx		bmx;
+	struct getbmapx		bmx = { 0 };
 	int			error;
 
-	if (copy_from_user(&bmx, arg, sizeof(struct getbmapx)))
+	/* struct getbmap is a strict subset of struct getbmapx. */
+	if (copy_from_user(&bmx, arg, offsetof(struct getbmapx, bmv_iflags)))
 		return -EFAULT;
 
 	if (bmx.bmv_count < 2)
@@ -1567,7 +1571,7 @@ xfs_ioc_getbmap(
 }
 
 STATIC int
-xfs_getbmapx_format(void **ap, struct getbmapx *bmv, int *full)
+xfs_getbmapx_format(void **ap, struct getbmapx *bmv)
 {
 	struct getbmapx __user	*base = (struct getbmapx __user *)*ap;
 
@@ -1607,6 +1611,84 @@ xfs_ioc_getbmapx(
 	return 0;
 }
 
+struct getfsmap_info {
+	struct xfs_mount	*mp;
+	struct fsmap_head __user *data;
+	unsigned int		idx;
+	__u32			last_flags;
+};
+
+STATIC int
+xfs_getfsmap_format(struct xfs_fsmap *xfm, void *priv)
+{
+	struct getfsmap_info	*info = priv;
+	struct fsmap		fm;
+
+	trace_xfs_getfsmap_mapping(info->mp, xfm);
+
+	info->last_flags = xfm->fmr_flags;
+	xfs_fsmap_from_internal(&fm, xfm);
+	if (copy_to_user(&info->data->fmh_recs[info->idx++], &fm,
+			sizeof(struct fsmap)))
+		return -EFAULT;
+
+	return 0;
+}
+
+STATIC int
+xfs_ioc_getfsmap(
+	struct xfs_inode	*ip,
+	struct fsmap_head	__user *arg)
+{
+	struct getfsmap_info	info = { NULL };
+	struct xfs_fsmap_head	xhead = {0};
+	struct fsmap_head	head;
+	bool			aborted = false;
+	int			error;
+
+	if (copy_from_user(&head, arg, sizeof(struct fsmap_head)))
+		return -EFAULT;
+	if (memchr_inv(head.fmh_reserved, 0, sizeof(head.fmh_reserved)) ||
+	    memchr_inv(head.fmh_keys[0].fmr_reserved, 0,
+		       sizeof(head.fmh_keys[0].fmr_reserved)) ||
+	    memchr_inv(head.fmh_keys[1].fmr_reserved, 0,
+		       sizeof(head.fmh_keys[1].fmr_reserved)))
+		return -EINVAL;
+
+	xhead.fmh_iflags = head.fmh_iflags;
+	xhead.fmh_count = head.fmh_count;
+	xfs_fsmap_to_internal(&xhead.fmh_keys[0], &head.fmh_keys[0]);
+	xfs_fsmap_to_internal(&xhead.fmh_keys[1], &head.fmh_keys[1]);
+
+	trace_xfs_getfsmap_low_key(ip->i_mount, &xhead.fmh_keys[0]);
+	trace_xfs_getfsmap_high_key(ip->i_mount, &xhead.fmh_keys[1]);
+
+	info.mp = ip->i_mount;
+	info.data = arg;
+	error = xfs_getfsmap(ip->i_mount, &xhead, xfs_getfsmap_format, &info);
+	if (error == XFS_BTREE_QUERY_RANGE_ABORT) {
+		error = 0;
+		aborted = true;
+	} else if (error)
+		return error;
+
+	/* If we didn't abort, set the "last" flag in the last fmx */
+	if (!aborted && info.idx) {
+		info.last_flags |= FMR_OF_LAST;
+		if (copy_to_user(&info.data->fmh_recs[info.idx - 1].fmr_flags,
+				&info.last_flags, sizeof(info.last_flags)))
+			return -EFAULT;
+	}
+
+	/* copy back header */
+	head.fmh_entries = xhead.fmh_entries;
+	head.fmh_oflags = xhead.fmh_oflags;
+	if (copy_to_user(arg, &head, sizeof(struct fsmap_head)))
+		return -EFAULT;
+
+	return 0;
+}
+
 int
 xfs_ioc_swapext(
 	xfs_swapext_t	*sxp)
@@ -1787,6 +1869,9 @@ xfs_file_ioctl(
 	case XFS_IOC_GETBMAPX:
 		return xfs_ioc_getbmapx(ip, arg);
 
+	case FS_IOC_GETFSMAP:
+		return xfs_ioc_getfsmap(ip, arg);
+
 	case XFS_IOC_FD_TO_HANDLE:
 	case XFS_IOC_PATH_TO_HANDLE:
 	case XFS_IOC_PATH_TO_FSHANDLE: {
@@ -1846,7 +1931,7 @@ xfs_file_ioctl(
 
 	case XFS_IOC_SET_RESBLKS: {
 		xfs_fsop_resblks_t inout;
-		__uint64_t	   in;
+		uint64_t	   in;
 
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
@@ -1932,12 +2017,12 @@ xfs_file_ioctl(
 	}
 
 	case XFS_IOC_GOINGDOWN: {
-		__uint32_t in;
+		uint32_t in;
 
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 
-		if (get_user(in, (__uint32_t __user *)arg))
+		if (get_user(in, (uint32_t __user *)arg))
 			return -EFAULT;
 
 		return xfs_fs_goingdown(mp, in);
@@ -1952,14 +2037,14 @@ xfs_file_ioctl(
 		if (copy_from_user(&in, arg, sizeof(in)))
 			return -EFAULT;
 
-		return xfs_errortag_add(in.errtag, mp);
+		return xfs_errortag_add(mp, in.errtag);
 	}
 
 	case XFS_IOC_ERROR_CLEARALL:
 		if (!capable(CAP_SYS_ADMIN))
 			return -EPERM;
 
-		return xfs_errortag_clearall(mp, 1);
+		return xfs_errortag_clearall(mp);
 
 	case XFS_IOC_FREE_EOFBLOCKS: {
 		struct xfs_fs_eofblocks eofb;
diff --git a/fs/xfs/xfs_ioctl.h b/fs/xfs/xfs_ioctl.h
index 8b52881bfd90..e86c3ea137d2 100644
--- a/fs/xfs/xfs_ioctl.h
+++ b/fs/xfs/xfs_ioctl.h
@@ -48,22 +48,22 @@ xfs_attrmulti_attr_get(
 	struct inode		*inode,
 	unsigned char		*name,
 	unsigned char		__user *ubuf,
-	__uint32_t		*len,
-	__uint32_t		flags);
+	uint32_t		*len,
+	uint32_t		flags);
 
 extern int
 xfs_attrmulti_attr_set(
 	struct inode		*inode,
 	unsigned char		*name,
 	const unsigned char	__user *ubuf,
-	__uint32_t		len,
-	__uint32_t		flags);
+	uint32_t		len,
+	uint32_t		flags);
 
 extern int
 xfs_attrmulti_attr_remove(
 	struct inode		*inode,
 	unsigned char		*name,
-	__uint32_t		flags);
+	uint32_t		flags);
 
 extern struct dentry *
 xfs_handle_to_dentry(
diff --git a/fs/xfs/xfs_ioctl32.c b/fs/xfs/xfs_ioctl32.c
index 7c49938c5aed..fa0bc4d46065 100644
--- a/fs/xfs/xfs_ioctl32.c
+++ b/fs/xfs/xfs_ioctl32.c
@@ -20,6 +20,7 @@
 #include <linux/mount.h>
 #include <linux/slab.h>
 #include <linux/uaccess.h>
+#include <linux/fsmap.h>
 #include "xfs.h"
 #include "xfs_fs.h"
 #include "xfs_format.h"
@@ -554,6 +555,7 @@ xfs_file_compat_ioctl(
 	case XFS_IOC_GOINGDOWN:
 	case XFS_IOC_ERROR_INJECTION:
 	case XFS_IOC_ERROR_CLEARALL:
+	case FS_IOC_GETFSMAP:
 		return xfs_file_ioctl(filp, cmd, p);
 #ifndef BROKEN_X86_ALIGNMENT
 	/* These are handled fine if no alignment issues */
diff --git a/fs/xfs/xfs_ioctl32.h b/fs/xfs/xfs_ioctl32.h
index b1bb45444df8..5492bcf6f442 100644
--- a/fs/xfs/xfs_ioctl32.h
+++ b/fs/xfs/xfs_ioctl32.h
@@ -112,9 +112,9 @@ typedef struct compat_xfs_fsop_handlereq {
 
 /* The bstat field in the swapext struct needs translation */
 typedef struct compat_xfs_swapext {
-	__int64_t		sx_version;	/* version */
-	__int64_t		sx_fdtarget;	/* fd of target file */
-	__int64_t		sx_fdtmp;	/* fd of tmp file */
+	int64_t			sx_version;	/* version */
+	int64_t			sx_fdtarget;	/* fd of target file */
+	int64_t			sx_fdtmp;	/* fd of tmp file */
 	xfs_off_t		sx_offset;	/* offset into file */
 	xfs_off_t		sx_length;	/* leng from offset */
 	char			sx_pad[16];	/* pad space, unused */
diff --git a/fs/xfs/xfs_iomap.c b/fs/xfs/xfs_iomap.c
index 1aa3abd67b36..813394c62849 100644
--- a/fs/xfs/xfs_iomap.c
+++ b/fs/xfs/xfs_iomap.c
@@ -162,7 +162,7 @@ xfs_iomap_write_direct(
 	xfs_fileoff_t	last_fsb;
 	xfs_filblks_t	count_fsb, resaligned;
 	xfs_fsblock_t	firstfsb;
-	xfs_extlen_t	extsz, temp;
+	xfs_extlen_t	extsz;
 	int		nimaps;
 	int		quota_flag;
 	int		rt;
@@ -203,14 +203,7 @@ xfs_iomap_write_direct(
 	}
 	count_fsb = last_fsb - offset_fsb;
 	ASSERT(count_fsb > 0);
-
-	resaligned = count_fsb;
-	if (unlikely(extsz)) {
-		if ((temp = do_mod(offset_fsb, extsz)))
-			resaligned += temp;
-		if ((temp = do_mod(resaligned, extsz)))
-			resaligned += extsz - temp;
-	}
+	resaligned = xfs_aligned_fsb_count(offset_fsb, count_fsb, extsz);
 
 	if (unlikely(rt)) {
 		resrtextents = qblocks = resaligned;
@@ -247,7 +240,7 @@ xfs_iomap_write_direct(
 	 */
 	if (IS_DAX(VFS_I(ip))) {
 		bmapi_flags = XFS_BMAPI_CONVERT | XFS_BMAPI_ZERO;
-		if (ISUNWRITTEN(imap)) {
+		if (imap->br_state == XFS_EXT_UNWRITTEN) {
 			tflags |= XFS_TRANS_RESERVE;
 			resblks = XFS_DIOSTRAT_SPACE_RES(mp, 0) << 1;
 		}
@@ -550,7 +543,7 @@ xfs_file_iomap_begin_delay(
 	if (unlikely(XFS_TEST_ERROR(
 	    (XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_EXTENTS &&
 	     XFS_IFORK_FORMAT(ip, XFS_DATA_FORK) != XFS_DINODE_FMT_BTREE),
-	     mp, XFS_ERRTAG_BMAPIFORMAT, XFS_RANDOM_BMAPIFORMAT))) {
+	     mp, XFS_ERRTAG_BMAPIFORMAT))) {
 		XFS_ERROR_REPORT(__func__, XFS_ERRLEVEL_LOW, mp);
 		error = -EFSCORRUPTED;
 		goto out_unlock;
@@ -637,6 +630,11 @@ retry:
 		goto out_unlock;
 	}
 
+	/*
+	 * Flag newly allocated delalloc blocks with IOMAP_F_NEW so we punch
+	 * them out if the write happens to fail.
+	 */
+	iomap->flags = IOMAP_F_NEW;
 	trace_xfs_iomap_alloc(ip, offset, count, 0, &got);
 done:
 	if (isnullstartblock(got.br_startblock))
@@ -685,7 +683,7 @@ xfs_iomap_write_allocate(
 	int		nres;
 
 	if (whichfork == XFS_COW_FORK)
-		flags |= XFS_BMAPI_COWFORK;
+		flags |= XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC;
 
 	/*
 	 * Make sure that the dquots are there.
@@ -947,7 +945,7 @@ static inline bool imap_needs_alloc(struct inode *inode,
 	return !nimaps ||
 		imap->br_startblock == HOLESTARTBLOCK ||
 		imap->br_startblock == DELAYSTARTBLOCK ||
-		(IS_DAX(inode) && ISUNWRITTEN(imap));
+		(IS_DAX(inode) && imap->br_state == XFS_EXT_UNWRITTEN);
 }
 
 static inline bool need_excl_ilock(struct xfs_inode *ip, unsigned flags)
@@ -978,6 +976,7 @@ xfs_file_iomap_begin(
 	int			nimaps = 1, error = 0;
 	bool			shared = false, trimmed = false;
 	unsigned		lockmode;
+	struct block_device	*bdev;
 
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
@@ -996,53 +995,51 @@ xfs_file_iomap_begin(
 		lockmode = xfs_ilock_data_map_shared(ip);
 	}
 
+	if ((flags & IOMAP_NOWAIT) && !(ip->i_df.if_flags & XFS_IFEXTENTS)) {
+		error = -EAGAIN;
+		goto out_unlock;
+	}
+
 	ASSERT(offset <= mp->m_super->s_maxbytes);
 	if ((xfs_fsize_t)offset + length > mp->m_super->s_maxbytes)
 		length = mp->m_super->s_maxbytes - offset;
 	offset_fsb = XFS_B_TO_FSBT(mp, offset);
 	end_fsb = XFS_B_TO_FSB(mp, offset + length);
 
-	if (xfs_is_reflink_inode(ip) &&
-	    (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT)) {
-		shared = xfs_reflink_find_cow_mapping(ip, offset, &imap);
-		if (shared) {
-			xfs_iunlock(ip, lockmode);
-			goto alloc_done;
-		}
-		ASSERT(!isnullstartblock(imap.br_startblock));
-	}
-
 	error = xfs_bmapi_read(ip, offset_fsb, end_fsb - offset_fsb, &imap,
 			       &nimaps, 0);
 	if (error)
 		goto out_unlock;
 
-	if ((flags & IOMAP_REPORT) ||
-	    (xfs_is_reflink_inode(ip) &&
-	     (flags & IOMAP_WRITE) && (flags & IOMAP_DIRECT))) {
+	if (flags & IOMAP_REPORT) {
 		/* Trim the mapping to the nearest shared extent boundary. */
 		error = xfs_reflink_trim_around_shared(ip, &imap, &shared,
 				&trimmed);
 		if (error)
 			goto out_unlock;
-
-		/*
-		 * We're here because we're trying to do a directio write to a
-		 * region that isn't aligned to a filesystem block.  If the
-		 * extent is shared, fall back to buffered mode to handle the
-		 * RMW.
-		 */
-		if (!(flags & IOMAP_REPORT) && shared) {
-			trace_xfs_reflink_bounce_dio_write(ip, &imap);
-			error = -EREMCHG;
-			goto out_unlock;
-		}
 	}
 
 	if ((flags & (IOMAP_WRITE | IOMAP_ZERO)) && xfs_is_reflink_inode(ip)) {
-		error = xfs_reflink_reserve_cow(ip, &imap, &shared);
-		if (error)
-			goto out_unlock;
+		if (flags & IOMAP_DIRECT) {
+			/*
+			 * A reflinked inode will result in CoW alloc.
+			 * FIXME: It could still overwrite on unshared extents
+			 * and not need allocation.
+			 */
+			if (flags & IOMAP_NOWAIT) {
+				error = -EAGAIN;
+				goto out_unlock;
+			}
+			/* may drop and re-acquire the ilock */
+			error = xfs_reflink_allocate_cow(ip, &imap, &shared,
+					&lockmode);
+			if (error)
+				goto out_unlock;
+		} else {
+			error = xfs_reflink_reserve_cow(ip, &imap, &shared);
+			if (error)
+				goto out_unlock;
+		}
 
 		end_fsb = imap.br_startoff + imap.br_blockcount;
 		length = XFS_FSB_TO_B(mp, end_fsb) - offset;
@@ -1050,6 +1047,14 @@ xfs_file_iomap_begin(
 
 	if ((flags & IOMAP_WRITE) && imap_needs_alloc(inode, &imap, nimaps)) {
 		/*
+		 * If nowait is set bail since we are going to make
+		 * allocations.
+		 */
+		if (flags & IOMAP_NOWAIT) {
+			error = -EAGAIN;
+			goto out_unlock;
+		}
+		/*
 		 * We cap the maximum length we map here to MAX_WRITEBACK_PAGES
 		 * pages to keep the chunks of work done where somewhat symmetric
 		 * with the work writeback does. This is a completely arbitrary
@@ -1071,7 +1076,6 @@ xfs_file_iomap_begin(
 		if (error)
 			return error;
 
-alloc_done:
 		iomap->flags = IOMAP_F_NEW;
 		trace_xfs_iomap_alloc(ip, offset, length, 0, &imap);
 	} else {
@@ -1082,6 +1086,14 @@ alloc_done:
 	}
 
 	xfs_bmbt_to_iomap(ip, iomap, &imap);
+
+	/* optionally associate a dax device with the iomap bdev */
+	bdev = iomap->bdev;
+	if (blk_queue_dax(bdev->bd_queue))
+		iomap->dax_dev = fs_dax_get_by_host(bdev->bd_disk->disk_name);
+	else
+		iomap->dax_dev = NULL;
+
 	if (shared)
 		iomap->flags |= IOMAP_F_SHARED;
 	return 0;
@@ -1095,25 +1107,46 @@ xfs_file_iomap_end_delalloc(
 	struct xfs_inode	*ip,
 	loff_t			offset,
 	loff_t			length,
-	ssize_t			written)
+	ssize_t			written,
+	struct iomap		*iomap)
 {
 	struct xfs_mount	*mp = ip->i_mount;
 	xfs_fileoff_t		start_fsb;
 	xfs_fileoff_t		end_fsb;
 	int			error = 0;
 
-	start_fsb = XFS_B_TO_FSB(mp, offset + written);
+	/*
+	 * Behave as if the write failed if drop writes is enabled. Set the NEW
+	 * flag to force delalloc cleanup.
+	 */
+	if (XFS_TEST_ERROR(false, mp, XFS_ERRTAG_DROP_WRITES)) {
+		iomap->flags |= IOMAP_F_NEW;
+		written = 0;
+	}
+
+	/*
+	 * start_fsb refers to the first unused block after a short write. If
+	 * nothing was written, round offset down to point at the first block in
+	 * the range.
+	 */
+	if (unlikely(!written))
+		start_fsb = XFS_B_TO_FSBT(mp, offset);
+	else
+		start_fsb = XFS_B_TO_FSB(mp, offset + written);
 	end_fsb = XFS_B_TO_FSB(mp, offset + length);
 
 	/*
-	 * Trim back delalloc blocks if we didn't manage to write the whole
-	 * range reserved.
+	 * Trim delalloc blocks if they were allocated by this write and we
+	 * didn't manage to write the whole range.
 	 *
 	 * We don't need to care about racing delalloc as we hold i_mutex
 	 * across the reserve/allocate/unreserve calls. If there are delalloc
 	 * blocks in the range, they are ours.
 	 */
-	if (start_fsb < end_fsb) {
+	if ((iomap->flags & IOMAP_F_NEW) && start_fsb < end_fsb) {
+		truncate_pagecache_range(VFS_I(ip), XFS_FSB_TO_B(mp, start_fsb),
+					 XFS_FSB_TO_B(mp, end_fsb) - 1);
+
 		xfs_ilock(ip, XFS_ILOCK_EXCL);
 		error = xfs_bmap_punch_delalloc_range(ip, start_fsb,
 					       end_fsb - start_fsb);
@@ -1138,13 +1171,14 @@ xfs_file_iomap_end(
 	unsigned		flags,
 	struct iomap		*iomap)
 {
+	fs_put_dax(iomap->dax_dev);
 	if ((flags & IOMAP_WRITE) && iomap->type == IOMAP_DELALLOC)
 		return xfs_file_iomap_end_delalloc(XFS_I(inode), offset,
-				length, written);
+				length, written, iomap);
 	return 0;
 }
 
-struct iomap_ops xfs_iomap_ops = {
+const struct iomap_ops xfs_iomap_ops = {
 	.iomap_begin		= xfs_file_iomap_begin,
 	.iomap_end		= xfs_file_iomap_end,
 };
@@ -1168,10 +1202,10 @@ xfs_xattr_iomap_begin(
 	if (XFS_FORCED_SHUTDOWN(mp))
 		return -EIO;
 
-	lockmode = xfs_ilock_data_map_shared(ip);
+	lockmode = xfs_ilock_attr_map_shared(ip);
 
 	/* if there are no attribute fork or extents, return ENOENT */
-	if (XFS_IFORK_Q(ip) || !ip->i_d.di_anextents) {
+	if (!XFS_IFORK_Q(ip) || !ip->i_d.di_anextents) {
 		error = -ENOENT;
 		goto out_unlock;
 	}
@@ -1190,6 +1224,6 @@ out_unlock:
 	return error;
 }
 
-struct iomap_ops xfs_xattr_iomap_ops = {
+const struct iomap_ops xfs_xattr_iomap_ops = {
 	.iomap_begin		= xfs_xattr_iomap_begin,
 };
diff --git a/fs/xfs/xfs_iomap.h b/fs/xfs/xfs_iomap.h
index 6d45cf01fcff..00db3ecea084 100644
--- a/fs/xfs/xfs_iomap.h
+++ b/fs/xfs/xfs_iomap.h
@@ -33,7 +33,27 @@ void xfs_bmbt_to_iomap(struct xfs_inode *, struct iomap *,
 		struct xfs_bmbt_irec *);
 xfs_extlen_t xfs_eof_alignment(struct xfs_inode *ip, xfs_extlen_t extsize);
 
-extern struct iomap_ops xfs_iomap_ops;
-extern struct iomap_ops xfs_xattr_iomap_ops;
+static inline xfs_filblks_t
+xfs_aligned_fsb_count(
+	xfs_fileoff_t		offset_fsb,
+	xfs_filblks_t		count_fsb,
+	xfs_extlen_t		extsz)
+{
+	if (extsz) {
+		xfs_extlen_t	align;
+
+		align = do_mod(offset_fsb, extsz);
+		if (align)
+			count_fsb += align;
+		align = do_mod(count_fsb, extsz);
+		if (align)
+			count_fsb += extsz - align;
+	}
+
+	return count_fsb;
+}
+
+extern const struct iomap_ops xfs_iomap_ops;
+extern const struct iomap_ops xfs_xattr_iomap_ops;
 
 #endif /* __XFS_IOMAP_H__*/
diff --git a/fs/xfs/xfs_iops.c b/fs/xfs/xfs_iops.c
index 22c16155f1b4..469c9fa4c178 100644
--- a/fs/xfs/xfs_iops.c
+++ b/fs/xfs/xfs_iops.c
@@ -190,12 +190,12 @@ xfs_generic_create(
 
 #ifdef CONFIG_XFS_POSIX_ACL
 	if (default_acl) {
-		error = xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
+		error = __xfs_set_acl(inode, default_acl, ACL_TYPE_DEFAULT);
 		if (error)
 			goto out_cleanup_inode;
 	}
 	if (acl) {
-		error = xfs_set_acl(inode, acl, ACL_TYPE_ACCESS);
+		error = __xfs_set_acl(inode, acl, ACL_TYPE_ACCESS);
 		if (error)
 			goto out_cleanup_inode;
 	}
@@ -460,7 +460,7 @@ xfs_vn_get_link(
 	if (!dentry)
 		return ERR_PTR(-ECHILD);
 
-	link = kmalloc(MAXPATHLEN+1, GFP_KERNEL);
+	link = kmalloc(XFS_SYMLINK_MAXLEN+1, GFP_KERNEL);
 	if (!link)
 		goto out_err;
 
@@ -489,11 +489,12 @@ xfs_vn_get_link_inline(
 
 STATIC int
 xfs_vn_getattr(
-	struct vfsmount		*mnt,
-	struct dentry		*dentry,
-	struct kstat		*stat)
+	const struct path	*path,
+	struct kstat		*stat,
+	u32			request_mask,
+	unsigned int		query_flags)
 {
-	struct inode		*inode = d_inode(dentry);
+	struct inode		*inode = d_inode(path->dentry);
 	struct xfs_inode	*ip = XFS_I(inode);
 	struct xfs_mount	*mp = ip->i_mount;
 
@@ -515,6 +516,20 @@ xfs_vn_getattr(
 	stat->blocks =
 		XFS_FSB_TO_BB(mp, ip->i_d.di_nblocks + ip->i_delayed_blks);
 
+	if (ip->i_d.di_version == 3) {
+		if (request_mask & STATX_BTIME) {
+			stat->result_mask |= STATX_BTIME;
+			stat->btime.tv_sec = ip->i_d.di_crtime.t_sec;
+			stat->btime.tv_nsec = ip->i_d.di_crtime.t_nsec;
+		}
+	}
+
+	if (ip->i_d.di_flags & XFS_DIFLAG_IMMUTABLE)
+		stat->attributes |= STATX_ATTR_IMMUTABLE;
+	if (ip->i_d.di_flags & XFS_DIFLAG_APPEND)
+		stat->attributes |= STATX_ATTR_APPEND;
+	if (ip->i_d.di_flags & XFS_DIFLAG_NODUMP)
+		stat->attributes |= STATX_ATTR_NODUMP;
 
 	switch (inode->i_mode & S_IFMT) {
 	case S_IFBLK:
diff --git a/fs/xfs/xfs_itable.c b/fs/xfs/xfs_itable.c
index 66e881790c17..c393a2f6d8c3 100644
--- a/fs/xfs/xfs_itable.c
+++ b/fs/xfs/xfs_itable.c
@@ -31,7 +31,7 @@
 #include "xfs_trace.h"
 #include "xfs_icache.h"
 
-STATIC int
+int
 xfs_internal_inum(
 	xfs_mount_t	*mp,
 	xfs_ino_t	ino)
@@ -361,7 +361,6 @@ xfs_bulkstat(
 	xfs_agino_t		agino;	/* inode # in allocation group */
 	xfs_agnumber_t		agno;	/* allocation group number */
 	xfs_btree_cur_t		*cur;	/* btree cursor for ialloc btree */
-	size_t			irbsize; /* size of irec buffer in bytes */
 	xfs_inobt_rec_incore_t	*irbuf;	/* start of irec buffer */
 	int			nirbuf;	/* size of irbuf */
 	int			ubcount; /* size of user's buffer */
@@ -388,11 +387,10 @@ xfs_bulkstat(
 	*ubcountp = 0;
 	*done = 0;
 
-	irbuf = kmem_zalloc_greedy(&irbsize, PAGE_SIZE, PAGE_SIZE * 4);
+	irbuf = kmem_zalloc_large(PAGE_SIZE * 4, KM_SLEEP);
 	if (!irbuf)
 		return -ENOMEM;
-
-	nirbuf = irbsize / sizeof(*irbuf);
+	nirbuf = (PAGE_SIZE * 4) / sizeof(*irbuf);
 
 	/*
 	 * Loop over the allocation groups, starting from the last
@@ -585,7 +583,7 @@ xfs_inumbers(
 		return error;
 
 	bcount = MIN(left, (int)(PAGE_SIZE / sizeof(*buffer)));
-	buffer = kmem_alloc(bcount * sizeof(*buffer), KM_SLEEP);
+	buffer = kmem_zalloc(bcount * sizeof(*buffer), KM_SLEEP);
 	do {
 		struct xfs_inobt_rec_incore	r;
 		int				stat;
diff --git a/fs/xfs/xfs_itable.h b/fs/xfs/xfs_itable.h
index 6ea8b3912fa4..17e86e0541af 100644
--- a/fs/xfs/xfs_itable.h
+++ b/fs/xfs/xfs_itable.h
@@ -96,4 +96,6 @@ xfs_inumbers(
 	void			__user *buffer, /* buffer with inode info */
 	inumbers_fmt_pf		formatter);
 
+int xfs_internal_inum(struct xfs_mount *mp, xfs_ino_t ino);
+
 #endif	/* __XFS_ITABLE_H__ */
diff --git a/fs/xfs/xfs_linux.h b/fs/xfs/xfs_linux.h
index 7a989de224f4..9301c5a6060b 100644
--- a/fs/xfs/xfs_linux.h
+++ b/fs/xfs/xfs_linux.h
@@ -19,18 +19,11 @@
 #define __XFS_LINUX__
 
 #include <linux/types.h>
+#include <linux/uuid.h>
 
 /*
  * Kernel specific type declarations for XFS
  */
-typedef signed char		__int8_t;
-typedef unsigned char		__uint8_t;
-typedef signed short int	__int16_t;
-typedef unsigned short int	__uint16_t;
-typedef signed int		__int32_t;
-typedef unsigned int		__uint32_t;
-typedef signed long long int	__int64_t;
-typedef unsigned long long int	__uint64_t;
 
 typedef __s64			xfs_off_t;	/* <file offset> type */
 typedef unsigned long long	xfs_ino_t;	/* <inode> type */
@@ -42,7 +35,6 @@ typedef __u32			xfs_nlink_t;
 
 #include "kmem.h"
 #include "mrlock.h"
-#include "uuid.h"
 
 #include <linux/semaphore.h>
 #include <linux/mm.h>
@@ -55,7 +47,7 @@ typedef __u32			xfs_nlink_t;
 #include <linux/file.h>
 #include <linux/swap.h>
 #include <linux/errno.h>
-#include <linux/sched.h>
+#include <linux/sched/signal.h>
 #include <linux/bitops.h>
 #include <linux/major.h>
 #include <linux/pagemap.h>
@@ -151,7 +143,6 @@ typedef __u32			xfs_nlink_t;
 #define __return_address __builtin_return_address(0)
 
 #define XFS_PROJID_DEFAULT	0
-#define MAXPATHLEN	1024
 
 #define MIN(a,b)	(min(a,b))
 #define MAX(a,b)	(max(a,b))
@@ -186,22 +177,22 @@ extern struct xstats xfsstats;
  * are converting to the init_user_ns. The uid is later mapped to a particular
  * user namespace value when crossing the kernel/user boundary.
  */
-static inline __uint32_t xfs_kuid_to_uid(kuid_t uid)
+static inline uint32_t xfs_kuid_to_uid(kuid_t uid)
 {
 	return from_kuid(&init_user_ns, uid);
 }
 
-static inline kuid_t xfs_uid_to_kuid(__uint32_t uid)
+static inline kuid_t xfs_uid_to_kuid(uint32_t uid)
 {
 	return make_kuid(&init_user_ns, uid);
 }
 
-static inline __uint32_t xfs_kgid_to_gid(kgid_t gid)
+static inline uint32_t xfs_kgid_to_gid(kgid_t gid)
 {
 	return from_kgid(&init_user_ns, gid);
 }
 
-static inline kgid_t xfs_gid_to_kgid(__uint32_t gid)
+static inline kgid_t xfs_gid_to_kgid(uint32_t gid)
 {
 	return make_kgid(&init_user_ns, gid);
 }
@@ -212,88 +203,6 @@ static inline kgid_t xfs_gid_to_kgid(__uint32_t gid)
 #define xfs_sort(a,n,s,fn)	sort(a,n,s,fn,NULL)
 #define xfs_stack_trace()	dump_stack()
 
-
-/* Move the kernel do_div definition off to one side */
-
-#if defined __i386__
-/* For ia32 we need to pull some tricks to get past various versions
- * of the compiler which do not like us using do_div in the middle
- * of large functions.
- */
-static inline __u32 xfs_do_div(void *a, __u32 b, int n)
-{
-	__u32	mod;
-
-	switch (n) {
-		case 4:
-			mod = *(__u32 *)a % b;
-			*(__u32 *)a = *(__u32 *)a / b;
-			return mod;
-		case 8:
-			{
-			unsigned long __upper, __low, __high, __mod;
-			__u64	c = *(__u64 *)a;
-			__upper = __high = c >> 32;
-			__low = c;
-			if (__high) {
-				__upper = __high % (b);
-				__high = __high / (b);
-			}
-			asm("divl %2":"=a" (__low), "=d" (__mod):"rm" (b), "0" (__low), "1" (__upper));
-			asm("":"=A" (c):"a" (__low),"d" (__high));
-			*(__u64 *)a = c;
-			return __mod;
-			}
-	}
-
-	/* NOTREACHED */
-	return 0;
-}
-
-/* Side effect free 64 bit mod operation */
-static inline __u32 xfs_do_mod(void *a, __u32 b, int n)
-{
-	switch (n) {
-		case 4:
-			return *(__u32 *)a % b;
-		case 8:
-			{
-			unsigned long __upper, __low, __high, __mod;
-			__u64	c = *(__u64 *)a;
-			__upper = __high = c >> 32;
-			__low = c;
-			if (__high) {
-				__upper = __high % (b);
-				__high = __high / (b);
-			}
-			asm("divl %2":"=a" (__low), "=d" (__mod):"rm" (b), "0" (__low), "1" (__upper));
-			asm("":"=A" (c):"a" (__low),"d" (__high));
-			return __mod;
-			}
-	}
-
-	/* NOTREACHED */
-	return 0;
-}
-#else
-static inline __u32 xfs_do_div(void *a, __u32 b, int n)
-{
-	__u32	mod;
-
-	switch (n) {
-		case 4:
-			mod = *(__u32 *)a % b;
-			*(__u32 *)a = *(__u32 *)a / b;
-			return mod;
-		case 8:
-			mod = do_div(*(__u64 *)a, b);
-			return mod;
-	}
-
-	/* NOTREACHED */
-	return 0;
-}
-
 /* Side effect free 64 bit mod operation */
 static inline __u32 xfs_do_mod(void *a, __u32 b, int n)
 {
@@ -310,20 +219,17 @@ static inline __u32 xfs_do_mod(void *a, __u32 b, int n)
 	/* NOTREACHED */
 	return 0;
 }
-#endif
 
-#undef do_div
-#define do_div(a, b)	xfs_do_div(&(a), (b), sizeof(a))
 #define do_mod(a, b)	xfs_do_mod(&(a), (b), sizeof(a))
 
-static inline __uint64_t roundup_64(__uint64_t x, __uint32_t y)
+static inline uint64_t roundup_64(uint64_t x, uint32_t y)
 {
 	x += y - 1;
 	do_div(x, y);
 	return x * y;
 }
 
-static inline __uint64_t howmany_64(__uint64_t x, __uint32_t y)
+static inline uint64_t howmany_64(uint64_t x, uint32_t y)
 {
 	x += y - 1;
 	do_div(x, y);
diff --git a/fs/xfs/xfs_log.c b/fs/xfs/xfs_log.c
index b1469f0a91a6..0053bcf2b10a 100644
--- a/fs/xfs/xfs_log.c
+++ b/fs/xfs/xfs_log.c
@@ -434,7 +434,7 @@ xfs_log_reserve(
 	int		 	unit_bytes,
 	int		 	cnt,
 	struct xlog_ticket	**ticp,
-	__uint8_t	 	client,
+	uint8_t		 	client,
 	bool			permanent)
 {
 	struct xlog		*log = mp->m_log;
@@ -825,9 +825,9 @@ xfs_log_unmount_write(xfs_mount_t *mp)
 		if (!error) {
 			/* the data section must be 32 bit size aligned */
 			struct {
-			    __uint16_t magic;
-			    __uint16_t pad1;
-			    __uint32_t pad2; /* may as well make it 64 bits */
+			    uint16_t magic;
+			    uint16_t pad1;
+			    uint32_t pad2; /* may as well make it 64 bits */
 			} magic = {
 				.magic = XLOG_UNMOUNT_TYPE,
 			};
@@ -1189,8 +1189,7 @@ xlog_iodone(xfs_buf_t *bp)
 	 * IOABORT state. The IOABORT state is only set in DEBUG mode to inject
 	 * CRC errors into log recovery.
 	 */
-	if (XFS_TEST_ERROR(bp->b_error, l->l_mp, XFS_ERRTAG_IODONE_IOERR,
-			   XFS_RANDOM_IODONE_IOERR) ||
+	if (XFS_TEST_ERROR(bp->b_error, l->l_mp, XFS_ERRTAG_IODONE_IOERR) ||
 	    iclog->ic_state & XLOG_STATE_IOABORT) {
 		if (iclog->ic_state & XLOG_STATE_IOABORT)
 			iclog->ic_state &= ~XLOG_STATE_IOABORT;
@@ -1293,7 +1292,7 @@ void
 xfs_log_work_queue(
 	struct xfs_mount        *mp)
 {
-	queue_delayed_work(mp->m_log_workqueue, &mp->m_log->l_work,
+	queue_delayed_work(mp->m_sync_workqueue, &mp->m_log->l_work,
 				msecs_to_jiffies(xfs_syncd_centisecs * 10));
 }
 
@@ -1665,7 +1664,7 @@ xlog_cksum(
 	char			*dp,
 	int			size)
 {
-	__uint32_t		crc;
+	uint32_t		crc;
 
 	/* first generate the crc for the record header ... */
 	crc = xfs_start_cksum_update((char *)rhead,
@@ -1828,7 +1827,7 @@ xlog_sync(
 		 */
 		dptr = (char *)&iclog->ic_header + count;
 		for (i = 0; i < split; i += BBSIZE) {
-			__uint32_t cycle = be32_to_cpu(*(__be32 *)dptr);
+			uint32_t cycle = be32_to_cpu(*(__be32 *)dptr);
 			if (++cycle == XLOG_HEADER_MAGIC_NUM)
 				cycle++;
 			*(__be32 *)dptr = cpu_to_be32(cycle);
@@ -1842,7 +1841,6 @@ xlog_sync(
 	/* calculcate the checksum */
 	iclog->ic_header.h_crc = xlog_cksum(log, &iclog->ic_header,
 					    iclog->ic_datap, size);
-#ifdef DEBUG
 	/*
 	 * Intentionally corrupt the log record CRC based on the error injection
 	 * frequency, if defined. This facilitates testing log recovery in the
@@ -1850,15 +1848,13 @@ xlog_sync(
 	 * write on I/O completion and shutdown the fs. The subsequent mount
 	 * detects the bad CRC and attempts to recover.
 	 */
-	if (log->l_badcrc_factor &&
-	    (prandom_u32() % log->l_badcrc_factor == 0)) {
-		iclog->ic_header.h_crc &= 0xAAAAAAAA;
+	if (XFS_TEST_ERROR(false, log->l_mp, XFS_ERRTAG_LOG_BAD_CRC)) {
+		iclog->ic_header.h_crc &= cpu_to_le32(0xAAAAAAAA);
 		iclog->ic_state |= XLOG_STATE_IOABORT;
 		xfs_warn(log->l_mp,
 	"Intentionally corrupted log record at LSN 0x%llx. Shutdown imminent.",
 			 be64_to_cpu(iclog->ic_header.h_lsn));
 	}
-#endif
 
 	bp->b_io_length = BTOBB(count);
 	bp->b_fspriv = iclog;
@@ -2024,7 +2020,7 @@ xlog_print_tic_res(
 	};
 #undef REG_TYPE_STR
 
-	xfs_warn(mp, "xlog_write: reservation summary:");
+	xfs_warn(mp, "ticket reservation summary:");
 	xfs_warn(mp, "  unit res    = %d bytes",
 		 ticket->t_unit_res);
 	xfs_warn(mp, "  current res = %d bytes",
@@ -2045,10 +2041,55 @@ xlog_print_tic_res(
 			    "bad-rtype" : res_type_str[r_type]),
 			    ticket->t_res_arr[i].r_len);
 	}
+}
+
+/*
+ * Print a summary of the transaction.
+ */
+void
+xlog_print_trans(
+	struct xfs_trans		*tp)
+{
+	struct xfs_mount		*mp = tp->t_mountp;
+	struct xfs_log_item_desc	*lidp;
+
+	/* dump core transaction and ticket info */
+	xfs_warn(mp, "transaction summary:");
+	xfs_warn(mp, "  flags	= 0x%x", tp->t_flags);
+
+	xlog_print_tic_res(mp, tp->t_ticket);
 
-	xfs_alert_tag(mp, XFS_PTAG_LOGRES,
-		"xlog_write: reservation ran out. Need to up reservation");
-	xfs_force_shutdown(mp, SHUTDOWN_LOG_IO_ERROR);
+	/* dump each log item */
+	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
+		struct xfs_log_item	*lip = lidp->lid_item;
+		struct xfs_log_vec	*lv = lip->li_lv;
+		struct xfs_log_iovec	*vec;
+		int			i;
+
+		xfs_warn(mp, "log item: ");
+		xfs_warn(mp, "  type	= 0x%x", lip->li_type);
+		xfs_warn(mp, "  flags	= 0x%x", lip->li_flags);
+		if (!lv)
+			continue;
+		xfs_warn(mp, "  niovecs	= %d", lv->lv_niovecs);
+		xfs_warn(mp, "  size	= %d", lv->lv_size);
+		xfs_warn(mp, "  bytes	= %d", lv->lv_bytes);
+		xfs_warn(mp, "  buf len	= %d", lv->lv_buf_len);
+
+		/* dump each iovec for the log item */
+		vec = lv->lv_iovecp;
+		for (i = 0; i < lv->lv_niovecs; i++) {
+			int dumplen = min(vec->i_len, 32);
+
+			xfs_warn(mp, "  iovec[%d]", i);
+			xfs_warn(mp, "    type	= 0x%x", vec->i_type);
+			xfs_warn(mp, "    len	= %d", vec->i_len);
+			xfs_warn(mp, "    first %d bytes of iovec[%d]:", dumplen, i);
+			xfs_hex_dump(vec->i_addr, dumplen);
+
+			vec++;
+		}
+	}
 }
 
 /*
@@ -2321,8 +2362,12 @@ xlog_write(
 	if (flags & (XLOG_COMMIT_TRANS | XLOG_UNMOUNT_TRANS))
 		ticket->t_curr_res -= sizeof(xlog_op_header_t);
 
-	if (ticket->t_curr_res < 0)
+	if (ticket->t_curr_res < 0) {
+		xfs_alert_tag(log->l_mp, XFS_PTAG_LOGRES,
+		     "ctx ticket reservation ran out. Need to up reservation");
 		xlog_print_tic_res(log->l_mp, ticket);
+		xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR);
+	}
 
 	index = 0;
 	lv = log_vector;
@@ -2363,8 +2408,8 @@ xlog_write(
 			}
 
 			reg = &vecp[index];
-			ASSERT(reg->i_len % sizeof(__int32_t) == 0);
-			ASSERT((unsigned long)ptr % sizeof(__int32_t) == 0);
+			ASSERT(reg->i_len % sizeof(int32_t) == 0);
+			ASSERT((unsigned long)ptr % sizeof(int32_t) == 0);
 
 			start_rec_copy = xlog_write_start_rec(ptr, ticket);
 			if (start_rec_copy) {
@@ -3143,7 +3188,7 @@ xlog_state_switch_iclogs(
 	/* Round up to next log-sunit */
 	if (xfs_sb_version_haslogv2(&log->l_mp->m_sb) &&
 	    log->l_mp->m_sb.sb_logsunit > 1) {
-		__uint32_t sunit_bb = BTOBB(log->l_mp->m_sb.sb_logsunit);
+		uint32_t sunit_bb = BTOBB(log->l_mp->m_sb.sb_logsunit);
 		log->l_curr_block = roundup(log->l_curr_block, sunit_bb);
 	}
 
@@ -3771,7 +3816,7 @@ xlog_verify_iclog(
 	xlog_in_core_2_t	*xhdr;
 	void			*base_ptr, *ptr, *p;
 	ptrdiff_t		field_offset;
-	__uint8_t		clientid;
+	uint8_t			clientid;
 	int			len, i, j, k, op_len;
 	int			idx;
 
diff --git a/fs/xfs/xfs_log.h b/fs/xfs/xfs_log.h
index b5e71072fde5..bf212772595c 100644
--- a/fs/xfs/xfs_log.h
+++ b/fs/xfs/xfs_log.h
@@ -124,7 +124,6 @@ struct xlog_ticket;
 struct xfs_log_item;
 struct xfs_item_ops;
 struct xfs_trans;
-struct xfs_log_callback;
 
 xfs_lsn_t xfs_log_done(struct xfs_mount *mp,
 		       struct xlog_ticket *ticket,
@@ -160,7 +159,7 @@ int	  xfs_log_reserve(struct xfs_mount *mp,
 			  int		   length,
 			  int		   count,
 			  struct xlog_ticket **ticket,
-			  __uint8_t	   clientid,
+			  uint8_t		   clientid,
 			  bool		   permanent);
 int	  xfs_log_regrant(struct xfs_mount *mp, struct xlog_ticket *tic);
 void      xfs_log_unmount(struct xfs_mount *mp);
diff --git a/fs/xfs/xfs_log_cil.c b/fs/xfs/xfs_log_cil.c
index a4ab192e1792..fbe72b134bef 100644
--- a/fs/xfs/xfs_log_cil.c
+++ b/fs/xfs/xfs_log_cil.c
@@ -30,6 +30,9 @@
 #include "xfs_trans_priv.h"
 #include "xfs_log.h"
 #include "xfs_log_priv.h"
+#include "xfs_trace.h"
+
+struct workqueue_struct *xfs_discard_wq;
 
 /*
  * Allocate a new ticket. Failing to get a new ticket makes it really hard to
@@ -407,6 +410,7 @@ xlog_cil_insert_items(
 	int			len = 0;
 	int			diff_iovecs = 0;
 	int			iclog_space;
+	int			iovhdr_res = 0, split_res = 0, ctx_res = 0;
 
 	ASSERT(tp);
 
@@ -416,30 +420,11 @@ xlog_cil_insert_items(
 	 */
 	xlog_cil_insert_format_items(log, tp, &len, &diff_iovecs);
 
-	/*
-	 * Now (re-)position everything modified at the tail of the CIL.
-	 * We do this here so we only need to take the CIL lock once during
-	 * the transaction commit.
-	 */
 	spin_lock(&cil->xc_cil_lock);
-	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
-		struct xfs_log_item	*lip = lidp->lid_item;
-
-		/* Skip items which aren't dirty in this transaction. */
-		if (!(lidp->lid_flags & XFS_LID_DIRTY))
-			continue;
-
-		/*
-		 * Only move the item if it isn't already at the tail. This is
-		 * to prevent a transient list_empty() state when reinserting
-		 * an item that is already the only item in the CIL.
-		 */
-		if (!list_is_last(&lip->li_cil, &cil->xc_cil))
-			list_move_tail(&lip->li_cil, &cil->xc_cil);
-	}
 
 	/* account for space used by new iovec headers  */
-	len += diff_iovecs * sizeof(xlog_op_header_t);
+	iovhdr_res = diff_iovecs * sizeof(xlog_op_header_t);
+	len += iovhdr_res;
 	ctx->nvecs += diff_iovecs;
 
 	/* attach the transaction to the CIL if it has any busy extents */
@@ -454,28 +439,66 @@ xlog_cil_insert_items(
 	 * during the transaction commit.
 	 */
 	if (ctx->ticket->t_curr_res == 0) {
-		ctx->ticket->t_curr_res = ctx->ticket->t_unit_res;
-		tp->t_ticket->t_curr_res -= ctx->ticket->t_unit_res;
+		ctx_res = ctx->ticket->t_unit_res;
+		ctx->ticket->t_curr_res = ctx_res;
+		tp->t_ticket->t_curr_res -= ctx_res;
 	}
 
 	/* do we need space for more log record headers? */
 	iclog_space = log->l_iclog_size - log->l_iclog_hsize;
 	if (len > 0 && (ctx->space_used / iclog_space !=
 				(ctx->space_used + len) / iclog_space)) {
-		int hdrs;
-
-		hdrs = (len + iclog_space - 1) / iclog_space;
+		split_res = (len + iclog_space - 1) / iclog_space;
 		/* need to take into account split region headers, too */
-		hdrs *= log->l_iclog_hsize + sizeof(struct xlog_op_header);
-		ctx->ticket->t_unit_res += hdrs;
-		ctx->ticket->t_curr_res += hdrs;
-		tp->t_ticket->t_curr_res -= hdrs;
+		split_res *= log->l_iclog_hsize + sizeof(struct xlog_op_header);
+		ctx->ticket->t_unit_res += split_res;
+		ctx->ticket->t_curr_res += split_res;
+		tp->t_ticket->t_curr_res -= split_res;
 		ASSERT(tp->t_ticket->t_curr_res >= len);
 	}
 	tp->t_ticket->t_curr_res -= len;
 	ctx->space_used += len;
 
+	/*
+	 * If we've overrun the reservation, dump the tx details before we move
+	 * the log items. Shutdown is imminent...
+	 */
+	if (WARN_ON(tp->t_ticket->t_curr_res < 0)) {
+		xfs_warn(log->l_mp, "Transaction log reservation overrun:");
+		xfs_warn(log->l_mp,
+			 "  log items: %d bytes (iov hdrs: %d bytes)",
+			 len, iovhdr_res);
+		xfs_warn(log->l_mp, "  split region headers: %d bytes",
+			 split_res);
+		xfs_warn(log->l_mp, "  ctx ticket: %d bytes", ctx_res);
+		xlog_print_trans(tp);
+	}
+
+	/*
+	 * Now (re-)position everything modified at the tail of the CIL.
+	 * We do this here so we only need to take the CIL lock once during
+	 * the transaction commit.
+	 */
+	list_for_each_entry(lidp, &tp->t_items, lid_trans) {
+		struct xfs_log_item	*lip = lidp->lid_item;
+
+		/* Skip items which aren't dirty in this transaction. */
+		if (!(lidp->lid_flags & XFS_LID_DIRTY))
+			continue;
+
+		/*
+		 * Only move the item if it isn't already at the tail. This is
+		 * to prevent a transient list_empty() state when reinserting
+		 * an item that is already the only item in the CIL.
+		 */
+		if (!list_is_last(&lip->li_cil, &cil->xc_cil))
+			list_move_tail(&lip->li_cil, &cil->xc_cil);
+	}
+
 	spin_unlock(&cil->xc_cil_lock);
+
+	if (tp->t_ticket->t_curr_res < 0)
+		xfs_force_shutdown(log->l_mp, SHUTDOWN_LOG_IO_ERROR);
 }
 
 static void
@@ -491,6 +514,75 @@ xlog_cil_free_logvec(
 	}
 }
 
+static void
+xlog_discard_endio_work(
+	struct work_struct	*work)
+{
+	struct xfs_cil_ctx	*ctx =
+		container_of(work, struct xfs_cil_ctx, discard_endio_work);
+	struct xfs_mount	*mp = ctx->cil->xc_log->l_mp;
+
+	xfs_extent_busy_clear(mp, &ctx->busy_extents, false);
+	kmem_free(ctx);
+}
+
+/*
+ * Queue up the actual completion to a thread to avoid IRQ-safe locking for
+ * pagb_lock.  Note that we need a unbounded workqueue, otherwise we might
+ * get the execution delayed up to 30 seconds for weird reasons.
+ */
+static void
+xlog_discard_endio(
+	struct bio		*bio)
+{
+	struct xfs_cil_ctx	*ctx = bio->bi_private;
+
+	INIT_WORK(&ctx->discard_endio_work, xlog_discard_endio_work);
+	queue_work(xfs_discard_wq, &ctx->discard_endio_work);
+}
+
+static void
+xlog_discard_busy_extents(
+	struct xfs_mount	*mp,
+	struct xfs_cil_ctx	*ctx)
+{
+	struct list_head	*list = &ctx->busy_extents;
+	struct xfs_extent_busy	*busyp;
+	struct bio		*bio = NULL;
+	struct blk_plug		plug;
+	int			error = 0;
+
+	ASSERT(mp->m_flags & XFS_MOUNT_DISCARD);
+
+	blk_start_plug(&plug);
+	list_for_each_entry(busyp, list, list) {
+		trace_xfs_discard_extent(mp, busyp->agno, busyp->bno,
+					 busyp->length);
+
+		error = __blkdev_issue_discard(mp->m_ddev_targp->bt_bdev,
+				XFS_AGB_TO_DADDR(mp, busyp->agno, busyp->bno),
+				XFS_FSB_TO_BB(mp, busyp->length),
+				GFP_NOFS, 0, &bio);
+		if (error && error != -EOPNOTSUPP) {
+			xfs_info(mp,
+	 "discard failed for extent [0x%llx,%u], error %d",
+				 (unsigned long long)busyp->bno,
+				 busyp->length,
+				 error);
+			break;
+		}
+	}
+
+	if (bio) {
+		bio->bi_private = ctx;
+		bio->bi_end_io = xlog_discard_endio;
+		submit_bio(bio);
+	} else {
+		xlog_discard_endio_work(&ctx->discard_endio_work);
+	}
+	blk_finish_plug(&plug);
+}
+
 /*
  * Mark all items committed and clear busy extents. We free the log vector
  * chains in a separate pass so that we unpin the log items as quickly as
@@ -525,14 +617,10 @@ xlog_cil_committed(
 
 	xlog_cil_free_logvec(ctx->lv_chain);
 
-	if (!list_empty(&ctx->busy_extents)) {
-		ASSERT(mp->m_flags & XFS_MOUNT_DISCARD);
-
-		xfs_discard_extents(mp, &ctx->busy_extents);
-		xfs_extent_busy_clear(mp, &ctx->busy_extents, false);
-	}
-
-	kmem_free(ctx);
+	if (!list_empty(&ctx->busy_extents))
+		xlog_discard_busy_extents(mp, ctx);
+	else
+		kmem_free(ctx);
 }
 
 /*
@@ -905,6 +993,7 @@ xfs_log_commit_cil(
 {
 	struct xlog		*log = mp->m_log;
 	struct xfs_cil		*cil = log->l_cilp;
+	xfs_lsn_t		xc_commit_lsn;
 
 	/*
 	 * Do all necessary memory allocation before we lock the CIL.
@@ -918,13 +1007,9 @@ xfs_log_commit_cil(
 
 	xlog_cil_insert_items(log, tp);
 
-	/* check we didn't blow the reservation */
-	if (tp->t_ticket->t_curr_res < 0)
-		xlog_print_tic_res(mp, tp->t_ticket);
-
-	tp->t_commit_lsn = cil->xc_ctx->sequence;
+	xc_commit_lsn = cil->xc_ctx->sequence;
 	if (commit_lsn)
-		*commit_lsn = tp->t_commit_lsn;
+		*commit_lsn = xc_commit_lsn;
 
 	xfs_log_done(mp, tp->t_ticket, NULL, regrant);
 	xfs_trans_unreserve_and_mod_sb(tp);
@@ -940,7 +1025,7 @@ xfs_log_commit_cil(
 	 * the log items. This affects (at least) processing of stale buffers,
 	 * inodes and EFIs.
 	 */
-	xfs_trans_free_items(tp, tp->t_commit_lsn, false);
+	xfs_trans_free_items(tp, xc_commit_lsn, false);
 
 	xlog_cil_push_background(log);
 
diff --git a/fs/xfs/xfs_log_priv.h b/fs/xfs/xfs_log_priv.h
index 2b6eec52178e..51bf7b827387 100644
--- a/fs/xfs/xfs_log_priv.h
+++ b/fs/xfs/xfs_log_priv.h
@@ -257,6 +257,7 @@ struct xfs_cil_ctx {
 	struct xfs_log_vec	*lv_chain;	/* logvecs being pushed */
 	struct xfs_log_callback	log_cb;		/* completion callback hook. */
 	struct list_head	committing;	/* ctx committing list */
+	struct work_struct	discard_endio_work;
 };
 
 /*
@@ -418,7 +419,7 @@ struct xlog {
 };
 
 #define XLOG_BUF_CANCEL_BUCKET(log, blkno) \
-	((log)->l_buf_cancel_table + ((__uint64_t)blkno % XLOG_BC_TABLE_SIZE))
+	((log)->l_buf_cancel_table + ((uint64_t)blkno % XLOG_BC_TABLE_SIZE))
 
 #define XLOG_FORCED_SHUTDOWN(log)	((log)->l_flags & XLOG_IO_ERROR)
 
@@ -455,6 +456,7 @@ xlog_write_adv_cnt(void **ptr, int *len, int *off, size_t bytes)
 }
 
 void	xlog_print_tic_res(struct xfs_mount *mp, struct xlog_ticket *ticket);
+void	xlog_print_trans(struct xfs_trans *);
 int
 xlog_write(
 	struct xlog		*log,
diff --git a/fs/xfs/xfs_log_recover.c b/fs/xfs/xfs_log_recover.c
index 4a98762ec8b4..9549188f5a36 100644
--- a/fs/xfs/xfs_log_recover.c
+++ b/fs/xfs/xfs_log_recover.c
@@ -352,13 +352,13 @@ xlog_header_check_mount(
 {
 	ASSERT(head->h_magicno == cpu_to_be32(XLOG_HEADER_MAGIC_NUM));
 
-	if (uuid_is_nil(&head->h_fs_uuid)) {
+	if (uuid_is_null(&head->h_fs_uuid)) {
 		/*
 		 * IRIX doesn't write the h_fs_uuid or h_fmt fields. If
-		 * h_fs_uuid is nil, we assume this log was last mounted
+		 * h_fs_uuid is null, we assume this log was last mounted
 		 * by IRIX and continue.
 		 */
-		xfs_warn(mp, "nil uuid in log - IRIX style log");
+		xfs_warn(mp, "null uuid in log - IRIX style log");
 	} else if (unlikely(!uuid_equal(&mp->m_sb.sb_uuid, &head->h_fs_uuid))) {
 		xfs_warn(mp, "log has mismatched uuid - can't recover");
 		xlog_header_check_dump(mp, head);
@@ -2230,9 +2230,9 @@ xlog_recover_get_buf_lsn(
 	struct xfs_mount	*mp,
 	struct xfs_buf		*bp)
 {
-	__uint32_t		magic32;
-	__uint16_t		magic16;
-	__uint16_t		magicda;
+	uint32_t		magic32;
+	uint16_t		magic16;
+	uint16_t		magicda;
 	void			*blk = bp->b_addr;
 	uuid_t			*uuid;
 	xfs_lsn_t		lsn = -1;
@@ -2381,9 +2381,9 @@ xlog_recover_validate_buf_type(
 	xfs_lsn_t		current_lsn)
 {
 	struct xfs_da_blkinfo	*info = bp->b_addr;
-	__uint32_t		magic32;
-	__uint16_t		magic16;
-	__uint16_t		magicda;
+	uint32_t		magic32;
+	uint16_t		magic16;
+	uint16_t		magicda;
 	char			*warnmsg = NULL;
 
 	/*
@@ -2852,7 +2852,7 @@ xlog_recover_buffer_pass2(
 	if (XFS_DINODE_MAGIC ==
 	    be16_to_cpu(*((__be16 *)xfs_buf_offset(bp, 0))) &&
 	    (BBTOB(bp->b_io_length) != MAX(log->l_mp->m_sb.sb_blocksize,
-			(__uint32_t)log->l_mp->m_inode_cluster_size))) {
+			(uint32_t)log->l_mp->m_inode_cluster_size))) {
 		xfs_buf_stale(bp);
 		error = xfs_bwrite(bp);
 	} else {
@@ -3423,7 +3423,7 @@ xlog_recover_efd_pass2(
 	xfs_efd_log_format_t	*efd_formatp;
 	xfs_efi_log_item_t	*efip = NULL;
 	xfs_log_item_t		*lip;
-	__uint64_t		efi_id;
+	uint64_t		efi_id;
 	struct xfs_ail_cursor	cur;
 	struct xfs_ail		*ailp = log->l_ailp;
 
@@ -3519,7 +3519,7 @@ xlog_recover_rud_pass2(
 	struct xfs_rud_log_format	*rud_formatp;
 	struct xfs_rui_log_item		*ruip = NULL;
 	struct xfs_log_item		*lip;
-	__uint64_t			rui_id;
+	uint64_t			rui_id;
 	struct xfs_ail_cursor		cur;
 	struct xfs_ail			*ailp = log->l_ailp;
 
@@ -3635,7 +3635,7 @@ xlog_recover_cud_pass2(
 	struct xfs_cud_log_format	*cud_formatp;
 	struct xfs_cui_log_item		*cuip = NULL;
 	struct xfs_log_item		*lip;
-	__uint64_t			cui_id;
+	uint64_t			cui_id;
 	struct xfs_ail_cursor		cur;
 	struct xfs_ail			*ailp = log->l_ailp;
 
@@ -3754,7 +3754,7 @@ xlog_recover_bud_pass2(
 	struct xfs_bud_log_format	*bud_formatp;
 	struct xfs_bui_log_item		*buip = NULL;
 	struct xfs_log_item		*lip;
-	__uint64_t			bui_id;
+	uint64_t			bui_id;
 	struct xfs_ail_cursor		cur;
 	struct xfs_ail			*ailp = log->l_ailp;
 
@@ -3796,7 +3796,7 @@ xlog_recover_bud_pass2(
  * This routine is called when an inode create format structure is found in a
  * committed transaction in the log.  It's purpose is to initialise the inodes
  * being allocated on disk. This requires us to get inode cluster buffers that
- * match the range to be intialised, stamped with inode templates and written
+ * match the range to be initialised, stamped with inode templates and written
  * by delayed write so that subsequent modifications will hit the cached buffer
  * and only need writing out at the end of recovery.
  */
@@ -4152,7 +4152,7 @@ xlog_recover_commit_trans(
 
 	#define XLOG_RECOVER_COMMIT_QUEUE_MAX 100
 
-	hlist_del(&trans->r_list);
+	hlist_del_init(&trans->r_list);
 
 	error = xlog_recover_reorder_trans(log, trans, pass);
 	if (error)
@@ -4354,6 +4354,8 @@ xlog_recover_free_trans(
 	xlog_recover_item_t	*item, *n;
 	int			i;
 
+	hlist_del_init(&trans->r_list);
+
 	list_for_each_entry_safe(item, n, &trans->r_itemq, ri_list) {
 		/* Free the regions in the item. */
 		list_del(&item->ri_list);
@@ -5224,12 +5226,16 @@ xlog_do_recovery_pass(
 	int			error2 = 0;
 	int			bblks, split_bblks;
 	int			hblks, split_hblks, wrapped_hblks;
+	int			i;
 	struct hlist_head	rhash[XLOG_RHASH_SIZE];
 	LIST_HEAD		(buffer_list);
 
 	ASSERT(head_blk != tail_blk);
 	rhead_blk = 0;
 
+	for (i = 0; i < XLOG_RHASH_SIZE; i++)
+		INIT_HLIST_HEAD(&rhash[i]);
+
 	/*
 	 * Read the header of the tail block and get the iclog buffer size from
 	 * h_size.  Use this to tell how many sectors make up the log header.
@@ -5466,6 +5472,19 @@ xlog_do_recovery_pass(
 	if (error && first_bad)
 		*first_bad = rhead_blk;
 
+	/*
+	 * Transactions are freed at commit time but transactions without commit
+	 * records on disk are never committed. Free any that may be left in the
+	 * hash table.
+	 */
+	for (i = 0; i < XLOG_RHASH_SIZE; i++) {
+		struct hlist_node	*tmp;
+		struct xlog_recover	*trans;
+
+		hlist_for_each_entry_safe(trans, tmp, &rhash[i], r_list)
+			xlog_recover_free_trans(trans);
+	}
+
 	return error ? error : error2;
 }
 
@@ -5772,9 +5791,9 @@ xlog_recover_check_summary(
 	xfs_buf_t	*agfbp;
 	xfs_buf_t	*agibp;
 	xfs_agnumber_t	agno;
-	__uint64_t	freeblks;
-	__uint64_t	itotal;
-	__uint64_t	ifree;
+	uint64_t	freeblks;
+	uint64_t	itotal;
+	uint64_t	ifree;
 	int		error;
 
 	mp = log->l_mp;
diff --git a/fs/xfs/xfs_message.c b/fs/xfs/xfs_message.c
index 11792d888e4e..e68bd1050eab 100644
--- a/fs/xfs/xfs_message.c
+++ b/fs/xfs/xfs_message.c
@@ -110,7 +110,10 @@ assfail(char *expr, char *file, int line)
 {
 	xfs_emerg(NULL, "Assertion failed: %s, file: %s, line: %d",
 		expr, file, line);
-	BUG();
+	if (xfs_globals.bug_on_assert)
+		BUG();
+	else
+		WARN_ON(1);
 }
 
 void
diff --git a/fs/xfs/xfs_mount.c b/fs/xfs/xfs_mount.c
index 9b9540db17a6..40d4e8b4e193 100644
--- a/fs/xfs/xfs_mount.c
+++ b/fs/xfs/xfs_mount.c
@@ -45,6 +45,7 @@
 #include "xfs_rmap_btree.h"
 #include "xfs_refcount_btree.h"
 #include "xfs_reflink.h"
+#include "xfs_extent_busy.h"
 
 
 static DEFINE_MUTEX(xfs_uuid_table_mutex);
@@ -72,17 +73,20 @@ xfs_uuid_mount(
 	uuid_t			*uuid = &mp->m_sb.sb_uuid;
 	int			hole, i;
 
+	/* Publish UUID in struct super_block */
+	uuid_copy(&mp->m_super->s_uuid, uuid);
+
 	if (mp->m_flags & XFS_MOUNT_NOUUID)
 		return 0;
 
-	if (uuid_is_nil(uuid)) {
-		xfs_warn(mp, "Filesystem has nil UUID - can't mount");
+	if (uuid_is_null(uuid)) {
+		xfs_warn(mp, "Filesystem has null UUID - can't mount");
 		return -EINVAL;
 	}
 
 	mutex_lock(&xfs_uuid_table_mutex);
 	for (i = 0, hole = -1; i < xfs_uuid_table_size; i++) {
-		if (uuid_is_nil(&xfs_uuid_table[i])) {
+		if (uuid_is_null(&xfs_uuid_table[i])) {
 			hole = i;
 			continue;
 		}
@@ -119,7 +123,7 @@ xfs_uuid_unmount(
 
 	mutex_lock(&xfs_uuid_table_mutex);
 	for (i = 0; i < xfs_uuid_table_size; i++) {
-		if (uuid_is_nil(&xfs_uuid_table[i]))
+		if (uuid_is_null(&xfs_uuid_table[i]))
 			continue;
 		if (!uuid_equal(uuid, &xfs_uuid_table[i]))
 			continue;
@@ -169,7 +173,7 @@ xfs_free_perag(
 int
 xfs_sb_validate_fsb_count(
 	xfs_sb_t	*sbp,
-	__uint64_t	nblocks)
+	uint64_t	nblocks)
 {
 	ASSERT(PAGE_SHIFT >= sbp->sb_blocklog);
 	ASSERT(sbp->sb_blocklog >= BBSHIFT);
@@ -187,7 +191,7 @@ xfs_initialize_perag(
 	xfs_agnumber_t	*maxagi)
 {
 	xfs_agnumber_t	index;
-	xfs_agnumber_t	first_initialised = 0;
+	xfs_agnumber_t	first_initialised = NULLAGNUMBER;
 	xfs_perag_t	*pag;
 	int		error = -ENOMEM;
 
@@ -202,22 +206,21 @@ xfs_initialize_perag(
 			xfs_perag_put(pag);
 			continue;
 		}
-		if (!first_initialised)
-			first_initialised = index;
 
 		pag = kmem_zalloc(sizeof(*pag), KM_MAYFAIL);
 		if (!pag)
-			goto out_unwind;
+			goto out_unwind_new_pags;
 		pag->pag_agno = index;
 		pag->pag_mount = mp;
 		spin_lock_init(&pag->pag_ici_lock);
 		mutex_init(&pag->pag_ici_reclaim_lock);
 		INIT_RADIX_TREE(&pag->pag_ici_root, GFP_ATOMIC);
 		if (xfs_buf_hash_init(pag))
-			goto out_unwind;
+			goto out_free_pag;
+		init_waitqueue_head(&pag->pagb_wait);
 
 		if (radix_tree_preload(GFP_NOFS))
-			goto out_unwind;
+			goto out_hash_destroy;
 
 		spin_lock(&mp->m_perag_lock);
 		if (radix_tree_insert(&mp->m_perag_tree, index, pag)) {
@@ -225,10 +228,13 @@ xfs_initialize_perag(
 			spin_unlock(&mp->m_perag_lock);
 			radix_tree_preload_end();
 			error = -EEXIST;
-			goto out_unwind;
+			goto out_hash_destroy;
 		}
 		spin_unlock(&mp->m_perag_lock);
 		radix_tree_preload_end();
+		/* first new pag is fully initialized */
+		if (first_initialised == NULLAGNUMBER)
+			first_initialised = index;
 	}
 
 	index = xfs_set_inode_alloc(mp, agcount);
@@ -239,11 +245,16 @@ xfs_initialize_perag(
 	mp->m_ag_prealloc_blocks = xfs_prealloc_blocks(mp);
 	return 0;
 
-out_unwind:
+out_hash_destroy:
 	xfs_buf_hash_destroy(pag);
+out_free_pag:
 	kmem_free(pag);
-	for (; index > first_initialised; index--) {
+out_unwind_new_pags:
+	/* unwind any prior newly initialized pags */
+	for (index = first_initialised; index < agcount; index++) {
 		pag = radix_tree_delete(&mp->m_perag_tree, index);
+		if (!pag)
+			break;
 		xfs_buf_hash_destroy(pag);
 		kmem_free(pag);
 	}
@@ -424,7 +435,7 @@ STATIC void
 xfs_set_maxicount(xfs_mount_t *mp)
 {
 	xfs_sb_t	*sbp = &(mp->m_sb);
-	__uint64_t	icount;
+	uint64_t	icount;
 
 	if (sbp->sb_imax_pct) {
 		/*
@@ -490,7 +501,7 @@ xfs_set_low_space_thresholds(
 	int i;
 
 	for (i = 0; i < XFS_LOWSP_MAX; i++) {
-		__uint64_t space = mp->m_sb.sb_dblocks;
+		uint64_t space = mp->m_sb.sb_dblocks;
 
 		do_div(space, 100);
 		mp->m_low_space[i] = space * (i + 1);
@@ -505,8 +516,7 @@ STATIC void
 xfs_set_inoalignment(xfs_mount_t *mp)
 {
 	if (xfs_sb_version_hasalign(&mp->m_sb) &&
-	    mp->m_sb.sb_inoalignmt >=
-	    XFS_B_TO_FSBT(mp, mp->m_inode_cluster_size))
+		mp->m_sb.sb_inoalignmt >= xfs_icluster_size_fsb(mp))
 		mp->m_inoalign_mask = mp->m_sb.sb_inoalignmt - 1;
 	else
 		mp->m_inoalign_mask = 0;
@@ -587,10 +597,10 @@ xfs_mount_reset_sbqflags(
 	return xfs_sync_sb(mp, false);
 }
 
-__uint64_t
+uint64_t
 xfs_default_resblks(xfs_mount_t *mp)
 {
-	__uint64_t resblks;
+	uint64_t resblks;
 
 	/*
 	 * We default to 5% or 8192 fsbs of space reserved, whichever is
@@ -601,7 +611,7 @@ xfs_default_resblks(xfs_mount_t *mp)
 	 */
 	resblks = mp->m_sb.sb_dblocks;
 	do_div(resblks, 20);
-	resblks = min_t(__uint64_t, resblks, 8192);
+	resblks = min_t(uint64_t, resblks, 8192);
 	return resblks;
 }
 
@@ -621,7 +631,7 @@ xfs_mountfs(
 {
 	struct xfs_sb		*sbp = &(mp->m_sb);
 	struct xfs_inode	*rip;
-	__uint64_t		resblks;
+	uint64_t		resblks;
 	uint			quotamount = 0;
 	uint			quotaflags = 0;
 	int			error = 0;
@@ -709,10 +719,13 @@ xfs_mountfs(
 	if (error)
 		goto out_del_stats;
 
+	error = xfs_errortag_init(mp);
+	if (error)
+		goto out_remove_error_sysfs;
 
 	error = xfs_uuid_mount(mp);
 	if (error)
-		goto out_remove_error_sysfs;
+		goto out_remove_errortag;
 
 	/*
 	 * Set the minimum read and write sizes
@@ -782,7 +795,10 @@ xfs_mountfs(
 	 *  Copies the low order bits of the timestamp and the randomly
 	 *  set "sequence" number out of a UUID.
 	 */
-	uuid_getnodeuniq(&sbp->sb_uuid, mp->m_fixedfsid);
+	mp->m_fixedfsid[0] =
+		(get_unaligned_be16(&sbp->sb_uuid.b[8]) << 16) |
+		 get_unaligned_be16(&sbp->sb_uuid.b[4]);
+	mp->m_fixedfsid[1] = get_unaligned_be32(&sbp->sb_uuid.b[0]);
 
 	mp->m_dmevmask = 0;	/* not persistent; set after each mount */
 
@@ -1031,6 +1047,8 @@ xfs_mountfs(
 	xfs_da_unmount(mp);
  out_remove_uuid:
 	xfs_uuid_unmount(mp);
+ out_remove_errortag:
+	xfs_errortag_del(mp);
  out_remove_error_sysfs:
 	xfs_error_sysfs_del(mp);
  out_del_stats:
@@ -1049,7 +1067,7 @@ void
 xfs_unmountfs(
 	struct xfs_mount	*mp)
 {
-	__uint64_t		resblks;
+	uint64_t		resblks;
 	int			error;
 
 	cancel_delayed_work_sync(&mp->m_eofblocks_work);
@@ -1073,6 +1091,13 @@ xfs_unmountfs(
 	xfs_log_force(mp, XFS_LOG_SYNC);
 
 	/*
+	 * Wait for all busy extents to be freed, including completion of
+	 * any discard operation.
+	 */
+	xfs_extent_busy_wait_all(mp);
+	flush_workqueue(xfs_discard_wq);
+
+	/*
 	 * We now need to tell the world we are unmounting. This will allow
 	 * us to detect that the filesystem is going away and we should error
 	 * out anything that we have been retrying in the background. This will
@@ -1127,10 +1152,11 @@ xfs_unmountfs(
 	xfs_uuid_unmount(mp);
 
 #if defined(DEBUG)
-	xfs_errortag_clearall(mp, 0);
+	xfs_errortag_clearall(mp);
 #endif
 	xfs_free_perag(mp);
 
+	xfs_errortag_del(mp);
 	xfs_error_sysfs_del(mp);
 	xfs_sysfs_del(&mp->m_stats.xs_kobj);
 	xfs_sysfs_del(&mp->m_kobj);
@@ -1191,7 +1217,7 @@ xfs_mod_icount(
 	struct xfs_mount	*mp,
 	int64_t			delta)
 {
-	__percpu_counter_add(&mp->m_icount, delta, XFS_ICOUNT_BATCH);
+	percpu_counter_add_batch(&mp->m_icount, delta, XFS_ICOUNT_BATCH);
 	if (__percpu_counter_compare(&mp->m_icount, 0, XFS_ICOUNT_BATCH) < 0) {
 		ASSERT(0);
 		percpu_counter_add(&mp->m_icount, -delta);
@@ -1270,7 +1296,7 @@ xfs_mod_fdblocks(
 	else
 		batch = XFS_FDBLOCKS_BATCH;
 
-	__percpu_counter_add(&mp->m_fdblocks, delta, batch);
+	percpu_counter_add_batch(&mp->m_fdblocks, delta, batch);
 	if (__percpu_counter_compare(&mp->m_fdblocks, mp->m_alloc_set_aside,
 				     XFS_FDBLOCKS_BATCH) >= 0) {
 		/* we had space! */
diff --git a/fs/xfs/xfs_mount.h b/fs/xfs/xfs_mount.h
index 7f351f706b7a..e0792d036be2 100644
--- a/fs/xfs/xfs_mount.h
+++ b/fs/xfs/xfs_mount.h
@@ -108,10 +108,10 @@ typedef struct xfs_mount {
 	xfs_buftarg_t		*m_ddev_targp;	/* saves taking the address */
 	xfs_buftarg_t		*m_logdev_targp;/* ptr to log device */
 	xfs_buftarg_t		*m_rtdev_targp;	/* ptr to rt device */
-	__uint8_t		m_blkbit_log;	/* blocklog + NBBY */
-	__uint8_t		m_blkbb_log;	/* blocklog - BBSHIFT */
-	__uint8_t		m_agno_log;	/* log #ag's */
-	__uint8_t		m_agino_log;	/* #bits for agino in inum */
+	uint8_t			m_blkbit_log;	/* blocklog + NBBY */
+	uint8_t			m_blkbb_log;	/* blocklog - BBSHIFT */
+	uint8_t			m_agno_log;	/* log #ag's */
+	uint8_t			m_agino_log;	/* #bits for agino in inum */
 	uint			m_inode_cluster_size;/* min inode buf size */
 	uint			m_blockmask;	/* sb_blocksize-1 */
 	uint			m_blockwsize;	/* sb_blocksize in words */
@@ -139,7 +139,7 @@ typedef struct xfs_mount {
 	struct mutex		m_growlock;	/* growfs mutex */
 	int			m_fixedfsid[2];	/* unchanged for life of FS */
 	uint			m_dmevmask;	/* DMI events for this FS */
-	__uint64_t		m_flags;	/* global mount flags */
+	uint64_t		m_flags;	/* global mount flags */
 	bool			m_inotbt_nores; /* no per-AG finobt resv. */
 	int			m_ialloc_inos;	/* inodes in inode allocation */
 	int			m_ialloc_blks;	/* blocks in inode allocation */
@@ -148,14 +148,14 @@ typedef struct xfs_mount {
 	int			m_inoalign_mask;/* mask sb_inoalignmt if used */
 	uint			m_qflags;	/* quota status flags */
 	struct xfs_trans_resv	m_resv;		/* precomputed res values */
-	__uint64_t		m_maxicount;	/* maximum inode count */
-	__uint64_t		m_resblks;	/* total reserved blocks */
-	__uint64_t		m_resblks_avail;/* available reserved blocks */
-	__uint64_t		m_resblks_save;	/* reserved blks @ remount,ro */
+	uint64_t		m_maxicount;	/* maximum inode count */
+	uint64_t		m_resblks;	/* total reserved blocks */
+	uint64_t		m_resblks_avail;/* available reserved blocks */
+	uint64_t		m_resblks_save;	/* reserved blks @ remount,ro */
 	int			m_dalign;	/* stripe unit */
 	int			m_swidth;	/* stripe width */
 	int			m_sinoalign;	/* stripe unit inode alignment */
-	__uint8_t		m_sectbb_log;	/* sectlog - BBSHIFT */
+	uint8_t			m_sectbb_log;	/* sectlog - BBSHIFT */
 	const struct xfs_nameops *m_dirnameops;	/* vector of dir name ops */
 	const struct xfs_dir_ops *m_dir_inode_ops; /* vector of dir inode ops */
 	const struct xfs_dir_ops *m_nondir_inode_ops; /* !dir inode ops */
@@ -183,6 +183,7 @@ typedef struct xfs_mount {
 	struct workqueue_struct	*m_reclaim_workqueue;
 	struct workqueue_struct	*m_log_workqueue;
 	struct workqueue_struct *m_eofblocks_workqueue;
+	struct workqueue_struct	*m_sync_workqueue;
 
 	/*
 	 * Generation of the filesysyem layout.  This is incremented by each
@@ -193,18 +194,17 @@ typedef struct xfs_mount {
 	 * ever support shrinks it would have to be persisted in addition
 	 * to various other kinds of pain inflicted on the pNFS server.
 	 */
-	__uint32_t		m_generation;
+	uint32_t		m_generation;
 
 	bool			m_fail_unmount;
 #ifdef DEBUG
 	/*
-	 * DEBUG mode instrumentation to test and/or trigger delayed allocation
-	 * block killing in the event of failed writes. When enabled, all
-	 * buffered writes are forced to fail. All delalloc blocks in the range
-	 * of the write (including pre-existing delalloc blocks!) are tossed as
-	 * part of the write failure error handling sequence.
+	 * Frequency with which errors are injected.  Replaces xfs_etest; the
+	 * value stored in here is the inverse of the frequency with which the
+	 * error triggers.  1 = always, 2 = half the time, etc.
 	 */
-	bool			m_fail_writes;
+	unsigned int		*m_errortag;
+	struct xfs_kobj		m_errortag_kobj;
 #endif
 } xfs_mount_t;
 
@@ -311,7 +311,7 @@ void xfs_do_force_shutdown(struct xfs_mount *mp, int flags, char *fname,
 static inline xfs_agnumber_t
 xfs_daddr_to_agno(struct xfs_mount *mp, xfs_daddr_t d)
 {
-	xfs_daddr_t ld = XFS_BB_TO_FSBT(mp, d);
+	xfs_rfsblock_t ld = XFS_BB_TO_FSBT(mp, d);
 	do_div(ld, mp->m_sb.sb_agblocks);
 	return (xfs_agnumber_t) ld;
 }
@@ -319,24 +319,10 @@ xfs_daddr_to_agno(struct xfs_mount *mp, xfs_daddr_t d)
 static inline xfs_agblock_t
 xfs_daddr_to_agbno(struct xfs_mount *mp, xfs_daddr_t d)
 {
-	xfs_daddr_t ld = XFS_BB_TO_FSBT(mp, d);
+	xfs_rfsblock_t ld = XFS_BB_TO_FSBT(mp, d);
 	return (xfs_agblock_t) do_div(ld, mp->m_sb.sb_agblocks);
 }
 
-#ifdef DEBUG
-static inline bool
-xfs_mp_fail_writes(struct xfs_mount *mp)
-{
-	return mp->m_fail_writes;
-}
-#else
-static inline bool
-xfs_mp_fail_writes(struct xfs_mount *mp)
-{
-	return 0;
-}
-#endif
-
 /* per-AG block reservation data structures*/
 enum xfs_ag_resv_type {
 	XFS_AG_RESV_NONE = 0,
@@ -365,12 +351,12 @@ typedef struct xfs_perag {
 	char		pagi_init;	/* this agi's entry is initialized */
 	char		pagf_metadata;	/* the agf is preferred to be metadata */
 	char		pagi_inodeok;	/* The agi is ok for inodes */
-	__uint8_t	pagf_levels[XFS_BTNUM_AGF];
+	uint8_t		pagf_levels[XFS_BTNUM_AGF];
 					/* # of levels in bno & cnt btree */
-	__uint32_t	pagf_flcount;	/* count of blocks in freelist */
+	uint32_t	pagf_flcount;	/* count of blocks in freelist */
 	xfs_extlen_t	pagf_freeblks;	/* total free blocks */
 	xfs_extlen_t	pagf_longest;	/* longest free space */
-	__uint32_t	pagf_btreeblks;	/* # of blocks held in AGF btrees */
+	uint32_t	pagf_btreeblks;	/* # of blocks held in AGF btrees */
 	xfs_agino_t	pagi_freecount;	/* number of free inodes */
 	xfs_agino_t	pagi_count;	/* number of allocated inodes */
 
@@ -384,6 +370,8 @@ typedef struct xfs_perag {
 	xfs_agino_t	pagl_rightrec;
 	spinlock_t	pagb_lock;	/* lock for pagb_tree */
 	struct rb_root	pagb_tree;	/* ordered tree of busy extents */
+	unsigned int	pagb_gen;	/* generation count for pagb_tree */
+	wait_queue_head_t pagb_wait;	/* woken when pagb_gen changes */
 
 	atomic_t        pagf_fstrms;    /* # of filestreams active in this AG */
 
@@ -407,7 +395,7 @@ typedef struct xfs_perag {
 	struct xfs_ag_resv	pag_agfl_resv;
 
 	/* reference count */
-	__uint8_t		pagf_refcount_level;
+	uint8_t			pagf_refcount_level;
 } xfs_perag_t;
 
 static inline struct xfs_ag_resv *
@@ -430,7 +418,7 @@ void xfs_buf_hash_destroy(xfs_perag_t *pag);
 
 extern void	xfs_uuid_table_free(void);
 extern int	xfs_log_sbcount(xfs_mount_t *);
-extern __uint64_t xfs_default_resblks(xfs_mount_t *mp);
+extern uint64_t xfs_default_resblks(xfs_mount_t *mp);
 extern int	xfs_mountfs(xfs_mount_t *mp);
 extern int	xfs_initialize_perag(xfs_mount_t *mp, xfs_agnumber_t agcount,
 				     xfs_agnumber_t *maxagi);
@@ -446,7 +434,7 @@ extern struct xfs_buf *xfs_getsb(xfs_mount_t *, int);
 extern int	xfs_readsb(xfs_mount_t *, int);
 extern void	xfs_freesb(xfs_mount_t *);
 extern bool	xfs_fs_writable(struct xfs_mount *mp, int level);
-extern int	xfs_sb_validate_fsb_count(struct xfs_sb *, __uint64_t);
+extern int	xfs_sb_validate_fsb_count(struct xfs_sb *, uint64_t);
 
 extern int	xfs_dev_is_read_only(struct xfs_mount *, char *);
 
diff --git a/fs/xfs/xfs_qm.c b/fs/xfs/xfs_qm.c
index b669b123287b..6ce948c436d5 100644
--- a/fs/xfs/xfs_qm.c
+++ b/fs/xfs/xfs_qm.c
@@ -851,8 +851,8 @@ xfs_qm_reset_dqcounts(
 	 * started afresh by xfs_qm_quotacheck.
 	 */
 #ifdef DEBUG
-	j = XFS_FSB_TO_B(mp, XFS_DQUOT_CLUSTER_SIZE_FSB);
-	do_div(j, sizeof(xfs_dqblk_t));
+	j = (int)XFS_FSB_TO_B(mp, XFS_DQUOT_CLUSTER_SIZE_FSB) /
+		sizeof(xfs_dqblk_t);
 	ASSERT(mp->m_quotainfo->qi_dqperchunk == j);
 #endif
 	dqb = bp->b_addr;
@@ -1247,6 +1247,7 @@ xfs_qm_flush_one(
 	struct xfs_dquot	*dqp,
 	void			*data)
 {
+	struct xfs_mount	*mp = dqp->q_mount;
 	struct list_head	*buffer_list = data;
 	struct xfs_buf		*bp = NULL;
 	int			error = 0;
@@ -1257,7 +1258,32 @@ xfs_qm_flush_one(
 	if (!XFS_DQ_IS_DIRTY(dqp))
 		goto out_unlock;
 
-	xfs_dqflock(dqp);
+	/*
+	 * The only way the dquot is already flush locked by the time quotacheck
+	 * gets here is if reclaim flushed it before the dqadjust walk dirtied
+	 * it for the final time. Quotacheck collects all dquot bufs in the
+	 * local delwri queue before dquots are dirtied, so reclaim can't have
+	 * possibly queued it for I/O. The only way out is to push the buffer to
+	 * cycle the flush lock.
+	 */
+	if (!xfs_dqflock_nowait(dqp)) {
+		/* buf is pinned in-core by delwri list */
+		DEFINE_SINGLE_BUF_MAP(map, dqp->q_blkno,
+				      mp->m_quotainfo->qi_dqchunklen);
+		bp = _xfs_buf_find(mp->m_ddev_targp, &map, 1, 0, NULL);
+		if (!bp) {
+			error = -EINVAL;
+			goto out_unlock;
+		}
+		xfs_buf_unlock(bp);
+
+		xfs_buf_delwri_pushbuf(bp, buffer_list);
+		xfs_buf_rele(bp);
+
+		error = -EAGAIN;
+		goto out_unlock;
+	}
+
 	error = xfs_qm_dqflush(dqp, &bp);
 	if (error)
 		goto out_unlock;
@@ -1384,12 +1410,7 @@ xfs_qm_quotacheck(
 	mp->m_qflags |= flags;
 
  error_return:
-	while (!list_empty(&buffer_list)) {
-		struct xfs_buf *bp =
-			list_first_entry(&buffer_list, struct xfs_buf, b_list);
-		list_del_init(&bp->b_list);
-		xfs_buf_relse(bp);
-	}
+	xfs_buf_delwri_cancel(&buffer_list);
 
 	if (error) {
 		xfs_warn(mp,
diff --git a/fs/xfs/xfs_qm_bhv.c b/fs/xfs/xfs_qm_bhv.c
index 3e52d5de7ae1..2be6d2735ca9 100644
--- a/fs/xfs/xfs_qm_bhv.c
+++ b/fs/xfs/xfs_qm_bhv.c
@@ -33,7 +33,7 @@ xfs_fill_statvfs_from_dquot(
 	struct kstatfs		*statp,
 	struct xfs_dquot	*dqp)
 {
-	__uint64_t		limit;
+	uint64_t		limit;
 
 	limit = dqp->q_core.d_blk_softlimit ?
 		be64_to_cpu(dqp->q_core.d_blk_softlimit) :
diff --git a/fs/xfs/xfs_qm_syscalls.c b/fs/xfs/xfs_qm_syscalls.c
index 475a3882a81f..9cb5c381b01c 100644
--- a/fs/xfs/xfs_qm_syscalls.c
+++ b/fs/xfs/xfs_qm_syscalls.c
@@ -759,5 +759,6 @@ xfs_qm_dqrele_all_inodes(
 	uint		 flags)
 {
 	ASSERT(mp->m_quotainfo);
-	xfs_inode_ag_iterator(mp, xfs_dqrele_inode, flags, NULL);
+	xfs_inode_ag_iterator_flags(mp, xfs_dqrele_inode, flags, NULL,
+				    XFS_AGITER_INEW_WAIT);
 }
diff --git a/fs/xfs/xfs_quotaops.c b/fs/xfs/xfs_quotaops.c
index f82d79a8c694..de9493253edf 100644
--- a/fs/xfs/xfs_quotaops.c
+++ b/fs/xfs/xfs_quotaops.c
@@ -269,7 +269,6 @@ xfs_fs_get_nextdqblk(
 	/* ID may be different, so convert back what we got */
 	*qid = make_kqid(current_user_ns(), qid->type, id);
 	return 0;
-	
 }
 
 STATIC int
diff --git a/fs/xfs/xfs_refcount_item.c b/fs/xfs/xfs_refcount_item.c
index 6e4c7446c3d4..96fe209b5eb6 100644
--- a/fs/xfs/xfs_refcount_item.c
+++ b/fs/xfs/xfs_refcount_item.c
@@ -221,6 +221,7 @@ void
 xfs_cui_release(
 	struct xfs_cui_log_item	*cuip)
 {
+	ASSERT(atomic_read(&cuip->cui_refcount) > 0);
 	if (atomic_dec_and_test(&cuip->cui_refcount)) {
 		xfs_trans_ail_remove(&cuip->cui_item, SHUTDOWN_LOG_IO_ERROR);
 		xfs_cui_item_free(cuip);
diff --git a/fs/xfs/xfs_reflink.c b/fs/xfs/xfs_reflink.c
index 07593a362cd0..ab2270a87196 100644
--- a/fs/xfs/xfs_reflink.c
+++ b/fs/xfs/xfs_reflink.c
@@ -82,11 +82,22 @@
  * mappings are a reservation against the free space in the filesystem;
  * adjacent mappings can also be combined into fewer larger mappings.
  *
+ * As an optimization, the CoW extent size hint (cowextsz) creates
+ * outsized aligned delalloc reservations in the hope of landing out of
+ * order nearby CoW writes in a single extent on disk, thereby reducing
+ * fragmentation and improving future performance.
+ *
+ * D: --RRRRRRSSSRRRRRRRR--- (data fork)
+ * C: ------DDDDDDD--------- (CoW fork)
+ *
  * When dirty pages are being written out (typically in writepage), the
- * delalloc reservations are converted into real mappings by allocating
- * blocks and replacing the delalloc mapping with real ones.  A delalloc
- * mapping can be replaced by several real ones if the free space is
- * fragmented.
+ * delalloc reservations are converted into unwritten mappings by
+ * allocating blocks and replacing the delalloc mapping with real ones.
+ * A delalloc mapping can be replaced by several unwritten ones if the
+ * free space is fragmented.
+ *
+ * D: --RRRRRRSSSRRRRRRRR---
+ * C: ------UUUUUUU---------
  *
  * We want to adapt the delalloc mechanism for copy-on-write, since the
  * write paths are similar.  The first two steps (creating the reservation
@@ -101,13 +112,29 @@
  * Block-aligned directio writes will use the same mechanism as buffered
  * writes.
  *
+ * Just prior to submitting the actual disk write requests, we convert
+ * the extents representing the range of the file actually being written
+ * (as opposed to extra pieces created for the cowextsize hint) to real
+ * extents.  This will become important in the next step:
+ *
+ * D: --RRRRRRSSSRRRRRRRR---
+ * C: ------UUrrUUU---------
+ *
  * CoW remapping must be done after the data block write completes,
  * because we don't want to destroy the old data fork map until we're sure
  * the new block has been written.  Since the new mappings are kept in a
  * separate fork, we can simply iterate these mappings to find the ones
  * that cover the file blocks that we just CoW'd.  For each extent, simply
  * unmap the corresponding range in the data fork, map the new range into
- * the data fork, and remove the extent from the CoW fork.
+ * the data fork, and remove the extent from the CoW fork.  Because of
+ * the presence of the cowextsize hint, however, we must be careful
+ * only to remap the blocks that we've actually written out --  we must
+ * never remap delalloc reservations nor CoW staging blocks that have
+ * yet to be written.  This corresponds exactly to the real extents in
+ * the CoW fork:
+ *
+ * D: --RRRRRRrrSRRRRRRRR---
+ * C: ------UU--UUU---------
  *
  * Since the remapping operation can be applied to an arbitrary file
  * range, we record the need for the remap step as a flag in the ioend
@@ -128,6 +155,7 @@
 int
 xfs_reflink_find_shared(
 	struct xfs_mount	*mp,
+	struct xfs_trans	*tp,
 	xfs_agnumber_t		agno,
 	xfs_agblock_t		agbno,
 	xfs_extlen_t		aglen,
@@ -139,18 +167,18 @@ xfs_reflink_find_shared(
 	struct xfs_btree_cur	*cur;
 	int			error;
 
-	error = xfs_alloc_read_agf(mp, NULL, agno, 0, &agbp);
+	error = xfs_alloc_read_agf(mp, tp, agno, 0, &agbp);
 	if (error)
 		return error;
 
-	cur = xfs_refcountbt_init_cursor(mp, NULL, agbp, agno, NULL);
+	cur = xfs_refcountbt_init_cursor(mp, tp, agbp, agno, NULL);
 
 	error = xfs_refcount_find_shared(cur, agbno, aglen, fbno, flen,
 			find_end_of_shared);
 
 	xfs_btree_del_cursor(cur, error ? XFS_BTREE_ERROR : XFS_BTREE_NOERROR);
 
-	xfs_buf_relse(agbp);
+	xfs_trans_brelse(tp, agbp);
 	return error;
 }
 
@@ -179,11 +207,7 @@ xfs_reflink_trim_around_shared(
 	int			error = 0;
 
 	/* Holes, unwritten, and delalloc extents cannot be shared */
-	if (!xfs_is_reflink_inode(ip) ||
-	    ISUNWRITTEN(irec) ||
-	    irec->br_startblock == HOLESTARTBLOCK ||
-	    irec->br_startblock == DELAYSTARTBLOCK ||
-	    isnullstartblock(irec->br_startblock)) {
+	if (!xfs_is_reflink_inode(ip) || !xfs_bmap_is_real_extent(irec)) {
 		*shared = false;
 		return 0;
 	}
@@ -194,7 +218,7 @@ xfs_reflink_trim_around_shared(
 	agbno = XFS_FSB_TO_AGBNO(ip->i_mount, irec->br_startblock);
 	aglen = irec->br_blockcount;
 
-	error = xfs_reflink_find_shared(ip->i_mount, agno, agbno,
+	error = xfs_reflink_find_shared(ip->i_mount, NULL, agno, agbno,
 			aglen, &fbno, &flen, true);
 	if (error)
 		return error;
@@ -296,103 +320,165 @@ xfs_reflink_reserve_cow(
 	return 0;
 }
 
-/* Allocate all CoW reservations covering a range of blocks in a file. */
-static int
-__xfs_reflink_allocate_cow(
-	struct xfs_inode	*ip,
-	xfs_fileoff_t		*offset_fsb,
-	xfs_fileoff_t		end_fsb)
+/* Convert part of an unwritten CoW extent to a real one. */
+STATIC int
+xfs_reflink_convert_cow_extent(
+	struct xfs_inode		*ip,
+	struct xfs_bmbt_irec		*imap,
+	xfs_fileoff_t			offset_fsb,
+	xfs_filblks_t			count_fsb,
+	struct xfs_defer_ops		*dfops)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-	struct xfs_bmbt_irec	imap;
-	struct xfs_defer_ops	dfops;
-	struct xfs_trans	*tp;
-	xfs_fsblock_t		first_block;
-	int			nimaps = 1, error;
-	bool			shared;
+	xfs_fsblock_t			first_block;
+	int				nimaps = 1;
 
-	xfs_defer_init(&dfops, &first_block);
-
-	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, 0, 0,
-			XFS_TRANS_RESERVE, &tp);
-	if (error)
-		return error;
+	if (imap->br_state == XFS_EXT_NORM)
+		return 0;
 
-	xfs_ilock(ip, XFS_ILOCK_EXCL);
+	xfs_trim_extent(imap, offset_fsb, count_fsb);
+	trace_xfs_reflink_convert_cow(ip, imap);
+	if (imap->br_blockcount == 0)
+		return 0;
+	return xfs_bmapi_write(NULL, ip, imap->br_startoff, imap->br_blockcount,
+			XFS_BMAPI_COWFORK | XFS_BMAPI_CONVERT, &first_block,
+			0, imap, &nimaps, dfops);
+}
 
-	/* Read extent from the source file. */
-	nimaps = 1;
-	error = xfs_bmapi_read(ip, *offset_fsb, end_fsb - *offset_fsb,
-			&imap, &nimaps, 0);
-	if (error)
-		goto out_unlock;
-	ASSERT(nimaps == 1);
+/* Convert all of the unwritten CoW extents in a file's range to real ones. */
+int
+xfs_reflink_convert_cow(
+	struct xfs_inode	*ip,
+	xfs_off_t		offset,
+	xfs_off_t		count)
+{
+	struct xfs_bmbt_irec	got;
+	struct xfs_defer_ops	dfops;
+	struct xfs_mount	*mp = ip->i_mount;
+	struct xfs_ifork	*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
+	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
+	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
+	xfs_extnum_t		idx;
+	bool			found;
+	int			error = 0;
 
-	error = xfs_reflink_reserve_cow(ip, &imap, &shared);
-	if (error)
-		goto out_trans_cancel;
+	xfs_ilock(ip, XFS_ILOCK_EXCL);
 
-	if (!shared) {
-		*offset_fsb = imap.br_startoff + imap.br_blockcount;
-		goto out_trans_cancel;
+	/* Convert all the extents to real from unwritten. */
+	for (found = xfs_iext_lookup_extent(ip, ifp, offset_fsb, &idx, &got);
+	     found && got.br_startoff < end_fsb;
+	     found = xfs_iext_get_extent(ifp, ++idx, &got)) {
+		error = xfs_reflink_convert_cow_extent(ip, &got, offset_fsb,
+				end_fsb - offset_fsb, &dfops);
+		if (error)
+			break;
 	}
 
-	xfs_trans_ijoin(tp, ip, 0);
-	error = xfs_bmapi_write(tp, ip, imap.br_startoff, imap.br_blockcount,
-			XFS_BMAPI_COWFORK, &first_block,
-			XFS_EXTENTADD_SPACE_RES(mp, XFS_DATA_FORK),
-			&imap, &nimaps, &dfops);
-	if (error)
-		goto out_trans_cancel;
-
-	error = xfs_defer_finish(&tp, &dfops, NULL);
-	if (error)
-		goto out_trans_cancel;
-
-	error = xfs_trans_commit(tp);
-
-	*offset_fsb = imap.br_startoff + imap.br_blockcount;
-out_unlock:
+	/* Finish up. */
 	xfs_iunlock(ip, XFS_ILOCK_EXCL);
 	return error;
-out_trans_cancel:
-	xfs_defer_cancel(&dfops);
-	xfs_trans_cancel(tp);
-	goto out_unlock;
 }
 
-/* Allocate all CoW reservations covering a part of a file. */
+/* Allocate all CoW reservations covering a range of blocks in a file. */
 int
-xfs_reflink_allocate_cow_range(
+xfs_reflink_allocate_cow(
 	struct xfs_inode	*ip,
-	xfs_off_t		offset,
-	xfs_off_t		count)
+	struct xfs_bmbt_irec	*imap,
+	bool			*shared,
+	uint			*lockmode)
 {
 	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		offset_fsb = XFS_B_TO_FSBT(mp, offset);
-	xfs_fileoff_t		end_fsb = XFS_B_TO_FSB(mp, offset + count);
-	int			error;
+	xfs_fileoff_t		offset_fsb = imap->br_startoff;
+	xfs_filblks_t		count_fsb = imap->br_blockcount;
+	struct xfs_bmbt_irec	got;
+	struct xfs_defer_ops	dfops;
+	struct xfs_trans	*tp = NULL;
+	xfs_fsblock_t		first_block;
+	int			nimaps, error = 0;
+	bool			trimmed;
+	xfs_filblks_t		resaligned;
+	xfs_extlen_t		resblks = 0;
+	xfs_extnum_t		idx;
 
+retry:
 	ASSERT(xfs_is_reflink_inode(ip));
-
-	trace_xfs_reflink_allocate_cow_range(ip, offset, count);
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_EXCL | XFS_ILOCK_SHARED));
 
 	/*
-	 * Make sure that the dquots are there.
+	 * Even if the extent is not shared we might have a preallocation for
+	 * it in the COW fork.  If so use it.
 	 */
-	error = xfs_qm_dqattach(ip, 0);
-	if (error)
-		return error;
+	if (xfs_iext_lookup_extent(ip, ip->i_cowfp, offset_fsb, &idx, &got) &&
+	    got.br_startoff <= offset_fsb) {
+		*shared = true;
 
-	while (offset_fsb < end_fsb) {
-		error = __xfs_reflink_allocate_cow(ip, &offset_fsb, end_fsb);
-		if (error) {
-			trace_xfs_reflink_allocate_cow_range_error(ip, error,
-					_RET_IP_);
-			break;
+		/* If we have a real allocation in the COW fork we're done. */
+		if (!isnullstartblock(got.br_startblock)) {
+			xfs_trim_extent(&got, offset_fsb, count_fsb);
+			*imap = got;
+			goto convert;
 		}
+
+		xfs_trim_extent(imap, got.br_startoff, got.br_blockcount);
+	} else {
+		error = xfs_reflink_trim_around_shared(ip, imap, shared, &trimmed);
+		if (error || !*shared)
+			goto out;
+	}
+
+	if (!tp) {
+		resaligned = xfs_aligned_fsb_count(imap->br_startoff,
+			imap->br_blockcount, xfs_get_cowextsz_hint(ip));
+		resblks = XFS_DIOSTRAT_SPACE_RES(mp, resaligned);
+
+		xfs_iunlock(ip, *lockmode);
+		error = xfs_trans_alloc(mp, &M_RES(mp)->tr_write, resblks, 0, 0, &tp);
+		*lockmode = XFS_ILOCK_EXCL;
+		xfs_ilock(ip, *lockmode);
+
+		if (error)
+			return error;
+
+		error = xfs_qm_dqattach_locked(ip, 0);
+		if (error)
+			goto out;
+		goto retry;
 	}
 
+	error = xfs_trans_reserve_quota_nblks(tp, ip, resblks, 0,
+			XFS_QMOPT_RES_REGBLKS);
+	if (error)
+		goto out;
+
+	xfs_trans_ijoin(tp, ip, 0);
+
+	xfs_defer_init(&dfops, &first_block);
+	nimaps = 1;
+
+	/* Allocate the entire reservation as unwritten blocks. */
+	error = xfs_bmapi_write(tp, ip, imap->br_startoff, imap->br_blockcount,
+			XFS_BMAPI_COWFORK | XFS_BMAPI_PREALLOC, &first_block,
+			resblks, imap, &nimaps, &dfops);
+	if (error)
+		goto out_bmap_cancel;
+
+	/* Finish up. */
+	error = xfs_defer_finish(&tp, &dfops, NULL);
+	if (error)
+		goto out_bmap_cancel;
+
+	error = xfs_trans_commit(tp);
+	if (error)
+		return error;
+convert:
+	return xfs_reflink_convert_cow_extent(ip, imap, offset_fsb, count_fsb,
+			&dfops);
+out_bmap_cancel:
+	xfs_defer_cancel(&dfops);
+	xfs_trans_unreserve_quota_nblks(tp, ip, (long)resblks, 0,
+			XFS_QMOPT_RES_REGBLKS);
+out:
+	if (tp)
+		xfs_trans_cancel(tp);
 	return error;
 }
 
@@ -459,14 +545,18 @@ xfs_reflink_trim_irec_to_next_cow(
 }
 
 /*
- * Cancel all pending CoW reservations for some block range of an inode.
+ * Cancel CoW reservations for some block range of an inode.
+ *
+ * If cancel_real is true this function cancels all COW fork extents for the
+ * inode; if cancel_real is false, real extents are not cleared.
  */
 int
 xfs_reflink_cancel_cow_blocks(
 	struct xfs_inode		*ip,
 	struct xfs_trans		**tpp,
 	xfs_fileoff_t			offset_fsb,
-	xfs_fileoff_t			end_fsb)
+	xfs_fileoff_t			end_fsb,
+	bool				cancel_real)
 {
 	struct xfs_ifork		*ifp = XFS_IFORK_PTR(ip, XFS_COW_FORK);
 	struct xfs_bmbt_irec		got, del;
@@ -490,7 +580,7 @@ xfs_reflink_cancel_cow_blocks(
 					&idx, &got, &del);
 			if (error)
 				break;
-		} else {
+		} else if (del.br_state == XFS_EXT_UNWRITTEN || cancel_real) {
 			xfs_trans_ijoin(*tpp, ip, 0);
 			xfs_defer_init(&dfops, &firstfsb);
 
@@ -532,13 +622,17 @@ xfs_reflink_cancel_cow_blocks(
 }
 
 /*
- * Cancel all pending CoW reservations for some byte range of an inode.
+ * Cancel CoW reservations for some byte range of an inode.
+ *
+ * If cancel_real is true this function cancels all COW fork extents for the
+ * inode; if cancel_real is false, real extents are not cleared.
  */
 int
 xfs_reflink_cancel_cow_range(
 	struct xfs_inode	*ip,
 	xfs_off_t		offset,
-	xfs_off_t		count)
+	xfs_off_t		count,
+	bool			cancel_real)
 {
 	struct xfs_trans	*tp;
 	xfs_fileoff_t		offset_fsb;
@@ -564,7 +658,8 @@ xfs_reflink_cancel_cow_range(
 	xfs_trans_ijoin(tp, ip, 0);
 
 	/* Scrape out the old CoW reservations */
-	error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb);
+	error = xfs_reflink_cancel_cow_blocks(ip, &tp, offset_fsb, end_fsb,
+			cancel_real);
 	if (error)
 		goto out_cancel;
 
@@ -611,8 +706,22 @@ xfs_reflink_end_cow(
 	offset_fsb = XFS_B_TO_FSBT(ip->i_mount, offset);
 	end_fsb = XFS_B_TO_FSB(ip->i_mount, offset + count);
 
-	/* Start a rolling transaction to switch the mappings */
-	resblks = XFS_EXTENTADD_SPACE_RES(ip->i_mount, XFS_DATA_FORK);
+	/*
+	 * Start a rolling transaction to switch the mappings.  We're
+	 * unlikely ever to have to remap 16T worth of single-block
+	 * extents, so just cap the worst case extent count to 2^32-1.
+	 * Stick a warning in just in case, and avoid 64-bit division.
+	 */
+	BUILD_BUG_ON(MAX_RW_COUNT > UINT_MAX);
+	if (end_fsb - offset_fsb > UINT_MAX) {
+		error = -EFSCORRUPTED;
+		xfs_force_shutdown(ip->i_mount, SHUTDOWN_CORRUPT_INCORE);
+		ASSERT(0);
+		goto out;
+	}
+	resblks = XFS_NEXTENTADD_SPACE_RES(ip->i_mount,
+			(unsigned int)(end_fsb - offset_fsb),
+			XFS_DATA_FORK);
 	error = xfs_trans_alloc(ip->i_mount, &M_RES(ip->i_mount)->tr_write,
 			resblks, 0, 0, &tp);
 	if (error)
@@ -641,6 +750,16 @@ xfs_reflink_end_cow(
 
 		ASSERT(!isnullstartblock(got.br_startblock));
 
+		/*
+		 * Don't remap unwritten extents; these are
+		 * speculatively preallocated CoW extents that have been
+		 * allocated but have not yet been involved in a write.
+		 */
+		if (got.br_state == XFS_EXT_UNWRITTEN) {
+			idx--;
+			goto next_extent;
+		}
+
 		/* Unmap the old blocks in the data fork. */
 		xfs_defer_init(&dfops, &firstfsb);
 		rlen = del.br_blockcount;
@@ -855,13 +974,14 @@ STATIC int
 xfs_reflink_update_dest(
 	struct xfs_inode	*dest,
 	xfs_off_t		newlen,
-	xfs_extlen_t		cowextsize)
+	xfs_extlen_t		cowextsize,
+	bool			is_dedupe)
 {
 	struct xfs_mount	*mp = dest->i_mount;
 	struct xfs_trans	*tp;
 	int			error;
 
-	if (newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0)
+	if (is_dedupe && newlen <= i_size_read(VFS_I(dest)) && cowextsize == 0)
 		return 0;
 
 	error = xfs_trans_alloc(mp, &M_RES(mp)->tr_ichange, 0, 0, 0, &tp);
@@ -882,6 +1002,10 @@ xfs_reflink_update_dest(
 		dest->i_d.di_flags2 |= XFS_DIFLAG2_COWEXTSIZE;
 	}
 
+	if (!is_dedupe) {
+		xfs_trans_ichgtime(tp, dest,
+				   XFS_ICHGTIME_MOD | XFS_ICHGTIME_CHG);
+	}
 	xfs_trans_log_inode(tp, dest, XFS_ILOG_CORE);
 
 	error = xfs_trans_commit(tp);
@@ -932,12 +1056,12 @@ xfs_reflink_remap_extent(
 	xfs_off_t		new_isize)
 {
 	struct xfs_mount	*mp = ip->i_mount;
+	bool			real_extent = xfs_bmap_is_real_extent(irec);
 	struct xfs_trans	*tp;
 	xfs_fsblock_t		firstfsb;
 	unsigned int		resblks;
 	struct xfs_defer_ops	dfops;
 	struct xfs_bmbt_irec	uirec;
-	bool			real_extent;
 	xfs_filblks_t		rlen;
 	xfs_filblks_t		unmap_len;
 	xfs_off_t		newlen;
@@ -946,11 +1070,6 @@ xfs_reflink_remap_extent(
 	unmap_len = irec->br_startoff + irec->br_blockcount - destoff;
 	trace_xfs_reflink_punch_range(ip, destoff, unmap_len);
 
-	/* Only remap normal extents. */
-	real_extent =  (irec->br_startblock != HOLESTARTBLOCK &&
-			irec->br_startblock != DELAYSTARTBLOCK &&
-			!ISUNWRITTEN(irec));
-
 	/* No reflinking if we're low on space */
 	if (real_extent) {
 		error = xfs_reflink_ag_has_free_space(mp,
@@ -1195,7 +1314,8 @@ xfs_reflink_remap_range(
 	    !(dest->i_d.di_flags2 & XFS_DIFLAG2_COWEXTSIZE))
 		cowextsize = src->i_d.di_cowextsize;
 
-	ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize);
+	ret = xfs_reflink_update_dest(dest, pos_out + len, cowextsize,
+			is_dedupe);
 
 out_unlock:
 	xfs_iunlock(src, XFS_MMAPLOCK_EXCL);
@@ -1245,9 +1365,7 @@ xfs_reflink_dirty_extents(
 			goto out;
 		if (nmaps == 0)
 			break;
-		if (map[0].br_startblock == HOLESTARTBLOCK ||
-		    map[0].br_startblock == DELAYSTARTBLOCK ||
-		    ISUNWRITTEN(&map[0]))
+		if (!xfs_bmap_is_real_extent(&map[0]))
 			goto next;
 
 		map[1] = map[0];
@@ -1256,8 +1374,8 @@ xfs_reflink_dirty_extents(
 			agbno = XFS_FSB_TO_AGBNO(mp, map[1].br_startblock);
 			aglen = map[1].br_blockcount;
 
-			error = xfs_reflink_find_shared(mp, agno, agbno, aglen,
-					&rbno, &rlen, true);
+			error = xfs_reflink_find_shared(mp, NULL, agno, agbno,
+					aglen, &rbno, &rlen, true);
 			if (error)
 				goto out;
 			if (rbno == NULLAGBLOCK)
@@ -1288,64 +1406,78 @@ out:
 	return error;
 }
 
-/* Clear the inode reflink flag if there are no shared extents. */
+/* Does this inode need the reflink flag? */
 int
-xfs_reflink_clear_inode_flag(
-	struct xfs_inode	*ip,
-	struct xfs_trans	**tpp)
+xfs_reflink_inode_has_shared_extents(
+	struct xfs_trans		*tp,
+	struct xfs_inode		*ip,
+	bool				*has_shared)
 {
-	struct xfs_mount	*mp = ip->i_mount;
-	xfs_fileoff_t		fbno;
-	xfs_filblks_t		end;
-	xfs_agnumber_t		agno;
-	xfs_agblock_t		agbno;
-	xfs_extlen_t		aglen;
-	xfs_agblock_t		rbno;
-	xfs_extlen_t		rlen;
-	struct xfs_bmbt_irec	map;
-	int			nmaps;
-	int			error = 0;
-
-	ASSERT(xfs_is_reflink_inode(ip));
+	struct xfs_bmbt_irec		got;
+	struct xfs_mount		*mp = ip->i_mount;
+	struct xfs_ifork		*ifp;
+	xfs_agnumber_t			agno;
+	xfs_agblock_t			agbno;
+	xfs_extlen_t			aglen;
+	xfs_agblock_t			rbno;
+	xfs_extlen_t			rlen;
+	xfs_extnum_t			idx;
+	bool				found;
+	int				error;
 
-	fbno = 0;
-	end = XFS_B_TO_FSB(mp, i_size_read(VFS_I(ip)));
-	while (end - fbno > 0) {
-		nmaps = 1;
-		/*
-		 * Look for extents in the file.  Skip holes, delalloc, or
-		 * unwritten extents; they can't be reflinked.
-		 */
-		error = xfs_bmapi_read(ip, fbno, end - fbno, &map, &nmaps, 0);
+	ifp = XFS_IFORK_PTR(ip, XFS_DATA_FORK);
+	if (!(ifp->if_flags & XFS_IFEXTENTS)) {
+		error = xfs_iread_extents(tp, ip, XFS_DATA_FORK);
 		if (error)
 			return error;
-		if (nmaps == 0)
-			break;
-		if (map.br_startblock == HOLESTARTBLOCK ||
-		    map.br_startblock == DELAYSTARTBLOCK ||
-		    ISUNWRITTEN(&map))
-			goto next;
+	}
 
-		agno = XFS_FSB_TO_AGNO(mp, map.br_startblock);
-		agbno = XFS_FSB_TO_AGBNO(mp, map.br_startblock);
-		aglen = map.br_blockcount;
+	*has_shared = false;
+	found = xfs_iext_lookup_extent(ip, ifp, 0, &idx, &got);
+	while (found) {
+		if (isnullstartblock(got.br_startblock) ||
+		    got.br_state != XFS_EXT_NORM)
+			goto next;
+		agno = XFS_FSB_TO_AGNO(mp, got.br_startblock);
+		agbno = XFS_FSB_TO_AGBNO(mp, got.br_startblock);
+		aglen = got.br_blockcount;
 
-		error = xfs_reflink_find_shared(mp, agno, agbno, aglen,
+		error = xfs_reflink_find_shared(mp, tp, agno, agbno, aglen,
 				&rbno, &rlen, false);
 		if (error)
 			return error;
 		/* Is there still a shared block here? */
-		if (rbno != NULLAGBLOCK)
+		if (rbno != NULLAGBLOCK) {
+			*has_shared = true;
 			return 0;
+		}
 next:
-		fbno = map.br_startoff + map.br_blockcount;
+		found = xfs_iext_get_extent(ifp, ++idx, &got);
 	}
 
+	return 0;
+}
+
+/* Clear the inode reflink flag if there are no shared extents. */
+int
+xfs_reflink_clear_inode_flag(
+	struct xfs_inode	*ip,
+	struct xfs_trans	**tpp)
+{
+	bool			needs_flag;
+	int			error = 0;
+
+	ASSERT(xfs_is_reflink_inode(ip));
+
+	error = xfs_reflink_inode_has_shared_extents(*tpp, ip, &needs_flag);
+	if (error || needs_flag)
+		return error;
+
 	/*
 	 * We didn't find any shared blocks so turn off the reflink flag.
 	 * First, get rid of any leftover CoW mappings.
 	 */
-	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF);
+	error = xfs_reflink_cancel_cow_blocks(ip, tpp, 0, NULLFILEOFF, true);
 	if (error)
 		return error;
 
diff --git a/fs/xfs/xfs_reflink.h b/fs/xfs/xfs_reflink.h
index aa6a4d64bd35..701487bab468 100644
--- a/fs/xfs/xfs_reflink.h
+++ b/fs/xfs/xfs_reflink.h
@@ -20,16 +20,18 @@
 #ifndef __XFS_REFLINK_H
 #define __XFS_REFLINK_H 1
 
-extern int xfs_reflink_find_shared(struct xfs_mount *mp, xfs_agnumber_t agno,
-		xfs_agblock_t agbno, xfs_extlen_t aglen, xfs_agblock_t *fbno,
-		xfs_extlen_t *flen, bool find_maximal);
+extern int xfs_reflink_find_shared(struct xfs_mount *mp, struct xfs_trans *tp,
+		xfs_agnumber_t agno, xfs_agblock_t agbno, xfs_extlen_t aglen,
+		xfs_agblock_t *fbno, xfs_extlen_t *flen, bool find_maximal);
 extern int xfs_reflink_trim_around_shared(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *irec, bool *shared, bool *trimmed);
 
 extern int xfs_reflink_reserve_cow(struct xfs_inode *ip,
 		struct xfs_bmbt_irec *imap, bool *shared);
-extern int xfs_reflink_allocate_cow_range(struct xfs_inode *ip,
-		xfs_off_t offset, xfs_off_t count);
+extern int xfs_reflink_allocate_cow(struct xfs_inode *ip,
+		struct xfs_bmbt_irec *imap, bool *shared, uint *lockmode);
+extern int xfs_reflink_convert_cow(struct xfs_inode *ip, xfs_off_t offset,
+		xfs_off_t count);
 extern bool xfs_reflink_find_cow_mapping(struct xfs_inode *ip, xfs_off_t offset,
 		struct xfs_bmbt_irec *imap);
 extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
@@ -37,14 +39,16 @@ extern void xfs_reflink_trim_irec_to_next_cow(struct xfs_inode *ip,
 
 extern int xfs_reflink_cancel_cow_blocks(struct xfs_inode *ip,
 		struct xfs_trans **tpp, xfs_fileoff_t offset_fsb,
-		xfs_fileoff_t end_fsb);
+		xfs_fileoff_t end_fsb, bool cancel_real);
 extern int xfs_reflink_cancel_cow_range(struct xfs_inode *ip, xfs_off_t offset,
-		xfs_off_t count);
+		xfs_off_t count, bool cancel_real);
 extern int xfs_reflink_end_cow(struct xfs_inode *ip, xfs_off_t offset,
 		xfs_off_t count);
 extern int xfs_reflink_recover_cow(struct xfs_mount *mp);
 extern int xfs_reflink_remap_range(struct file *file_in, loff_t pos_in,
 		struct file *file_out, loff_t pos_out, u64 len, bool is_dedupe);
+extern int xfs_reflink_inode_has_shared_extents(struct xfs_trans *tp,
+		struct xfs_inode *ip, bool *has_shared);
 extern int xfs_reflink_clear_inode_flag(struct xfs_inode *ip,
 		struct xfs_trans **tpp);
 extern int xfs_reflink_unshare(struct xfs_inode *ip, xfs_off_t offset,
diff --git a/fs/xfs/xfs_rmap_item.c b/fs/xfs/xfs_rmap_item.c
index 73c827831551..f3b139c9aa16 100644
--- a/fs/xfs/xfs_rmap_item.c
+++ b/fs/xfs/xfs_rmap_item.c
@@ -243,6 +243,7 @@ void
 xfs_rui_release(
 	struct xfs_rui_log_item	*ruip)
 {
+	ASSERT(atomic_read(&ruip->rui_refcount) > 0);
 	if (atomic_dec_and_test(&ruip->rui_refcount)) {
 		xfs_trans_ail_remove(&ruip->rui_item, SHUTDOWN_LOG_IO_ERROR);
 		xfs_rui_item_free(ruip);
diff --git a/fs/xfs/xfs_rtalloc.c b/fs/xfs/xfs_rtalloc.c
index 802bcc326d9f..91472193643b 100644
--- a/fs/xfs/xfs_rtalloc.c
+++ b/fs/xfs/xfs_rtalloc.c
@@ -1093,7 +1093,6 @@ xfs_rtallocate_extent(
 	xfs_extlen_t	minlen,		/* minimum length to allocate */
 	xfs_extlen_t	maxlen,		/* maximum length to allocate */
 	xfs_extlen_t	*len,		/* out: actual length allocated */
-	xfs_alloctype_t	type,		/* allocation type XFS_ALLOCTYPE... */
 	int		wasdel,		/* was a delayed allocation extent */
 	xfs_extlen_t	prod,		/* extent product factor */
 	xfs_rtblock_t	*rtblock)	/* out: start block allocated */
@@ -1123,27 +1122,16 @@ xfs_rtallocate_extent(
 		}
 	}
 
+retry:
 	sumbp = NULL;
-	/*
-	 * Allocate by size, or near another block, or exactly at some block.
-	 */
-	switch (type) {
-	case XFS_ALLOCTYPE_ANY_AG:
+	if (bno == 0) {
 		error = xfs_rtallocate_extent_size(mp, tp, minlen, maxlen, len,
 				&sumbp,	&sb, prod, &r);
-		break;
-	case XFS_ALLOCTYPE_NEAR_BNO:
+	} else {
 		error = xfs_rtallocate_extent_near(mp, tp, bno, minlen, maxlen,
 				len, &sumbp, &sb, prod, &r);
-		break;
-	case XFS_ALLOCTYPE_THIS_BNO:
-		error = xfs_rtallocate_extent_exact(mp, tp, bno, minlen, maxlen,
-				len, &sumbp, &sb, prod, &r);
-		break;
-	default:
-		error = -EIO;
-		ASSERT(0);
 	}
+
 	if (error)
 		return error;
 
@@ -1158,7 +1146,11 @@ xfs_rtallocate_extent(
 			xfs_trans_mod_sb(tp, XFS_TRANS_SB_RES_FREXTENTS, -slen);
 		else
 			xfs_trans_mod_sb(tp, XFS_TRANS_SB_FREXTENTS, -slen);
+	} else if (prod > 1) {
+		prod = 1;
+		goto retry;
 	}
+
 	*rtblock = r;
 	return 0;
 }
@@ -1264,13 +1256,13 @@ xfs_rtpick_extent(
 {
 	xfs_rtblock_t	b;		/* result block */
 	int		log2;		/* log of sequence number */
-	__uint64_t	resid;		/* residual after log removed */
-	__uint64_t	seq;		/* sequence number of file creation */
-	__uint64_t	*seqp;		/* pointer to seqno in inode */
+	uint64_t	resid;		/* residual after log removed */
+	uint64_t	seq;		/* sequence number of file creation */
+	uint64_t	*seqp;		/* pointer to seqno in inode */
 
 	ASSERT(xfs_isilocked(mp->m_rbmip, XFS_ILOCK_EXCL));
 
-	seqp = (__uint64_t *)&VFS_I(mp->m_rbmip)->i_atime;
+	seqp = (uint64_t *)&VFS_I(mp->m_rbmip)->i_atime;
 	if (!(mp->m_rbmip->i_d.di_flags & XFS_DIFLAG_NEWRTBM)) {
 		mp->m_rbmip->i_d.di_flags |= XFS_DIFLAG_NEWRTBM;
 		*seqp = 0;
diff --git a/fs/xfs/xfs_rtalloc.h b/fs/xfs/xfs_rtalloc.h
index 355dd9e1cb64..79defa722bf1 100644
--- a/fs/xfs/xfs_rtalloc.h
+++ b/fs/xfs/xfs_rtalloc.h
@@ -23,6 +23,16 @@
 struct xfs_mount;
 struct xfs_trans;
 
+struct xfs_rtalloc_rec {
+	xfs_rtblock_t		ar_startblock;
+	xfs_rtblock_t		ar_blockcount;
+};
+
+typedef int (*xfs_rtalloc_query_range_fn)(
+	struct xfs_trans	*tp,
+	struct xfs_rtalloc_rec	*rec,
+	void			*priv);
+
 #ifdef CONFIG_XFS_RT
 /*
  * Function prototypes for exported functions.
@@ -40,7 +50,6 @@ xfs_rtallocate_extent(
 	xfs_extlen_t		minlen,	/* minimum length to allocate */
 	xfs_extlen_t		maxlen,	/* maximum length to allocate */
 	xfs_extlen_t		*len,	/* out: actual length allocated */
-	xfs_alloctype_t		type,	/* allocation type XFS_ALLOCTYPE... */
 	int			wasdel,	/* was a delayed allocation extent */
 	xfs_extlen_t		prod,	/* extent product factor */
 	xfs_rtblock_t		*rtblock); /* out: start block allocated */
@@ -98,6 +107,8 @@ xfs_growfs_rt(
 /*
  * From xfs_rtbitmap.c
  */
+int xfs_rtbuf_get(struct xfs_mount *mp, struct xfs_trans *tp,
+		  xfs_rtblock_t block, int issum, struct xfs_buf **bpp);
 int xfs_rtcheck_range(struct xfs_mount *mp, struct xfs_trans *tp,
 		      xfs_rtblock_t start, xfs_extlen_t len, int val,
 		      xfs_rtblock_t *new, int *stat);
@@ -119,13 +130,22 @@ int xfs_rtmodify_summary(struct xfs_mount *mp, struct xfs_trans *tp, int log,
 int xfs_rtfree_range(struct xfs_mount *mp, struct xfs_trans *tp,
 		     xfs_rtblock_t start, xfs_extlen_t len,
 		     struct xfs_buf **rbpp, xfs_fsblock_t *rsb);
-
-
+int xfs_rtalloc_query_range(struct xfs_trans *tp,
+			    struct xfs_rtalloc_rec *low_rec,
+			    struct xfs_rtalloc_rec *high_rec,
+			    xfs_rtalloc_query_range_fn fn,
+			    void *priv);
+int xfs_rtalloc_query_all(struct xfs_trans *tp,
+			  xfs_rtalloc_query_range_fn fn,
+			  void *priv);
 #else
-# define xfs_rtallocate_extent(t,b,min,max,l,a,f,p,rb)  (ENOSYS)
+# define xfs_rtallocate_extent(t,b,min,max,l,f,p,rb)    (ENOSYS)
 # define xfs_rtfree_extent(t,b,l)                       (ENOSYS)
 # define xfs_rtpick_extent(m,t,l,rb)                    (ENOSYS)
 # define xfs_growfs_rt(mp,in)                           (ENOSYS)
+# define xfs_rtalloc_query_range(t,l,h,f,p)             (ENOSYS)
+# define xfs_rtalloc_query_all(t,f,p)                   (ENOSYS)
+# define xfs_rtbuf_get(m,t,b,i,p)                       (ENOSYS)
 static inline int		/* error */
 xfs_rtmount_init(
 	xfs_mount_t	*mp)	/* file system mount structure */
diff --git a/fs/xfs/xfs_stats.c b/fs/xfs/xfs_stats.c
index f11282c96887..056e12b421eb 100644
--- a/fs/xfs/xfs_stats.c
+++ b/fs/xfs/xfs_stats.c
@@ -33,9 +33,9 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 {
 	int		i, j;
 	int		len = 0;
-	__uint64_t	xs_xstrat_bytes = 0;
-	__uint64_t	xs_write_bytes = 0;
-	__uint64_t	xs_read_bytes = 0;
+	uint64_t	xs_xstrat_bytes = 0;
+	uint64_t	xs_write_bytes = 0;
+	uint64_t	xs_read_bytes = 0;
 
 	static const struct xstats_entry {
 		char	*desc;
@@ -100,7 +100,7 @@ int xfs_stats_format(struct xfsstats __percpu *stats, char *buf)
 void xfs_stats_clearall(struct xfsstats __percpu *stats)
 {
 	int		c;
-	__uint32_t	vn_active;
+	uint32_t	vn_active;
 
 	xfs_notice(NULL, "Clearing xfsstats");
 	for_each_possible_cpu(c) {
diff --git a/fs/xfs/xfs_stats.h b/fs/xfs/xfs_stats.h
index 375840f5a99a..f64d0ae345c4 100644
--- a/fs/xfs/xfs_stats.h
+++ b/fs/xfs/xfs_stats.h
@@ -54,125 +54,125 @@ enum {
  */
 struct __xfsstats {
 # define XFSSTAT_END_EXTENT_ALLOC	4
-	__uint32_t		xs_allocx;
-	__uint32_t		xs_allocb;
-	__uint32_t		xs_freex;
-	__uint32_t		xs_freeb;
+	uint32_t		xs_allocx;
+	uint32_t		xs_allocb;
+	uint32_t		xs_freex;
+	uint32_t		xs_freeb;
 # define XFSSTAT_END_ALLOC_BTREE	(XFSSTAT_END_EXTENT_ALLOC+4)
-	__uint32_t		xs_abt_lookup;
-	__uint32_t		xs_abt_compare;
-	__uint32_t		xs_abt_insrec;
-	__uint32_t		xs_abt_delrec;
+	uint32_t		xs_abt_lookup;
+	uint32_t		xs_abt_compare;
+	uint32_t		xs_abt_insrec;
+	uint32_t		xs_abt_delrec;
 # define XFSSTAT_END_BLOCK_MAPPING	(XFSSTAT_END_ALLOC_BTREE+7)
-	__uint32_t		xs_blk_mapr;
-	__uint32_t		xs_blk_mapw;
-	__uint32_t		xs_blk_unmap;
-	__uint32_t		xs_add_exlist;
-	__uint32_t		xs_del_exlist;
-	__uint32_t		xs_look_exlist;
-	__uint32_t		xs_cmp_exlist;
+	uint32_t		xs_blk_mapr;
+	uint32_t		xs_blk_mapw;
+	uint32_t		xs_blk_unmap;
+	uint32_t		xs_add_exlist;
+	uint32_t		xs_del_exlist;
+	uint32_t		xs_look_exlist;
+	uint32_t		xs_cmp_exlist;
 # define XFSSTAT_END_BLOCK_MAP_BTREE	(XFSSTAT_END_BLOCK_MAPPING+4)
-	__uint32_t		xs_bmbt_lookup;
-	__uint32_t		xs_bmbt_compare;
-	__uint32_t		xs_bmbt_insrec;
-	__uint32_t		xs_bmbt_delrec;
+	uint32_t		xs_bmbt_lookup;
+	uint32_t		xs_bmbt_compare;
+	uint32_t		xs_bmbt_insrec;
+	uint32_t		xs_bmbt_delrec;
 # define XFSSTAT_END_DIRECTORY_OPS	(XFSSTAT_END_BLOCK_MAP_BTREE+4)
-	__uint32_t		xs_dir_lookup;
-	__uint32_t		xs_dir_create;
-	__uint32_t		xs_dir_remove;
-	__uint32_t		xs_dir_getdents;
+	uint32_t		xs_dir_lookup;
+	uint32_t		xs_dir_create;
+	uint32_t		xs_dir_remove;
+	uint32_t		xs_dir_getdents;
 # define XFSSTAT_END_TRANSACTIONS	(XFSSTAT_END_DIRECTORY_OPS+3)
-	__uint32_t		xs_trans_sync;
-	__uint32_t		xs_trans_async;
-	__uint32_t		xs_trans_empty;
+	uint32_t		xs_trans_sync;
+	uint32_t		xs_trans_async;
+	uint32_t		xs_trans_empty;
 # define XFSSTAT_END_INODE_OPS		(XFSSTAT_END_TRANSACTIONS+7)
-	__uint32_t		xs_ig_attempts;
-	__uint32_t		xs_ig_found;
-	__uint32_t		xs_ig_frecycle;
-	__uint32_t		xs_ig_missed;
-	__uint32_t		xs_ig_dup;
-	__uint32_t		xs_ig_reclaims;
-	__uint32_t		xs_ig_attrchg;
+	uint32_t		xs_ig_attempts;
+	uint32_t		xs_ig_found;
+	uint32_t		xs_ig_frecycle;
+	uint32_t		xs_ig_missed;
+	uint32_t		xs_ig_dup;
+	uint32_t		xs_ig_reclaims;
+	uint32_t		xs_ig_attrchg;
 # define XFSSTAT_END_LOG_OPS		(XFSSTAT_END_INODE_OPS+5)
-	__uint32_t		xs_log_writes;
-	__uint32_t		xs_log_blocks;
-	__uint32_t		xs_log_noiclogs;
-	__uint32_t		xs_log_force;
-	__uint32_t		xs_log_force_sleep;
+	uint32_t		xs_log_writes;
+	uint32_t		xs_log_blocks;
+	uint32_t		xs_log_noiclogs;
+	uint32_t		xs_log_force;
+	uint32_t		xs_log_force_sleep;
 # define XFSSTAT_END_TAIL_PUSHING	(XFSSTAT_END_LOG_OPS+10)
-	__uint32_t		xs_try_logspace;
-	__uint32_t		xs_sleep_logspace;
-	__uint32_t		xs_push_ail;
-	__uint32_t		xs_push_ail_success;
-	__uint32_t		xs_push_ail_pushbuf;
-	__uint32_t		xs_push_ail_pinned;
-	__uint32_t		xs_push_ail_locked;
-	__uint32_t		xs_push_ail_flushing;
-	__uint32_t		xs_push_ail_restarts;
-	__uint32_t		xs_push_ail_flush;
+	uint32_t		xs_try_logspace;
+	uint32_t		xs_sleep_logspace;
+	uint32_t		xs_push_ail;
+	uint32_t		xs_push_ail_success;
+	uint32_t		xs_push_ail_pushbuf;
+	uint32_t		xs_push_ail_pinned;
+	uint32_t		xs_push_ail_locked;
+	uint32_t		xs_push_ail_flushing;
+	uint32_t		xs_push_ail_restarts;
+	uint32_t		xs_push_ail_flush;
 # define XFSSTAT_END_WRITE_CONVERT	(XFSSTAT_END_TAIL_PUSHING+2)
-	__uint32_t		xs_xstrat_quick;
-	__uint32_t		xs_xstrat_split;
+	uint32_t		xs_xstrat_quick;
+	uint32_t		xs_xstrat_split;
 # define XFSSTAT_END_READ_WRITE_OPS	(XFSSTAT_END_WRITE_CONVERT+2)
-	__uint32_t		xs_write_calls;
-	__uint32_t		xs_read_calls;
+	uint32_t		xs_write_calls;
+	uint32_t		xs_read_calls;
 # define XFSSTAT_END_ATTRIBUTE_OPS	(XFSSTAT_END_READ_WRITE_OPS+4)
-	__uint32_t		xs_attr_get;
-	__uint32_t		xs_attr_set;
-	__uint32_t		xs_attr_remove;
-	__uint32_t		xs_attr_list;
+	uint32_t		xs_attr_get;
+	uint32_t		xs_attr_set;
+	uint32_t		xs_attr_remove;
+	uint32_t		xs_attr_list;
 # define XFSSTAT_END_INODE_CLUSTER	(XFSSTAT_END_ATTRIBUTE_OPS+3)
-	__uint32_t		xs_iflush_count;
-	__uint32_t		xs_icluster_flushcnt;
-	__uint32_t		xs_icluster_flushinode;
+	uint32_t		xs_iflush_count;
+	uint32_t		xs_icluster_flushcnt;
+	uint32_t		xs_icluster_flushinode;
 # define XFSSTAT_END_VNODE_OPS		(XFSSTAT_END_INODE_CLUSTER+8)
-	__uint32_t		vn_active;	/* # vnodes not on free lists */
-	__uint32_t		vn_alloc;	/* # times vn_alloc called */
-	__uint32_t		vn_get;		/* # times vn_get called */
-	__uint32_t		vn_hold;	/* # times vn_hold called */
-	__uint32_t		vn_rele;	/* # times vn_rele called */
-	__uint32_t		vn_reclaim;	/* # times vn_reclaim called */
-	__uint32_t		vn_remove;	/* # times vn_remove called */
-	__uint32_t		vn_free;	/* # times vn_free called */
+	uint32_t		vn_active;	/* # vnodes not on free lists */
+	uint32_t		vn_alloc;	/* # times vn_alloc called */
+	uint32_t		vn_get;		/* # times vn_get called */
+	uint32_t		vn_hold;	/* # times vn_hold called */
+	uint32_t		vn_rele;	/* # times vn_rele called */
+	uint32_t		vn_reclaim;	/* # times vn_reclaim called */
+	uint32_t		vn_remove;	/* # times vn_remove called */
+	uint32_t		vn_free;	/* # times vn_free called */
 #define XFSSTAT_END_BUF			(XFSSTAT_END_VNODE_OPS+9)
-	__uint32_t		xb_get;
-	__uint32_t		xb_create;
-	__uint32_t		xb_get_locked;
-	__uint32_t		xb_get_locked_waited;
-	__uint32_t		xb_busy_locked;
-	__uint32_t		xb_miss_locked;
-	__uint32_t		xb_page_retries;
-	__uint32_t		xb_page_found;
-	__uint32_t		xb_get_read;
+	uint32_t		xb_get;
+	uint32_t		xb_create;
+	uint32_t		xb_get_locked;
+	uint32_t		xb_get_locked_waited;
+	uint32_t		xb_busy_locked;
+	uint32_t		xb_miss_locked;
+	uint32_t		xb_page_retries;
+	uint32_t		xb_page_found;
+	uint32_t		xb_get_read;
 /* Version 2 btree counters */
 #define XFSSTAT_END_ABTB_V2		(XFSSTAT_END_BUF + __XBTS_MAX)
-	__uint32_t		xs_abtb_2[__XBTS_MAX];
+	uint32_t		xs_abtb_2[__XBTS_MAX];
 #define XFSSTAT_END_ABTC_V2		(XFSSTAT_END_ABTB_V2 + __XBTS_MAX)
-	__uint32_t		xs_abtc_2[__XBTS_MAX];
+	uint32_t		xs_abtc_2[__XBTS_MAX];
 #define XFSSTAT_END_BMBT_V2		(XFSSTAT_END_ABTC_V2 + __XBTS_MAX)
-	__uint32_t		xs_bmbt_2[__XBTS_MAX];
+	uint32_t		xs_bmbt_2[__XBTS_MAX];
 #define XFSSTAT_END_IBT_V2		(XFSSTAT_END_BMBT_V2 + __XBTS_MAX)
-	__uint32_t		xs_ibt_2[__XBTS_MAX];
+	uint32_t		xs_ibt_2[__XBTS_MAX];
 #define XFSSTAT_END_FIBT_V2		(XFSSTAT_END_IBT_V2 + __XBTS_MAX)
-	__uint32_t		xs_fibt_2[__XBTS_MAX];
+	uint32_t		xs_fibt_2[__XBTS_MAX];
 #define XFSSTAT_END_RMAP_V2		(XFSSTAT_END_FIBT_V2 + __XBTS_MAX)
-	__uint32_t		xs_rmap_2[__XBTS_MAX];
+	uint32_t		xs_rmap_2[__XBTS_MAX];
 #define XFSSTAT_END_REFCOUNT		(XFSSTAT_END_RMAP_V2 + __XBTS_MAX)
-	__uint32_t		xs_refcbt_2[__XBTS_MAX];
+	uint32_t		xs_refcbt_2[__XBTS_MAX];
 #define XFSSTAT_END_XQMSTAT		(XFSSTAT_END_REFCOUNT + 6)
-	__uint32_t		xs_qm_dqreclaims;
-	__uint32_t		xs_qm_dqreclaim_misses;
-	__uint32_t		xs_qm_dquot_dups;
-	__uint32_t		xs_qm_dqcachemisses;
-	__uint32_t		xs_qm_dqcachehits;
-	__uint32_t		xs_qm_dqwants;
+	uint32_t		xs_qm_dqreclaims;
+	uint32_t		xs_qm_dqreclaim_misses;
+	uint32_t		xs_qm_dquot_dups;
+	uint32_t		xs_qm_dqcachemisses;
+	uint32_t		xs_qm_dqcachehits;
+	uint32_t		xs_qm_dqwants;
 #define XFSSTAT_END_QM			(XFSSTAT_END_XQMSTAT+2)
-	__uint32_t		xs_qm_dquot;
-	__uint32_t		xs_qm_dquot_unused;
+	uint32_t		xs_qm_dquot;
+	uint32_t		xs_qm_dquot_unused;
 /* Extra precision counters */
-	__uint64_t		xs_xstrat_bytes;
-	__uint64_t		xs_write_bytes;
-	__uint64_t		xs_read_bytes;
+	uint64_t		xs_xstrat_bytes;
+	uint64_t		xs_write_bytes;
+	uint64_t		xs_read_bytes;
 };
 
 struct xfsstats {
@@ -186,7 +186,7 @@ struct xfsstats {
  * simple wrapper for getting the array index of s struct member offset
  */
 #define XFS_STATS_CALC_INDEX(member)	\
-	(offsetof(struct __xfsstats, member) / (int)sizeof(__uint32_t))
+	(offsetof(struct __xfsstats, member) / (int)sizeof(uint32_t))
 
 
 int xfs_stats_format(struct xfsstats __percpu *stats, char *buf);
diff --git a/fs/xfs/xfs_super.c b/fs/xfs/xfs_super.c
index eecbaac08eba..38aaacdbb8b3 100644
--- a/fs/xfs/xfs_super.c
+++ b/fs/xfs/xfs_super.c
@@ -52,6 +52,7 @@
 #include "xfs_reflink.h"
 
 #include <linux/namei.h>
+#include <linux/dax.h>
 #include <linux/init.h>
 #include <linux/slab.h>
 #include <linux/mount.h>
@@ -195,7 +196,7 @@ xfs_parseargs(
 	int			dsunit = 0;
 	int			dswidth = 0;
 	int			iosize = 0;
-	__uint8_t		iosizelog = 0;
+	uint8_t			iosizelog = 0;
 
 	/*
 	 * set up the mount name first so all the errors will refer to the
@@ -555,7 +556,7 @@ xfs_showargs(
 
 	return 0;
 }
-static __uint64_t
+static uint64_t
 xfs_max_file_offset(
 	unsigned int		blockshift)
 {
@@ -586,7 +587,7 @@ xfs_max_file_offset(
 # endif
 #endif
 
-	return (((__uint64_t)pagefactor) << bitshift) - 1;
+	return (((uint64_t)pagefactor) << bitshift) - 1;
 }
 
 /*
@@ -621,7 +622,7 @@ xfs_set_inode_alloc(
 	 * the max inode percentage.  Used only for inode32.
 	 */
 	if (mp->m_maxicount) {
-		__uint64_t	icount;
+		uint64_t	icount;
 
 		icount = sbp->sb_dblocks * sbp->sb_imax_pct;
 		do_div(icount, 100);
@@ -877,8 +878,15 @@ xfs_init_mount_workqueues(
 	if (!mp->m_eofblocks_workqueue)
 		goto out_destroy_log;
 
+	mp->m_sync_workqueue = alloc_workqueue("xfs-sync/%s", WQ_FREEZABLE, 0,
+					       mp->m_fsname);
+	if (!mp->m_sync_workqueue)
+		goto out_destroy_eofb;
+
 	return 0;
 
+out_destroy_eofb:
+	destroy_workqueue(mp->m_eofblocks_workqueue);
 out_destroy_log:
 	destroy_workqueue(mp->m_log_workqueue);
 out_destroy_reclaim:
@@ -899,6 +907,7 @@ STATIC void
 xfs_destroy_mount_workqueues(
 	struct xfs_mount	*mp)
 {
+	destroy_workqueue(mp->m_sync_workqueue);
 	destroy_workqueue(mp->m_eofblocks_workqueue);
 	destroy_workqueue(mp->m_log_workqueue);
 	destroy_workqueue(mp->m_reclaim_workqueue);
@@ -953,7 +962,7 @@ xfs_fs_destroy_inode(
 	XFS_STATS_INC(ip->i_mount, vn_remove);
 
 	if (xfs_is_reflink_inode(ip)) {
-		error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF);
+		error = xfs_reflink_cancel_cow_range(ip, 0, NULLFILEOFF, true);
 		if (error && !XFS_FORCED_SHUTDOWN(ip->i_mount))
 			xfs_warn(ip->i_mount,
 "Error %d while evicting CoW blocks for inode %llu.",
@@ -1079,12 +1088,12 @@ xfs_fs_statfs(
 	struct xfs_mount	*mp = XFS_M(dentry->d_sb);
 	xfs_sb_t		*sbp = &mp->m_sb;
 	struct xfs_inode	*ip = XFS_I(d_inode(dentry));
-	__uint64_t		fakeinos, id;
-	__uint64_t		icount;
-	__uint64_t		ifree;
-	__uint64_t		fdblocks;
+	uint64_t		fakeinos, id;
+	uint64_t		icount;
+	uint64_t		ifree;
+	uint64_t		fdblocks;
 	xfs_extlen_t		lsize;
-	__int64_t		ffree;
+	int64_t			ffree;
 
 	statp->f_type = XFS_SB_MAGIC;
 	statp->f_namelen = MAXNAMELEN - 1;
@@ -1107,7 +1116,7 @@ xfs_fs_statfs(
 	statp->f_bavail = statp->f_bfree;
 
 	fakeinos = statp->f_bfree << sbp->sb_inopblog;
-	statp->f_files = MIN(icount + fakeinos, (__uint64_t)XFS_MAXINUMBER);
+	statp->f_files = MIN(icount + fakeinos, (uint64_t)XFS_MAXINUMBER);
 	if (mp->m_maxicount)
 		statp->f_files = min_t(typeof(statp->f_files),
 					statp->f_files,
@@ -1120,7 +1129,7 @@ xfs_fs_statfs(
 
 	/* make sure statp->f_ffree does not underflow */
 	ffree = statp->f_files - (icount - ifree);
-	statp->f_ffree = max_t(__int64_t, ffree, 0);
+	statp->f_ffree = max_t(int64_t, ffree, 0);
 
 
 	if ((ip->i_d.di_flags & XFS_DIFLAG_PROJINHERIT) &&
@@ -1133,7 +1142,7 @@ xfs_fs_statfs(
 STATIC void
 xfs_save_resvblks(struct xfs_mount *mp)
 {
-	__uint64_t resblks = 0;
+	uint64_t resblks = 0;
 
 	mp->m_resblks_save = mp->m_resblks;
 	xfs_reserve_blocks(mp, &resblks, NULL);
@@ -1142,7 +1151,7 @@ xfs_save_resvblks(struct xfs_mount *mp)
 STATIC void
 xfs_restore_resvblks(struct xfs_mount *mp)
 {
-	__uint64_t resblks;
+	uint64_t resblks;
 
 	if (mp->m_resblks_save) {
 		resblks = mp->m_resblks_save;
@@ -1757,7 +1766,8 @@ STATIC int __init
 xfs_init_zones(void)
 {
 	xfs_ioend_bioset = bioset_create(4 * MAX_BUF_PER_PAGE,
-			offsetof(struct xfs_ioend, io_inline_bio));
+			offsetof(struct xfs_ioend, io_inline_bio),
+			BIOSET_NEED_BVECS);
 	if (!xfs_ioend_bioset)
 		goto out;
 
@@ -1956,12 +1966,20 @@ xfs_init_workqueues(void)
 	if (!xfs_alloc_wq)
 		return -ENOMEM;
 
+	xfs_discard_wq = alloc_workqueue("xfsdiscard", WQ_UNBOUND, 0);
+	if (!xfs_discard_wq)
+		goto out_free_alloc_wq;
+
 	return 0;
+out_free_alloc_wq:
+	destroy_workqueue(xfs_alloc_wq);
+	return -ENOMEM;
 }
 
 STATIC void
 xfs_destroy_workqueues(void)
 {
+	destroy_workqueue(xfs_discard_wq);
 	destroy_workqueue(xfs_alloc_wq);
 }
 
diff --git a/fs/xfs/xfs_super.h b/fs/xfs/xfs_super.h
index b6418abd85ad..5f2f32408011 100644
--- a/fs/xfs/xfs_super.h
+++ b/fs/xfs/xfs_super.h
@@ -73,6 +73,8 @@ extern const struct quotactl_ops xfs_quotactl_operations;
 
 extern void xfs_reinit_percpu_counters(struct xfs_mount *mp);
 
+extern struct workqueue_struct *xfs_discard_wq;
+
 #define XFS_M(sb)		((struct xfs_mount *)((sb)->s_fs_info))
 
 #endif	/* __XFS_SUPER_H__ */
diff --git a/fs/xfs/xfs_symlink.c b/fs/xfs/xfs_symlink.c
index f2cb45ed1d54..23a50d7aa46a 100644
--- a/fs/xfs/xfs_symlink.c
+++ b/fs/xfs/xfs_symlink.c
@@ -43,8 +43,8 @@
 #include "xfs_log.h"
 
 /* ----- Kernel only functions below ----- */
-STATIC int
-xfs_readlink_bmap(
+int
+xfs_readlink_bmap_ilocked(
 	struct xfs_inode	*ip,
 	char			*link)
 {
@@ -61,6 +61,8 @@ xfs_readlink_bmap(
 	int			fsblocks = 0;
 	int			offset;
 
+	ASSERT(xfs_isilocked(ip, XFS_ILOCK_SHARED | XFS_ILOCK_EXCL));
+
 	fsblocks = xfs_symlink_blocks(mp, pathlen);
 	error = xfs_bmapi_read(ip, 0, fsblocks, mval, &nmaps, 0);
 	if (error)
@@ -143,7 +145,7 @@ xfs_readlink(
 	if (!pathlen)
 		goto out;
 
-	if (pathlen < 0 || pathlen > MAXPATHLEN) {
+	if (pathlen < 0 || pathlen > XFS_SYMLINK_MAXLEN) {
 		xfs_alert(mp, "%s: inode (%llu) bad symlink length (%lld)",
 			 __func__, (unsigned long long) ip->i_ino,
 			 (long long) pathlen);
@@ -153,7 +155,7 @@ xfs_readlink(
 	}
 
 
-	error = xfs_readlink_bmap(ip, link);
+	error = xfs_readlink_bmap_ilocked(ip, link);
 
  out:
 	xfs_iunlock(ip, XFS_ILOCK_SHARED);
@@ -202,7 +204,7 @@ xfs_symlink(
 	 * Check component lengths of the target path name.
 	 */
 	pathlen = strlen(target_path);
-	if (pathlen >= MAXPATHLEN)      /* total string too long */
+	if (pathlen >= XFS_SYMLINK_MAXLEN)      /* total string too long */
 		return -ENAMETOOLONG;
 
 	udqp = gdqp = NULL;
@@ -559,7 +561,7 @@ xfs_inactive_symlink(
 		return 0;
 	}
 
-	if (pathlen < 0 || pathlen > MAXPATHLEN) {
+	if (pathlen < 0 || pathlen > XFS_SYMLINK_MAXLEN) {
 		xfs_alert(mp, "%s: inode (0x%llx) bad symlink length (%d)",
 			 __func__, (unsigned long long)ip->i_ino, pathlen);
 		xfs_iunlock(ip, XFS_ILOCK_EXCL);
diff --git a/fs/xfs/xfs_symlink.h b/fs/xfs/xfs_symlink.h
index e75245d09116..aeaee8923617 100644
--- a/fs/xfs/xfs_symlink.h
+++ b/fs/xfs/xfs_symlink.h
@@ -21,6 +21,7 @@
 
 int xfs_symlink(struct xfs_inode *dp, struct xfs_name *link_name,
 		const char *target_path, umode_t mode, struct xfs_inode **ipp);
+int xfs_readlink_bmap_ilocked(struct xfs_inode *ip, char *link);
 int xfs_readlink(struct xfs_inode *ip, char *link);
 int xfs_inactive_symlink(struct xfs_inode *ip);
 
diff --git a/fs/xfs/xfs_sysctl.h b/fs/xfs/xfs_sysctl.h
index 984a3499cfe3..82afee005140 100644
--- a/fs/xfs/xfs_sysctl.h
+++ b/fs/xfs/xfs_sysctl.h
@@ -95,6 +95,7 @@ extern xfs_param_t	xfs_params;
 
 struct xfs_globals {
 	int	log_recovery_delay;	/* log recovery delay (secs) */
+	bool	bug_on_assert;		/* BUG() the kernel on assert failure */
 };
 extern struct xfs_globals	xfs_globals;
 
diff --git a/fs/xfs/xfs_sysfs.c b/fs/xfs/xfs_sysfs.c
index de6195e38910..8b2ccc234f36 100644
--- a/fs/xfs/xfs_sysfs.c
+++ b/fs/xfs/xfs_sysfs.c
@@ -90,15 +90,25 @@ to_mp(struct kobject *kobject)
 	return container_of(kobj, struct xfs_mount, m_kobj);
 }
 
+static struct attribute *xfs_mp_attrs[] = {
+	NULL,
+};
+
+struct kobj_type xfs_mp_ktype = {
+	.release = xfs_sysfs_release,
+	.sysfs_ops = &xfs_sysfs_ops,
+	.default_attrs = xfs_mp_attrs,
+};
+
 #ifdef DEBUG
+/* debug */
 
 STATIC ssize_t
-fail_writes_store(
+bug_on_assert_store(
 	struct kobject		*kobject,
 	const char		*buf,
 	size_t			count)
 {
-	struct xfs_mount	*mp = to_mp(kobject);
 	int			ret;
 	int			val;
 
@@ -107,9 +117,9 @@ fail_writes_store(
 		return ret;
 
 	if (val == 1)
-		mp->m_fail_writes = true;
+		xfs_globals.bug_on_assert = true;
 	else if (val == 0)
-		mp->m_fail_writes = false;
+		xfs_globals.bug_on_assert = false;
 	else
 		return -EINVAL;
 
@@ -117,33 +127,13 @@ fail_writes_store(
 }
 
 STATIC ssize_t
-fail_writes_show(
+bug_on_assert_show(
 	struct kobject		*kobject,
 	char			*buf)
 {
-	struct xfs_mount	*mp = to_mp(kobject);
-
-	return snprintf(buf, PAGE_SIZE, "%d\n", mp->m_fail_writes ? 1 : 0);
+	return snprintf(buf, PAGE_SIZE, "%d\n", xfs_globals.bug_on_assert ? 1 : 0);
 }
-XFS_SYSFS_ATTR_RW(fail_writes);
-
-#endif /* DEBUG */
-
-static struct attribute *xfs_mp_attrs[] = {
-#ifdef DEBUG
-	ATTR_LIST(fail_writes),
-#endif
-	NULL,
-};
-
-struct kobj_type xfs_mp_ktype = {
-	.release = xfs_sysfs_release,
-	.sysfs_ops = &xfs_sysfs_ops,
-	.default_attrs = xfs_mp_attrs,
-};
-
-#ifdef DEBUG
-/* debug */
+XFS_SYSFS_ATTR_RW(bug_on_assert);
 
 STATIC ssize_t
 log_recovery_delay_store(
@@ -176,6 +166,7 @@ log_recovery_delay_show(
 XFS_SYSFS_ATTR_RW(log_recovery_delay);
 
 static struct attribute *xfs_dbg_attrs[] = {
+	ATTR_LIST(bug_on_assert),
 	ATTR_LIST(log_recovery_delay),
 	NULL,
 };
@@ -314,47 +305,11 @@ write_grant_head_show(
 }
 XFS_SYSFS_ATTR_RO(write_grant_head);
 
-#ifdef DEBUG
-STATIC ssize_t
-log_badcrc_factor_store(
-	struct kobject	*kobject,
-	const char	*buf,
-	size_t		count)
-{
-	struct xlog	*log = to_xlog(kobject);
-	int		ret;
-	uint32_t	val;
-
-	ret = kstrtouint(buf, 0, &val);
-	if (ret)
-		return ret;
-
-	log->l_badcrc_factor = val;
-
-	return count;
-}
-
-STATIC ssize_t
-log_badcrc_factor_show(
-	struct kobject	*kobject,
-	char		*buf)
-{
-	struct xlog	*log = to_xlog(kobject);
-
-	return snprintf(buf, PAGE_SIZE, "%d\n", log->l_badcrc_factor);
-}
-
-XFS_SYSFS_ATTR_RW(log_badcrc_factor);
-#endif	/* DEBUG */
-
 static struct attribute *xfs_log_attrs[] = {
 	ATTR_LIST(log_head_lsn),
 	ATTR_LIST(log_tail_lsn),
 	ATTR_LIST(reserve_grant_head),
 	ATTR_LIST(write_grant_head),
-#ifdef DEBUG
-	ATTR_LIST(log_badcrc_factor),
-#endif
 	NULL,
 };
 
diff --git a/fs/xfs/xfs_trace.c b/fs/xfs/xfs_trace.c
index 7f17ae6d709a..5d95fe348294 100644
--- a/fs/xfs/xfs_trace.c
+++ b/fs/xfs/xfs_trace.c
@@ -47,6 +47,7 @@
 #include "xfs_inode_item.h"
 #include "xfs_bmap_btree.h"
 #include "xfs_filestream.h"
+#include "xfs_fsmap.h"
 
 /*
  * We include this last to have the helpers above available for the trace
diff --git a/fs/xfs/xfs_trace.h b/fs/xfs/xfs_trace.h
index 69c5bcd9a51b..bcc3cdf8e1c5 100644
--- a/fs/xfs/xfs_trace.h
+++ b/fs/xfs/xfs_trace.h
@@ -40,6 +40,8 @@ struct xfs_inode_log_format;
 struct xfs_bmbt_irec;
 struct xfs_btree_cur;
 struct xfs_refcount_irec;
+struct xfs_fsmap;
+struct xfs_rmap_irec;
 
 DECLARE_EVENT_CLASS(xfs_attr_list_class,
 	TP_PROTO(struct xfs_attr_list_context *ctx),
@@ -249,7 +251,7 @@ TRACE_EVENT(xfs_iext_insert,
 		  __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS),
 		  (long)__entry->idx,
 		  __entry->startoff,
-		  (__int64_t)__entry->startblock,
+		  (int64_t)__entry->startblock,
 		  __entry->blockcount,
 		  __entry->state,
 		  (char *)__entry->caller_ip)
@@ -293,7 +295,7 @@ DECLARE_EVENT_CLASS(xfs_bmap_class,
 		  __print_flags(__entry->bmap_state, "|", XFS_BMAP_EXT_FLAGS),
 		  (long)__entry->idx,
 		  __entry->startoff,
-		  (__int64_t)__entry->startblock,
+		  (int64_t)__entry->startblock,
 		  __entry->blockcount,
 		  __entry->state,
 		  (char *)__entry->caller_ip)
@@ -365,6 +367,7 @@ DEFINE_BUF_EVENT(xfs_buf_iowait_done);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queue);
 DEFINE_BUF_EVENT(xfs_buf_delwri_queued);
 DEFINE_BUF_EVENT(xfs_buf_delwri_split);
+DEFINE_BUF_EVENT(xfs_buf_delwri_pushbuf);
 DEFINE_BUF_EVENT(xfs_buf_get_uncached);
 DEFINE_BUF_EVENT(xfs_buf_item_relse);
 DEFINE_BUF_EVENT(xfs_buf_item_iodone_async);
@@ -687,7 +690,7 @@ DEFINE_INODE_EVENT(xfs_inode_clear_cowblocks_tag);
 DEFINE_INODE_EVENT(xfs_inode_free_cowblocks_invalid);
 
 DEFINE_INODE_EVENT(xfs_filemap_fault);
-DEFINE_INODE_EVENT(xfs_filemap_pmd_fault);
+DEFINE_INODE_EVENT(xfs_filemap_huge_fault);
 DEFINE_INODE_EVENT(xfs_filemap_page_mkwrite);
 DEFINE_INODE_EVENT(xfs_filemap_pfn_mkwrite);
 
@@ -1278,7 +1281,7 @@ DECLARE_EVENT_CLASS(xfs_imap_class,
 		  __entry->count,
 		  __print_symbolic(__entry->type, XFS_IO_TYPES),
 		  __entry->startoff,
-		  (__int64_t)__entry->startblock,
+		  (int64_t)__entry->startblock,
 		  __entry->blockcount)
 )
 
@@ -1488,25 +1491,6 @@ TRACE_EVENT(xfs_extent_busy_trim,
 		  __entry->tlen)
 );
 
-TRACE_EVENT(xfs_trans_commit_lsn,
-	TP_PROTO(struct xfs_trans *trans),
-	TP_ARGS(trans),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(struct xfs_trans *, tp)
-		__field(xfs_lsn_t, lsn)
-	),
-	TP_fast_assign(
-		__entry->dev = trans->t_mountp->m_super->s_dev;
-		__entry->tp = trans;
-		__entry->lsn = trans->t_commit_lsn;
-	),
-	TP_printk("dev %d:%d trans 0x%p commit_lsn 0x%llx",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->tp,
-		  __entry->lsn)
-);
-
 TRACE_EVENT(xfs_agf,
 	TP_PROTO(struct xfs_mount *mp, struct xfs_agf *agf, int flags,
 		 unsigned long caller_ip),
@@ -2055,7 +2039,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_buf_item_class,
 	TP_ARGS(log, buf_f),
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
-		__field(__int64_t, blkno)
+		__field(int64_t, blkno)
 		__field(unsigned short, len)
 		__field(unsigned short, flags)
 		__field(unsigned short, size)
@@ -2104,7 +2088,7 @@ DECLARE_EVENT_CLASS(xfs_log_recover_ino_item_class,
 		__field(int, fields)
 		__field(unsigned short, asize)
 		__field(unsigned short, dsize)
-		__field(__int64_t, blkno)
+		__field(int64_t, blkno)
 		__field(int, len)
 		__field(int, boffset)
 	),
@@ -2190,7 +2174,7 @@ DECLARE_EVENT_CLASS(xfs_discard_class,
 		__entry->agbno = agbno;
 		__entry->len = len;
 	),
-	TP_printk("dev %d:%d agno %u agbno %u len %u\n",
+	TP_printk("dev %d:%d agno %u agbno %u len %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
 		  __entry->agbno,
@@ -2245,7 +2229,6 @@ DEFINE_BTREE_CUR_EVENT(xfs_btree_overlapped_query_range);
 
 /* deferred ops */
 struct xfs_defer_pending;
-struct xfs_defer_intake;
 struct xfs_defer_ops;
 
 DECLARE_EVENT_CLASS(xfs_defer_class,
@@ -2254,8 +2237,8 @@ DECLARE_EVENT_CLASS(xfs_defer_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(void *, dop)
-		__field(bool, committed)
-		__field(bool, low)
+		__field(char, committed)
+		__field(char, low)
 	),
 	TP_fast_assign(
 		__entry->dev = mp ? mp->m_super->s_dev : 0;
@@ -2263,7 +2246,7 @@ DECLARE_EVENT_CLASS(xfs_defer_class,
 		__entry->committed = dop->dop_committed;
 		__entry->low = dop->dop_low;
 	),
-	TP_printk("dev %d:%d ops %p committed %d low %d\n",
+	TP_printk("dev %d:%d ops %p committed %d low %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->dop,
 		  __entry->committed,
@@ -2280,8 +2263,8 @@ DECLARE_EVENT_CLASS(xfs_defer_error_class,
 	TP_STRUCT__entry(
 		__field(dev_t, dev)
 		__field(void *, dop)
-		__field(bool, committed)
-		__field(bool, low)
+		__field(char, committed)
+		__field(char, low)
 		__field(int, error)
 	),
 	TP_fast_assign(
@@ -2291,7 +2274,7 @@ DECLARE_EVENT_CLASS(xfs_defer_error_class,
 		__entry->low = dop->dop_low;
 		__entry->error = error;
 	),
-	TP_printk("dev %d:%d ops %p committed %d low %d err %d\n",
+	TP_printk("dev %d:%d ops %p committed %d low %d err %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->dop,
 		  __entry->committed,
@@ -2310,7 +2293,7 @@ DECLARE_EVENT_CLASS(xfs_defer_pending_class,
 		__field(dev_t, dev)
 		__field(int, type)
 		__field(void *, intent)
-		__field(bool, committed)
+		__field(char, committed)
 		__field(int, nr)
 	),
 	TP_fast_assign(
@@ -2320,7 +2303,7 @@ DECLARE_EVENT_CLASS(xfs_defer_pending_class,
 		__entry->committed = dfp->dfp_done != NULL;
 		__entry->nr = dfp->dfp_count;
 	),
-	TP_printk("dev %d:%d optype %d intent %p committed %d nr %d\n",
+	TP_printk("dev %d:%d optype %d intent %p committed %d nr %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->type,
 		  __entry->intent,
@@ -2615,7 +2598,8 @@ DECLARE_EVENT_CLASS(xfs_ag_resv_class,
 		__entry->asked = r ? r->ar_asked : 0;
 		__entry->len = len;
 	),
-	TP_printk("dev %d:%d agno %u resv %d freeblks %u flcount %u resv %u ask %u len %u\n",
+	TP_printk("dev %d:%d agno %u resv %d freeblks %u flcount %u "
+		  "resv %u ask %u len %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
 		  __entry->resv,
@@ -2668,7 +2652,7 @@ DECLARE_EVENT_CLASS(xfs_ag_btree_lookup_class,
 		__entry->agbno = agbno;
 		__entry->dir = dir;
 	),
-	TP_printk("dev %d:%d agno %u agbno %u cmp %s(%d)\n",
+	TP_printk("dev %d:%d agno %u agbno %u cmp %s(%d)",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
 		  __entry->agbno,
@@ -2701,7 +2685,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_class,
 		__entry->blockcount = irec->rc_blockcount;
 		__entry->refcount = irec->rc_refcount;
 	),
-	TP_printk("dev %d:%d agno %u agbno %u len %u refcount %u\n",
+	TP_printk("dev %d:%d agno %u agbno %u len %u refcount %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
 		  __entry->startblock,
@@ -2736,7 +2720,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_extent_at_class,
 		__entry->refcount = irec->rc_refcount;
 		__entry->agbno = agbno;
 	),
-	TP_printk("dev %d:%d agno %u agbno %u len %u refcount %u @ agbno %u\n",
+	TP_printk("dev %d:%d agno %u agbno %u len %u refcount %u @ agbno %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
 		  __entry->startblock,
@@ -2777,7 +2761,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_class,
 		__entry->i2_refcount = i2->rc_refcount;
 	),
 	TP_printk("dev %d:%d agno %u agbno %u len %u refcount %u -- "
-		  "agbno %u len %u refcount %u\n",
+		  "agbno %u len %u refcount %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
 		  __entry->i1_startblock,
@@ -2823,7 +2807,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_double_extent_at_class,
 		__entry->agbno = agbno;
 	),
 	TP_printk("dev %d:%d agno %u agbno %u len %u refcount %u -- "
-		  "agbno %u len %u refcount %u @ agbno %u\n",
+		  "agbno %u len %u refcount %u @ agbno %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
 		  __entry->i1_startblock,
@@ -2876,7 +2860,7 @@ DECLARE_EVENT_CLASS(xfs_refcount_triple_extent_class,
 	),
 	TP_printk("dev %d:%d agno %u agbno %u len %u refcount %u -- "
 		  "agbno %u len %u refcount %u -- "
-		  "agbno %u len %u refcount %u\n",
+		  "agbno %u len %u refcount %u",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->agno,
 		  __entry->i1_startblock,
@@ -3002,31 +2986,6 @@ DEFINE_EVENT(xfs_inode_error_class, name, \
 		 unsigned long caller_ip), \
 	TP_ARGS(ip, error, caller_ip))
 
-/* reflink allocator */
-TRACE_EVENT(xfs_bmap_remap_alloc,
-	TP_PROTO(struct xfs_inode *ip, xfs_fsblock_t fsbno,
-		 xfs_extlen_t len),
-	TP_ARGS(ip, fsbno, len),
-	TP_STRUCT__entry(
-		__field(dev_t, dev)
-		__field(xfs_ino_t, ino)
-		__field(xfs_fsblock_t, fsbno)
-		__field(xfs_extlen_t, len)
-	),
-	TP_fast_assign(
-		__entry->dev = VFS_I(ip)->i_sb->s_dev;
-		__entry->ino = ip->i_ino;
-		__entry->fsbno = fsbno;
-		__entry->len = len;
-	),
-	TP_printk("dev %d:%d ino 0x%llx fsbno 0x%llx len %x",
-		  MAJOR(__entry->dev), MINOR(__entry->dev),
-		  __entry->ino,
-		  __entry->fsbno,
-		  __entry->len)
-);
-DEFINE_INODE_ERROR_EVENT(xfs_bmap_remap_alloc_error);
-
 /* reflink tracepoint classes */
 
 /* two-file io tracepoint class */
@@ -3089,6 +3048,7 @@ DECLARE_EVENT_CLASS(xfs_inode_irec_class,
 		__field(xfs_fileoff_t, lblk)
 		__field(xfs_extlen_t, len)
 		__field(xfs_fsblock_t, pblk)
+		__field(int, state)
 	),
 	TP_fast_assign(
 		__entry->dev = VFS_I(ip)->i_sb->s_dev;
@@ -3096,13 +3056,15 @@ DECLARE_EVENT_CLASS(xfs_inode_irec_class,
 		__entry->lblk = irec->br_startoff;
 		__entry->len = irec->br_blockcount;
 		__entry->pblk = irec->br_startblock;
+		__entry->state = irec->br_state;
 	),
-	TP_printk("dev %d:%d ino 0x%llx lblk 0x%llx len 0x%x pblk %llu",
+	TP_printk("dev %d:%d ino 0x%llx lblk 0x%llx len 0x%x pblk %llu st %d",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->ino,
 		  __entry->lblk,
 		  __entry->len,
-		  __entry->pblk)
+		  __entry->pblk,
+		  __entry->state)
 );
 #define DEFINE_INODE_IREC_EVENT(name) \
 DEFINE_EVENT(xfs_inode_irec_class, name, \
@@ -3225,7 +3187,7 @@ TRACE_EVENT(xfs_ioctl_clone,
 	),
 	TP_printk("dev %d:%d "
 		  "ino 0x%lx isize 0x%llx -> "
-		  "ino 0x%lx isize 0x%llx\n",
+		  "ino 0x%lx isize 0x%llx",
 		  MAJOR(__entry->dev), MINOR(__entry->dev),
 		  __entry->src_ino,
 		  __entry->src_isize,
@@ -3242,11 +3204,11 @@ DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_around_shared);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_alloc);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_found);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_enospc);
+DEFINE_INODE_IREC_EVENT(xfs_reflink_convert_cow);
 
 DEFINE_RW_EVENT(xfs_reflink_reserve_cow);
-DEFINE_RW_EVENT(xfs_reflink_allocate_cow_range);
 
-DEFINE_INODE_IREC_EVENT(xfs_reflink_bounce_dio_write);
+DEFINE_SIMPLE_IO_EVENT(xfs_reflink_bounce_dio_write);
 DEFINE_IOMAP_EVENT(xfs_reflink_find_cow_mapping);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_trim_irec);
 
@@ -3254,7 +3216,6 @@ DEFINE_SIMPLE_IO_EVENT(xfs_reflink_cancel_cow_range);
 DEFINE_SIMPLE_IO_EVENT(xfs_reflink_end_cow);
 DEFINE_INODE_IREC_EVENT(xfs_reflink_cow_remap);
 
-DEFINE_INODE_ERROR_EVENT(xfs_reflink_allocate_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_cancel_cow_range_error);
 DEFINE_INODE_ERROR_EVENT(xfs_reflink_end_cow_error);
 
@@ -3266,6 +3227,88 @@ DEFINE_INODE_IREC_EVENT(xfs_swap_extent_rmap_remap);
 DEFINE_INODE_IREC_EVENT(xfs_swap_extent_rmap_remap_piece);
 DEFINE_INODE_ERROR_EVENT(xfs_swap_extent_rmap_error);
 
+/* fsmap traces */
+DECLARE_EVENT_CLASS(xfs_fsmap_class,
+	TP_PROTO(struct xfs_mount *mp, u32 keydev, xfs_agnumber_t agno,
+		 struct xfs_rmap_irec *rmap),
+	TP_ARGS(mp, keydev, agno, rmap),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, keydev)
+		__field(xfs_agnumber_t, agno)
+		__field(xfs_fsblock_t, bno)
+		__field(xfs_filblks_t, len)
+		__field(uint64_t, owner)
+		__field(uint64_t, offset)
+		__field(unsigned int, flags)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->keydev = new_decode_dev(keydev);
+		__entry->agno = agno;
+		__entry->bno = rmap->rm_startblock;
+		__entry->len = rmap->rm_blockcount;
+		__entry->owner = rmap->rm_owner;
+		__entry->offset = rmap->rm_offset;
+		__entry->flags = rmap->rm_flags;
+	),
+	TP_printk("dev %d:%d keydev %d:%d agno %u bno %llu len %llu owner %lld offset %llu flags 0x%x",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->keydev), MINOR(__entry->keydev),
+		  __entry->agno,
+		  __entry->bno,
+		  __entry->len,
+		  __entry->owner,
+		  __entry->offset,
+		  __entry->flags)
+)
+#define DEFINE_FSMAP_EVENT(name) \
+DEFINE_EVENT(xfs_fsmap_class, name, \
+	TP_PROTO(struct xfs_mount *mp, u32 keydev, xfs_agnumber_t agno, \
+		 struct xfs_rmap_irec *rmap), \
+	TP_ARGS(mp, keydev, agno, rmap))
+DEFINE_FSMAP_EVENT(xfs_fsmap_low_key);
+DEFINE_FSMAP_EVENT(xfs_fsmap_high_key);
+DEFINE_FSMAP_EVENT(xfs_fsmap_mapping);
+
+DECLARE_EVENT_CLASS(xfs_getfsmap_class,
+	TP_PROTO(struct xfs_mount *mp, struct xfs_fsmap *fsmap),
+	TP_ARGS(mp, fsmap),
+	TP_STRUCT__entry(
+		__field(dev_t, dev)
+		__field(dev_t, keydev)
+		__field(xfs_daddr_t, block)
+		__field(xfs_daddr_t, len)
+		__field(uint64_t, owner)
+		__field(uint64_t, offset)
+		__field(uint64_t, flags)
+	),
+	TP_fast_assign(
+		__entry->dev = mp->m_super->s_dev;
+		__entry->keydev = new_decode_dev(fsmap->fmr_device);
+		__entry->block = fsmap->fmr_physical;
+		__entry->len = fsmap->fmr_length;
+		__entry->owner = fsmap->fmr_owner;
+		__entry->offset = fsmap->fmr_offset;
+		__entry->flags = fsmap->fmr_flags;
+	),
+	TP_printk("dev %d:%d keydev %d:%d block %llu len %llu owner %lld offset %llu flags 0x%llx",
+		  MAJOR(__entry->dev), MINOR(__entry->dev),
+		  MAJOR(__entry->keydev), MINOR(__entry->keydev),
+		  __entry->block,
+		  __entry->len,
+		  __entry->owner,
+		  __entry->offset,
+		  __entry->flags)
+)
+#define DEFINE_GETFSMAP_EVENT(name) \
+DEFINE_EVENT(xfs_getfsmap_class, name, \
+	TP_PROTO(struct xfs_mount *mp, struct xfs_fsmap *fsmap), \
+	TP_ARGS(mp, fsmap))
+DEFINE_GETFSMAP_EVENT(xfs_getfsmap_low_key);
+DEFINE_GETFSMAP_EVENT(xfs_getfsmap_high_key);
+DEFINE_GETFSMAP_EVENT(xfs_getfsmap_mapping);
+
 #endif /* _TRACE_XFS_H */
 
 #undef TRACE_INCLUDE_PATH
diff --git a/fs/xfs/xfs_trans.c b/fs/xfs/xfs_trans.c
index 70f42ea86dfb..2011620008de 100644
--- a/fs/xfs/xfs_trans.c
+++ b/fs/xfs/xfs_trans.c
@@ -134,7 +134,7 @@ xfs_trans_reserve(
 	bool		rsvd = (tp->t_flags & XFS_TRANS_RESERVE) != 0;
 
 	/* Mark this thread as being in a transaction */
-	current_set_flags_nested(&tp->t_pflags, PF_FSTRANS);
+	current_set_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 
 	/*
 	 * Attempt to reserve the needed disk blocks by decrementing
@@ -144,7 +144,7 @@ xfs_trans_reserve(
 	if (blocks > 0) {
 		error = xfs_mod_fdblocks(tp->t_mountp, -((int64_t)blocks), rsvd);
 		if (error != 0) {
-			current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+			current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 			return -ENOSPC;
 		}
 		tp->t_blk_res += blocks;
@@ -221,7 +221,7 @@ undo_blocks:
 		tp->t_blk_res = 0;
 	}
 
-	current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 
 	return error;
 }
@@ -263,6 +263,28 @@ xfs_trans_alloc(
 }
 
 /*
+ * Create an empty transaction with no reservation.  This is a defensive
+ * mechanism for routines that query metadata without actually modifying
+ * them -- if the metadata being queried is somehow cross-linked (think a
+ * btree block pointer that points higher in the tree), we risk deadlock.
+ * However, blocks grabbed as part of a transaction can be re-grabbed.
+ * The verifiers will notice the corrupt block and the operation will fail
+ * back to userspace without deadlocking.
+ *
+ * Note the zero-length reservation; this transaction MUST be cancelled
+ * without any dirty data.
+ */
+int
+xfs_trans_alloc_empty(
+	struct xfs_mount		*mp,
+	struct xfs_trans		**tpp)
+{
+	struct xfs_trans_res		resv = {0};
+
+	return xfs_trans_alloc(mp, &resv, 0, 0, XFS_TRANS_NO_WRITECOUNT, tpp);
+}
+
+/*
  * Record the indicated change to the given field for application
  * to the file system's superblock when the transaction commits.
  * For now, just store the change in the transaction structure.
@@ -914,7 +936,7 @@ __xfs_trans_commit(
 
 	xfs_log_commit_cil(mp, tp, &commit_lsn, regrant);
 
-	current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	xfs_trans_free(tp);
 
 	/*
@@ -944,7 +966,7 @@ out_unreserve:
 		if (commit_lsn == -1 && !error)
 			error = -EIO;
 	}
-	current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 	xfs_trans_free_items(tp, NULLCOMMITLSN, !!error);
 	xfs_trans_free(tp);
 
@@ -998,7 +1020,7 @@ xfs_trans_cancel(
 		xfs_log_done(mp, tp->t_ticket, NULL, false);
 
 	/* mark this thread as no longer being in a transaction */
-	current_restore_flags_nested(&tp->t_pflags, PF_FSTRANS);
+	current_restore_flags_nested(&tp->t_pflags, PF_MEMALLOC_NOFS);
 
 	xfs_trans_free_items(tp, NULLCOMMITLSN, dirty);
 	xfs_trans_free(tp);
@@ -1012,17 +1034,14 @@ xfs_trans_cancel(
  * chunk we've been working on and get a new transaction to continue.
  */
 int
-__xfs_trans_roll(
+xfs_trans_roll(
 	struct xfs_trans	**tpp,
-	struct xfs_inode	*dp,
-	int			*committed)
+	struct xfs_inode	*dp)
 {
 	struct xfs_trans	*trans;
 	struct xfs_trans_res	tres;
 	int			error;
 
-	*committed = 0;
-
 	/*
 	 * Ensure that the inode is always logged.
 	 */
@@ -1048,7 +1067,6 @@ __xfs_trans_roll(
 	if (error)
 		return error;
 
-	*committed = 1;
 	trans = *tpp;
 
 	/*
@@ -1071,12 +1089,3 @@ __xfs_trans_roll(
 		xfs_trans_ijoin(trans, dp, 0);
 	return 0;
 }
-
-int
-xfs_trans_roll(
-	struct xfs_trans	**tpp,
-	struct xfs_inode	*dp)
-{
-	int			committed;
-	return __xfs_trans_roll(tpp, dp, &committed);
-}
diff --git a/fs/xfs/xfs_trans.h b/fs/xfs/xfs_trans.h
index 61b7fbdd3ebd..6bdad6f58934 100644
--- a/fs/xfs/xfs_trans.h
+++ b/fs/xfs/xfs_trans.h
@@ -32,7 +32,6 @@ struct xfs_mount;
 struct xfs_trans;
 struct xfs_trans_res;
 struct xfs_dquot_acct;
-struct xfs_busy_extent;
 struct xfs_rud_log_item;
 struct xfs_rui_log_item;
 struct xfs_btree_cur;
@@ -106,10 +105,6 @@ typedef struct xfs_trans {
 	unsigned int		t_rtx_res;	/* # of rt extents resvd */
 	unsigned int		t_rtx_res_used;	/* # of resvd rt extents used */
 	struct xlog_ticket	*t_ticket;	/* log mgr ticket */
-	xfs_lsn_t		t_lsn;		/* log seq num of start of
-						 * transaction. */
-	xfs_lsn_t		t_commit_lsn;	/* log seq num of end of
-						 * transaction. */
 	struct xfs_mount	*t_mountp;	/* ptr to fs mount struct */
 	struct xfs_dquot_acct   *t_dqinfo;	/* acctg info for dquots */
 	unsigned int		t_flags;	/* misc flags */
@@ -159,6 +154,8 @@ typedef struct xfs_trans {
 int		xfs_trans_alloc(struct xfs_mount *mp, struct xfs_trans_res *resp,
 			uint blocks, uint rtextents, uint flags,
 			struct xfs_trans **tpp);
+int		xfs_trans_alloc_empty(struct xfs_mount *mp,
+			struct xfs_trans **tpp);
 void		xfs_trans_mod_sb(xfs_trans_t *, uint, int64_t);
 
 struct xfs_buf	*xfs_trans_get_buf_map(struct xfs_trans *tp,
@@ -227,7 +224,6 @@ int		xfs_trans_free_extent(struct xfs_trans *,
 				      struct xfs_efd_log_item *, xfs_fsblock_t,
 				      xfs_extlen_t, struct xfs_owner_info *);
 int		xfs_trans_commit(struct xfs_trans *);
-int		__xfs_trans_roll(struct xfs_trans **, struct xfs_inode *, int *);
 int		xfs_trans_roll(struct xfs_trans **, struct xfs_inode *);
 void		xfs_trans_cancel(xfs_trans_t *);
 int		xfs_trans_ail_init(struct xfs_mount *);
@@ -249,7 +245,7 @@ struct xfs_rud_log_item *xfs_trans_get_rud(struct xfs_trans *tp,
 		struct xfs_rui_log_item *ruip);
 int xfs_trans_log_finish_rmap_update(struct xfs_trans *tp,
 		struct xfs_rud_log_item *rudp, enum xfs_rmap_intent_type type,
-		__uint64_t owner, int whichfork, xfs_fileoff_t startoff,
+		uint64_t owner, int whichfork, xfs_fileoff_t startoff,
 		xfs_fsblock_t startblock, xfs_filblks_t blockcount,
 		xfs_exntst_t state, struct xfs_btree_cur **pcur);
 
@@ -275,6 +271,6 @@ int xfs_trans_log_finish_bmap_update(struct xfs_trans *tp,
 		struct xfs_bud_log_item *rudp, struct xfs_defer_ops *dfops,
 		enum xfs_bmap_intent_type type, struct xfs_inode *ip,
 		int whichfork, xfs_fileoff_t startoff, xfs_fsblock_t startblock,
-		xfs_filblks_t blockcount, xfs_exntst_t state);
+		xfs_filblks_t *blockcount, xfs_exntst_t state);
 
 #endif	/* __XFS_TRANS_H__ */
diff --git a/fs/xfs/xfs_trans_ail.c b/fs/xfs/xfs_trans_ail.c
index d6c9c3e9e02b..9056c0f34a3c 100644
--- a/fs/xfs/xfs_trans_ail.c
+++ b/fs/xfs/xfs_trans_ail.c
@@ -684,8 +684,23 @@ xfs_trans_ail_update_bulk(
 	}
 }
 
-/*
- * xfs_trans_ail_delete_bulk - remove multiple log items from the AIL
+bool
+xfs_ail_delete_one(
+	struct xfs_ail		*ailp,
+	struct xfs_log_item 	*lip)
+{
+	struct xfs_log_item	*mlip = xfs_ail_min(ailp);
+
+	trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn);
+	xfs_ail_delete(ailp, lip);
+	lip->li_flags &= ~XFS_LI_IN_AIL;
+	lip->li_lsn = 0;
+
+	return mlip == lip;
+}
+
+/**
+ * Remove a log items from the AIL
  *
  * @xfs_trans_ail_delete_bulk takes an array of log items that all need to
  * removed from the AIL. The caller is already holding the AIL lock, and done
@@ -706,52 +721,36 @@ xfs_trans_ail_update_bulk(
  * before returning.
  */
 void
-xfs_trans_ail_delete_bulk(
+xfs_trans_ail_delete(
 	struct xfs_ail		*ailp,
-	struct xfs_log_item	**log_items,
-	int			nr_items,
+	struct xfs_log_item	*lip,
 	int			shutdown_type) __releases(ailp->xa_lock)
 {
-	xfs_log_item_t		*mlip;
-	int			mlip_changed = 0;
-	int			i;
+	struct xfs_mount	*mp = ailp->xa_mount;
+	bool			mlip_changed;
 
-	mlip = xfs_ail_min(ailp);
-
-	for (i = 0; i < nr_items; i++) {
-		struct xfs_log_item *lip = log_items[i];
-		if (!(lip->li_flags & XFS_LI_IN_AIL)) {
-			struct xfs_mount	*mp = ailp->xa_mount;
-
-			spin_unlock(&ailp->xa_lock);
-			if (!XFS_FORCED_SHUTDOWN(mp)) {
-				xfs_alert_tag(mp, XFS_PTAG_AILDELETE,
-		"%s: attempting to delete a log item that is not in the AIL",
-						__func__);
-				xfs_force_shutdown(mp, shutdown_type);
-			}
-			return;
+	if (!(lip->li_flags & XFS_LI_IN_AIL)) {
+		spin_unlock(&ailp->xa_lock);
+		if (!XFS_FORCED_SHUTDOWN(mp)) {
+			xfs_alert_tag(mp, XFS_PTAG_AILDELETE,
+	"%s: attempting to delete a log item that is not in the AIL",
+					__func__);
+			xfs_force_shutdown(mp, shutdown_type);
 		}
-
-		trace_xfs_ail_delete(lip, mlip->li_lsn, lip->li_lsn);
-		xfs_ail_delete(ailp, lip);
-		lip->li_flags &= ~XFS_LI_IN_AIL;
-		lip->li_lsn = 0;
-		if (mlip == lip)
-			mlip_changed = 1;
+		return;
 	}
 
+	mlip_changed = xfs_ail_delete_one(ailp, lip);
 	if (mlip_changed) {
-		if (!XFS_FORCED_SHUTDOWN(ailp->xa_mount))
-			xlog_assign_tail_lsn_locked(ailp->xa_mount);
+		if (!XFS_FORCED_SHUTDOWN(mp))
+			xlog_assign_tail_lsn_locked(mp);
 		if (list_empty(&ailp->xa_ail))
 			wake_up_all(&ailp->xa_empty);
-		spin_unlock(&ailp->xa_lock);
+	}
 
+	spin_unlock(&ailp->xa_lock);
+	if (mlip_changed)
 		xfs_log_space_wake(ailp->xa_mount);
-	} else {
-		spin_unlock(&ailp->xa_lock);
-	}
 }
 
 int
diff --git a/fs/xfs/xfs_trans_bmap.c b/fs/xfs/xfs_trans_bmap.c
index 6408e7d7c08c..14543d93cd4b 100644
--- a/fs/xfs/xfs_trans_bmap.c
+++ b/fs/xfs/xfs_trans_bmap.c
@@ -63,7 +63,7 @@ xfs_trans_log_finish_bmap_update(
 	int				whichfork,
 	xfs_fileoff_t			startoff,
 	xfs_fsblock_t			startblock,
-	xfs_filblks_t			blockcount,
+	xfs_filblks_t			*blockcount,
 	xfs_exntst_t			state)
 {
 	int				error;
@@ -196,16 +196,23 @@ xfs_bmap_update_finish_item(
 	void				**state)
 {
 	struct xfs_bmap_intent		*bmap;
+	xfs_filblks_t			count;
 	int				error;
 
 	bmap = container_of(item, struct xfs_bmap_intent, bi_list);
+	count = bmap->bi_bmap.br_blockcount;
 	error = xfs_trans_log_finish_bmap_update(tp, done_item, dop,
 			bmap->bi_type,
 			bmap->bi_owner, bmap->bi_whichfork,
 			bmap->bi_bmap.br_startoff,
 			bmap->bi_bmap.br_startblock,
-			bmap->bi_bmap.br_blockcount,
+			&count,
 			bmap->bi_bmap.br_state);
+	if (!error && count > 0) {
+		ASSERT(bmap->bi_type == XFS_BMAP_UNMAP);
+		bmap->bi_bmap.br_blockcount = count;
+		return -EAGAIN;
+	}
 	kmem_free(bmap);
 	return error;
 }
diff --git a/fs/xfs/xfs_trans_buf.c b/fs/xfs/xfs_trans_buf.c
index 8ee29ca132dc..86987d823d76 100644
--- a/fs/xfs/xfs_trans_buf.c
+++ b/fs/xfs/xfs_trans_buf.c
@@ -356,6 +356,7 @@ xfs_trans_brelse(xfs_trans_t	*tp,
 		 xfs_buf_t	*bp)
 {
 	xfs_buf_log_item_t	*bip;
+	int			freed;
 
 	/*
 	 * Default to a normal brelse() call if the tp is NULL.
@@ -419,16 +420,22 @@ xfs_trans_brelse(xfs_trans_t	*tp,
 	/*
 	 * Drop our reference to the buf log item.
 	 */
-	atomic_dec(&bip->bli_refcount);
+	freed = atomic_dec_and_test(&bip->bli_refcount);
 
 	/*
-	 * If the buf item is not tracking data in the log, then
-	 * we must free it before releasing the buffer back to the
-	 * free pool.  Before releasing the buffer to the free pool,
-	 * clear the transaction pointer in b_fsprivate2 to dissolve
-	 * its relation to this transaction.
+	 * If the buf item is not tracking data in the log, then we must free it
+	 * before releasing the buffer back to the free pool.
+	 *
+	 * If the fs has shutdown and we dropped the last reference, it may fall
+	 * on us to release a (possibly dirty) bli if it never made it to the
+	 * AIL (e.g., the aborted unpin already happened and didn't release it
+	 * due to our reference). Since we're already shutdown and need xa_lock,
+	 * just force remove from the AIL and release the bli here.
 	 */
-	if (!xfs_buf_item_dirty(bip)) {
+	if (XFS_FORCED_SHUTDOWN(tp->t_mountp) && freed) {
+		xfs_trans_ail_remove(&bip->bli_item, SHUTDOWN_LOG_IO_ERROR);
+		xfs_buf_item_relse(bp);
+	} else if (!xfs_buf_item_dirty(bip)) {
 /***
 		ASSERT(bp->b_pincount == 0);
 ***/
diff --git a/fs/xfs/xfs_trans_priv.h b/fs/xfs/xfs_trans_priv.h
index 49931b72da8a..d91706c56c63 100644
--- a/fs/xfs/xfs_trans_priv.h
+++ b/fs/xfs/xfs_trans_priv.h
@@ -106,18 +106,9 @@ xfs_trans_ail_update(
 	xfs_trans_ail_update_bulk(ailp, NULL, &lip, 1, lsn);
 }
 
-void	xfs_trans_ail_delete_bulk(struct xfs_ail *ailp,
-				struct xfs_log_item **log_items, int nr_items,
-				int shutdown_type)
-				__releases(ailp->xa_lock);
-static inline void
-xfs_trans_ail_delete(
-	struct xfs_ail	*ailp,
-	xfs_log_item_t	*lip,
-	int		shutdown_type) __releases(ailp->xa_lock)
-{
-	xfs_trans_ail_delete_bulk(ailp, &lip, 1, shutdown_type);
-}
+bool xfs_ail_delete_one(struct xfs_ail *ailp, struct xfs_log_item *lip);
+void xfs_trans_ail_delete(struct xfs_ail *ailp, struct xfs_log_item *lip,
+		int shutdown_type) __releases(ailp->xa_lock);
 
 static inline void
 xfs_trans_ail_remove(
diff --git a/fs/xfs/xfs_trans_rmap.c b/fs/xfs/xfs_trans_rmap.c
index 9ead064b5e90..9b577beb43d7 100644
--- a/fs/xfs/xfs_trans_rmap.c
+++ b/fs/xfs/xfs_trans_rmap.c
@@ -96,7 +96,7 @@ xfs_trans_log_finish_rmap_update(
 	struct xfs_trans		*tp,
 	struct xfs_rud_log_item		*rudp,
 	enum xfs_rmap_intent_type	type,
-	__uint64_t			owner,
+	uint64_t			owner,
 	int				whichfork,
 	xfs_fileoff_t			startoff,
 	xfs_fsblock_t			startblock,